1 files changed, 47 insertions, 33 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2259114c7242..9a89b8deafae 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -84,7 +84,6 @@
 #include <crypto/hash.h>
 #include <linux/scatterlist.h>
 
-int sysctl_tcp_tw_reuse __read_mostly;
 int sysctl_tcp_low_latency __read_mostly;
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -95,12 +94,12 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 struct inet_hashinfo tcp_hashinfo;
 EXPORT_SYMBOL(tcp_hashinfo);
 
-static  __u32 tcp_v4_init_sequence(const struct sk_buff *skb)
+static u32 tcp_v4_init_sequence(const struct sk_buff *skb, u32 *tsoff)
 {
 	return secure_tcp_sequence_number(ip_hdr(skb)->daddr,
 					  ip_hdr(skb)->saddr,
 					  tcp_hdr(skb)->dest,
-					  tcp_hdr(skb)->source);
+					  tcp_hdr(skb)->source, tsoff);
 }
 
 int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
@@ -120,7 +119,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	   and use initial timestamp retrieved from peer table.
 	 */
 	if (tcptw->tw_ts_recent_stamp &&
-	    (!twp || (sysctl_tcp_tw_reuse &&
+	    (!twp || (sock_net(sk)->ipv4.sysctl_tcp_tw_reuse &&
 			     get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
 		tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
 		if (tp->write_seq == 0)
@@ -146,7 +145,9 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	struct flowi4 *fl4;
 	struct rtable *rt;
 	int err;
+	u32 seq;
 	struct ip_options_rcu *inet_opt;
+	struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
 
 	if (addr_len < sizeof(struct sockaddr_in))
 		return -EINVAL;
@@ -197,7 +198,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 			tp->write_seq	   = 0;
 	}
 
-	if (tcp_death_row.sysctl_tw_recycle &&
+	if (tcp_death_row->sysctl_tw_recycle &&
 	    !tp->rx_opt.ts_recent_stamp && fl4->daddr == daddr)
 		tcp_fetch_timewait_stamp(sk, &rt->dst);
 
@@ -216,7 +217,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	 * complete initialization after this.
 	 */
 	tcp_set_state(sk, TCP_SYN_SENT);
-	err = inet_hash_connect(&tcp_death_row, sk);
+	err = inet_hash_connect(tcp_death_row, sk);
 	if (err)
 		goto failure;
 
@@ -232,18 +233,27 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	/* OK, now commit destination to socket.  */
 	sk->sk_gso_type = SKB_GSO_TCPV4;
 	sk_setup_caps(sk, &rt->dst);
+	rt = NULL;
 
-	if (!tp->write_seq && likely(!tp->repair))
-		tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr,
-							   inet->inet_daddr,
-							   inet->inet_sport,
-							   usin->sin_port);
+	if (likely(!tp->repair)) {
+		seq = secure_tcp_sequence_number(inet->inet_saddr,
+						 inet->inet_daddr,
+						 inet->inet_sport,
+						 usin->sin_port,
+						 &tp->tsoffset);
+		if (!tp->write_seq)
+			tp->write_seq = seq;
+	}
 
 	inet->inet_id = tp->write_seq ^ jiffies;
 
+	if (tcp_fastopen_defer_connect(sk, &err))
+		return err;
+	if (err)
+		goto failure;
+
 	err = tcp_connect(sk);
 
-	rt = NULL;
 	if (err)
 		goto failure;
 
@@ -442,7 +452,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 			if (!sock_owned_by_user(sk)) {
 				tcp_v4_mtu_reduced(sk);
 			} else {
-				if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags))
+				if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &sk->sk_tsq_flags))
 					sock_hold(sk);
 			}
 			goto out;
@@ -691,6 +701,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 		     offsetof(struct inet_timewait_sock, tw_bound_dev_if));
 
 	arg.tos = ip_hdr(skb)->tos;
+	arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
 	local_bh_disable();
 	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
 			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
@@ -711,7 +722,7 @@ out:
    outside socket context is ugly, certainly. What can I do?
  */
 
-static void tcp_v4_send_ack(struct net *net,
+static void tcp_v4_send_ack(const struct sock *sk,
 			    struct sk_buff *skb, u32 seq, u32 ack,
 			    u32 win, u32 tsval, u32 tsecr, int oif,
 			    struct tcp_md5sig_key *key,
@@ -726,6 +737,7 @@ static void tcp_v4_send_ack(struct net *net,
 #endif
 			];
 	} rep;
+	struct net *net = sock_net(sk);
 	struct ip_reply_arg arg;
 
 	memset(&rep.th, 0, sizeof(struct tcphdr));
@@ -775,6 +787,7 @@ static void tcp_v4_send_ack(struct net *net,
 	if (oif)
 		arg.bound_dev_if = oif;
 	arg.tos = tos;
+	arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
 	local_bh_disable();
 	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
 			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
@@ -790,7 +803,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	struct inet_timewait_sock *tw = inet_twsk(sk);
 	struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
 
