1 files changed, 88 insertions, 135 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f1756ee02207..3571f2be4470 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -122,7 +122,7 @@ 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 == NULL || (sysctl_tcp_tw_reuse &&
+	    (!twp || (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)
@@ -189,7 +189,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	if (!inet->inet_saddr)
 		inet->inet_saddr = fl4->saddr;
-	inet->inet_rcv_saddr = inet->inet_saddr;
+	sk_rcv_saddr_set(sk, inet->inet_saddr);
 
 	if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) {
 		/* Reset inherited state */
@@ -204,7 +204,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		tcp_fetch_timewait_stamp(sk, &rt->dst);
 
 	inet->inet_dport = usin->sin_port;
-	inet->inet_daddr = daddr;
+	sk_daddr_set(sk, daddr);
 
 	inet_csk(sk)->icsk_ext_hdr_len = 0;
 	if (inet_opt)
@@ -310,6 +310,34 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk)
 		dst->ops->redirect(dst, sk, skb);
 }
 
+
+/* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */
+void tcp_req_err(struct sock *sk, u32 seq)
+{
+	struct request_sock *req = inet_reqsk(sk);
+	struct net *net = sock_net(sk);
+
+	/* ICMPs are not backlogged, hence we cannot get
+	 * an established socket here.
+	 */
+	WARN_ON(req->sk);
+
+	if (seq != tcp_rsk(req)->snt_isn) {
+		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
+		reqsk_put(req);
+	} else {
+		/*
+		 * Still in SYN_RECV, just remove it silently.
+		 * There is no good way to pass the error to the newly
+		 * created socket, and POSIX does not want network
+		 * errors returned from accept().
+		 */
+		NET_INC_STATS_BH(net, LINUX_MIB_LISTENDROPS);
+		inet_csk_reqsk_queue_drop(req->rsk_listener, req);
+	}
+}
+EXPORT_SYMBOL(tcp_req_err);
+
 /*
  * This routine is called by the ICMP module when it gets some
  * sort of error condition.  If err < 0 then the socket should
@@ -343,8 +371,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	int err;
 	struct net *net = dev_net(icmp_skb->dev);
 
-	sk = inet_lookup(net, &tcp_hashinfo, iph->daddr, th->dest,
-			iph->saddr, th->source, inet_iif(icmp_skb));
+	sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr,
+				       th->dest, iph->saddr, ntohs(th->source),
+				       inet_iif(icmp_skb));
 	if (!sk) {
 		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
 		return;
@@ -353,6 +382,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		inet_twsk_put(inet_twsk(sk));
 		return;
 	}
+	seq = ntohl(th->seq);
+	if (sk->sk_state == TCP_NEW_SYN_RECV)
+		return tcp_req_err(sk, seq);
 
 	bh_lock_sock(sk);
 	/* If too many ICMPs get dropped on busy
@@ -374,7 +406,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 
 	icsk = inet_csk(sk);
 	tp = tcp_sk(sk);
-	seq = ntohl(th->seq);
 	/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
 	fastopen = tp->fastopen_rsk;
 	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
@@ -458,42 +489,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	}
 
 	switch (sk->sk_state) {
-		struct request_sock *req, **prev;
-	case TCP_LISTEN:
-		if (sock_owned_by_user(sk))
-			goto out;
-
-		req = inet_csk_search_req(sk, &prev, th->dest,
-					  iph->daddr, iph->saddr);
-		if (!req)
-			goto out;
-
-		/* ICMPs are not backlogged, hence we cannot get
-		   an established socket here.
-		 */
-		WARN_ON(req->sk);
-
-		if (seq != tcp_rsk(req)->snt_isn) {
-			NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
-			goto out;
-		}
-
-		/*
-		 * Still in SYN_RECV, just remove it silently.
-		 * There is no good way to pass the error to the newly
-		 * created socket, and POSIX does not want network
-		 * errors returned from accept().
-		 */
-		inet_csk_reqsk_queue_drop(sk, req, prev);
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
-		goto out;
-
 	case TCP_SYN_SENT:
 	case TCP_SYN_RECV:
 		/* Only in fast or simultaneous open. If a fast open socket is
 		 * is already accepted it is treated as a connected one below.
 		 */
-		if (fastopen && fastopen->sk == NULL)
+		if (fastopen && !fastopen->sk)
 			break;
 
 		if (!sock_owned_by_user(sk)) {
@@ -647,7 +648,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 		if (!key)
 			goto release_sk1;
 
