* [PATCH v4 14/23] ext4: implement partial block zero range path using iomap
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
Introduce a new iomap_ops instance, ext4_iomap_zero_ops, along with
ext4_iomap_block_zero_range() to implement block zeroing via the iomap
infrastructure for ext4.
ext4_iomap_block_zero_range() calls iomap_zero_range() with
ext4_iomap_zero_begin() as the callback. The callback locates and zeros
out either a mapped partial block or a dirty, unwritten partial block.
Important constraints:
Zeroing out under an active journal handle can cause deadlock, because
the order of acquiring the folio lock and starting a handle is
inconsistent with the iomap writeback path.
Therefore, ext4_iomap_block_zero_range():
- Must NOT be called under an active handle.
- Cannot rely on data=ordered mode to ensure zeroed data persistence
before updating i_disksize (for the cases of post-EOF append write,
post-EOF fallocate, and truncate up). In subsequent patches, we will
address this by synchronizing commit I/O but doesn't waiting for
completion, and updating i_disksize to i_size only after the zeroed
data has been written back.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/inode.c | 92 +++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 92 insertions(+)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c6fe42d012fc..e0dae2501292 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4101,6 +4101,51 @@ static int ext4_iomap_buffered_da_write_end(struct inode *inode, loff_t offset,
return 0;
}
+static int ext4_iomap_zero_begin(struct inode *inode,
+ loff_t offset, loff_t length, unsigned int flags,
+ struct iomap *iomap, struct iomap *srcmap)
+{
+ struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap);
+ struct ext4_map_blocks map;
+ u8 blkbits = inode->i_blkbits;
+ unsigned int iomap_flags = 0;
+ int ret;
+
+ ret = ext4_emergency_state(inode->i_sb);
+ if (unlikely(ret))
+ return ret;
+
+ if (WARN_ON_ONCE(!(flags & IOMAP_ZERO)))
+ return -EINVAL;
+
+ ret = ext4_iomap_map_blocks(inode, offset, length, NULL, &map);
+ if (ret < 0)
+ return ret;
+
+ /*
+ * Look up dirty folios for unwritten mappings within EOF. Providing
+ * this bypasses the flush iomap uses to trigger extent conversion
+ * when unwritten mappings have dirty pagecache in need of zeroing.
+ */
+ if (map.m_flags & EXT4_MAP_UNWRITTEN) {
+ loff_t start = ((loff_t)map.m_lblk) << blkbits;
+ loff_t end = ((loff_t)map.m_lblk + map.m_len) << blkbits;
+
+ iomap_fill_dirty_folios(iter, &start, end, &iomap_flags);
+ if ((start >> blkbits) < map.m_lblk + map.m_len)
+ map.m_len = (start >> blkbits) - map.m_lblk;
+ }
+
+ ext4_set_iomap(inode, iomap, &map, offset, length, flags);
+ iomap->flags |= iomap_flags;
+
+ return 0;
+}
+
+static const struct iomap_ops ext4_iomap_zero_ops = {
+ .iomap_begin = ext4_iomap_zero_begin,
+};
+
/*
* Since we always allocate unwritten extents, there is no need for
* iomap_end to clean up allocated blocks on a short write.
@@ -4616,6 +4661,47 @@ static int ext4_block_journalled_zero_range(struct inode *inode, loff_t from,
return err;
}
+static int ext4_block_iomap_zero_range(struct inode *inode, loff_t from,
+ loff_t length, bool *did_zero,
+ bool *zero_written)
+{
+ int ret;
+
+ /*
+ * Zeroing out under an active handle can cause deadlock since
+ * the order of acquiring the folio lock and starting a handle is
+ * inconsistent with the iomap writeback procedure.
+ */
+ if (WARN_ON_ONCE(ext4_handle_valid(journal_current_handle())))
+ return -EINVAL;
+
+ /* The zeroing scope should not extend across a block. */
+ if (WARN_ON_ONCE((from >> inode->i_blkbits) !=
+ ((from + length - 1) >> inode->i_blkbits)))
+ return -EINVAL;
+
+ if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS) &&
+ !(inode_state_read_once(inode) & (I_NEW | I_FREEING)))
+ WARN_ON_ONCE(!inode_is_locked(inode) &&
+ !rwsem_is_locked(&inode->i_mapping->invalidate_lock));
+
+ ret = iomap_zero_range(inode, from, length, did_zero,
+ &ext4_iomap_zero_ops, &ext4_iomap_write_ops,
+ NULL);
+ if (ret)
+ return ret;
+
+ /*
+ * TODO: The iomap does not distinguish between different types of
+ * zeroing and always sets zero_written if a zeroing operation is
+ * performed, which may result in unnecessary order operations.
+ */
+ if (did_zero && zero_written)
+ *zero_written = *did_zero;
+
+ return 0;
+}
+
/*
* Zeros out a mapping of length 'length' starting from file offset
* 'from'. The range to be zero'd must be contained with in one block.
@@ -4642,6 +4728,9 @@ static int ext4_block_zero_range(struct inode *inode,
} else if (ext4_should_journal_data(inode)) {
return ext4_block_journalled_zero_range(inode, from, length,
did_zero);
+ } else if (ext4_inode_buffered_iomap(inode)) {
+ return ext4_block_iomap_zero_range(inode, from, length,
+ did_zero, zero_written);
}
return ext4_block_do_zero_range(inode, from, length, did_zero,
zero_written);
@@ -4682,6 +4771,9 @@ int ext4_block_zero_eof(struct inode *inode, loff_t from, loff_t end)
* truncating up or performing an append write, because there might be
* exposing stale on-disk data which may caused by concurrent post-EOF
* mmap write during folio writeback.
+ *
+ * TODO: In the iomap path, handle this by updating i_disksize to
+ * i_size after the zeroed data has been written back.
*/
if (ext4_should_order_data(inode) &&
did_zero && zero_written && !IS_DAX(inode)) {
--
2.52.0
^ permalink raw reply related
* [PATCH v4 18/23] ext4: wait for ordered I/O in the iomap buffered I/O path
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
For append writes, wait for ordered I/O to complete before updating
i_disksize. This ensures that zeroed data is flushed to disk before the
metadata update, preventing stale data from being exposed during
unaligned post-EOF append writes.
Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/ext4.h | 11 +++++++
fs/ext4/inode.c | 80 ++++++++++++++++++++++++++++++++++++++++++-----
fs/ext4/page-io.c | 60 +++++++++++++++++++++++++++++++++++
fs/ext4/super.c | 23 ++++++++++----
4 files changed, 161 insertions(+), 13 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 078feda47e36..9ce2128eea3e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1195,6 +1195,15 @@ struct ext4_inode_info {
#ifdef CONFIG_FS_ENCRYPTION
struct fscrypt_inode_info *i_crypt_info;
#endif
+
+ /*
+ * Track ordered zeroed data during post-EOF append writes, fallocate,
+ * and truncate-up operations. These parameters are used only in the
+ * iomap buffered I/O path.
+ */
+ ext4_lblk_t i_ordered_lblk;
+ ext4_lblk_t i_ordered_len;
+ wait_queue_head_t i_ordered_wq;
};
/*
@@ -3858,6 +3867,8 @@ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
__u64 len, __u64 *moved_len);
/* page-io.c */
+#define EXT4_IOMAP_IOEND_ORDER_IO 1UL /* This I/O is an ordered one */
+
extern int __init ext4_init_pageio(void);
extern void ext4_exit_pageio(void);
extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index e013aeb03d7b..11fb369efeb1 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4345,6 +4345,7 @@ static int ext4_iomap_writeback_submit(struct iomap_writepage_ctx *wpc,
{
struct iomap_ioend *ioend = wpc->wb_ctx;
struct ext4_inode_info *ei = EXT4_I(ioend->io_inode);
+ ext4_lblk_t start, end, order_lblk, order_len;
/*
* After I/O completion, a worker needs to be scheduled when:
@@ -4357,6 +4358,30 @@ static int ext4_iomap_writeback_submit(struct iomap_writepage_ctx *wpc,
test_opt(ioend->io_inode->i_sb, DATA_ERR_ABORT))
ioend->io_bio.bi_end_io = ext4_iomap_end_bio;
+ /*
+ * Mark the I/O as ordered. Ordered I/O requires separate endio
+ * handling and must not be merged with regular I/O operations.
+ */
+ order_len = READ_ONCE(ei->i_ordered_len);
+ if (order_len) {
+ /*
+ * Pair with smp_store_release() in ext4_block_zero_eof().
+ * Ensure we see the updated i_ordered_lblk that was written
+ * before the release store to i_ordered_len.
+ */
+ smp_rmb();
+ order_lblk = READ_ONCE(ei->i_ordered_lblk);
+ start = ioend->io_offset >> ioend->io_inode->i_blkbits;
+ end = EXT4_B_TO_LBLK(ioend->io_inode,
+ ioend->io_offset + ioend->io_size);
+
+ if (start <= order_lblk && end >= order_lblk + order_len) {
+ ioend->io_bio.bi_end_io = ext4_iomap_end_bio;
+ ioend->io_private = (void *)EXT4_IOMAP_IOEND_ORDER_IO;
+ ioend->io_flags |= IOMAP_IOEND_BOUNDARY;
+ }
+ }
+
return iomap_ioend_writeback_submit(wpc, error);
}
@@ -4746,8 +4771,10 @@ static int ext4_iomap_submit_zero_block(struct inode *inode,
loff_t from, loff_t end)
{
struct address_space *mapping = inode->i_mapping;
+ struct ext4_inode_info *ei = EXT4_I(inode);
struct folio *folio;
bool do_submit = false;
+ int ret;
folio = filemap_lock_folio(mapping, from >> PAGE_SHIFT);
if (IS_ERR(folio))
@@ -4757,14 +4784,50 @@ static int ext4_iomap_submit_zero_block(struct inode *inode,
folio_wait_writeback(folio);
WARN_ON_ONCE(folio_test_writeback(folio));
- if (likely(folio_test_dirty(folio)))
+ /*
+ * Mark the ordered range. It will be cleared upon I/O completion
+ * in ext4_iomap_end_bio(). Any operation that extends i_disksize
+ * (including append write end io past the zeroed boundary,
+ * truncate up and append fallocate) must wait for this I/O to
+ * complete before updating i_disksize.
+ *
+ * When multiple overlapping unaligned EOF writes are in flight, we
+ * only need to track and wait for the first one. Subsequent writes
+ * will zero the gap in memory and ensure that the zeroed data is
+ * written out along with the valid data in the same block before
+ * i_disksize is updated.
+ */
+ if (likely(folio_test_dirty(folio) &&
+ READ_ONCE(ei->i_ordered_len) == 0)) {
+ WRITE_ONCE(ei->i_ordered_lblk,
+ from >> inode->i_blkbits);
+ /*
+ * Pairs with smp_rmb() in ext4_iomap_writeback_submit()
+ * and ext4_iomap_wb_ordered_wait(). Ensure the updated
+ * i_ordered_lblk is visible when i_ordered_len becomes
+ * non-zero.
+ */
+ smp_store_release(&ei->i_ordered_len, 1);
do_submit = true;
+ }
folio_unlock(folio);
folio_put(folio);
/* Submit zeroed block. */
- if (do_submit)
- return filemap_fdatawrite_range(mapping, from, end - 1);
+ if (do_submit) {
+ ret = filemap_fdatawrite_range(mapping, from, end - 1);
+ if (ret) {
+ /*
+ * Pairs with wait_event() in
+ * ext4_iomap_wb_ordered_wait(). Ensure
+ * i_ordered_len = 0 is visible before waking up
+ * waiters.
+ */
+ smp_store_release(&ei->i_ordered_len, 0);
+ wake_up_all(&ei->i_ordered_wq);
+ return ret;
+ }
+ }
return 0;
}
@@ -4827,10 +4890,13 @@ int ext4_block_zero_eof(struct inode *inode, loff_t from, loff_t end)
* data=ordered mode. We submit zeroed range directly here.
* Do not wait for I/O completion for performance.
*
- * TODO: Any operation that extends i_disksize (including
- * append write end io past the zeroed boundary, truncate up,
- * and append fallocate) must wait for the relevant I/O to
- * complete before updating i_disksize.
+ * The end_io handler ext4_iomap_wb_ordered_wait() will wait
+ * for I/O completion before updating i_disksize if the write
+ * extends beyond the zeroed boundary.
+ *
+ * TODO: Any other operation that extends i_disksize
+ * (including truncate up and append fallocate) must wait for
+ * the relevant I/O to complete before updating i_disksize.
*/
} else if (ext4_inode_buffered_iomap(inode)) {
err = ext4_iomap_submit_zero_block(inode, from, end);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 3050c887329f..ad05ebb49bf6 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -613,6 +613,46 @@ int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *folio,
return 0;
}
+/*
+ * If the old disk size is not block size aligned and the current
+ * writeback range is entirely beyond the old EOF block, we should
+ * wait for the zeroed data written in ext4_block_zero_eof() to be
+ * written out, otherwise, it may expose stale data in that block.
+ */
+static void ext4_iomap_wb_ordered_wait(struct inode *inode,
+ loff_t pos, loff_t end)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ unsigned int blocksize = i_blocksize(inode);
+ loff_t disksize = READ_ONCE(ei->i_disksize);
+ ext4_lblk_t order_lblk, order_len;
+
+ /*
+ * Waiting for ordered I/O is unnecessary when:
+ * - The on-disk size is block-aligned (no stale data exists).
+ * - The write start is within the block of the old EOF
+ * (overwriting, or appending to a block that already contains
+ * valid data).
+ */
+ if (!(disksize & (blocksize - 1)) ||
+ pos < round_up(disksize, blocksize))
+ return;
+
+ order_len = READ_ONCE(ei->i_ordered_len);
+ if (!order_len)
+ return;
+
+ /*
+ * Pair with smp_store_release() in ext4_iomap_end_bio() and
+ * ext4_block_zero_eof(). Ensure we see the updated i_ordered_lblk
+ * that was written before the release store to i_ordered_len.
+ */
+ smp_rmb();
+ order_lblk = READ_ONCE(ei->i_ordered_lblk);
+ if ((pos >> inode->i_blkbits) >= order_lblk + order_len)
+ wait_event(ei->i_ordered_wq, READ_ONCE(ei->i_ordered_len) == 0);
+}
+
static int ext4_iomap_wb_update_disksize(handle_t *handle, struct inode *inode,
loff_t end)
{
@@ -656,6 +696,9 @@ static void ext4_iomap_finish_ioend(struct iomap_ioend *ioend)
goto out;
}
+ /* Wait ordered zero data to be written out. */
+ ext4_iomap_wb_ordered_wait(inode, pos, pos + size);
+
/* We may need to convert one extent and dirty the inode. */
credits = ext4_chunk_trans_blocks(inode,
EXT4_MAX_BLOCKS(size, pos, inode->i_blkbits));
@@ -717,8 +760,25 @@ void ext4_iomap_end_bio(struct bio *bio)
struct inode *inode = ioend->io_inode;
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ unsigned long io_mode = (unsigned long)ioend->io_private;
unsigned long flags;
+ /*
+ * This is an ordered I/O, clear the ordered range set in
+ * ext4_block_zero_eof() and wake up all waiters that will update
+ * the inode i_disksize.
+ */
+ if (io_mode == EXT4_IOMAP_IOEND_ORDER_IO) {
+ /*
+ * Pairs with wait_event() in ext4_iomap_wb_ordered_wait().
+ * Ensure i_ordered_len = 0 is visible before waking up
+ * waiters.
+ */
+ smp_store_release(&ei->i_ordered_len, 0);
+ wake_up_all(&ei->i_ordered_wq);
+ goto defer;
+ }
+
/* Needs to convert unwritten extents or update the i_disksize. */
if ((ioend->io_flags & IOMAP_IOEND_UNWRITTEN) ||
ioend->io_offset + ioend->io_size > READ_ONCE(ei->i_disksize))
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 62bfe05a64bc..9c0a00e716f3 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1444,6 +1444,9 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
ext4_fc_init_inode(&ei->vfs_inode);
spin_lock_init(&ei->i_fc_lock);
mmb_init(&ei->i_metadata_bhs, &ei->vfs_inode.i_data);
+ ei->i_ordered_lblk = 0;
+ ei->i_ordered_len = 0;
+ init_waitqueue_head(&ei->i_ordered_wq);
return &ei->vfs_inode;
}
@@ -1480,12 +1483,20 @@ static void ext4_destroy_inode(struct inode *inode)
dump_stack();
}
- if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ERROR_FS) &&
- WARN_ON_ONCE(EXT4_I(inode)->i_reserved_data_blocks))
- ext4_msg(inode->i_sb, KERN_ERR,
- "Inode %llu (%p): i_reserved_data_blocks (%u) not cleared!",
- inode->i_ino, EXT4_I(inode),
- EXT4_I(inode)->i_reserved_data_blocks);
+ if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ERROR_FS)) {
+ if (WARN_ON_ONCE(EXT4_I(inode)->i_reserved_data_blocks))
+ ext4_msg(inode->i_sb, KERN_ERR,
+ "Inode %llu (%p): i_reserved_data_blocks (%u) not cleared!",
+ inode->i_ino, EXT4_I(inode),
+ EXT4_I(inode)->i_reserved_data_blocks);
+
+ if (WARN_ON_ONCE(EXT4_I(inode)->i_ordered_len))
+ ext4_msg(inode->i_sb, KERN_ERR,
+ "Inode %llu (%p): i_ordered_lblk (%u) and i_ordered_len (%u) not cleared!",
+ inode->i_ino, EXT4_I(inode),
+ EXT4_I(inode)->i_ordered_lblk,
+ EXT4_I(inode)->i_ordered_len);
+ }
}
static void ext4_shutdown(struct super_block *sb)
--
2.52.0
^ permalink raw reply related
* [PATCH v4 08/23] ext4: implement buffered write path using iomap
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
Introduce two new iomap_ops instances for ext4 buffered writes:
- ext4_iomap_buffered_da_write_ops: for delayed allocation mode, using
ext4_da_map_blocks() to map delalloc extents.
