1 files changed, 65 insertions, 41 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index de3bd8458588..dfa5beb0c1c8 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -55,7 +55,7 @@ int sysctl_tcp_workaround_signed_windows __read_mostly = 0;
 int sysctl_tcp_tso_win_divisor __read_mostly = 3;
 
 int sysctl_tcp_mtu_probing __read_mostly = 0;
-int sysctl_tcp_base_mss __read_mostly = 512;
+int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS;
 
 /* By default, RFC2861 behavior.  */
 int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
@@ -119,9 +119,13 @@ static __u16 tcp_advertise_mss(struct sock *sk)
         struct dst_entry *dst = __sk_dst_get(sk);
         int mss = tp->advmss;
 
-        if (dst && dst_metric(dst, RTAX_ADVMSS) < mss) {
-                mss = dst_metric(dst, RTAX_ADVMSS);
-                tp->advmss = mss;
+        if (dst) {
+                unsigned int metric = dst_metric_advmss(dst);
+
+                if (metric < mss) {
+                        mss = metric;
+                        tp->advmss = mss;
+                }
         }
 
         return (__u16)mss;
@@ -224,24 +228,22 @@ void tcp_select_initial_window(int __space, __u32 mss,
                 }
         }
 
-        /* Set initial window to value enough for senders,
-         * following RFC2414. Senders, not following this RFC,
-         * will be satisfied with 2.
+        /* Set initial window to a value enough for senders starting with
+         * initial congestion window of TCP_DEFAULT_INIT_RCVWND. Place
+         * a limit on the initial window when mss is larger than 1460.
          */
         if (mss > (1 << *rcv_wscale)) {
-                int init_cwnd = 4;
-                if (mss > 1460 * 3)
-                        init_cwnd = 2;
-                else if (mss > 1460)
-                        init_cwnd = 3;
+                int init_cwnd = TCP_DEFAULT_INIT_RCVWND;
+                if (mss > 1460)
+                        init_cwnd =
+                        max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2);
                 /* when initializing use the value from init_rcv_wnd
                  * rather than the default from above
                  */
-                if (init_rcv_wnd &&
-                    (*rcv_wnd > init_rcv_wnd * mss))
-                        *rcv_wnd = init_rcv_wnd * mss;
-                else if (*rcv_wnd > init_cwnd * mss)
-                        *rcv_wnd = init_cwnd * mss;
+                if (init_rcv_wnd)
+                        *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
+                else
+                        *rcv_wnd = min(*rcv_wnd, init_cwnd * mss);
         }
 
         /* Set the clamp no higher than max representable value */
@@ -392,27 +394,30 @@ struct tcp_out_options {
  */
 static u8 tcp_cookie_size_check(u8 desired)
 {
-        if (desired > 0) {
+        int cookie_size;
+
+        if (desired > 0)
                 /* previously specified */
                 return desired;
-        }
-        if (sysctl_tcp_cookie_size <= 0) {
+
+        cookie_size = ACCESS_ONCE(sysctl_tcp_cookie_size);
+        if (cookie_size <= 0)
                 /* no default specified */
                 return 0;
-        }
-        if (sysctl_tcp_cookie_size <= TCP_COOKIE_MIN) {
+
+        if (cookie_size <= TCP_COOKIE_MIN)
                 /* value too small, specify minimum */
                 return TCP_COOKIE_MIN;
-        }
-        if (sysctl_tcp_cookie_size >= TCP_COOKIE_MAX) {
+
+        if (cookie_size >= TCP_COOKIE_MAX)
                 /* value too large, specify maximum */
                 return TCP_COOKIE_MAX;
-        }
-        if (0x1 & sysctl_tcp_cookie_size) {
+
+        if (cookie_size & 1)
                 /* 8-bit multiple, illegal, fix it */
-                return (u8)(sysctl_tcp_cookie_size + 0x1);
-        }
-        return (u8)sysctl_tcp_cookie_size;
+                cookie_size++;
+
+        return (u8)cookie_size;
 }
 
 /* Write previously computed TCP options to the packet.
@@ -828,8 +833,11 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
                                                            &md5);
         tcp_header_size = tcp_options_size + sizeof(struct tcphdr);
 
-        if (tcp_packets_in_flight(tp) == 0)
+        if (tcp_packets_in_flight(tp) == 0) {
                 tcp_ca_event(sk, CA_EVENT_TX_START);
+                skb->ooo_okay = 1;
+        } else
+                skb->ooo_okay = 0;
 
         skb_push(skb, tcp_header_size);
         skb_reset_transport_header(skb);
@@ -1342,7 +1350,7 @@ static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp,
         return 0;
 }
 
