[PATCH net v2 1/2] net: fib: restore ECMP balance from loopback

[Vadim Fedorenko <vadim.fedorenko@linux.dev>]

Preference of nexthop with source address broke ECMP for packets with
source addresses which are not in the broadcast domain, but rather added
to loopback/dummy interfaces. Original behaviour was to balance over
nexthops while now it uses the latest nexthop from the group.

For the case with 198.51.100.1/32 assigned to dummy0 and routed using
192.0.2.0/24 and 203.0.113.0/24 networks:

2: dummy0: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
    link/ether d6:54:8a:ff:78:f5 brd ff:ff:ff:ff:ff:ff
    inet 198.51.100.1/32 scope global dummy0
       valid_lft forever preferred_lft forever
7: veth1@if6: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
    link/ether 06:ed:98:87:6d:8a brd ff:ff:ff:ff:ff:ff link-netnsid 0
    inet 192.0.2.2/24 scope global veth1
       valid_lft forever preferred_lft forever
    inet6 fe80::4ed:98ff:fe87:6d8a/64 scope link proto kernel_ll
       valid_lft forever preferred_lft forever
9: veth3@if8: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
    link/ether ae:75:23:38:a0:d2 brd ff:ff:ff:ff:ff:ff link-netnsid 0
    inet 203.0.113.2/24 scope global veth3
       valid_lft forever preferred_lft forever
    inet6 fe80::ac75:23ff:fe38:a0d2/64 scope link proto kernel_ll
       valid_lft forever preferred_lft forever

~ ip ro list:
default
	nexthop via 192.0.2.1 dev veth1 weight 1
	nexthop via 203.0.113.1 dev veth3 weight 1
192.0.2.0/24 dev veth1 proto kernel scope link src 192.0.2.2
203.0.113.0/24 dev veth3 proto kernel scope link src 203.0.113.2

before:
   for i in {1..255} ; do ip ro get 10.0.0.$i; done | grep veth | awk ' {print $(NF-2)}' | sort | uniq -c:
    255 veth3

after:
   for i in {1..255} ; do ip ro get 10.0.0.$i; done | grep veth | awk ' {print $(NF-2)}' | sort | uniq -c:
    122 veth1
    133 veth3

Fixes: 32607a332cfe ("ipv4: prefer multipath nexthop that matches source address")
Signed-off-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
---
v1 -> v2:

- add score calculation for nexthop to keep original logic
- adjust commit message to explain the config
- use dummy device instead of loopback
---

 net/ipv4/fib_semantics.c | 24 ++++++++----------------
 1 file changed, 8 insertions(+), 16 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index a5f3c8459758..4d3650d20ff2 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -2167,8 +2167,8 @@ void fib_select_multipath(struct fib_result *res, int hash,
 {
 	struct fib_info *fi = res->fi;
 	struct net *net = fi->fib_net;
-	bool found = false;
 	bool use_neigh;
+	int score = -1;
 	__be32 saddr;
 
 	if (unlikely(res->fi->nh)) {
@@ -2180,7 +2180,7 @@ void fib_select_multipath(struct fib_result *res, int hash,
 	saddr = fl4 ? fl4->saddr : 0;
 
 	change_nexthops(fi) {
-		int nh_upper_bound;
+		int nh_upper_bound, nh_score = 0;
 
 		/* Nexthops without a carrier are assigned an upper bound of
 		 * minus one when "ignore_routes_with_linkdown" is set.
@@ -2190,24 +2190,16 @@ void fib_select_multipath(struct fib_result *res, int hash,
 		    (use_neigh && !fib_good_nh(nexthop_nh)))
 			continue;
 
-		if (!found) {
+		if (saddr && nexthop_nh->nh_saddr == saddr)
+			nh_score += 2;
+		if (hash <= nh_upper_bound)
+			nh_score++;
+		if (score < nh_score) {
 			res->nh_sel = nhsel;
 			res->nhc = &nexthop_nh->nh_common;
-			found = !saddr || nexthop_nh->nh_saddr == saddr;
+			score = nh_score;
 		}
 
-		if (hash > nh_upper_bound)
-			continue;
-
-		if (!saddr || nexthop_nh->nh_saddr == saddr) {
-			res->nh_sel = nhsel;
-			res->nhc = &nexthop_nh->nh_common;
-			return;
-		}
-
-		if (found)
-			return;
-
 	} endfor_nexthops(fi);
 }
 #endif
-- 
2.47.3