Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
  [XFRM]: BEET mode
  [TCP]: Kill warning in tcp_clean_rtx_queue().
  [NET_SCHED]: Remove old estimator implementation
  [ATM]: [zatm] always *pcr in alloc_shaper()
  [ATM]: [ambassador] Change the return type to reflect reality
  [ATM]: kmalloc to kzalloc patches for drivers/atm
  [TIPC]: fix printk warning
  [XFRM]: Clearing xfrm_policy_count[] to zero during flush is incorrect.
  [XFRM] STATE: Use destination address for src hash.
  [NEIGH]: always use hash_mask under tbl lock
  [UDP]: Fix MSG_PROBE crash
  [UDP6]: Fix flowi clobbering
  [NET_SCHED]: Revert "HTB: fix incorrect use of RB_EMPTY_NODE"
  [NETFILTER]: ebt_mark: add or/and/xor action support to mark target
  [NETFILTER]: ipt_REJECT: remove largely duplicate route_reverse function
  [NETFILTER]: Honour source routing for LVS-NAT
  [NETFILTER]: add type parameter to ip_route_me_harder
  [NETFILTER]: Kconfig: fix xt_physdev dependencies

12 files changed, 214 insertions, 92 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index d172a980444..5572071af73 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -434,6 +434,15 @@ config INET_XFRM_MODE_TUNNEL
 
 	  If unsure, say Y.
 
+config INET_XFRM_MODE_BEET
+	tristate "IP: IPsec BEET mode"
+	default y
+	select XFRM
+	---help---
+	  Support for IPsec BEET mode.
+
+	  If unsure, say Y.
+
 config INET_DIAG
 	tristate "INET: socket monitoring interface"
 	default y
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index f66049e28ae..15645c51520 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_INET_AH) += ah4.o
 obj-$(CONFIG_INET_ESP) += esp4.o
 obj-$(CONFIG_INET_IPCOMP) += ipcomp.o
 obj-$(CONFIG_INET_XFRM_TUNNEL) += xfrm4_tunnel.o
+obj-$(CONFIG_INET_XFRM_MODE_BEET) += xfrm4_mode_beet.o
 obj-$(CONFIG_INET_TUNNEL) += tunnel4.o
 obj-$(CONFIG_INET_XFRM_MODE_TRANSPORT) += xfrm4_mode_transport.o
 obj-$(CONFIG_INET_XFRM_MODE_TUNNEL) += xfrm4_mode_tunnel.o
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 13b29360d10..b5c205b5766 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -253,7 +253,8 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 		 *    as per draft-ietf-ipsec-udp-encaps-06,
 		 *    section 3.1.2
 		 */
-		if (x->props.mode == XFRM_MODE_TRANSPORT)
+		if (x->props.mode == XFRM_MODE_TRANSPORT ||
+		    x->props.mode == XFRM_MODE_BEET)
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 	}
 
@@ -271,17 +272,28 @@ static u32 esp4_get_max_size(struct xfrm_state *x, int mtu)
 {
 	struct esp_data *esp = x->data;
 	u32 blksize = ALIGN(crypto_blkcipher_blocksize(esp->conf.tfm), 4);
-
-	if (x->props.mode == XFRM_MODE_TUNNEL) {
-		mtu = ALIGN(mtu + 2, blksize);
-	} else {
-		/* The worst case. */
+	int enclen = 0;
+
+	switch (x->props.mode) {
+	case XFRM_MODE_TUNNEL:
+		mtu = ALIGN(mtu +2, blksize);
+		break;
+	default:
+	case XFRM_MODE_TRANSPORT:
+		/* The worst case */
 		mtu = ALIGN(mtu + 2, 4) + blksize - 4;
+		break;
+	case XFRM_MODE_BEET:
+ 		/* The worst case. */
+		enclen = IPV4_BEET_PHMAXLEN;
+		mtu = ALIGN(mtu + enclen + 2, blksize);
+		break;
 	}
+
 	if (esp->conf.padlen)
 		mtu = ALIGN(mtu, esp->conf.padlen);
 
