For FS_XFLAG_FORCEALIGN support, we want to treat any sub-extent IO like
sub-fsblock DIO, in that we will zero the sub-extent when the mapping is
unwritten.
This will be important for atomic writes support, in that atomically
writing over a partially written extent would mean that we would need to
do the unwritten extent conversion write separately, and the write could
no longer be atomic.
It is the task of the FS to set iomap.extent_size per iter to indicate
sub-extent zeroing required.
Signed-off-by: John Garry <john.g.garry@xxxxxxxxxx>
---
fs/iomap/direct-io.c | 17 +++++++++++------
include/linux/iomap.h | 1 +
2 files changed, 12 insertions(+), 6 deletions(-)
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index f3b43d223a46..a3ed7cfa95bc 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -277,7 +277,7 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
{
const struct iomap *iomap = &iter->iomap;
struct inode *inode = iter->inode;
- unsigned int fs_block_size = i_blocksize(inode), pad;
+ unsigned int zeroing_size, pad;
loff_t length = iomap_length(iter);
loff_t pos = iter->pos;
blk_opf_t bio_opf;
@@ -288,6 +288,11 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
size_t copied = 0;
size_t orig_count;
+ if (iomap->extent_size)
+ zeroing_size = iomap->extent_size;
+ else
+ zeroing_size = i_blocksize(inode);
+
if ((pos | length) & (bdev_logical_block_size(iomap->bdev) - 1) ||
!bdev_iter_is_aligned(iomap->bdev, dio->submit.iter))
return -EINVAL;
@@ -354,8 +359,8 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
dio->iocb->ki_flags &= ~IOCB_HIPRI;
if (need_zeroout) {
- /* zero out from the start of the block to the write offset */
- pad = pos & (fs_block_size - 1);
+ /* zero out from the start of the region to the write offset */
+ pad = pos & (zeroing_size - 1);
if (pad)
iomap_dio_zero(iter, dio, pos - pad, pad);
}
@@ -428,10 +433,10 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
zero_tail:
if (need_zeroout ||
((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode))) {
- /* zero out from the end of the write to the end of the block */
- pad = pos & (fs_block_size - 1);
+ /* zero out from the end of the write to the end of the region */
+ pad = pos & (zeroing_size - 1);
if (pad)
- iomap_dio_zero(iter, dio, pos, fs_block_size - pad);
+ iomap_dio_zero(iter, dio, pos, zeroing_size - pad);
}
out:
/* Undo iter limitation to current extent */
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 6fc1c858013d..42623b1cdc04 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -97,6 +97,7 @@ struct iomap {
u64 length; /* length of mapping, bytes */
u16 type; /* type of mapping */
u16 flags; /* flags for mapping */
+ unsigned int extent_size;
struct block_device *bdev; /* block device for I/O */
struct dax_device *dax_dev; /* dax_dev for dax operations */
void *inline_data;
--
2.31.1
