* [PATCH 2/4] iomap: move iter revert case out of the unwritten branch
2025-08-10 4:48 [PATCH 0/4] iomap: allow partial folio write with iomap_folio_state alexjlzheng
2025-08-10 4:48 ` [PATCH 1/4] iomap: make sure iomap_adjust_read_range() are aligned with block_size alexjlzheng
@ 2025-08-10 4:48 ` alexjlzheng
2025-08-10 4:48 ` [PATCH 3/4] iomap: make iomap_write_end() return the number of written length again alexjlzheng
2025-08-10 4:48 ` [PATCH 4/4] iomap: don't abandon the whole thing with iomap_folio_state alexjlzheng
3 siblings, 0 replies; 7+ messages in thread
From: alexjlzheng @ 2025-08-10 4:48 UTC (permalink / raw)
To: brauner, djwong; +Cc: linux-xfs, linux-fsdevel, linux-kernel, Jinliang Zheng
From: Jinliang Zheng <alexjlzheng@tencent.com>
This reverts commit e1f453d4336d ("iomap: do some small logical
cleanup in buffered write"), for preparetion for the next patches
which allow iomap_write_end() return a partial write length.
Signed-off-by: Jinliang Zheng <alexjlzheng@tencent.com>
---
fs/iomap/buffered-io.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 27fa93ca8675..df801220f4b3 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1019,6 +1019,11 @@ static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i,
if (old_size < pos)
pagecache_isize_extended(iter->inode, old_size, pos);
+ if (written < bytes)
+ iomap_write_failed(iter->inode, pos + written,
+ bytes - written);
+ if (unlikely(copied != written))
+ iov_iter_revert(i, copied - written);
cond_resched();
if (unlikely(written == 0)) {
@@ -1028,9 +1033,6 @@ static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i,
* halfway through, might be a race with munmap,
* might be severe memory pressure.
*/
- iomap_write_failed(iter->inode, pos, bytes);
- iov_iter_revert(i, copied);
-
if (chunk > PAGE_SIZE)
chunk /= 2;
if (copied) {
--
2.49.0
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH 3/4] iomap: make iomap_write_end() return the number of written length again
2025-08-10 4:48 [PATCH 0/4] iomap: allow partial folio write with iomap_folio_state alexjlzheng
2025-08-10 4:48 ` [PATCH 1/4] iomap: make sure iomap_adjust_read_range() are aligned with block_size alexjlzheng
2025-08-10 4:48 ` [PATCH 2/4] iomap: move iter revert case out of the unwritten branch alexjlzheng
@ 2025-08-10 4:48 ` alexjlzheng
2025-08-10 4:48 ` [PATCH 4/4] iomap: don't abandon the whole thing with iomap_folio_state alexjlzheng
3 siblings, 0 replies; 7+ messages in thread
From: alexjlzheng @ 2025-08-10 4:48 UTC (permalink / raw)
To: brauner, djwong; +Cc: linux-xfs, linux-fsdevel, linux-kernel, Jinliang Zheng
From: Jinliang Zheng <alexjlzheng@tencent.com>
In the next patch, we allow iomap_write_end() to conditionally accept
partial writes, so this patch makes iomap_write_end() return the number
of accepted write bytes in preparation for the next patch.
Signed-off-by: Jinliang Zheng <alexjlzheng@tencent.com>
---
fs/iomap/buffered-io.c | 27 +++++++++++++--------------
1 file changed, 13 insertions(+), 14 deletions(-)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index df801220f4b3..1b92a0f15bc1 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -873,7 +873,7 @@ static int iomap_write_begin(struct iomap_iter *iter,
return status;
}
-static bool __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
+static int __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
size_t copied, struct folio *folio)
{
flush_dcache_folio(folio);
@@ -890,11 +890,11 @@ static bool __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
* redo the whole thing.
*/
if (unlikely(copied < len && !folio_test_uptodate(folio)))
- return false;
+ return 0;
iomap_set_range_uptodate(folio, offset_in_folio(folio, pos), len);
iomap_set_range_dirty(folio, offset_in_folio(folio, pos), copied);
filemap_dirty_folio(inode->i_mapping, folio);
- return true;
+ return copied;
}
static void iomap_write_end_inline(const struct iomap_iter *iter,
@@ -915,10 +915,10 @@ static void iomap_write_end_inline(const struct iomap_iter *iter,
}
/*
- * Returns true if all copied bytes have been written to the pagecache,
- * otherwise return false.
+ * Returns number of copied bytes have been written to the pagecache,
+ * zero if block is partial update.
*/
-static bool iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied,
+static int iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied,
struct folio *folio)
{
const struct iomap *srcmap = iomap_iter_srcmap(iter);
@@ -926,7 +926,7 @@ static bool iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied,
if (srcmap->type == IOMAP_INLINE) {
iomap_write_end_inline(iter, folio, pos, copied);
- return true;
+ return copied;
}
if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
@@ -934,7 +934,7 @@ static bool iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied,
bh_written = block_write_end(pos, len, copied, folio);
WARN_ON_ONCE(bh_written != copied && bh_written != 0);
- return bh_written == copied;
+ return bh_written;
}
return __iomap_write_end(iter->inode, pos, len, copied, folio);
@@ -1000,8 +1000,7 @@ static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i,
flush_dcache_folio(folio);
copied = copy_folio_from_iter_atomic(folio, offset, bytes, i);
- written = iomap_write_end(iter, bytes, copied, folio) ?
