Merge branch 'for-bfields' of git://linux-nfs.org/~tomtucker/xprt-switch-2.6 into for-2.6.27

21 files changed, 110 insertions, 409 deletions

diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 418862f..9b539fa 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1288,7 +1288,6 @@ static void arp_format_neigh_entry(struct seq_file *seq,
 				   struct neighbour *n)
 {
 	char hbuffer[HBUFFERLEN];
-	const char hexbuf[] = "0123456789ABCDEF";
 	int k, j;
 	char tbuf[16];
 	struct net_device *dev = n->dev;
@@ -1302,8 +1301,8 @@ static void arp_format_neigh_entry(struct seq_file *seq,
 	else {
 #endif
 	for (k = 0, j = 0; k < HBUFFERLEN - 3 && j < dev->addr_len; j++) {
-		hbuffer[k++] = hexbuf[(n->ha[j] >> 4) & 15];
-		hbuffer[k++] = hexbuf[n->ha[j] & 15];
+		hbuffer[k++] = hex_asc_hi(n->ha[j]);
+		hbuffer[k++] = hex_asc_lo(n->ha[j]);
 		hbuffer[k++] = ':';
 	}
 	hbuffer[--k] = 0;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 6848e47..79a7ef6 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -90,7 +90,6 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
 	[IFA_LOCAL]     	= { .type = NLA_U32 },
 	[IFA_ADDRESS]   	= { .type = NLA_U32 },
 	[IFA_BROADCAST] 	= { .type = NLA_U32 },
-	[IFA_ANYCAST]   	= { .type = NLA_U32 },
 	[IFA_LABEL]     	= { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
 };
 
@@ -536,9 +535,6 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh)
 	if (tb[IFA_BROADCAST])
 		ifa->ifa_broadcast = nla_get_be32(tb[IFA_BROADCAST]);
 
-	if (tb[IFA_ANYCAST])
-		ifa->ifa_anycast = nla_get_be32(tb[IFA_ANYCAST]);
-
 	if (tb[IFA_LABEL])
 		nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
 	else
@@ -745,7 +741,6 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 				break;
 			inet_del_ifa(in_dev, ifap, 0);
 			ifa->ifa_broadcast = 0;
-			ifa->ifa_anycast = 0;
 			ifa->ifa_scope = 0;
 		}
 
@@ -1113,7 +1108,6 @@ static inline size_t inet_nlmsg_size(void)
 	       + nla_total_size(4) /* IFA_ADDRESS */
 	       + nla_total_size(4) /* IFA_LOCAL */
 	       + nla_total_size(4) /* IFA_BROADCAST */
-	       + nla_total_size(4) /* IFA_ANYCAST */
 	       + nla_total_size(IFNAMSIZ); /* IFA_LABEL */
 }
 
@@ -1143,9 +1137,6 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
 	if (ifa->ifa_broadcast)
 		NLA_PUT_BE32(skb, IFA_BROADCAST, ifa->ifa_broadcast);
 
-	if (ifa->ifa_anycast)
-		NLA_PUT_BE32(skb, IFA_ANYCAST, ifa->ifa_anycast);
-
 	if (ifa->ifa_label[0])
 		NLA_PUT_STRING(skb, IFA_LABEL, ifa->ifa_label);
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 0f1557a..0b2ac6a 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -506,7 +506,6 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX+1] = {
 	[RTA_PREFSRC]		= { .type = NLA_U32 },
 	[RTA_METRICS]		= { .type = NLA_NESTED },
 	[RTA_MULTIPATH]		= { .len = sizeof(struct rtnexthop) },
-	[RTA_PROTOINFO]		= { .type = NLA_U32 },
 	[RTA_FLOW]		= { .type = NLA_U32 },
 };
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 3b83c34..0d4d728 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -960,7 +960,10 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
 	rtm->rtm_dst_len = dst_len;
 	rtm->rtm_src_len = 0;
 	rtm->rtm_tos = tos;
-	rtm->rtm_table = tb_id;
+	if (tb_id < 256)
+		rtm->rtm_table = tb_id;
+	else
+		rtm->rtm_table = RT_TABLE_COMPAT;
 	NLA_PUT_U32(skb, RTA_TABLE, tb_id);
 	rtm->rtm_type = type;
 	rtm->rtm_flags = fi->fib_flags;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 828ea21..ec83448 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -419,7 +419,8 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
 	struct inet_connection_sock *icsk = inet_csk(parent);
 	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
 	struct listen_sock *lopt = queue->listen_opt;
-	int thresh = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
+	int max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
+	int thresh = max_retries;
 	unsigned long now = jiffies;
 	struct request_sock **reqp, *req;
 	int i, budget;
@@ -455,6 +456,9 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
 		}
 	}
 
