Merge branch 'master' of /home/trondmy/kernel/linux-2.6/

17 files changed, 294 insertions, 161 deletions

diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index f8a107ab5592..e923d4dea418 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -106,6 +106,26 @@ config INET6_TUNNEL
         tristate
         default n
 
+config INET6_XFRM_MODE_TRANSPORT
+        tristate "IPv6: IPsec transport mode"
+        depends on IPV6
+        default IPV6
+        select XFRM
+        ---help---
+          Support for IPsec transport mode.
+
+          If unsure, say Y.
+
+config INET6_XFRM_MODE_TUNNEL
+        tristate "IPv6: IPsec tunnel mode"
+        depends on IPV6
+        default IPV6
+        select XFRM
+        ---help---
+          Support for IPsec tunnel mode.
+
+          If unsure, say Y.
+
 config IPV6_TUNNEL
         tristate "IPv6: IPv6-in-IPv6 tunnel"
         select INET6_TUNNEL
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index a760b0988fbb..386e0a626948 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -20,6 +20,8 @@ obj-$(CONFIG_INET6_ESP) += esp6.o
 obj-$(CONFIG_INET6_IPCOMP) += ipcomp6.o
 obj-$(CONFIG_INET6_XFRM_TUNNEL) += xfrm6_tunnel.o
 obj-$(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_NETFILTER) += netfilter/
 
 obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 445006ee4522..c2c26fa0943d 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2860,6 +2860,11 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
         return inet6_addr_add(ifm->ifa_index, pfx, ifm->ifa_prefixlen);
 }
 
+/* Maximum length of ifa_cacheinfo attributes */
+#define INET6_IFADDR_RTA_SPACE \
+                RTA_SPACE(16) /* IFA_ADDRESS */ + \
+                RTA_SPACE(sizeof(struct ifa_cacheinfo)) /* CACHEINFO */
+
 static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
                              u32 pid, u32 seq, int event, unsigned int flags)
 {
@@ -3092,7 +3097,7 @@ static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb)
 static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa)
 {
         struct sk_buff *skb;
-        int size = NLMSG_SPACE(sizeof(struct ifaddrmsg)+128);
+        int size = NLMSG_SPACE(sizeof(struct ifaddrmsg) + INET6_IFADDR_RTA_SPACE);
 
         skb = alloc_skb(size, GFP_ATOMIC);
         if (!skb) {
@@ -3142,6 +3147,17 @@ static void inline ipv6_store_devconf(struct ipv6_devconf *cnf,
 #endif
 }
 
+/* Maximum length of ifinfomsg attributes */
+#define INET6_IFINFO_RTA_SPACE \
+                RTA_SPACE(IFNAMSIZ) /* IFNAME */ + \
+                RTA_SPACE(MAX_ADDR_LEN) /* ADDRESS */ + \
+                RTA_SPACE(sizeof(u32)) /* MTU */ + \
+                RTA_SPACE(sizeof(int)) /* LINK */ + \
+                RTA_SPACE(0) /* PROTINFO */ + \
+                RTA_SPACE(sizeof(u32)) /* FLAGS */ + \
+                RTA_SPACE(sizeof(struct ifla_cacheinfo)) /* CACHEINFO */ + \
+                RTA_SPACE(sizeof(__s32[DEVCONF_MAX])) /* CONF */
+
 static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, 
                              u32 pid, u32 seq, int event, unsigned int flags)
 {
@@ -3235,8 +3251,7 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 void inet6_ifinfo_notify(int event, struct inet6_dev *idev)
 {
         struct sk_buff *skb;
-        /* 128 bytes ?? */
-        int size = NLMSG_SPACE(sizeof(struct ifinfomsg)+128);
+        int size = NLMSG_SPACE(sizeof(struct ifinfomsg) + INET6_IFINFO_RTA_SPACE);
         
         skb = alloc_skb(size, GFP_ATOMIC);
         if (!skb) {
@@ -3252,6 +3267,11 @@ void inet6_ifinfo_notify(int event, struct inet6_dev *idev)
         netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_IFINFO, GFP_ATOMIC);
 }
 
