Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking changes from David S Miller:

 1) Remove the ipv4 routing cache.  Now lookups go directly into the FIB
    trie and use prebuilt routes cached there.

    No more garbage collection, no more rDOS attacks on the routing
    cache.  Instead we now get predictable and consistent performance,
    no matter what the pattern of traffic we service.

    This has been almost 2 years in the making.  Special thanks to
    Julian Anastasov, Eric Dumazet, Steffen Klassert, and others who
    have helped along the way.

    I'm sure that with a change of this magnitude there will be some
    kind of fallout, but such things ought the be simple to fix at this
    point.  Luckily I'm not European so I'll be around all of August to
    fix things :-)

    The major stages of this work here are each fronted by a forced
    merge commit whose commit message contains a top-level description
    of the motivations and implementation issues.

 2) Pre-demux of established ipv4 TCP sockets, saves a route demux on
    input.

 3) TCP SYN/ACK performance tweaks from Eric Dumazet.

 4) Add namespace support for netfilter L4 conntrack helpers, from Gao
    Feng.

 5) Add config mechanism for Energy Efficient Ethernet to ethtool, from
    Yuval Mintz.

 6) Remove quadratic behavior from /proc/net/unix, from Eric Dumazet.

 7) Support for connection tracker helpers in userspace, from Pablo
    Neira Ayuso.

 8) Allow userspace driven TX load balancing functions in TEAM driver,
    from Jiri Pirko.

 9) Kill off NLMSG_PUT and RTA_PUT macros, more gross stuff with
    embedded gotos.

10) TCP Small Queues, essentially minimize the amount of TCP data queued
    up in the packet scheduler layer.  Whereas the existing BQL (Byte
    Queue Limits) limits the pkt_sched --> netdevice queuing levels,
    this controls the TCP --> pkt_sched queueing levels.

    From Eric Dumazet.

11) Reduce the number of get_page/put_page ops done on SKB fragments,
    from Alexander Duyck.

12) Implement protection against blind resets in TCP (RFC 5961), from
    Eric Dumazet.

13) Support the client side of TCP Fast Open, basically the ability to
    send data in the SYN exchange, from Yuchung Cheng.

    Basically, the sender queues up data with a sendmsg() call using
    MSG_FASTOPEN, then they do the connect() which emits the queued up
    fastopen data.

14) Avoid all the problems we get into in TCP when timers or PMTU events
    hit a locked socket.  The TCP Small Queues changes added a
    tcp_release_cb() that allows us to queue work up to the
    release_sock() caller, and that's what we use here too.  From Eric
    Dumazet.

15) Zero copy on TX support for TUN driver, from Michael S. Tsirkin.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1870 commits)
  genetlink: define lockdep_genl_is_held() when CONFIG_LOCKDEP
  r8169: revert "add byte queue limit support".
  ipv4: Change rt->rt_iif encoding.
  net: Make skb->skb_iif always track skb->dev
  ipv4: Prepare for change of rt->rt_iif encoding.
  ipv4: Remove all RTCF_DIRECTSRC handliing.
  ipv4: Really ignore ICMP address requests/replies.
  decnet: Don't set RTCF_DIRECTSRC.
  net/ipv4/ip_vti.c: Fix __rcu warnings detected by sparse.
  ipv4: Remove redundant assignment
  rds: set correct msg_namelen
  openvswitch: potential NULL deref in sample()
  tcp: dont drop MTU reduction indications
  bnx2x: Add new 57840 device IDs
  tcp: avoid oops in tcp_metrics and reset tcpm_stamp
  niu: Change niu_rbr_fill() to use unlikely() to check niu_rbr_add_page() return value
  niu: Fix to check for dma mapping errors.
  net: Fix references to out-of-scope variables in put_cmsg_compat()
  net: ethernet: davinci_emac: add pm_runtime support
  net: ethernet: davinci_emac: Remove unnecessary #include
  ...

