tcp: introduce tcp_under_memory_pressure()

[mirror_ubuntu-bionic-kernel.git] / net / ipv4 / tcp_output.c

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a369e8a70b2c775bfee94d7f329ee892c2cdc895..08c2cc40b26d65227eccaf3b5a068c16cef62fa1 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2392,7 +2392,7 @@ u32 __tcp_select_window(struct sock *sk)
        if (free_space < (full_space >> 1)) {
                icsk->icsk_ack.quick = 0;
 
-               if (sk_under_memory_pressure(sk))
+               if (tcp_under_memory_pressure(sk))
                        tp->rcv_ssthresh = min(tp->rcv_ssthresh,
                                               4U * tp->advmss);
 
@@ -2816,8 +2816,10 @@ begin_fwd:
  * connection tear down and (memory) recovery.
  * Otherwise tcp_send_fin() could be tempted to either delay FIN
  * or even be forced to close flow without any FIN.
+ * In general, we want to allow one skb per socket to avoid hangs
+ * with edge trigger epoll()
  */
-static void sk_forced_wmem_schedule(struct sock *sk, int size)
+void sk_forced_mem_schedule(struct sock *sk, int size)
 {
        int amt, status;
 
@@ -2841,7 +2843,7 @@ void tcp_send_fin(struct sock *sk)
         * Note: in the latter case, FIN packet will be sent after a timeout,
         * as TCP stack thinks it has already been transmitted.
         */
-       if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+       if (tskb && (tcp_send_head(sk) || tcp_under_memory_pressure(sk))) {
 coalesce:
                TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
                TCP_SKB_CB(tskb)->end_seq++;
@@ -2864,7 +2866,7 @@ coalesce:
                        return;
                }
                skb_reserve(skb, MAX_TCP_HEADER);
-               sk_forced_wmem_schedule(sk, skb->truesize);
+               sk_forced_mem_schedule(sk, skb->truesize);
                /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
                tcp_init_nondata_skb(skb, tp->write_seq,
                                     TCPHDR_ACK | TCPHDR_FIN);
@@ -3382,7 +3384,7 @@ EXPORT_SYMBOL_GPL(tcp_send_ack);
  * one is with SEG.SEQ=SND.UNA to deliver urgent pointer, another is
  * out-of-date with SND.UNA-1 to probe window.
  */
-static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
+static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib)
 {
        struct tcp_sock *tp = tcp_sk(sk);
        struct sk_buff *skb;
@@ -3400,6 +3402,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
         */
        tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK);
        skb_mstamp_get(&skb->skb_mstamp);
+       NET_INC_STATS_BH(sock_net(sk), mib);
        return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
 }
 
@@ -3407,12 +3410,12 @@ void tcp_send_window_probe(struct sock *sk)
 {
        if (sk->sk_state == TCP_ESTABLISHED) {
                tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
-               tcp_xmit_probe_skb(sk, 0);
+               tcp_xmit_probe_skb(sk, 0, LINUX_MIB_TCPWINPROBE);
        }
 }
 
 /* Initiate keepalive or window probe from timer. */
-int tcp_write_wakeup(struct sock *sk)
+int tcp_write_wakeup(struct sock *sk, int mib)
 {
        struct tcp_sock *tp = tcp_sk(sk);
        struct sk_buff *skb;
@@ -3449,8 +3452,8 @@ int tcp_write_wakeup(struct sock *sk)
                return err;
        } else {
                if (between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF))
-                       tcp_xmit_probe_skb(sk, 1);
-               return tcp_xmit_probe_skb(sk, 0);
+                       tcp_xmit_probe_skb(sk, 1, mib);
+               return tcp_xmit_probe_skb(sk, 0, mib);
        }
 }
 
@@ -3464,7 +3467,7 @@ void tcp_send_probe0(struct sock *sk)
        unsigned long probe_max;
        int err;
 
-       err = tcp_write_wakeup(sk);
+       err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE);
 
        if (tp->packets_out || !tcp_send_head(sk)) {
                /* Cancel probe timer, if it is not required. */
@@ -3490,7 +3493,7 @@ void tcp_send_probe0(struct sock *sk)
                probe_max = TCP_RESOURCE_PROBE_INTERVAL;
        }
        inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-                                 inet_csk_rto_backoff(icsk, probe_max),
+                                 tcp_probe0_when(sk, probe_max),
                                  TCP_RTO_MAX);
 }