+/* Maximum length of prefix_cacheinfo attributes */
+#define INET6_PREFIX_RTA_SPACE \
+                RTA_SPACE(sizeof(((struct prefix_info *)NULL)->prefix)) /* ADDRESS */ + \
+                RTA_SPACE(sizeof(struct prefix_cacheinfo)) /* CACHEINFO */
+
 static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev,
                         struct prefix_info *pinfo, u32 pid, u32 seq, 
                         int event, unsigned int flags)
@@ -3296,7 +3316,7 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev,
                          struct prefix_info *pinfo)
 {
         struct sk_buff *skb;
-        int size = NLMSG_SPACE(sizeof(struct prefixmsg)+128);
+        int size = NLMSG_SPACE(sizeof(struct prefixmsg) + INET6_PREFIX_RTA_SPACE);
 
         skb = alloc_skb(size, GFP_ATOMIC);
         if (!skb) {
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 6778173a3dda..d31c0d6c0448 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -292,7 +292,7 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
 
                 memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
                 memset(ah->auth_data, 0, ahp->icv_trunc_len);
-                skb_push(skb, skb->data - skb->nh.raw);
+                skb_push(skb, hdr_len);
                 ahp->icv(ahp, skb, ah->auth_data);
                 if (memcmp(ah->auth_data, auth_data, ahp->icv_trunc_len)) {
                         LIMIT_NETDEBUG(KERN_WARNING "ipsec ah authentication error\n");
@@ -301,12 +301,8 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
                 }
         }
 
-        skb->nh.raw = skb_pull(skb, ah_hlen);
-        memcpy(skb->nh.raw, tmp_hdr, hdr_len);
-        skb->nh.ipv6h->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
-        skb_pull(skb, hdr_len);
-        skb->h.raw = skb->data;
-
+        skb->h.raw = memcpy(skb->nh.raw += ah_hlen, tmp_hdr, hdr_len);
+        __skb_pull(skb, ah_hlen + hdr_len);
 
         kfree(tmp_hdr);
 
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 22f046079037..a15a6f320f70 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -142,25 +142,17 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 
         int hdr_len = skb->h.raw - skb->nh.raw;
         int nfrags;
-        unsigned char *tmp_hdr = NULL;
         int ret = 0;
 
         if (!pskb_may_pull(skb, sizeof(struct ipv6_esp_hdr))) {
                 ret = -EINVAL;
-                goto out_nofree;
+                goto out;
         }
 
         if (elen <= 0 || (elen & (blksize-1))) {
                 ret = -EINVAL;
-                goto out_nofree;
-        }
-
-        tmp_hdr = kmalloc(hdr_len, GFP_ATOMIC);
-        if (!tmp_hdr) {
-                ret = -ENOMEM;
-                goto out_nofree;
+                goto out;
         }
-        memcpy(tmp_hdr, skb->nh.raw, hdr_len);
 
         /* If integrity check is required, do this. */
         if (esp->auth.icv_full_len) {
@@ -222,16 +214,12 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
                 /* ... check padding bits here. Silly. :-) */ 
 
                 pskb_trim(skb, skb->len - alen - padlen - 2);
-                skb->h.raw = skb_pull(skb, sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen);
-                skb->nh.raw += sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen;
-                memcpy(skb->nh.raw, tmp_hdr, hdr_len);
-                skb->nh.ipv6h->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
                 ret = nexthdr[1];
         }
 
+        skb->h.raw = __skb_pull(skb, sizeof(*esph) + esp->conf.ivlen) - hdr_len;
+
 out:
-        kfree(tmp_hdr);
-out_nofree:
         return ret;
 }
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index e46048974f37..d29620f4910e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -39,6 +39,7 @@
 #include <linux/in6.h>
 #include <linux/tcp.h>
 #include <linux/route.h>
+#include <linux/module.h>
 
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv6.h>
@@ -458,6 +459,7 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
         nf_bridge_get(to->nf_bridge);
 #endif
 #endif
+        skb_copy_secmark(to, from);
 }
 
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
@@ -488,6 +490,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
         return offset;
 }
+EXPORT_SYMBOL_GPL(ip6_find_1stfragopt);
 
 static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 48636436028a..f28cd37feed3 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -65,38 +65,25 @@ static LIST_HEAD(ipcomp6_tfms_list);
 
 static int ipcomp6_input(struct xfrm_state *x, struct sk_buff *skb)
 {
-        int err = 0;
-        u8 nexthdr = 0;
-        int hdr_len = skb->h.raw - skb->nh.raw;
-        unsigned char *tmp_hdr = NULL;
+        int err = -ENOMEM;
         struct ipv6hdr *iph;
+        struct ipv6_comp_hdr *ipch;
         int plen, dlen;
         struct ipcomp_data *ipcd = x->data;
         u8 *start, *scratch;
         struct crypto_tfm *tfm;
         int cpu;
 