- ext4_iomap_buffered_write_ops: for non-delayed allocation mode, using
ext4_iomap_get_blocks() to directly allocate blocks.
Also add ext4_iomap_valid() for the iomap infrastructure to check extent
validity.
Key changes and considerations:
- Unwritten extents for new blocks (dioread_nolock always on)
Since data=ordered mode is not used to prevent stale data exposure in
the non-delayed allocation path, new blocks are always allocated as
unwritten extents.
- Short write and write failure handling
a. Delalloc path: On short write or failure, the stale delalloc range
must be dropped and its space reservation released. Otherwise, a
clean folio may cover leftover delalloc extents, causing
inaccurate space reservation accounting.
b. Non-delalloc path: No cleanup of allocated blocks is needed on
short write.
- Lock ordering reversal
The folio lock and transaction start ordering is reversed compared to
the buffer_head buffered write path. To handle this, the journal
handle must be stopped in iomap_begin() callbacks. The lock ordering
documentation in super.c has been updated accordingly.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/ext4.h | 4 ++
fs/ext4/file.c | 20 +++++-
fs/ext4/inode.c | 165 +++++++++++++++++++++++++++++++++++++++++++++++-
fs/ext4/super.c | 10 ++-
4 files changed, 192 insertions(+), 7 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1e27d73d7427..4832e7f7db82 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3057,6 +3057,7 @@ int ext4_walk_page_buffers(handle_t *handle,
int do_journal_get_write_access(handle_t *handle, struct inode *inode,
struct buffer_head *bh);
void ext4_set_inode_mapping_order(struct inode *inode);
+int ext4_nonda_switch(struct super_block *sb);
#define FALL_BACK_TO_NONDELALLOC 1
#define CONVERT_INLINE_DATA 2
@@ -3926,6 +3927,9 @@ static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
extern const struct iomap_ops ext4_iomap_ops;
extern const struct iomap_ops ext4_iomap_report_ops;
+extern const struct iomap_ops ext4_iomap_buffered_write_ops;
+extern const struct iomap_ops ext4_iomap_buffered_da_write_ops;
+extern const struct iomap_write_ops ext4_iomap_write_ops;
static inline int ext4_buffer_uptodate(struct buffer_head *bh)
{
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index eb1a323962b1..7f9bfbbc4a4e 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -299,6 +299,21 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
return count;
}
+static ssize_t ext4_iomap_buffered_write(struct kiocb *iocb,
+ struct iov_iter *from)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+ const struct iomap_ops *iomap_ops;
+
+ if (test_opt(inode->i_sb, DELALLOC) && !ext4_nonda_switch(inode->i_sb))
+ iomap_ops = &ext4_iomap_buffered_da_write_ops;
+ else
+ iomap_ops = &ext4_iomap_buffered_write_ops;
+
+ return iomap_file_buffered_write(iocb, from, iomap_ops,
+ &ext4_iomap_write_ops, NULL);
+}
+
static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
struct iov_iter *from)
{
@@ -313,7 +328,10 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
if (ret <= 0)
goto out;
- ret = generic_perform_write(iocb, from);
+ if (ext4_inode_buffered_iomap(inode))
+ ret = ext4_iomap_buffered_write(iocb, from);
+ else
+ ret = generic_perform_write(iocb, from);
out:
inode_unlock(inode);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 39577a6b65b9..1ae7d3f4a1c8 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3097,7 +3097,7 @@ static int ext4_dax_writepages(struct address_space *mapping,
return ret;
}
-static int ext4_nonda_switch(struct super_block *sb)
+int ext4_nonda_switch(struct super_block *sb)
{
s64 free_clusters, dirty_clusters;
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -3467,6 +3467,15 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
return inode_state_read_once(inode) & I_DIRTY_DATASYNC;
}
+static bool ext4_iomap_valid(struct inode *inode, const struct iomap *iomap)
+{
+ return iomap->validity_cookie == READ_ONCE(EXT4_I(inode)->i_es_seq);
+}
+
+const struct iomap_write_ops ext4_iomap_write_ops = {
+ .iomap_valid = ext4_iomap_valid,
+};
+
static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
struct ext4_map_blocks *map, loff_t offset,
loff_t length, unsigned int flags)
@@ -3501,6 +3510,8 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
iomap->flags |= IOMAP_F_MERGED;
+ iomap->validity_cookie = map->m_seq;
+
/*
* Flags passed to ext4_map_blocks() for direct I/O writes can result
* in m_flags having both EXT4_MAP_MAPPED and EXT4_MAP_UNWRITTEN bits
@@ -3908,8 +3919,12 @@ const struct iomap_ops ext4_iomap_report_ops = {
.iomap_begin = ext4_iomap_begin_report,
};
+/* Map blocks */
+typedef int (ext4_get_blocks_t)(struct inode *, struct ext4_map_blocks *);
+
static int ext4_iomap_map_blocks(struct inode *inode, loff_t offset,
- loff_t length, struct ext4_map_blocks *map)
+ loff_t length, ext4_get_blocks_t get_blocks,
+ struct ext4_map_blocks *map)
{
u8 blkbits = inode->i_blkbits;
@@ -3921,6 +3936,9 @@ static int ext4_iomap_map_blocks(struct inode *inode, loff_t offset,
map->m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
EXT4_MAX_LOGICAL_BLOCK) - map->m_lblk + 1;
+ if (get_blocks)
+ return get_blocks(inode, map);
+
return ext4_map_blocks(NULL, inode, map, 0);
}
@@ -3938,7 +3956,7 @@ static int ext4_iomap_buffered_read_begin(struct inode *inode, loff_t offset,
if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
return -ERANGE;
- ret = ext4_iomap_map_blocks(inode, offset, length, &map);
+ ret = ext4_iomap_map_blocks(inode, offset, length, NULL, &map);
if (ret < 0)
return ret;
@@ -3946,6 +3964,147 @@ static int ext4_iomap_buffered_read_begin(struct inode *inode, loff_t offset,
return 0;
}
+static int ext4_iomap_get_blocks(struct inode *inode,
+ struct ext4_map_blocks *map)
+{
+ loff_t i_size = i_size_read(inode);
+ handle_t *handle;
+ int ret;
+
+ /*
+ * Check if the blocks have already been allocated, this could
+ * avoid initiating a new journal transaction and return the
+ * mapping information directly.
+ */
+ if ((map->m_lblk + map->m_len) <=
+ round_up(i_size, i_blocksize(inode)) >> inode->i_blkbits) {
+ ret = ext4_map_blocks(NULL, inode, map, 0);
+ if (ret < 0)
+ return ret;
+ if (map->m_flags & (EXT4_MAP_MAPPED | EXT4_MAP_UNWRITTEN |
+ EXT4_MAP_DELAYED))
+ return 0;
+ }
+
+ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
+ ext4_chunk_trans_blocks(inode, map->m_len));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ ret = ext4_map_blocks(handle, inode, map,
+ EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT);
+ /*
+ * Stop handle here following the lock ordering of the folio lock
+ * and the transaction start.
+ */
+ ext4_journal_stop(handle);
+
+ return ret;
+}
+
+static int ext4_iomap_buffered_do_write_begin(struct inode *inode,
+ loff_t offset, loff_t length, unsigned int flags,
+ struct iomap *iomap, struct iomap *srcmap, bool delalloc)
+{
+ int ret, retries = 0;
+ struct ext4_map_blocks map;
+ ext4_get_blocks_t *get_blocks;
+
+ ret = ext4_emergency_state(inode->i_sb);
+ if (unlikely(ret))
+ return ret;
+
+ /* Inline data and non-extent are not supported. */
+ if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
+ return -ERANGE;
+ if (WARN_ON_ONCE(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+ return -EINVAL;
+ if (WARN_ON_ONCE(!(flags & IOMAP_WRITE)))
+ return -EINVAL;
+
+ if (delalloc)
+ get_blocks = ext4_da_map_blocks;
+ else
+ get_blocks = ext4_iomap_get_blocks;
+retry:
+ ret = ext4_iomap_map_blocks(inode, offset, length, get_blocks, &map);
+ if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
+ if (ret < 0)
+ return ret;
+
+ ext4_set_iomap(inode, iomap, &map, offset, length, flags);
+ return 0;
+}
+
+static int ext4_iomap_buffered_write_begin(struct inode *inode,
+ loff_t offset, loff_t length, unsigned int flags,
+ struct iomap *iomap, struct iomap *srcmap)
+{
+ return ext4_iomap_buffered_do_write_begin(inode, offset, length, flags,
+ iomap, srcmap, false);
+}
+
+static int ext4_iomap_buffered_da_write_begin(struct inode *inode,
+ loff_t offset, loff_t length, unsigned int flags,
+ struct iomap *iomap, struct iomap *srcmap)
+{
+ return ext4_iomap_buffered_do_write_begin(inode, offset, length, flags,
+ iomap, srcmap, true);
+}
+
+/*
+ * On write failure, drop the stale delayed allocation range and release
+ * its reserved space for both start and end blocks. Otherwise, we may
+ * leave a range of delayed extents covered by a clean folio, which can
+ * result in inaccurate space reservation accounting.
+ */
+static void ext4_iomap_punch_delalloc(struct inode *inode, loff_t offset,
+ loff_t length, struct iomap *iomap)
+{
+ down_write(&EXT4_I(inode)->i_data_sem);
+ ext4_es_remove_extent(inode, offset >> inode->i_blkbits,
+ DIV_ROUND_UP_ULL(length, EXT4_BLOCK_SIZE(inode->i_sb)));
+ up_write(&EXT4_I(inode)->i_data_sem);
+}
+
+static int ext4_iomap_buffered_da_write_end(struct inode *inode, loff_t offset,
+ loff_t length, ssize_t written,
+ unsigned int flags,
+ struct iomap *iomap)
+{
+ loff_t start_byte, end_byte;
+
+ /* If we didn't reserve the blocks, we're not allowed to punch them. */
+ if (iomap->type != IOMAP_DELALLOC || !(iomap->flags & IOMAP_F_NEW))
+ return 0;
+
+ /* Nothing to do if we've written the entire delalloc extent */
+ start_byte = iomap_last_written_block(inode, offset, written);
+ end_byte = round_up(offset + length, i_blocksize(inode));
+ if (start_byte >= end_byte)
+ return 0;
+
+ filemap_invalidate_lock(inode->i_mapping);
+ iomap_write_delalloc_release(inode, start_byte, end_byte, flags,
+ iomap, ext4_iomap_punch_delalloc);
+ filemap_invalidate_unlock(inode->i_mapping);
+ return 0;
+}
+
+/*
+ * Since we always allocate unwritten extents, there is no need for
+ * iomap_end to clean up allocated blocks on a short write.
+ */
+const struct iomap_ops ext4_iomap_buffered_write_ops = {
+ .iomap_begin = ext4_iomap_buffered_write_begin,
+};
+
+const struct iomap_ops ext4_iomap_buffered_da_write_ops = {
+ .iomap_begin = ext4_iomap_buffered_da_write_begin,
+ .iomap_end = ext4_iomap_buffered_da_write_end,
+};
+
const struct iomap_ops ext4_iomap_buffered_read_ops = {
.iomap_begin = ext4_iomap_buffered_read_begin,
};
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6a77db4d3124..9bc294b769db 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -104,9 +104,13 @@ static const struct fs_parameter_spec ext4_param_specs[];
* -> page lock -> i_data_sem (rw)
*
* buffered write path:
- * sb_start_write -> i_mutex -> mmap_lock
- * sb_start_write -> i_mutex -> transaction start -> page lock ->
- * i_data_sem (rw)
+ * sb_start_write -> i_rwsem (w) -> mmap_lock
+ * - buffer_head path:
+ * sb_start_write -> i_rwsem (w) -> transaction start -> folio lock ->
+ * i_data_sem (rw)
+ * - iomap path:
+ * sb_start_write -> i_rwsem (w) -> transaction start -> i_data_sem (rw)
+ * sb_start_write -> i_rwsem (w) -> folio lock (not under an active handle)
*
* truncate:
* sb_start_write -> i_mutex -> invalidate_lock (w) -> i_mmap_rwsem (w) ->
--
2.52.0
^ permalink raw reply related
* [PATCH v4 07/23] ext4: do not use data=ordered mode for inodes using buffered iomap path
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
The data=ordered mode introduces two fundamental conflicts with the
iomap buffered write path, leading to potential deadlocks.
1) Lock ordering conflict
In the iomap writeback path, each folio is processed sequentially:
the folio lock is acquired first, followed by starting a transaction
to create block mappings. In data=ordered mode, writeback triggered
by the journal commit process may attempt to acquire a folio lock
that is already held by iomap. Meanwhile, iomap, under that same
folio lock, may start a new transaction and wait for the currently
committing transaction to finish, resulting in a deadlock.
2) Partial folio submission not supported
When block size is smaller than folio size, a folio may contain both
mapped and unmapped blocks. In data=ordered mode, if the journal
waits for such a folio to be written back while the regular writeback
process has already started committing it (with the writeback flag
set), mapping the remaining unmapped blocks can deadlock. This is
because the writeback flag is cleared only after the entire folio is
processed and committed.
To support data=ordered mode, the iomap core would need two invasive
changes:
- Acquire the transaction handle before locking any folio for
writeback.
- Support partial folio submission.
Both changes are complicated and risk performance regressions.
Therefore, we must avoid using data=ordered mode when converting to the
iomap path.
Currently, data=ordered mode is used in three scenarios:
- Append write
- Post-EOF partial block truncate-up followed by append write
- Online defragmentation
We can address the first two without data=ordered mode:
- For append write: always allocate unwritten blocks (i.e. always
enable dioread_nolock), preserving the behavior of current
extent-type inodes.
- For post-EOF truncate-up + append write: postpone updating i_disksize
until after the zeroed partial block has been written back.
Online defragmentation does not yet support iomap; this can be resolved
separately in the future.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/ext4_jbd2.h | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 63d17c5201b5..26999f173870 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -383,7 +383,12 @@ static inline int ext4_should_journal_data(struct inode *inode)
static inline int ext4_should_order_data(struct inode *inode)
{
- return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE;
+ /*
+ * inodes using the iomap buffered I/O path do not use the
+ * data=ordered mode.
+ */
+ return !ext4_inode_buffered_iomap(inode) &&
+ (ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE);
}
static inline int ext4_should_writeback_data(struct inode *inode)
--
2.52.0
^ permalink raw reply related
* [PATCH v4 10/23] ext4: implement mmap path using iomap
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
Introduce ext4_iomap_page_mkwrite() to implement the mmap iomap path
for ext4. The heavy lifting is delegated to iomap_page_mkwrite(), which
only requires ext4_iomap_buffered_write_ops and
ext4_iomap_buffered_da_write_ops to allocate and map blocks.
Note that the lock ordering between folio lock and transaction start in
this path is reversed compared to the buffer_head buffered write path.
The lock ordering documentation in super.c has been updated accordingly.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/inode.c | 32 +++++++++++++++++++++++++++++++-
fs/ext4/super.c | 8 ++++++--
2 files changed, 37 insertions(+), 3 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index a80195bd6f20..c6fe42d012fc 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4020,7 +4020,7 @@ static int ext4_iomap_buffered_do_write_begin(struct inode *inode,
return -ERANGE;
if (WARN_ON_ONCE(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EINVAL;
- if (WARN_ON_ONCE(!(flags & IOMAP_WRITE)))
+ if (WARN_ON_ONCE(!(flags & (IOMAP_WRITE | IOMAP_FAULT))))
return -EINVAL;
if (delalloc)
@@ -4080,6 +4080,14 @@ static int ext4_iomap_buffered_da_write_end(struct inode *inode, loff_t offset,
if (iomap->type != IOMAP_DELALLOC || !(iomap->flags & IOMAP_F_NEW))
return 0;
+ /*
+ * iomap_page_mkwrite() will never fail in a way that requires delalloc
+ * extents that it allocated to be revoked. Hence never try to release
+ * them here.
