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@xxxxxxxx>
---
fs/ext4/ext4.h | 4 ++++
fs/ext4/extents.c | 8 ++++++++
fs/ext4/inode.c | 25 ++++++++++++++++++++++---
include/trace/events/ext4.h | 3 ++-
4 files changed, 36 insertions(+), 4 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 353089c35485..e667a7947b48 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -556,6 +556,10 @@ enum {
#define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080
/* Convert written extents to unwritten */
#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN 0x0100
+ /* Write zeros to newly created written extents */
+#define EXT4_GET_BLOCKS_ZERO 0x0200
+#define EXT4_GET_BLOCKS_CREATE_ZERO (EXT4_GET_BLOCKS_CREATE |\
+ EXT4_GET_BLOCKS_ZERO)
/*
* The bit position of these flags must not overlap with any of the
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index c0c7650c35ba..f7df02a15a18 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4044,6 +4044,14 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
}
/* IO end_io complete, convert the filled extent to written */
if (flags & EXT4_GET_BLOCKS_CONVERT) {
+ if (flags & EXT4_GET_BLOCKS_ZERO) {
+ if (allocated > map->m_len)
+ allocated = map->m_len;
+ err = ext4_issue_zeroout(inode, map->m_lblk, newblock,
+ allocated);
+ if (err < 0)
+ goto out2;
+ }
ret = ext4_convert_unwritten_extents_endio(handle, inode, map,
ppath);
if (ret >= 0) {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 39cdad9e2338..32e643a82890 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -637,13 +637,29 @@ found:
}
/*
+ * 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 @@ found:
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 @@ int ext4_get_block_dax(struct inode *inode, sector_t iblock,
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",
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 5f2ace56efc5..4e4b2fa78609 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -42,7 +42,8 @@ struct extent_status;
{ EXT4_GET_BLOCKS_CONVERT, "CONVERT" }, \
{ EXT4_GET_BLOCKS_METADATA_NOFAIL, "METADATA_NOFAIL" }, \
{ EXT4_GET_BLOCKS_NO_NORMALIZE, "NO_NORMALIZE" }, \
- { EXT4_GET_BLOCKS_KEEP_SIZE, "KEEP_SIZE" })
+ { EXT4_GET_BLOCKS_KEEP_SIZE, "KEEP_SIZE" }, \
+ { EXT4_GET_BLOCKS_ZERO, "ZERO" })
#define show_mflags(flags) __print_flags(flags, "", \
{ EXT4_MAP_NEW, "N" }, \
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