-        if ((skb_is_nonlinear(skb) || skb_cloned(skb)) &&
-                skb_linearize(skb, GFP_ATOMIC) != 0) {
-                err = -ENOMEM;
+        if (skb_linearize_cow(skb))
                 goto out;
-        }
 
         skb->ip_summed = CHECKSUM_NONE;
 
         /* Remove ipcomp header and decompress original payload */
         iph = skb->nh.ipv6h;
-        tmp_hdr = kmalloc(hdr_len, GFP_ATOMIC);
-        if (!tmp_hdr)
-                goto out;
-        memcpy(tmp_hdr, iph, hdr_len);
-        nexthdr = *(u8 *)skb->data;
-        skb_pull(skb, sizeof(struct ipv6_comp_hdr)); 
-        skb->nh.raw += sizeof(struct ipv6_comp_hdr);
-        memcpy(skb->nh.raw, tmp_hdr, hdr_len);
-        iph = skb->nh.ipv6h;
-        iph->payload_len = htons(ntohs(iph->payload_len) - sizeof(struct ipv6_comp_hdr));
-        skb->h.raw = skb->data;
+        ipch = (void *)skb->data;
+        skb->h.raw = skb->nh.raw + sizeof(*ipch);
+        __skb_pull(skb, sizeof(*ipch));
 
         /* decompression */
         plen = skb->len;
@@ -125,18 +112,11 @@ static int ipcomp6_input(struct xfrm_state *x, struct sk_buff *skb)
 
         skb_put(skb, dlen - plen);
         memcpy(skb->data, scratch, dlen);
+        err = ipch->nexthdr;
 
-        iph = skb->nh.ipv6h;
-        iph->payload_len = htons(skb->len);
-        
 out_put_cpu:
         put_cpu();
 out:
-        kfree(tmp_hdr);
-        if (err)
-                goto error_out;
-        return nexthdr;
-error_out:
         return err;
 }
 
@@ -159,10 +139,8 @@ static int ipcomp6_output(struct xfrm_state *x, struct sk_buff *skb)
                 goto out_ok;
         }
 
-        if ((skb_is_nonlinear(skb) || skb_cloned(skb)) &&
-                skb_linearize(skb, GFP_ATOMIC) != 0) {
+        if (skb_linearize_cow(skb))
                 goto out_ok;
-        }
 
         /* compression */
         plen = skb->len - hdr_len;
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 93bae36f2663..2a71c3b669f1 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -189,7 +189,7 @@ static unsigned int ipv6_confirm(unsigned int hooknum,
 
         /* This is where we call the helper: as the packet goes out. */
         ct = nf_ct_get(*pskb, &ctinfo);
-        if (!ct)
+        if (!ct || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)
                 goto out;
 
         help = nfct_help(ct);
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index 86c6703265d0..ef18a7b7014b 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -233,7 +233,7 @@ icmpv6_error(struct sk_buff *skb, unsigned int dataoff,
                 return -NF_ACCEPT;
         }
 
-        if (hooknum == NF_IP6_PRE_ROUTING &&
+        if (nf_conntrack_checksum && hooknum == NF_IP6_PRE_ROUTING &&
             nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) {
                 nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL,
                               "nf_ct_icmpv6: ICMPv6 checksum failed\n");
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 3e319035f82d..c32a029e43f0 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -456,13 +456,9 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
                 DEBUGP("queue: message is too short.\n");
                 goto err;
         }
-        if (end-offset < skb->len) {
-                if (pskb_trim(skb, end - offset)) {
-                        DEBUGP("Can't trim\n");
-                        goto err;
-                }
-                if (skb->ip_summed != CHECKSUM_UNNECESSARY)
-                        skb->ip_summed = CHECKSUM_NONE;
+        if (pskb_trim_rcsum(skb, end - offset)) {
+                DEBUGP("Can't trim\n");
+                goto err;
         }
 
