1 files changed, 133 insertions, 85 deletions

diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 7254e3f899a..2a0bbda2c76 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -20,26 +20,26 @@
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
 #include <net/mip6.h>
 #endif
 
-static struct dst_ops xfrm6_dst_ops;
 static struct xfrm_policy_afinfo xfrm6_policy_afinfo;
 
 static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos,
-					  xfrm_address_t *saddr,
-					  xfrm_address_t *daddr)
+					  const xfrm_address_t *saddr,
+					  const xfrm_address_t *daddr)
 {
-	struct flowi fl = {};
+	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int err;
 
-	memcpy(&fl.fl6_dst, daddr, sizeof(fl.fl6_dst));
+	memset(&fl6, 0, sizeof(fl6));
+	memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
 	if (saddr)
-		memcpy(&fl.fl6_src, saddr, sizeof(fl.fl6_src));
+		memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr));
 
-	dst = ip6_route_output(net, NULL, &fl);
+	dst = ip6_route_output(net, NULL, &fl6);
 
 	err = dst->error;
 	if (dst->error) {
@@ -68,39 +68,16 @@ static int xfrm6_get_saddr(struct net *net,
 	return 0;
 }
 
-static struct dst_entry *
-__xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
+static int xfrm6_get_tos(const struct flowi *fl)
 {
-	struct dst_entry *dst;
-
-	/* Still not clear if we should set fl->fl6_{src,dst}... */
-	read_lock_bh(&policy->lock);
-	for (dst = policy->bundles; dst; dst = dst->next) {
-		struct xfrm_dst *xdst = (struct xfrm_dst*)dst;
-		struct in6_addr fl_dst_prefix, fl_src_prefix;
-
-		ipv6_addr_prefix(&fl_dst_prefix,
-				 &fl->fl6_dst,
-				 xdst->u.rt6.rt6i_dst.plen);
-		ipv6_addr_prefix(&fl_src_prefix,
-				 &fl->fl6_src,
-				 xdst->u.rt6.rt6i_src.plen);
-		if (ipv6_addr_equal(&xdst->u.rt6.rt6i_dst.addr, &fl_dst_prefix) &&
-		    ipv6_addr_equal(&xdst->u.rt6.rt6i_src.addr, &fl_src_prefix) &&
-		    xfrm_bundle_ok(policy, xdst, fl, AF_INET6,
-				   (xdst->u.rt6.rt6i_dst.plen != 128 ||
-				    xdst->u.rt6.rt6i_src.plen != 128))) {
-			dst_clone(dst);
-			break;
-		}
-	}
-	read_unlock_bh(&policy->lock);
-	return dst;
+	return 0;
 }
 
-static int xfrm6_get_tos(struct flowi *fl)
+static void xfrm6_init_dst(struct net *net, struct xfrm_dst *xdst)
 {
-	return 0;
+	struct rt6_info *rt = (struct rt6_info *)xdst;
+
+	rt6_init_peer(rt, net->ipv6.peers);
 }
 
 static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
@@ -117,16 +94,21 @@ static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
 	return 0;
 }
 
-static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev)
+static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
+			  const struct flowi *fl)
 {
 	struct rt6_info *rt = (struct rt6_info*)xdst->route;
 
 	xdst->u.dst.dev = dev;
 	dev_hold(dev);
 
-	xdst->u.rt6.rt6i_idev = in6_dev_get(rt->u.dst.dev);
-	if (!xdst->u.rt6.rt6i_idev)
+	xdst->u.rt6.rt6i_idev = in6_dev_get(dev);
+	if (!xdst->u.rt6.rt6i_idev) {
+		dev_put(dev);
 		return -ENODEV;
+	}
+
+	rt6_transfer_peer(&xdst->u.rt6, rt);
 
 	/* Sheit... I remember I did this right. Apparently,
 	 * it was magically lost, so this code needs audit */
@@ -146,16 +128,24 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev)
 static inline void
 _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 {
+	struct flowi6 *fl6 = &fl->u.ip6;
 	int onlyproto = 0;
 	u16 offset = skb_network_header_len(skb);
-	struct ipv6hdr *hdr = ipv6_hdr(skb);
+	const struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct ipv6_opt_hdr *exthdr;
 	const unsigned char *nh = skb_network_header(skb);
 	u8 nexthdr = nh[IP6CB(skb)->nhoff];
+	int oif = 0;
+
+	if (skb_dst(skb))
+		oif = skb_dst(skb)->dev->ifindex;
 
