Skip to contentSkip to conversation

io_uring/kbuf: don't truncate end buffer for multiple buffer peeks

PATCH New Jens Axboe 1 participant 1 message Jun 13, 2025 io_uring

lore
Share & tools
lore

Jens Axboe

author maintainer
#0 lore raw

PATCH 1/1 io_uring/kbuf: don't truncate end buffer for multiple buffer peeks

If peeking a bunch of buffers, normally io_ring_buffers_peek() will truncate the end buffer. This isn't optimal as presumably more data will be arriving later, and hence it's better to stop with the last full buffer rather than truncate the end buffer.

Fixes 35c8711c8fc4 ("io_uring/kbuf: add helpers for getting/peeking multiple buffers")

---

io_uring/kbuf.c +4 -1
index 2ea65f3cef72..ce95e3af44a9 100644
@@ -270,8 +270,11 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg,
 		/* truncate end piece, if needed, for non partial buffers */
 		if (len > arg->max_len) {
 			len = arg->max_len;
-			if (!(bl->flags & IOBL_INC))
+			if (!(bl->flags & IOBL_INC)) {
+				if (iov != arg->iovs)
+					break;
 				buf->len = len;
+			}
 		}
 
 		iov->iov_base = u64_to_user_ptr(buf->addr);
Signature · 1 line
Jens Axboe