2024-02-13 10:34:48

by Christoph Hellwig

Subject: Re: [RFC PATCH v3 07/26] iomap: don't increase i_size if it's not a write operation

Wouldn't it make more sense to just move the size manipulation to the
write-only code? An untested version of that is below. With this
the naming of the status variable becomes even more confusing than
it already is, maybe we need to do a cleanup of the *_write_end
calling conventions as it always returns the passed in copied value
or 0.

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 3dab060aed6d7b..8401a9ca702fc0 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -876,34 +876,13 @@ 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);
- if (ret < len)
- iomap_write_failed(iter->inode, pos + ret, len - ret);
- 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)
@@ -918,6 +897,7 @@ 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 */
@@ -964,7 +944,24 @@ 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.
+ */
+ 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);
if (unlikely(copied != status))
iov_iter_revert(i, copied - status);

@@ -1334,6 +1331,7 @@ 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;

@@ -1398,6 +1396,7 @@ 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;