+	if (queue->rskq_defer_accept)
+		max_retries = queue->rskq_defer_accept;
+
 	budget = 2 * (lopt->nr_table_entries / (timeout / interval));
 	i = lopt->clock_hand;
 
@@ -462,8 +466,9 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
 		reqp=&lopt->syn_table[i];
 		while ((req = *reqp) != NULL) {
 			if (time_after_eq(now, req->expires)) {
-				if (req->retrans < thresh &&
-				    !req->rsk_ops->rtx_syn_ack(parent, req)) {
+				if ((req->retrans < thresh ||
+				     (inet_rsk(req)->acked && req->retrans < max_retries))
+				    && !req->rsk_ops->rtx_syn_ack(parent, req)) {
 					unsigned long timeo;
 
 					if (req->retrans++ == 0)
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 2ada033..4342cba 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -313,9 +313,8 @@ static void ipgre_tunnel_uninit(struct net_device *dev)
 
 static void ipgre_err(struct sk_buff *skb, u32 info)
 {
-#ifndef I_WISH_WORLD_WERE_PERFECT
 
-/* It is not :-( All the routers (except for Linux) return only
+/* All the routers (except for Linux) return only
    8 bytes of packet payload. It means, that precise relaying of
    ICMP in the real Internet is absolutely infeasible.
 
