1 files changed, 208 insertions, 198 deletions

diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index b2b60f3e9cd..6156f68a1e9 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -1,192 +1,131 @@
-/* 
+/*
  * xfrm4_policy.c
  *
  * Changes:
  *	Kazunori MIYAZAWA @USAGI
  * 	YOSHIFUJI Hideaki @USAGI
  *		Split up af-specific portion
- * 	
+ *
  */
 
-#include <asm/bug.h>
-#include <linux/compiler.h>
-#include <linux/config.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
 #include <linux/inetdevice.h>
+#include <linux/if_tunnel.h>
+#include <net/dst.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
 
-static struct dst_ops xfrm4_dst_ops;
 static struct xfrm_policy_afinfo xfrm4_policy_afinfo;
 
-static struct xfrm_type_map xfrm4_type_map = { .lock = RW_LOCK_UNLOCKED };
+static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
+					    int tos,
+					    const xfrm_address_t *saddr,
+					    const xfrm_address_t *daddr)
+{
+	struct rtable *rt;
+
+	memset(fl4, 0, sizeof(*fl4));
+	fl4->daddr = daddr->a4;
+	fl4->flowi4_tos = tos;
+	if (saddr)
+		fl4->saddr = saddr->a4;
 
-static int xfrm4_dst_lookup(struct xfrm_dst **dst, struct flowi *fl)
+	rt = __ip_route_output_key(net, fl4);
+	if (!IS_ERR(rt))
+		return &rt->dst;
+
+	return ERR_CAST(rt);
+}
+
+static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos,
+					  const xfrm_address_t *saddr,
+					  const xfrm_address_t *daddr)
 {
-	return __ip_route_output_key((struct rtable**)dst, fl);
+	struct flowi4 fl4;
+
+	return __xfrm4_dst_lookup(net, &fl4, tos, saddr, daddr);
 }
 
-static struct dst_entry *
-__xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
+static int xfrm4_get_saddr(struct net *net,
+			   xfrm_address_t *saddr, xfrm_address_t *daddr)
 {
 	struct dst_entry *dst;
+	struct flowi4 fl4;
 
-	read_lock_bh(&policy->lock);
-	for (dst = policy->bundles; dst; dst = dst->next) {
-		struct xfrm_dst *xdst = (struct xfrm_dst*)dst;
-		if (xdst->u.rt.fl.oif == fl->oif &&	/*XXX*/
-		    xdst->u.rt.fl.fl4_dst == fl->fl4_dst &&
-	    	    xdst->u.rt.fl.fl4_src == fl->fl4_src &&
-		    xfrm_bundle_ok(xdst, fl, AF_INET)) {
-			dst_clone(dst);
-			break;
-		}
-	}
-	read_unlock_bh(&policy->lock);
-	return dst;
+	dst = __xfrm4_dst_lookup(net, &fl4, 0, NULL, daddr);
+	if (IS_ERR(dst))
+		return -EHOSTUNREACH;
+
+	saddr->a4 = fl4.saddr;
+	dst_release(dst);
+	return 0;
 }
 
-/* Allocate chain of dst_entry's, attach known xfrm's, calculate
- * all the metrics... Shortly, bundle a bundle.
- */
+static int xfrm4_get_tos(const struct flowi *fl)
+{
+	return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos; /* Strip ECN bits */
+}
 
-static int
-__xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int nx,
-		      struct flowi *fl, struct dst_entry **dst_p)
+static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst,
+			   int nfheader_len)
 {
-	struct dst_entry *dst, *dst_prev;
-	struct rtable *rt0 = (struct rtable*)(*dst_p);
-	struct rtable *rt = rt0;
-	u32 remote = fl->fl4_dst;
-	u32 local  = fl->fl4_src;
-	struct flowi fl_tunnel = {
-		.nl_u = {
-			.ip4_u = {
-				.saddr = local,
-				.daddr = remote
-			}
-		}
-	};
-	int i;
-	int err;
-	int header_len = 0;
-	int trailer_len = 0;
-
-	dst = dst_prev = NULL;
-	dst_hold(&rt->u.dst);
-
-	for (i = 0; i < nx; i++) {
-		struct dst_entry *dst1 = dst_alloc(&xfrm4_dst_ops);
-		struct xfrm_dst *xdst;
-		int tunnel = 0;
-
-		if (unlikely(dst1 == NULL)) {
-			err = -ENOBUFS;
-			dst_release(&rt->u.dst);
-			goto error;
-		}
+	return 0;
+}
 