-	memset(fl, 0, sizeof(struct flowi));
-	ipv6_addr_copy(&fl->fl6_dst, reverse ? &hdr->saddr : &hdr->daddr);
-	ipv6_addr_copy(&fl->fl6_src, reverse ? &hdr->daddr : &hdr->saddr);
+	memset(fl6, 0, sizeof(struct flowi6));
+	fl6->flowi6_mark = skb->mark;
+	fl6->flowi6_oif = reverse ? skb->skb_iif : oif;
+
+	fl6->daddr = reverse ? hdr->saddr : hdr->daddr;
+	fl6->saddr = reverse ? hdr->daddr : hdr->saddr;
 
 	while (nh + offset + 1 < skb->data ||
 	       pskb_may_pull(skb, nh + offset + 1 - skb->data)) {
@@ -182,31 +172,31 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 			     pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
 				__be16 *ports = (__be16 *)exthdr;
 
-				fl->fl_ip_sport = ports[!!reverse];
-				fl->fl_ip_dport = ports[!reverse];
+				fl6->fl6_sport = ports[!!reverse];
+				fl6->fl6_dport = ports[!reverse];
 			}
-			fl->proto = nexthdr;
+			fl6->flowi6_proto = nexthdr;
 			return;
 
 		case IPPROTO_ICMPV6:
 			if (!onlyproto && pskb_may_pull(skb, nh + offset + 2 - skb->data)) {
 				u8 *icmp = (u8 *)exthdr;
 
-				fl->fl_icmp_type = icmp[0];
-				fl->fl_icmp_code = icmp[1];
+				fl6->fl6_icmp_type = icmp[0];
+				fl6->fl6_icmp_code = icmp[1];
 			}
-			fl->proto = nexthdr;
+			fl6->flowi6_proto = nexthdr;
 			return;
 
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
 		case IPPROTO_MH:
 			if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) {
 				struct ip6_mh *mh;
 				mh = (struct ip6_mh *)exthdr;
 
-				fl->fl_mh_type = mh->ip6mh_type;
+				fl6->fl6_mh_type = mh->ip6mh_type;
 			}
-			fl->proto = nexthdr;
+			fl6->flowi6_proto = nexthdr;
 			return;
 #endif
 
@@ -215,8 +205,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 		case IPPROTO_ESP:
 		case IPPROTO_COMP:
 		default:
-			fl->fl_ipsec_spi = 0;
-			fl->proto = nexthdr;
+			fl6->fl6_ipsec_spi = 0;
+			fl6->flowi6_proto = nexthdr;
 			return;
 		}
 	}
@@ -224,16 +214,28 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 
 static inline int xfrm6_garbage_collect(struct dst_ops *ops)
 {
-	xfrm6_policy_afinfo.garbage_collect(&init_net);
-	return (atomic_read(&xfrm6_dst_ops.entries) > xfrm6_dst_ops.gc_thresh*2);
+	struct net *net = container_of(ops, struct net, xfrm.xfrm6_dst_ops);
+
+	xfrm6_policy_afinfo.garbage_collect(net);
+	return dst_entries_get_fast(ops) > ops->gc_thresh * 2;
 }
 
-static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu)
+static void xfrm6_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 xfrm6_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 xfrm6_dst_destroy(struct dst_entry *dst)
@@ -242,6 +244,11 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
 
 	if (likely(xdst->u.rt6.rt6i_idev))
 		in6_dev_put(xdst->u.rt6.rt6i_idev);
+	dst_destroy_metrics_generic(dst);
+	if (rt6_has_peer(&xdst->u.rt6)) {
+		struct inet_peer *peer = rt6_peer_ptr(&xdst->u.rt6);
+		inet_putpeer(peer);
+	}
 	xfrm_dst_destroy(xdst);
 }
 
@@ -277,11 +284,12 @@ static struct dst_ops xfrm6_dst_ops = {
 	.protocol =		cpu_to_be16(ETH_P_IPV6),
 	.gc =			xfrm6_garbage_collect,
 	.update_pmtu =		xfrm6_update_pmtu,
+	.redirect =		xfrm6_redirect,
+	.cow_metrics =		dst_cow_metrics_generic,
 	.destroy =		xfrm6_dst_destroy,
 	.ifdown =		xfrm6_dst_ifdown,
 	.local_out =		__ip6_local_out,
-	.gc_thresh =		1024,
-	.entries =		ATOMIC_INIT(0),
+	.gc_thresh =		32768,
 };
 
 static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
@@ -289,11 +297,12 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
 	.dst_ops =		&xfrm6_dst_ops,
 	.dst_lookup =		xfrm6_dst_lookup,
 	.get_saddr = 		xfrm6_get_saddr,
-	.find_bundle =		__xfrm6_find_bundle,
 	.decode_session =	_decode_session6,
 	.get_tos =		xfrm6_get_tos,
+	.init_dst =		xfrm6_init_dst,
 	.init_path =		xfrm6_init_path,
 	.fill_dst =		xfrm6_fill_dst,
+	.blackhole_route =	ip6_blackhole_route,
 };
 
 static int __init xfrm6_policy_init(void)
@@ -310,7 +319,7 @@ static void xfrm6_policy_fini(void)
 static struct ctl_table xfrm6_policy_table[] = {
 	{
 		.procname       = "xfrm6_gc_thresh",
-		.data	   	= &xfrm6_dst_ops.gc_thresh,
+		.data	   	= &init_net.xfrm.xfrm6_dst_ops.gc_thresh,
 		.maxlen	 	= sizeof(int),
 		.mode	   	= 0644,
 		.proc_handler   = proc_dointvec,
@@ -318,40 +327,79 @@ static struct ctl_table xfrm6_policy_table[] = {
 	{ }
 };
 
-static struct ctl_table_header *sysctl_hdr;
+static int __net_init xfrm6_net_init(struct net *net)
+{
+	struct ctl_table *table;
+	struct ctl_table_header *hdr;
+
+	table = xfrm6_policy_table;
+	if (!net_eq(net, &init_net)) {
+		table = kmemdup(table, sizeof(xfrm6_policy_table), GFP_KERNEL);
+		if (!table)
+			goto err_alloc;
+
+		table[0].data = &net->xfrm.xfrm6_dst_ops.gc_thresh;
+	}
+
+	hdr = register_net_sysctl(net, "net/ipv6", table);
+	if (!hdr)
+		goto err_reg;
+
+	net->ipv6.sysctl.xfrm6_hdr = hdr;
+	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(table);
+err_alloc:
+	return -ENOMEM;
+}
+
+static void __net_exit xfrm6_net_exit(struct net *net)
+{
+	struct ctl_table *table;
+
+	if (net->ipv6.sysctl.xfrm6_hdr == NULL)
+		return;
+
+	table = net->ipv6.sysctl.xfrm6_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(net->ipv6.sysctl.xfrm6_hdr);
+	if (!net_eq(net, &init_net))
+		kfree(table);
+}
+
+static struct pernet_operations xfrm6_net_ops = {
+	.init	= xfrm6_net_init,
+	.exit	= xfrm6_net_exit,
+};
 #endif
 
 int __init xfrm6_init(void)
 {
 	int ret;
-	unsigned int gc_thresh;
+
+	dst_entries_init(&xfrm6_dst_ops);
 
 	ret = xfrm6_policy_init();
-	if (ret)
+	if (ret) {
+		dst_entries_destroy(&xfrm6_dst_ops);
 		goto out;
-
+	}
 	ret = xfrm6_state_init();
 	if (ret)
 		goto out_policy;
-	/*
-	 * We need a good default value for the xfrm6 gc threshold.
-	 * In ipv4 we set it to the route hash table size * 8, which
-	 * is half the size of the maximaum route cache for ipv4.  It
-	 * would be good to do the same thing for v6, except the table is
-	 * constructed differently here.  Here each table for a net namespace
-	 * can have FIB_TABLE_HASHSZ entries, so lets go with the same
-	 * computation that we used for ipv4 here.  Also, lets keep the initial
-	 * gc_thresh to a minimum of 1024, since, the ipv6 route cache defaults
-	 * to that as a minimum as well
-	 */
-	gc_thresh = FIB6_TABLE_HASHSZ * 8;
-	xfrm6_dst_ops.gc_thresh = (gc_thresh < 1024) ? 1024 : gc_thresh;
+
+	ret = xfrm6_protocol_init();
+	if (ret)
+		goto out_state;
+
 #ifdef CONFIG_SYSCTL
-	sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv6_ctl_path,
-						xfrm6_policy_table);
+	register_pernet_subsys(&xfrm6_net_ops);
 #endif
 out:
 	return ret;
+out_state:
+	xfrm6_state_fini();
 out_policy:
 	xfrm6_policy_fini();
 	goto out;
@@ -360,10 +408,10 @@ out_policy:
 void xfrm6_fini(void)
 {
 #ifdef CONFIG_SYSCTL
-	if (sysctl_hdr)
-		unregister_net_sysctl_table(sysctl_hdr);
+	unregister_pernet_subsys(&xfrm6_net_ops);
 #endif
-	//xfrm6_input_fini();
+	xfrm6_protocol_fini();
 	xfrm6_policy_fini();
 	xfrm6_state_fini();
+	dst_entries_destroy(&xfrm6_dst_ops);
 }