tipc: keep the skb in rcv queue until the whole data is read

Currently, when userspace reads a datagram with a buffer that is
smaller than this datagram, the data will be truncated and only
part of it can be received by users. It doesn't seem right that
users don't know the datagram size and have to use a huge buffer
to read it to avoid the truncation.

This patch to fix it by keeping the skb in rcv queue until the
whole data is read by users. Only the last msg of the datagram
will be marked with MSG_EOR, just as TCP/SCTP does.

Note that this will work as above only when MSG_EOR is set in the
flags parameter of recvmsg(), so that it won't break any old user
applications.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 34a97ea36cc854f0ac57fa1c6732dbed2c95af64..9b0b311c7ec17d797467da077115300f2909d9a7 100644 (file)
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1880,6 +1880,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
        bool connected = !tipc_sk_type_connectionless(sk);
        struct tipc_sock *tsk = tipc_sk(sk);
        int rc, err, hlen, dlen, copy;
+       struct tipc_skb_cb *skb_cb;
        struct sk_buff_head xmitq;
        struct tipc_msg *hdr;
        struct sk_buff *skb;
@@ -1903,6 +1904,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
                if (unlikely(rc))
                        goto exit;
                skb = skb_peek(&sk->sk_receive_queue);
+               skb_cb = TIPC_SKB_CB(skb);
                hdr = buf_msg(skb);
                dlen = msg_data_sz(hdr);
                hlen = msg_hdr_sz(hdr);
@@ -1922,18 +1924,33 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
 
        /* Capture data if non-error msg, otherwise just set return value */
        if (likely(!err)) {
-               copy = min_t(int, dlen, buflen);
-               if (unlikely(copy != dlen))
-                       m->msg_flags |= MSG_TRUNC;
-               rc = skb_copy_datagram_msg(skb, hlen, m, copy);
+               int offset = skb_cb->bytes_read;
+
+               copy = min_t(int, dlen - offset, buflen);
+               rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy);
+               if (unlikely(rc))
+                       goto exit;
+               if (unlikely(offset + copy < dlen)) {
+                       if (flags & MSG_EOR) {
+                               if (!(flags & MSG_PEEK))
+                                       skb_cb->bytes_read = offset + copy;
+                       } else {
+                               m->msg_flags |= MSG_TRUNC;
+                               skb_cb->bytes_read = 0;
+                       }
+               } else {
+                       if (flags & MSG_EOR)
+                               m->msg_flags |= MSG_EOR;
+                       skb_cb->bytes_read = 0;
+               }
        } else {
                copy = 0;
                rc = 0;
-               if (err != TIPC_CONN_SHUTDOWN && connected && !m->msg_control)
+               if (err != TIPC_CONN_SHUTDOWN && connected && !m->msg_control) {
                        rc = -ECONNRESET;
+                       goto exit;
+               }
        }
-       if (unlikely(rc))
-               goto exit;
 
        /* Mark message as group event if applicable */
        if (unlikely(grp_evt)) {
@@ -1956,9 +1973,10 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
                tipc_node_distr_xmit(sock_net(sk), &xmitq);
        }
 
-       tsk_advance_rx_queue(sk);
+       if (!skb_cb->bytes_read)
+               tsk_advance_rx_queue(sk);
 
-       if (likely(!connected))
+       if (likely(!connected) || skb_cb->bytes_read)
                goto exit;
 
        /* Send connection flow control advertisement when applicable */