@@ -398,149 +397,6 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
 out:
 	read_unlock(&ipgre_lock);
 	return;
-#else
-	struct iphdr *iph = (struct iphdr*)dp;
-	struct iphdr *eiph;
-	__be16	     *p = (__be16*)(dp+(iph->ihl<<2));
-	const int type = icmp_hdr(skb)->type;
-	const int code = icmp_hdr(skb)->code;
-	int rel_type = 0;
-	int rel_code = 0;
-	__be32 rel_info = 0;
-	__u32 n = 0;
-	__be16 flags;
-	int grehlen = (iph->ihl<<2) + 4;
-	struct sk_buff *skb2;
-	struct flowi fl;
-	struct rtable *rt;
-
-	if (p[1] != htons(ETH_P_IP))
-		return;
-
-	flags = p[0];
-	if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
-		if (flags&(GRE_VERSION|GRE_ROUTING))
-			return;
-		if (flags&GRE_CSUM)
-			grehlen += 4;
-		if (flags&GRE_KEY)
-			grehlen += 4;
-		if (flags&GRE_SEQ)
-			grehlen += 4;
-	}
-	if (len < grehlen + sizeof(struct iphdr))
-		return;
-	eiph = (struct iphdr*)(dp + grehlen);
-
-	switch (type) {
-	default:
-		return;
-	case ICMP_PARAMETERPROB:
-		n = ntohl(icmp_hdr(skb)->un.gateway) >> 24;
-		if (n < (iph->ihl<<2))
-			return;
-
-		/* So... This guy found something strange INSIDE encapsulated
-		   packet. Well, he is fool, but what can we do ?
-		 */
-		rel_type = ICMP_PARAMETERPROB;
-		n -= grehlen;
-		rel_info = htonl(n << 24);
-		break;
-
-	case ICMP_DEST_UNREACH:
-		switch (code) {
-		case ICMP_SR_FAILED:
-		case ICMP_PORT_UNREACH:
-			/* Impossible event. */
-			return;
-		case ICMP_FRAG_NEEDED:
-			/* And it is the only really necessary thing :-) */
-			n = ntohs(icmp_hdr(skb)->un.frag.mtu);
-			if (n < grehlen+68)
-				return;
-			n -= grehlen;
-			/* BSD 4.2 MORE DOES NOT EXIST IN NATURE. */
-			if (n > ntohs(eiph->tot_len))
-				return;
-			rel_info = htonl(n);
-			break;
-		default:
-			/* All others are translated to HOST_UNREACH.
-			   rfc2003 contains "deep thoughts" about NET_UNREACH,
-			   I believe, it is just ether pollution. --ANK
-			 */
-			rel_type = ICMP_DEST_UNREACH;
-			rel_code = ICMP_HOST_UNREACH;
-			break;
-		}
-		break;
-	case ICMP_TIME_EXCEEDED:
-		if (code != ICMP_EXC_TTL)
-			return;
-		break;
-	}
-
-	/* Prepare fake skb to feed it to icmp_send */
-	skb2 = skb_clone(skb, GFP_ATOMIC);
-	if (skb2 == NULL)
-		return;
-	dst_release(skb2->dst);
-	skb2->dst = NULL;
-	skb_pull(skb2, skb->data - (u8*)eiph);
-	skb_reset_network_header(skb2);
-
-	/* Try to guess incoming interface */
-	memset(&fl, 0, sizeof(fl));
-	fl.fl4_dst = eiph->saddr;
-	fl.fl4_tos = RT_TOS(eiph->tos);
-	fl.proto = IPPROTO_GRE;
-	if (ip_route_output_key(dev_net(skb->dev), &rt, &fl)) {
-		kfree_skb(skb2);
-		return;
-	}
-	skb2->dev = rt->u.dst.dev;
-
-	/* route "incoming" packet */
-	if (rt->rt_flags&RTCF_LOCAL) {
-		ip_rt_put(rt);
-		rt = NULL;
-		fl.fl4_dst = eiph->daddr;
-		fl.fl4_src = eiph->saddr;
-		fl.fl4_tos = eiph->tos;
-		if (ip_route_output_key(dev_net(skb->dev), &rt, &fl) ||
-		    rt->u.dst.dev->type != ARPHRD_IPGRE) {
-			ip_rt_put(rt);
-			kfree_skb(skb2);
-			return;
-		}
-	} else {
-		ip_rt_put(rt);
-		if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) ||
-		    skb2->dst->dev->type != ARPHRD_IPGRE) {
-			kfree_skb(skb2);
-			return;
-		}
-	}
-
-	/* change mtu on this route */
-	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
-		if (n > dst_mtu(skb2->dst)) {
-			kfree_skb(skb2);
-			return;
-		}
-		skb2->dst->ops->update_pmtu(skb2->dst, n);
-	} else if (type == ICMP_TIME_EXCEEDED) {
-		struct ip_tunnel *t = netdev_priv(skb2->dev);
-		if (t->parms.iph.ttl) {
-			rel_type = ICMP_DEST_UNREACH;
-			rel_code = ICMP_HOST_UNREACH;
-		}
-	}
-
-	icmp_send(skb2, rel_type, rel_code, rel_info);
-	kfree_skb(skb2);
-#endif
 }
 
 static inline void ipgre_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb)
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 149111f..af5cb53 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -278,9 +278,8 @@ static void ipip_tunnel_uninit(struct net_device *dev)
 
 static int ipip_err(struct sk_buff *skb, u32 info)
 {
-#ifndef I_WISH_WORLD_WERE_PERFECT
 
