1 files changed, 77 insertions, 57 deletions

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 711d209f9124..33df8b8575cc 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -234,7 +234,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.fl6_dport = usin->sin6_port;
 	fl6.fl6_sport = inet->inet_sport;
 
-	opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+	opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
 	final_p = fl6_update_dst(&fl6, opt, &final);
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
@@ -336,8 +336,8 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 					skb->dev->ifindex);
 
 	if (!sk) {
-		ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
-				   ICMP6_MIB_INERRORS);
+		__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
+				  ICMP6_MIB_INERRORS);
 		return;
 	}
 
@@ -352,13 +352,13 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
-		NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
+		__NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS);
 
 	if (sk->sk_state == TCP_CLOSE)
 		goto out;
 
 	if (ipv6_hdr(skb)->hop_limit < inet6_sk(sk)->min_hopcount) {
-		NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
+		__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
 		goto out;
 	}
 
@@ -368,7 +368,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
 	if (sk->sk_state != TCP_LISTEN &&
 	    !between(seq, snd_una, tp->snd_nxt)) {
-		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
+		__NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS);
 		goto out;
 	}
 
@@ -439,10 +439,11 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 			      struct flowi *fl,
 			      struct request_sock *req,
 			      struct tcp_fastopen_cookie *foc,
-			      bool attach_req)
+			      enum tcp_synack_type synack_type)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt;
 	struct flowi6 *fl6 = &fl->u.ip6;
 	struct sk_buff *skb;
 	int err = -ENOMEM;
@@ -452,7 +453,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 					       IPPROTO_TCP)) == NULL)
 		goto done;
 
-	skb = tcp_make_synack(sk, dst, req, foc, attach_req);
+	skb = tcp_make_synack(sk, dst, req, foc, synack_type);
 
 	if (skb) {
 		__tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
@@ -463,8 +464,10 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
 		rcu_read_lock();
-		err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
-			       np->tclass);
+		opt = ireq->ipv6_opt;
+		if (!opt)
+			opt = rcu_dereference(np->opt);
+		err = ip6_xmit(sk, skb, fl6, opt, np->tclass);
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
@@ -476,6 +479,7 @@ done:
 
 static void tcp_v6_reqsk_destructor(struct request_sock *req)
 {
+	kfree(inet_rsk(req)->ipv6_opt);
 	kfree_skb(inet_rsk(req)->pktopts);
 }
 
@@ -526,26 +530,33 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval,
 			      AF_INET6, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
 }
 
-static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
-					const struct in6_addr *daddr,
-					const struct in6_addr *saddr, int nbytes)
+static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp,
+				   const struct in6_addr *daddr,
+				   const struct in6_addr *saddr,
+				   const struct tcphdr *th, int nbytes)
 {
 	struct tcp6_pseudohdr *bp;
 	struct scatterlist sg;
+	struct tcphdr *_th;
 
-	bp = &hp->md5_blk.ip6;
+	bp = hp->scratch;
 	/* 1. TCP pseudo-header (RFC2460) */
 	bp->saddr = *saddr;
 	bp->daddr = *daddr;
 	bp->protocol = cpu_to_be32(IPPROTO_TCP);
 	bp->len = cpu_to_be32(nbytes);
 
-	sg_init_one(&sg, bp, sizeof(*bp));
-	ahash_request_set_crypt(hp->md5_req, &sg, NULL, sizeof(*bp));
+	_th = (struct tcphdr *)(bp + 1);
+	memcpy(_th, th, sizeof(*th));
+	_th->check = 0;
+
+	sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th));
+	ahash_request_set_crypt(hp->md5_req, &sg, NULL,
+				sizeof(*bp) + sizeof(*th));
 	return crypto_ahash_update(hp->md5_req);
 }
 
