[PATCH v3 ipsec] Fixing support for nested XFRM-I tunnels

[PATCH v3 ipsec] Fixing support for nested XFRM-I tunnels

[Benedict Wong]

v1 -> v2: Rebased; reference to xi removed, updated patch to check if_id
v2 -> v3: Rebased; xfrm_interface.c moved to xfrm_interface_core.c

[PATCH v3 ipsec] Fix XFRM-I support for nested ESP tunnels

[Benedict Wong]

This change adds support for nested IPsec tunnels by ensuring that
XFRM-I verifies existing policies before decapsulating a subsequent
policies. Addtionally, this clears the secpath entries after policies
are verified, ensuring that previous tunnels with no-longer-valid
do not pollute subsequent policy checks.

This is necessary especially for nested tunnels, as the IP addresses,
protocol and ports may all change, thus not matching the previous
policies. In order to ensure that packets match the relevant inbound
templates, the xfrm_policy_check should be done before handing off to
the inner XFRM protocol to decrypt and decapsulate.

Notably, raw ESP/AH packets did not perform policy checks inherently,
whereas all other encapsulated packets (UDP, TCP encapsulated) do policy
checks after calling xfrm_input handling in the respective encapsulation
layer.

Test: Verified with additional Android Kernel Unit tests
Signed-off-by: Benedict Wong <benedictwong@google.com>
---
 net/xfrm/xfrm_interface_core.c | 54 +++++++++++++++++++++++++++++++---
 net/xfrm/xfrm_policy.c         |  3 ++
 2 files changed, 53 insertions(+), 4 deletions(-)

diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index 1f99dc469027..35279c220bd7 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -310,6 +310,52 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet)
 	skb->mark = 0;
 }
 
+static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi,
+		       int encap_type, unsigned short family)
+{
+	struct sec_path *sp;
+
+	sp = skb_sec_path(skb);
+	if (sp && (sp->len || sp->olen) &&
+	    !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+		goto discard;
+
+	XFRM_SPI_SKB_CB(skb)->family = family;
+	if (family == AF_INET) {
+		XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+	} else {
+		XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr);
+		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
+	}
+
+	return xfrm_input(skb, nexthdr, spi, encap_type);
+discard:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int xfrmi4_rcv(struct sk_buff *skb)
+{
+	return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET);
+}
+
+static int xfrmi6_rcv(struct sk_buff *skb)
+{
+	return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff],
+			   0, 0, AF_INET6);
+}
+
+static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
+{
+	return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET);
+}
+
+static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
+{
+	return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6);
+}
+
 static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
 {
 	const struct xfrm_mode *inner_mode;
@@ -945,8 +991,8 @@ static struct pernet_operations xfrmi_net_ops = {
 };
 
 static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = {
-	.handler	=	xfrm6_rcv,
-	.input_handler	=	xfrm_input,
+	.handler	=	xfrmi6_rcv,
+	.input_handler	=	xfrmi6_input,
 	.cb_handler	=	xfrmi_rcv_cb,
 	.err_handler	=	xfrmi6_err,
 	.priority	=	10,
@@ -996,8 +1042,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = {
 #endif
 
 static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = {
-	.handler	=	xfrm4_rcv,
-	.input_handler	=	xfrm_input,
+	.handler	=	xfrmi4_rcv,
+	.input_handler	=	xfrmi4_input,
 	.cb_handler	=	xfrmi_rcv_cb,
 	.err_handler	=	xfrmi4_err,
 	.priority	=	10,
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index e9eb82c5457d..ed0976f8e42b 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3742,6 +3742,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 			goto reject;
 		}
 
+		if (if_id)
+			secpath_reset(skb);
+
 		xfrm_pols_put(pols, npols);
 		return 1;
 	}
-- 
2.39.0.314.g84b9a713c41-goog

Re: [PATCH v3 ipsec] Fix XFRM-I support for nested ESP tunnels

[Steffen Klassert]

On Thu, Jan 05, 2023 at 09:28:12PM +0000, Benedict Wong wrote:
> This change adds support for nested IPsec tunnels by ensuring that
> XFRM-I verifies existing policies before decapsulating a subsequent
> policies. Addtionally, this clears the secpath entries after policies
> are verified, ensuring that previous tunnels with no-longer-valid
> do not pollute subsequent policy checks.
> 
> This is necessary especially for nested tunnels, as the IP addresses,
> protocol and ports may all change, thus not matching the previous
> policies. In order to ensure that packets match the relevant inbound
> templates, the xfrm_policy_check should be done before handing off to
> the inner XFRM protocol to decrypt and decapsulate.
> 
> Notably, raw ESP/AH packets did not perform policy checks inherently,
> whereas all other encapsulated packets (UDP, TCP encapsulated) do policy
> checks after calling xfrm_input handling in the respective encapsulation
> layer.
> 
> Test: Verified with additional Android Kernel Unit tests
> Signed-off-by: Benedict Wong <benedictwong@google.com>

Applied, thanks a lot Ben!