+ */
+ if (flags & IOMAP_FAULT)
+ return 0;
+
/* Nothing to do if we've written the entire delalloc extent */
start_byte = iomap_last_written_block(inode, offset, written);
end_byte = round_up(offset + length, i_blocksize(inode));
@@ -7191,6 +7199,23 @@ static int ext4_block_page_mkwrite(struct inode *inode, struct folio *folio,
return ret;
}
+static vm_fault_t ext4_iomap_page_mkwrite(struct vm_fault *vmf)
+{
+ struct inode *inode = file_inode(vmf->vma->vm_file);
+ const struct iomap_ops *iomap_ops;
+
+ /*
+ * ext4_nonda_switch() could writeback this folio, so have to
+ * call it before lock folio.
+ */
+ if (test_opt(inode->i_sb, DELALLOC) && !ext4_nonda_switch(inode->i_sb))
+ iomap_ops = &ext4_iomap_buffered_da_write_ops;
+ else
+ iomap_ops = &ext4_iomap_buffered_write_ops;
+
+ return iomap_page_mkwrite(vmf, iomap_ops, NULL);
+}
+
vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
@@ -7213,6 +7238,11 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
filemap_invalidate_lock_shared(mapping);
+ if (ext4_inode_buffered_iomap(inode)) {
+ ret = ext4_iomap_page_mkwrite(vmf);
+ goto out;
+ }
+
err = ext4_convert_inline_data(inode);
if (err)
goto out_ret;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 51d87db53543..62bfe05a64bc 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -100,8 +100,12 @@ static const struct fs_parameter_spec ext4_param_specs[];
* Lock ordering
*
* page fault path:
- * mmap_lock -> sb_start_pagefault -> invalidate_lock (r) -> transaction start
- * -> page lock -> i_data_sem (rw)
+ * - buffer_head path:
+ * mmap_lock -> sb_start_pagefault -> invalidate_lock (r) ->
+ * transaction start -> folio lock -> i_data_sem (rw)
+ * - iomap path:
+ * mmap_lock -> sb_start_pagefault -> invalidate_lock (r) ->
+ * folio lock -> transaction start -> i_data_sem (rw)
*
* buffered write path:
* sb_start_write -> i_rwsem (w) -> mmap_lock
--
2.52.0
^ permalink raw reply related
* [PATCH v4 20/23] ext4: wait for ordered I/O to complete during insert and collapse range
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
Currently, i_disksize is updated after ordered data writeback to prevent
exposing stale data in the post-EOF block, and operations like append
allocate, zero range, and truncate defer the i_disksize update until
ordered I/O completes.
However, insert range and collapse range still directly update
i_disksize. This is safe because they have already called
filemap_write_and_wait_range() to flush data up to LLONG_MAX, ensuring
that ordered I/O has completed if any dirty data was present.
One exception is when the ordered I/O is caused by a previous truncate
up. In this case, there is no dirty data to flush. Therefore, add an
explicit wait for I/O completion to handle this case. This will not have
significant impact on performance.
Finally, also add a WARN_ON_ONCE check before updating i_disksize to
detect any unexpected cases that could still expose stale data.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/extents.c | 18 ++++++++++++++++++
fs/ext4/inode.c | 4 +++-
2 files changed, 21 insertions(+), 1 deletion(-)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 125f628e738a..85c74c37f0ca 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -5565,6 +5565,14 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)
if (ret)
return ret;
+ /*
+ * Wait for ordered I/O to be complete. Updating i_disksize beyond
+ * the current i_disksize here risks exposuring stale data.
+ */
+ if (ext4_inode_buffered_iomap(inode))
+ wait_event(EXT4_I(inode)->i_ordered_wq,
+ READ_ONCE(EXT4_I(inode)->i_ordered_len) == 0);
+
truncate_pagecache(inode, start);
credits = ext4_chunk_trans_extent(inode, 0);
@@ -5597,6 +5605,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)
goto out_handle;
}
+ WARN_ON_ONCE(READ_ONCE(EXT4_I(inode)->i_ordered_len) != 0);
new_size = inode->i_size - len;
i_size_write(inode, new_size);
EXT4_I(inode)->i_disksize = new_size;
@@ -5661,6 +5670,14 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len)
if (ret)
return ret;
+ /*
+ * Wait for ordered I/O to be complete. Updating i_disksize beyond
+ * the current i_disksize here risks exposuring stale data.
+ */
+ if (ext4_inode_buffered_iomap(inode))
+ wait_event(EXT4_I(inode)->i_ordered_wq,
+ READ_ONCE(EXT4_I(inode)->i_ordered_len) == 0);
+
truncate_pagecache(inode, start);
credits = ext4_chunk_trans_extent(inode, 0);
@@ -5671,6 +5688,7 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len)
ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle);
/* Expand file to avoid data loss if there is error while shifting */
+ WARN_ON_ONCE(READ_ONCE(EXT4_I(inode)->i_ordered_len) != 0);
inode->i_size += len;
EXT4_I(inode)->i_disksize += len;
ret = ext4_mark_inode_dirty(handle, inode);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 23efb44f0c27..e47b504e85c9 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4899,7 +4899,9 @@ int ext4_block_zero_eof(struct inode *inode, loff_t from, loff_t end)
* i_size by the end_io handler once the ongoing I/O
* completes.
*
- * - TODO: handle insert range and collapse range.
+ * - Insert range and collapse range operations:
+ * Wait synchronously for the relevant I/O to complete
+ * before updating i_disksize.
*/
} else if (ext4_inode_buffered_iomap(inode)) {
err = ext4_iomap_submit_zero_block(inode, from, end);
--
2.52.0
^ permalink raw reply related
* [PATCH v4 22/23] ext4: partially enable iomap for the buffered I/O path of regular files
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
Introduce ext4_enable_buffered_iomap() to determine whether a regular
file inode should use the iomap buffered I/O path. We now support the
default filesystem features, mount options, and the bigalloc feature.
However, inline data, fsverity, fscrypt, indirect inode type, and
data=journal mode are not fully supported.
The decision is made at inode initialization time in __ext4_new_inode()
and __ext4_iget() by setting the EXT4_STATE_BUFFERED_IOMAP state flag.
If any of these unsupported features are met, the inode silently falls
back to the traditional buffer_head path. Switching the buffered I/O
path on an active inode is not supported, with the exception of changing
a per-inode journal flag.
For features like encryption, verity, and inline data that can be
dynamically enabled at the superblock level, checking the global feature
flag avoids the complexity of toggling the path on individual inodes.
Additionally:
- Extend ext4_inode_journal_mode() to force ordered mode for inodes
using the iomap path under a data=journal mount. For the global data
journal mode (EXT4_MOUNT_JOURNAL_DATA), dynamic enablement is
deferred until the next inode re-initialization. For the per-inode
data journal mode (EXT4_INODE_JOURNAL_DATA), dynamic changes take
effect immediately, as it is safe to switch address_space operations
and drop all page cache under i_rwsem and filemap_invalidate_lock.
- Add WARN_ON_ONCE() guards in _ext4_get_block() and
ext4_do_writepages() to catch inodes using the iomap path from
accidentally entering the legacy buffer_head writeback path.
- Reject extent-to-indirect migration via ext4_ind_migrate() for inodes
on the iomap path.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/ext4.h | 1 +
fs/ext4/ext4_jbd2.c | 8 +++--
fs/ext4/ialloc.c | 1 +
fs/ext4/inode.c | 77 +++++++++++++++++++++++++++++++++++++++++++--
fs/ext4/migrate.c | 2 ++
5 files changed, 85 insertions(+), 4 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0a3bb44f1e6e..afba952abd28 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3068,6 +3068,7 @@ int ext4_walk_page_buffers(handle_t *handle,
int do_journal_get_write_access(handle_t *handle, struct inode *inode,
struct buffer_head *bh);
void ext4_set_inode_mapping_order(struct inode *inode);
+void ext4_enable_buffered_iomap(struct inode *inode);
int ext4_nonda_switch(struct super_block *sb);
#define FALL_BACK_TO_NONDELALLOC 1
#define CONVERT_INLINE_DATA 2
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 9a8c225f2753..4534cf6f5e76 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -17,8 +17,12 @@ int ext4_inode_journal_mode(struct inode *inode)
test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
(ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
!test_opt(inode->i_sb, DELALLOC))) {
- /* We do not support data journalling for encrypted data */
- if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode))
+ /*
+ * We do not support data journalling for encrypted data
+ * and buffered IOMAP path.
+ */
+ if (S_ISREG(inode->i_mode) &&
+ (IS_ENCRYPTED(inode) || ext4_inode_buffered_iomap(inode)))
return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */
return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 3fd8f0099852..ea64b9e9e382 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1340,6 +1340,7 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
}
}
+ ext4_enable_buffered_iomap(inode);
ext4_set_inode_mapping_order(inode);
ext4_update_inode_fsync_trans(handle, inode, 1);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index cf83b4e619e0..0407e7b54dcd 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -918,6 +918,9 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
if (ext4_has_inline_data(inode))
return -ERANGE;
+ /* inode using the iomap buffered I/O path should not go here. */
+ if (WARN_ON_ONCE(ext4_inode_buffered_iomap(inode)))
+ return -EINVAL;
map.m_lblk = iblock;
map.m_len = bh->b_size >> inode->i_blkbits;
@@ -2797,6 +2800,12 @@ static int ext4_do_writepages(struct mpage_da_data *mpd)
if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
goto out_writepages;
+ /* inode using the iomap buffered I/O path should not go here. */
+ if (WARN_ON_ONCE(ext4_inode_buffered_iomap(inode))) {
+ ret = -EINVAL;
+ goto out_writepages;
+ }
+
/*
* If the filesystem has aborted, it is read-only, so return
* right away instead of dumping stack traces later on that
@@ -3929,6 +3938,9 @@ static int ext4_iomap_map_blocks(struct inode *inode, loff_t offset,
{
u8 blkbits = inode->i_blkbits;
+ /* inode using the buffer_head buffered I/O path should not go here. */
+ if (WARN_ON_ONCE(!ext4_inode_buffered_iomap(inode)))
+ return -EINVAL;
if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
return -EINVAL;
@@ -4406,6 +4418,10 @@ static int ext4_iomap_writepages(struct address_space *mapping,
.ops = &ext4_writeback_ops,
};
+ /* inode using the buffer_head buffered I/O path should not go here. */
+ if (WARN_ON_ONCE(!ext4_inode_buffered_iomap(inode)))
+ return -EINVAL;
+
ret = ext4_emergency_state(sb);
if (unlikely(ret))
return ret;
@@ -5864,6 +5880,59 @@ static int check_igot_inode(struct inode *inode, ext4_iget_flags flags,
return -EFSCORRUPTED;
}
+/*
+ * Determine whether an inode should use the iomap buffered I/O path.
+ * EXT4_STATE_BUFFERED_IOMAP is generally set at inode initialization
+ * time. Online switching of the buffered I/O path on an active inode is
+ * NOT supported, with the exception of changing a per-inode journal
+ * flag.
+ *
+ * For features like inline data, fsverity, and encryption that can be
+ * dynamically enabled or disabled, we check the superblock-level
+ * feature flags. If any of these is globally enabled, no inode is
+ * allowed into the iomap buffered I/O path. This avoids the complexity
+ * of dynamic toggling.
+ *
+ * For the global data journal mode (EXT4_MOUNT_JOURNAL_DATA), dynamic
+ * change through remount is deferred. It will only become available
+ * after the inode is re-initialized (i.e., after the last reference
+ * drops and the inode is re-read from disk with the journal flag
+ * cleared).
+ *
+ * For the per-inode data journal mode (EXT4_INODE_JOURNAL_DATA),
+ * dynamic changes take effect immediately. This is safe because
+ * address_space operations can be switched and all page cache can be
+ * dropped under i_rwsem and filemap_invalidate_lock.
+ *
+ * For extent-to-indirect block migration (via EXT4_IOC_SETFLAGS
+ * clearing EXT4_EXTENTS_FL), this operation is directly rejected for
+ * inodes using the iomap path.
+ */
+void ext4_enable_buffered_iomap(struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+
+ if (!S_ISREG(inode->i_mode))
+ return;
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE))
+ return;
+
+ /* Unsupported Features */
+ if (ext4_has_feature_inline_data(sb))
+ return;
+ if (ext4_has_feature_verity(sb))
+ return;
+ if (ext4_has_feature_encrypt(sb))
+ return;
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+ ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
+ return;
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+ return;
+
+ ext4_set_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP);
+}
+
void ext4_set_inode_mapping_order(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
@@ -6149,6 +6218,8 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
if (ret)
goto bad_inode;
+ ext4_enable_buffered_iomap(inode);
+
if (S_ISREG(inode->i_mode)) {
inode->i_op = &ext4_file_inode_operations;
inode->i_fop = &ext4_file_operations;
@@ -7326,9 +7397,10 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
* the inode's in-core data-journaling state flag now.
*/
- if (val)
+ if (val) {
ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
- else {
+ ext4_clear_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP);
+ } else {
err = jbd2_journal_flush(journal, 0);
if (err < 0) {
jbd2_journal_unlock_updates(journal);
@@ -7337,6 +7409,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
return err;
}
ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
+ ext4_enable_buffered_iomap(inode);
}
ext4_set_aops(inode);
ext4_set_inode_mapping_order(inode);
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 477d43d7e294..3b49ecf427ae 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -620,6 +620,8 @@ int ext4_ind_migrate(struct inode *inode)
if (ext4_has_feature_bigalloc(inode->i_sb))
return -EOPNOTSUPP;
+ if (ext4_inode_buffered_iomap(inode))
+ return -EOPNOTSUPP;
/*
* In order to get correct extent info, force all delayed allocation
--
2.52.0
^ permalink raw reply related
* [PATCH v4 03/23] ext4: simplify error handling in ext4_setattr()
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
Refactor the error handling in ext4_setattr() for better clarity:
- Return directly on ext4_break_layouts() failure.
- Propagate ext4_truncate() errors using the existing error variable
and jump to the common 'err_out' label.
- Propagate posix_acl_chmod() errors also through the error variable,
as it theoretically does not return a non-fatal error.
With these changes, every error path either returns immediately or jumps
to err_out. Consequently, the "if (!error)" condition guarding
setattr_copy() and mark_inode_dirty() becomes unreachable for error
cases. Remove this redundant check and the unused rc variable can be
removed as well.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/inode.c | 32 +++++++++++++++-----------------
1 file changed, 15 insertions(+), 17 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 35e958f89bd5..b1ef706987c3 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5989,7 +5989,7 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
- int error, rc = 0;
+ int error;
int orphan = 0;
const unsigned int ia_valid = attr->ia_valid;
bool inc_ivers = true;
@@ -6102,10 +6102,10 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
filemap_invalidate_lock(inode->i_mapping);
- rc = ext4_break_layouts(inode);
- if (rc) {
+ error = ext4_break_layouts(inode);
+ if (error) {
filemap_invalidate_unlock(inode->i_mapping);
- goto err_out;
+ return error;
}
if (attr->ia_size > oldsize)
@@ -6117,15 +6117,19 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
}
filemap_invalidate_unlock(inode->i_mapping);
+ if (error)
+ goto err_out;
}
- if (!error) {
- if (inc_ivers)
- inode_inc_iversion(inode);
- setattr_copy(idmap, inode, attr);
- mark_inode_dirty(inode);
- }
+ if (inc_ivers)
+ inode_inc_iversion(inode);
+ setattr_copy(idmap, inode, attr);
+ mark_inode_dirty(inode);
+ if (ia_valid & ATTR_MODE)
+ error = posix_acl_chmod(idmap, dentry, inode->i_mode);
+
+err_out:
/*
* If the call to ext4_truncate failed to get a transaction handle at
* all, we need to clean up the in-core orphan list manually.
