xfrm: fix "disable_policy" flag use when arriving from different devices

In IPv4 setting the "disable_policy" flag on a device means no policy
should be enforced for traffic originating from the device. This was
implemented by seting the DST_NOPOLICY flag in the dst based on the
originating device.

However, dsts are cached in nexthops regardless of the originating
devices, in which case, the DST_NOPOLICY flag value may be incorrect.

Consider the following setup:

                     +------------------------------+
                     | ROUTER                       |
  +-------------+    | +-----------------+          |
  | ipsec src   |----|-|ipsec0           |          |
  +-------------+    | |disable_policy=0 |   +----+ |
                     | +-----------------+   |eth1|-|-----
  +-------------+    | +-----------------+   +----+ |
  | noipsec src |----|-|eth0             |          |
  +-------------+    | |disable_policy=1 |          |
                     | +-----------------+          |
                     +------------------------------+

Where ROUTER has a default route towards eth1.

dst entries for traffic arriving from eth0 would have DST_NOPOLICY
and would be cached and therefore can be reused by traffic originating
from ipsec0, skipping policy check.

Fix by setting a IPSKB_NOPOLICY flag in IPCB and observing it instead
of the DST in IN/FWD IPv4 policy checks.

Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Reported-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

include/net/ip.h

@@ -56,6 +56,7 @@ struct inet_skb_parm {
 #define IPSKB_DOREDIRECT	BIT(5)
 #define IPSKB_FRAG_PMTU		BIT(6)
 #define IPSKB_L3SLAVE		BIT(7)
+#define IPSKB_NOPOLICY		BIT(8)
 
 	u16			frag_max_size;
 };

include/net/xfrm.h

@@ -1093,6 +1093,18 @@ static inline bool __xfrm_check_nopolicy(struct net *net, struct sk_buff *skb,
 	return false;
 }
 
+static inline bool __xfrm_check_dev_nopolicy(struct sk_buff *skb,
+					     int dir, unsigned short family)
+{
+	if (dir != XFRM_POLICY_OUT && family == AF_INET) {
+		/* same dst may be used for traffic originating from
+		 * devices with different policy settings.
+		 */
+		return IPCB(skb)->flags & IPSKB_NOPOLICY;
+	}
+	return skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY);
+}
+
 static inline int __xfrm_policy_check2(struct sock *sk, int dir,
 				       struct sk_buff *skb,
 				       unsigned int family, int reverse)
@@ -1104,7 +1116,7 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir,
 		return __xfrm_policy_check(sk, ndir, skb, family);
 
 	return __xfrm_check_nopolicy(net, skb, dir) ||
-	       (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) ||
+	       __xfrm_check_dev_nopolicy(skb, dir, family) ||
 	       __xfrm_policy_check(sk, ndir, skb, family);
 }
 

net/ipv4/route.c

@@ -1726,6 +1726,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
 	unsigned int flags = RTCF_MULTICAST;
 	struct rtable *rth;
+	bool no_policy;
 	u32 itag = 0;
 	int err;
 
@@ -1736,8 +1737,12 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (our)
 		flags |= RTCF_LOCAL;
 
+	no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY);
+	if (no_policy)
+		IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
 	rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
-			   IN_DEV_ORCONF(in_dev, NOPOLICY), false);
+			   no_policy, false);
 	if (!rth)
 		return -ENOBUFS;
 
@@ -1795,7 +1800,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	struct rtable *rth;
 	int err;
 	struct in_device *out_dev;
-	bool do_cache;
+	bool do_cache, no_policy;
 	u32 itag = 0;
 
 	/* get a working reference to the output device */
@@ -1840,6 +1845,10 @@ static int __mkroute_input(struct sk_buff *skb,
 		}
 	}
 
+	no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY);
+	if (no_policy)
+		IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
 	fnhe = find_exception(nhc, daddr);
 	if (do_cache) {
 		if (fnhe)
@@ -1852,8 +1861,7 @@ static int __mkroute_input(struct sk_buff *skb,
 		}
 	}
 
-	rth = rt_dst_alloc(out_dev->dev, 0, res->type,
+	rth = rt_dst_alloc(out_dev->dev, 0, res->type, no_policy,
-			   IN_DEV_ORCONF(in_dev, NOPOLICY),
 			   IN_DEV_ORCONF(out_dev, NOXFRM));
 	if (!rth) {
 		err = -ENOBUFS;
@@ -2228,6 +2236,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	struct rtable	*rth;
 	struct flowi4	fl4;
 	bool do_cache = true;
+	bool no_policy;
 
 	/* IP on this device is disabled. */
 
@@ -2346,6 +2355,10 @@ out:	return err;
 	RT_CACHE_STAT_INC(in_brd);
 
 local_input:
+	no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY);
+	if (no_policy)
+		IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
 	do_cache &= res->fi && !itag;
 	if (do_cache) {
 		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
@@ -2360,7 +2373,7 @@ out:	return err;
 
 	rth = rt_dst_alloc(ip_rt_get_dev(net, res),
 			   flags | RTCF_LOCAL, res->type,
-			   IN_DEV_ORCONF(in_dev, NOPOLICY), false);
+			   no_policy, false);
 	if (!rth)
 		goto e_nobufs;