1 files changed, 56 insertions, 148 deletions

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 9df64a50b075..f49476e2d884 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -277,22 +277,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	rt = (struct rt6_info *) dst;
 	if (tcp_death_row.sysctl_tw_recycle &&
 	    !tp->rx_opt.ts_recent_stamp &&
-	    ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr)) {
-		struct inet_peer *peer = rt6_get_peer(rt);
-		/*
-		 * VJ's idea. We save last timestamp seen from
-		 * the destination in peer table, when entering state
-		 * TIME-WAIT * and initialize rx_opt.ts_recent from it,
-		 * when trying new connection.
-		 */
-		if (peer) {
-			inet_peer_refcheck(peer);
-			if ((u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) {
-				tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
-				tp->rx_opt.ts_recent = peer->tcp_ts;
-			}
-		}
-	}
+	    ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr))
+		tcp_fetch_timewait_stamp(sk, dst);
 
 	icsk->icsk_ext_hdr_len = 0;
 	if (np->opt)
@@ -329,6 +315,23 @@ failure:
 	return err;
 }
 
+static void tcp_v6_mtu_reduced(struct sock *sk)
+{
+	struct dst_entry *dst;
+
+	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
+		return;
+
+	dst = inet6_csk_update_pmtu(sk, tcp_sk(sk)->mtu_info);
+	if (!dst)
+		return;
+
+	if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
+		tcp_sync_mss(sk, dst_mtu(dst));
+		tcp_simple_retransmit(sk);
+	}
+}
+
 static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		u8 type, u8 code, int offset, __be32 info)
 {
@@ -356,7 +359,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	}
 
 	bh_lock_sock(sk);
-	if (sock_owned_by_user(sk))
+	if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
 		NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
 
 	if (sk->sk_state == TCP_CLOSE)
@@ -377,49 +380,19 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	np = inet6_sk(sk);
 
-	if (type == ICMPV6_PKT_TOOBIG) {
-		struct dst_entry *dst;
-
-		if (sock_owned_by_user(sk))
-			goto out;
-		if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
-			goto out;
-
-		/* icmp should have updated the destination cache entry */
-		dst = __sk_dst_check(sk, np->dst_cookie);
-
-		if (dst == NULL) {
-			struct inet_sock *inet = inet_sk(sk);
-			struct flowi6 fl6;
-
-			/* BUGGG_FUTURE: Again, it is not clear how
-			   to handle rthdr case. Ignore this complexity
-			   for now.
-			 */
-			memset(&fl6, 0, sizeof(fl6));
-			fl6.flowi6_proto = IPPROTO_TCP;
-			fl6.daddr = np->daddr;
-			fl6.saddr = np->saddr;
-			fl6.flowi6_oif = sk->sk_bound_dev_if;
-			fl6.flowi6_mark = sk->sk_mark;
-			fl6.fl6_dport = inet->inet_dport;
-			fl6.fl6_sport = inet->inet_sport;
-			security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
-
-			dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false);
-			if (IS_ERR(dst)) {
-				sk->sk_err_soft = -PTR_ERR(dst);
-				goto out;
-			}
+	if (type == NDISC_REDIRECT) {
+		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		} else
-			dst_hold(dst);
+		if (dst)
+			dst->ops->redirect(dst, sk, skb);
+	}
 
-		if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
-			tcp_sync_mss(sk, dst_mtu(dst));
-			tcp_simple_retransmit(sk);
-		} /* else let the usual retransmit timer handle it */
-		dst_release(dst);
+	if (type == ICMPV6_PKT_TOOBIG) {
+		tp->mtu_info = ntohl(info);
+		if (!sock_owned_by_user(sk))
+			tcp_v6_mtu_reduced(sk);
+		else
+			set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags);
 		goto out;
 	}
 
@@ -475,62 +448,43 @@ out:
 }
 
 
-static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
+static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
+			      struct flowi6 *fl6,
+			      struct request_sock *req,
 			      struct request_values *rvp,
 			      u16 queue_mapping)
 {
 	struct inet6_request_sock *treq = inet6_rsk(req);
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sk_buff * skb;
-	struct ipv6_txoptions *opt = NULL;
-	struct in6_addr * final_p, final;
-	struct flowi6 fl6;
-	struct dst_entry *dst;
-	int err;
+	int err = -ENOMEM;
 