-	return mtu + x->props.header_len + esp->auth.icv_trunc_len;
+	return mtu + x->props.header_len + esp->auth.icv_trunc_len - enclen;
 }
 
 static void esp4_err(struct sk_buff *skb, u32 info)
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 2017d36024d..3839b706142 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -206,6 +206,7 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info)
 static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x)
 {
 	struct xfrm_state *t;
+	u8 mode = XFRM_MODE_TUNNEL;
 	
 	t = xfrm_state_alloc();
 	if (t == NULL)
@@ -216,7 +217,9 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x)
 	t->id.daddr.a4 = x->id.daddr.a4;
 	memcpy(&t->sel, &x->sel, sizeof(t->sel));
 	t->props.family = AF_INET;
-	t->props.mode = XFRM_MODE_TUNNEL;
+	if (x->props.mode == XFRM_MODE_BEET)
+		mode = x->props.mode;
+	t->props.mode = mode;
 	t->props.saddr.a4 = x->props.saddr.a4;
 	t->props.flags = x->props.flags;
 
diff --git a/net/ipv4/ipvs/ip_vs_core.c b/net/ipv4/ipvs/ip_vs_core.c
index 6dee03935f7..1445bb47fea 100644
--- a/net/ipv4/ipvs/ip_vs_core.c
+++ b/net/ipv4/ipvs/ip_vs_core.c
@@ -813,6 +813,16 @@ ip_vs_out(unsigned int hooknum, struct sk_buff **pskb,
 	skb->nh.iph->saddr = cp->vaddr;
 	ip_send_check(skb->nh.iph);
 
+ 	/* For policy routing, packets originating from this
+ 	 * machine itself may be routed differently to packets
+ 	 * passing through.  We want this packet to be routed as
+ 	 * if it came from this machine itself.  So re-compute
+ 	 * the routing information.
+ 	 */
+ 	if (ip_route_me_harder(pskb, RTN_LOCAL) != 0)
+ 		goto drop;
+	skb = *pskb;
+
 	IP_VS_DBG_PKT(10, pp, skb, 0, "After SNAT");
 
 	ip_vs_out_stats(cp, skb);
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 5ac15379a0c..e2005c6810a 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -8,7 +8,7 @@
 #include <net/ip.h>
 
 /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
-int ip_route_me_harder(struct sk_buff **pskb)
+int ip_route_me_harder(struct sk_buff **pskb, unsigned addr_type)
 {
 	struct iphdr *iph = (*pskb)->nh.iph;
 	struct rtable *rt;
@@ -16,10 +16,13 @@ int ip_route_me_harder(struct sk_buff **pskb)
 	struct dst_entry *odst;
 	unsigned int hh_len;
 
+	if (addr_type == RTN_UNSPEC)
+		addr_type = inet_addr_type(iph->saddr);
+
 	/* some non-standard hacks like ipt_REJECT.c:send_reset() can cause
 	 * packets with foreign saddr to appear on the NF_IP_LOCAL_OUT hook.
 	 */
-	if (inet_addr_type(iph->saddr) == RTN_LOCAL) {
+	if (addr_type == RTN_LOCAL) {
 		fl.nl_u.ip4_u.daddr = iph->daddr;
 		fl.nl_u.ip4_u.saddr = iph->saddr;
 		fl.nl_u.ip4_u.tos = RT_TOS(iph->tos);
@@ -156,7 +159,7 @@ static int nf_ip_reroute(struct sk_buff **pskb, const struct nf_info *info)
 		if (!(iph->tos == rt_info->tos
 		      && iph->daddr == rt_info->daddr
 		      && iph->saddr == rt_info->saddr))
-			return ip_route_me_harder(pskb);
+			return ip_route_me_harder(pskb, RTN_UNSPEC);
 	}
 	return 0;
 }
diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c
index 021395b6746..d85d2de5044 100644
--- a/net/ipv4/netfilter/ip_nat_standalone.c
+++ b/net/ipv4/netfilter/ip_nat_standalone.c
@@ -265,7 +265,8 @@ ip_nat_local_fn(unsigned int hooknum,
 		       ct->tuplehash[!dir].tuple.src.u.all
 #endif
 		    )
-			return ip_route_me_harder(pskb) == 0 ? ret : NF_DROP;
+			if (ip_route_me_harder(pskb, RTN_UNSPEC))
+				ret = NF_DROP;
 	}
 	return ret;
 }
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index fd0c05efed8..ad0312d0e4f 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -38,76 +38,16 @@ MODULE_DESCRIPTION("iptables REJECT target module");
 #define DEBUGP(format, args...)
 #endif
 
