tcp: Namespace-ify sysctl_tcp_tso_win_divisor

[linux-2.6-microblaze.git] / net / ipv4 / tcp_ipv4.c

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5418ecf..284ff16 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -85,6 +85,8 @@
 #include <crypto/hash.h>
 #include <linux/scatterlist.h>
 
+#include <trace/events/tcp.h>
+
 #ifdef CONFIG_TCP_MD5SIG
 static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
                               __be32 daddr, __be32 saddr, const struct tcphdr *th);
@@ -701,8 +703,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
         * routing might fail in this case. No choice here, if we choose to force
         * input interface, we will misroute in case of asymmetric route.
         */
-       if (sk)
+       if (sk) {
                arg.bound_dev_if = sk->sk_bound_dev_if;
+               trace_tcp_send_reset(sk, skb);
+       }
 
        BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) !=
                     offsetof(struct inet_timewait_sock, tw_bound_dev_if));
@@ -877,7 +881,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 
                err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
                                            ireq->ir_rmt_addr,
-                                           ireq->opt);
+                                           rcu_dereference(ireq->ireq_opt));
                err = net_xmit_eval(err);
        }
 
@@ -889,7 +893,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
  */
 static void tcp_v4_reqsk_destructor(struct request_sock *req)
 {
-       kfree(inet_rsk(req)->opt);
+       kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
 }
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1265,10 +1269,11 @@ static void tcp_v4_init_req(struct request_sock *req,
                            struct sk_buff *skb)
 {
        struct inet_request_sock *ireq = inet_rsk(req);
+       struct net *net = sock_net(sk_listener);
 
        sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
        sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
-       ireq->opt = tcp_v4_save_options(sock_net(sk_listener), skb);
+       RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb));
 }
 
 static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
@@ -1355,10 +1360,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
        sk_daddr_set(newsk, ireq->ir_rmt_addr);
        sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
        newsk->sk_bound_dev_if = ireq->ir_iif;
-       newinet->inet_saddr           = ireq->ir_loc_addr;
-       inet_opt              = ireq->opt;
-       rcu_assign_pointer(newinet->inet_opt, inet_opt);
-       ireq->opt             = NULL;
+       newinet->inet_saddr   = ireq->ir_loc_addr;
+       inet_opt              = rcu_dereference(ireq->ireq_opt);
+       RCU_INIT_POINTER(newinet->inet_opt, inet_opt);
        newinet->mc_index     = inet_iif(skb);
        newinet->mc_ttl       = ip_hdr(skb)->ttl;
        newinet->rcv_tos      = ip_hdr(skb)->tos;
@@ -1403,9 +1407,12 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
        if (__inet_inherit_port(sk, newsk) < 0)
                goto put_and_exit;
        *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
-       if (*own_req)
+       if (likely(*own_req)) {
                tcp_move_syn(newtp, req);
-
+               ireq->ireq_opt = NULL;
+       } else {
+               newinet->inet_opt = NULL;
+       }
        return newsk;
 
 exit_overflow:
@@ -1416,6 +1423,7 @@ exit:
        tcp_listendrop(sk);
        return NULL;
 put_and_exit:
+       newinet->inet_opt = NULL;
        inet_csk_prepare_forced_close(newsk);
        tcp_done(newsk);
        goto exit;
@@ -1779,8 +1787,9 @@ do_time_wait:
                        refcounted = false;
                        goto process;
                }
-               /* Fall through to ACK */
        }
+               /* to ACK */
+               /* fall through */
        case TCP_TW_ACK:
                tcp_v4_timewait_ack(sk, skb);
                break;
@@ -1860,6 +1869,8 @@ void tcp_v4_destroy_sock(struct sock *sk)
 {
        struct tcp_sock *tp = tcp_sk(sk);
 
+       trace_tcp_destroy_sock(sk);
+
        tcp_clear_xmit_timers(sk);
 
        tcp_cleanup_congestion_control(sk);
@@ -1892,6 +1903,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 
        /* If socket is aborted during connect operation */
        tcp_free_fastopen_req(tp);
+       tcp_fastopen_destroy_cipher(sk);
        tcp_saved_syn_free(tp);
 
        sk_sockets_allocated_dec(sk);
@@ -2472,6 +2484,21 @@ static int __net_init tcp_sk_init(struct net *net)
        net->ipv4.sysctl_tcp_sack = 1;
        net->ipv4.sysctl_tcp_window_scaling = 1;
        net->ipv4.sysctl_tcp_timestamps = 1;
+       net->ipv4.sysctl_tcp_early_retrans = 3;
+       net->ipv4.sysctl_tcp_recovery = TCP_RACK_LOSS_DETECTION;
+       net->ipv4.sysctl_tcp_slow_start_after_idle = 1; /* By default, RFC2861 behavior.  */
+       net->ipv4.sysctl_tcp_retrans_collapse = 1;
+       net->ipv4.sysctl_tcp_max_reordering = 300;
+       net->ipv4.sysctl_tcp_dsack = 1;
+       net->ipv4.sysctl_tcp_app_win = 31;
+       net->ipv4.sysctl_tcp_adv_win_scale = 1;
+       net->ipv4.sysctl_tcp_frto = 2;
+       net->ipv4.sysctl_tcp_moderate_rcvbuf = 1;
+       /* This limits the percentage of the congestion window which we
+        * will allow a single TSO frame to consume.  Building TSO frames
+        * which are too large can cause TCP streams to be bursty.
+        */
+       net->ipv4.sysctl_tcp_tso_win_divisor = 3;
 
        net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
        spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);