[PATCH 0/2] Fix return with MSG_TUNC overtruncating buffers

[PATCH 0/2] Fix return with MSG_TUNC overtruncating buffers

[Gabriel Krisman Bertazi]

Jens,

This is an attempt to fix the issue reported at [1].  It works by
splitting the return size (which can be the full size of the packet)
from the value actually commited in the buffer.  Please, let me know
your thoughts.  Patch 1 is a small preparation and patch 2 has the fix.

This was tested for regressions against liburing as well as using the
reproducer from the bug, which I can turn into a proper test case
against liburing.

I sent this before but the submission was botched.  Please take this
version in consideration.

Thanks,

[1]  https://github.com/axboe/liburing/issues/1619

Gabriel Krisman Bertazi (2):
  io_uring/net: let io_recv_buf_select return the length of the buffer
    region
  io_uring/net: don't overconsume buffers when using MSG_TRUNC

 io_uring/net.c | 48 +++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 37 insertions(+), 11 deletions(-)

-- 
2.55.0

[PATCH 1/2] io_uring/net: let io_recv_buf_select return the length of the buffer region

[Gabriel Krisman Bertazi]

In preparation to using this field as an upper limit to truncation,
return the size of the allocated region.

Fixes: ae98dbf43d75 ("io_uring/kbuf: add support for incremental buffer consumption")
Cc: stable@vger.kernel.org
Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
---
 io_uring/net.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/io_uring/net.c b/io_uring/net.c
index fbe719d86c46..647156c9331a 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -1108,6 +1108,7 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg
 			      struct io_br_sel *sel, unsigned int issue_flags)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+	size_t len;
 	int ret;
 
 	/*
@@ -1153,13 +1154,14 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg
 		/* special case 1 vec, can be a fast path */
 		if (ret == 1) {
 			sr->buf = arg.iovs[0].iov_base;
-			sr->len = arg.iovs[0].iov_len;
+			len = sr->len = arg.iovs[0].iov_len;
 			goto map_ubuf;
 		}
 		iov_iter_init(&kmsg->msg.msg_iter, ITER_DEST, arg.iovs, ret,
-				arg.out_len);
+			      arg.out_len);
+		len = arg.out_len;
 	} else {
-		size_t len = sel->val;
+		len = sel->val;
 
 		*sel = io_buffer_select(req, &len, sr->buf_group, issue_flags);
 		if (!sel->addr)
@@ -1173,7 +1175,7 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg
 			return ret;
 	}
 
-	return 0;
+	return len;
 }
 
 int io_recv(struct io_kiocb *req, unsigned int issue_flags)
-- 
2.55.0

[PATCH 2/2] io_uring/net: don't overconsume buffers when using MSG_TRUNC

[Gabriel Krisman Bertazi]

When a recv/recvmsg is issued with MSG_TRUNC and the incoming packet is
larger than the provided buffer, the net layer returns the full length
of the packet rather than the number of bytes actually copied into the
buffer.  As a result, io_uring advances more of the provided buffer ring
than was actually filled.  Use the actual filled region size to consume
the buffer, but still return the full size to preserve MSG_TRUNC
semantics.

Take care with multishot, because that seems to already truncate the
consumption based on the available payload size.

This was reported in https://github.com/axboe/liburing/issues/1619.

Fixes: ae98dbf43d75 ("io_uring/kbuf: add support for incremental buffer consumption")
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260728191454.1850326-1-krisman@suse.de
Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
---
 io_uring/net.c | 38 +++++++++++++++++++++++++++++++-------
 1 file changed, 31 insertions(+), 7 deletions(-)

diff --git a/io_uring/net.c b/io_uring/net.c
index 647156c9331a..f8110dc9f860 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -853,7 +853,7 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 static inline bool io_recv_finish(struct io_kiocb *req,
 				  struct io_async_msghdr *kmsg,
 				  struct io_br_sel *sel, bool mshot_finished,
-				  unsigned issue_flags)
+				  unsigned issue_flags, size_t consumed)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 	unsigned int cflags = 0;
@@ -877,7 +877,7 @@ static inline bool io_recv_finish(struct io_kiocb *req,
 	if (sr->flags & IORING_RECVSEND_BUNDLE) {
 		size_t this_ret = sel->val - sr->done_io;
 