-		if (!dst)
-			dst = dst1;
-		else {
-			dst_prev->child = dst1;
-			dst1->flags |= DST_NOHASH;
-			dst_clone(dst1);
-		}
+static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
+			  const struct flowi *fl)
+{
+	struct rtable *rt = (struct rtable *)xdst->route;
+	const struct flowi4 *fl4 = &fl->u.ip4;
 
-		xdst = (struct xfrm_dst *)dst1;
-		xdst->route = &rt->u.dst;
+	xdst->u.rt.rt_iif = fl4->flowi4_iif;
 
-		dst1->next = dst_prev;
-		dst_prev = dst1;
-		if (xfrm[i]->props.mode) {
-			remote = xfrm[i]->id.daddr.a4;
-			local  = xfrm[i]->props.saddr.a4;
-			tunnel = 1;
-		}
-		header_len += xfrm[i]->props.header_len;
-		trailer_len += xfrm[i]->props.trailer_len;
-
-		if (tunnel) {
-			fl_tunnel.fl4_src = local;
-			fl_tunnel.fl4_dst = remote;
-			err = xfrm_dst_lookup((struct xfrm_dst **)&rt,
-					      &fl_tunnel, AF_INET);
-			if (err)
-				goto error;
-		} else
-			dst_hold(&rt->u.dst);
-	}
+	xdst->u.dst.dev = dev;
+	dev_hold(dev);
 
-	dst_prev->child = &rt->u.dst;
-	dst->path = &rt->u.dst;
-
-	*dst_p = dst;
-	dst = dst_prev;
-
-	dst_prev = *dst_p;
-	i = 0;
-	for (; dst_prev != &rt->u.dst; dst_prev = dst_prev->child) {
-		struct xfrm_dst *x = (struct xfrm_dst*)dst_prev;
-		x->u.rt.fl = *fl;
-
-		dst_prev->xfrm = xfrm[i++];
-		dst_prev->dev = rt->u.dst.dev;
-		if (rt->u.dst.dev)
-			dev_hold(rt->u.dst.dev);
-		dst_prev->obsolete	= -1;
-		dst_prev->flags	       |= DST_HOST;
-		dst_prev->lastuse	= jiffies;
-		dst_prev->header_len	= header_len;
-		dst_prev->trailer_len	= trailer_len;
-		memcpy(&dst_prev->metrics, &x->route->metrics, sizeof(dst_prev->metrics));
-
-		/* Copy neighbout for reachability confirmation */
-		dst_prev->neighbour	= neigh_clone(rt->u.dst.neighbour);
-		dst_prev->input		= rt->u.dst.input;
-		dst_prev->output	= xfrm4_output;
-		if (rt->peer)
-			atomic_inc(&rt->peer->refcnt);
-		x->u.rt.peer = rt->peer;
-		/* Sheit... I remember I did this right. Apparently,
-		 * it was magically lost, so this code needs audit */
-		x->u.rt.rt_flags = rt0->rt_flags&(RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL);
-		x->u.rt.rt_type = rt->rt_type;
-		x->u.rt.rt_src = rt0->rt_src;
-		x->u.rt.rt_dst = rt0->rt_dst;
-		x->u.rt.rt_gateway = rt->rt_gateway;
-		x->u.rt.rt_spec_dst = rt0->rt_spec_dst;
-		x->u.rt.idev = rt0->idev;
-		in_dev_hold(rt0->idev);
-		header_len -= x->u.dst.xfrm->props.header_len;
-		trailer_len -= x->u.dst.xfrm->props.trailer_len;
-	}
+	/* Sheit... I remember I did this right. Apparently,
+	 * it was magically lost, so this code needs audit */
+	xdst->u.rt.rt_is_input = rt->rt_is_input;
+	xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST |
+					      RTCF_LOCAL);
+	xdst->u.rt.rt_type = rt->rt_type;
+	xdst->u.rt.rt_gateway = rt->rt_gateway;
+	xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
+	xdst->u.rt.rt_pmtu = rt->rt_pmtu;
+	INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
 
-	xfrm_init_pmtu(dst);
 	return 0;
-
-error:
-	if (dst)
-		dst_free(dst);
-	return err;
 }
 
 static void
-_decode_session4(struct sk_buff *skb, struct flowi *fl)
+_decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 {
-	struct iphdr *iph = skb->nh.iph;
-	u8 *xprth = skb->nh.raw + iph->ihl*4;
+	const struct iphdr *iph = ip_hdr(skb);
+	u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
+	struct flowi4 *fl4 = &fl->u.ip4;
+	int oif = 0;
+
+	if (skb_dst(skb))
+		oif = skb_dst(skb)->dev->ifindex;
 
-	memset(fl, 0, sizeof(struct flowi));
-	if (!(iph->frag_off & htons(IP_MF | IP_OFFSET))) {
+	memset(fl4, 0, sizeof(struct flowi4));
+	fl4->flowi4_mark = skb->mark;
+	fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
+
+	if (!ip_is_fragment(iph)) {
 		switch (iph->protocol) {
 		case IPPROTO_UDP:
+		case IPPROTO_UDPLITE:
 		case IPPROTO_TCP:
 		case IPPROTO_SCTP:
-			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
-				u16 *ports = (u16 *)xprth;
+		case IPPROTO_DCCP:
+			if (xprth + 4 < skb->data ||
+			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
+				__be16 *ports = (__be16 *)xprth;
 
-				fl->fl_ip_sport = ports[0];
-				fl->fl_ip_dport = ports[1];
+				fl4->fl4_sport = ports[!!reverse];
+				fl4->fl4_dport = ports[!reverse];
 			}
 			break;
 
@@ -194,130 +133,201 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl)
 			if (pskb_may_pull(skb, xprth + 2 - skb->data)) {
 				u8 *icmp = xprth;
 
-				fl->fl_icmp_type = icmp[0];
-				fl->fl_icmp_code = icmp[1];
+				fl4->fl4_icmp_type = icmp[0];
+				fl4->fl4_icmp_code = icmp[1];
 			}
 			break;
 
 		case IPPROTO_ESP:
 			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
-				u32 *ehdr = (u32 *)xprth;
+				__be32 *ehdr = (__be32 *)xprth;
 
-				fl->fl_ipsec_spi = ehdr[0];
+				fl4->fl4_ipsec_spi = ehdr[0];
 			}
 			break;
 
 		case IPPROTO_AH:
 			if (pskb_may_pull(skb, xprth + 8 - skb->data)) {
-				u32 *ah_hdr = (u32*)xprth;
+				__be32 *ah_hdr = (__be32 *)xprth;
 
-				fl->fl_ipsec_spi = ah_hdr[1];
+				fl4->fl4_ipsec_spi = ah_hdr[1];
 			}
 			break;
 
 		case IPPROTO_COMP:
 			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
-				u16 *ipcomp_hdr = (u16 *)xprth;
+				__be16 *ipcomp_hdr = (__be16 *)xprth;
+
+				fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
+			}
+			break;
+
+		case IPPROTO_GRE:
+			if (pskb_may_pull(skb, xprth + 12 - skb->data)) {
+				__be16 *greflags = (__be16 *)xprth;
+				__be32 *gre_hdr = (__be32 *)xprth;
 
-				fl->fl_ipsec_spi = ntohl(ntohs(ipcomp_hdr[1]));
+				if (greflags[0] & GRE_KEY) {
+					if (greflags[0] & GRE_CSUM)
+						gre_hdr++;
+					fl4->fl4_gre_key = gre_hdr[1];
+				}
 			}
 			break;
+
 		default:
-			fl->fl_ipsec_spi = 0;
+			fl4->fl4_ipsec_spi = 0;
 			break;
-		};
+		}
 	}
-	fl->proto = iph->protocol;
-	fl->fl4_dst = iph->daddr;
-	fl->fl4_src = iph->saddr;
+	fl4->flowi4_proto = iph->protocol;
+	fl4->daddr = reverse ? iph->saddr : iph->daddr;
+	fl4->saddr = reverse ? iph->daddr : iph->saddr;
+	fl4->flowi4_tos = iph->tos;
 }
 
-static inline int xfrm4_garbage_collect(void)
+static inline int xfrm4_garbage_collect(struct dst_ops *ops)
 {
-	read_lock(&xfrm4_policy_afinfo.lock);
-	xfrm4_policy_afinfo.garbage_collect();
-	read_unlock(&xfrm4_policy_afinfo.lock);
-	return (atomic_read(&xfrm4_dst_ops.entries) > xfrm4_dst_ops.gc_thresh*2);
+	struct net *net = container_of(ops, struct net, xfrm.xfrm4_dst_ops);
+
+	xfrm4_policy_afinfo.garbage_collect(net);
+	return (dst_entries_get_slow(ops) > ops->gc_thresh * 2);
 }
 
-static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			      struct sk_buff *skb, u32 mtu)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->update_pmtu(path, mtu);
+	path->ops->update_pmtu(path, sk, skb, mtu);
+}
+
+static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk,
+			   struct sk_buff *skb)
+{
+	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
+	struct dst_entry *path = xdst->route;
+
+	path->ops->redirect(path, sk, skb);
 }
 
 static void xfrm4_dst_destroy(struct dst_entry *dst)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 
-	if (likely(xdst->u.rt.idev))
-		in_dev_put(xdst->u.rt.idev);
+	dst_destroy_metrics_generic(dst);
+
 	xfrm_dst_destroy(xdst);
 }
 
 static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 			     int unregister)
 {
-	struct xfrm_dst *xdst;
-
 	if (!unregister)
 		return;
 
-	xdst = (struct xfrm_dst *)dst;
-	if (xdst->u.rt.idev->dev == dev) {
-		struct in_device *loopback_idev = in_dev_get(&loopback_dev);
-		BUG_ON(!loopback_idev);
-
-		do {
-			in_dev_put(xdst->u.rt.idev);
-			xdst->u.rt.idev = loopback_idev;
-			in_dev_hold(loopback_idev);
-			xdst = (struct xfrm_dst *)xdst->u.dst.child;
-		} while (xdst->u.dst.xfrm);
-
-		__in_dev_put(loopback_idev);
-	}
-
 	xfrm_dst_ifdown(dst, dev);
 }
 
 static struct dst_ops xfrm4_dst_ops = {
 	.family =		AF_INET,
-	.protocol =		__constant_htons(ETH_P_IP),
+	.protocol =		cpu_to_be16(ETH_P_IP),
 	.gc =			xfrm4_garbage_collect,
 	.update_pmtu =		xfrm4_update_pmtu,
+	.redirect =		xfrm4_redirect,
+	.cow_metrics =		dst_cow_metrics_generic,
 	.destroy =		xfrm4_dst_destroy,
 	.ifdown =		xfrm4_dst_ifdown,
-	.gc_thresh =		1024,
-	.entry_size =		sizeof(struct xfrm_dst),
+	.local_out =		__ip_local_out,
+	.gc_thresh =		32768,
 };
 
 static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
 	.family = 		AF_INET,
-	.lock = 		RW_LOCK_UNLOCKED,
-	.type_map = 		&xfrm4_type_map,
 	.dst_ops =		&xfrm4_dst_ops,
 	.dst_lookup =		xfrm4_dst_lookup,
-	.find_bundle = 		__xfrm4_find_bundle,
-	.bundle_create =	__xfrm4_bundle_create,
+	.get_saddr =		xfrm4_get_saddr,
 	.decode_session =	_decode_session4,
+	.get_tos =		xfrm4_get_tos,
+	.init_path =		xfrm4_init_path,
+	.fill_dst =		xfrm4_fill_dst,
+	.blackhole_route =	ipv4_blackhole_route,
 };
 
-static void __init xfrm4_policy_init(void)
+#ifdef CONFIG_SYSCTL
+static struct ctl_table xfrm4_policy_table[] = {
+	{
+		.procname       = "xfrm4_gc_thresh",
+		.data           = &init_net.xfrm.xfrm4_dst_ops.gc_thresh,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{ }
+};
+
+static int __net_init xfrm4_net_init(struct net *net)
 {
-	xfrm_policy_register_afinfo(&xfrm4_policy_afinfo);
+	struct ctl_table *table;
+	struct ctl_table_header *hdr;
+
+	table = xfrm4_policy_table;
+	if (!net_eq(net, &init_net)) {
+		table = kmemdup(table, sizeof(xfrm4_policy_table), GFP_KERNEL);
+		if (!table)
+			goto err_alloc;
+
+		table[0].data = &net->xfrm.xfrm4_dst_ops.gc_thresh;
+	}
+
+	hdr = register_net_sysctl(net, "net/ipv4", table);
+	if (!hdr)
+		goto err_reg;
+
+	net->ipv4.xfrm4_hdr = hdr;
+	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(table);
+err_alloc:
+	return -ENOMEM;
 }
 
-static void __exit xfrm4_policy_fini(void)
+static void __net_exit xfrm4_net_exit(struct net *net)
 {
-	xfrm_policy_unregister_afinfo(&xfrm4_policy_afinfo);
+	struct ctl_table *table;
+
+	if (net->ipv4.xfrm4_hdr == NULL)
+		return;
+
+	table = net->ipv4.xfrm4_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(net->ipv4.xfrm4_hdr);
+	if (!net_eq(net, &init_net))
+		kfree(table);
+}
+
+static struct pernet_operations __net_initdata xfrm4_net_ops = {
+	.init	= xfrm4_net_init,
+	.exit	= xfrm4_net_exit,
+};
+#endif
+
+static void __init xfrm4_policy_init(void)
+{
+	xfrm_policy_register_afinfo(&xfrm4_policy_afinfo);
 }
 
 void __init xfrm4_init(void)
 {
+	dst_entries_init(&xfrm4_dst_ops);
+
 	xfrm4_state_init();
 	xfrm4_policy_init();
+	xfrm4_protocol_init();
+#ifdef CONFIG_SYSCTL
+	register_pernet_subsys(&xfrm4_net_ops);
+#endif
 }