Btrfs: fix the file extent gap when doing direct IO

When we write some data to the place that is beyond the end of the file
in direct I/O mode, a data hole will be created. And Btrfs should insert
a file extent item that point to this hole into the fs tree. But unfortunately
Btrfs forgets doing it.

The following is a simple way to reproduce it:
 # mkfs.btrfs /dev/sdc2
 # mount /dev/sdc2 /test4
 # touch /test4/a
 # dd if=/dev/zero of=/test4/a seek=8 count=1 bs=4K oflag=direct conv=nocreat,notrunc
 # umount /test4
 # btrfsck /dev/sdc2
 root 5 inode 257 errors 100

Reported-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Tested-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 15e5a1cd8764a1d11447408558fddd4163962de0..98d95bb5f253cdb3c0a2fe590c079a647901d12a 100644 (file)
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1075,12 +1075,6 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file,
        start_pos = pos & ~((u64)root->sectorsize - 1);
        last_pos = ((u64)index + num_pages) << PAGE_CACHE_SHIFT;
 
-       if (start_pos > inode->i_size) {
-               err = btrfs_cont_expand(inode, i_size_read(inode), start_pos);
-               if (err)
-                       return err;
-       }
-
 again:
        for (i = 0; i < num_pages; i++) {
                pages[i] = find_or_create_page(inode->i_mapping, index + i,
@@ -1338,6 +1332,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
        struct inode *inode = fdentry(file)->d_inode;
        struct btrfs_root *root = BTRFS_I(inode)->root;
        loff_t *ppos = &iocb->ki_pos;
+       u64 start_pos;
        ssize_t num_written = 0;
        ssize_t err = 0;
        size_t count, ocount;
@@ -1386,6 +1381,15 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
        file_update_time(file);
        BTRFS_I(inode)->sequence++;
 
+       start_pos = round_down(pos, root->sectorsize);
+       if (start_pos > i_size_read(inode)) {
+               err = btrfs_cont_expand(inode, i_size_read(inode), start_pos);
+               if (err) {
+                       mutex_unlock(&inode->i_mutex);
+                       goto out;
+               }
+       }
+
        if (unlikely(file->f_flags & O_DIRECT)) {
                num_written = __btrfs_direct_write(iocb, iov, nr_segs,
                                                   pos, ppos, count, ocount);