ext4: implement allocation of pre-zeroed blocks
DAX page fault path needs to get blocks that are pre-zeroed to avoid
races when two concurrent page faults happen in the same block of a
file. Implement support for this in ext4_map_blocks().
Signed-off-by: Jan Kara <jack@suse.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0c9a5ee..4241d0c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -637,13 +637,29 @@
}
/*
+ * We have to zeroout blocks before inserting them into extent
+ * status tree. Otherwise someone could look them up there and
+ * use them before they are really zeroed.
+ */
+ if (flags & EXT4_GET_BLOCKS_ZERO &&
+ map->m_flags & EXT4_MAP_MAPPED &&
+ map->m_flags & EXT4_MAP_NEW) {
+ ret = ext4_issue_zeroout(inode, map->m_lblk,
+ map->m_pblk, map->m_len);
+ if (ret) {
+ retval = ret;
+ goto out_sem;
+ }
+ }
+
+ /*
* If the extent has been zeroed out, we don't need to update
* extent status tree.
*/
if ((flags & EXT4_GET_BLOCKS_PRE_IO) &&
ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
if (ext4_es_is_written(&es))
- goto has_zeroout;
+ goto out_sem;
}
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
@@ -654,11 +670,13 @@
status |= EXTENT_STATUS_DELAYED;
ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
map->m_pblk, status);
- if (ret < 0)
+ if (ret < 0) {
retval = ret;
+ goto out_sem;
+ }
}
-has_zeroout:
+out_sem:
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
ret = check_block_validity(inode, map);
@@ -3083,6 +3101,7 @@
struct buffer_head *bh_result, int create)
{
int flags = EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_UNWRIT_EXT;
+
if (create)
flags |= EXT4_GET_BLOCKS_CREATE;
ext4_debug("ext4_get_block_dax: inode %lu, create flag %d\n",