-	tcp_v4_send_ack(sock_net(sk), skb,
+	tcp_v4_send_ack(sk, skb,
 			tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_time_stamp + tcptw->tw_ts_offset,
@@ -818,10 +831,10 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 	 * exception of <SYN> segments, MUST be right-shifted by
 	 * Rcv.Wind.Shift bits:
 	 */
-	tcp_v4_send_ack(sock_net(sk), skb, seq,
+	tcp_v4_send_ack(sk, skb, seq,
 			tcp_rsk(req)->rcv_nxt,
 			req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
-			tcp_time_stamp,
+			tcp_time_stamp + tcp_rsk(req)->ts_off,
 			req->ts_recent,
 			0,
 			tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
@@ -1315,10 +1328,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst_mtu(dst));
-	newtp->advmss = dst_metric_advmss(dst);
-	if (tcp_sk(sk)->rx_opt.user_mss &&
-	    tcp_sk(sk)->rx_opt.user_mss < newtp->advmss)
-		newtp->advmss = tcp_sk(sk)->rx_opt.user_mss;
+	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);
 
@@ -1552,8 +1562,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 	 * It has been noticed pure SACK packets were sometimes dropped
 	 * (if cooked by drivers without copybreak feature).
 	 */
-	if (!skb->data_len)
-		skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
+	skb_condense(skb);
 
 	if (unlikely(sk_add_backlog(sk, skb, limit))) {
 		bh_unlock_sock(sk);
@@ -1813,7 +1822,6 @@ const struct inet_connection_sock_af_ops ipv4_specific = {
 	.getsockopt	   = ip_getsockopt,
 	.addr2sockaddr	   = inet_csk_addr2sockaddr,
 	.sockaddr_len	   = sizeof(struct sockaddr_in),
-	.bind_conflict	   = inet_csk_bind_conflict,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ip_setsockopt,
 	.compat_getsockopt = compat_ip_getsockopt,
@@ -1884,9 +1892,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	tcp_free_fastopen_req(tp);
 	tcp_saved_syn_free(tp);
 
-	local_bh_disable();
 	sk_sockets_allocated_dec(sk);
-	local_bh_enable();
 }
 EXPORT_SYMBOL(tcp_v4_destroy_sock);
 
@@ -1908,7 +1914,7 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 	if (!sk) {
 get_head:
 		ilb = &tcp_hashinfo.listening_hash[st->bucket];
-		spin_lock_bh(&ilb->lock);
+		spin_lock(&ilb->lock);
 		sk = sk_head(&ilb->head);
 		st->offset = 0;
 		goto get_sk;
@@ -1925,7 +1931,7 @@ get_sk:
 		if (sk->sk_family == st->family)
 			return sk;
 	}
-	spin_unlock_bh(&ilb->lock);
+	spin_unlock(&ilb->lock);
 	st->offset = 0;
 	if (++st->bucket < INET_LHTABLE_SIZE)
 		goto get_head;
@@ -2133,7 +2139,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v)
 	switch (st->state) {
 	case TCP_SEQ_STATE_LISTENING:
 		if (v != SEQ_START_TOKEN)
-			spin_unlock_bh(&tcp_hashinfo.listening_hash[st->bucket].lock);
+			spin_unlock(&tcp_hashinfo.listening_hash[st->bucket].lock);
 		break;
 	case TCP_SEQ_STATE_ESTABLISHED:
 		if (v)
@@ -2225,7 +2231,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 	int state;
 
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
-	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
 		timer_expires	= icsk->icsk_timeout;
@@ -2372,6 +2378,7 @@ struct proto tcp_prot = {
 	.shutdown		= tcp_shutdown,
 	.setsockopt		= tcp_setsockopt,
 	.getsockopt		= tcp_getsockopt,
+	.keepalive		= tcp_set_keepalive,
 	.recvmsg		= tcp_recvmsg,
 	.sendmsg		= tcp_sendmsg,
 	.sendpage		= tcp_sendpage,
@@ -2415,7 +2422,7 @@ static void __net_exit tcp_sk_exit(struct net *net)
 
 static int __net_init tcp_sk_init(struct net *net)
 {
-	int res, cpu;
+	int res, cpu, cnt;
 
 	net->ipv4.tcp_sk = alloc_percpu(struct sock *);
 	if (!net->ipv4.tcp_sk)
@@ -2452,6 +2459,14 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_orphan_retries = 0;
 	net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
 	net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
+	net->ipv4.sysctl_tcp_tw_reuse = 0;
+
+	cnt = tcp_hashinfo.ehash_mask + 1;
+	net->ipv4.tcp_death_row.sysctl_tw_recycle = 0;
+	net->ipv4.tcp_death_row.sysctl_max_tw_buckets = (cnt + 1) / 2;
+	net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;
+
+	net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256);
 
 	return 0;
 fail:
@@ -2462,7 +2477,7 @@ fail:
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
 {
-	inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET);
+	inet_twsk_purge(&tcp_hashinfo, AF_INET);
 }
 
 static struct pernet_operations __net_initdata tcp_sk_ops = {
@@ -2473,7 +2488,6 @@ static struct pernet_operations __net_initdata tcp_sk_ops = {
 
 void __init tcp_v4_init(void)
 {
-	inet_hashinfo_init(&tcp_hashinfo);
 	if (register_pernet_subsys(&tcp_sk_ops))
 		panic("Failed to create the TCP control socket.\n");
 }