10 files changed, 42 insertions, 18 deletions

diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 535584c00f91..0c34bfabc11f 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -892,13 +892,16 @@ static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
                 struct inet_diag_req_v2 *r, struct nlattr *bc)
 {
         const struct inet_diag_handler *handler;
+        int err = 0;
 
         handler = inet_diag_lock_handler(r->sdiag_protocol);
         if (!IS_ERR(handler))
                 handler->dump(skb, cb, r, bc);
+        else
+                err = PTR_ERR(handler);
         inet_diag_unlock_handler(handler);
 
-        return skb->len;
+        return err ? : skb->len;
 }
 
 static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index 9e0ffaf1d942..a82047282dbb 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -184,7 +184,8 @@ nf_nat_ipv4_out(unsigned int hooknum,
 
                 if ((ct->tuplehash[dir].tuple.src.u3.ip !=
                      ct->tuplehash[!dir].tuple.dst.u3.ip) ||
-                    (ct->tuplehash[dir].tuple.src.u.all !=
+                    (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
+                     ct->tuplehash[dir].tuple.src.u.all !=
                      ct->tuplehash[!dir].tuple.dst.u.all))
                         if (nf_xfrm_me_harder(skb, AF_INET) < 0)
                                 ret = NF_DROP;
@@ -221,6 +222,7 @@ nf_nat_ipv4_local_fn(unsigned int hooknum,
                 }
 #ifdef CONFIG_XFRM
                 else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
+                         ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
                          ct->tuplehash[dir].tuple.dst.u.all !=
                          ct->tuplehash[!dir].tuple.src.u.all)
                         if (nf_xfrm_me_harder(skb, AF_INET) < 0)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 432f4bb77238..a8c651216fa6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1163,8 +1163,12 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
         spin_lock_bh(&fnhe_lock);
 
         if (daddr == fnhe->fnhe_daddr) {
-                struct rtable *orig;
-
+                struct rtable *orig = rcu_dereference(fnhe->fnhe_rth);
+                if (orig && rt_is_expired(orig)) {
+                        fnhe->fnhe_gw = 0;
+                        fnhe->fnhe_pmtu = 0;
+                        fnhe->fnhe_expires = 0;
+                }
                 if (fnhe->fnhe_pmtu) {
                         unsigned long expires = fnhe->fnhe_expires;
                         unsigned long diff = expires - jiffies;
@@ -1181,7 +1185,6 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
                 } else if (!rt->rt_gateway)
                         rt->rt_gateway = daddr;
 
-                orig = rcu_dereference(fnhe->fnhe_rth);
                 rcu_assign_pointer(fnhe->fnhe_rth, rt);
                 if (orig)
                         rt_free(orig);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f32c02e2a543..197c0008503c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -549,14 +549,12 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
                          !tp->urg_data ||
                          before(tp->urg_seq, tp->copied_seq) ||
                          !before(tp->urg_seq, tp->rcv_nxt)) {
-                        struct sk_buff *skb;
 
                         answ = tp->rcv_nxt - tp->copied_seq;
 
-                        /* Subtract 1, if FIN is in queue. */
-                        skb = skb_peek_tail(&sk->sk_receive_queue);
-                        if (answ && skb)
-                                answ -= tcp_hdr(skb)->fin;
+                        /* Subtract 1, if FIN was received */
+                        if (answ && sock_flag(sk, SOCK_DONE))
+                                answ--;
                 } else
                         answ = tp->urg_seq - tp->copied_seq;
                 release_sock(sk);
@@ -2766,6 +2764,8 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
                 info->tcpi_options |= TCPI_OPT_ECN;
         if (tp->ecn_flags & TCP_ECN_SEEN)
                 info->tcpi_options |= TCPI_OPT_ECN_SEEN;
+        if (tp->syn_data_acked)
+                info->tcpi_options |= TCPI_OPT_SYN_DATA;
 
         info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto);
         info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato);
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 813b43a76fec..834857f3c871 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -313,11 +313,13 @@ static void tcp_illinois_info(struct sock *sk, u32 ext,
                         .tcpv_rttcnt = ca->cnt_rtt,
                         .tcpv_minrtt = ca->base_rtt,
                 };
-                u64 t = ca->sum_rtt;
 
