[PATCH] io_uring/net: commit partial buffers on retry

[Jens Axboe <axboe@kernel.dk>]

Ring provided buffers are potentially only valid within the single
execution context in which they were acquired. io_uring deals with this
and invalidates them on retry. But on the networking side, if
MSG_WAITALL is set, or if the socket is of the streaming type and too
little was processed, then it will hang on to the buffer rather than
recycle or commit it. This is problematic for two reasons:

1) If someone unregisters the provided buffer ring before a later retry,
   then the req->buf_list will no longer be valid.

2) If multiple sockers are using the same buffer group, then multiple
   receives can consume the same memory. This can cause data corruption
   in the application, as either receive could land in the same
   userspace buffer.

Fix this by disallowing partial retries from pinning a provided buffer
across multiple executions, if ring provided buffers are used.

Cc: stable@vger.kernel.org
Reported-by: pt x <superman.xpt@gmail.com>
Fixes: c56e022c0a27 ("io_uring: add support for user mapped provided buffer ring")
Signed-off-by: Jens Axboe <axboe@kernel.dk>

---

diff --git a/io_uring/net.c b/io_uring/net.c
index dd96e355982f..d69f2afa4f7a 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -494,6 +494,15 @@ static int io_bundle_nbufs(struct io_async_msghdr *kmsg, int ret)
 	return nbufs;
 }
 
+static int io_net_kbuf_recyle(struct io_kiocb *req,
+			      struct io_async_msghdr *kmsg, int len)
+{
+	req->flags |= REQ_F_BL_NO_RECYCLE;
+	if (req->flags & REQ_F_BUFFERS_COMMIT)
+		io_kbuf_commit(req, req->buf_list, len, io_bundle_nbufs(kmsg, len));
+	return IOU_RETRY;
+}
+
 static inline bool io_send_finish(struct io_kiocb *req, int *ret,
 				  struct io_async_msghdr *kmsg,
 				  unsigned issue_flags)
@@ -562,8 +571,7 @@ int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
 			kmsg->msg.msg_controllen = 0;
 			kmsg->msg.msg_control = NULL;
 			sr->done_io += ret;
-			req->flags |= REQ_F_BL_NO_RECYCLE;
-			return -EAGAIN;
+			return io_net_kbuf_recyle(req, kmsg, ret);
 		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
@@ -674,8 +682,7 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags)
 			sr->len -= ret;
 			sr->buf += ret;
 			sr->done_io += ret;
-			req->flags |= REQ_F_BL_NO_RECYCLE;
-			return -EAGAIN;
+			return io_net_kbuf_recyle(req, kmsg, ret);
 		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
@@ -1071,8 +1078,7 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 		}
 		if (ret > 0 && io_net_retry(sock, flags)) {
 			sr->done_io += ret;
-			req->flags |= REQ_F_BL_NO_RECYCLE;
-			return IOU_RETRY;
+			return io_net_kbuf_recyle(req, kmsg, ret);
 		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
@@ -1218,8 +1224,7 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 			sr->len -= ret;
 			sr->buf += ret;
 			sr->done_io += ret;
-			req->flags |= REQ_F_BL_NO_RECYCLE;
-			return -EAGAIN;
+			return io_net_kbuf_recyle(req, kmsg, ret);
 		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
@@ -1500,8 +1505,7 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags)
 			zc->len -= ret;
 			zc->buf += ret;
 			zc->done_io += ret;
-			req->flags |= REQ_F_BL_NO_RECYCLE;
-			return -EAGAIN;
+			return io_net_kbuf_recyle(req, kmsg, ret);
 		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
@@ -1571,8 +1575,7 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags)
 
 		if (ret > 0 && io_net_retry(sock, flags)) {
 			sr->done_io += ret;
-			req->flags |= REQ_F_BL_NO_RECYCLE;
-			return -EAGAIN;
+			return io_net_kbuf_recyle(req, kmsg, ret);
 		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;

-- 
Jens Axboe