[PATCH 1/2] ext4: use fsdata to track inline data write state
From: Aditya Srivastava
Date: Tue Jun 30 2026 - 11:32:48 EST
From: Aditya Prakash Srivastava <aditya.ansh182@xxxxxxxxx>
Instead of checking the live inode state (`ext4_has_inline_data(inode)`
and `ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)`) in the
write_end handlers, use the `fsdata` parameter of the address space
operations to explicitly pass down the state in which `write_begin`
prepared the write.
A concurrent thread (such as `ext4_page_mkwrite()`) can convert the
inline data to an extent between `write_begin` and `write_end`. If this
happens, the write_end handlers would previously miss the inline
write_end path and fall through to extent-based write_end logic. However,
since block buffers were never allocated in `write_begin`, this resulted
in NULL pointer dereferences or data loss because `folio_buffers(folio)`
was NULL.
By defining `EXT4_WRITE_DATA_INLINE` (3) and communicating this state via
`fsdata`:
1) `ext4_write_begin()` and `ext4_da_write_begin()` explicitly set
`*fsdata` to `EXT4_WRITE_DATA_INLINE` when an inline write is
successfully prepared.
2) `ext4_write_end()`, `ext4_journalled_write_end()`, and
`ext4_da_write_end()` rely solely on `fsdata` / `write_mode` to
invoke `ext4_write_inline_data_end()`.
This removes the crude race fallbacks and makes the write_end
determination unambiguous, simple, and clean.
Suggested-by: Jan Kara <jack@xxxxxxx>
Signed-off-by: Aditya Prakash Srivastava <aditya.ansh182@xxxxxxxxx>
---
fs/ext4/ext4.h | 1 +
fs/ext4/inode.c | 22 +++++++++++++---------
2 files changed, 14 insertions(+), 9 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index b37c136ea3ab..521bd5d6321c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3138,6 +3138,7 @@ int do_journal_get_write_access(handle_t *handle, struct inode *inode,
void ext4_set_inode_mapping_order(struct inode *inode);
#define FALL_BACK_TO_NONDELALLOC 1
#define CONVERT_INLINE_DATA 2
+#define EXT4_WRITE_DATA_INLINE 3
typedef enum {
EXT4_IGET_NORMAL = 0,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ce99807c5f5b..e2e8ac5fb8d8 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1302,6 +1302,9 @@ static int ext4_write_begin(const struct kiocb *iocb,
if (unlikely(ret))
return ret;
+ if (fsdata && *fsdata != (void *)FALL_BACK_TO_NONDELALLOC)
+ *fsdata = NULL;
+
trace_ext4_write_begin(inode, pos, len);
/*
* Reserve one block more for addition to orphan list in case
@@ -1316,8 +1319,11 @@ static int ext4_write_begin(const struct kiocb *iocb,
foliop);
if (ret < 0)
return ret;
- if (ret == 1)
+ if (ret == 1) {
+ if (fsdata)
+ *fsdata = (void *)EXT4_WRITE_DATA_INLINE;
return 0;
+ }
}
/*
@@ -1450,8 +1456,7 @@ static int ext4_write_end(const struct kiocb *iocb,
trace_ext4_write_end(inode, pos, len, copied);
- if (ext4_has_inline_data(inode) &&
- ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA))
+ if (fsdata == (void *)EXT4_WRITE_DATA_INLINE)
return ext4_write_inline_data_end(inode, pos, len, copied,
folio);
@@ -1560,8 +1565,7 @@ static int ext4_journalled_write_end(const struct kiocb *iocb,
BUG_ON(!ext4_handle_valid(handle));
- if (ext4_has_inline_data(inode) &&
- ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA))
+ if (fsdata == (void *)EXT4_WRITE_DATA_INLINE)
return ext4_write_inline_data_end(inode, pos, len, copied,
folio);
@@ -3161,8 +3165,10 @@ static int ext4_da_write_begin(const struct kiocb *iocb,
foliop, fsdata, true);
if (ret < 0)
return ret;
- if (ret == 1)
+ if (ret == 1) {
+ *fsdata = (void *)EXT4_WRITE_DATA_INLINE;
return 0;
+ }
}
retry:
@@ -3299,9 +3305,7 @@ static int ext4_da_write_end(const struct kiocb *iocb,
trace_ext4_da_write_end(inode, pos, len, copied);
- if (write_mode != CONVERT_INLINE_DATA &&
- ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) &&
- ext4_has_inline_data(inode))
+ if (write_mode == EXT4_WRITE_DATA_INLINE)
return ext4_write_inline_data_end(inode, pos, len, copied,
folio);
--
2.47.3