-static inline struct rtable *route_reverse(struct sk_buff *skb, 
-					   struct tcphdr *tcph, int hook)
-{
-	struct iphdr *iph = skb->nh.iph;
-	struct dst_entry *odst;
-	struct flowi fl = {};
-	struct rtable *rt;
-
-	/* We don't require ip forwarding to be enabled to be able to
-	 * send a RST reply for bridged traffic. */
-	if (hook != NF_IP_FORWARD
-#ifdef CONFIG_BRIDGE_NETFILTER
-	    || (skb->nf_bridge && skb->nf_bridge->mask & BRNF_BRIDGED)
-#endif
-	   ) {
-		fl.nl_u.ip4_u.daddr = iph->saddr;
-		if (hook == NF_IP_LOCAL_IN)
-			fl.nl_u.ip4_u.saddr = iph->daddr;
-		fl.nl_u.ip4_u.tos = RT_TOS(iph->tos);
-
-		if (ip_route_output_key(&rt, &fl) != 0)
-			return NULL;
-	} else {
-		/* non-local src, find valid iif to satisfy
-		 * rp-filter when calling ip_route_input. */
-		fl.nl_u.ip4_u.daddr = iph->daddr;
-		if (ip_route_output_key(&rt, &fl) != 0)
-			return NULL;
-
-		odst = skb->dst;
-		if (ip_route_input(skb, iph->saddr, iph->daddr,
-		                   RT_TOS(iph->tos), rt->u.dst.dev) != 0) {
-			dst_release(&rt->u.dst);
-			return NULL;
-		}
-		dst_release(&rt->u.dst);
-		rt = (struct rtable *)skb->dst;
-		skb->dst = odst;
-
-		fl.nl_u.ip4_u.daddr = iph->saddr;
-		fl.nl_u.ip4_u.saddr = iph->daddr;
-		fl.nl_u.ip4_u.tos = RT_TOS(iph->tos);
-	}
-
-	if (rt->u.dst.error) {
-		dst_release(&rt->u.dst);
-		return NULL;
-	}
-
-	fl.proto = IPPROTO_TCP;
-	fl.fl_ip_sport = tcph->dest;
-	fl.fl_ip_dport = tcph->source;
-	security_skb_classify_flow(skb, &fl);
-
-	xfrm_lookup((struct dst_entry **)&rt, &fl, NULL, 0);
-
-	return rt;
-}
-
 /* Send RST reply */
 static void send_reset(struct sk_buff *oldskb, int hook)
 {
 	struct sk_buff *nskb;
 	struct iphdr *iph = oldskb->nh.iph;
 	struct tcphdr _otcph, *oth, *tcph;
-	struct rtable *rt;
 	__be16 tmp_port;
 	__be32 tmp_addr;
 	int needs_ack;
-	int hh_len;
+	unsigned int addr_type;
 
 	/* IP header checks: fragment. */
 	if (oldskb->nh.iph->frag_off & htons(IP_OFFSET))
@@ -126,23 +66,13 @@ static void send_reset(struct sk_buff *oldskb, int hook)
 	if (nf_ip_checksum(oldskb, hook, iph->ihl * 4, IPPROTO_TCP))
 		return;
 
-	if ((rt = route_reverse(oldskb, oth, hook)) == NULL)
-		return;
-
-	hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
-
 	/* We need a linear, writeable skb.  We also need to expand
 	   headroom in case hh_len of incoming interface < hh_len of
 	   outgoing interface */
-	nskb = skb_copy_expand(oldskb, hh_len, skb_tailroom(oldskb),
+	nskb = skb_copy_expand(oldskb, LL_MAX_HEADER, skb_tailroom(oldskb),
 			       GFP_ATOMIC);
-	if (!nskb) {
-		dst_release(&rt->u.dst);
+	if (!nskb)
 		return;
-	}
-
-	dst_release(nskb->dst);
-	nskb->dst = &rt->u.dst;
 