-/* It is not :-( All the routers (except for Linux) return only
+/* All the routers (except for Linux) return only
    8 bytes of packet payload. It means, that precise relaying of
    ICMP in the real Internet is absolutely infeasible.
  */
@@ -337,133 +336,6 @@ static int ipip_err(struct sk_buff *skb, u32 info)
 out:
 	read_unlock(&ipip_lock);
 	return err;
-#else
-	struct iphdr *iph = (struct iphdr*)dp;
-	int hlen = iph->ihl<<2;
-	struct iphdr *eiph;
-	const int type = icmp_hdr(skb)->type;
-	const int code = icmp_hdr(skb)->code;
-	int rel_type = 0;
-	int rel_code = 0;
-	__be32 rel_info = 0;
-	__u32 n = 0;
-	struct sk_buff *skb2;
-	struct flowi fl;
-	struct rtable *rt;
-
-	if (len < hlen + sizeof(struct iphdr))
-		return 0;
-	eiph = (struct iphdr*)(dp + hlen);
-
-	switch (type) {
-	default:
-		return 0;
-	case ICMP_PARAMETERPROB:
-		n = ntohl(icmp_hdr(skb)->un.gateway) >> 24;
-		if (n < hlen)
-			return 0;
-
-		/* So... This guy found something strange INSIDE encapsulated
-		   packet. Well, he is fool, but what can we do ?
-		 */
-		rel_type = ICMP_PARAMETERPROB;
-		rel_info = htonl((n - hlen) << 24);
-		break;
-
-	case ICMP_DEST_UNREACH:
-		switch (code) {
-		case ICMP_SR_FAILED:
-		case ICMP_PORT_UNREACH:
-			/* Impossible event. */
-			return 0;
-		case ICMP_FRAG_NEEDED:
-			/* And it is the only really necessary thing :-) */
-			n = ntohs(icmp_hdr(skb)->un.frag.mtu);
-			if (n < hlen+68)
-				return 0;
-			n -= hlen;
-			/* BSD 4.2 MORE DOES NOT EXIST IN NATURE. */
-			if (n > ntohs(eiph->tot_len))
-				return 0;
-			rel_info = htonl(n);
-			break;
-		default:
-			/* All others are translated to HOST_UNREACH.
-			   rfc2003 contains "deep thoughts" about NET_UNREACH,
-			   I believe, it is just ether pollution. --ANK
-			 */
-			rel_type = ICMP_DEST_UNREACH;
-			rel_code = ICMP_HOST_UNREACH;
-			break;
-		}
-		break;
-	case ICMP_TIME_EXCEEDED:
-		if (code != ICMP_EXC_TTL)
-			return 0;
-		break;
-	}
-
-	/* Prepare fake skb to feed it to icmp_send */
-	skb2 = skb_clone(skb, GFP_ATOMIC);
-	if (skb2 == NULL)
-		return 0;
-	dst_release(skb2->dst);
-	skb2->dst = NULL;
-	skb_pull(skb2, skb->data - (u8*)eiph);
-	skb_reset_network_header(skb2);
-
-	/* Try to guess incoming interface */
-	memset(&fl, 0, sizeof(fl));
-	fl.fl4_daddr = eiph->saddr;
-	fl.fl4_tos = RT_TOS(eiph->tos);
-	fl.proto = IPPROTO_IPIP;
-	if (ip_route_output_key(dev_net(skb->dev), &rt, &key)) {
-		kfree_skb(skb2);
-		return 0;
-	}
-	skb2->dev = rt->u.dst.dev;
-
-	/* route "incoming" packet */
-	if (rt->rt_flags&RTCF_LOCAL) {
-		ip_rt_put(rt);
-		rt = NULL;
-		fl.fl4_daddr = eiph->daddr;
-		fl.fl4_src = eiph->saddr;
-		fl.fl4_tos = eiph->tos;
-		if (ip_route_output_key(dev_net(skb->dev), &rt, &fl) ||
-		    rt->u.dst.dev->type != ARPHRD_TUNNEL) {
-			ip_rt_put(rt);
-			kfree_skb(skb2);
-			return 0;
-		}
-	} else {
-		ip_rt_put(rt);
-		if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) ||
-		    skb2->dst->dev->type != ARPHRD_TUNNEL) {
-			kfree_skb(skb2);
-			return 0;
-		}
-	}
-
-	/* change mtu on this route */
-	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
-		if (n > dst_mtu(skb2->dst)) {
-			kfree_skb(skb2);
-			return 0;
-		}
-		skb2->dst->ops->update_pmtu(skb2->dst, n);
-	} else if (type == ICMP_TIME_EXCEEDED) {
-		struct ip_tunnel *t = netdev_priv(skb2->dev);
-		if (t->parms.iph.ttl) {
-			rel_type = ICMP_DEST_UNREACH;
-			rel_code = ICMP_HOST_UNREACH;
-		}
-	}
-
-	icmp_send(skb2, rel_type, rel_code, rel_info);
-	kfree_skb(skb2);
-	return 0;
-#endif
 }
 
 static inline void ipip_ecn_decapsulate(const struct iphdr *outer_iph,
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 0457859..d2a887f 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -556,7 +556,6 @@ static void nf_nat_cleanup_conntrack(struct nf_conn *ct)
 
 	spin_lock_bh(&nf_nat_lock);
 	hlist_del_rcu(&nat->bysource);
-	nat->ct = NULL;
 	spin_unlock_bh(&nf_nat_lock);
 }
 