         /* Find out which fragments are in front and at the back of us
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 301eee726b0f..a50eb306e9e2 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1218,8 +1218,16 @@ process:
         bh_lock_sock(sk);
         ret = 0;
         if (!sock_owned_by_user(sk)) {
-                if (!tcp_prequeue(sk, skb))
-                        ret = tcp_v6_do_rcv(sk, skb);
+#ifdef CONFIG_NET_DMA
+                struct tcp_sock *tp = tcp_sk(sk);
+                if (tp->ucopy.dma_chan)
+                        ret = tcp_v6_do_rcv(sk, skb);
+                else
+#endif
+                {
+                        if (!tcp_prequeue(sk, skb))
+                                ret = tcp_v6_do_rcv(sk, skb);
+                }
         } else
                 sk_add_backlog(sk, skb);
         bh_unlock_sock(sk);
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 00cfdee18dca..0405d74ff910 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -13,21 +13,9 @@
 #include <linux/string.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv6.h>
-#include <net/dsfield.h>
-#include <net/inet_ecn.h>
-#include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/xfrm.h>
 
-static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
-{
-        struct ipv6hdr *outer_iph = skb->nh.ipv6h;
-        struct ipv6hdr *inner_iph = skb->h.ipv6h;
-
-        if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph)))
-                IP6_ECN_set_ce(inner_iph);
-}
-
 int xfrm6_rcv_spi(struct sk_buff *skb, u32 spi)
 {
         int err;
@@ -81,21 +69,10 @@ int xfrm6_rcv_spi(struct sk_buff *skb, u32 spi)
 
                 xfrm_vec[xfrm_nr++] = x;
 
+                if (x->mode->input(x, skb))
+                        goto drop;
+
                 if (x->props.mode) { /* XXX */
-                        if (nexthdr != IPPROTO_IPV6)
-                                goto drop;
-                        if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
-                                goto drop;
-                        if (skb_cloned(skb) &&
-                            pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
-                                goto drop;
-                        if (x->props.flags & XFRM_STATE_DECAP_DSCP)
-                                ipv6_copy_dscp(skb->nh.ipv6h, skb->h.ipv6h);
-                        if (!(x->props.flags & XFRM_STATE_NOECN))
-                                ipip6_ecn_decapsulate(skb);
-                        skb->mac.raw = memmove(skb->data - skb->mac_len,
-                                               skb->mac.raw, skb->mac_len);
-                        skb->nh.raw = skb->data;
                         decaps = 1;
                         break;
                 }
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
new file mode 100644
index 000000000000..711d713e36d8
--- /dev/null
+++ b/net/ipv6/xfrm6_mode_transport.c
@@ -0,0 +1,88 @@
+/*
+ * xfrm6_mode_transport.c - Transport mode encapsulation for IPv6.
+ *
+ * Copyright (C) 2002 USAGI/WIDE Project
+ * Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+
+#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/ipv6.h>
+#include <net/xfrm.h>
+
+/* Add encapsulation header.
+ *
+ * The IP header and mutable extension headers will be moved forward to make
+ * space for the encapsulation header.
+ *
+ * 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_transport_output(struct sk_buff *skb)
+{
+        struct xfrm_state *x = skb->dst->xfrm;
+        struct ipv6hdr *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);
+        return 0;
+}
+
+/* Remove encapsulation header.
+ *
+ * The IP header will be moved over the top of the encapsulation header.
+ *
+ * On entry, skb->h shall point to where the IP header should be and skb->nh
+ * shall be set to where the IP header currently is.  skb->data shall point
+ * to the start of the payload.
+ */
+static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+        int ihl = skb->data - skb->h.raw;
+
+        if (skb->h.raw != skb->nh.raw)
+                skb->nh.raw = memmove(skb->h.raw, skb->nh.raw, ihl);
+        skb->nh.ipv6h->payload_len = htons(skb->len + ihl -
+                                           sizeof(struct ipv6hdr));
+        skb->h.raw = skb->data;
+        return 0;
+}
+
+static struct xfrm_mode xfrm6_transport_mode = {
+        .input = xfrm6_transport_input,
+        .output = xfrm6_transport_output,
+        .owner = THIS_MODULE,
+        .encap = XFRM_MODE_TRANSPORT,
+};
+
+static int __init xfrm6_transport_init(void)
+{
+        return xfrm_register_mode(&xfrm6_transport_mode, AF_INET6);
+}
+
+static void __exit xfrm6_transport_exit(void)
+{
+        int err;
+
+        err = xfrm_unregister_mode(&xfrm6_transport_mode, AF_INET6);
+        BUG_ON(err);
+}
+
+module_init(xfrm6_transport_init);
+module_exit(xfrm6_transport_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_TRANSPORT);
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
new file mode 100644
index 000000000000..8af79be2edca
--- /dev/null
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -0,0 +1,121 @@
+/*
+ * xfrm6_mode_tunnel.c - Tunnel mode encapsulation for IPv6.
+ *
+ * Copyright (C) 2002 USAGI/WIDE Project
+ * Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+
+#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>
+
+static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
+{
+        struct ipv6hdr *outer_iph = skb->nh.ipv6h;
+        struct ipv6hdr *inner_iph = skb->h.ipv6h;
+
+        if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph)))
+                IP6_ECN_set_ce(inner_iph);
+}
+
+/* Add encapsulation header.
+ *
+ * The top IP header will be constructed per RFC 2401.  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_tunnel_output(struct sk_buff *skb)
+{
+        struct dst_entry *dst = skb->dst;
+        struct xfrm_state *x = dst->xfrm;
+        struct ipv6hdr *iph, *top_iph;
+        int dsfield;
+
+        skb_push(skb, x->props.header_len);
+        iph = skb->nh.ipv6h;
+
+        skb->nh.raw = skb->data;
+        top_iph = skb->nh.ipv6h;
+        skb->nh.raw = &top_iph->nexthdr;
+        skb->h.ipv6h = top_iph + 1;
+
+        top_iph->version = 6;
+        top_iph->priority = iph->priority;
+        top_iph->flow_lbl[0] = iph->flow_lbl[0];
+        top_iph->flow_lbl[1] = iph->flow_lbl[1];
+        top_iph->flow_lbl[2] = iph->flow_lbl[2];
+        dsfield = ipv6_get_dsfield(top_iph);
+        dsfield = INET_ECN_encapsulate(dsfield, dsfield);
+        if (x->props.flags & XFRM_STATE_NOECN)
+                dsfield &= ~INET_ECN_MASK;
+        ipv6_change_dsfield(top_iph, 0, dsfield);
+        top_iph->nexthdr = IPPROTO_IPV6; 
+        top_iph->hop_limit = dst_metric(dst->child, RTAX_HOPLIMIT);
+        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_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+        int err = -EINVAL;
+
+        if (skb->nh.raw[IP6CB(skb)->nhoff] != IPPROTO_IPV6)
+                goto out;
+        if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+                goto out;
+
+        if (skb_cloned(skb) &&
+            (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+                goto out;
+
+        if (x->props.flags & XFRM_STATE_DECAP_DSCP)
+                ipv6_copy_dscp(skb->nh.ipv6h, skb->h.ipv6h);
+        if (!(x->props.flags & XFRM_STATE_NOECN))
+                ipip6_ecn_decapsulate(skb);
+        skb->mac.raw = memmove(skb->data - skb->mac_len,
+                               skb->mac.raw, skb->mac_len);
+        skb->nh.raw = skb->data;
+        err = 0;
+
+out:
+        return err;
+}
+
+static struct xfrm_mode xfrm6_tunnel_mode = {
+        .input = xfrm6_tunnel_input,
+        .output = xfrm6_tunnel_output,
+        .owner = THIS_MODULE,
+        .encap = XFRM_MODE_TUNNEL,
+};
+
+static int __init xfrm6_tunnel_init(void)
+{
+        return xfrm_register_mode(&xfrm6_tunnel_mode, AF_INET6);
+}
+
+static void __exit xfrm6_tunnel_exit(void)
+{
+        int err;
+
+        err = xfrm_unregister_mode(&xfrm6_tunnel_mode, AF_INET6);
+        BUG_ON(err);
+}
+
+module_init(xfrm6_tunnel_init);
+module_exit(xfrm6_tunnel_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_TUNNEL);
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 80242172a5df..16e84254a252 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -14,68 +14,9 @@
 #include <linux/spinlock.h>
 #include <linux/icmpv6.h>
 #include <linux/netfilter_ipv6.h>
-#include <net/dsfield.h>
-#include <net/inet_ecn.h>
 #include <net/ipv6.h>
 #include <net/xfrm.h>
 
-/* Add encapsulation header.
- *
- * In transport mode, the IP header and mutable extension headers will be moved
- * forward to make space for the encapsulation header.
- *
- * In tunnel mode, the top IP header will be constructed per RFC 2401.
- * 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 void xfrm6_encap(struct sk_buff *skb)
-{
-        struct dst_entry *dst = skb->dst;
-        struct xfrm_state *x = dst->xfrm;
-        struct ipv6hdr *iph, *top_iph;
-        int dsfield;
-
-        skb_push(skb, x->props.header_len);
-        iph = skb->nh.ipv6h;
-
-        if (!x->props.mode) {
-                u8 *prevhdr;
-                int hdr_len;
-
-                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);
-                return;
-        }
-
-        skb->nh.raw = skb->data;
-        top_iph = skb->nh.ipv6h;
-        skb->nh.raw = &top_iph->nexthdr;
-        skb->h.ipv6h = top_iph + 1;
-
-        top_iph->version = 6;
-        top_iph->priority = iph->priority;
-        top_iph->flow_lbl[0] = iph->flow_lbl[0];
-        top_iph->flow_lbl[1] = iph->flow_lbl[1];
-        top_iph->flow_lbl[2] = iph->flow_lbl[2];
-        dsfield = ipv6_get_dsfield(top_iph);
-        dsfield = INET_ECN_encapsulate(dsfield, dsfield);
-        if (x->props.flags & XFRM_STATE_NOECN)
-                dsfield &= ~INET_ECN_MASK;
-        ipv6_change_dsfield(top_iph, 0, dsfield);
-        top_iph->nexthdr = IPPROTO_IPV6; 
-        top_iph->hop_limit = dst_metric(dst->child, RTAX_HOPLIMIT);
-        ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr);
-        ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr);
-}
-
 static int xfrm6_tunnel_check_size(struct sk_buff *skb)
 {
         int mtu, ret = 0;
@@ -118,7 +59,9 @@ static int xfrm6_output_one(struct sk_buff *skb)
                 if (err)
                         goto error;
 
-                xfrm6_encap(skb);
+                err = x->mode->output(skb);
+                if (err)
+                        goto error;
 
                 err = x->type->output(x, skb);
                 if (err)
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 88c840f1beb6..ee715f2691e9 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -23,8 +23,6 @@
 static struct dst_ops xfrm6_dst_ops;
 static struct xfrm_policy_afinfo xfrm6_policy_afinfo;
 
-static struct xfrm_type_map xfrm6_type_map = { .lock = RW_LOCK_UNLOCKED };
-
 static int xfrm6_dst_lookup(struct xfrm_dst **dst, struct flowi *fl)
 {
         int err = 0;
@@ -249,9 +247,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl)
 
 static inline int xfrm6_garbage_collect(void)
 {
-        read_lock(&xfrm6_policy_afinfo.lock);
         xfrm6_policy_afinfo.garbage_collect();
-        read_unlock(&xfrm6_policy_afinfo.lock);
         return (atomic_read(&xfrm6_dst_ops.entries) > xfrm6_dst_ops.gc_thresh*2);
 }
 
@@ -311,8 +307,6 @@ static struct dst_ops xfrm6_dst_ops = {
 
 static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
         .family =               AF_INET6,
-        .lock =                 RW_LOCK_UNLOCKED,
-        .type_map =             &xfrm6_type_map,
         .dst_ops =              &xfrm6_dst_ops,
         .dst_lookup =           xfrm6_dst_lookup,
         .find_bundle =          __xfrm6_find_bundle,
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index a5723024d3b3..b33296b3f6de 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -135,7 +135,6 @@ __xfrm6_find_acq(u8 mode, u32 reqid, u8 proto,
 
 static struct xfrm_state_afinfo xfrm6_state_afinfo = {
         .family                 = AF_INET6,
-        .lock                   = RW_LOCK_UNLOCKED,
         .init_tempsel           = __xfrm6_init_tempsel,
         .state_lookup           = __xfrm6_state_lookup,
         .find_acq               = __xfrm6_find_acq,