The io_uring_prep_readv2/writev2() man pages recommend using the
non-vectored read/write operations when possible for performance
reasons.

I didn't measure a significant difference but it doesn't hurt to have
this optimization in place.

Suggested-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block/io_uring.c | 29 ++++++++++++++++++++++++-----
 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/block/io_uring.c b/block/io_uring.c
index dd930ee57e..bbefbddcc0 100644
--- a/block/io_uring.c
+++ b/block/io_uring.c
@@ -49,12 +49,24 @@ static void luring_prep_sqe(struct io_uring_sqe *sqe, void *opaque)
 #ifdef HAVE_IO_URING_PREP_WRITEV2
     {
         int luring_flags = (flags & BDRV_REQ_FUA) ? RWF_DSYNC : 0;
-        io_uring_prep_writev2(sqe, fd, qiov->iov,
-                              qiov->niov, offset, luring_flags);
+        if (luring_flags != 0 || qiov->niov > 1) {
+            io_uring_prep_writev2(sqe, fd, qiov->iov,
+                                  qiov->niov, offset, luring_flags);
+        } else {
+            /* The man page says non-vectored is faster than vectored */
+            struct iovec *iov = qiov->iov;
+            io_uring_prep_write(sqe, fd, iov->iov_base, iov->iov_len, offset);
+        }
     }
 #else
         assert(flags == 0);
-        io_uring_prep_writev(sqe, fd, qiov->iov, qiov->niov, offset);
+        if (qiov->niov > 1) {
+            io_uring_prep_writev(sqe, fd, qiov->iov, qiov->niov, offset);
+        } else {
+            /* The man page says non-vectored is faster than vectored */
+            struct iovec *iov = qiov->iov;
+            io_uring_prep_write(sqe, fd, iov->iov_base, iov->iov_len, offset);
+        }
 #endif
         break;
     case QEMU_AIO_ZONE_APPEND:
@@ -65,8 +77,15 @@ static void luring_prep_sqe(struct io_uring_sqe *sqe, void *opaque)
         if (req->resubmit_qiov.iov != NULL) {
             qiov = &req->resubmit_qiov;
         }
-        io_uring_prep_readv(sqe, fd, qiov->iov, qiov->niov,
-                            offset + req->total_read);
+        if (qiov->niov > 1) {
+            io_uring_prep_readv(sqe, fd, qiov->iov, qiov->niov,
+                                offset + req->total_read);
+        } else {
+            /* The man page says non-vectored is faster than vectored */
+            struct iovec *iov = qiov->iov;
+            io_uring_prep_read(sqe, fd, iov->iov_base, iov->iov_len,
+                               offset + req->total_read);
+        }
         break;
     }
     case QEMU_AIO_FLUSH:
-- 
2.51.0