@@ -6133,14 +6137,8 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
if (orphan && inode->i_nlink)
ext4_orphan_del(NULL, inode);
- if (!error && (ia_valid & ATTR_MODE))
- rc = posix_acl_chmod(idmap, dentry, inode->i_mode);
-
-err_out:
- if (error)
+ if (error)
ext4_std_error(inode->i_sb, error);
- if (!error)
- error = rc;
return error;
}
--
2.52.0
^ permalink raw reply related
* [PATCH v4 05/23] ext4: implement buffered read path using iomap
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
Implement the iomap read path for ext4 by introducing a new
ext4_iomap_buffered_read_ops instance. This provides the read_folio()
and readahead() callbacks for ext4_iomap_aops. The implementation
introduces:
- ext4_iomap_map_blocks(): Helper function to query extent mappings for
a given read range using ext4_map_blocks() and convert the mapping
information to iomap type
- ext4_iomap_buffered_read_begin(): The iomap_begin callback that maps
blocks, validates filesystem state, and populates the iomap. It
returns -ERANGE for inline data which is not yet supported.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
fs/ext4/inode.c | 45 ++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 44 insertions(+), 1 deletion(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 178ac2be37b7..6c4d9137b279 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3908,14 +3908,57 @@ const struct iomap_ops ext4_iomap_report_ops = {
.iomap_begin = ext4_iomap_begin_report,
};
+static int ext4_iomap_map_blocks(struct inode *inode, loff_t offset,
+ loff_t length, struct ext4_map_blocks *map)
+{
+ u8 blkbits = inode->i_blkbits;
+
+ if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
+ return -EINVAL;
+
+ /* Calculate the first and last logical blocks respectively. */
+ map->m_lblk = offset >> blkbits;
+ map->m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
+ EXT4_MAX_LOGICAL_BLOCK) - map->m_lblk + 1;
+
+ return ext4_map_blocks(NULL, inode, map, 0);
+}
+
+static int ext4_iomap_buffered_read_begin(struct inode *inode, loff_t offset,
+ loff_t length, unsigned int flags, struct iomap *iomap,
+ struct iomap *srcmap)
+{
+ struct ext4_map_blocks map;
+ int ret;
+
+ if (unlikely(ext4_forced_shutdown(inode->i_sb)))
+ return -EIO;
+
+ /* Inline data support is not yet available. */
+ if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
+ return -ERANGE;
+
+ ret = ext4_iomap_map_blocks(inode, offset, length, &map);
+ if (ret < 0)
+ return ret;
+
+ ext4_set_iomap(inode, iomap, &map, offset, length, flags);
+ return 0;
+}
+
+const struct iomap_ops ext4_iomap_buffered_read_ops = {
+ .iomap_begin = ext4_iomap_buffered_read_begin,
+};
+
static int ext4_iomap_read_folio(struct file *file, struct folio *folio)
{
+ iomap_bio_read_folio(folio, &ext4_iomap_buffered_read_ops);
return 0;
}
static void ext4_iomap_readahead(struct readahead_control *rac)
{
-
+ iomap_bio_readahead(rac, &ext4_iomap_buffered_read_ops);
}
static int ext4_iomap_writepages(struct address_space *mapping,
--
2.52.0
^ permalink raw reply related
* [PATCH v4 17/23] ext4: submit zeroed post-EOF data immediately in the iomap buffered I/O path
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
In the generic buffered_head I/O path, we rely on the data=order mode to
ensure that the zeroed EOF block data is written before updating
i_disksize, thus preventing stale data from being exposed.
However, the iomap buffered I/O path cannot use this mechanism. Instead,
we issue the I/O immediately after performing the zero operation
(without synchronous waiting for performance). This can reduce the risk
of exposing stale data, but it does not guarantee that the zero data
will be flushed to disk before the metadata of i_disksize is updated.
The subsequent patches will wait for this I/O to complete before
updating i_disksize.
Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/inode.c | 66 ++++++++++++++++++++++++++++++++++++++++---------
1 file changed, 55 insertions(+), 11 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 239d387ffaf2..e013aeb03d7b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4742,6 +4742,32 @@ static int ext4_block_zero_range(struct inode *inode,
zero_written);
}
+static int ext4_iomap_submit_zero_block(struct inode *inode,
+ loff_t from, loff_t end)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct folio *folio;
+ bool do_submit = false;
+
+ folio = filemap_lock_folio(mapping, from >> PAGE_SHIFT);
+ if (IS_ERR(folio))
+ /* Already writeback and clear? */
+ return PTR_ERR(folio) == -ENOENT ? 0 : PTR_ERR(folio);
+
+ folio_wait_writeback(folio);
+ WARN_ON_ONCE(folio_test_writeback(folio));
+
+ if (likely(folio_test_dirty(folio)))
+ do_submit = true;
+ folio_unlock(folio);
+ folio_put(folio);
+
+ /* Submit zeroed block. */
+ if (do_submit)
+ return filemap_fdatawrite_range(mapping, from, end - 1);
+ return 0;
+}
+
/*
* Zero out a mapping from file offset 'from' up to the end of the block
* which corresponds to 'from' or to the given 'end' inside this block.
@@ -4765,8 +4791,10 @@ int ext4_block_zero_eof(struct inode *inode, loff_t from, loff_t end)
if (IS_ENCRYPTED(inode) && !fscrypt_has_encryption_key(inode))
return 0;
- if (length > blocksize - offset)
+ if (length > blocksize - offset) {
length = blocksize - offset;
+ end = from + length;
+ }
err = ext4_block_zero_range(inode, from, length,
&did_zero, &zero_written);
@@ -4781,18 +4809,34 @@ int ext4_block_zero_eof(struct inode *inode, loff_t from, loff_t end)
* TODO: In the iomap path, handle this by updating i_disksize to
* i_size after the zeroed data has been written back.
*/
- if (ext4_should_order_data(inode) &&
- did_zero && zero_written && !IS_DAX(inode)) {
- handle_t *handle;
+ if (did_zero && zero_written && !IS_DAX(inode)) {
+ if (ext4_should_order_data(inode)) {
+ handle_t *handle;
- handle = ext4_journal_start(inode, EXT4_HT_MISC, 1);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
+ handle = ext4_journal_start(inode, EXT4_HT_MISC, 1);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
- err = ext4_jbd2_inode_add_write(handle, inode, from, length);
- ext4_journal_stop(handle);
- if (err)
- return err;
+ err = ext4_jbd2_inode_add_write(handle, inode, from,
+ length);
+ ext4_journal_stop(handle);
+ if (err)
+ return err;
+ /*
+ * inodes using the iomap buffered I/O path do not use the
+ * data=ordered mode. We submit zeroed range directly here.
+ * Do not wait for I/O completion for performance.
+ *
+ * TODO: Any operation that extends i_disksize (including
+ * append write end io past the zeroed boundary, truncate up,
+ * and append fallocate) must wait for the relevant I/O to
+ * complete before updating i_disksize.
+ */
+ } else if (ext4_inode_buffered_iomap(inode)) {
+ err = ext4_iomap_submit_zero_block(inode, from, end);
+ if (err)
+ return err;
+ }
}
return 0;
--
2.52.0
^ permalink raw reply related
* [PATCH v4 23/23] ext4: introduce a mount option for iomap buffered I/O path
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
Since the iomap buffered I/O path does not yet support all existing ext4
features, it cannot be enabled by default. Introduce the
'buffered_iomap' and 'nobuffered_iomap' mount options to explicitly
enable or disable the iomap buffered I/O path for regular files.
Toggling this option via remount is allowed. The change of I/O path will
not take effect immediately. It will be deferred. The new setting will
only take effect after the inode is re-initialized (i.e., after the last
reference is dropped and the inode is re-read from disk).
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/ext4.h | 1 +
fs/ext4/inode.c | 6 ++++++
fs/ext4/super.c | 7 +++++++
3 files changed, 14 insertions(+)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index afba952abd28..33da8c1915a7 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1290,6 +1290,7 @@ struct ext4_inode_info {
* scanning in mballoc
*/
#define EXT4_MOUNT2_ABORT 0x00000100 /* Abort filesystem */
+#define EXT4_MOUNT2_BUFFERED_IOMAP 0x00000200 /* Use iomap for buffered I/O */
#define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \
~EXT4_MOUNT_##opt
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0407e7b54dcd..1432ef29748b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5907,11 +5907,17 @@ static int check_igot_inode(struct inode *inode, ext4_iget_flags flags,
* For extent-to-indirect block migration (via EXT4_IOC_SETFLAGS
* clearing EXT4_EXTENTS_FL), this operation is directly rejected for
* inodes using the iomap path.
+ *
+ * When remounting to toggle the buffered_iomap mount option, the change
+ * of I/O path is deferred as well, it will be available after the inode
+ * is re-initialized.
*/
void ext4_enable_buffered_iomap(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
+ if (!test_opt2(sb, BUFFERED_IOMAP))
+ return;
if (!S_ISREG(inode->i_mode))
return;
if (ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE))
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9c0a00e716f3..2fc07739c9e8 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1733,6 +1733,7 @@ enum {
Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
Opt_no_prefetch_block_bitmaps, Opt_mb_optimize_scan,
+ Opt_buffered_iomap, Opt_nobuffered_iomap,
Opt_errors, Opt_data, Opt_data_err, Opt_jqfmt, Opt_dax_type,
#ifdef CONFIG_EXT4_DEBUG
Opt_fc_debug_max_replay, Opt_fc_debug_force
@@ -1871,6 +1872,8 @@ static const struct fs_parameter_spec ext4_param_specs[] = {
fsparam_flag ("no_prefetch_block_bitmaps",
Opt_no_prefetch_block_bitmaps),
fsparam_s32 ("mb_optimize_scan", Opt_mb_optimize_scan),
+ fsparam_flag ("buffered_iomap", Opt_buffered_iomap),
+ fsparam_flag ("nobuffered_iomap", Opt_nobuffered_iomap),
fsparam_string ("check", Opt_removed), /* mount option from ext2/3 */
fsparam_flag ("nocheck", Opt_removed), /* mount option from ext2/3 */
fsparam_flag ("reservation", Opt_removed), /* mount option from ext2/3 */
@@ -1964,6 +1967,10 @@ static const struct mount_opts {
{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
{Opt_no_prefetch_block_bitmaps, EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS,
MOPT_SET},
+ {Opt_buffered_iomap, EXT4_MOUNT2_BUFFERED_IOMAP,
+ MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY},
+ {Opt_nobuffered_iomap, EXT4_MOUNT2_BUFFERED_IOMAP,
+ MOPT_CLEAR | MOPT_2 | MOPT_EXT4_ONLY},
#ifdef CONFIG_EXT4_DEBUG
{Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY},
--
2.52.0
^ permalink raw reply related
* [PATCH v4 04/23] ext4: add iomap address space operations for buffered I/O
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
Introduce initial support for iomap in the buffered I/O path for regular
files on ext4.
- Add a new inode state flag EXT4_STATE_BUFFERED_IOMAP to indicate the
inode uses iomap instead of buffer_head for buffered I/O
- Add helper ext4_inode_buffered_iomap() to check the flag
- Add new address space operations ext4_iomap_aops with callbacks that
will use generic iomap implementations
- Add ext4_iomap_aops to ext4_set_aops() when the flag is set
The following callbacks(read_folio(), readahead(), writepages()) are
provided as placeholders and will be implemented in later patches.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
fs/ext4/ext4.h | 7 +++++++
fs/ext4/inode.c | 32 ++++++++++++++++++++++++++++++++
2 files changed, 39 insertions(+)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 94283a991e5c..1e27d73d7427 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1972,6 +1972,7 @@ enum {
EXT4_STATE_FC_COMMITTING, /* Fast commit ongoing */
EXT4_STATE_FC_FLUSHING_DATA, /* Fast commit flushing data */
EXT4_STATE_ORPHAN_FILE, /* Inode orphaned in orphan file */
+ EXT4_STATE_BUFFERED_IOMAP, /* Inode use iomap for buffered IO */
};
#define EXT4_INODE_BIT_FNS(name, field, offset) \
@@ -2040,6 +2041,12 @@ static inline bool ext4_inode_orphan_tracked(struct inode *inode)
!list_empty(&EXT4_I(inode)->i_orphan);
}
+/* Whether the inode pass through the iomap infrastructure for buffered I/O */
+static inline bool ext4_inode_buffered_iomap(struct inode *inode)
+{
+ return ext4_test_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP);
+}
+
/*
* Codes for operating systems
*/
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index b1ef706987c3..178ac2be37b7 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3908,6 +3908,22 @@ const struct iomap_ops ext4_iomap_report_ops = {
.iomap_begin = ext4_iomap_begin_report,
};
+static int ext4_iomap_read_folio(struct file *file, struct folio *folio)
+{
+ return 0;
+}
+
+static void ext4_iomap_readahead(struct readahead_control *rac)
+{
+
+}
+
+static int ext4_iomap_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ return 0;
+}
+
/*
* For data=journal mode, folio should be marked dirty only when it was
* writeably mapped. When that happens, it was already attached to the
@@ -3994,6 +4010,20 @@ static const struct address_space_operations ext4_da_aops = {
.swap_activate = ext4_iomap_swap_activate,
};
+static const struct address_space_operations ext4_iomap_aops = {
+ .read_folio = ext4_iomap_read_folio,
+ .readahead = ext4_iomap_readahead,
+ .writepages = ext4_iomap_writepages,
+ .dirty_folio = iomap_dirty_folio,
+ .bmap = ext4_bmap,
+ .invalidate_folio = iomap_invalidate_folio,
+ .release_folio = iomap_release_folio,
+ .migrate_folio = filemap_migrate_folio,
+ .is_partially_uptodate = iomap_is_partially_uptodate,
+ .error_remove_folio = generic_error_remove_folio,
+ .swap_activate = ext4_iomap_swap_activate,
+};
+
static const struct address_space_operations ext4_dax_aops = {
.writepages = ext4_dax_writepages,
.dirty_folio = noop_dirty_folio,
@@ -4015,6 +4045,8 @@ void ext4_set_aops(struct inode *inode)
}
if (IS_DAX(inode))
inode->i_mapping->a_ops = &ext4_dax_aops;
+ else if (ext4_inode_buffered_iomap(inode))
+ inode->i_mapping->a_ops = &ext4_iomap_aops;
else if (test_opt(inode->i_sb, DELALLOC))
inode->i_mapping->a_ops = &ext4_da_aops;
else
--
2.52.0
^ permalink raw reply related
* [PATCH v4 21/23] ext4: add tracepoints for ordered I/O in the iomap buffered I/O path
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
To facilitate the tracing of ordered I/Os in the iomap buffered I/O
path, add tracepoints to track the ordered I/O flow:
- ext4_iomap_ordered_submit: trace when ordered I/O is being submitted;
- ext4_iomap_ordered_complete: trace when ordered I/O completes;
- ext4_iomap_disksize_update: trace when i_disksize is updated, either
when appending I/O or when an ordered I/O completes;
- ext4_block_zero_eof - trace zero EOF partial block.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/inode.c | 4 ++
fs/ext4/page-io.c | 9 ++++
include/trace/events/ext4.h | 97 +++++++++++++++++++++++++++++++++++++
3 files changed, 110 insertions(+)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index e47b504e85c9..cf83b4e619e0 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4376,6 +4376,9 @@ static int ext4_iomap_writeback_submit(struct iomap_writepage_ctx *wpc,
ioend->io_offset + ioend->io_size);
if (start <= order_lblk && end >= order_lblk + order_len) {
+ trace_ext4_iomap_ordered_submit(ioend->io_inode,
+ ioend->io_offset, ioend->io_size,
+ order_lblk, order_len);
ioend->io_bio.bi_end_io = ext4_iomap_end_bio;
ioend->io_private = (void *)EXT4_IOMAP_IOEND_ORDER_IO;
ioend->io_flags |= IOMAP_IOEND_BOUNDARY;
@@ -4910,6 +4913,7 @@ int ext4_block_zero_eof(struct inode *inode, loff_t from, loff_t end)
}
}
+ trace_ext4_block_zero_eof(inode, from, length, did_zero, zero_written);
return 0;
}
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 2ad9f900c9f3..b5b32dc388be 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -31,6 +31,8 @@
#include "xattr.h"
#include "acl.h"
+#include <trace/events/ext4.h>
+
static struct kmem_cache *io_end_cachep;
static struct kmem_cache *io_end_vec_cachep;
@@ -682,6 +684,9 @@ static int ext4_iomap_wb_update_disksize(handle_t *handle, struct inode *inode,
* not yet on disk, but stale data will never be exposed.
*/
new_disksize = is_ordered ? i_size : min(end, i_size);
+ trace_ext4_iomap_disksize_update(inode, end, i_size, ei->i_disksize,
+ new_disksize, is_ordered);
+
if (new_disksize > ei->i_disksize)
ei->i_disksize = new_disksize;
up_write(&ei->i_data_sem);
@@ -784,6 +789,10 @@ void ext4_iomap_end_bio(struct bio *bio)
* the inode i_disksize.
*/
if (io_mode == EXT4_IOMAP_IOEND_ORDER_IO) {
+ trace_ext4_iomap_ordered_complete(inode, ioend->io_offset,
+ ioend->io_size, READ_ONCE(ei->i_ordered_lblk),
+ READ_ONCE(ei->i_ordered_len));
+
/*
* Pairs with wait_event() in ext4_iomap_wb_ordered_wait().
