From c92b96553a80c1dbe2ebe128bbe37c8f98f148bf Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Mon, 8 Oct 2012 11:41:19 +0000
Subject: ipv4: Add FLOWI_FLAG_KNOWN_NH

Add flag to request that output route should be
returned with known rt_gateway, in case we want to use
it as nexthop for neighbour resolving.

	The returned route can be cached as follows:

- in NH exception: because the cached routes are not shared
	with other destinations
- in FIB NH: when using gateway because all destinations for
	NH share same gateway

	As last option, to return rt_gateway!=0 we have to
set DST_NOCACHE.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/flow.h b/include/net/flow.h
index e1dd508..628e11b 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -21,6 +21,7 @@ struct flowi_common {
 	__u8	flowic_flags;
 #define FLOWI_FLAG_ANYSRC		0x01
 #define FLOWI_FLAG_CAN_SLEEP		0x02
+#define FLOWI_FLAG_KNOWN_NH		0x04
 	__u32	flowic_secid;
 };
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 3a116cb..1a0da8d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1762,6 +1762,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	struct in_device *in_dev;
 	u16 type = res->type;
 	struct rtable *rth;
+	bool do_cache;
 
 	in_dev = __in_dev_get_rcu(dev_out);
 	if (!in_dev)
@@ -1798,24 +1799,36 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	}
 
 	fnhe = NULL;
+	do_cache = fi != NULL;
 	if (fi) {
 		struct rtable __rcu **prth;
+		struct fib_nh *nh = &FIB_RES_NH(*res);
 
-		fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr);
+		fnhe = find_exception(nh, fl4->daddr);
 		if (fnhe)
 			prth = &fnhe->fnhe_rth;
-		else
-			prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output);
+		else {
+			if (unlikely(fl4->flowi4_flags &
+				     FLOWI_FLAG_KNOWN_NH &&
+				     !(nh->nh_gw &&
+				       nh->nh_scope == RT_SCOPE_LINK))) {
+				do_cache = false;
+				goto add;
+			}
+			prth = __this_cpu_ptr(nh->nh_pcpu_rth_output);
+		}
 		rth = rcu_dereference(*prth);
 		if (rt_cache_valid(rth)) {
 			dst_hold(&rth->dst);
 			return rth;
 		}
 	}
+
+add:
 	rth = rt_dst_alloc(dev_out,
 			   IN_DEV_CONF_GET(in_dev, NOPOLICY),
 			   IN_DEV_CONF_GET(in_dev, NOXFRM),
-			   fi);
+			   do_cache);
 	if (!rth)
 		return ERR_PTR(-ENOBUFS);
 
-- 
cgit v0.10.2