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

Conflicts:
	drivers/net/ethernet/emulex/benet/be_main.c
	drivers/net/ethernet/intel/igb/igb_main.c
	drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
	include/net/scm.h
	net/batman-adv/routing.c
	net/ipv4/tcp_input.c

The e{uid,gid} --> {uid,gid} credentials fix conflicted with the
cleanup in net-next to now pass cred structs around.

The be2net driver had a bug fix in 'net' that overlapped with the VLAN
interface changes by Patrick McHardy in net-next.

An IGB conflict existed because in 'net' the build_skb() support was
reverted, and in 'net-next' there was a comment style fix within that
code.

Several batman-adv conflicts were resolved by making sure that all
calls to batadv_is_my_mac() are changed to have a new bat_priv first
argument.

Eric Dumazet's TS ECR fix in TCP in 'net' conflicted with the F-RTO
rewrite in 'net-next', mostly overlapping changes.

Thanks to Stephen Rothwell and Antonio Quartulli for help with several
of these merge resolutions.

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 104 insertions, 61 deletions

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 2759dfd576a..dfc39d4d48b 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -587,13 +587,16 @@ static void check_lifetime(struct work_struct *work)
 {
 	unsigned long now, next, next_sec, next_sched;
 	struct in_ifaddr *ifa;
+	struct hlist_node *n;
 	int i;
 
 	now = jiffies;
 	next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
 
-	rcu_read_lock();
 	for (i = 0; i < IN4_ADDR_HSIZE; i++) {
+		bool change_needed = false;
+
+		rcu_read_lock();
 		hlist_for_each_entry_rcu(ifa, &inet_addr_lst[i], hash) {
 			unsigned long age;
 
@@ -606,16 +609,7 @@ static void check_lifetime(struct work_struct *work)
 
 			if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME &&
 			    age >= ifa->ifa_valid_lft) {
-				struct in_ifaddr **ifap ;
-
-				rtnl_lock();
-				for (ifap = &ifa->ifa_dev->ifa_list;
-				     *ifap != NULL; ifap = &ifa->ifa_next) {
-					if (*ifap == ifa)
-						inet_del_ifa(ifa->ifa_dev,
-							     ifap, 1);
-				}
-				rtnl_unlock();
+				change_needed = true;
 			} else if (ifa->ifa_preferred_lft ==
 				   INFINITY_LIFE_TIME) {
 				continue;
@@ -625,10 +619,8 @@ static void check_lifetime(struct work_struct *work)
 					next = ifa->ifa_tstamp +
 					       ifa->ifa_valid_lft * HZ;
 
-				if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) {
-					ifa->ifa_flags |= IFA_F_DEPRECATED;
-					rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0);
-				}
+				if (!(ifa->ifa_flags & IFA_F_DEPRECATED))
+					change_needed = true;
 			} else if (time_before(ifa->ifa_tstamp +
 					       ifa->ifa_preferred_lft * HZ,
 					       next)) {
@@ -636,8 +628,42 @@ static void check_lifetime(struct work_struct *work)
 				       ifa->ifa_preferred_lft * HZ;
 			}
 		}
+		rcu_read_unlock();
+		if (!change_needed)
+			continue;
+		rtnl_lock();
+		hlist_for_each_entry_safe(ifa, n, &inet_addr_lst[i], hash) {
+			unsigned long age;
+
+			if (ifa->ifa_flags & IFA_F_PERMANENT)
+				continue;
+
+			/* We try to batch several events at once. */
+			age = (now - ifa->ifa_tstamp +
+			       ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+
+			if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME &&
+			    age >= ifa->ifa_valid_lft) {
+				struct in_ifaddr **ifap;
+
+				for (ifap = &ifa->ifa_dev->ifa_list;
+				     *ifap != NULL; ifap = &(*ifap)->ifa_next) {
+					if (*ifap == ifa) {
+						inet_del_ifa(ifa->ifa_dev,
+							     ifap, 1);
+						break;
+					}
+				}
+			} else if (ifa->ifa_preferred_lft !=
+				   INFINITY_LIFE_TIME &&
+				   age >= ifa->ifa_preferred_lft &&
+				   !(ifa->ifa_flags & IFA_F_DEPRECATED)) {
+				ifa->ifa_flags |= IFA_F_DEPRECATED;
+				rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0);
+			}
+		}
+		rtnl_unlock();
 	}
-	rcu_read_unlock();
 
 	next_sec = round_jiffies_up(next);
 	next_sched = next;
@@ -804,6 +830,8 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 			return -EEXIST;
 		ifa = ifa_existing;
 		set_ifa_lifetime(ifa, valid_lft, prefered_lft);
+		cancel_delayed_work(&check_lifetime_work);
+		schedule_delayed_work(&check_lifetime_work, 0);
 		rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid);
 		blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
 	}
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 3b4f0cd2e63..4cfe34d4cc9 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -139,8 +139,6 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	/* skb is pure payload to encrypt */
 
-	err = -ENOMEM;
-
 	esp = x->data;
 	aead = esp->aead;
 	alen = crypto_aead_authsize(aead);
@@ -176,8 +174,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	}
 
 	tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
-	if (!tmp)
+	if (!tmp) {
+		err = -ENOMEM;
 		goto error;
+	}
 
 	seqhi = esp_tmp_seqhi(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 938520668b2..b66910aaef4 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -219,8 +219,7 @@ static void ip_expire(unsigned long arg)
 		if (!head->dev)
 			goto out_rcu_unlock;
 
-		/* skb dst is stale, drop it, and perform route lookup again */
-		skb_dst_drop(head);
+		/* skb has no dst, perform route lookup again */
 		iph = ip_hdr(head);
 		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
 					   iph->tos, head->dev);
@@ -494,9 +493,16 @@ found:
 		qp->q.max_size = skb->len + ihl;
 
 	if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
-	    qp->q.meat == qp->q.len)
-		return ip_frag_reasm(qp, prev, dev);
+	    qp->q.meat == qp->q.len) {
+		unsigned long orefdst = skb->_skb_refdst;
 
+		skb->_skb_refdst = 0UL;
+		err = ip_frag_reasm(qp, prev, dev);
+		skb->_skb_refdst = orefdst;
+		return err;
+	}
+
+	skb_dst_drop(skb);
 	inet_frag_lru_move(&qp->q);
 	return -EINPROGRESS;
 
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index c30130062cd..c49dcd0284a 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -66,6 +66,12 @@ static bool rpfilter_lookup_reverse(struct flowi4 *fl4,
 	return dev_match;
 }
 
+static bool rpfilter_is_local(const struct sk_buff *skb)
+{
+	const struct rtable *rt = skb_rtable(skb);
+	return rt && (rt->rt_flags & RTCF_LOCAL);
+}
+
 static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
 {
 	const struct xt_rpfilter_info *info;
@@ -76,7 +82,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	info = par->matchinfo;
 	invert = info->flags & XT_RPFILTER_INVERT;
 
-	if (par->in->flags & IFF_LOOPBACK)
+	if (rpfilter_is_local(skb))
 		return true ^ invert;
 
 	iph = ip_hdr(skb);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 7f4a5cb8f8d..b05c96e7af8 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -348,8 +348,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	 * hasn't changed since we received the original syn, but I see
 	 * no easy way to do this.
 	 */
-	flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk),
-			   RT_SCOPE_UNIVERSE, IPPROTO_TCP,
+	flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark,
+			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
 			   inet_sk_flowi_flags(sk),
 			   (opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
 			   ireq->loc_addr, th->source, th->dest);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6d9ca35f0c3..aafd052865b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -111,6 +111,7 @@ int sysctl_tcp_early_retrans __read_mostly = 3;
 #define FLAG_SND_UNA_ADVANCED	0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
 #define FLAG_DSACKING_ACK	0x800 /* SACK blocks contained D-SACK info */
 #define FLAG_SACK_RENEGING	0x2000 /* snd_una advanced to a sacked seq */
+#define FLAG_UPDATE_TS_RECENT	0x4000 /* tcp_replace_ts_recent() */
 
 #define FLAG_ACKED		(FLAG_DATA_ACKED|FLAG_SYN_ACKED)
 #define FLAG_NOT_DUP		(FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
@@ -3265,6 +3266,27 @@ static void tcp_send_challenge_ack(struct sock *sk)
 	}
 }
 
+static void tcp_store_ts_recent(struct tcp_sock *tp)
+{
+	tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval;
+	tp->rx_opt.ts_recent_stamp = get_seconds();
+}
+
+static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
+{
+	if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) {
+		/* PAWS bug workaround wrt. ACK frames, the PAWS discard
+		 * extra check below makes sure this can only happen
+		 * for pure ACK frames.  -DaveM
+		 *
+		 * Not only, also it occurs for expired timestamps.
+		 */
+
+		if (tcp_paws_check(&tp->rx_opt, 0))
+			tcp_store_ts_recent(tp);
+	}
+}
+
 /* This routine deals with acks during a TLP episode.
  * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe.
  */
@@ -3340,6 +3362,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	prior_fackets = tp->fackets_out;
 	prior_in_flight = tcp_packets_in_flight(tp);
 
+	/* ts_recent update must be made after we are sure that the packet
+	 * is in window.
+	 */
+	if (flag & FLAG_UPDATE_TS_RECENT)
+		tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
+
 	if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) {
 		/* Window is constant, pure forward advance.
 		 * No more checks are required.
@@ -3636,27 +3664,6 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
 EXPORT_SYMBOL(tcp_parse_md5sig_option);
 #endif
 
-static inline void tcp_store_ts_recent(struct tcp_sock *tp)
-{
-	tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval;
-	tp->rx_opt.ts_recent_stamp = get_seconds();
-}
-
-static inline void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
-{
-	if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) {
-		/* PAWS bug workaround wrt. ACK frames, the PAWS discard
-		 * extra check below makes sure this can only happen
-		 * for pure ACK frames.  -DaveM
-		 *
-		 * Not only, also it occurs for expired timestamps.
-		 */
-
-		if (tcp_paws_check(&tp->rx_opt, 0))
-			tcp_store_ts_recent(tp);
-	}
-}
-
 /* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM
  *
  * It is not fatal. If this ACK does _not_ change critical state (seqs, window)
@@ -5250,14 +5257,9 @@ slow_path:
 		return 0;
 
 step5:
-	if (tcp_ack(sk, skb, FLAG_SLOWPATH) < 0)
+	if (tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT) < 0)
 		goto discard;
 
-	/* ts_recent update must be made after we are sure that the packet
-	 * is in window.
-	 */
-	tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
-
 	tcp_rcv_rtt_measure_ts(sk, skb);
 
 	/* Process urgent data. */
@@ -5666,7 +5668,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 
 	/* step 5: check the ACK field */
 	if (true) {
-		int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0;
+		int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH |
+						  FLAG_UPDATE_TS_RECENT) > 0;
 
 		switch (sk->sk_state) {
 		case TCP_SYN_RECV:
@@ -5817,11 +5820,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 		}
 	}
 
-	/* ts_recent update must be made after we are sure that the packet
-	 * is in window.
-	 */
-	tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
-
 	/* step 6: check the URG bit */
 	tcp_urg(sk, skb, th);
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5f28131eb37..b735c23a961 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2353,8 +2353,12 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	 */
 	TCP_SKB_CB(skb)->when = tcp_time_stamp;
 
-	/* make sure skb->data is aligned on arches that require it */
-	if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) {
+	/* make sure skb->data is aligned on arches that require it
+	 * and check if ack-trimming & collapsing extended the headroom
+	 * beyond what csum_start can cover.
+	 */
+	if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) ||
+		     skb_headroom(skb) >= 0xFFFF)) {
 		struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
 						   GFP_ATOMIC);
 		return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
@@ -2666,6 +2670,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	skb_reserve(skb, MAX_TCP_HEADER);
 
 	skb_dst_set(skb, dst);
+	security_skb_owned_by(skb, sk);
 
 	mss = dst_metric_advmss(dst);
 	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)