* Ensure i_ordered_len = 0 is visible before waking up
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index ebafa06cd191..423aec6d09d1 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -3141,6 +3141,103 @@ DEFINE_SET_IOMAP_EVENT(ext4_iomap_buffered_write_begin);
DEFINE_SET_IOMAP_EVENT(ext4_iomap_map_writeback_range);
DEFINE_SET_IOMAP_EVENT(ext4_iomap_zero_begin);
+/* Ordered I/O tracepoints for iomap buffered I/O path */
+DECLARE_EVENT_CLASS(ext4_iomap_ordered_io,
+ TP_PROTO(struct inode *inode, loff_t io_offset, size_t io_size,
+ ext4_lblk_t i_ordered_lblk, unsigned int i_ordered_len),
+ TP_ARGS(inode, io_offset, io_size, i_ordered_lblk, i_ordered_len),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(u64, ino)
+ __field(loff_t, io_offset)
+ __field(size_t, io_size)
+ __field(ext4_lblk_t, i_ordered_lblk)
+ __field(unsigned int, i_ordered_len)
+ ),
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->io_offset = io_offset;
+ __entry->io_size = io_size;
+ __entry->i_ordered_lblk = i_ordered_lblk;
+ __entry->i_ordered_len = i_ordered_len;
+ ),
+ TP_printk("dev %d:%d ino %llu io_offset %lld io_size %zu i_ordered_lblk %u i_ordered_len %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino, __entry->io_offset, __entry->io_size,
+ __entry->i_ordered_lblk, __entry->i_ordered_len)
+);
+
+DEFINE_EVENT(ext4_iomap_ordered_io, ext4_iomap_ordered_submit,
+ TP_PROTO(struct inode *inode, loff_t io_offset, size_t io_size,
+ ext4_lblk_t i_ordered_lblk, unsigned int i_ordered_len),
+ TP_ARGS(inode, io_offset, io_size, i_ordered_lblk, i_ordered_len)
+);
+
+DEFINE_EVENT(ext4_iomap_ordered_io, ext4_iomap_ordered_complete,
+ TP_PROTO(struct inode *inode, loff_t io_offset, size_t io_size,
+ ext4_lblk_t i_ordered_lblk, unsigned int i_ordered_len),
+ TP_ARGS(inode, io_offset, io_size, i_ordered_lblk, i_ordered_len)
+);
+
+
+/* i_disksize update tracepoint */
+TRACE_EVENT(ext4_iomap_disksize_update,
+ TP_PROTO(struct inode *inode, loff_t end, loff_t i_size,
+ loff_t i_disksize, loff_t new_disksize, bool is_ordered),
+ TP_ARGS(inode, end, i_size, i_disksize, new_disksize, is_ordered),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(u64, ino)
+ __field(loff_t, end)
+ __field(loff_t, i_size)
+ __field(loff_t, i_disksize)
+ __field(loff_t, new_disksize)
+ __field(bool, is_ordered)
+ ),
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->end = end;
+ __entry->i_size = i_size;
+ __entry->i_disksize = i_disksize;
+ __entry->new_disksize = new_disksize;
+ __entry->is_ordered = is_ordered;
+ ),
+ TP_printk("dev %d:%d ino %llu end %lld i_size %lld i_disksize %lld new_disksize %lld is_ordered %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino, __entry->end, __entry->i_size,
+ __entry->i_disksize, __entry->new_disksize,
+ __entry->is_ordered)
+);
+
+/* Block zero EOF tracepoint */
+TRACE_EVENT(ext4_block_zero_eof,
+ TP_PROTO(struct inode *inode, loff_t from, loff_t length,
+ bool did_zero, bool zero_written),
+ TP_ARGS(inode, from, length, did_zero, zero_written),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(u64, ino)
+ __field(loff_t, from)
+ __field(loff_t, length)
+ __field(bool, did_zero)
+ __field(bool, zero_written)
+ ),
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->from = from;
+ __entry->length = length;
+ __entry->did_zero = did_zero;
+ __entry->zero_written = zero_written;
+ ),
+ TP_printk("dev %d:%d ino %llu zero EOF from %lld length %lld did_zero %d zero_written %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino, __entry->from, __entry->length,
+ __entry->did_zero, __entry->zero_written)
+);
+
#endif /* _TRACE_EXT4_H */
/* This part must be outside protection */
--
2.52.0
^ permalink raw reply related
* [PATCH v4 06/23] ext4: pass out extent seq counter when mapping da blocks
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
The iomap buffered write path does not hold any locks between querying
inode extent mapping information and performing buffered writes. It
relies on the sequence counter saved in the inode to detect stale
mappings.
Commit 07c440e8da8f ("ext4: pass out extent seq counter when mapping
blocks") added the m_seq field to ext4_map_blocks to pass out extent
sequence numbers, but it missed two callsites within
ext4_da_map_blocks(). These callsites are on the delayed allocation
path, which is also used in the iomap buffered write path. Pass out the
sequence counter to ensure stale mappings can be detected.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
fs/ext4/inode.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 6c4d9137b279..39577a6b65b9 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1929,7 +1929,7 @@ static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map)
ext4_check_map_extents_env(inode);
/* Lookup extent status tree firstly */
- if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es, NULL)) {
+ if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es, &map->m_seq)) {
map->m_len = min_t(unsigned int, map->m_len,
es.es_len - (map->m_lblk - es.es_lblk));
@@ -1982,7 +1982,7 @@ static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map)
* is held in write mode, before inserting a new da entry in
* the extent status tree.
*/
- if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es, NULL)) {
+ if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es, &map->m_seq)) {
map->m_len = min_t(unsigned int, map->m_len,
es.es_len - (map->m_lblk - es.es_lblk));
--
2.52.0
^ permalink raw reply related
* [PATCH v4 00/23] ext4: use iomap for regular file's buffered I/O path
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
From: Zhang Yi <yi.zhang@huawei.com>
Hi,
This version is a small revision of v3 with no design changes. It fixes
some issues pointed out by Jan and Sashiko, and adds numerous comments
to clarify functionality and key considerations. You can get commits
here:
https://github.com/zhangyi089/linux/commits/ext4_buffered_iomap_v4/
Original Cover-letter:
===
This series adds the iomap buffered I/O path support for regular files,
based on the latest upstream kernel. It implements the core iomap APIs
on ext4 and introduces the 'buffered_iomap' mount option to enable the
iomap buffered I/O path. It supports default features, default mount
options and bigalloc feature. However, it does not support online
defragmentation, inline data, fsverify, fscrypt, non-extent inodes, and
data=journal mode, it will fall to buffered_head I/O path automatically
if these features and options are used.
This iomap buffered I/O path is not enabled by default because the
preceding features are not supported. Users can explicitly enable or
disable it via 'buffered_iomap' and 'nobuffered_iomap' mount options.
Key notes
=========
1. Lock ordering difference
The lock ordering of folio lock and transaction start in the iomap
path is the opposite of that in the buffer_head path.
2. data=ordered mode is not used
Two main reasons:
a) The lock ordering of folio lock and transaction start for
data=ordered mode is opposite to the iomap path, which would cause
a deadlock.
b) The iomap writeback path does not support partial folio submission
(required by data=ordered mode when block size < folio size, and
it is currently handled by ext4_bio_write_folio()), which would
also cause a deadlock.
To replace data=ordered mode functionality:
- For append write: Always allocate unwritten extents (dioread_nolock
behavior) to prevent stale data exposure.
- For post-EOF partial block zeroing: Issue zeroing I/O immediately
and asynchronously or synchronously wait for completion before
updating i_disksize. On ordered I/O completion, set i_disksize to
i_size to avoid lost updates in the truncate up and append
fallocate cases. (Jan suggested).
- For online defragmentation: Not supported yet, needs further
consideration.
3. Always enable dioread_nolock
Two main reasons:
a) Since data=ordered mode cannot be used, allocating written blocks
directly would expose stale data.
b) To optimize writeback, we should allocate blocks based on writeback
length rather than per-folio mapping. Direct written allocation
would over-allocate blocks.
dioread_nolock has been the default mount option for many years, and
Jan pointed out that we may no longer need to disable it, so gradually
remove this mount option in the future.
Series structure
================
- Patch 01-03: Simplify truncate operations and prepare for conversion.
- Patch 04-16: Implement core iomap buffered read/write, writeback,
mmap, and partial block zeroing paths.
- Patch 17-21: Handle ordered I/O for zeroing post-EOF partial block.
- Patch 22-23: Enable iomap buffered I/O path.
Testing and Performance
=======================
Tested with xfstests-bld using -g auto, fast_commit, and 64k
configurations. No new regressions were observed.
For the special case of zeroing post-EOF partial block, I add a new
generic/790 to address this scenario.
https://lore.kernel.org/fstests/20260428085750.1072612-1-yi.zhang@huaweicloud.com/
Performance tested with fio on a 150 GB memory-backed virtual machine
(no much difference compared to v2 and v3, so no update):
Buffered write (MiB/s)
===
bs write cache uncached write
bh iomap bh iomap
1k 423 403 36.3 57
4k 1067 1093 58.4 61
64k 4321 6488 869 1206
1M 4640 7378 3158 4818
Buffered read (MiB/s)
===
bs read hole read pre-cache read ondisk data
bh iomap bh iomap bh iomap
1k 635 643 661 653 605 602
4k 1987 2075 2128 2159 1761 1716
64k 6068 6267 9472 9545 4475 4451
1M 5471 6072 8657 9191 4405 4467
Large I/O write performance improved by approximately 30% to 50%.
Read performance showed no significant difference.
Changes since v3:
- Rebased on the latest upstream kernel.
- Improve commit messages for patches 07-23 to clarify functionality
and key considerations.
- Move the patches that enables IOMAP to the end of this series.
- Patch 02: Move ext4_set_inode_size() declarations from ext4.h into
inode.c, move truncate_pagecache() and ext4_truncate() to
ext4_truncate_down() as Jan suggested.
- Patch 08: Add check for non-extent inodes in the non-delalloc write
path, and clarify the reason why we don't need to truncate blocks on
short writes. (Pointed out by sashiko)
- Patch 09: Fix the issue where DATA_ERR_ABORT fails to work in
overwrite scenarios. Replace iomap_finish_ioends() with
iomap_finish_ioend() during end_io to prevent might_sleep() being
called in interrupt context. (Pointed out by sashiko)
- Patch 11: Fix underflow of the nr_blks variable. (Pointed out by
sashiko)
- Patch 17: Factor out ext4_iomap_submit_zero_block() helper to handle
ordered mode after zeroing a post-EOF partial block in the iomap
path, also add comments.
- Patch 18: Fix off-by-one in ext4_iomap_wb_ordered_wait() and clarify
why a single i_ordered_len tracker suffices. (Pointed out by sashiko)
- Patch 19: Fix an issue where the correct file size may be lost due to
a missing memory barrier. (Pointed out by sashiko)
- Patch 20: Change the logic for waiting on ordered I/Os in the insert
range and collapse range from asynchronous to synchronous.
- Patch 21: Allow per-inode journal mode changes but disallow per-inode
extent type changes, add comments of restrictions on using iomap.
Changes since v2:
- Rebased on the latest upstream kernel (7.1-rc1).
- Added patches 01-03 to simplify truncate operations.
- Added patch 13 to fix incorrect did_zero parameter in
iomap_zero_range().
- Added patches 19-22 to handle ordered I/O for zeroing post-EOF
partial block.
- Minor code and comment optimizations.
Changes since v1:
- Rebase this series on linux-next 20260122.
- Refactor partial block zero range, stop passing handle to
ext4_block_truncate_page() and ext4_zero_partial_blocks(), and move
partial block zeroing operation outside an active journal transaction
to prevent potential deadlocks because of the lock ordering of folio
and transaction start.
- Clarify the lock ordering of folio lock and transaction start, update
the comments accordingly.
- Fix some issues related to fast commit, pollute post-EOF folio.
- Some minor code and comments optimizations.
v3: https://lore.kernel.org/linux-ext4/20260422021042.4157510-1-yi.zhang@huaweicloud.com/
v2: https://lore.kernel.org/linux-ext4/20260203062523.3869120-1-yi.zhang@huawei.com/
v1: https://lore.kernel.org/linux-ext4/20241022111059.2566137-1-yi.zhang@huaweicloud.com/
RFC v4: https://lore.kernel.org/linux-ext4/20240410142948.2817554-1-yi.zhang@huaweicloud.com/
RFC v3: https://lore.kernel.org/linux-ext4/20240127015825.1608160-1-yi.zhang@huaweicloud.com/
RFC v2: https://lore.kernel.org/linux-ext4/20240102123918.799062-1-yi.zhang@huaweicloud.com/
RFC v1: https://lore.kernel.org/linux-ext4/20231123125121.4064694-1-yi.zhang@huaweicloud.com/
Comments and suggestions are welcome!
Thanks,
Yi.
Zhang Yi (23):
ext4: simplify size updating in ext4_setattr()
ext4: factor out ext4_truncate_[up|down]()
ext4: simplify error handling in ext4_setattr()
ext4: add iomap address space operations for buffered I/O
ext4: implement buffered read path using iomap
ext4: pass out extent seq counter when mapping da blocks
ext4: do not use data=ordered mode for inodes using buffered iomap
path
ext4: implement buffered write path using iomap
ext4: implement writeback path using iomap
ext4: implement mmap path using iomap
iomap: correct the range of a partial dirty clear
iomap: support invalidating partial folios
iomap: fix incorrect did_zero setting in iomap_zero_iter()
ext4: implement partial block zero range path using iomap
ext4: add block mapping tracepoints for iomap buffered I/O path
ext4: disable online defrag when inode using iomap buffered I/O path
ext4: submit zeroed post-EOF data immediately in the iomap buffered
I/O path
ext4: wait for ordered I/O in the iomap buffered I/O path
ext4: update i_disksize to i_size on ordered I/O completion
ext4: wait for ordered I/O to complete during insert and collapse
range
ext4: add tracepoints for ordered I/O in the iomap buffered I/O path
ext4: partially enable iomap for the buffered I/O path of regular
files
ext4: introduce a mount option for iomap buffered I/O path
fs/ext4/ext4.h | 57 +-
fs/ext4/ext4_jbd2.c | 8 +-
fs/ext4/ext4_jbd2.h | 7 +-
fs/ext4/extents.c | 18 +
fs/ext4/file.c | 20 +-
fs/ext4/ialloc.c | 1 +
fs/ext4/inode.c | 1040 ++++++++++++++++++++++++++++++-----
fs/ext4/migrate.c | 2 +
fs/ext4/move_extent.c | 11 +
fs/ext4/page-io.c | 210 +++++++
fs/ext4/super.c | 55 +-
fs/iomap/buffered-io.c | 22 +-
fs/iomap/ioend.c | 3 +-
include/linux/iomap.h | 1 +
include/trace/events/ext4.h | 142 +++++
15 files changed, 1446 insertions(+), 151 deletions(-)
--
2.52.0
^ permalink raw reply
* [PATCH v4 09/23] ext4: implement writeback path using iomap
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
Add the iomap writeback path for ext4 buffered I/O. This introduces:
- ext4_iomap_writepages(): the main writeback entry point.
- ext4_writeback_ops: a new iomap_writeback_ops instance to handle
block mapping and I/O submission.
- A new end I/O worker for converting unwritten extents, updating file
size, and handling DATA_ERR_ABORT after I/O completion.
Core implementation details:
- ->writeback_range() callback
Calls ext4_iomap_map_writeback_range() to query the longest range of
existing mapped extents. For performance, when a block range is not
yet allocated, it allocates based on the writeback length and delalloc
extent length, rather than allocating for a single folio at a time.
The folio is then added to an iomap_ioend instance.
- ->writeback_submit() callback
Registers ext4_iomap_end_bio() as the end bio callback. This callback
schedules a worker to handle:
- Unwritten extent conversion.
- i_disksize update after data is written back.
- Journal abort on writeback I/O failure.
Key changes and considerations:
- Append write and unwritten extents
Since data=ordered mode is not used to prevent stale data exposure
during append writebacks, new blocks are always allocated as unwritten
extents (i.e. always enable dioread_nolock), and i_disksize update is
postponed until I/O completion. Additionally, the deadlock that the
reserve handle was expected to resolve does not occur anymore.
Therefore, the end I/O worker can start a normal journal handle
instead of a reserve handle when converting unwritten extents.