@@ -570,8 +569,8 @@ static void nf_nat_move_storage(void *new, void *old)
 		return;
 
 	spin_lock_bh(&nf_nat_lock);
-	hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource);
 	new_nat->ct = ct;
+	hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource);
 	spin_unlock_bh(&nf_nat_lock);
 }
 
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index 5daefad..7750c97 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -232,6 +232,11 @@ static unsigned char asn1_length_decode(struct asn1_ctx *ctx,
 			}
 		}
 	}
+
+	/* don't trust len bigger than ctx buffer */
+	if (*len > ctx->end - ctx->pointer)
+		return 0;
+
 	return 1;
 }
 
@@ -250,6 +255,10 @@ static unsigned char asn1_header_decode(struct asn1_ctx *ctx,
 	if (!asn1_length_decode(ctx, &def, &len))
 		return 0;
 
+	/* primitive shall be definite, indefinite shall be constructed */
+	if (*con == ASN1_PRI && !def)
+		return 0;
+
 	if (def)
 		*eoc = ctx->pointer + len;
 	else
@@ -434,6 +443,11 @@ static unsigned char asn1_oid_decode(struct asn1_ctx *ctx,
 	unsigned long *optr;
 
 	size = eoc - ctx->pointer + 1;
+
+	/* first subid actually encodes first two subids */
+	if (size < 2 || size > ULONG_MAX/sizeof(unsigned long))
+		return 0;
+
 	*oid = kmalloc(size * sizeof(unsigned long), GFP_ATOMIC);
 	if (*oid == NULL) {
 		if (net_ratelimit())
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index fead049..37a1ecd 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -608,6 +608,14 @@ static void raw_close(struct sock *sk, long timeout)
 	sk_common_release(sk);
 }
 
+static int raw_destroy(struct sock *sk)
+{
+	lock_sock(sk);
+	ip_flush_pending_frames(sk);
+	release_sock(sk);
+	return 0;
+}
+
 /* This gets rid of all the nasties in af_inet. -DaveM */
 static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
@@ -820,6 +828,7 @@ struct proto raw_prot = {
 	.name		   = "RAW",
 	.owner		   = THIS_MODULE,
 	.close		   = raw_close,
+	.destroy	   = raw_destroy,
 	.connect	   = ip4_datagram_connect,
 	.disconnect	   = udp_disconnect,
 	.ioctl		   = raw_ioctl,
@@ -925,7 +934,7 @@ static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i)
 	      srcp  = inet->num;
 
 	seq_printf(seq, "%4d: %08X:%04X %08X:%04X"
-		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d",
+		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n",
 		i, src, srcp, dest, destp, sp->sk_state,
 		atomic_read(&sp->sk_wmem_alloc),
 		atomic_read(&sp->sk_rmem_alloc),
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 92f90ae..96be336 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -160,7 +160,7 @@ static struct dst_ops ipv4_dst_ops = {
 	.negative_advice =	ipv4_negative_advice,
 	.link_failure =		ipv4_link_failure,
 	.update_pmtu =		ip_rt_update_pmtu,
-	.local_out =		ip_local_out,
+	.local_out =		__ip_local_out,
 	.entry_size =		sizeof(struct rtable),
 	.entries =		ATOMIC_INIT(0),
 };
@@ -1792,7 +1792,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	if (err)
 		flags |= RTCF_DIRECTSRC;
 
-	if (out_dev == in_dev && err && !(flags & RTCF_MASQ) &&
+	if (out_dev == in_dev && err &&
 	    (IN_DEV_SHARED_MEDIA(out_dev) ||
 	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
 		flags |= RTCF_DOREDIRECT;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 73ba989..d182a2a 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -285,7 +285,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 		cookie_check_timestamp(&tcp_opt);
 
 	ret = NULL;
-	req = reqsk_alloc(&tcp_request_sock_ops); /* for safety */
+	req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */
 	if (!req)
 		goto out;
 
