summaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_bmap_util.c
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2015-11-03 12:27:22 +1100
committerDave Chinner <david@fromorbit.com>2015-11-03 12:27:22 +1100
commit3fbbbea34bac049c0b5938dc065f7d8ee1ef7e67 (patch)
tree2618b5476a3ac80ed4eb6dc7a3161b5d9ff5f4fc /fs/xfs/xfs_bmap_util.c
parent3e12dbbdbd8809f0455920e42fdbf9eddc002651 (diff)
downloadop-kernel-dev-3fbbbea34bac049c0b5938dc065f7d8ee1ef7e67.zip
op-kernel-dev-3fbbbea34bac049c0b5938dc065f7d8ee1ef7e67.tar.gz
xfs: introduce BMAPI_ZERO for allocating zeroed extents
To enable DAX to do atomic allocation of zeroed extents, we need to drive the block zeroing deep into the allocator. Because xfs_bmapi_write() can return merged extents on allocation that were only partially allocated (i.e. requested range spans allocated and hole regions, allocation into the hole was contiguous), we cannot zero the extent returned from xfs_bmapi_write() as that can overwrite existing data with zeros. Hence we have to drive the extent zeroing into the allocation code, prior to where we merge the extents into the BMBT and return the resultant map. This means we need to propagate this need down to the xfs_alloc_vextent() and issue the block zeroing at this point. While this functionality is being introduced for DAX, there is no reason why it is specific to DAX - we can per-zero blocks during the allocation transaction on any type of device. It's just slow (and usually slower than unwritten allocation and conversion) on traditional block devices so doesn't tend to get used. We can, however, hook hardware zeroing optimisations via sb_issue_zeroout() to this operation, so it may be useful in future and hence the "allocate zeroed blocks" API needs to be implementation neutral. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
Diffstat (limited to 'fs/xfs/xfs_bmap_util.c')
-rw-r--r--fs/xfs/xfs_bmap_util.c36
1 files changed, 36 insertions, 0 deletions
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 3bf4ad0..3f59698 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -57,6 +57,35 @@ xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
}
/*
+ * Routine to zero an extent on disk allocated to the specific inode.
+ *
+ * The VFS functions take a linearised filesystem block offset, so we have to
+ * convert the sparse xfs fsb to the right format first.
+ * VFS types are real funky, too.
+ */
+int
+xfs_zero_extent(
+ struct xfs_inode *ip,
+ xfs_fsblock_t start_fsb,
+ xfs_off_t count_fsb)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ xfs_daddr_t sector = xfs_fsb_to_db(ip, start_fsb);
+ sector_t block = XFS_BB_TO_FSBT(mp, sector);
+ ssize_t size = XFS_FSB_TO_B(mp, count_fsb);
+
+ if (IS_DAX(VFS_I(ip)))
+ return dax_clear_blocks(VFS_I(ip), block, size);
+
+ /*
+ * let the block layer decide on the fastest method of
+ * implementing the zeroing.
+ */
+ return sb_issue_zeroout(mp->m_super, block, count_fsb, GFP_NOFS);
+
+}
+
+/*
* Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi
* caller. Frees all the extents that need freeing, which must be done
* last due to locking considerations. We never free any extents in
@@ -229,6 +258,13 @@ xfs_bmap_rtalloc(
xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT :
XFS_TRANS_DQ_RTBCOUNT, (long) ralen);
+
+ /* Zero the extent if we were asked to do so */
+ if (ap->userdata & XFS_ALLOC_USERDATA_ZERO) {
+ error = xfs_zero_extent(ap->ip, ap->blkno, ap->length);
+ if (error)
+ return error;
+ }
} else {
ap->length = 0;
}
OpenPOWER on IntegriCloud