-		genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, NULL, skb);
+		genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb);
 		if (genhash || memcmp(hash_location, newhash, 16) != 0)
 			goto release_sk1;
 	} else {
@@ -855,35 +856,6 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req)
 	kfree(inet_rsk(req)->opt);
 }
 
-/*
- * Return true if a syncookie should be sent
- */
-bool tcp_syn_flood_action(struct sock *sk,
-			 const struct sk_buff *skb,
-			 const char *proto)
-{
-	const char *msg = "Dropping request";
-	bool want_cookie = false;
-	struct listen_sock *lopt;
-
-#ifdef CONFIG_SYN_COOKIES
-	if (sysctl_tcp_syncookies) {
-		msg = "Sending cookies";
-		want_cookie = true;
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES);
-	} else
-#endif
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP);
-
-	lopt = inet_csk(sk)->icsk_accept_queue.listen_opt;
-	if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) {
-		lopt->synflood_warned = 1;
-		pr_info("%s: Possible SYN flooding on port %d. %s.  Check SNMP counters.\n",
-			proto, ntohs(tcp_hdr(skb)->dest), msg);
-	}
-	return want_cookie;
-}
-EXPORT_SYMBOL(tcp_syn_flood_action);
 
 #ifdef CONFIG_TCP_MD5SIG
 /*
@@ -897,10 +869,10 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
 					 const union tcp_md5_addr *addr,
 					 int family)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
+	const struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_key *key;
 	unsigned int size = sizeof(struct in_addr);
-	struct tcp_md5sig_info *md5sig;
+	const struct tcp_md5sig_info *md5sig;
 
 	/* caller either holds rcu_read_lock() or socket lock */
 	md5sig = rcu_dereference_check(tp->md5sig_info,
@@ -923,24 +895,15 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
 EXPORT_SYMBOL(tcp_md5_do_lookup);
 
 struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
-					 struct sock *addr_sk)
+					 const struct sock *addr_sk)
 {
-	union tcp_md5_addr *addr;
+	const union tcp_md5_addr *addr;
 
-	addr = (union tcp_md5_addr *)&inet_sk(addr_sk)->inet_daddr;
+	addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr;
 	return tcp_md5_do_lookup(sk, addr, AF_INET);
 }
 EXPORT_SYMBOL(tcp_v4_md5_lookup);
 
-static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk,
-						      struct request_sock *req)
-{
-	union tcp_md5_addr *addr;
-
-	addr = (union tcp_md5_addr *)&inet_rsk(req)->ir_rmt_addr;
-	return tcp_md5_do_lookup(sk, addr, AF_INET);
-}
-
 /* This can be called on a newly created socket, from other files */
 int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 		   int family, const u8 *newkey, u8 newkeylen, gfp_t gfp)
@@ -1101,8 +1064,8 @@ clear_hash_noput:
 	return 1;
 }
 
-int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
-			const struct sock *sk, const struct request_sock *req,
+int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
+			const struct sock *sk,
 			const struct sk_buff *skb)
 {
 	struct tcp_md5sig_pool *hp;
@@ -1110,12 +1073,9 @@ int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
 	const struct tcphdr *th = tcp_hdr(skb);
 	__be32 saddr, daddr;
 
-	if (sk) {
-		saddr = inet_sk(sk)->inet_saddr;
-		daddr = inet_sk(sk)->inet_daddr;
-	} else if (req) {
-		saddr = inet_rsk(req)->ir_loc_addr;
-		daddr = inet_rsk(req)->ir_rmt_addr;
+	if (sk) { /* valid for establish/request sockets */
+		saddr = sk->sk_rcv_saddr;
+		daddr = sk->sk_daddr;
 	} else {
 		const struct iphdr *iph = ip_hdr(skb);
 		saddr = iph->saddr;
@@ -1152,8 +1112,9 @@ clear_hash_noput:
 }
 EXPORT_SYMBOL(tcp_v4_md5_hash_skb);
 
-static bool __tcp_v4_inbound_md5_hash(struct sock *sk,
-				      const struct sk_buff *skb)
+/* Called with rcu_read_lock() */
+static bool tcp_v4_inbound_md5_hash(struct sock *sk,
+				    const struct sk_buff *skb)
 {
 	/*
 	 * This gets called for each TCP segment that arrives
@@ -1193,7 +1154,7 @@ static bool __tcp_v4_inbound_md5_hash(struct sock *sk,
 	 */
 	genhash = tcp_v4_md5_hash_skb(newhash,
 				      hash_expected,
-				      NULL, NULL, skb);
+				      NULL, skb);
 
 	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
 		net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n",
@@ -1205,28 +1166,16 @@ static bool __tcp_v4_inbound_md5_hash(struct sock *sk,
 	}
 	return false;
 }
-
-static bool tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb)
-{
-	bool ret;
-
-	rcu_read_lock();
-	ret = __tcp_v4_inbound_md5_hash(sk, skb);
-	rcu_read_unlock();
-
-	return ret;
-}
-
 #endif
 
-static void tcp_v4_init_req(struct request_sock *req, struct sock *sk,
+static void tcp_v4_init_req(struct request_sock *req, struct sock *sk_listener,
 			    struct sk_buff *skb)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 
-	ireq->ir_loc_addr = ip_hdr(skb)->daddr;
-	ireq->ir_rmt_addr = ip_hdr(skb)->saddr;
-	ireq->no_srccheck = inet_sk(sk)->transparent;
+	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
+	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
+	ireq->no_srccheck = inet_sk(sk_listener)->transparent;
 	ireq->opt = tcp_v4_save_options(skb);
 }
 
@@ -1259,7 +1208,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = {
 static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
 	.mss_clamp	=	TCP_MSS_DEFAULT,
 #ifdef CONFIG_TCP_MD5SIG
-	.md5_lookup	=	tcp_v4_reqsk_md5_lookup,
+	.req_md5_lookup	=	tcp_v4_md5_lookup,
 	.calc_md5_hash	=	tcp_v4_md5_hash_skb,
 #endif
 	.init_req	=	tcp_v4_init_req,
@@ -1318,8 +1267,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	newtp		      = tcp_sk(newsk);
 	newinet		      = inet_sk(newsk);
 	ireq		      = inet_rsk(req);
-	newinet->inet_daddr   = ireq->ir_rmt_addr;
-	newinet->inet_rcv_saddr = ireq->ir_loc_addr;
+	sk_daddr_set(newsk, ireq->ir_rmt_addr);
+	sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
 	newinet->inet_saddr	      = ireq->ir_loc_addr;
 	inet_opt	      = ireq->opt;
 	rcu_assign_pointer(newinet->inet_opt, inet_opt);
@@ -1356,7 +1305,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	/* Copy over the MD5 key from the original socket */
 	key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr,
 				AF_INET);
-	if (key != NULL) {
+	if (key) {
 		/*
 		 * We're using one, so create a matching key
 		 * on the newsk structure. If we fail to get
@@ -1391,15 +1340,17 @@ EXPORT_SYMBOL(tcp_v4_syn_recv_sock);
 
 static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
 {
-	struct tcphdr *th = tcp_hdr(skb);
+	const struct tcphdr *th = tcp_hdr(skb);
 	const struct iphdr *iph = ip_hdr(skb);
+	struct request_sock *req;
 	struct sock *nsk;
-	struct request_sock **prev;
-	/* Find possible connection requests. */
-	struct request_sock *req = inet_csk_search_req(sk, &prev, th->source,
-						       iph->saddr, iph->daddr);
-	if (req)
-		return tcp_check_req(sk, skb, req, prev, false);
+
+	req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr);
+	if (req) {
+		nsk = tcp_check_req(sk, skb, req, false);
+		reqsk_put(req);
+		return nsk;
+	}
 
 	nsk = inet_lookup_established(sock_net(sk), &tcp_hashinfo, iph->saddr,
 			th->source, iph->daddr, th->dest, inet_iif(skb));
@@ -1439,7 +1390,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 		sk_mark_napi_id(sk, skb);
 		if (dst) {
 			if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
-			    dst->ops->check(dst, 0) == NULL) {
+			    !dst->ops->check(dst, 0)) {
 				dst_release(dst);
 				sk->sk_rx_dst = NULL;
 			}
@@ -1517,7 +1468,7 @@ void tcp_v4_early_demux(struct sk_buff *skb)
 	if (sk) {
 		skb->sk = sk;
 		skb->destructor = sock_edemux;
-		if (sk->sk_state != TCP_TIME_WAIT) {
+		if (sk_fullsock(sk)) {
 			struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);
 
 			if (dst)
@@ -1734,7 +1685,7 @@ do_time_wait:
 							iph->daddr, th->dest,
 							inet_iif(skb));
 		if (sk2) {
-			inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
+			inet_twsk_deschedule(inet_twsk(sk));
 			inet_twsk_put(inet_twsk(sk));
 			sk = sk2;
 			goto process;
@@ -1846,7 +1797,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	if (inet_csk(sk)->icsk_bind_hash)
 		inet_put_port(sk);
 
