ipv6: Select best matching nexthop object in fib6_table_lookup()

Currently, when using multipath routes without nexthop objects,
fib6_table_lookup() selects the nexthop with the highest score. This
means that when both a source address and an oif are specified, the
nexthop that is chosen is the one that matches in terms of oif:

 # sysctl -wq net.ipv6.conf.all.forwarding=1
 # ip address add 2001:db8:2::1/64 dev lo
 # ip route add 2001:db8:10::/64 nexthop via fe80::1 dev dummy1 nexthop via fe80::2 dev dummy2

 # perf record -e fib6:fib6_table_lookup -- bash -c "for i in {1..100}; do ip route get 2001:db8:10::${i} from 2001:db8:2::1 oif dummy1; done > /dev/null"
 # perf script | grep -o dummy[0-9] | sort | uniq -c
     100 dummy1
 # perf record -e fib6:fib6_table_lookup -- bash -c "for i in {1..100}; do ip route get 2001:db8:10::${i} from 2001:db8:2::1 oif dummy2; done > /dev/null"
 # perf script | grep -o dummy[0-9] | sort | uniq -c
     100 dummy2

When using nexthop objects, fib6_table_lookup() selects the first
matching nexthop and not necessarily the one with the highest score:

 # ip nexthop add id 1 via fe80::1 dev dummy1
 # ip nexthop add id 2 via fe80::2 dev dummy2
 # ip nexthop add id 3 group 1/2
 # ip route add 2001:db8:20::/64 nhid 3

 # perf record -e fib6:fib6_table_lookup -- bash -c "for i in {1..100}; do ip route get 2001:db8:20::${i} from 2001:db8:2::1 oif dummy1; done > /dev/null"
 # perf script | grep -o dummy[0-9] | sort | uniq -c
     100 dummy1
 # perf record -e fib6:fib6_table_lookup -- bash -c "for i in {1..100}; do ip route get 2001:db8:20::${i} from 2001:db8:2::1 oif dummy2; done > /dev/null"
 # perf script | grep -o dummy[0-9] | sort | uniq -c
     100 dummy1

This is not very significant right now because the nexthop is later
overwritten during path selection in fib6_select_path(). However, the
next patch is going to skip path selection when we have an oif match
during output route lookup.

As a preparation for this change, align the nexthop object behavior with
the legacy one and make sure that fib6_table_lookup() always selects the
best matching nexthop. Do that by always returning 0 from
rt6_nh_find_match() in order not to terminate the loop in
nexthop_for_each_fib6_nh() and storing in arg->nh the best matching
nexthop so far.

Behavior after the change:

 # perf record -e fib6:fib6_table_lookup -- bash -c "for i in {1..100}; do ip route get 2001:db8:20::${i} from 2001:db8:2::1 oif dummy1; done > /dev/null"
 # perf script | grep -o dummy[0-9] | sort | uniq -c
     100 dummy1
 # perf record -e fib6:fib6_table_lookup -- bash -c "for i in {1..100}; do ip route get 2001:db8:20::${i} from 2001:db8:2::1 oif dummy2; done > /dev/null"
 # perf script | grep -o dummy[0-9] | sort | uniq -c
     100 dummy2

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20260611154605.992528-2-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 9 insertions, 8 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8259c7527aa4..09dac3aa8778 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -819,9 +819,11 @@ static int rt6_nh_find_match(struct fib6_nh *nh, void *_arg)
 {
 	struct fib6_nh_frl_arg *arg = _arg;
 
-	arg->nh = nh;
-	return find_match(nh, arg->flags, arg->oif, arg->strict,
-			  arg->mpri, arg->do_rr);
+	if (find_match(nh, arg->flags, arg->oif, arg->strict, arg->mpri,
+		       arg->do_rr))
+		arg->nh = nh;
+
+	return 0;
 }
 
 static void __find_rr_leaf(struct fib6_info *f6i_start,
@@ -861,11 +863,10 @@ static void __find_rr_leaf(struct fib6_info *f6i_start,
 				res->nh = nexthop_fib6_nh(f6i->nh);
 				return;
 			}
-			if (nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_find_match,
-						     &arg)) {
-				matched = true;
-				nh = arg.nh;
-			}
+			nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_find_match,
+						 &arg);
+			matched = !!arg.nh;
+			nh = arg.nh;
 		} else {
 			nh = f6i->fib6_nh;
 			if (find_match(nh, f6i->fib6_flags, oif, strict,