- copied : 0;
+ written = iomap_write_end(iter, bytes, copied, folio);
/*
* Update the in-memory inode size after copying the data into
@@ -1315,7 +1314,7 @@ static int iomap_unshare_iter(struct iomap_iter *iter,
do {
struct folio *folio;
size_t offset;
- bool ret;
+ int ret;
bytes = min_t(u64, SIZE_MAX, bytes);
status = iomap_write_begin(iter, write_ops, &folio, &offset,
@@ -1327,7 +1326,7 @@ static int iomap_unshare_iter(struct iomap_iter *iter,
ret = iomap_write_end(iter, bytes, bytes, folio);
__iomap_put_folio(iter, write_ops, bytes, folio);
- if (WARN_ON_ONCE(!ret))
+ if (WARN_ON_ONCE(ret != bytes))
return -EIO;
cond_resched();
@@ -1388,7 +1387,7 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero,
do {
struct folio *folio;
size_t offset;
- bool ret;
+ int ret;
bytes = min_t(u64, SIZE_MAX, bytes);
status = iomap_write_begin(iter, write_ops, &folio, &offset,
@@ -1406,7 +1405,7 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero,
ret = iomap_write_end(iter, bytes, bytes, folio);
__iomap_put_folio(iter, write_ops, bytes, folio);
- if (WARN_ON_ONCE(!ret))
+ if (WARN_ON_ONCE(ret != bytes))
return -EIO;
status = iomap_iter_advance(iter, &bytes);
--
2.49.0
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH 4/4] iomap: don't abandon the whole thing with iomap_folio_state
2025-08-10 4:48 [PATCH 0/4] iomap: allow partial folio write with iomap_folio_state alexjlzheng
` (2 preceding siblings ...)
2025-08-10 4:48 ` [PATCH 3/4] iomap: make iomap_write_end() return the number of written length again alexjlzheng
@ 2025-08-10 4:48 ` alexjlzheng
2025-08-10 7:33 ` kernel test robot
3 siblings, 1 reply; 7+ messages in thread
From: alexjlzheng @ 2025-08-10 4:48 UTC (permalink / raw)
To: brauner, djwong; +Cc: linux-xfs, linux-fsdevel, linux-kernel, Jinliang Zheng
From: Jinliang Zheng <alexjlzheng@tencent.com>
With iomap_folio_state, we can identify uptodate states at the block
level, and a read_folio reading can correctly handle partially
uptodate folios.
Therefore, when a partial write occurs, accept the block-aligned
partial write instead of rejecting the entire write.
Signed-off-by: Jinliang Zheng <alexjlzheng@tencent.com>
---
fs/iomap/buffered-io.c | 32 +++++++++++++++++++++++++++-----
1 file changed, 27 insertions(+), 5 deletions(-)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 1b92a0f15bc1..10701923d968 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -873,6 +873,25 @@ static int iomap_write_begin(struct iomap_iter *iter,
return status;
}
+static int iomap_trim_tail_partial(struct inode *inode, loff_t pos,
+ size_t copied, struct folio *folio)
+{
+ struct iomap_folio_state *ifs = folio->private;
+ unsigned block_size, last_blk, last_blk_bytes;
+
+ if (!ifs || !copied)
+ return 0;
+
+ block_size = 1 << inode->i_blkbits;
+ last_blk = offset_in_folio(folio, pos + copied - 1) >> inode->i_blkbits;
+ last_blk_bytes = (pos + copied) % block_size;
+
+ if (!ifs_block_is_uptodate(ifs, last_blk))
+ copied -= min(copied, last_blk_bytes);
+
+ return copied;
+}
+
static int __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
size_t copied, struct folio *folio)
{
@@ -886,12 +905,15 @@ static int __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
* read_folio might come in and destroy our partial write.
*
* Do the simplest thing and just treat any short write to a
- * non-uptodate page as a zero-length write, and force the caller to
- * redo the whole thing.
+ * non-uptodate block as a zero-length write, and force the caller to
+ * redo the things begin from the block.
*/
- if (unlikely(copied < len && !folio_test_uptodate(folio)))
- return 0;
- iomap_set_range_uptodate(folio, offset_in_folio(folio, pos), len);
+ if (unlikely(copied < len && !folio_test_uptodate(folio))) {
+ copied = iomap_trim_tail_partial(inode, pos, copied, folio);
+ if (!copied)
+ return 0;
+ }
+ iomap_set_range_uptodate(folio, offset_in_folio(folio, pos), copied);
iomap_set_range_dirty(folio, offset_in_folio(folio, pos), copied);
filemap_dirty_folio(inode->i_mapping, folio);
return copied;
--
2.49.0
^ permalink raw reply related [flat|nested] 7+ messages in thread