-static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
+static int tcp_v6_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 			       const struct in6_addr *daddr, struct in6_addr *saddr,
 			       const struct tcphdr *th)
 {
@@ -559,9 +570,7 @@ static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
 
 	if (crypto_ahash_init(req))
 		goto clear_hash;
-	if (tcp_v6_md5_hash_pseudoheader(hp, daddr, saddr, th->doff << 2))
-		goto clear_hash;
-	if (tcp_md5_hash_header(hp, th))
+	if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, th->doff << 2))
 		goto clear_hash;
 	if (tcp_md5_hash_key(hp, key))
 		goto clear_hash;
@@ -606,9 +615,7 @@ static int tcp_v6_md5_hash_skb(char *md5_hash,
 	if (crypto_ahash_init(req))
 		goto clear_hash;
 
-	if (tcp_v6_md5_hash_pseudoheader(hp, daddr, saddr, skb->len))
-		goto clear_hash;
-	if (tcp_md5_hash_header(hp, th))
+	if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, skb->len))
 		goto clear_hash;
 	if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2))
 		goto clear_hash;
@@ -649,12 +656,12 @@ static bool tcp_v6_inbound_md5_hash(const struct sock *sk,
 		return false;
 
 	if (hash_expected && !hash_location) {
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND);
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND);
 		return true;
 	}
 
 	if (!hash_expected && hash_location) {
-		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
 		return true;
 	}
 
@@ -738,7 +745,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 static void tcp_v6_send_response(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, int rst,
-				 u8 tclass, u32 label)
+				 u8 tclass, __be32 label)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
 	struct tcphdr *t1;
@@ -810,8 +817,13 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	fl6.flowi6_proto = IPPROTO_TCP;
 	if (rt6_need_strict(&fl6.daddr) && !oif)
 		fl6.flowi6_oif = tcp_v6_iif(skb);
-	else
+	else {
+		if (!oif && netif_index_is_l3_master(net, skb->skb_iif))
+			oif = skb->skb_iif;
+
 		fl6.flowi6_oif = oif;
+	}
+
 	fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
 	fl6.fl6_dport = t1->dest;
 	fl6.fl6_sport = t1->source;
@@ -825,9 +837,9 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	if (!IS_ERR(dst)) {
 		skb_dst_set(buff, dst);
 		ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass);
-		TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
+		TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
 		if (rst)
-			TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
+			TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
 		return;
 	}
 
@@ -858,6 +870,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 		return;
 
 #ifdef CONFIG_TCP_MD5SIG
+	rcu_read_lock();
 	hash_location = tcp_parse_md5sig_option(th);
 	if (sk && sk_fullsock(sk)) {
 		key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr);
@@ -875,16 +888,15 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 					   th->source, &ipv6h->daddr,
 					   ntohs(th->source), tcp_v6_iif(skb));
 		if (!sk1)
-			return;
+			goto out;
 
-		rcu_read_lock();
 		key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr);
 		if (!key)
-			goto release_sk1;
+			goto out;
 
 		genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, skb);
 		if (genhash || memcmp(hash_location, newhash, 16) != 0)
-			goto release_sk1;
+			goto out;
 	}
 #endif
 
@@ -898,18 +910,15 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 	tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
 
 #ifdef CONFIG_TCP_MD5SIG
-release_sk1:
-	if (sk1) {
-		rcu_read_unlock();
-		sock_put(sk1);
-	}
+out:
+	rcu_read_unlock();
 #endif
 }
 
 static void tcp_v6_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, u8 tclass,
-			    u32 label)
+			    __be32 label)
 {
 	tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0,
 			     tclass, label);
@@ -967,7 +976,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 				&tcp_request_sock_ipv6_ops, sk, skb);
 
 drop:
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
+	tcp_listendrop(sk);
 	return 0; /* don't send reset */
 }
 
@@ -1107,7 +1116,9 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	   but we make one more one thing there: reattach optmem
 	   to newsk.
 	 */
-	opt = rcu_dereference(np->opt);
+	opt = ireq->ipv6_opt;
+	if (!opt)
+		opt = rcu_dereference(np->opt);
 	if (opt) {
 		opt = ipv6_dup_options(newsk, opt);
 		RCU_INIT_POINTER(newnp->opt, opt);
@@ -1168,11 +1179,11 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	return newsk;
 
 out_overflow:
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
+	__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
 out_nonewsk:
 	dst_release(dst);
 out:
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
+	tcp_listendrop(sk);
 	return NULL;
 }
 