- Lock ordering
The ->writeback_range() callback runs under the folio lock, requiring
the journal handle to be started under that same lock. This reverses
the order compared to the buffer_head writeback path. The lock ordering
documentation in super.c has been updated accordingly.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/ext4.h | 4 +
fs/ext4/inode.c | 208 +++++++++++++++++++++++++++++++++++++++++-
fs/ext4/page-io.c | 126 +++++++++++++++++++++++++
fs/ext4/super.c | 7 +-
fs/iomap/ioend.c | 3 +-
include/linux/iomap.h | 1 +
6 files changed, 346 insertions(+), 3 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 4832e7f7db82..078feda47e36 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1173,6 +1173,8 @@ struct ext4_inode_info {
*/
struct list_head i_rsv_conversion_list;
struct work_struct i_rsv_conversion_work;
+ struct list_head i_iomap_ioend_list;
+ struct work_struct i_iomap_ioend_work;
/*
* Transactions that contain inode's metadata needed to complete
@@ -3870,6 +3872,8 @@ int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *page,
size_t len);
extern struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end);
extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end);
+extern void ext4_iomap_end_io(struct work_struct *work);
+extern void ext4_iomap_end_bio(struct bio *bio);
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 1ae7d3f4a1c8..a80195bd6f20 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -44,6 +44,7 @@
#include <linux/iversion.h>
#include "ext4_jbd2.h"
+#include "ext4_extents.h"
#include "xattr.h"
#include "acl.h"
#include "truncate.h"
@@ -4120,10 +4121,215 @@ static void ext4_iomap_readahead(struct readahead_control *rac)
iomap_bio_readahead(rac, &ext4_iomap_buffered_read_ops);
}
+static int ext4_iomap_map_one_extent(struct inode *inode,
+ struct ext4_map_blocks *map)
+{
+ struct extent_status es;
+ handle_t *handle = NULL;
+ int credits, map_flags;
+ int retval;
+
+ credits = ext4_chunk_trans_blocks(inode, map->m_len);
+ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, credits);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ map->m_flags = 0;
+ /*
+ * It is necessary to look up extent and map blocks under i_data_sem
+ * in write mode, otherwise, the delalloc extent may become stale
+ * during concurrent truncate operations.
+ */
+ ext4_fc_track_inode(handle, inode);
+ down_write(&EXT4_I(inode)->i_data_sem);
+ if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es, &map->m_seq)) {
+ retval = es.es_len - (map->m_lblk - es.es_lblk);
+ map->m_len = min_t(unsigned int, retval, map->m_len);
+
+ if (ext4_es_is_delayed(&es)) {
+ map->m_flags |= EXT4_MAP_DELAYED;
+ trace_ext4_da_write_pages_extent(inode, map);
+ /*
+ * Call ext4_map_create_blocks() to allocate any
+ * delayed allocation blocks. It is possible that
+ * we're going to need more metadata blocks, however
+ * we must not fail because we're in writeback and
+ * there is nothing we can do so it might result in
+ * data loss. So use reserved blocks to allocate
+ * metadata if possible.
+ */
+ map_flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT |
+ EXT4_GET_BLOCKS_METADATA_NOFAIL |
+ EXT4_EX_NOCACHE;
+
+ retval = ext4_map_create_blocks(handle, inode, map,
+ map_flags);
+ if (retval > 0)
+ ext4_fc_track_range(handle, inode, map->m_lblk,
+ map->m_lblk + map->m_len - 1);
+ goto out;
+ } else if (unlikely(ext4_es_is_hole(&es)))
+ goto out;
+
+ /* Found written or unwritten extent. */
+ map->m_pblk = ext4_es_pblock(&es) + map->m_lblk - es.es_lblk;
+ map->m_flags = ext4_es_is_written(&es) ?
+ EXT4_MAP_MAPPED : EXT4_MAP_UNWRITTEN;
+ goto out;
+ }
+
+ retval = ext4_map_query_blocks(handle, inode, map, EXT4_EX_NOCACHE);
+out:
+ up_write(&EXT4_I(inode)->i_data_sem);
+ ext4_journal_stop(handle);
+ return retval < 0 ? retval : 0;
+}
+
+static int ext4_iomap_map_writeback_range(struct iomap_writepage_ctx *wpc,
+ loff_t offset, unsigned int dirty_len)
+{
+ struct inode *inode = wpc->inode;
+ struct super_block *sb = inode->i_sb;
+ struct journal_s *journal = EXT4_SB(sb)->s_journal;
+ struct ext4_map_blocks map;
+ unsigned int blkbits = inode->i_blkbits;
+ unsigned int index = offset >> blkbits;
+ unsigned int blk_end, blk_len;
+ int ret;
+
+ ret = ext4_emergency_state(sb);
+ if (unlikely(ret))
+ return ret;
+
+ /* Check validity of the cached writeback mapping. */
+ if (offset >= wpc->iomap.offset &&
+ offset < wpc->iomap.offset + wpc->iomap.length &&
+ ext4_iomap_valid(inode, &wpc->iomap))
+ return 0;
+
+ blk_len = dirty_len >> blkbits;
+ blk_end = min_t(unsigned int, (wpc->wbc->range_end >> blkbits),
+ (UINT_MAX - 1));
+ if (blk_end > index + blk_len)
+ blk_len = blk_end - index + 1;
+
+retry:
+ map.m_lblk = index;
+ map.m_len = min_t(unsigned int, MAX_WRITEPAGES_EXTENT_LEN, blk_len);
+ ret = ext4_map_blocks(NULL, inode, &map,
+ EXT4_GET_BLOCKS_IO_SUBMIT | EXT4_EX_NOCACHE);
+ if (ret < 0)
+ return ret;
+
+ /*
+ * The map is not a delalloc extent, it must either be a hole
+ * or an extent which have already been allocated.
+ */
+ if (!(map.m_flags & EXT4_MAP_DELAYED))
+ goto out;
+
+ /* Map one delalloc extent. */
+ ret = ext4_iomap_map_one_extent(inode, &map);
+ if (ret < 0) {
+ if (ext4_emergency_state(sb))
+ return ret;
+
+ /*
+ * Retry transient ENOSPC errors, if
+ * ext4_count_free_blocks() is non-zero, a commit
+ * should free up blocks.
+ */
+ if (ret == -ENOSPC && journal && ext4_count_free_clusters(sb)) {
+ jbd2_journal_force_commit_nested(journal);
+ goto retry;
+ }
+
+ ext4_msg(sb, KERN_CRIT,
+ "Delayed block allocation failed for inode %llu at logical offset %llu with max blocks %u with error %d",
+ inode->i_ino, (unsigned long long)map.m_lblk,
+ (unsigned int)map.m_len, -ret);
+ ext4_msg(sb, KERN_CRIT,
+ "This should not happen!! Data will be lost\n");
+ if (ret == -ENOSPC)
+ ext4_print_free_blocks(inode);
+ return ret;
+ }
+out:
+ ext4_set_iomap(inode, &wpc->iomap, &map, offset, dirty_len, 0);
+ return 0;
+}
+
+static void ext4_iomap_discard_folio(struct folio *folio, loff_t pos)
+{
+ struct inode *inode = folio->mapping->host;
+ loff_t length = folio_pos(folio) + folio_size(folio) - pos;
+
+ ext4_iomap_punch_delalloc(inode, pos, length, NULL);
+}
+
+static ssize_t ext4_iomap_writeback_range(struct iomap_writepage_ctx *wpc,
+ struct folio *folio, u64 offset,
+ unsigned int len, u64 end_pos)
+{
+ ssize_t ret;
+
+ ret = ext4_iomap_map_writeback_range(wpc, offset, len);
+ if (!ret)
+ ret = iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
+ if (ret < 0)
+ ext4_iomap_discard_folio(folio, offset);
+ return ret;
+}
+
+static int ext4_iomap_writeback_submit(struct iomap_writepage_ctx *wpc,
+ int error)
+{
+ struct iomap_ioend *ioend = wpc->wb_ctx;
+ struct ext4_inode_info *ei = EXT4_I(ioend->io_inode);
+
+ /*
+ * After I/O completion, a worker needs to be scheduled when:
+ * 1) Unwritten extents require conversion.
+ * 2) The file size needs to be extended.
+ * 3) The journal needs to be aborted due to an I/O error.
+ */
+ if ((ioend->io_flags & IOMAP_IOEND_UNWRITTEN) ||
+ (ioend->io_offset + ioend->io_size > READ_ONCE(ei->i_disksize)) ||
+ test_opt(ioend->io_inode->i_sb, DATA_ERR_ABORT))
+ ioend->io_bio.bi_end_io = ext4_iomap_end_bio;
+
+ return iomap_ioend_writeback_submit(wpc, error);
+}
+
+static const struct iomap_writeback_ops ext4_writeback_ops = {
+ .writeback_range = ext4_iomap_writeback_range,
+ .writeback_submit = ext4_iomap_writeback_submit,
+};
+
static int ext4_iomap_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
- return 0;
+ struct inode *inode = mapping->host;
+ struct super_block *sb = inode->i_sb;
+ long nr = wbc->nr_to_write;
+ int alloc_ctx, ret;
+ struct iomap_writepage_ctx wpc = {
+ .inode = inode,
+ .wbc = wbc,
+ .ops = &ext4_writeback_ops,
+ };
+
+ ret = ext4_emergency_state(sb);
+ if (unlikely(ret))
+ return ret;
+
+ alloc_ctx = ext4_writepages_down_read(sb);
+ trace_ext4_writepages(inode, wbc);
+ ret = iomap_writepages(&wpc);
+ trace_ext4_writepages_result(inode, wbc, ret, nr - wbc->nr_to_write);
+ ext4_writepages_up_read(sb, alloc_ctx);
+
+ return ret;
}
/*
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index dc82e7b57e75..3050c887329f 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -22,6 +22,7 @@
#include <linux/bio.h>
#include <linux/workqueue.h>
#include <linux/kernel.h>
+#include <linux/iomap.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/sched/mm.h>
@@ -611,3 +612,128 @@ int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *folio,
return 0;
}
+
+static int ext4_iomap_wb_update_disksize(handle_t *handle, struct inode *inode,
+ loff_t end)
+{
+ loff_t new_disksize = end;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int ret;
+
+ if (new_disksize <= READ_ONCE(ei->i_disksize))
+ return 0;
+
+ /*
+ * Update on-disk size after IO is completed. Races with truncate
+ * are avoided by checking i_size under i_data_sem.
+ */
+ down_write(&ei->i_data_sem);
+ new_disksize = min(new_disksize, i_size_read(inode));
+ if (new_disksize > ei->i_disksize)
+ ei->i_disksize = new_disksize;
+ up_write(&ei->i_data_sem);
+ ret = ext4_mark_inode_dirty(handle, inode);
+ if (ret)
+ EXT4_ERROR_INODE_ERR(inode, -ret, "Failed to mark inode dirty");
+
+ return ret;
+}
+
+static void ext4_iomap_finish_ioend(struct iomap_ioend *ioend)
+{
+ struct inode *inode = ioend->io_inode;
+ struct super_block *sb = inode->i_sb;
+ loff_t pos = ioend->io_offset;
+ size_t size = ioend->io_size;
+ handle_t *handle;
+ int credits;
+ int ret, err;
+
+ ret = blk_status_to_errno(ioend->io_bio.bi_status);
+ if (unlikely(ret)) {
+ if (test_opt(sb, DATA_ERR_ABORT) && !ext4_emergency_state(sb))
+ jbd2_journal_abort(EXT4_SB(sb)->s_journal, ret);
+ goto out;
+ }
+
+ /* We may need to convert one extent and dirty the inode. */
+ credits = ext4_chunk_trans_blocks(inode,
+ EXT4_MAX_BLOCKS(size, pos, inode->i_blkbits));
+ handle = ext4_journal_start(inode, EXT4_HT_EXT_CONVERT, credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out_err;
+ }
+
+ if (ioend->io_flags & IOMAP_IOEND_UNWRITTEN) {
+ ret = ext4_convert_unwritten_extents(handle, inode, pos, size);
+ if (ret)
+ goto out_journal;
+ }
+
+ ret = ext4_iomap_wb_update_disksize(handle, inode, pos + size);
+out_journal:
+ err = ext4_journal_stop(handle);
+ if (!ret)
+ ret = err;
+out_err:
+ if (ret < 0 && !ext4_emergency_state(sb)) {
+ ext4_msg(sb, KERN_EMERG,
+ "failed to convert unwritten extents to written extents or update inode size -- potential data loss! (inode %llu, error %d)",
+ inode->i_ino, ret);
+ }
+out:
+ iomap_finish_ioends(ioend, ret);
+}
+
+/*
+ * Work on buffered iomap completed IO, to convert unwritten extents to
+ * mapped extents
+ */
+void ext4_iomap_end_io(struct work_struct *work)
+{
+ struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info,
+ i_iomap_ioend_work);
+ struct iomap_ioend *ioend;
+ struct list_head ioend_list;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+ list_replace_init(&ei->i_iomap_ioend_list, &ioend_list);
+ spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+
+ iomap_sort_ioends(&ioend_list);
+ while (!list_empty(&ioend_list)) {
+ ioend = list_entry(ioend_list.next, struct iomap_ioend, io_list);
+ list_del_init(&ioend->io_list);
+ iomap_ioend_try_merge(ioend, &ioend_list);
+ ext4_iomap_finish_ioend(ioend);
+ }
+}
+
+void ext4_iomap_end_bio(struct bio *bio)
+{
+ struct iomap_ioend *ioend = iomap_ioend_from_bio(bio);
+ struct inode *inode = ioend->io_inode;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ unsigned long flags;
+
+ /* Needs to convert unwritten extents or update the i_disksize. */
+ if ((ioend->io_flags & IOMAP_IOEND_UNWRITTEN) ||
+ ioend->io_offset + ioend->io_size > READ_ONCE(ei->i_disksize))
+ goto defer;
+
+ /* Needs to abort the journal on data_err=abort. */
+ if (unlikely(ioend->io_bio.bi_status))
+ goto defer;
+
+ iomap_finish_ioend(ioend, 0);
+ return;
+defer:
+ spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+ if (list_empty(&ei->i_iomap_ioend_list))
+ queue_work(sbi->rsv_conversion_wq, &ei->i_iomap_ioend_work);
+ list_add_tail(&ioend->io_list, &ei->i_iomap_ioend_list);
+ spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9bc294b769db..51d87db53543 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -123,7 +123,10 @@ static const struct fs_parameter_spec ext4_param_specs[];
* sb_start_write -> i_mutex -> transaction start -> i_data_sem (rw)
*
* writepages:
- * transaction start -> page lock(s) -> i_data_sem (rw)
+ * - buffer_head path:
+ * transaction start -> folio lock(s) -> i_data_sem (rw)
+ * - iomap path:
+ * folio lock -> transaction start -> i_data_sem (rw)
*/
static const struct fs_context_operations ext4_context_ops = {
@@ -1428,10 +1431,12 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
#endif
ei->jinode = NULL;
INIT_LIST_HEAD(&ei->i_rsv_conversion_list);
+ INIT_LIST_HEAD(&ei->i_iomap_ioend_list);
spin_lock_init(&ei->i_completed_io_lock);
ei->i_sync_tid = 0;
ei->i_datasync_tid = 0;
INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
+ INIT_WORK(&ei->i_iomap_ioend_work, ext4_iomap_end_io);
ext4_fc_init_inode(&ei->vfs_inode);
spin_lock_init(&ei->i_fc_lock);
mmb_init(&ei->i_metadata_bhs, &ei->vfs_inode.i_data);
diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c
index acf3cf98b23a..89bbd3027b81 100644
--- a/fs/iomap/ioend.c
+++ b/fs/iomap/ioend.c
@@ -305,7 +305,7 @@ ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
}
EXPORT_SYMBOL_GPL(iomap_add_to_ioend);
-static u32 iomap_finish_ioend(struct iomap_ioend *ioend, int error)
+u32 iomap_finish_ioend(struct iomap_ioend *ioend, int error)
{
if (ioend->io_parent) {
struct bio *bio = &ioend->io_bio;
@@ -333,6 +333,7 @@ static u32 iomap_finish_ioend(struct iomap_ioend *ioend, int error)
return iomap_finish_ioend_buffered_read(ioend);
return iomap_finish_ioend_buffered_write(ioend);
}
+EXPORT_SYMBOL_GPL(iomap_finish_ioend);
/*
* Ioend completion routine for merged bios. This can only be called from task
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 2c5685adf3a9..7974ed441300 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -479,6 +479,7 @@ struct iomap_ioend *iomap_init_ioend(struct inode *inode, struct bio *bio,
loff_t file_offset, u16 ioend_flags);
struct iomap_ioend *iomap_split_ioend(struct iomap_ioend *ioend,
unsigned int max_len, bool is_append);
+u32 iomap_finish_ioend(struct iomap_ioend *ioend, int error);
void iomap_finish_ioends(struct iomap_ioend *ioend, int error);
void iomap_ioend_try_merge(struct iomap_ioend *ioend,
struct list_head *more_ioends);
--
2.52.0
^ permalink raw reply related
* [PATCH v4 01/23] ext4: simplify size updating in ext4_setattr()
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
The logic for updating the file size in ext4_setattr() is currently
somewhat messy. By directly entering the error-handling path after
failing to add an orphan inode, the unnecessary recovery process
involving old_disksize and the file size can be avoided.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
fs/ext4/inode.c | 22 +++++++++-------------
1 file changed, 9 insertions(+), 13 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c2c2d6ac7f3d..0751dc55e94f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5953,7 +5953,6 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
if (attr->ia_valid & ATTR_SIZE) {
handle_t *handle;
loff_t oldsize = inode->i_size;
- loff_t old_disksize;
int shrink = (attr->ia_size < inode->i_size);
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
@@ -6037,6 +6036,8 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
if (ext4_handle_valid(handle) && shrink) {
error = ext4_orphan_add(handle, inode);
orphan = 1;
+ if (error)
+ goto out_handle;
}
if (shrink)
@@ -6052,23 +6053,18 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
inode->i_sb->s_blocksize_bits);
- down_write(&EXT4_I(inode)->i_data_sem);
- old_disksize = EXT4_I(inode)->i_disksize;
- EXT4_I(inode)->i_disksize = attr->ia_size;
-
/*
* We have to update i_size under i_data_sem together
* with i_disksize to avoid races with writeback code
- * running ext4_wb_update_i_disksize().
