@@ -491,8 +491,6 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t
/* caller is responsible for file_start_write/file_end_write */
ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
{
- mm_segment_t old_fs;
- const char __user *p;
ssize_t ret;
if (!(file->f_mode & FMODE_WRITE))
@@ -500,18 +498,29 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t
if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
- old_fs = get_fs();
- set_fs(KERNEL_DS);
- p = (__force const char __user *)buf;
if (count > MAX_RW_COUNT)
count = MAX_RW_COUNT;
- if (file->f_op->write)
- ret = file->f_op->write(file, p, count, pos);
- else if (file->f_op->write_iter)
- ret = new_sync_write(file, p, count, pos);
- else
+ if (file->f_op->write_iter) {
+ struct kvec iov = { .iov_base = (void *)buf, .iov_len = count };
+ struct kiocb kiocb;
+ struct iov_iter iter;
+
+ init_sync_kiocb(&kiocb, file);
+ kiocb.ki_pos = *pos;
+ iov_iter_kvec(&iter, WRITE, &iov, 1, count);
+ ret = file->f_op->write_iter(&kiocb, &iter);
+ if (ret > 0)
+ *pos = kiocb.ki_pos;
+ } else if (file->f_op->write) {
+ mm_segment_t old_fs = get_fs();
+
+ set_fs(KERNEL_DS);
+ ret = file->f_op->write(file, (__force const char __user *)buf,
+ count, pos);
+ set_fs(old_fs);
+ } else {
ret = -EINVAL;
- set_fs(old_fs);
+ }
if (ret > 0) {
fsnotify_modify(file);
add_wchar(current, ret);
If we write to a file that implements ->write_iter there is no need to change the address limit if we send a kvec down. Implement that case, and prefer it over using plain ->write with a changed address limit if available. Signed-off-by: Christoph Hellwig <hch@lst.de> --- fs/read_write.c | 31 ++++++++++++++++++++----------- 1 file changed, 20 insertions(+), 11 deletions(-)