Merge branch 'next' into for-linus

Prepare first round of input updates for 3.20.

1 files changed, 80 insertions, 57 deletions

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 29964c3d363c..9c0b54e87b47 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -59,7 +59,6 @@
 #include <net/snmp.h>
 #include <net/dsfield.h>
 #include <net/timewait_sock.h>
-#include <net/netdma.h>
 #include <net/inet_common.h>
 #include <net/secure_seq.h>
 #include <net/tcp_memcontrol.h>
@@ -93,13 +92,16 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
 static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
-	const struct rt6_info *rt = (const struct rt6_info *)dst;
 
-	dst_hold(dst);
-	sk->sk_rx_dst = dst;
-	inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
-	if (rt->rt6i_node)
-		inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
+	if (dst) {
+		const struct rt6_info *rt = (const struct rt6_info *)dst;
+
+		dst_hold(dst);
+		sk->sk_rx_dst = dst;
+		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+		if (rt->rt6i_node)
+			inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
+	}
 }
 
 static void tcp_v6_hash(struct sock *sk)
@@ -198,8 +200,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	sk->sk_v6_daddr = usin->sin6_addr;
 	np->flow_label = fl6.flowlabel;
 
-	ip6_set_txhash(sk);
-
 	/*
 	 *	TCP over IPv4
 	 */
@@ -295,6 +295,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	if (err)
 		goto late_failure;
 
+	ip6_set_txhash(sk);
+
 	if (!tp->write_seq && likely(!tp->repair))
 		tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
 							     sk->sk_v6_daddr.s6_addr32,
@@ -422,6 +424,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (sock_owned_by_user(sk))
 			goto out;
 
+		/* Note : We use inet6_iif() here, not tcp_v6_iif() */
 		req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr,
 					   &hdr->saddr, inet6_iif(skb));
 		if (!req)
@@ -736,10 +739,11 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk,
 	/* So that link locals have meaning */
 	if (!sk->sk_bound_dev_if &&
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
-		ireq->ir_iif = inet6_iif(skb);
+		ireq->ir_iif = tcp_v6_iif(skb);
 
-	if (!TCP_SKB_CB(skb)->when &&
-	    (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo ||
+	if (!TCP_SKB_CB(skb)->tcp_tw_isn &&
+	    (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) ||
+	     np->rxopt.bits.rxinfo ||
 	     np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim ||
 	     np->rxopt.bits.rxohlim || np->repflow)) {
 		atomic_inc(&skb->users);
@@ -783,16 +787,16 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 	.queue_hash_add =	inet6_csk_reqsk_queue_hash_add,
 };
 
-static void tcp_v6_send_response(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)
+static void tcp_v6_send_response(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)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
 	struct tcphdr *t1;
 	struct sk_buff *buff;
 	struct flowi6 fl6;
-	struct net *net = dev_net(skb_dst(skb)->dev);
+	struct net *net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
 	struct sock *ctl_sk = net->ipv6.tcp_sk;
 	unsigned int tot_len = sizeof(struct tcphdr);
 	struct dst_entry *dst;
@@ -857,7 +861,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 
 	fl6.flowi6_proto = IPPROTO_TCP;
 	if (rt6_need_strict(&fl6.daddr) && !oif)
-		fl6.flowi6_oif = inet6_iif(skb);
+		fl6.flowi6_oif = tcp_v6_iif(skb);
 	else
 		fl6.flowi6_oif = oif;
 	fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
@@ -899,7 +903,10 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 	if (th->rst)
 		return;
 
-	if (!ipv6_unicast_destination(skb))
+	/* If sk not NULL, it means we did a successful lookup and incoming
+	 * route had to be correct. prequeue might have dropped our dst.
+	 */
+	if (!sk && !ipv6_unicast_destination(skb))
 		return;
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -915,7 +922,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 		sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev),
 					   &tcp_hashinfo, &ipv6h->saddr,
 					   th->source, &ipv6h->daddr,
-					   ntohs(th->source), inet6_iif(skb));
+					   ntohs(th->source), tcp_v6_iif(skb));
 		if (!sk1)
 			return;
 
