If a protocol doesn't support zerocopy it will silently fall back to copying. This type of behaviour has always been a source of troubles so it's better to fail such requests instead. Cc: <stable@xxxxxxxxxxxxxxx> # 6.0 Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx> --- io_uring/net.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/io_uring/net.c b/io_uring/net.c index 8c7226b5bf41..26ff3675214d 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1056,6 +1056,8 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags) sock = sock_from_file(req->file); if (unlikely(!sock)) return -ENOTSOCK; + if (!test_bit(SOCK_SUPPORT_ZC, &sock->flags)) + return -EOPNOTSUPP; msg.msg_name = NULL; msg.msg_control = NULL; -- 2.38.0