-                do_div(t, ca->cnt_rtt);
-                info.tcpv_rtt = t;
+                if (info.tcpv_rttcnt > 0) {
+                        u64 t = ca->sum_rtt;
 
+                        do_div(t, info.tcpv_rttcnt);
+                        info.tcpv_rtt = t;
+                }
                 nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
         }
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 432c36649db3..2c2b13a999ea 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4529,6 +4529,9 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
         struct tcphdr *th;
         bool fragstolen;
 
+        if (size == 0)
+                return 0;
+
         skb = alloc_skb(size + sizeof(*th), sk->sk_allocation);
         if (!skb)
                 goto err;
@@ -5646,6 +5649,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
                 tcp_rearm_rto(sk);
                 return true;
         }
+        tp->syn_data_acked = tp->syn_data;
         return false;
 }
 
@@ -5963,7 +5967,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 
         req = tp->fastopen_rsk;
         if (req != NULL) {
-                BUG_ON(sk->sk_state != TCP_SYN_RECV &&
+                WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
                     sk->sk_state != TCP_FIN_WAIT1);
 
                 if (tcp_check_req(sk, skb, req, NULL, true) == NULL)
@@ -6052,7 +6056,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
                          * ACK we have received, this would have acknowledged
                          * our SYNACK so stop the SYNACK timer.
                          */
-                        if (acceptable && req != NULL) {
+                        if (req != NULL) {
+                                /* Return RST if ack_seq is invalid.
+                                 * Note that RFC793 only says to generate a
+                                 * DUPACK for it but for TCP Fast Open it seems
+                                 * better to treat this case like TCP_SYN_RECV
+                                 * above.
+                                 */
+                                if (!acceptable)
+                                        return 1;
                                 /* We no longer need the request sock. */
                                 reqsk_fastopen_remove(sk, req, false);
                                 tcp_rearm_rto(sk);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ef998b008a57..0c4a64355603 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1461,6 +1461,7 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk,
                 skb_set_owner_r(skb, child);
                 __skb_queue_tail(&child->sk_receive_queue, skb);
                 tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+                tp->syn_data_acked = 1;
         }
         sk->sk_data_ready(sk, 0);
         bh_unlock_sock(child);
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 4c752a6e0bcd..53bc5847bfa8 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -864,7 +864,7 @@ static int parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr,
         }
         a = info->attrs[TCP_METRICS_ATTR_ADDR_IPV6];
         if (a) {
-                if (nla_len(a) != sizeof(sizeof(struct in6_addr)))
+                if (nla_len(a) != sizeof(struct in6_addr))
                         return -EINVAL;
                 addr->family = AF_INET6;
                 memcpy(addr->addr.a6, nla_data(a), sizeof(addr->addr.a6));
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 27536ba16c9d..a7302d974f32 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -510,6 +510,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
                 newtp->rx_opt.mss_clamp = req->mss;
                 TCP_ECN_openreq_child(newtp, req);
                 newtp->fastopen_rsk = NULL;
+                newtp->syn_data_acked = 0;
 
                 TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_PASSIVEOPENS);
         }
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index fc04711e80c8..d47c1b4421a3 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -347,8 +347,8 @@ void tcp_retransmit_timer(struct sock *sk)
                 return;
         }
         if (tp->fastopen_rsk) {
-                BUG_ON(sk->sk_state != TCP_SYN_RECV &&
-                    sk->sk_state != TCP_FIN_WAIT1);
+                WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
+                             sk->sk_state != TCP_FIN_WAIT1);
                 tcp_fastopen_synack_timer(sk);
                 /* Before we receive ACK to our SYN-ACK don't retransmit
                  * anything else (e.g., data or FIN segments).