-	memset(&fl6, 0, sizeof(fl6));
-	fl6.flowi6_proto = IPPROTO_TCP;
-	fl6.daddr = treq->rmt_addr;
-	fl6.saddr = treq->loc_addr;
-	fl6.flowlabel = 0;
-	fl6.flowi6_oif = treq->iif;
-	fl6.flowi6_mark = sk->sk_mark;
-	fl6.fl6_dport = inet_rsk(req)->rmt_port;
-	fl6.fl6_sport = inet_rsk(req)->loc_port;
-	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
-
-	opt = np->opt;
-	final_p = fl6_update_dst(&fl6, opt, &final);
-
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
-	if (IS_ERR(dst)) {
-		err = PTR_ERR(dst);
-		dst = NULL;
+	/* First, grab a route. */
+	if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL)
 		goto done;
-	}
+
 	skb = tcp_make_synack(sk, dst, req, rvp);
-	err = -ENOMEM;
+
 	if (skb) {
 		__tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
 
-		fl6.daddr = treq->rmt_addr;
+		fl6->daddr = treq->rmt_addr;
 		skb_set_queue_mapping(skb, queue_mapping);
-		err = ip6_xmit(sk, skb, &fl6, opt, np->tclass);
+		err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
 		err = net_xmit_eval(err);
 	}
 
 done:
-	if (opt && opt != np->opt)
-		sock_kfree_s(sk, opt, opt->tot_len);
-	dst_release(dst);
 	return err;
 }
 
 static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req,
 			     struct request_values *rvp)
 {
+	struct flowi6 fl6;
+
 	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
-	return tcp_v6_send_synack(sk, req, rvp, 0);
+	return tcp_v6_send_synack(sk, NULL, &fl6, req, rvp, 0);
 }
 
 static void tcp_v6_reqsk_destructor(struct request_sock *req)
@@ -1057,6 +1011,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 	__u32 isn = TCP_SKB_CB(skb)->when;
 	struct dst_entry *dst = NULL;
+	struct flowi6 fl6;
 	bool want_cookie = false;
 
 	if (skb->protocol == htons(ETH_P_IP))
@@ -1085,7 +1040,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	tcp_clear_options(&tmp_opt);
 	tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
 	tmp_opt.user_mss = tp->rx_opt.user_mss;
-	tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+	tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
 
 	if (tmp_opt.cookie_plus > 0 &&
 	    tmp_opt.saw_tstamp &&
@@ -1150,8 +1105,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		treq->iif = inet6_iif(skb);
 
 	if (!isn) {
-		struct inet_peer *peer = NULL;
-
 		if (ipv6_opt_accepted(sk, skb) ||
 		    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
 		    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
@@ -1176,14 +1129,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		 */
 		if (tmp_opt.saw_tstamp &&
 		    tcp_death_row.sysctl_tw_recycle &&
-		    (dst = inet6_csk_route_req(sk, req)) != NULL &&
-		    (peer = rt6_get_peer((struct rt6_info *)dst)) != NULL &&
-		    ipv6_addr_equal((struct in6_addr *)peer->daddr.addr.a6,
-				    &treq->rmt_addr)) {
-			inet_peer_refcheck(peer);
-			if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL &&
-			    (s32)(peer->tcp_ts - req->ts_recent) >
-							TCP_PAWS_WINDOW) {
+		    (dst = inet6_csk_route_req(sk, &fl6, req)) != NULL) {
+			if (!tcp_peer_is_proven(req, dst, true)) {
 				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
 				goto drop_and_release;
 			}
@@ -1192,8 +1139,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		else if (!sysctl_tcp_syncookies &&
 			 (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
 			  (sysctl_max_syn_backlog >> 2)) &&
-			 (!peer || !peer->tcp_ts_stamp) &&
-			 (!dst || !dst_metric(dst, RTAX_RTT))) {
+			 !tcp_peer_is_proven(req, dst, false)) {
 			/* Without syncookies last quarter of
 			 * backlog is filled with destinations,
 			 * proven to be alive.
@@ -1215,7 +1161,7 @@ have_isn:
 	if (security_inet_conn_request(sk, skb, req))
 		goto drop_and_release;
 