-		cflags |= io_put_kbufs(req, this_ret, sel->buf_list, io_bundle_nbufs(kmsg, this_ret));
+		cflags |= io_put_kbufs(req, consumed, sel->buf_list, io_bundle_nbufs(kmsg, consumed));
 		if (sr->flags & IORING_RECV_RETRY)
 			cflags = req->cqe.flags | (cflags & CQE_F_MASK);
 		if (sr->mshot_len && sel->val >= sr->mshot_len)
@@ -899,7 +899,7 @@ static inline bool io_recv_finish(struct io_kiocb *req,
 			return false;
 		}
 	} else {
-		cflags |= io_put_kbuf(req, sel->val, sel->buf_list);
+		cflags |= io_put_kbuf(req, consumed, sel->buf_list);
 	}
 
 	/*
@@ -1027,6 +1027,7 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	int ret, min_ret = 0;
 	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
 	bool mshot_finished = true;
+	size_t len, consumed = 0;
 
 	sock = sock_from_file(req->file);
 	if (unlikely(!sock))
@@ -1042,9 +1043,8 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 
 retry_multishot:
 	sel.buf_list = NULL;
+	len = sr->len;
 	if (io_do_buffer_select(req)) {
-		size_t len = sr->len;
-
 		sel = io_buffer_select(req, &len, sr->buf_group, issue_flags);
 		if (!sel.addr)
 			return -ENOBUFS;
@@ -1065,6 +1065,7 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	if (req->flags & REQ_F_APOLL_MULTISHOT) {
 		ret = io_recvmsg_multishot(sock, sr, kmsg, flags,
 					   &mshot_finished);
+		consumed = ret;
 	} else {
 		/* disable partial retry for recvmsg with cmsg attached */
 		if (flags & MSG_WAITALL && !kmsg->msg.msg_controllen)
@@ -1072,6 +1073,15 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 
 		ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg,
 					 kmsg->uaddr, flags);
+		/*
+		 * With MSG_TRUNC, the net layer will return the full size of
+		 * the packet, even if we only filled part of it in the buffers.
+		 * Adjust the returned size to consume only the real part of the
+		 * buffer.
+		 */
+		consumed = ret;
+		if (ret > len)
+			consumed = len;
 	}
 
 	if (ret < min_ret) {
@@ -1098,7 +1108,7 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 		io_kbuf_recycle(req, sel.buf_list, issue_flags);
 
 	sel.val = ret;
-	if (!io_recv_finish(req, kmsg, &sel, mshot_finished, issue_flags))
+	if (!io_recv_finish(req, kmsg, &sel, mshot_finished, issue_flags, consumed))
 		goto retry_multishot;
 
 	return sel.val;
@@ -1186,6 +1196,7 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	struct socket *sock;
 	unsigned flags;
 	int ret, min_ret = 0;
+	size_t consumed = 0, len = 0;
 	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
 	bool mshot_finished;
 
@@ -1215,6 +1226,7 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 
 retry_multishot:
 	sel.buf_list = NULL;
+	len = sr->len;
 	if (io_do_buffer_select(req)) {
 		sel.val = sr->len;
 		ret = io_recv_buf_select(req, kmsg, &sel, issue_flags);
@@ -1222,6 +1234,7 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 			kmsg->msg.msg_inq = -1;
 			goto out_free;
 		}
+		len = ret;
 		sr->buf = NULL;
 	}
 
@@ -1252,6 +1265,17 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	}
 
 	mshot_finished = ret <= 0;
+
+	/*
+	 * With MSG_TRUNC, the net layer will return the full size of
+	 * the packet, even if we only filled part of it in the buffers.
+	 * Adjust the returned size to consume only the real part of the
+	 * buffer.
+	 */
+	consumed = ret;
+	if (ret > len)
+		consumed = len;
+
 	if (ret > 0)
 		ret += sr->done_io;
 	else if (sr->done_io)
@@ -1260,7 +1284,7 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 		io_kbuf_recycle(req, sel.buf_list, issue_flags);
 
 	sel.val = ret;
-	if (!io_recv_finish(req, kmsg, &sel, mshot_finished, issue_flags))
+	if (!io_recv_finish(req, kmsg, &sel, mshot_finished, issue_flags, consumed))
 		goto retry_multishot;
 
 	return sel.val;
-- 
2.55.0