Merge branch 'bugzilla-21212' into release

[firefly-linux-kernel-4.4.55.git] / net / ipv4 / tcp_output.c

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index de3bd84585881f99f8a23eb28fa9f380516d087c..61c2463e2753f809c12f31967e7fa189e41e1f54 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -224,24 +224,17 @@ 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 value enough for senders, following RFC5681. */
        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 = rfc3390_bytes_to_packets(mss);
+
                /* 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 +385,30 @@ 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.
@@ -1376,9 +1372,9 @@ 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 +1445,10 @@ 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 +1515,7 @@ 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 +1547,14 @@ 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 {
@@ -2429,6 +2427,12 @@ 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),
@@ -2555,6 +2559,11 @@ static void tcp_connect_init(struct sock *sk)
 
        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,