-	if (tcp_v6_send_synack(sk, req,
+	if (tcp_v6_send_synack(sk, dst, &fl6, req,
 			       (struct request_values *)&tmp_ext,
 			       skb_get_queue_mapping(skb)) ||
 	    want_cookie)
@@ -1242,10 +1188,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	struct inet_sock *newinet;
 	struct tcp_sock *newtp;
 	struct sock *newsk;
-	struct ipv6_txoptions *opt;
 #ifdef CONFIG_TCP_MD5SIG
 	struct tcp_md5sig_key *key;
 #endif
+	struct flowi6 fl6;
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		/*
@@ -1302,13 +1248,12 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	}
 
 	treq = inet6_rsk(req);
-	opt = np->opt;
 
 	if (sk_acceptq_is_full(sk))
 		goto out_overflow;
 
 	if (!dst) {
-		dst = inet6_csk_route_req(sk, req);
+		dst = inet6_csk_route_req(sk, &fl6, req);
 		if (!dst)
 			goto out;
 	}
@@ -1371,11 +1316,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	   but we make one more one thing there: reattach optmem
 	   to newsk.
 	 */
-	if (opt) {
-		newnp->opt = ipv6_dup_options(newsk, opt);
-		if (opt != np->opt)
-			sock_kfree_s(sk, opt, opt->tot_len);
-	}
+	if (np->opt)
+		newnp->opt = ipv6_dup_options(newsk, np->opt);
 
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
 	if (newnp->opt)
@@ -1422,8 +1364,6 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 out_overflow:
 	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
 out_nonewsk:
-	if (opt && opt != np->opt)
-		sock_kfree_s(sk, opt, opt->tot_len);
 	dst_release(dst);
 out:
 	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
@@ -1734,42 +1674,10 @@ do_time_wait:
 	goto discard_it;
 }
 
-static struct inet_peer *tcp_v6_get_peer(struct sock *sk, bool *release_it)
-{
-	struct rt6_info *rt = (struct rt6_info *) __sk_dst_get(sk);
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct inet_peer *peer;
-
-	if (!rt ||
-	    !ipv6_addr_equal(&np->daddr, &rt->rt6i_dst.addr)) {
-		peer = inet_getpeer_v6(&np->daddr, 1);
-		*release_it = true;
-	} else {
-		if (!rt->rt6i_peer)
-			rt6_bind_peer(rt, 1);
-		peer = rt->rt6i_peer;
-		*release_it = false;
-	}
-
-	return peer;
-}
-
-static void *tcp_v6_tw_get_peer(struct sock *sk)
-{
-	const struct inet6_timewait_sock *tw6 = inet6_twsk(sk);
-	const struct inet_timewait_sock *tw = inet_twsk(sk);
-
-	if (tw->tw_family == AF_INET)
-		return tcp_v4_tw_get_peer(sk);
-
-	return inet_getpeer_v6(&tw6->tw_v6_daddr, 1);
-}
-
 static struct timewait_sock_ops tcp6_timewait_sock_ops = {
 	.twsk_obj_size	= sizeof(struct tcp6_timewait_sock),
 	.twsk_unique	= tcp_twsk_unique,
 	.twsk_destructor= tcp_twsk_destructor,
-	.twsk_getpeer	= tcp_v6_tw_get_peer,
 };
 
 static const struct inet_connection_sock_af_ops ipv6_specific = {
@@ -1778,7 +1686,6 @@ static const struct inet_connection_sock_af_ops ipv6_specific = {
 	.rebuild_header	   = inet6_sk_rebuild_header,
 	.conn_request	   = tcp_v6_conn_request,
 	.syn_recv_sock	   = tcp_v6_syn_recv_sock,
-	.get_peer	   = tcp_v6_get_peer,
 	.net_header_len	   = sizeof(struct ipv6hdr),
 	.net_frag_header_len = sizeof(struct frag_hdr),
 	.setsockopt	   = ipv6_setsockopt,
@@ -1810,7 +1717,6 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = {
 	.rebuild_header	   = inet_sk_rebuild_header,
 	.conn_request	   = tcp_v6_conn_request,
 	.syn_recv_sock	   = tcp_v6_syn_recv_sock,
-	.get_peer	   = tcp_v4_get_peer,
 	.net_header_len	   = sizeof(struct iphdr),
 	.setsockopt	   = ipv6_setsockopt,
 	.getsockopt	   = ipv6_getsockopt,
@@ -2049,6 +1955,8 @@ struct proto tcpv6_prot = {
 	.sendmsg		= tcp_sendmsg,
 	.sendpage		= tcp_sendpage,
 	.backlog_rcv		= tcp_v6_do_rcv,
+	.release_cb		= tcp_release_cb,
+	.mtu_reduced		= tcp_v6_mtu_reduced,
 	.hash			= tcp_v6_hash,
 	.unhash			= inet_unhash,
 	.get_port		= inet_csk_get_port,