@@ -939,7 +946,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 			  (th->doff << 2);
 
 	oif = sk ? sk->sk_bound_dev_if : 0;
-	tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
+	tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
 
 #ifdef CONFIG_TCP_MD5SIG
 release_sk1:
@@ -950,13 +957,13 @@ release_sk1:
 #endif
 }
 
-static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
-			    u32 win, u32 tsval, u32 tsecr, int oif,
+static void tcp_v6_send_ack(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)
 {
-	tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, oif, key, 0, tclass,
-			     label);
+	tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0,
+			     tclass, label);
 }
 
 static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
@@ -964,7 +971,7 @@ static void tcp_v6_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_v6_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+	tcp_v6_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,
 			tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
@@ -979,10 +986,10 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
 	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
 	 */
-	tcp_v6_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
+	tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ?
 			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
-			tcp_rsk(req)->rcv_nxt,
-			req->rcv_wnd, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
+			tcp_rsk(req)->rcv_nxt, req->rcv_wnd,
+			tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
 			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
 			0, 0);
 }
@@ -997,13 +1004,14 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb)
 	/* Find possible connection requests. */
 	req = inet6_csk_search_req(sk, &prev, th->source,
 				   &ipv6_hdr(skb)->saddr,
-				   &ipv6_hdr(skb)->daddr, inet6_iif(skb));
+				   &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb));
 	if (req)
 		return tcp_check_req(sk, skb, req, prev, false);
 
 	nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo,
-			&ipv6_hdr(skb)->saddr, th->source,
-			&ipv6_hdr(skb)->daddr, ntohs(th->dest), inet6_iif(skb));
+					 &ipv6_hdr(skb)->saddr, th->source,
+					 &ipv6_hdr(skb)->daddr, ntohs(th->dest),
+					 tcp_v6_iif(skb));
 
 	if (nsk) {
 		if (nsk->sk_state != TCP_TIME_WAIT) {
@@ -1087,7 +1095,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		newnp->ipv6_fl_list = NULL;
 		newnp->pktoptions  = NULL;
 		newnp->opt	   = NULL;
-		newnp->mcast_oif   = inet6_iif(skb);
+		newnp->mcast_oif   = tcp_v6_iif(skb);
 		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
 		newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
 		if (np->repflow)
@@ -1171,7 +1179,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 			skb_set_owner_r(newnp->pktoptions, newsk);
 	}
 	newnp->opt	  = NULL;
-	newnp->mcast_oif  = inet6_iif(skb);
+	newnp->mcast_oif  = tcp_v6_iif(skb);
 	newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
 	newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
 	if (np->repflow)
@@ -1288,6 +1296,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 		struct dst_entry *dst = sk->sk_rx_dst;
 
 		sock_rps_save_rxhash(sk, skb);
+		sk_mark_napi_id(sk, skb);
 		if (dst) {
 			if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
 			    dst->ops->check(dst, np->rx_dst_cookie) == NULL) {
@@ -1317,6 +1326,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 		 */
 		if (nsk != sk) {
 			sock_rps_save_rxhash(nsk, skb);
+			sk_mark_napi_id(sk, skb);
 			if (tcp_child_process(sk, nsk, skb))
 				goto reset;
 			if (opt_skb)
@@ -1357,14 +1367,14 @@ ipv6_pktoptions:
 	if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt &&
 	    !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) {
 		if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo)
-			np->mcast_oif = inet6_iif(opt_skb);
+			np->mcast_oif = tcp_v6_iif(opt_skb);
 		if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
 			np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
 		if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
 			np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb));
 		if (np->repflow)
 			np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
-		if (ipv6_opt_accepted(sk, opt_skb)) {
+		if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) {
 			skb_set_owner_r(opt_skb, sk);
 			opt_skb = xchg(&np->pktoptions, opt_skb);
 		} else {
@@ -1377,6 +1387,28 @@ ipv6_pktoptions:
 	return 0;
 }
 