-	BUG_ON(tp->fastopen_rsk != NULL);
+	BUG_ON(tp->fastopen_rsk);
 
 	/* If socket is aborted during connect operation */
 	tcp_free_fastopen_req(tp);
@@ -1904,13 +1855,13 @@ get_req:
 		}
 		sk	  = sk_nulls_next(st->syn_wait_sk);
 		st->state = TCP_SEQ_STATE_LISTENING;
-		read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+		spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 	} else {
 		icsk = inet_csk(sk);
-		read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+		spin_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 		if (reqsk_queue_len(&icsk->icsk_accept_queue))
 			goto start_req;
-		read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+		spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 		sk = sk_nulls_next(sk);
 	}
 get_sk:
@@ -1922,7 +1873,7 @@ get_sk:
 			goto out;
 		}
 		icsk = inet_csk(sk);
-		read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+		spin_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 		if (reqsk_queue_len(&icsk->icsk_accept_queue)) {
 start_req:
 			st->uid		= sock_i_uid(sk);
@@ -1931,7 +1882,7 @@ start_req:
 			st->sbucket	= 0;
 			goto get_req;
 		}
-		read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+		spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 	}
 	spin_unlock_bh(&ilb->lock);
 	st->offset = 0;
@@ -2150,7 +2101,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v)
 	case TCP_SEQ_STATE_OPENREQ:
 		if (v) {
 			struct inet_connection_sock *icsk = inet_csk(st->syn_wait_sk);
-			read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+			spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 		}
 	case TCP_SEQ_STATE_LISTENING:
 		if (v != SEQ_START_TOKEN)
@@ -2204,17 +2155,17 @@ void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
 }
 EXPORT_SYMBOL(tcp_proc_unregister);
 
-static void get_openreq4(const struct sock *sk, const struct request_sock *req,
+static void get_openreq4(const struct request_sock *req,
 			 struct seq_file *f, int i, kuid_t uid)
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
-	long delta = req->expires - jiffies;
+	long delta = req->rsk_timer.expires - jiffies;
 
 	seq_printf(f, "%4d: %08X:%04X %08X:%04X"
 		" %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK",
 		i,
 		ireq->ir_loc_addr,
-		ntohs(inet_sk(sk)->inet_sport),
+		ireq->ir_num,
 		ireq->ir_rmt_addr,
 		ntohs(ireq->ir_rmt_port),
 		TCP_SYN_RECV,
@@ -2225,7 +2176,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req,
 		from_kuid_munged(seq_user_ns(f), uid),
 		0,  /* non standard timer */
 		0, /* open_requests have no inode */
-		atomic_read(&sk->sk_refcnt),
+		0,
 		req);
 }
 
@@ -2291,9 +2242,9 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 static void get_timewait4_sock(const struct inet_timewait_sock *tw,
 			       struct seq_file *f, int i)
 {
+	long delta = tw->tw_timer.expires - jiffies;
 	__be32 dest, src;
 	__u16 destp, srcp;
-	s32 delta = tw->tw_ttd - inet_tw_time_stamp();
 
 	dest  = tw->tw_daddr;
 	src   = tw->tw_rcv_saddr;
@@ -2332,7 +2283,7 @@ static int tcp4_seq_show(struct seq_file *seq, void *v)
 			get_tcp4_sock(v, seq, st->num);
 		break;
 	case TCP_SEQ_STATE_OPENREQ:
-		get_openreq4(st->syn_wait_sk, v, seq, st->num, st->uid);
+		get_openreq4(v, seq, st->num, st->uid);
 		break;
 	}
 out:
@@ -2460,6 +2411,8 @@ static int __net_init tcp_sk_init(struct net *net)
 	}
 	net->ipv4.sysctl_tcp_ecn = 2;
 	net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
+	net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD;
+	net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL;
 	return 0;
 
 fail: