Merge linux-stable 3.0.28 into android-3.0

Change-Id: Iee820738e53627f5d0447a87ceff34443aa72786
Signed-off-by: Todd Poynor <toddpoynor@google.com>

18 files changed, 326 insertions, 119 deletions

diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index c1f4154..36d1440 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -136,8 +136,6 @@ static void ah_output_done(struct crypto_async_request *base, int err)
 		memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr));
 	}
 
-	err = ah->nexthdr;
-
 	kfree(AH_SKB_CB(skb)->tmp);
 	xfrm_output_resume(skb, err);
 }
@@ -264,12 +262,12 @@ static void ah_input_done(struct crypto_async_request *base, int err)
 	if (err)
 		goto out;
 
+	err = ah->nexthdr;
+
 	skb->network_header += ah_hlen;
 	memcpy(skb_network_header(skb), work_iph, ihl);
 	__skb_pull(skb, ah_hlen + ihl);
 	skb_set_transport_header(skb, -ihl);
-
-	err = ah->nexthdr;
 out:
 	kfree(AH_SKB_CB(skb)->tmp);
 	xfrm_input_resume(skb, err);
@@ -371,8 +369,6 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
 		if (err == -EINPROGRESS)
 			goto out;
 
-		if (err == -EBUSY)
-			err = NET_XMIT_DROP;
 		goto out_free;
 	}
 
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 1b74d3b..d8f852d 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -518,26 +518,32 @@ EXPORT_SYMBOL(arp_find);
 
 /* END OF OBSOLETE FUNCTIONS */
 
+struct neighbour *__arp_bind_neighbour(struct dst_entry *dst, __be32 nexthop)
+{
+	struct net_device *dev = dst->dev;
+
+	if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
+		nexthop = 0;
+	return __neigh_lookup_errno(
+#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE)
+		dev->type == ARPHRD_ATM ?
+		clip_tbl_hook :
+#endif
+		&arp_tbl, &nexthop, dev);
+}
+
 int arp_bind_neighbour(struct dst_entry *dst)
 {
 	struct net_device *dev = dst->dev;
-	struct neighbour *n = dst->neighbour;
+	struct neighbour *n = dst_get_neighbour(dst);
 
 	if (dev == NULL)
 		return -EINVAL;
 	if (n == NULL) {
-		__be32 nexthop = ((struct rtable *)dst)->rt_gateway;
-		if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
-			nexthop = 0;
-		n = __neigh_lookup_errno(
-#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE)
-					 dev->type == ARPHRD_ATM ?
-					 clip_tbl_hook :
-#endif
-					 &arp_tbl, &nexthop, dev);
+		n = __arp_bind_neighbour(dst, ((struct rtable *)dst)->rt_gateway);
 		if (IS_ERR(n))
 			return PTR_ERR(n);
-		dst->neighbour = n;
+		dst_set_neighbour(dst, n);
 	}
 	return 0;
 }
@@ -900,7 +906,8 @@ static int arp_process(struct sk_buff *skb)
 			if (addr_type == RTN_UNICAST  &&
 			    (arp_fwd_proxy(in_dev, dev, rt) ||
 			     arp_fwd_pvlan(in_dev, dev, rt, sip, tip) ||
-			     pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) {
+			     (rt->dst.dev != dev &&
+			      pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))) {
 				n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
 				if (n)
 					neigh_release(n);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 66439a7..c48323a 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1496,7 +1496,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write,
 			     void __user *buffer,
 			     size_t *lenp, loff_t *ppos)
 {
+	int old_value = *(int *)ctl->data;
 	int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+	int new_value = *(int *)ctl->data;
 
 	if (write) {
 		struct ipv4_devconf *cnf = ctl->extra1;
@@ -1507,6 +1509,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write,
 
 		if (cnf == net->ipv4.devconf_dflt)
 			devinet_copy_dflt_conf(net, i);
+		if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1)
+			if ((new_value == 0) && (old_value != 0))
+				rt_cache_flush(net, 0);
 	}
 
 	return ret;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index d577199..e0d42db 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -875,6 +875,8 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
 		 * to be intended in a v3 query.
 		 */
 		max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE);
+		if (!max_delay)
+			max_delay = 1;	/* can't mod w/ 0 */
 	} else { /* v3 */
 		if (!pskb_may_pull(skb, sizeof(struct igmpv3_query)))
 			return;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 3b34d1c..29a07b6 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -84,7 +84,7 @@ int ip_forward(struct sk_buff *skb)
 
 	rt = skb_rtable(skb);
 
-	if (opt->is_strictroute && ip_hdr(skb)->daddr != rt->rt_gateway)
+	if (opt->is_strictroute && opt->nexthop != rt->rt_gateway)
 		goto sr_failed;
 
 	if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 8871067..d7bb94c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -731,9 +731,9 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 		}
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 		else if (skb->protocol == htons(ETH_P_IPV6)) {
+			struct neighbour *neigh = dst_get_neighbour(skb_dst(skb));
 			const struct in6_addr *addr6;
 			int addr_type;
-			struct neighbour *neigh = skb_dst(skb)->neighbour;
 
 			if (neigh == NULL)
 				goto tx_error;
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index ec93335..42dd1a9 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -568,11 +568,12 @@ void ip_forward_options(struct sk_buff *skb)
 		     ) {
 			if (srrptr + 3 > srrspace)
 				break;
-			if (memcmp(&ip_hdr(skb)->daddr, &optptr[srrptr-1], 4) == 0)
+			if (memcmp(&opt->nexthop, &optptr[srrptr-1], 4) == 0)
 				break;
 		}
 		if (srrptr + 3 <= srrspace) {
 			opt->is_changed = 1;
+			ip_hdr(skb)->daddr = opt->nexthop;
 			ip_rt_get_source(&optptr[srrptr-1], skb, rt);
 			optptr[2] = srrptr+4;
 		} else if (net_ratelimit())
@@ -640,6 +641,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
 	}
 	if (srrptr <= srrspace) {
 		opt->srr_is_hit = 1;
+		opt->nexthop = nexthop;
 		opt->is_changed = 1;
 	}
 	return 0;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 0c99db4..51a3eec 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -182,6 +182,8 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	struct rtable *rt = (struct rtable *)dst;
 	struct net_device *dev = dst->dev;
 	unsigned int hh_len = LL_RESERVED_SPACE(dev);
+	struct neighbour *neigh;
+	int res;
 
 	if (rt->rt_type == RTN_MULTICAST) {
 		IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTMCAST, skb->len);
@@ -203,10 +205,22 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 		skb = skb2;
 	}
 
-	if (dst->hh)
-		return neigh_hh_output(dst->hh, skb);
-	else if (dst->neighbour)
-		return dst->neighbour->output(skb);
+	rcu_read_lock();
+	if (dst->hh) {
+		int res = neigh_hh_output(dst->hh, skb);
+
+		rcu_read_unlock();
+		return res;
+	} else {
+		neigh = dst_get_neighbour(dst);
+		if (neigh) {
+			res = neigh->output(skb);
+
+			rcu_read_unlock();
+			return res;
+		}
+		rcu_read_unlock();
+	}
 
 	if (net_ratelimit())
 		printk(KERN_DEBUG "ip_finish_output2: No header cache and no neighbour!\n");
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index ab7e554..7fbcaba 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -252,6 +252,10 @@ static int __init ic_open_devs(void)
 		}
 	}
 
+	/* no point in waiting if we could not bring up at least one device */
+	if (!ic_first_dev)
+		goto have_carrier;
+
 	/* wait for a carrier on at least one device */
 	start = jiffies;
 	while (jiffies - start < msecs_to_jiffies(CONF_CARRIER_TIMEOUT)) {
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 378b20b..6f06f7f 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -285,6 +285,8 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net,
 	if (register_netdevice(dev) < 0)
 		goto failed_free;
 
+	strcpy(nt->parms.name, dev->name);
+
 	dev_hold(dev);
 	ipip_tunnel_link(ipn, nt);
 	return nt;
@@ -759,7 +761,6 @@ static int ipip_tunnel_init(struct net_device *dev)
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 
 	tunnel->dev = dev;
-	strcpy(tunnel->parms.name, dev->name);
 
 	memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
 	memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
@@ -825,6 +826,7 @@ static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head)
 static int __net_init ipip_init_net(struct net *net)
 {
 	struct ipip_net *ipn = net_generic(net, ipip_net_id);
+	struct ip_tunnel *t;
 	int err;
 
 	ipn->tunnels[0] = ipn->tunnels_wc;
@@ -848,6 +850,9 @@ static int __net_init ipip_init_net(struct net *net)
 	if ((err = register_netdev(ipn->fb_tunnel_dev)))
 		goto err_reg_dev;
 
+	t = netdev_priv(ipn->fb_tunnel_dev);
+
+	strcpy(t->parms.name, ipn->fb_tunnel_dev->name);
 	return 0;
 
 err_reg_dev:
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 75ef66f..6b95f74 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -91,6 +91,7 @@
 #include <linux/rcupdate.h>
 #include <linux/times.h>
 #include <linux/slab.h>
+#include <linux/prefetch.h>
 #include <net/dst.h>
 #include <net/net_namespace.h>
 #include <net/protocol.h>
@@ -132,6 +133,9 @@ static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 static int rt_chain_length_max __read_mostly	= 20;
 
+static struct delayed_work expires_work;
+static unsigned long expires_ljiffies;
+
 /*
  *	Interface to generic destination cache.
  */
@@ -412,7 +416,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
 			   "HHUptod\tSpecDst");
 	else {
 		struct rtable *r = v;
-		int len;
+		struct neighbour *n;
+		int len, HHUptod;
+
+		rcu_read_lock();
+		n = dst_get_neighbour(&r->dst);
+		HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0;
+		rcu_read_unlock();
 
 		seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
 			      "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
@@ -427,8 +437,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
 			      dst_metric(&r->dst, RTAX_RTTVAR)),
 			r->rt_key_tos,
 			r->dst.hh ? atomic_read(&r->dst.hh->hh_refcnt) : -1,
-			r->dst.hh ? (r->dst.hh->hh_output ==
-				       dev_queue_xmit) : 0,
+			HHUptod,
 			r->rt_spec_dst, &len);
 
 		seq_printf(seq, "%*s\n", 127 - len, "");
@@ -821,6 +830,97 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth)
 	return ONE;
 }
 
+static void rt_check_expire(void)
+{
+	static unsigned int rover;
+	unsigned int i = rover, goal;
+	struct rtable *rth;
+	struct rtable __rcu **rthp;
+	unsigned long samples = 0;
+	unsigned long sum = 0, sum2 = 0;
+	unsigned long delta;
+	u64 mult;
+
+	delta = jiffies - expires_ljiffies;
+	expires_ljiffies = jiffies;
+	mult = ((u64)delta) << rt_hash_log;
+	if (ip_rt_gc_timeout > 1)
+		do_div(mult, ip_rt_gc_timeout);
+	goal = (unsigned int)mult;
+	if (goal > rt_hash_mask)
+		goal = rt_hash_mask + 1;
+	for (; goal > 0; goal--) {
+		unsigned long tmo = ip_rt_gc_timeout;
+		unsigned long length;
+
+		i = (i + 1) & rt_hash_mask;
+		rthp = &rt_hash_table[i].chain;
+
+		if (need_resched())
+			cond_resched();
+
+		samples++;
+
+		if (rcu_dereference_raw(*rthp) == NULL)
+			continue;
+		length = 0;
+		spin_lock_bh(rt_hash_lock_addr(i));
+		while ((rth = rcu_dereference_protected(*rthp,
+					lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) {
+			prefetch(rth->dst.rt_next);
+			if (rt_is_expired(rth)) {
+				*rthp = rth->dst.rt_next;
+				rt_free(rth);
+				continue;
+			}
+			if (rth->dst.expires) {
+				/* Entry is expired even if it is in use */
+				if (time_before_eq(jiffies, rth->dst.expires)) {
+nofree:
+					tmo >>= 1;
+					rthp = &rth->dst.rt_next;
+					/*
+					 * We only count entries on
+					 * a chain with equal hash inputs once
+					 * so that entries for different QOS
+					 * levels, and other non-hash input
+					 * attributes don't unfairly skew
+					 * the length computation
+					 */
+					length += has_noalias(rt_hash_table[i].chain, rth);
+					continue;
+				}
+			} else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
+				goto nofree;
+
+			/* Cleanup aged off entries. */
+			*rthp = rth->dst.rt_next;
+			rt_free(rth);
+		}
+		spin_unlock_bh(rt_hash_lock_addr(i));
+		sum += length;
+		sum2 += length*length;
+	}
+	if (samples) {
+		unsigned long avg = sum / samples;
+		unsigned long sd = int_sqrt(sum2 / samples - avg*avg);
+		rt_chain_length_max = max_t(unsigned long,
+					ip_rt_gc_elasticity,
+					(avg + 4*sd) >> FRACT_BITS);
+	}
+	rover = i;
+}
+
+/*
+ * rt_worker_func() is run in process context.
+ * we call rt_check_expire() to scan part of the hash table
+ */
+static void rt_worker_func(struct work_struct *work)
+{
+	rt_check_expire();
+	schedule_delayed_work(&expires_work, ip_rt_gc_interval);
+}
+
 /*
  * Perturbation of rt_genid by a small quantity [1..256]
  * Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
@@ -1269,11 +1369,41 @@ static void rt_del(unsigned hash, struct rtable *rt)
 	spin_unlock_bh(rt_hash_lock_addr(hash));
 }
 
+static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
+{
+	struct rtable *rt = (struct rtable *) dst;
+	__be32 orig_gw = rt->rt_gateway;
+	struct neighbour *n, *old_n;
+
+	dst_confirm(&rt->dst);
+
+	rt->rt_gateway = peer->redirect_learned.a4;
+	n = __arp_bind_neighbour(&rt->dst, rt->rt_gateway);
+	if (IS_ERR(n))
+		return PTR_ERR(n);
+	old_n = xchg(&rt->dst._neighbour, n);
+	if (old_n)
+		neigh_release(old_n);
+	if (!n || !(n->nud_state & NUD_VALID)) {
+		if (n)
+			neigh_event_send(n, NULL);
+		rt->rt_gateway = orig_gw;
+		return -EAGAIN;
+	} else {
+		rt->rt_flags |= RTCF_REDIRECTED;
+		call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
+	}
+	return 0;
+}
+
 /* called in rcu_read_lock() section */
 void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 		    __be32 saddr, struct net_device *dev)
 {
+	int s, i;
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
+	__be32 skeys[2] = { saddr, 0 };
+	int    ikeys[2] = { dev->ifindex, 0 };
 	struct inet_peer *peer;
 	struct net *net;
 
@@ -1296,13 +1426,43 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 			goto reject_redirect;
 	}
 
-	peer = inet_getpeer_v4(daddr, 1);
-	if (peer) {
-		peer->redirect_learned.a4 = new_gw;
+	for (s = 0; s < 2; s++) {
+		for (i = 0; i < 2; i++) {
+			unsigned int hash;
+			struct rtable __rcu **rthp;
+			struct rtable *rt;
 
-		inet_putpeer(peer);
+			hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net));
 
-		atomic_inc(&__rt_peer_genid);
+			rthp = &rt_hash_table[hash].chain;
+
+			while ((rt = rcu_dereference(*rthp)) != NULL) {
+				rthp = &rt->dst.rt_next;
+
+				if (rt->rt_key_dst != daddr ||
+				    rt->rt_key_src != skeys[s] ||
+				    rt->rt_oif != ikeys[i] ||
+				    rt_is_input_route(rt) ||
+				    rt_is_expired(rt) ||
+				    !net_eq(dev_net(rt->dst.dev), net) ||
+				    rt->dst.error ||
+				    rt->dst.dev != dev ||
+				    rt->rt_gateway != old_gw)
+					continue;
+
+				if (!rt->peer)
+					rt_bind_peer(rt, rt->rt_dst, 1);
+
+				peer = rt->peer;
+				if (peer) {
+					if (peer->redirect_learned.a4 != new_gw) {
+						peer->redirect_learned.a4 = new_gw;
+						atomic_inc(&__rt_peer_genid);
+					}
+					check_peer_redir(&rt->dst, peer);
+				}
+			}
+		}
 	}
 	return;
 
@@ -1589,31 +1749,6 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 	}
 }
 
-static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
-{
-	struct rtable *rt = (struct rtable *) dst;
-	__be32 orig_gw = rt->rt_gateway;
-
-	dst_confirm(&rt->dst);
-
-	neigh_release(rt->dst.neighbour);
-	rt->dst.neighbour = NULL;
-
-	rt->rt_gateway = peer->redirect_learned.a4;
-	if (arp_bind_neighbour(&rt->dst) ||
-	    !(rt->dst.neighbour->nud_state & NUD_VALID)) {
-		if (rt->dst.neighbour)
-			neigh_event_send(rt->dst.neighbour, NULL);
-		rt->rt_gateway = orig_gw;
-		return -EAGAIN;
-	} else {
-		rt->rt_flags |= RTCF_REDIRECTED;
-		call_netevent_notifiers(NETEVENT_NEIGH_UPDATE,
-					rt->dst.neighbour);
-	}
-	return 0;
-}
-
 static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 {
 	struct rtable *rt = (struct rtable *) dst;
@@ -3088,6 +3223,13 @@ static ctl_table ipv4_route_table[] = {
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
+		.procname	= "gc_interval",
+		.data		= &ip_rt_gc_interval,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{
 		.procname	= "redirect_load",
 		.data		= &ip_rt_redirect_load,
 		.maxlen		= sizeof(int),
@@ -3297,6 +3439,11 @@ int __init ip_rt_init(void)
 	devinet_init();
 	ip_fib_init();
 
+	INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func);
+	expires_ljiffies = jiffies;
+	schedule_delayed_work(&expires_work,
+		net_random() % ip_rt_gc_interval + ip_rt_gc_interval);
+
 	if (ip_rt_proc_init())
 		printk(KERN_ERR "Unable to create route proc files\n");
 #ifdef CONFIG_XFRM
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 4382629..895f215 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -277,6 +277,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	struct rtable *rt;
 	__u8 rcv_wscale;
 	bool ecn_ok = false;
+	struct flowi4 fl4;
 
 	if (!sysctl_tcp_syncookies || !th->ack || th->rst)
 		goto out;
@@ -344,20 +345,16 @@ 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.
 	 */
-	{
-		struct flowi4 fl4;
-
-		flowi4_init_output(&fl4, 0, 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);
-		security_req_classify_flow(req, flowi4_to_flowi(&fl4));
-		rt = ip_route_output_key(sock_net(sk), &fl4);
-		if (IS_ERR(rt)) {
-			reqsk_free(req);
-			goto out;
-		}
+	flowi4_init_output(&fl4, 0, 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);
+	security_req_classify_flow(req, flowi4_to_flowi(&fl4));
+	rt = ip_route_output_key(sock_net(sk), &fl4);
+	if (IS_ERR(rt)) {
+		reqsk_free(req);
+		goto out;
 	}
 
 	/* Try to redo what tcp_v4_send_synack did. */
@@ -371,5 +368,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	ireq->rcv_wscale  = rcv_wscale;
 
 	ret = get_cookie_sock(sk, skb, req, &rt->dst);
+	/* ip_queue_xmit() depends on our flow being setup
+	 * Normal sockets get it right from inet_csk_route_child_sock()
+	 */
+	if (ret)
+		inet_sk(ret)->cork.fl.u.ip4 = fl4;
 out:	return ret;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b6771f9..72b1857 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1289,25 +1289,26 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
 	return in_sack;
 }
 
-static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk,
-			  struct tcp_sacktag_state *state,
+/* Mark the given newly-SACKed range as such, adjusting counters and hints. */
+static u8 tcp_sacktag_one(struct sock *sk,
+			  struct tcp_sacktag_state *state, u8 sacked,
+			  u32 start_seq, u32 end_seq,
 			  int dup_sack, int pcount)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	u8 sacked = TCP_SKB_CB(skb)->sacked;
 	int fack_count = state->fack_count;
 
 	/* Account D-SACK for retransmitted packet. */
 	if (dup_sack && (sacked & TCPCB_RETRANS)) {
 		if (tp->undo_marker && tp->undo_retrans &&
-		    after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker))
+		    after(end_seq, tp->undo_marker))
 			tp->undo_retrans--;
 		if (sacked & TCPCB_SACKED_ACKED)
 			state->reord = min(fack_count, state->reord);
 	}
 
 	/* Nothing to do; acked frame is about to be dropped (was ACKed). */
-	if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
+	if (!after(end_seq, tp->snd_una))
 		return sacked;
 
 	if (!(sacked & TCPCB_SACKED_ACKED)) {
@@ -1326,13 +1327,13 @@ static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk,
 				/* New sack for not retransmitted frame,
 				 * which was in hole. It is reordering.
 				 */
-				if (before(TCP_SKB_CB(skb)->seq,
+				if (before(start_seq,
 					   tcp_highest_sack_seq(tp)))
 					state->reord = min(fack_count,
 							   state->reord);
 
 				/* SACK enhanced F-RTO (RFC4138; Appendix B) */
-				if (!after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark))
+				if (!after(end_seq, tp->frto_highmark))
 					state->flag |= FLAG_ONLY_ORIG_SACKED;
 			}
 
@@ -1350,8 +1351,7 @@ static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk,
 
 		/* Lost marker hint past SACKed? Tweak RFC3517 cnt */
 		if (!tcp_is_fack(tp) && (tp->lost_skb_hint != NULL) &&
-		    before(TCP_SKB_CB(skb)->seq,
-			   TCP_SKB_CB(tp->lost_skb_hint)->seq))
+		    before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq))
 			tp->lost_cnt_hint += pcount;
 
 		if (fack_count > tp->fackets_out)
@@ -1370,6 +1370,9 @@ static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk,
 	return sacked;
 }
 
+/* Shift newly-SACKed bytes from this skb to the immediately previous
+ * already-SACKed sk_buff. Mark the newly-SACKed bytes as such.
+ */
 static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 			   struct tcp_sacktag_state *state,
 			   unsigned int pcount, int shifted, int mss,
@@ -1377,12 +1380,21 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *prev = tcp_write_queue_prev(sk, skb);
+	u32 start_seq = TCP_SKB_CB(skb)->seq;	/* start of newly-SACKed */
+	u32 end_seq = start_seq + shifted;	/* end of newly-SACKed */
 
 	BUG_ON(!pcount);
 
-	/* Tweak before seqno plays */
-	if (!tcp_is_fack(tp) && tcp_is_sack(tp) && tp->lost_skb_hint &&
-	    !before(TCP_SKB_CB(tp->lost_skb_hint)->seq, TCP_SKB_CB(skb)->seq))
+	/* Adjust counters and hints for the newly sacked sequence
+	 * range but discard the return value since prev is already
+	 * marked. We must tag the range first because the seq
+	 * advancement below implicitly advances
+	 * tcp_highest_sack_seq() when skb is highest_sack.
+	 */
+	tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
+			start_seq, end_seq, dup_sack, pcount);
+
+	if (skb == tp->lost_skb_hint)
 		tp->lost_cnt_hint += pcount;
 
 	TCP_SKB_CB(prev)->end_seq += shifted;
@@ -1408,9 +1420,6 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 		skb_shinfo(skb)->gso_type = 0;
 	}
 
-	/* We discard results */
-	tcp_sacktag_one(skb, sk, state, dup_sack, pcount);
-
 	/* Difference in this won't matter, both ACKed by the same cumul. ACK */
 	TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS);
 
@@ -1558,6 +1567,10 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 		}
 	}
 
+	/* tcp_sacktag_one() won't SACK-tag ranges below snd_una */
+	if (!after(TCP_SKB_CB(skb)->seq + len, tp->snd_una))
+		goto fallback;
+
 	if (!skb_shift(prev, skb, len))
 		goto fallback;
 	if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack))
@@ -1648,10 +1661,14 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
 			break;
 
 		if (in_sack) {
-			TCP_SKB_CB(skb)->sacked = tcp_sacktag_one(skb, sk,
-								  state,
-								  dup_sack,
-								  tcp_skb_pcount(skb));
+			TCP_SKB_CB(skb)->sacked =
+				tcp_sacktag_one(sk,
+						state,
+						TCP_SKB_CB(skb)->sacked,
+						TCP_SKB_CB(skb)->seq,
+						TCP_SKB_CB(skb)->end_seq,
+						dup_sack,
+						tcp_skb_pcount(skb));
 
 			if (!before(TCP_SKB_CB(skb)->seq,
 				    tcp_highest_sack_seq(tp)))
@@ -2536,6 +2553,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 
 		if (cnt > packets) {
 			if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) ||
+			    (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
 			    (oldcnt >= packets))
 				break;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b3e6956..53a5af6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -630,7 +630,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 	arg.iov[0].iov_len  = sizeof(rep.th);
 
 #ifdef CONFIG_TCP_MD5SIG
-	key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr) : NULL;
+	key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->saddr) : NULL;
 	if (key) {
 		rep.opt[0] = htonl((TCPOPT_NOP << 24) |
 				   (TCPOPT_NOP << 16) |
@@ -650,6 +650,11 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 				      arg.iov[0].iov_len, IPPROTO_TCP, 0);
 	arg.csumoffset = offsetof(struct tcphdr, check) / 2;
 	arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0;
+	/* When socket is gone, all binding information is lost.
+	 * routing might fail in this case. using iif for oif to
+	 * make sure we can deliver it
+	 */
+	arg.bound_dev_if = sk ? sk->sk_bound_dev_if : inet_iif(skb);
 
 	net = dev_net(skb_dst(skb)->dev);
 	ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr,
@@ -909,18 +914,21 @@ int tcp_v4_md5_do_add(struct sock *sk, __be32 addr,
 			}
 			sk_nocaps_add(sk, NETIF_F_GSO_MASK);
 		}
-		if (tcp_alloc_md5sig_pool(sk) == NULL) {
+
+		md5sig = tp->md5sig_info;
+		if (md5sig->entries4 == 0 &&
+		    tcp_alloc_md5sig_pool(sk) == NULL) {
 			kfree(newkey);
 			return -ENOMEM;
 		}
-		md5sig = tp->md5sig_info;
 
 		if (md5sig->alloced4 == md5sig->entries4) {
 			keys = kmalloc((sizeof(*keys) *
 					(md5sig->entries4 + 1)), GFP_ATOMIC);
 			if (!keys) {
 				kfree(newkey);
-				tcp_free_md5sig_pool();
+				if (md5sig->entries4 == 0)
+					tcp_free_md5sig_pool();
 				return -ENOMEM;
 			}
 
@@ -964,6 +972,7 @@ int tcp_v4_md5_do_del(struct sock *sk, __be32 addr)
 				kfree(tp->md5sig_info->keys4);
 				tp->md5sig_info->keys4 = NULL;
 				tp->md5sig_info->alloced4 = 0;
+				tcp_free_md5sig_pool();
 			} else if (tp->md5sig_info->entries4 != i) {
 				/* Need to do some manipulation */
 				memmove(&tp->md5sig_info->keys4[i],
@@ -971,7 +980,6 @@ int tcp_v4_md5_do_del(struct sock *sk, __be32 addr)
 					(tp->md5sig_info->entries4 - i) *
 					 sizeof(struct tcp4_md5sig_key));
 			}
-			tcp_free_md5sig_pool();
 			return 0;
 		}
 	}
@@ -1446,9 +1454,13 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
 	newinet->inet_id = newtp->write_seq ^ jiffies;
 
-	if (!dst && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL)
-		goto put_and_exit;
-
+	if (!dst) {
+		dst = inet_csk_route_child_sock(sk, newsk, req);
+		if (!dst)
+			goto put_and_exit;
+	} else {
+		/* syncookie case : see end of cookie_v4_check() */
+	}
 	sk_setup_caps(newsk, dst);
 
 	tcp_mtup_init(newsk);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 882e0b0..faf257b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1134,11 +1134,9 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 	sk_mem_uncharge(sk, len);
 	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
 
-	/* Any change of skb->len requires recalculation of tso
-	 * factor and mss.
-	 */
+	/* Any change of skb->len requires recalculation of tso factor. */
 	if (tcp_skb_pcount(skb) > 1)
-		tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk));
+		tcp_set_skb_tso_segs(sk, skb, tcp_skb_mss(skb));
 
 	return 0;
 }
diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c
index 6341818..e3db3f9 100644
--- a/net/ipv4/xfrm4_mode_beet.c
+++ b/net/ipv4/xfrm4_mode_beet.c
@@ -110,10 +110,7 @@ static int xfrm4_beet_input(struct xfrm_state *x, struct sk_buff *skb)
 
 	skb_push(skb, sizeof(*iph));
 	skb_reset_network_header(skb);
-
-	memmove(skb->data - skb->mac_len, skb_mac_header(skb),
-		skb->mac_len);
-	skb_set_mac_header(skb, -skb->mac_len);
+	skb_mac_header_rebuild(skb);
 
 	xfrm4_beet_make_header(skb);
 
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 534972e..ed4bf11 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -66,7 +66,6 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 
 static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 {
-	const unsigned char *old_mac;
 	int err = -EINVAL;
 
 	if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP)
@@ -84,10 +83,9 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 	if (!(x->props.flags & XFRM_STATE_NOECN))
 		ipip_ecn_decapsulate(skb);
 
-	old_mac = skb_mac_header(skb);
-	skb_set_mac_header(skb, -skb->mac_len);
-	memmove(skb_mac_header(skb), old_mac, skb->mac_len);
 	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+
 	err = 0;
 
 out:
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 981e43e..581fe0a 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -79,13 +79,13 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	struct rtable *rt = (struct rtable *)xdst->route;
 	const struct flowi4 *fl4 = &fl->u.ip4;
 
-	rt->rt_key_dst = fl4->daddr;
-	rt->rt_key_src = fl4->saddr;
-	rt->rt_key_tos = fl4->flowi4_tos;
-	rt->rt_route_iif = fl4->flowi4_iif;
-	rt->rt_iif = fl4->flowi4_iif;
-	rt->rt_oif = fl4->flowi4_oif;
-	rt->rt_mark = fl4->flowi4_mark;
+	xdst->u.rt.rt_key_dst = fl4->daddr;
+	xdst->u.rt.rt_key_src = fl4->saddr;
+	xdst->u.rt.rt_key_tos = fl4->flowi4_tos;
+	xdst->u.rt.rt_route_iif = fl4->flowi4_iif;
+	xdst->u.rt.rt_iif = fl4->flowi4_iif;
+	xdst->u.rt.rt_oif = fl4->flowi4_oif;
+	xdst->u.rt.rt_mark = fl4->flowi4_mark;
 
 	xdst->u.dst.dev = dev;
 	dev_hold(dev);