xfs: add DAX block zeroing support

Orabug: 22913653

Add initial support for DAX block zeroing operations to XFS. DAX
cannot use buffered IO through the page cache for zeroing, nor do we
need to issue IO for uncached block zeroing. In both cases, we can
simply call out to the dax block zeroing function.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
(cherry picked from commit 4f69f578a87d39c20b1ff70005a125e4594c3de8)
Signed-off-by: Dan Duval <dan.duval@oracle.com>

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index a52bbd3abc7df3ac7fa07a12b5dc9ec336d9ab49..4a2965515ca883a92df0313ba908893103fd1ddf 100644 (file)
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1133,14 +1133,29 @@ xfs_zero_remaining_bytes(
                        break;
                ASSERT(imap.br_blockcount >= 1);
                ASSERT(imap.br_startoff == offset_fsb);
+               ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+
+               if (imap.br_startblock == HOLESTARTBLOCK ||
+                   imap.br_state == XFS_EXT_UNWRITTEN) {
+                       /* skip the entire extent */
+                       lastoffset = XFS_FSB_TO_B(mp, imap.br_startoff +
+                                                     imap.br_blockcount) - 1;
+                       continue;
+               }
+
                lastoffset = XFS_FSB_TO_B(mp, imap.br_startoff + 1) - 1;
                if (lastoffset > endoff)
                        lastoffset = endoff;
-               if (imap.br_startblock == HOLESTARTBLOCK)
-                       continue;
-               ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
-               if (imap.br_state == XFS_EXT_UNWRITTEN)
+
+               /* DAX can just zero the backing device directly */
+               if (IS_DAX(VFS_I(ip))) {
+                       error = dax_zero_page_range(VFS_I(ip), offset,
+                                                   lastoffset - offset + 1,
+                                                   xfs_get_blocks_direct);
+                       if (error)
+                               return error;
                        continue;
+               }
 
                error = xfs_buf_read_uncached(XFS_IS_REALTIME_INODE(ip) ?
                                mp->m_rtdev_targp : mp->m_ddev_targp,

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index d0981f973f618b0a183a6bd1182c59046ca40187..55c919a001ff9cd7e43ef8ce1c8b36a14fa7a920 100644 (file)
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -79,14 +79,15 @@ xfs_rw_ilock_demote(
 }
 
 /*
- *     xfs_iozero
+ * xfs_iozero clears the specified range supplied via the page cache (except in
+ * the DAX case). Writes through the page cache will allocate blocks over holes,
+ * though the callers usually map the holes first and avoid them. If a block is
+ * not completely zeroed, then it will be read from disk before being partially
+ * zeroed.
  *
- *     xfs_iozero clears the specified range of buffer supplied,
- *     and marks all the affected blocks as valid and modified.  If
- *     an affected block is not allocated, it will be allocated.  If
- *     an affected block is not completely overwritten, and is not
- *     valid before the operation, it will be read from disk before
- *     being partially zeroed.
+ * In the DAX case, we can just directly write to the underlying pages. This
+ * will not allocate blocks, but will avoid holes and unwritten extents and so
+ * not do unnecessary work.
  */
 int
 xfs_iozero(
@@ -96,7 +97,8 @@ xfs_iozero(
 {
        struct page             *page;
        struct address_space    *mapping;
-       int                     status;
+       int                     status = 0;
+
 
        mapping = VFS_I(ip)->i_mapping;
        do {
@@ -108,20 +110,27 @@ xfs_iozero(
                if (bytes > count)
                        bytes = count;
 
-               status = pagecache_write_begin(NULL, mapping, pos, bytes,
-                                       AOP_FLAG_UNINTERRUPTIBLE,
-                                       &page, &fsdata);
-               if (status)
-                       break;
+               if (IS_DAX(VFS_I(ip))) {
+                       status = dax_zero_page_range(VFS_I(ip), pos, bytes,
+                                                    xfs_get_blocks_direct);
+                       if (status)
+                               break;
+               } else {
+                       status = pagecache_write_begin(NULL, mapping, pos, bytes,
+                                               AOP_FLAG_UNINTERRUPTIBLE,
+                                               &page, &fsdata);
+                       if (status)
+                               break;
 
-               zero_user(page, offset, bytes);
+                       zero_user(page, offset, bytes);
 
-               status = pagecache_write_end(NULL, mapping, pos, bytes, bytes,
-                                       page, fsdata);
-               WARN_ON(status <= 0); /* can't return less than zero! */
+                       status = pagecache_write_end(NULL, mapping, pos, bytes,
+                                               bytes, page, fsdata);
+                       WARN_ON(status <= 0); /* can't return less than zero! */
+                       status = 0;
+               }
                pos += bytes;
                count -= bytes;
-               status = 0;
        } while (count);
 
        return status;