-/* Intialize TSO state of a skb.
+/* Initialize TSO state of a skb.
  * This must be invoked the first time we consider transmitting
  * SKB onto the wire.
  */
@@ -1376,9 +1384,9 @@ static inline int tcp_nagle_check(const struct tcp_sock *tp,
                                   const struct sk_buff *skb,
                                   unsigned mss_now, int nonagle)
 {
-        return (skb->len < mss_now &&
+        return skb->len < mss_now &&
                 ((nonagle & TCP_NAGLE_CORK) ||
-                 (!nonagle && tp->packets_out && tcp_minshall_check(tp))));
+                 (!nonagle && tp->packets_out && tcp_minshall_check(tp)));
 }
 
 /* Return non-zero if the Nagle test allows this packet to be
@@ -1449,10 +1457,10 @@ int tcp_may_send_now(struct sock *sk)
         struct tcp_sock *tp = tcp_sk(sk);
         struct sk_buff *skb = tcp_send_head(sk);
 
-        return (skb &&
+        return skb &&
                 tcp_snd_test(sk, skb, tcp_current_mss(sk),
                              (tcp_skb_is_last(sk, skb) ?
-                              tp->nonagle : TCP_NAGLE_PUSH)));
+                              tp->nonagle : TCP_NAGLE_PUSH));
 }
 
 /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
@@ -1519,6 +1527,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
         struct tcp_sock *tp = tcp_sk(sk);
         const struct inet_connection_sock *icsk = inet_csk(sk);
         u32 send_win, cong_win, limit, in_flight;
+        int win_divisor;
 
         if (TCP_SKB_CB(skb)->flags & TCPHDR_FIN)
                 goto send_now;
@@ -1550,13 +1559,14 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
         if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len))
                 goto send_now;
 
-        if (sysctl_tcp_tso_win_divisor) {
+        win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor);
+        if (win_divisor) {
                 u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
 
                 /* If at least some fraction of a window is available,
                  * just use it.
                  */
-                chunk /= sysctl_tcp_tso_win_divisor;
+                chunk /= win_divisor;
                 if (limit >= chunk)
                         goto send_now;
         } else {
@@ -2152,7 +2162,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
                 if (!tp->retrans_stamp)
                         tp->retrans_stamp = TCP_SKB_CB(skb)->when;
 
-                tp->undo_retrans++;
+                tp->undo_retrans += tcp_skb_pcount(skb);
 
                 /* snd_nxt is stored to detect loss of retransmitted segment,
                  * see tcp_input.c tcp_sacktag_write_queue().
@@ -2421,7 +2431,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 
         skb_dst_set(skb, dst_clone(dst));
 
-        mss = dst_metric(dst, RTAX_ADVMSS);
+        mss = dst_metric_advmss(dst);
         if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
                 mss = tp->rx_opt.user_mss;
 
@@ -2429,6 +2439,12 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
                 __u8 rcv_wscale;
                 /* Set this up on the first call only */
                 req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
+
+                /* limit the window selection if the user enforce a smaller rx buffer */
+                if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+                    (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0))
+                        req->window_clamp = tcp_full_space(sk);
+
                 /* tcp_full_space because it is guaranteed to be the first packet */
                 tcp_select_initial_window(tcp_full_space(sk),
                         mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
@@ -2549,12 +2565,17 @@ static void tcp_connect_init(struct sock *sk)
 
         if (!tp->window_clamp)
                 tp->window_clamp = dst_metric(dst, RTAX_WINDOW);
-        tp->advmss = dst_metric(dst, RTAX_ADVMSS);
+        tp->advmss = dst_metric_advmss(dst);
         if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->advmss)
                 tp->advmss = tp->rx_opt.user_mss;
 
         tcp_initialize_rcv_mss(sk);
 
+        /* limit the window selection if the user enforce a smaller rx buffer */
+        if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+            (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0))
+                tp->window_clamp = tcp_full_space(sk);
+
         tcp_select_initial_window(tcp_full_space(sk),
                                   tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
                                   &tp->rcv_wnd,
@@ -2587,6 +2608,7 @@ int tcp_connect(struct sock *sk)
 {
         struct tcp_sock *tp = tcp_sk(sk);
         struct sk_buff *buff;
+        int err;
 
         tcp_connect_init(sk);
 
@@ -2609,7 +2631,9 @@ int tcp_connect(struct sock *sk)
         sk->sk_wmem_queued += buff->truesize;
         sk_mem_charge(sk, buff->truesize);
         tp->packets_out += tcp_skb_pcount(buff);
-        tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
+        err = tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
+        if (err == -ECONNREFUSED)
+                return err;
 
         /* We change tp->snd_nxt after the tcp_transmit_skb() call
          * in order to make this packet get counted in tcpOutSegs.