+ * updating disksize in mpage_map_and_submit_extent().
*/
- if (!error)
- i_size_write(inode, attr->ia_size);
- else
- EXT4_I(inode)->i_disksize = old_disksize;
+ down_write(&EXT4_I(inode)->i_data_sem);
+ i_size_write(inode, attr->ia_size);
+ EXT4_I(inode)->i_disksize = attr->ia_size;
up_write(&EXT4_I(inode)->i_data_sem);
- rc = ext4_mark_inode_dirty(handle, inode);
- if (!error)
- error = rc;
+
+ error = ext4_mark_inode_dirty(handle, inode);
+out_handle:
ext4_journal_stop(handle);
if (error)
goto out_mmap_sem;
--
2.52.0
^ permalink raw reply related
* [PATCH v4 13/23] iomap: fix incorrect did_zero setting in iomap_zero_iter()
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
The did_zero output parameter was unconditionally set after the loop,
which is incorrect. It should only be set when the zeroing operation
actually completes, not when IOMAP_F_STALE is set or when
IOMAP_F_FOLIO_BATCH is set but !folio causes the loop to break early,
or when iomap_iter_advance() returns an error.
This causes did_zero to be incorrectly set when zeroing a clean
unwritten extent because the loop exits early without actually zeroing
any data.
Fix it by using a local variable to track whether any folio was actually
zeroed, and only set did_zero after the loop if zeroing happened.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
---
This is cherry picked form:
https://lore.kernel.org/linux-fsdevel/20260310082250.3535486-1-yi.zhang@huaweicloud.com/
No changes.
fs/iomap/buffered-io.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 876c2f507f58..27ab33edbdee 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1542,6 +1542,7 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero,
const struct iomap_write_ops *write_ops)
{
u64 bytes = iomap_length(iter);
+ bool zeroed = false;
int status;
do {
@@ -1560,6 +1561,8 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero,
/* a NULL folio means we're done with a folio batch */
if (!folio) {
status = iomap_iter_advance_full(iter);
+ if (status)
+ return status;
break;
}
@@ -1570,6 +1573,7 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero,
bytes);
folio_zero_range(folio, offset, bytes);
+ zeroed = true;
folio_mark_accessed(folio);
ret = iomap_write_end(iter, bytes, bytes, folio);
@@ -1579,10 +1583,10 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero,
status = iomap_iter_advance(iter, bytes);
if (status)
- break;
+ return status;
} while ((bytes = iomap_length(iter)) > 0);
- if (did_zero)
+ if (did_zero && zeroed)
*did_zero = true;
return status;
}
--
2.52.0
^ permalink raw reply related
* [PATCH v4 16/23] ext4: disable online defrag when inode using iomap buffered I/O path
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
Online defragmentation does not currently support inodes using the
iomap buffered I/O path. The existing implementation relies on
buffer_head for sub-folio block management and data=ordered mode for
data consistency, both of which are incompatible with the iomap path.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/move_extent.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 3329b7ad5dbd..f707a1096544 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -476,6 +476,17 @@ static int mext_check_validity(struct inode *orig_inode,
return -EOPNOTSUPP;
}
+ /*
+ * TODO: support online defrag for inodes that using the buffered
+ * I/O iomap path.
+ */
+ if (ext4_inode_buffered_iomap(orig_inode) ||
+ ext4_inode_buffered_iomap(donor_inode)) {
+ ext4_msg(sb, KERN_ERR,
+ "Online defrag not supported for inode with iomap buffered IO path");
+ return -EOPNOTSUPP;
+ }
+
if (donor_inode->i_mode & (S_ISUID|S_ISGID)) {
ext4_debug("ext4 move extent: suid or sgid is set to donor file [ino:orig %llu, donor %llu]\n",
orig_inode->i_ino, donor_inode->i_ino);
--
2.52.0
^ permalink raw reply related
* [PATCH v4 02/23] ext4: factor out ext4_truncate_[up|down]()
From: Zhang Yi @ 2026-05-11 7:23 UTC (permalink / raw)
To: linux-ext4, linux-fsdevel
Cc: linux-kernel, tytso, adilger.kernel, libaokun, jack, ojaswin,
ritesh.list, djwong, hch, yi.zhang, yi.zhang, yizhang089,
yangerkun, yukuai
In-Reply-To: <20260511072344.191271-1-yi.zhang@huaweicloud.com>
From: Zhang Yi <yi.zhang@huawei.com>
Refactor ext4_setattr() by introducing two helper functions,
ext4_truncate_up() and ext4_truncate_down(), to handle size changes. The
current ATTR_SIZE processing consolidates checks for both shrinking and
non-shrinking cases, leading to cluttered code. Separating the
truncation paths improves readability.
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/inode.c | 199 +++++++++++++++++++++++++++---------------------
1 file changed, 112 insertions(+), 87 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0751dc55e94f..35e958f89bd5 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5855,6 +5855,112 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
}
}
+/*
+ * Set i_size and i_disksize to 'newsize'.
+ *
+ * Both i_rwsem and i_data_sem are required here to avoid races between
+ * generic append writeback and concurrent truncate that also modify
+ * i_size and i_disksize.
+ */
+static inline void ext4_set_inode_size(struct inode *inode, loff_t newsize)
+{
+ WARN_ON_ONCE(S_ISREG(inode->i_mode) && !inode_is_locked(inode));
+
+ down_write(&EXT4_I(inode)->i_data_sem);
+ i_size_write(inode, newsize);
+ EXT4_I(inode)->i_disksize = newsize;
+ up_write(&EXT4_I(inode)->i_data_sem);
+}
+
+static int ext4_truncate_up(struct inode *inode, loff_t oldsize, loff_t newsize)
+{
+ ext4_lblk_t old_lblk, new_lblk;
+ handle_t *handle;
+ int ret;
+
+ if (!IS_ALIGNED(oldsize | newsize, i_blocksize(inode))) {
+ ret = ext4_inode_attach_jinode(inode);
+ if (ret)
+ return ret;
+ }
+
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
+ if (!IS_ALIGNED(oldsize, i_blocksize(inode))) {
+ ret = ext4_block_zero_eof(inode, oldsize, LLONG_MAX);
+ if (ret)
+ return ret;
+ }
+
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ old_lblk = oldsize > 0 ? (oldsize - 1) >> inode->i_blkbits : 0;
+ new_lblk = newsize > 0 ? (newsize - 1) >> inode->i_blkbits : 0;
+ ext4_fc_track_range(handle, inode, old_lblk, new_lblk);
+
+ ext4_set_inode_size(inode, newsize);
+
+ ret = ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_stop(handle);
+ if (ret)
+ return ret;
+ /*
+ * isize extend must be called outside an active handle due to
+ * the lock ordering of transaction start and folio lock in the
+ * iomap buffered I/O path (folio lock -> transaction start).
+ */
+ pagecache_isize_extended(inode, oldsize, newsize);
+ return 0;
+}
+
+static int ext4_truncate_down(struct inode *inode, loff_t oldsize,
+ loff_t newsize, int *orphan)
+{
+ ext4_lblk_t start_lblk;
+ handle_t *handle;
+ int ret;
+
+ /* Do not change i_size. */
+ if (newsize == oldsize)
+ goto truncate;
+
+ /* Shrink. */
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ if (ext4_handle_valid(handle)) {
+ ret = ext4_orphan_add(handle, inode);
+ *orphan = 1;
+ if (ret) {
+ ext4_journal_stop(handle);
+ return ret;
+ }
+ }
+
+ start_lblk = newsize > 0 ? (newsize - 1) >> inode->i_blkbits : 0;
+ ext4_fc_track_range(handle, inode, start_lblk, EXT_MAX_BLOCKS - 1);
+
+ ext4_set_inode_size(inode, newsize);
+
+ ret = ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_stop(handle);
+ if (ret)
+ return ret;
+
+ if (ext4_should_journal_data(inode))
+ ext4_wait_for_tail_page_commit(inode);
+truncate:
+ /*
+ * Truncate pagecache after we've waited for commit in data=journal
+ * mode to make pages freeable. Call ext4_truncate() even if
+ * i_size didn't change to truncatea possible preallocated blocks.
+ */
+ truncate_pagecache(inode, newsize);
+ return ext4_truncate(inode);
+}
+
/*
* ext4_setattr()
*
@@ -5951,7 +6057,6 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
}
if (attr->ia_valid & ATTR_SIZE) {
- handle_t *handle;
loff_t oldsize = inode->i_size;
int shrink = (attr->ia_size < inode->i_size);
@@ -6003,94 +6108,14 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
goto err_out;
}
- if (attr->ia_size != inode->i_size) {
- /* attach jbd2 jinode for EOF folio tail zeroing */
- if (attr->ia_size & (inode->i_sb->s_blocksize - 1) ||
- oldsize & (inode->i_sb->s_blocksize - 1)) {
- error = ext4_inode_attach_jinode(inode);
- if (error)
- goto out_mmap_sem;
- }
-
- /*
- * Update c/mtime and tail zero the EOF folio on
- * truncate up. ext4_truncate() handles the shrink case
- * below.
- */
- if (!shrink) {
- inode_set_mtime_to_ts(inode,
- inode_set_ctime_current(inode));
- if (oldsize & (inode->i_sb->s_blocksize - 1)) {
- error = ext4_block_zero_eof(inode,
- oldsize, LLONG_MAX);
- if (error)
- goto out_mmap_sem;
- }
- }
-
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
- if (IS_ERR(handle)) {
- error = PTR_ERR(handle);
- goto out_mmap_sem;
- }
- if (ext4_handle_valid(handle) && shrink) {
- error = ext4_orphan_add(handle, inode);
- orphan = 1;
- if (error)
- goto out_handle;
- }
-
- if (shrink)
- ext4_fc_track_range(handle, inode,
- (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
- inode->i_sb->s_blocksize_bits,
- EXT_MAX_BLOCKS - 1);
- else
- ext4_fc_track_range(
- handle, inode,
- (oldsize > 0 ? oldsize - 1 : oldsize) >>
- inode->i_sb->s_blocksize_bits,
- (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
- inode->i_sb->s_blocksize_bits);
-
- /*
- * We have to update i_size under i_data_sem together
- * with i_disksize to avoid races with writeback code
- * updating disksize in mpage_map_and_submit_extent().
- */
- down_write(&EXT4_I(inode)->i_data_sem);
- i_size_write(inode, attr->ia_size);
- EXT4_I(inode)->i_disksize = attr->ia_size;
- up_write(&EXT4_I(inode)->i_data_sem);
-
- error = ext4_mark_inode_dirty(handle, inode);
-out_handle:
- ext4_journal_stop(handle);
- if (error)
- goto out_mmap_sem;
- if (!shrink) {
- pagecache_isize_extended(inode, oldsize,
- inode->i_size);
- } else if (ext4_should_journal_data(inode)) {
- ext4_wait_for_tail_page_commit(inode);
- }
+ if (attr->ia_size > oldsize)
+ error = ext4_truncate_up(inode, oldsize, attr->ia_size);
+ else {
+ /* Shrink or do not change i_size. */
+ error = ext4_truncate_down(inode, oldsize,
+ attr->ia_size, &orphan);
}
- /*
- * Truncate pagecache after we've waited for commit
- * in data=journal mode to make pages freeable.
- */
- truncate_pagecache(inode, inode->i_size);
- /*
- * Call ext4_truncate() even if i_size didn't change to
- * truncate possible preallocated blocks.
- */
- if (attr->ia_size <= oldsize) {
- rc = ext4_truncate(inode);
- if (rc)
- error = rc;
- }
-out_mmap_sem:
filemap_invalidate_unlock(inode->i_mapping);
}
--
2.52.0
^ permalink raw reply related
* Re: [f2fs-dev] [GIT PULL] fsverity updates for 7.0
From: patchwork-bot+f2fs @ 2026-05-11 1:41 UTC (permalink / raw)
To: Eric Biggers
Cc: torvalds, fsverity, tytso, djwong, aalbersh, linux-kernel,
linux-f2fs-devel, dsterba, linux-fsdevel, jack, linux-ext4, hch,
linux-btrfs
In-Reply-To: <20260212012652.GA8885@sol>
Hello:
This pull request was applied to jaegeuk/f2fs.git (dev)
by Linus Torvalds <torvalds@linux-foundation.org>:
On Wed, 11 Feb 2026 17:26:52 -0800 you wrote:
> The following changes since commit 63804fed149a6750ffd28610c5c1c98cce6bd377:
>
> Linux 6.19-rc7 (2026-01-25 14:11:24 -0800)
>
> are available in the Git repository at:
>
> git://git.kernel.org/pub/scm/fs/fsverity/linux.git tags/fsverity-for-linus
>
> [...]
Here is the summary with links:
- [f2fs-dev,GIT,PULL] fsverity updates for 7.0
https://git.kernel.org/jaegeuk/f2fs/c/1bfaee9d3351
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply
* Re: [PATCH 1/2] ext4/064 encryption + casefold feature combination WITHOUT dirdata
From: Zorro Lang @ 2026-05-09 17:05 UTC (permalink / raw)
To: Artem Blagodarenko; +Cc: fstests, adilger.kernel, tytso, linux-ext4
In-Reply-To: <20260419185209.4526-1-ablagodarenko@ddn.com>
On Sun, Apr 19, 2026 at 02:52:08PM -0400, Artem Blagodarenko wrote:
> From: Artem Blagodarenko <artem.blagodarenko@gmail.com>
>
> This test verifies that files created in directories with both
> encryption and case-insensitive (casefold) attributes work correctly.
> See ext4/065 for the same test WITH dirdata feature enabled.
>
> Signed-off-by: Artem Blagodarenko <artem.blagodarenko@gmail.com>
> ---
> tests/ext4/064 | 154 +++++++++++++++++++++++++++++++++++++++++++++
> tests/ext4/064.out | 17 +++++
> 2 files changed, 171 insertions(+)
> create mode 100755 tests/ext4/064
> create mode 100644 tests/ext4/064.out
>
> diff --git a/tests/ext4/064 b/tests/ext4/064
> new file mode 100755
> index 00000000..6ad865a9
> --- /dev/null
> +++ b/tests/ext4/064
> @@ -0,0 +1,154 @@
> +#! /bin/bash
> +# SPDX-License-Identifier: GPL-2.0
> +#
> +# Copyright (c) 2026 The Lustre Collective. All Rights Reserved.
> +# Author: Artem Blagodarenko <ablagodarenko@thelustrecollective.com>
> +#
> +# FS QA Test ext4/064
> +#
> +# Test ext4 encryption + casefold feature combination WITHOUT dirdata.
> +# This test verifies that files created in directories with both
> +# encryption and case-insensitive (casefold) attributes work correctly.
> +# See ext4/065 for the same test WITH dirdata feature enabled.
> +#
> +. ./common/preamble
> +_begin_fstest auto quick encrypt casefold
> +
> +# get standard environment and checks
> +. ./common/filter
> +. ./common/encrypt
> +. ./common/casefold
> +. ./common/attr
> +
> +_exclude_fs ext2
> +_exclude_fs ext3
> +
> +_require_scratch_nocheck
> +_require_encrypted_casefold
Do you want to write a new helper names _require_encrypted_casefold? Or do you
mean _require_scratch_casefold at here?
CC ext4-list to get more review points.