 	/* This packet will not be the same as the other: clear nf fields */
 	nf_reset(nskb);
@@ -184,6 +114,21 @@ static void send_reset(struct sk_buff *oldskb, int hook)
 	tcph->window = 0;
 	tcph->urg_ptr = 0;
 
+	/* Set DF, id = 0 */
+	nskb->nh.iph->frag_off = htons(IP_DF);
+	nskb->nh.iph->id = 0;
+
+	addr_type = RTN_UNSPEC;
+	if (hook != NF_IP_FORWARD
+#ifdef CONFIG_BRIDGE_NETFILTER
+	    || (nskb->nf_bridge && nskb->nf_bridge->mask & BRNF_BRIDGED)
+#endif
+	   )
+		addr_type = RTN_LOCAL;
+
+	if (ip_route_me_harder(&nskb, addr_type))
+		goto free_nskb;
+
 	/* Adjust TCP checksum */
 	nskb->ip_summed = CHECKSUM_NONE;
 	tcph->check = 0;
@@ -192,12 +137,8 @@ static void send_reset(struct sk_buff *oldskb, int hook)
 				   nskb->nh.iph->daddr,
 				   csum_partial((char *)tcph,
 						sizeof(struct tcphdr), 0));
-
-	/* Adjust IP TTL, DF */
+	/* Adjust IP TTL */
 	nskb->nh.iph->ttl = dst_metric(nskb->dst, RTAX_HOPLIMIT);
-	/* Set DF, id = 0 */
-	nskb->nh.iph->frag_off = htons(IP_DF);
-	nskb->nh.iph->id = 0;
 
 	/* Adjust IP checksum */
 	nskb->nh.iph->check = 0;
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index e62ea2bb9c0..b91f3582359 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -157,7 +157,8 @@ ipt_local_hook(unsigned int hook,
 		|| (*pskb)->nfmark != nfmark
 #endif
 		|| (*pskb)->nh.iph->tos != tos))
-		return ip_route_me_harder(pskb) == 0 ? ret : NF_DROP;
+		if (ip_route_me_harder(pskb, RTN_UNSPEC))
+			ret = NF_DROP;
 
 	return ret;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3f884cea14f..cf06accbe68 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2259,7 +2259,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p)
 	u32 pkts_acked = 0;
 	void (*rtt_sample)(struct sock *sk, u32 usrtt)
 		= icsk->icsk_ca_ops->rtt_sample;
-	struct timeval tv;
+	struct timeval tv = { .tv_sec = 0, .tv_usec = 0 };
 
 	while ((skb = skb_peek(&sk->sk_write_queue)) &&
 	       skb != sk->sk_send_head) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 6d6142f9c47..865d75214a9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -675,6 +675,8 @@ do_append_data:
 		udp_flush_pending_frames(sk);
 	else if (!corkreq)
 		err = udp_push_pending_frames(sk, up);
+	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
+		up->pending = 0;
 	release_sock(sk);
 
 out:
diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c
new file mode 100644
index 00000000000..89cf59ea7bb
--- /dev/null
+++ b/net/ipv4/xfrm4_mode_beet.c
@@ -0,0 +1,139 @@
+/*
+ * xfrm4_mode_beet.c - BEET mode encapsulation for IPv4.
+ *
+ * Copyright (c) 2006 Diego Beltrami <diego.beltrami@gmail.com>
+ *                    Miika Komu     <miika@iki.fi>
+ *                    Herbert Xu     <herbert@gondor.apana.org.au>
+ *                    Abhinav Pathak <abhinav.pathak@hiit.fi>
+ *                    Jeff Ahrenholz <ahrenholz@gmail.com>
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/stringify.h>
+#include <net/dst.h>
+#include <net/ip.h>
+#include <net/xfrm.h>
+
+/* Add encapsulation header.
+ *
+ * The top IP header will be constructed per draft-nikander-esp-beet-mode-06.txt.
+ * The following fields in it shall be filled in by x->type->output:
+ *      tot_len
+ *      check
+ *
+ * On exit, skb->h will be set to the start of the payload to be processed
+ * by x->type->output and skb->nh will be set to the top IP header.
+ */
+static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct iphdr *iph, *top_iph = NULL;
+	int hdrlen, optlen;
+
+	iph = skb->nh.iph;
+	skb->h.ipiph = iph;
+
+	hdrlen = 0;
+	optlen = iph->ihl * 4 - sizeof(*iph);
+	if (unlikely(optlen))
+		hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4);
+
+	skb->nh.raw = skb_push(skb, x->props.header_len + hdrlen);
+	top_iph = skb->nh.iph;
+	hdrlen = iph->ihl * 4 - optlen;
+	skb->h.raw += hdrlen;
+
+	memmove(top_iph, iph, hdrlen);
+	if (unlikely(optlen)) {
+		struct ip_beet_phdr *ph;
+
+		BUG_ON(optlen < 0);
+
+		ph = (struct ip_beet_phdr *)skb->h.raw;
+		ph->padlen = 4 - (optlen & 4);
+		ph->hdrlen = (optlen + ph->padlen + sizeof(*ph)) / 8;
+		ph->nexthdr = top_iph->protocol;
+
+		top_iph->protocol = IPPROTO_BEETPH;
+		top_iph->ihl = sizeof(struct iphdr) / 4;
+	}
+
+	top_iph->saddr = x->props.saddr.a4;
+	top_iph->daddr = x->id.daddr.a4;
+
+	return 0;
+}
+
+static int xfrm4_beet_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct iphdr *iph = skb->nh.iph;
+	int phlen = 0;
+	int optlen = 0;
+	__u8 ph_nexthdr = 0, protocol = 0;
+	int err = -EINVAL;
+
+	protocol = iph->protocol;
+
+	if (unlikely(iph->protocol == IPPROTO_BEETPH)) {
+		struct ip_beet_phdr *ph = (struct ip_beet_phdr*)(iph + 1);
+
+		if (!pskb_may_pull(skb, sizeof(*ph)))
+			goto out;
+
+		phlen = ph->hdrlen * 8;
+		optlen = phlen - ph->padlen - sizeof(*ph);
+		if (optlen < 0 || optlen & 3 || optlen > 250)
+			goto out;
+
+		if (!pskb_may_pull(skb, phlen))
+			goto out;
+
+		ph_nexthdr = ph->nexthdr;
+	}
+
+	skb_push(skb, sizeof(*iph) - phlen + optlen);
+	memmove(skb->data, skb->nh.raw, sizeof(*iph));
+	skb->nh.raw = skb->data;
+
+	iph = skb->nh.iph;
+	iph->ihl = (sizeof(*iph) + optlen) / 4;
+	iph->tot_len = htons(skb->len);
+	iph->daddr = x->sel.daddr.a4;
+	iph->saddr = x->sel.saddr.a4;
+	if (ph_nexthdr)
+		iph->protocol = ph_nexthdr;
+	else
+		iph->protocol = protocol;
+	iph->check = 0;
+	iph->check = ip_fast_csum(skb->nh.raw, iph->ihl);
+	err = 0;
+out:
+	return err;
+}
+
+static struct xfrm_mode xfrm4_beet_mode = {
+	.input = xfrm4_beet_input,
+	.output = xfrm4_beet_output,
+	.owner = THIS_MODULE,
+	.encap = XFRM_MODE_BEET,
+};
+
+static int __init xfrm4_beet_init(void)
+{
+	return xfrm_register_mode(&xfrm4_beet_mode, AF_INET);
+}
+
+static void __exit xfrm4_beet_exit(void)
+{
+	int err;
+
+	err = xfrm_unregister_mode(&xfrm4_beet_mode, AF_INET);
+	BUG_ON(err);
+}
+
+module_init(xfrm4_beet_init);
+module_exit(xfrm4_beet_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_XFRM_MODE(AF_INET, XFRM_MODE_BEET);