[PATCH v4 6/9] iomap: don't increase i_size if it's not a write operation

From: Zhang Yi
Date: Wed Mar 20 2024 - 07:14:28 EST


From: Zhang Yi <yi.zhang@xxxxxxxxxx>

Increase i_size in iomap_zero_range() and iomap_unshare_iter() is not
needed, the caller should handle it. Especially, when truncate partial
block, we should not increase i_size beyond the new EOF here. It doesn't
affect xfs and gfs2 now because they set the new file size after zero
out, it doesn't matter that a transient increase in i_size, but it will
affect ext4 because it set file size before truncate. So move the i_size
updating logic to iomap_write_iter().

Signed-off-by: Zhang Yi <yi.zhang@xxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: Darrick J. Wong <djwong@xxxxxxxxxx>
---
fs/iomap/buffered-io.c | 50 +++++++++++++++++++++---------------------
1 file changed, 25 insertions(+), 25 deletions(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 7e32a204650b..e9112dc78d15 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -837,32 +837,13 @@ static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
size_t copied, struct folio *folio)
{
const struct iomap *srcmap = iomap_iter_srcmap(iter);
- loff_t old_size = iter->inode->i_size;
- size_t ret;
-
- if (srcmap->type == IOMAP_INLINE) {
- ret = iomap_write_end_inline(iter, folio, pos, copied);
- } else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
- ret = block_write_end(NULL, iter->inode->i_mapping, pos, len,
- copied, &folio->page, NULL);
- } else {
- ret = __iomap_write_end(iter->inode, pos, len, copied, folio);
- }
-
- /*
- * Update the in-memory inode size after copying the data into the page
- * cache. It's up to the file system to write the updated size to disk,
- * preferably after I/O completion so that no stale data is exposed.
- */
- if (pos + ret > old_size) {
- i_size_write(iter->inode, pos + ret);
- iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
- }
- __iomap_put_folio(iter, pos, ret, folio);

- if (old_size < pos)
- pagecache_isize_extended(iter->inode, old_size, pos);
- return ret;
+ if (srcmap->type == IOMAP_INLINE)
+ return iomap_write_end_inline(iter, folio, pos, copied);
+ if (srcmap->flags & IOMAP_F_BUFFER_HEAD)
+ return block_write_end(NULL, iter->inode->i_mapping, pos, len,
+ copied, &folio->page, NULL);
+ return __iomap_write_end(iter->inode, pos, len, copied, folio);
}

static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
@@ -877,6 +858,7 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)

do {
struct folio *folio;
+ loff_t old_size;
size_t offset; /* Offset into folio */
size_t bytes; /* Bytes to write to folio */
size_t copied; /* Bytes copied from user */
@@ -926,6 +908,22 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
copied = copy_folio_from_iter_atomic(folio, offset, bytes, i);
status = iomap_write_end(iter, pos, bytes, copied, folio);

+ /*
+ * Update the in-memory inode size after copying the data into
+ * the page cache. It's up to the file system to write the
+ * updated size to disk, preferably after I/O completion so that
+ * no stale data is exposed. Only once that's done can we
+ * unlock and release the folio.
+ */
+ old_size = iter->inode->i_size;
+ if (pos + status > old_size) {
+ i_size_write(iter->inode, pos + status);
+ iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
+ }
+ __iomap_put_folio(iter, pos, status, folio);
+
+ if (old_size < pos)
+ pagecache_isize_extended(iter->inode, old_size, pos);
if (status < bytes)
iomap_write_failed(iter->inode, pos + status,
bytes - status);
@@ -1298,6 +1296,7 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
bytes = folio_size(folio) - offset;

bytes = iomap_write_end(iter, pos, bytes, bytes, folio);
+ __iomap_put_folio(iter, pos, bytes, folio);
if (WARN_ON_ONCE(bytes == 0))
return -EIO;

@@ -1362,6 +1361,7 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
folio_mark_accessed(folio);

bytes = iomap_write_end(iter, pos, bytes, bytes, folio);
+ __iomap_put_folio(iter, pos, bytes, folio);
if (WARN_ON_ONCE(bytes == 0))
return -EIO;

--
2.39.2