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

5 files changed, 155 insertions, 32 deletions

diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index a2d211da2aba..a460e8132b4d 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -136,6 +136,16 @@ config INET6_XFRM_MODE_TUNNEL
 
           If unsure, say Y.
 
+config INET6_XFRM_MODE_BEET
+        tristate "IPv6: IPsec BEET mode"
+        depends on IPV6
+        default IPV6
+        select XFRM
+        ---help---
+          Support for IPsec BEET mode.
+
+          If unsure, say Y.
+
 config INET6_XFRM_MODE_ROUTEOPTIMIZATION
         tristate "IPv6: MIPv6 route optimization mode (EXPERIMENTAL)"
         depends on IPV6 && EXPERIMENTAL
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 0213c6612b58..87274e47fe32 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -26,6 +26,7 @@ obj-$(CONFIG_INET6_TUNNEL) += tunnel6.o
 obj-$(CONFIG_INET6_XFRM_MODE_TRANSPORT) += xfrm6_mode_transport.o
 obj-$(CONFIG_INET6_XFRM_MODE_TUNNEL) += xfrm6_mode_tunnel.o
 obj-$(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION) += xfrm6_mode_ro.o
+obj-$(CONFIG_INET6_XFRM_MODE_BEET) += xfrm6_mode_beet.o
 obj-$(CONFIG_NETFILTER) += netfilter/
 
 obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index a2860e35efd7..71f59f18ede8 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -199,6 +199,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x)
 {
         struct xfrm_state *t = NULL;
+        u8 mode = XFRM_MODE_TUNNEL;
 
         t = xfrm_state_alloc();
         if (!t)
@@ -212,7 +213,9 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x)
         memcpy(t->id.daddr.a6, x->id.daddr.a6, sizeof(struct in6_addr));
         memcpy(&t->sel, &x->sel, sizeof(t->sel));
         t->props.family = AF_INET6;
-        t->props.mode = XFRM_MODE_TUNNEL;
+        if (x->props.mode == XFRM_MODE_BEET)
+                mode = x->props.mode;
+        t->props.mode = mode;
         memcpy(t->props.saddr.a6, x->props.saddr.a6, sizeof(struct in6_addr));
 
         if (xfrm_init_state(t))
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 9662561701d1..e0c3934a7e4b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -546,7 +546,7 @@ static int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
         struct in6_addr *daddr, *final_p = NULL, final;
         struct ipv6_txoptions *opt = NULL;
         struct ip6_flowlabel *flowlabel = NULL;
-        struct flowi *fl = &inet->cork.fl;
+        struct flowi fl;
         struct dst_entry *dst;
         int addr_len = msg->msg_namelen;
         int ulen = len;
@@ -626,19 +626,19 @@ do_udp_sendmsg:
         }
         ulen += sizeof(struct udphdr);
 
-        memset(fl, 0, sizeof(*fl));
+        memset(&fl, 0, sizeof(fl));
 
         if (sin6) {
                 if (sin6->sin6_port == 0)
                         return -EINVAL;
 
-                fl->fl_ip_dport = sin6->sin6_port;
+                fl.fl_ip_dport = sin6->sin6_port;
                 daddr = &sin6->sin6_addr;
 
                 if (np->sndflow) {
-                        fl->fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
-                        if (fl->fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
-                                flowlabel = fl6_sock_lookup(sk, fl->fl6_flowlabel);
+                        fl.fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
+                        if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
+                                flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
                                 if (flowlabel == NULL)
                                         return -EINVAL;
                                 daddr = &flowlabel->dst;
@@ -656,32 +656,32 @@ do_udp_sendmsg:
                 if (addr_len >= sizeof(struct sockaddr_in6) &&
                     sin6->sin6_scope_id &&
                     ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL)
-                        fl->oif = sin6->sin6_scope_id;
+                        fl.oif = sin6->sin6_scope_id;
         } else {
                 if (sk->sk_state != TCP_ESTABLISHED)
                         return -EDESTADDRREQ;
 
-                fl->fl_ip_dport = inet->dport;
+                fl.fl_ip_dport = inet->dport;
                 daddr = &np->daddr;
-                fl->fl6_flowlabel = np->flow_label;
+                fl.fl6_flowlabel = np->flow_label;
                 connected = 1;
         }
 
-        if (!fl->oif)
-                fl->oif = sk->sk_bound_dev_if;
+        if (!fl.oif)
+                fl.oif = sk->sk_bound_dev_if;
 
         if (msg->msg_controllen) {
                 opt = &opt_space;
                 memset(opt, 0, sizeof(struct ipv6_txoptions));
                 opt->tot_len = sizeof(*opt);
 
-                err = datagram_send_ctl(msg, fl, opt, &hlimit, &tclass);
+                err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass);
                 if (err < 0) {
                         fl6_sock_release(flowlabel);
                         return err;
                 }
-                if ((fl->fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
-                        flowlabel = fl6_sock_lookup(sk, fl->fl6_flowlabel);
+                if ((fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
+                        flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
                         if (flowlabel == NULL)
                                 return -EINVAL;
                 }
@@ -695,39 +695,39 @@ do_udp_sendmsg:
                 opt = fl6_merge_options(&opt_space, flowlabel, opt);
         opt = ipv6_fixup_options(&opt_space, opt);
 
-        fl->proto = IPPROTO_UDP;
-        ipv6_addr_copy(&fl->fl6_dst, daddr);
-        if (ipv6_addr_any(&fl->fl6_src) && !ipv6_addr_any(&np->saddr))
-                ipv6_addr_copy(&fl->fl6_src, &np->saddr);
-        fl->fl_ip_sport = inet->sport;
+        fl.proto = IPPROTO_UDP;
+        ipv6_addr_copy(&fl.fl6_dst, daddr);
+        if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr))
+                ipv6_addr_copy(&fl.fl6_src, &np->saddr);
+        fl.fl_ip_sport = inet->sport;
         
         /* merge ip6_build_xmit from ip6_output */
         if (opt && opt->srcrt) {
                 struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
-                ipv6_addr_copy(&final, &fl->fl6_dst);
-                ipv6_addr_copy(&fl->fl6_dst, rt0->addr);
+                ipv6_addr_copy(&final, &fl.fl6_dst);
+                ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
                 final_p = &final;
                 connected = 0;
         }
 
-        if (!fl->oif && ipv6_addr_is_multicast(&fl->fl6_dst)) {
-                fl->oif = np->mcast_oif;
+        if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) {
+                fl.oif = np->mcast_oif;
                 connected = 0;
         }
 
-        security_sk_classify_flow(sk, fl);
+        security_sk_classify_flow(sk, &fl);
 
-        err = ip6_sk_dst_lookup(sk, &dst, fl);
+        err = ip6_sk_dst_lookup(sk, &dst, &fl);
         if (err)
                 goto out;
         if (final_p)
-                ipv6_addr_copy(&fl->fl6_dst, final_p);
+                ipv6_addr_copy(&fl.fl6_dst, final_p);
 
-        if ((err = xfrm_lookup(&dst, fl, sk, 0)) < 0)
+        if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
                 goto out;
 
         if (hlimit < 0) {
-                if (ipv6_addr_is_multicast(&fl->fl6_dst))
+                if (ipv6_addr_is_multicast(&fl.fl6_dst))
                         hlimit = np->mcast_hops;
                 else
                         hlimit = np->hop_limit;
@@ -763,21 +763,23 @@ back_from_confirm:
 do_append_data:
         up->len += ulen;
         err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, ulen,
-                sizeof(struct udphdr), hlimit, tclass, opt, fl,
+                sizeof(struct udphdr), hlimit, tclass, opt, &fl,
                 (struct rt6_info*)dst,
                 corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
         if (err)
                 udp_v6_flush_pending_frames(sk);
         else if (!corkreq)
                 err = udp_v6_push_pending_frames(sk, up);
+        else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
+                up->pending = 0;
 
         if (dst) {
                 if (connected) {
                         ip6_dst_store(sk, dst,
-                                      ipv6_addr_equal(&fl->fl6_dst, &np->daddr) ?
+                                      ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ?
                                       &np->daddr : NULL,
 #ifdef CONFIG_IPV6_SUBTREES
-                                      ipv6_addr_equal(&fl->fl6_src, &np->saddr) ?
+                                      ipv6_addr_equal(&fl.fl6_src, &np->saddr) ?
                                       &np->saddr :
 #endif
                                       NULL);
diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c
new file mode 100644
index 000000000000..edcfffa9e87b
--- /dev/null
+++ b/net/ipv6/xfrm6_mode_beet.c
@@ -0,0 +1,107 @@
+/*
+ * xfrm6_mode_beet.c - BEET mode encapsulation for IPv6.
+ *
+ * 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/dsfield.h>
+#include <net/dst.h>
+#include <net/inet_ecn.h>
+#include <net/ipv6.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:
+ *      payload_len
+ *
+ * On exit, skb->h will be set to the start of the encapsulation header to be
+ * filled in by x->type->output and skb->nh will be set to the nextheader field
+ * of the extension header directly preceding the encapsulation header, or in
+ * its absence, that of the top IP header.  The value of skb->data will always
+ * point to the top IP header.
+ */
+static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+        struct ipv6hdr *iph, *top_iph;
+        u8 *prevhdr;
+        int hdr_len;
+
+        skb_push(skb, x->props.header_len);
+        iph = skb->nh.ipv6h;
+
+        hdr_len = ip6_find_1stfragopt(skb, &prevhdr);
+        skb->nh.raw = prevhdr - x->props.header_len;
+        skb->h.raw = skb->data + hdr_len;
+        memmove(skb->data, iph, hdr_len);
+
+        skb->nh.raw = skb->data;
+        top_iph = skb->nh.ipv6h;
+        skb->nh.raw = &top_iph->nexthdr;
+        skb->h.ipv6h = top_iph + 1;
+
+        ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr);
+        ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr);
+
+        return 0;
+}
+
+static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+        struct ipv6hdr *ip6h;
+        int size = sizeof(struct ipv6hdr);
+        int err = -EINVAL;
+
+        if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+                goto out;
+
+        skb_push(skb, size);
+        memmove(skb->data, skb->nh.raw, size);
+        skb->nh.raw = skb->data;
+
+        skb->mac.raw = memmove(skb->data - skb->mac_len,
+                               skb->mac.raw, skb->mac_len);
+
+        ip6h = skb->nh.ipv6h;
+        ip6h->payload_len = htons(skb->len - size);
+        ipv6_addr_copy(&ip6h->daddr, (struct in6_addr *) &x->sel.daddr.a6);
+        ipv6_addr_copy(&ip6h->saddr, (struct in6_addr *) &x->sel.saddr.a6);
+        err = 0;
+out:
+        return err;
+}
+
+static struct xfrm_mode xfrm6_beet_mode = {
+        .input = xfrm6_beet_input,
+        .output = xfrm6_beet_output,
+        .owner = THIS_MODULE,
+        .encap = XFRM_MODE_BEET,
+};
+
+static int __init xfrm6_beet_init(void)
+{
+        return xfrm_register_mode(&xfrm6_beet_mode, AF_INET6);
+}
+
+static void __exit xfrm6_beet_exit(void)
+{
+        int err;
+
+        err = xfrm_unregister_mode(&xfrm6_beet_mode, AF_INET6);
+        BUG_ON(err);
+}
+
+module_init(xfrm6_beet_init);
+module_exit(xfrm6_beet_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_BEET);