fix O_SYNC|O_APPEND syncing the wrong range on write()

It actually goes back to 2004 ([PATCH] Concurrent O_SYNC write support)
when sync_page_range() had been introduced; generic_file_write{,v}() correctly
synced
	pos_after_write - written .. pos_after_write - 1
but generic_file_aio_write() synced
	pos_before_write .. pos_before_write + written - 1
instead.  Which is not the same thing with O_APPEND, obviously.
A couple of years later correct variant had been killed off when
everything switched to use of generic_file_aio_write().

All users of generic_file_aio_write() are affected, and the same bug
has been copied into other instances of ->aio_write().

The fix is trivial; the only subtle point is that generic_write_sync()
ought to be inlined to avoid calculations useless for the majority of
calls.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 853d6d1cc822280a0deb1e5106aff7d84323e869..a7eda8ebfacc8ca90210358b5e2300c7530e0223 100644 (file)
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2559,8 +2559,8 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov,
        if (rc > 0) {
                ssize_t err;
 
-               err = generic_write_sync(file, pos, rc);
-               if (err < 0 && rc > 0)
+               err = generic_write_sync(file, iocb->ki_pos - rc, rc);
+               if (err < 0)
                        rc = err;
        }
 

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 43e64f6022eb4af22e7ac95eb6aaa34e7e6735a9..1a5073959f322655b93ade8189107b9148d244ed 100644 (file)
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -152,7 +152,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
        if (ret > 0) {
                ssize_t err;
 
-               err = generic_write_sync(file, pos, ret);
+               err = generic_write_sync(file, iocb->ki_pos - ret, ret);
                if (err < 0 && ret > 0)
                        ret = err;
        }

diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index ea4ba9daeb472069cd9d8664b58ff363806ab4e4..db9bd8a31725477eb9130bb6868d25bda510aa4a 100644 (file)
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -2134,7 +2134,7 @@ static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
        ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos);
        mutex_unlock(&inode->i_mutex);
        if (ret > 0) {
-               int err = generic_write_sync(file, pos, ret);
+               int err = generic_write_sync(file, iocb->ki_pos - ret, ret);
                if (err < 0)
                        ret = err;
        }

diff --git a/fs/sync.c b/fs/sync.c
index f15537452231d003a05f99b6b28d3c63b85dc8f0..e8ba024a055b5a55d6320ba38edf1338c7d90e65 100644 (file)
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -222,23 +222,6 @@ SYSCALL_DEFINE1(fdatasync, unsigned int, fd)
        return do_fsync(fd, 1);
 }
 
-/**
- * generic_write_sync - perform syncing after a write if file / inode is sync
- * @file:      file to which the write happened
- * @pos:       offset where the write started
- * @count:     length of the write
- *
- * This is just a simple wrapper about our general syncing function.
- */
-int generic_write_sync(struct file *file, loff_t pos, loff_t count)
-{
-       if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host))
-               return 0;
-       return vfs_fsync_range(file, pos, pos + count - 1,
-                              (file->f_flags & __O_SYNC) ? 0 : 1);
-}
-EXPORT_SYMBOL(generic_write_sync);
-
 /*
  * sys_sync_file_range() permits finely controlled syncing over a segment of
  * a file in the range offset .. (offset+nbytes-1) inclusive.  If nbytes is

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 2e7989e3a2d67374d17e5086ec3b15bfbcb32e2d..64b48eade91d14c79408b6863f199e9181350f81 100644 (file)
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -799,7 +799,7 @@ xfs_file_aio_write(
                XFS_STATS_ADD(xs_write_bytes, ret);
 
                /* Handle various SYNC-type writes */
-               err = generic_write_sync(file, pos, ret);
+               err = generic_write_sync(file, iocb->ki_pos - ret, ret);
                if (err < 0)
                        ret = err;
        }

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 09f553c59813a2b2f88991ab0ab854880e07e574..75ff961be0515a8765c2544e3946d67cb6756dcf 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2273,7 +2273,13 @@ extern int filemap_fdatawrite_range(struct address_space *mapping,
 extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
                           int datasync);
 extern int vfs_fsync(struct file *file, int datasync);
-extern int generic_write_sync(struct file *file, loff_t pos, loff_t count);
+static inline int generic_write_sync(struct file *file, loff_t pos, loff_t count)
+{
+       if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host))
+               return 0;
+       return vfs_fsync_range(file, pos, pos + count - 1,
+                              (file->f_flags & __O_SYNC) ? 0 : 1);
+}
 extern void emergency_sync(void);
 extern void emergency_remount(void);
 #ifdef CONFIG_BLOCK

diff --git a/mm/filemap.c b/mm/filemap.c
index d56d3c145b9f26d3210ec8ad17430be6c46af2a9..7a13f6ac5421b9fead7729df856556b12269ad8c 100644 (file)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2553,8 +2553,8 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
        if (ret > 0) {
                ssize_t err;
 
-               err = generic_write_sync(file, pos, ret);
-               if (err < 0 && ret > 0)
+               err = generic_write_sync(file, iocb->ki_pos - ret, ret);
+               if (err < 0)
                        ret = err;
        }
        return ret;