@@ -301,7 +301,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	ireq->rmt_port		= th->source;
 	ireq->loc_addr		= ip_hdr(skb)->daddr;
 	ireq->rmt_addr		= ip_hdr(skb)->saddr;
-	ireq->opt		= NULL;
 	ireq->snd_wscale	= tcp_opt.snd_wscale;
 	ireq->rcv_wscale	= tcp_opt.rcv_wscale;
 	ireq->sack_ok		= tcp_opt.sack_ok;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f886531..fc54a48 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1227,7 +1227,14 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 				copied += used;
 				offset += used;
 			}
-			if (offset != skb->len)
+			/*
+			 * If recv_actor drops the lock (e.g. TCP splice
+			 * receive) the skb pointer might be invalid when
+			 * getting here: tcp_collapse might have deleted it
+			 * while aggregating skbs from the socket queue.
+			 */
+			skb = tcp_recv_skb(sk, seq-1, &offset);
+			if (!skb || (offset+1 != skb->len))
 				break;
 		}
 		if (tcp_hdr(skb)->fin) {
@@ -2105,12 +2112,15 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_DEFER_ACCEPT:
-		if (val < 0) {
-			err = -EINVAL;
-		} else {
-			if (val > MAX_TCP_ACCEPT_DEFERRED)
-				val = MAX_TCP_ACCEPT_DEFERRED;
-			icsk->icsk_accept_queue.rskq_defer_accept = val;
+		icsk->icsk_accept_queue.rskq_defer_accept = 0;
+		if (val > 0) {
+			/* Translate value in seconds to number of
+			 * retransmits */
+			while (icsk->icsk_accept_queue.rskq_defer_accept < 32 &&
+			       val > ((TCP_TIMEOUT_INIT / HZ) <<
+				       icsk->icsk_accept_queue.rskq_defer_accept))
+				icsk->icsk_accept_queue.rskq_defer_accept++;
+			icsk->icsk_accept_queue.rskq_defer_accept++;
 		}
 		break;
 
@@ -2292,7 +2302,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			val = (val ? : sysctl_tcp_fin_timeout) / HZ;
 		break;
 	case TCP_DEFER_ACCEPT:
-		val = icsk->icsk_accept_queue.rskq_defer_accept;
+		val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 :
+			((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1));
 		break;
 	case TCP_WINDOW_CLAMP:
 		val = tp->window_clamp;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b54d9d3..cad73b7 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1392,9 +1392,9 @@ static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb,
 
 	if (before(next_dup->start_seq, skip_to_seq)) {
 		skb = tcp_sacktag_skip(skb, sk, next_dup->start_seq, fack_count);
-		tcp_sacktag_walk(skb, sk, NULL,
-				 next_dup->start_seq, next_dup->end_seq,
-				 1, fack_count, reord, flag);
+		skb = tcp_sacktag_walk(skb, sk, NULL,
+				     next_dup->start_seq, next_dup->end_seq,
+				     1, fack_count, reord, flag);
 	}
 
 	return skb;
@@ -2483,6 +2483,20 @@ static inline void tcp_complete_cwr(struct sock *sk)
 	tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR);
 }
 
+static void tcp_try_keep_open(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	int state = TCP_CA_Open;
+
+	if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker)
+		state = TCP_CA_Disorder;
+
+	if (inet_csk(sk)->icsk_ca_state != state) {
+		tcp_set_ca_state(sk, state);
+		tp->high_seq = tp->snd_nxt;
+	}
+}
+
 static void tcp_try_to_open(struct sock *sk, int flag)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -2496,15 +2510,7 @@ static void tcp_try_to_open(struct sock *sk, int flag)
 		tcp_enter_cwr(sk, 1);
 
 	if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
-		int state = TCP_CA_Open;
-
-		if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker)
-			state = TCP_CA_Disorder;
-
-		if (inet_csk(sk)->icsk_ca_state != state) {
-			tcp_set_ca_state(sk, state);
-			tp->high_seq = tp->snd_nxt;
-		}
+		tcp_try_keep_open(sk);
 		tcp_moderate_cwnd(tp);
 	} else {
 		tcp_cwnd_down(sk, flag);
@@ -3310,8 +3316,11 @@ no_queue:
 	return 1;
 
 old_ack:
-	if (TCP_SKB_CB(skb)->sacked)
+	if (TCP_SKB_CB(skb)->sacked) {
 		tcp_sacktag_write_queue(sk, skb, prior_snd_una);
+		if (icsk->icsk_ca_state == TCP_CA_Open)
+			tcp_try_keep_open(sk);
+	}
 
 uninteresting_ack:
 	SOCK_DEBUG(sk, "Ack %u out of %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
@@ -4532,49 +4541,6 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, struct tcphdr *th)
 	}
 }
 
-static int tcp_defer_accept_check(struct sock *sk)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (tp->defer_tcp_accept.request) {
-		int queued_data =  tp->rcv_nxt - tp->copied_seq;
-		int hasfin =  !skb_queue_empty(&sk->sk_receive_queue) ?
-			tcp_hdr((struct sk_buff *)
-				sk->sk_receive_queue.prev)->fin : 0;
-
-		if (queued_data && hasfin)
-			queued_data--;
-
-		if (queued_data &&
-		    tp->defer_tcp_accept.listen_sk->sk_state == TCP_LISTEN) {
-			if (sock_flag(sk, SOCK_KEEPOPEN)) {
-				inet_csk_reset_keepalive_timer(sk,
-							       keepalive_time_when(tp));
-			} else {
-				inet_csk_delete_keepalive_timer(sk);
-			}
-
-			inet_csk_reqsk_queue_add(
-				tp->defer_tcp_accept.listen_sk,
-				tp->defer_tcp_accept.request,
-				sk);
-
-			tp->defer_tcp_accept.listen_sk->sk_data_ready(
-				tp->defer_tcp_accept.listen_sk, 0);
-
-			sock_put(tp->defer_tcp_accept.listen_sk);
-			sock_put(sk);
-			tp->defer_tcp_accept.listen_sk = NULL;
-			tp->defer_tcp_accept.request = NULL;
-		} else if (hasfin ||
-			   tp->defer_tcp_accept.listen_sk->sk_state != TCP_LISTEN) {
-			tcp_reset(sk);
-			return -1;
-		}
-	}
-	return 0;
-}
-
 static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -4935,8 +4901,6 @@ step5:
 
 	tcp_data_snd_check(sk);
 	tcp_ack_snd_check(sk);
-
-	tcp_defer_accept_check(sk);
 	return 0;
 
 csum_error:
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cd601a8..12695be 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -85,10 +85,6 @@
 int sysctl_tcp_tw_reuse __read_mostly;
 int sysctl_tcp_low_latency __read_mostly;
 
-/* Check TCP sequence numbers in ICMP packets. */
-#define ICMP_MIN_LENGTH 8
-
-void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb);
 
 #ifdef CONFIG_TCP_MD5SIG
 static struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk,
@@ -1285,7 +1281,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
 		goto drop;
 
-	req = reqsk_alloc(&tcp_request_sock_ops);
+	req = inet_reqsk_alloc(&tcp_request_sock_ops);
 	if (!req)
 		goto drop;
 
@@ -1918,14 +1914,6 @@ int tcp_v4_destroy_sock(struct sock *sk)
 		sk->sk_sndmsg_page = NULL;
 	}
 
-	if (tp->defer_tcp_accept.request) {
-		reqsk_free(tp->defer_tcp_accept.request);
-		sock_put(tp->defer_tcp_accept.listen_sk);
-		sock_put(sk);
-		tp->defer_tcp_accept.listen_sk = NULL;
-		tp->defer_tcp_accept.request = NULL;
-	}
-
 	atomic_dec(&tcp_sockets_allocated);
 
 	return 0;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 019c8c1..8245247 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -571,8 +571,10 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 	   does sequence test, SYN is truncated, and thus we consider
 	   it a bare ACK.
 
-	   Both ends (listening sockets) accept the new incoming
-	   connection and try to talk to each other. 8-)
+	   If icsk->icsk_accept_queue.rskq_defer_accept, we silently drop this
+	   bare ACK.  Otherwise, we create an established connection.  Both
+	   ends (listening sockets) accept the new incoming connection and try
+	   to talk to each other. 8-)
 
 	   Note: This case is both harmless, and rare.  Possibility is about the
 	   same as us discovering intelligent life on another plant tomorrow.
@@ -640,6 +642,13 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 		if (!(flg & TCP_FLAG_ACK))
 			return NULL;
 
+		/* If TCP_DEFER_ACCEPT is set, drop bare ACK. */
+		if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
+		    TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
+			inet_rsk(req)->acked = 1;
+			return NULL;
+		}
+
 		/* OK, ACK is valid, create big socket and
 		 * feed this segment to it. It will repeat all
 		 * the tests. THIS SEGMENT MUST MOVE SOCKET TO
@@ -678,24 +687,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 		inet_csk_reqsk_queue_unlink(sk, req, prev);
 		inet_csk_reqsk_queue_removed(sk, req);
 
-		if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
-		    TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
-
-			/* the accept queue handling is done is est recv slow
-			 * path so lets make sure to start there
-			 */
-			tcp_sk(child)->pred_flags = 0;
-			sock_hold(sk);
-			sock_hold(child);
-			tcp_sk(child)->defer_tcp_accept.listen_sk = sk;
-			tcp_sk(child)->defer_tcp_accept.request = req;
-
-			inet_csk_reset_keepalive_timer(child,
-						       inet_csk(sk)->icsk_accept_queue.rskq_defer_accept * HZ);
-		} else {
-			inet_csk_reqsk_queue_add(sk, req, child);
-		}
-
+		inet_csk_reqsk_queue_add(sk, req, child);
 		return child;
 
 	listen_overflow:
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index debf235..ad993ec 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1836,7 +1836,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	unsigned int cur_mss = tcp_current_mss(sk, 0);
+	unsigned int cur_mss;
 	int err;
 
 	/* Inconslusive MTU probe */
@@ -1858,6 +1858,11 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 			return -ENOMEM;
 	}
 
+	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
+		return -EHOSTUNREACH; /* Routing failure or similar. */
+
+	cur_mss = tcp_current_mss(sk, 0);
+
 	/* If receiver has shrunk his window, and skb is out of
 	 * new window, do not retransmit it. The exception is the
 	 * case, when window is shrunk to zero. In this case
@@ -1884,9 +1889,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	    (sysctl_tcp_retrans_collapse != 0))
 		tcp_retrans_try_collapse(sk, skb, cur_mss);
 
-	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
-		return -EHOSTUNREACH; /* Routing failure or similar. */
-
 	/* Some Solaris stacks overoptimize and ignore the FIN on a
 	 * retransmit when old data is attached.  So strip it off
 	 * since it is cheap to do so and saves bytes on the network.
@@ -2129,6 +2131,8 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	TCP_SKB_CB(skb)->when = tcp_time_stamp;
 	if (tcp_transmit_skb(sk, skb, 0, priority))
 		NET_INC_STATS(LINUX_MIB_TCPABORTFAILED);
+
+	TCP_INC_STATS(TCP_MIB_OUTRSTS);
 }
 
 /* WARNING: This routine must only be called when we have already sent
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 4de68cf..63ed9d6 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -489,11 +489,6 @@ static void tcp_keepalive_timer (unsigned long data)
 		goto death;
 	}
 
-	if (tp->defer_tcp_accept.request && sk->sk_state == TCP_ESTABLISHED) {
-		tcp_send_active_reset(sk, GFP_ATOMIC);
-		goto death;
-	}
-
 	if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE)
 		goto out;
 
diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
index d3b709a..cb1f0e8 100644
--- a/net/ipv4/tunnel4.c
+++ b/net/ipv4/tunnel4.c
@@ -97,7 +97,7 @@ static int tunnel64_rcv(struct sk_buff *skb)
 {
 	struct xfrm_tunnel *handler;
 
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
 		goto drop;
 
 	for (handler = tunnel64_handlers; handler; handler = handler->next)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index db1cb7c..56fcda3 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -420,7 +420,7 @@ void udp_err(struct sk_buff *skb, u32 info)
 /*
  * Throw away all pending data and cancel the corking. Socket is locked.
  */
-static void udp_flush_pending_frames(struct sock *sk)
+void udp_flush_pending_frames(struct sock *sk)
 {
 	struct udp_sock *up = udp_sk(sk);
 
@@ -430,6 +430,7 @@ static void udp_flush_pending_frames(struct sock *sk)
 		ip_flush_pending_frames(sk);
 	}
 }
+EXPORT_SYMBOL(udp_flush_pending_frames);
 
 /**
  * 	udp4_hwcsum_outgoing  -  handle outgoing HW checksumming
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 584e6d7..7135279 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -52,7 +52,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 		IP_ECN_clear(top_iph);
 
 	top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
-			    0 : XFRM_MODE_SKB_CB(skb)->frag_off;
+		0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
 	ip_select_ident(top_iph, dst->child, NULL);
 
 	top_iph->ttl = dst_metric(dst->child, RTAX_HOPLIMIT);