+static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
+			   const struct tcphdr *th)
+{
+	/* This is tricky: we move IP6CB at its correct location into
+	 * TCP_SKB_CB(). It must be done after xfrm6_policy_check(), because
+	 * _decode_session6() uses IP6CB().
+	 * barrier() makes sure compiler won't play aliasing games.
+	 */
+	memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb),
+		sizeof(struct inet6_skb_parm));
+	barrier();
+
+	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
+	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
+				    skb->len - th->doff*4);
+	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
+	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
+	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
+	TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
+	TCP_SKB_CB(skb)->sacked = 0;
+}
+
 static int tcp_v6_rcv(struct sk_buff *skb)
 {
 	const struct tcphdr *th;
@@ -1408,15 +1440,9 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 
 	th = tcp_hdr(skb);
 	hdr = ipv6_hdr(skb);
-	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
-	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
-				    skb->len - th->doff*4);
-	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-	TCP_SKB_CB(skb)->when = 0;
-	TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
-	TCP_SKB_CB(skb)->sacked = 0;
 
-	sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest);
+	sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest,
+				inet6_iif(skb));
 	if (!sk)
 		goto no_tcp_socket;
 
@@ -1432,6 +1458,8 @@ process:
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_and_relse;
 
+	tcp_v6_fill_cb(skb, hdr, th);
+
 #ifdef CONFIG_TCP_MD5SIG
 	if (tcp_v6_inbound_md5_hash(sk, skb))
 		goto discard_and_relse;
@@ -1440,24 +1468,14 @@ process:
 	if (sk_filter(sk, skb))
 		goto discard_and_relse;
 
-	sk_mark_napi_id(sk, skb);
+	sk_incoming_cpu_update(sk);
 	skb->dev = NULL;
 
 	bh_lock_sock_nested(sk);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
-#ifdef CONFIG_NET_DMA
-		struct tcp_sock *tp = tcp_sk(sk);
-		if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-			tp->ucopy.dma_chan = net_dma_find_channel();
-		if (tp->ucopy.dma_chan)
+		if (!tcp_prequeue(sk, skb))
 			ret = tcp_v6_do_rcv(sk, skb);
-		else
-#endif
-		{
-			if (!tcp_prequeue(sk, skb))
-				ret = tcp_v6_do_rcv(sk, skb);
-		}
 	} else if (unlikely(sk_add_backlog(sk, skb,
 					   sk->sk_rcvbuf + sk->sk_sndbuf))) {
 		bh_unlock_sock(sk);
@@ -1473,6 +1491,8 @@ no_tcp_socket:
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto discard_it;
 
+	tcp_v6_fill_cb(skb, hdr, th);
+
 	if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) {
 csum_error:
 		TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS);
@@ -1496,6 +1516,8 @@ do_time_wait:
 		goto discard_it;
 	}
 
+	tcp_v6_fill_cb(skb, hdr, th);
+
 	if (skb->len < (th->doff<<2)) {
 		inet_twsk_put(inet_twsk(sk));
 		goto bad_packet;
@@ -1513,7 +1535,7 @@ do_time_wait:
 		sk2 = inet6_lookup_listener(dev_net(skb->dev), &tcp_hashinfo,
 					    &ipv6_hdr(skb)->saddr, th->source,
 					    &ipv6_hdr(skb)->daddr,
-					    ntohs(th->dest), inet6_iif(skb));
+					    ntohs(th->dest), tcp_v6_iif(skb));
 		if (sk2 != NULL) {
 			struct inet_timewait_sock *tw = inet_twsk(sk);
 			inet_twsk_deschedule(tw, &tcp_death_row);
@@ -1552,6 +1574,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb)
 	if (th->doff < sizeof(struct tcphdr) / 4)
 		return;
 
+	/* Note : We use inet6_iif() here, not tcp_v6_iif() */
 	sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
 					&hdr->saddr, th->source,
 					&hdr->daddr, ntohs(th->dest),