@@ -1279,8 +1290,8 @@ discard:
 	kfree_skb(skb);
 	return 0;
 csum_err:
-	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_CSUMERRORS);
-	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
+	TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
+	TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
 	goto discard;
 
 
@@ -1351,6 +1362,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 {
 	const struct tcphdr *th;
 	const struct ipv6hdr *hdr;
+	bool refcounted;
 	struct sock *sk;
 	int ret;
 	struct net *net = dev_net(skb->dev);
@@ -1361,14 +1373,14 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	/*
 	 *	Count it even if it's bad.
 	 */
-	TCP_INC_STATS_BH(net, TCP_MIB_INSEGS);
+	__TCP_INC_STATS(net, TCP_MIB_INSEGS);
 
 	if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
 		goto discard_it;
 
-	th = tcp_hdr(skb);
+	th = (const struct tcphdr *)skb->data;
 
-	if (th->doff < sizeof(struct tcphdr)/4)
+	if (unlikely(th->doff < sizeof(struct tcphdr)/4))
 		goto bad_packet;
 	if (!pskb_may_pull(skb, th->doff*4))
 		goto discard_it;
@@ -1376,12 +1388,13 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	if (skb_checksum_init(skb, IPPROTO_TCP, ip6_compute_pseudo))
 		goto csum_error;
 
-	th = tcp_hdr(skb);
+	th = (const struct tcphdr *)skb->data;
 	hdr = ipv6_hdr(skb);
 
 lookup:
 	sk = __inet6_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th),
-				th->source, th->dest, inet6_iif(skb));
+				th->source, th->dest, inet6_iif(skb),
+				&refcounted);
 	if (!sk)
 		goto no_tcp_socket;
 
@@ -1404,6 +1417,7 @@ process:
 			goto lookup;
 		}
 		sock_hold(sk);
+		refcounted = true;
 		nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
@@ -1421,7 +1435,7 @@ process:
 		}
 	}
 	if (hdr->hop_limit < inet6_sk(sk)->min_hopcount) {
-		NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
+		__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
 		goto discard_and_relse;
 	}
 
@@ -1454,13 +1468,14 @@ process:
 	} else if (unlikely(sk_add_backlog(sk, skb,
 					   sk->sk_rcvbuf + sk->sk_sndbuf))) {
 		bh_unlock_sock(sk);
-		NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
+		__NET_INC_STATS(net, LINUX_MIB_TCPBACKLOGDROP);
 		goto discard_and_relse;
 	}
 	bh_unlock_sock(sk);
 
 put_and_return:
-	sock_put(sk);
+	if (refcounted)
+		sock_put(sk);
 	return ret ? -1 : 0;
 
 no_tcp_socket:
@@ -1471,9 +1486,9 @@ no_tcp_socket:
 
 	if (tcp_checksum_complete(skb)) {
 csum_error:
-		TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
+		__TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
 bad_packet:
-		TCP_INC_STATS_BH(net, TCP_MIB_INERRS);
+		__TCP_INC_STATS(net, TCP_MIB_INERRS);
 	} else {
 		tcp_v6_send_reset(NULL, skb);
 	}
@@ -1483,7 +1498,9 @@ discard_it:
 	return 0;
 
 discard_and_relse:
-	sock_put(sk);
+	sk_drops_add(sk, skb);
+	if (refcounted)
+		sock_put(sk);
 	goto discard_it;
 
 do_time_wait:
@@ -1514,6 +1531,7 @@ do_time_wait:
 			inet_twsk_deschedule_put(tw);
 			sk = sk2;
 			tcp_v6_restore_cb(skb);
+			refcounted = false;
 			goto process;
 		}
 		/* Fall through to ACK */
@@ -1712,7 +1730,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	destp = ntohs(inet->inet_dport);
 	srcp  = ntohs(inet->inet_sport);
 
-	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
 		timer_expires	= icsk->icsk_timeout;
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {