Merge remote-tracking branch 'origin/testing'

Xin Long says:

==================
Now ipip and ipv6 tunnels processing is supported by xfrm4/6_tunnel,
but not in vti and xfrmi. This feature is needed by processing those
uncompressed small fragments and packets when using comp protocol.
It means vti and xfrmi won't be able to accept small fragments or
packets when using comp protocol, which is not expected.

xfrm4/6_tunnel eventually calls xfrm_input() to process ipip and ipv6
tunnels with an ipip/ipv6-proto state (a child state of comp-proto
state), and vti and xfrmi should do the same.

The extra things for vti to do is:

  - vti_input() should be called before xfrm_input() to set
    XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4/6 = tunnel. [A]

  - vti_rcv_cb() should be called after xfrm_input() to update
    the skb->dev. [B]

And the extra things for xfrmi to do is:

   - The ipip/ipv6-proto state should be assigned if_id from its
     parent's state. [C]

   - xfrmi_rcv_cb() should be called after xfrm_input() to update
     the skb->dev. [D]

Patch 4-7 does the things in [A].

To implement [B] and [D], patch 1-3 is to build a callback function
for xfrm4/6_tunnel, which can be called after xfrm_input(), similar
to xfrm4/6_protocol's .cb_handler. vti and xfrmi only needs to give
their own callback function in patch 4-7 and 9-10, which already
exists: vti_rcv_cb() and xfrmi_rcv_cb().

Patch 8 is to do the thing in [C] by assigning child tunnel's if_id
from its parent tunnel.

With the whole patch series, the segments or packets with any size
can work with ipsec comp proto on vti and xfrmi.

v1->v2:
  - See Patch 2-3.
v2->v3:
  - See Patch 2-3, 4, 6, 9-10.
==================

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

include/net/xfrm.h

@@ -373,7 +373,8 @@ struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family);
 struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family);
 
 struct xfrm_input_afinfo {
-	unsigned int		family;
+	u8			family;
+	bool			is_ipip;
 	int			(*callback)(struct sk_buff *skb, u8 protocol,
 					    int err);
 };
@@ -1415,6 +1416,7 @@ struct xfrm6_protocol {
 /* XFRM tunnel handlers.  */
 struct xfrm_tunnel {
 	int (*handler)(struct sk_buff *skb);
+	int (*cb_handler)(struct sk_buff *skb, int err);
 	int (*err_handler)(struct sk_buff *skb, u32 info);
 
 	struct xfrm_tunnel __rcu *next;
@@ -1423,6 +1425,7 @@ struct xfrm_tunnel {
 
 struct xfrm6_tunnel {
 	int (*handler)(struct sk_buff *skb);
+	int (*cb_handler)(struct sk_buff *skb, int err);
 	int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			   u8 type, u8 code, int offset, __be32 info);
 	struct xfrm6_tunnel __rcu *next;

net/ipv4/ip_vti.c

@@ -91,32 +91,6 @@ static int vti_rcv_proto(struct sk_buff *skb)
 	return vti_rcv(skb, 0, false);
 }
 
-static int vti_rcv_tunnel(struct sk_buff *skb)
-{
-	struct ip_tunnel_net *itn = net_generic(dev_net(skb->dev), vti_net_id);
-	const struct iphdr *iph = ip_hdr(skb);
-	struct ip_tunnel *tunnel;
-
-	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
-				  iph->saddr, iph->daddr, 0);
-	if (tunnel) {
-		struct tnl_ptk_info tpi = {
-			.proto = htons(ETH_P_IP),
-		};
-
-		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
-			goto drop;
-		if (iptunnel_pull_header(skb, 0, tpi.proto, false))
-			goto drop;
-		return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, false);
-	}
-
-	return -EINVAL;
-drop:
-	kfree_skb(skb);
-	return 0;
-}
-
 static int vti_rcv_cb(struct sk_buff *skb, int err)
 {
 	unsigned short family;
@@ -495,11 +469,22 @@ static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
 	.priority	=	100,
 };
 
-static struct xfrm_tunnel ipip_handler __read_mostly = {
+#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL)
+static int vti_rcv_tunnel(struct sk_buff *skb)
+{
+	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+
+	return vti_input(skb, IPPROTO_IPIP, ip_hdr(skb)->saddr, 0, false);
+}
+
+static struct xfrm_tunnel vti_ipip_handler __read_mostly = {
 	.handler	=	vti_rcv_tunnel,
+	.cb_handler	=	vti_rcv_cb,
 	.err_handler	=	vti4_err,
 	.priority	=	0,
 };
+#endif
 
 static int __net_init vti_init_net(struct net *net)
 {
@@ -669,10 +654,17 @@ static int __init vti_init(void)
 	if (err < 0)
 		goto xfrm_proto_comp_failed;
 
+#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL)
 	msg = "ipip tunnel";
-	err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
+	err = xfrm4_tunnel_register(&vti_ipip_handler, AF_INET);
 	if (err < 0)
-		goto xfrm_tunnel_failed;
+		goto xfrm_tunnel_ipip_failed;
+#if IS_ENABLED(CONFIG_IPV6)
+	err = xfrm4_tunnel_register(&vti_ipip_handler, AF_INET6);
+	if (err < 0)
+		goto xfrm_tunnel_ipip6_failed;
+#endif
+#endif
 
 	msg = "netlink interface";
 	err = rtnl_link_register(&vti_link_ops);
@@ -682,8 +674,14 @@ static int __init vti_init(void)
 	return err;
 
 rtnl_link_failed:
-	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
-xfrm_tunnel_failed:
+#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL)
+#if IS_ENABLED(CONFIG_IPV6)
+	xfrm4_tunnel_deregister(&vti_ipip_handler, AF_INET6);
+xfrm_tunnel_ipip6_failed:
+#endif
+	xfrm4_tunnel_deregister(&vti_ipip_handler, AF_INET);
+xfrm_tunnel_ipip_failed:
+#endif
 	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
 xfrm_proto_comp_failed:
 	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
@@ -699,7 +697,12 @@ static int __init vti_init(void)
 static void __exit vti_fini(void)
 {
 	rtnl_link_unregister(&vti_link_ops);
-	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
+#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL)
+#if IS_ENABLED(CONFIG_IPV6)
+	xfrm4_tunnel_deregister(&vti_ipip_handler, AF_INET6);
+#endif
+	xfrm4_tunnel_deregister(&vti_ipip_handler, AF_INET);
+#endif
 	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
 	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
 	xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);

net/ipv4/ipcomp.c

@@ -72,6 +72,7 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x)
 	t->props.flags = x->props.flags;
 	t->props.extra_flags = x->props.extra_flags;
 	memcpy(&t->mark, &x->mark, sizeof(t->mark));
+	t->if_id = x->if_id;
 
 	if (xfrm_init_state(t))
 		goto error;

net/ipv4/tunnel4.c

@@ -110,6 +110,33 @@ static int tunnel4_rcv(struct sk_buff *skb)
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL)
+static int tunnel4_rcv_cb(struct sk_buff *skb, u8 proto, int err)
+{
+	struct xfrm_tunnel __rcu *head;
+	struct xfrm_tunnel *handler;
+	int ret;
+
+	head = (proto == IPPROTO_IPIP) ? tunnel4_handlers : tunnel64_handlers;
+
+	for_each_tunnel_rcu(head, handler) {
+		if (handler->cb_handler) {
+			ret = handler->cb_handler(skb, err);
+			if (ret <= 0)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static const struct xfrm_input_afinfo tunnel4_input_afinfo = {
+	.family		=	AF_INET,
+	.is_ipip	=	true,
+	.callback	=	tunnel4_rcv_cb,
+};
+#endif
+
 #if IS_ENABLED(CONFIG_IPV6)
 static int tunnel64_rcv(struct sk_buff *skb)
 {
@@ -230,6 +257,18 @@ static int __init tunnel4_init(void)
 #endif
 		goto err;
 	}
+#endif
+#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL)
+	if (xfrm_input_register_afinfo(&tunnel4_input_afinfo)) {
+		inet_del_protocol(&tunnel4_protocol, IPPROTO_IPIP);
+#if IS_ENABLED(CONFIG_IPV6)
+		inet_del_protocol(&tunnel64_protocol, IPPROTO_IPV6);
+#endif
+#if IS_ENABLED(CONFIG_MPLS)
+		inet_del_protocol(&tunnelmpls4_protocol, IPPROTO_MPLS);
+#endif
+		goto err;
+	}
 #endif
 	return 0;
 
@@ -240,6 +279,10 @@ static int __init tunnel4_init(void)
 
 static void __exit tunnel4_fini(void)
 {
+#if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL)
+	if (xfrm_input_unregister_afinfo(&tunnel4_input_afinfo))
+		pr_err("tunnel4 close: can't remove input afinfo\n");
+#endif
 #if IS_ENABLED(CONFIG_MPLS)
 	if (inet_del_protocol(&tunnelmpls4_protocol, IPPROTO_MPLS))
 		pr_err("tunnelmpls4 close: can't remove protocol\n");

net/ipv6/ip6_vti.c

@@ -1218,6 +1218,26 @@ static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = {
 	.priority	=	100,
 };
 
+#if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL)
+static int vti6_rcv_tunnel(struct sk_buff *skb)
+{
+	const xfrm_address_t *saddr;
+	__be32 spi;
+
+	saddr = (const xfrm_address_t *)&ipv6_hdr(skb)->saddr;
+	spi = xfrm6_tunnel_spi_lookup(dev_net(skb->dev), saddr);
+
+	return vti6_input_proto(skb, IPPROTO_IPV6, spi, 0);
+}
+
+static struct xfrm6_tunnel vti_ipv6_handler __read_mostly = {
+	.handler	=	vti6_rcv_tunnel,
+	.cb_handler	=	vti6_rcv_cb,
+	.err_handler	=	vti6_err,
+	.priority	=	0,
+};
+#endif
+
 /**
  * vti6_tunnel_init - register protocol and reserve needed resources
  *
@@ -1243,6 +1263,15 @@ static int __init vti6_tunnel_init(void)
 	err = xfrm6_protocol_register(&vti_ipcomp6_protocol, IPPROTO_COMP);
 	if (err < 0)
 		goto xfrm_proto_comp_failed;
+#if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL)
+	msg = "ipv6 tunnel";
+	err = xfrm6_tunnel_register(&vti_ipv6_handler, AF_INET6);
+	if (err < 0)
+		goto vti_tunnel_ipv6_failed;
+	err = xfrm6_tunnel_register(&vti_ipv6_handler, AF_INET);
+	if (err < 0)
+		goto vti_tunnel_ip6ip_failed;
+#endif
 
 	msg = "netlink interface";
 	err = rtnl_link_register(&vti6_link_ops);
@@ -1252,6 +1281,12 @@ static int __init vti6_tunnel_init(void)
 	return 0;
 
 rtnl_link_failed:
+#if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL)
+	err = xfrm6_tunnel_deregister(&vti_ipv6_handler, AF_INET);
+vti_tunnel_ip6ip_failed:
+	err = xfrm6_tunnel_deregister(&vti_ipv6_handler, AF_INET6);
+vti_tunnel_ipv6_failed:
+#endif
 	xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP);
 xfrm_proto_comp_failed:
 	xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH);
@@ -1270,6 +1305,10 @@ static int __init vti6_tunnel_init(void)
 static void __exit vti6_tunnel_cleanup(void)
 {
 	rtnl_link_unregister(&vti6_link_ops);
+#if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL)
+	xfrm6_tunnel_deregister(&vti_ipv6_handler, AF_INET);
+	xfrm6_tunnel_deregister(&vti_ipv6_handler, AF_INET6);
+#endif
 	xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP);
 	xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH);
 	xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);

net/ipv6/ipcomp6.c

@@ -91,6 +91,7 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x)
 	t->props.mode = x->props.mode;
 	memcpy(t->props.saddr.a6, x->props.saddr.a6, sizeof(struct in6_addr));
 	memcpy(&t->mark, &x->mark, sizeof(t->mark));
+	t->if_id = x->if_id;
 
 	if (xfrm_init_state(t))
 		goto error;

net/ipv6/tunnel6.c

@@ -155,6 +155,33 @@ static int tunnel6_rcv(struct sk_buff *skb)
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL)
+static int tunnel6_rcv_cb(struct sk_buff *skb, u8 proto, int err)
+{
+	struct xfrm6_tunnel __rcu *head;
+	struct xfrm6_tunnel *handler;
+	int ret;
+
+	head = (proto == IPPROTO_IPV6) ? tunnel6_handlers : tunnel46_handlers;
+
+	for_each_tunnel_rcu(head, handler) {
+		if (handler->cb_handler) {
+			ret = handler->cb_handler(skb, err);
+			if (ret <= 0)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static const struct xfrm_input_afinfo tunnel6_input_afinfo = {
+	.family		=	AF_INET6,
+	.is_ipip	=	true,
+	.callback	=	tunnel6_rcv_cb,
+};
+#endif
+
 static int tunnel46_rcv(struct sk_buff *skb)
 {
 	struct xfrm6_tunnel *handler;
@@ -245,11 +272,25 @@ static int __init tunnel6_init(void)
 		inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP);
 		return -EAGAIN;
 	}
+#if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL)
+	if (xfrm_input_register_afinfo(&tunnel6_input_afinfo)) {
+		pr_err("%s: can't add input afinfo\n", __func__);
+		inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6);
+		inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP);
+		if (xfrm6_tunnel_mpls_supported())
+			inet6_del_protocol(&tunnelmpls6_protocol, IPPROTO_MPLS);
+		return -EAGAIN;
+	}
+#endif
 	return 0;
 }
 
 static void __exit tunnel6_fini(void)
 {
+#if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL)
+	if (xfrm_input_unregister_afinfo(&tunnel6_input_afinfo))
+		pr_err("%s: can't remove input afinfo\n", __func__);
+#endif
 	if (inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP))
 		pr_err("%s: can't remove protocol\n", __func__);
 	if (inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6))