Thanks,
Zorro
> +_require_command "$CHATTR_PROG" chattr
> +_require_command "$LSATTR_PROG" lsattr
> +_require_xfs_io_command "set_encpolicy"
> +_require_xfs_io_command "add_enckey"
> +
> +# Helper to add a v2 encryption key and set policy on a directory
> +_setup_encrypted_casefold_dir()
> +{
> + local dir=$1
> + local raw_key=$(_generate_raw_encryption_key)
> + local keyspec=$(_add_enckey $SCRATCH_MNT "$raw_key" | awk '{print $NF}')
> + _set_encpolicy $dir $keyspec
> + _casefold_set_attr $dir
> + echo $keyspec
> +}
> +
> +# Create a filesystem with both encrypt and casefold features
> +_scratch_mkfs -O encrypt,casefold &>>$seqres.full
> +_scratch_mount
> +
> +# Test 1: Create an encrypted + casefolded directory and verify lookups work
> +echo "Test 1: Basic encrypted casefold lookup"
> +mkdir $SCRATCH_MNT/test1
> +_setup_encrypted_casefold_dir $SCRATCH_MNT/test1 > /dev/null
> +
> +# Create file with lowercase, lookup with uppercase
> +echo "hello" > $SCRATCH_MNT/test1/testfile.txt
> +if [ -f "$SCRATCH_MNT/test1/TESTFILE.TXT" ]; then
> + echo "Case-insensitive lookup works in encrypted dir"
> +else
> + echo "FAIL: Case-insensitive lookup failed in encrypted dir"
> +fi
> +
> +# Verify the exact name on disk is preserved
> +if _casefold_check_exact_name "$SCRATCH_MNT/test1" "testfile.txt"; then
> + echo "Original filename preserved"
> +else
> + echo "FAIL: Original filename not preserved"
> +fi
> +
> +# Test 2: Create files with different case variations
> +echo "Test 2: Conflicting names in encrypted casefold dir"
> +mkdir $SCRATCH_MNT/test2
> +_setup_encrypted_casefold_dir $SCRATCH_MNT/test2 > /dev/null
> +
> +echo "first" > $SCRATCH_MNT/test2/MyFile.txt
> +# This should fail or overwrite since "MYFILE.TXT" is equivalent
> +echo "second" > $SCRATCH_MNT/test2/MYFILE.TXT 2>/dev/null
> +content=$(cat $SCRATCH_MNT/test2/myfile.txt)
> +echo "Content after writes: $content"
> +
> +# Test 3: Unicode normalization in encrypted casefold dir
> +echo "Test 3: Unicode in encrypted casefold dir"
> +mkdir $SCRATCH_MNT/test3
> +_setup_encrypted_casefold_dir $SCRATCH_MNT/test3 > /dev/null
> +
> +# Test with UTF-8 characters
> +fr_file1=$(echo -e "cafe\xcc\x81.txt")
> +fr_file2=$(echo -e "caf\xc3\xa9.txt")
> +echo "french" > "$SCRATCH_MNT/test3/$fr_file1"
> +if [ -f "$SCRATCH_MNT/test3/$fr_file2" ]; then
> + echo "Unicode normalization works in encrypted dir"
> +else
> + echo "FAIL: Unicode normalization failed in encrypted dir"
> +fi
> +
> +# Test 4: Directory operations in encrypted casefold dir
> +echo "Test 4: Directory operations in encrypted casefold dir"
> +mkdir $SCRATCH_MNT/test4
> +_setup_encrypted_casefold_dir $SCRATCH_MNT/test4 > /dev/null
> +
> +mkdir $SCRATCH_MNT/test4/SubDir
> +if [ -d "$SCRATCH_MNT/test4/SUBDIR" ]; then
> + echo "Directory case-insensitive lookup works"
> +else
> + echo "FAIL: Directory case-insensitive lookup failed"
> +fi
> +
> +# Test 5: Verify inheritance of casefold+encryption in subdirectories
> +echo "Test 5: Inheritance of attributes"
> +mkdir $SCRATCH_MNT/test5
> +_setup_encrypted_casefold_dir $SCRATCH_MNT/test5 > /dev/null
> +
> +mkdir $SCRATCH_MNT/test5/child
> +echo "data" > $SCRATCH_MNT/test5/child/file.txt
> +if [ -f "$SCRATCH_MNT/test5/CHILD/FILE.TXT" ]; then
> + echo "Attributes inherited correctly"
> +else
> + echo "FAIL: Attributes not inherited"
> +fi
> +
> +# Test 6: Remove and recreate with different case
> +echo "Test 6: Remove and recreate with different case"
> +mkdir $SCRATCH_MNT/test6
> +_setup_encrypted_casefold_dir $SCRATCH_MNT/test6 > /dev/null
> +
> +echo "original" > $SCRATCH_MNT/test6/RemoveMe.txt
> +rm $SCRATCH_MNT/test6/REMOVEME.TXT
> +echo "recreated" > $SCRATCH_MNT/test6/REMOVEME.TXT
> +if _casefold_check_exact_name "$SCRATCH_MNT/test6" "REMOVEME.TXT"; then
> + echo "Recreated file has new case"
> +else
> + echo "FAIL: Recreated file case incorrect"
> +fi
> +
> +# Test 7: Hard links in encrypted casefold dir
> +echo "Test 7: Hard links in encrypted casefold dir"
> +mkdir $SCRATCH_MNT/test7
> +_setup_encrypted_casefold_dir $SCRATCH_MNT/test7 > /dev/null
> +
> +echo "linkdata" > $SCRATCH_MNT/test7/original.txt
> +ln $SCRATCH_MNT/test7/original.txt $SCRATCH_MNT/test7/hardlink.txt
> +if [ -f "$SCRATCH_MNT/test7/HARDLINK.TXT" ]; then
> + echo "Hard link case-insensitive lookup works"
> +else
> + echo "FAIL: Hard link case-insensitive lookup failed"
> +fi
> +
> +# Cleanup and verify filesystem
> +_scratch_unmount
> +_check_scratch_fs
> +
> +echo "Encrypted casefold tests completed"
> +
> +# success, all done
> +status=0
> +exit
> diff --git a/tests/ext4/064.out b/tests/ext4/064.out
> new file mode 100644
> index 00000000..0197e51e
> --- /dev/null
> +++ b/tests/ext4/064.out
> @@ -0,0 +1,17 @@
> +QA output created by 064
> +Test 1: Basic encrypted casefold lookup
> +Case-insensitive lookup works in encrypted dir
> +Original filename preserved
> +Test 2: Conflicting names in encrypted casefold dir
> +Content after writes: second
> +Test 3: Unicode in encrypted casefold dir
> +Unicode normalization works in encrypted dir
> +Test 4: Directory operations in encrypted casefold dir
> +Directory case-insensitive lookup works
> +Test 5: Inheritance of attributes
> +Attributes inherited correctly
> +Test 6: Remove and recreate with different case
> +Recreated file has new case
> +Test 7: Hard links in encrypted casefold dir
> +Hard link case-insensitive lookup works
> +Encrypted casefold tests completed
> --
> 2.43.5
>
>
^ permalink raw reply
* [syzbot] Monthly ext4 report (May 2026)
From: syzbot @ 2026-05-09 12:32 UTC (permalink / raw)
To: linux-ext4, linux-kernel, syzkaller-bugs
Hello ext4 maintainers/developers,
This is a 31-day syzbot report for the ext4 subsystem.
All related reports/information can be found at:
https://syzkaller.appspot.com/upstream/s/ext4
During the period, 4 new issues were detected and 0 were fixed.
In total, 50 issues are still open and 175 have already been fixed.
Some of the still happening issues:
Ref Crashes Repro Title
<1> 7887 Yes WARNING in ext4_xattr_inode_update_ref (2)
https://syzkaller.appspot.com/bug?extid=76916a45d2294b551fd9
<2> 7431 Yes KASAN: out-of-bounds Read in ext4_xattr_set_entry
https://syzkaller.appspot.com/bug?extid=f792df426ff0f5ceb8d1
<3> 6043 Yes possible deadlock in ext4_writepages (2)
https://syzkaller.appspot.com/bug?extid=eb5b4ef634a018917f3c
<4> 3089 Yes kernel BUG in ext4_do_writepages
https://syzkaller.appspot.com/bug?extid=d1da16f03614058fdc48
<5> 2985 Yes possible deadlock in ext4_destroy_inline_data (2)
https://syzkaller.appspot.com/bug?extid=bb2455d02bda0b5701e3
<6> 2947 Yes INFO: task hung in sync_inodes_sb (5)
https://syzkaller.appspot.com/bug?extid=30476ec1b6dc84471133
<7> 996 Yes WARNING in ext4_xattr_inode_lookup_create
https://syzkaller.appspot.com/bug?extid=fe42a669c87e4a980051
<8> 723 Yes possible deadlock in do_writepages (2)
https://syzkaller.appspot.com/bug?extid=756f498a88797cda9299
<9> 429 Yes possible deadlock in ext4_evict_inode (5)
https://syzkaller.appspot.com/bug?extid=212e8f62790f8e0bc63b
<10> 290 Yes kernel BUG in ext4_mb_use_inode_pa (2)
https://syzkaller.appspot.com/bug?extid=d79019213609e7056a19
---
This report is generated by a bot. It may contain errors.
See https://goo.gl/tpsmEJ for more information about syzbot.
syzbot engineers can be reached at syzkaller@googlegroups.com.
To disable reminders for individual bugs, reply with the following command:
#syz set <Ref> no-reminders
To change bug's subsystems, reply with:
#syz set <Ref> subsystems: new-subsystem
You may send multiple commands in a single email message.
^ permalink raw reply
* Re: [PATCH 6.6.y] ext4: validate p_idx bounds in ext4_ext_correct_indexes
From: Sasha Levin @ 2026-05-08 21:11 UTC (permalink / raw)
To: gregkh, stable, tejas.bharambe
Cc: Sasha Levin, patches, linux-kernel, tytso, adilger.kernel,
linux-ext4, Jianqiang kang
In-Reply-To: <20260508065845.3031006-1-jianqkang@sina.cn>
> Subject: [PATCH 6.6.y] ext4: validate p_idx bounds in ext4_ext_correct_indexes
>
> commit 2acb5c12ebd860f30e4faf67e6cc8c44ddfe5fe8 upstream.
Now queued for 6.6 and 6.1, thanks.
--
Thanks,
Sasha
^ permalink raw reply
* [PATCH RFC 15/17] ext4: use fast incremental CRC update in __ext4_new_inode()
From: Baokun Li @ 2026-05-08 12:15 UTC (permalink / raw)
To: linux-ext4
Cc: linux-crypto, ebiggers, ardb, tytso, adilger.kernel, jack,
yi.zhang, ojaswin, ritesh.list, Baokun Li
In-Reply-To: <20260508121539.4174601-1-libaokun@linux.alibaba.com>
Merge the bitmap modification and group descriptor update into a single
group lock acquisition in __ext4_new_inode(). Previously the bitmap bit
was set under one lock/unlock pair, and the GDP fields (UNINIT,
itable_unused, free_inodes, dirs, csum) were updated under a separate
lock/unlock pair with a gap in between. Another thread could modify the
bitmap and update the checksum during that gap, making incremental CRC
incorrect.
Now the full sequence -- set bit, update free inodes, clear UNINIT,
update itable_unused, and compute checksum -- happens atomically under
the same ext4_lock_group(). The alloc_sem is acquired before the group
lock to maintain correct locking order with itable lazyinit.
Use ext4_inode_bitmap_csum_set_fast() for the normal path where the
stored checksum is valid. When EXT4_BG_INODE_UNINIT is set, fall back
to ext4_inode_bitmap_csum_set() for a full recalculation to establish
a correct baseline (mkfs leaves the checksum as zero for UNINIT groups).
Signed-off-by: Baokun Li <libaokun@linux.alibaba.com>
---
fs/ext4/ialloc.c | 129 +++++++++++++++++++++++------------------------
1 file changed, 63 insertions(+), 66 deletions(-)
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 8b75b331b26e..9dd1cdb367ba 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1135,7 +1135,25 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
ext4_std_error(sb, err);
goto out;
}
+
+ BUFFER_TRACE(group_desc_bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, sb, group_desc_bh,
+ EXT4_JTR_NONE);
+ if (err) {
+ ext4_std_error(sb, err);
+ goto out;
+ }
+
+ /* We may have to initialize the block bitmap if it isn't already */
+ err = ext4_might_init_block_bitmap(handle, sb, group, gdp);
+ if (err)
+ goto out;
+
+ if (ext4_has_group_desc_csum(sb) &&
+ !(sbi->s_mount_state & EXT4_FC_REPLAY))
+ down_read(&grp->alloc_sem);
ext4_lock_group(sb, group);
+
ret2 = ext4_test_and_set_bit(bit, inode_bitmap_bh->b_data);
if (ret2) {
/* Someone already took the bit. Repeat the search
@@ -1147,9 +1165,54 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
ret2 = 0;
} else {
ret2 = 1; /* we didn't grab the inode */
+ goto unlock_group;
+ }
+ }
+
+ /* Update the relevant bg descriptor fields */
+ ext4_free_inodes_set(sb, gdp,
+ ext4_free_inodes_count(sb, gdp) - 1);
+ if (S_ISDIR(mode)) {
+ ext4_used_dirs_set(sb, gdp,
+ ext4_used_dirs_count(sb, gdp) + 1);
+ if (sbi->s_log_groups_per_flex) {
+ ext4_group_t f = ext4_flex_group(sbi, group);
+ atomic_inc(&sbi_array_rcu_deref(sbi, s_flex_groups,
+ f)->used_dirs);
+ }
+ }
+
+ if (ext4_has_group_desc_csum(sb)) {
+ bool fast_crc = true;
+ int free = EXT4_INODES_PER_GROUP(sb) -
+ ext4_itable_unused_count(sb, gdp);
+
+ if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+ gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
+ free = 0;
+ /* Incremental CRC needs a valid csum baseline */
+ fast_crc = false;
}
+ /*
+ * Check the relative inode number against the
+ * last used relative inode number in this group.
+ * If it is greater we need to update the
+ * bg_itable_unused count.
+ */
+ if (bit >= free)
+ ext4_itable_unused_set(sb, gdp,
+ EXT4_INODES_PER_GROUP(sb) - bit - 1);
+ if (fast_crc)
+ ext4_inode_bitmap_csum_set_fast(sb, gdp, bit);
+ else
+ ext4_inode_bitmap_csum_set(sb, gdp, inode_bitmap_bh);
+ ext4_group_desc_csum_set(sb, group, gdp);
}
+unlock_group:
ext4_unlock_group(sb, group);
+ if (ext4_has_group_desc_csum(sb) &&
+ !(sbi->s_mount_state & EXT4_FC_REPLAY))
+ up_read(&grp->alloc_sem);
if (!ret2)
goto got; /* we grabbed the inode! */
@@ -1168,72 +1231,6 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
goto out;
}
- BUFFER_TRACE(group_desc_bh, "get_write_access");
- err = ext4_journal_get_write_access(handle, sb, group_desc_bh,
- EXT4_JTR_NONE);
- if (err) {
- ext4_std_error(sb, err);
- goto out;
- }
-
- /* We may have to initialize the block bitmap if it isn't already */
- err = ext4_might_init_block_bitmap(handle, sb, group, gdp);
- if (err)
- goto out;
-
- /* Update the relevant bg descriptor fields */
- if (ext4_has_group_desc_csum(sb)) {
- int free;
- struct ext4_group_info *grp = NULL;
-
- if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
- grp = ext4_get_group_info(sb, group);
- if (!grp) {
- err = -EFSCORRUPTED;
- goto out;
- }
- down_read(&grp->alloc_sem); /*
- * protect vs itable
- * lazyinit
- */
- }
- ext4_lock_group(sb, group); /* while we modify the bg desc */
- free = EXT4_INODES_PER_GROUP(sb) -
- ext4_itable_unused_count(sb, gdp);
- if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
- gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
- free = 0;
- }
- /*
- * Check the relative inode number against the last used
- * relative inode number in this group. if it is greater
- * we need to update the bg_itable_unused count
- */
- if (bit >= free)
- ext4_itable_unused_set(sb, gdp,
- (EXT4_INODES_PER_GROUP(sb) - bit - 1));
- if (!(sbi->s_mount_state & EXT4_FC_REPLAY))
- up_read(&grp->alloc_sem);
- } else {
- ext4_lock_group(sb, group);
- }
-
- ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1);
- if (S_ISDIR(mode)) {
- ext4_used_dirs_set(sb, gdp, ext4_used_dirs_count(sb, gdp) + 1);
- if (sbi->s_log_groups_per_flex) {
- ext4_group_t f = ext4_flex_group(sbi, group);
-
- atomic_inc(&sbi_array_rcu_deref(sbi, s_flex_groups,
- f)->used_dirs);
- }
- }
- if (ext4_has_group_desc_csum(sb)) {
- ext4_inode_bitmap_csum_set(sb, gdp, inode_bitmap_bh);
- ext4_group_desc_csum_set(sb, group, gdp);
- }
- ext4_unlock_group(sb, group);
-
BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh);
if (err) {
--
2.43.7
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox