1 files changed, 49 insertions, 94 deletions

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b78aac30c49..ecd44b0c45f 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -32,6 +32,17 @@ int sysctl_tcp_retries2 __read_mostly = TCP_RETR2;
 int sysctl_tcp_orphan_retries __read_mostly;
 int sysctl_tcp_thin_linear_timeouts __read_mostly;
 
+static void tcp_write_timer(unsigned long);
+static void tcp_delack_timer(unsigned long);
+static void tcp_keepalive_timer (unsigned long data);
+
+void tcp_init_xmit_timers(struct sock *sk)
+{
+        inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer,
+                                  &tcp_keepalive_timer);
+}
+EXPORT_SYMBOL(tcp_init_xmit_timers);
+
 static void tcp_write_err(struct sock *sk)
 {
         sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT;
@@ -66,7 +77,10 @@ static int tcp_out_of_resources(struct sock *sk, int do_reset)
         if (sk->sk_err_soft)
                 shift++;
 
-        if (tcp_check_oom(sk, shift)) {
+        if (tcp_too_many_orphans(sk, shift)) {
+                if (net_ratelimit())
+                        printk(KERN_INFO "Out of socket memory\n");
+
                 /* Catch exceptional cases, when connection requires reset.
                  *      1. Last segment was sent recently. */
                 if ((s32)(tcp_time_stamp - tp->lsndtime) <= TCP_TIMEWAIT_LEN ||
@@ -157,13 +171,13 @@ static int tcp_write_timeout(struct sock *sk)
 {
         struct inet_connection_sock *icsk = inet_csk(sk);
         int retry_until;
-        bool do_reset, syn_set = false;
+        bool do_reset, syn_set = 0;
 
         if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
                 if (icsk->icsk_retransmits)
                         dst_negative_advice(sk);
                 retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
-                syn_set = true;
+                syn_set = 1;
         } else {
                 if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
                         /* Black hole detection */
@@ -194,11 +208,21 @@ static int tcp_write_timeout(struct sock *sk)
         return 0;
 }
 
-void tcp_delack_timer_handler(struct sock *sk)
+static void tcp_delack_timer(unsigned long data)
 {
+        struct sock *sk = (struct sock *)data;
         struct tcp_sock *tp = tcp_sk(sk);
         struct inet_connection_sock *icsk = inet_csk(sk);
 
+        bh_lock_sock(sk);
+        if (sock_owned_by_user(sk)) {
+                /* Try again later. */
+                icsk->icsk_ack.blocked = 1;
+                NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
+                sk_reset_timer(sk, &icsk->icsk_delack_timer, jiffies + TCP_DELACK_MIN);
+                goto out_unlock;
+        }
+
         sk_mem_reclaim_partial(sk);
 
         if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
@@ -237,24 +261,9 @@ void tcp_delack_timer_handler(struct sock *sk)
         }
 
 out:
-        if (sk_under_memory_pressure(sk))
+        if (tcp_memory_pressure)
                 sk_mem_reclaim(sk);
-}
-
-static void tcp_delack_timer(unsigned long data)
-{
-        struct sock *sk = (struct sock *)data;
-
-        bh_lock_sock(sk);
-        if (!sock_owned_by_user(sk)) {
-                tcp_delack_timer_handler(sk);
-        } else {
-                inet_csk(sk)->icsk_ack.blocked = 1;
-                NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
-                /* deleguate our work to tcp_release_cb() */
-                if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags))
-                        sock_hold(sk);
-        }
+out_unlock:
         bh_unlock_sock(sk);
         sock_put(sk);
 }
@@ -305,35 +314,6 @@ static void tcp_probe_timer(struct sock *sk)
 }
 
 /*
- *      Timer for Fast Open socket to retransmit SYNACK. Note that the
- *      sk here is the child socket, not the parent (listener) socket.
- */
-static void tcp_fastopen_synack_timer(struct sock *sk)
-{
-        struct inet_connection_sock *icsk = inet_csk(sk);
-        int max_retries = icsk->icsk_syn_retries ? :
-            sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
-        struct request_sock *req;
-
-        req = tcp_sk(sk)->fastopen_rsk;
-        req->rsk_ops->syn_ack_timeout(sk, req);
-
-        if (req->num_timeout >= max_retries) {
-                tcp_write_err(sk);
-                return;
-        }
-        /* XXX (TFO) - Unlike regular SYN-ACK retransmit, we ignore error
-         * returned from rtx_syn_ack() to make it more persistent like
-         * regular retransmit because if the child socket has been accepted
-         * it's not good to give up too easily.
-         */
-        inet_rtx_syn_ack(sk, req);
-        req->num_timeout++;
-        inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-                          TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
-}
-
-/*
  *      The TCP retransmit timer.
  */
 
@@ -342,19 +322,6 @@ void tcp_retransmit_timer(struct sock *sk)
         struct tcp_sock *tp = tcp_sk(sk);
         struct inet_connection_sock *icsk = inet_csk(sk);
 
-        if (tp->early_retrans_delayed) {
-                tcp_resume_early_retransmit(sk);
-                return;
-        }
-        if (tp->fastopen_rsk) {
-                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).
-                 */
-                return;
-        }
         if (!tp->packets_out)
                 goto out;
 
@@ -367,22 +334,22 @@ void tcp_retransmit_timer(struct sock *sk)
                  * connection. If the socket is an orphan, time it out,
                  * we cannot allow such beasts to hang infinitely.
                  */
+#ifdef TCP_DEBUG
                 struct inet_sock *inet = inet_sk(sk);
                 if (sk->sk_family == AF_INET) {
-                        LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"),
-                                       &inet->inet_daddr,
-                                       ntohs(inet->inet_dport), inet->inet_num,
-                                       tp->snd_una, tp->snd_nxt);
+                        LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
+                               &inet->inet_daddr, ntohs(inet->inet_dport),
+                               inet->inet_num, tp->snd_una, tp->snd_nxt);
                 }
-#if IS_ENABLED(CONFIG_IPV6)
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
                 else if (sk->sk_family == AF_INET6) {
                         struct ipv6_pinfo *np = inet6_sk(sk);
-                        LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"),
-                                       &np->daddr,
-                                       ntohs(inet->inet_dport), inet->inet_num,
-                                       tp->snd_una, tp->snd_nxt);
+                        LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
+                               &np->daddr, ntohs(inet->inet_dport),
+                               inet->inet_num, tp->snd_una, tp->snd_nxt);
                 }
 #endif
+#endif
                 if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) {
                         tcp_write_err(sk);
                         goto out;
@@ -481,11 +448,19 @@ out_reset_timer:
 out:;
 }
 
-void tcp_write_timer_handler(struct sock *sk)
+static void tcp_write_timer(unsigned long data)
 {
+        struct sock *sk = (struct sock *)data;
         struct inet_connection_sock *icsk = inet_csk(sk);
         int event;
 
+        bh_lock_sock(sk);
+        if (sock_owned_by_user(sk)) {
+                /* Try again later */
+                sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + (HZ / 20));
+                goto out_unlock;
+        }
+
         if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending)
                 goto out;
 
@@ -508,20 +483,7 @@ void tcp_write_timer_handler(struct sock *sk)
 
 out:
         sk_mem_reclaim(sk);
-}
-
-static void tcp_write_timer(unsigned long data)
-{
-        struct sock *sk = (struct sock *)data;
-
-        bh_lock_sock(sk);
-        if (!sock_owned_by_user(sk)) {
-                tcp_write_timer_handler(sk);
-        } else {
-                /* deleguate our work to tcp_release_cb() */
-                if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags))
-                        sock_hold(sk);
-        }
+out_unlock:
         bh_unlock_sock(sk);
         sock_put(sk);
 }
@@ -638,10 +600,3 @@ out:
         bh_unlock_sock(sk);
         sock_put(sk);
 }
-
-void tcp_init_xmit_timers(struct sock *sk)
-{
-        inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer,
-                                  &tcp_keepalive_timer);
-}
-EXPORT_SYMBOL(tcp_init_xmit_timers);