ext4: don't take the i_mutex lock when doing DIO overwrites
Aligned and overwrite direct I/O can be parallelized. In
ext4_file_dio_write, we first check whether these conditions are
satisfied or not. If so, we take i_data_sem and release i_mutex lock
directly. Meanwhile iocb->private is set to indicate that this is a
dio overwrite, and it will be handled in ext4_ext_direct_IO.
[ Added fix from Dan Carpenter to fix locking bug on the error path. ]
CC: Tao Ma <tm@tao.ma>
CC: Eric Sandeen <sandeen@redhat.com>
CC: Robin Dong <hao.bigrat@gmail.com>
Signed-off-by: Zheng Liu <wenqing.lz@taobao.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 76cb3b1..bed574d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2996,6 +2996,16 @@
if (rw == WRITE && final_size <= inode->i_size) {
int overwrite = 0;
+ BUG_ON(iocb->private == NULL);
+
+ /* If we do a overwrite dio, i_mutex locking can be released */
+ overwrite = *((int *)iocb->private);
+
+ if (overwrite) {
+ down_read(&EXT4_I(inode)->i_data_sem);
+ mutex_unlock(&inode->i_mutex);
+ }
+
/*
* We could direct write to holes and fallocate.
*
@@ -3021,8 +3031,10 @@
if (!is_sync_kiocb(iocb)) {
ext4_io_end_t *io_end =
ext4_init_io_end(inode, GFP_NOFS);
- if (!io_end)
- return -ENOMEM;
+ if (!io_end) {
+ ret = -ENOMEM;
+ goto retake_lock;
+ }
io_end->flag |= EXT4_IO_END_DIRECT;
iocb->private = io_end;
/*
@@ -3083,6 +3095,14 @@
ret = err;
ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
}
+
+ retake_lock:
+ /* take i_mutex locking again if we do a ovewrite dio */
+ if (overwrite) {
+ up_read(&EXT4_I(inode)->i_data_sem);
+ mutex_lock(&inode->i_mutex);
+ }
+
return ret;
}