@@ -3615,7 +3615,7 @@ static inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter)
return -EINVAL;
}
-static bool need_read_all(struct io_kiocb *req)
+static bool need_complete_io(struct io_kiocb *req)
{
return req->flags & REQ_F_ISREG ||
S_ISBLK(file_inode(req->file)->i_mode);
@@ -3679,7 +3679,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
} else if (ret == -EIOCBQUEUED) {
goto out_free;
} else if (ret == req->result || ret <= 0 || !force_nonblock ||
- (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) {
+ (req->flags & REQ_F_NOWAIT) || !need_complete_io(req)) {
/* read all, failed, already did sync or don't want to retry */
goto done;
}
@@ -3777,9 +3777,10 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
if (unlikely(!io_file_supports_nowait(req)))
goto copy_iov;
- /* file path doesn't support NOWAIT for non-direct_IO */
- if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) &&
- (req->flags & REQ_F_ISREG))
+ /* File path supports NOWAIT for non-direct_IO only for block devices. */
+ if (!(kiocb->ki_flags & IOCB_DIRECT) &&
+ !(kiocb->ki_filp->f_mode & FMODE_BUF_WASYNC) &&
+ (req->flags & REQ_F_ISREG))
goto copy_iov;
kiocb->ki_flags |= IOCB_NOWAIT;
@@ -3831,6 +3832,24 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
/* IOPOLL retry should happen for io-wq threads */
if (ret2 == -EAGAIN && (req->ctx->flags & IORING_SETUP_IOPOLL))
goto copy_iov;
+
+ if (ret2 != req->result && ret2 >= 0 && need_complete_io(req)) {
+ struct io_async_rw *rw;
+
+ /* This is a partial write. The file pos has already been
+ * updated, setup the async struct to complete the request
+ * in the worker. Also update bytes_done to account for
+ * the bytes already written.
+ */
+ iov_iter_save_state(&s->iter, &s->iter_state);
+ ret = io_setup_async_rw(req, iovec, s, true);
+
+ rw = req->async_data;
+ if (rw)
+ rw->bytes_done += ret2;
+
+ return ret ? ret : -EAGAIN;
+ }
done:
kiocb_done(req, ret2, issue_flags);
} else {
This enables the async buffered writes for block devices in io_uring. Buffered writes are enabled for blocks that are already in the page cache or can be acquired with noio. It is possible that a write request cannot be completely fullfilled (short write). In that case the request is punted and sent to the io workers to be completed. Before submitting the request to the io workers, the request is updated with how much has already been written. Signed-off-by: Stefan Roesch <shr@fb.com> --- fs/io_uring.c | 29 ++++++++++++++++++++++++----- 1 file changed, 24 insertions(+), 5 deletions(-)