[PATCH net-next 1/2] seg6: skip the route refcount in seg6_lookup_any_nexthop()

ip6_route_input() attaches the input route to the skb without taking a
reference, relying on the RCU read-side section of the receive path.
seg6_lookup_any_nexthop() is called from that same section, either
directly from the seg6local input handler or from a netfilter okfn,
but still takes and drops a route reference for every packet.

Look the route up with RT6_LOOKUP_F_DST_NOREF, as ip6_route_input()
does, for the input and table lookups.

Throughput at 0.5% packet loss of 94-byte End packets (two-segment
SRH, no payload), spread by RSS on an ixgbe 82599ES across two 2.30 GHz
Xeon E5-2650 v3 with 10 cores each, offered by TRex and binary-searched
over 10 runs of 10 s, in Mpps:

  queues  cores                   before   after
  1       1                        0.735   0.770  (+4.8%)
  10      10 on the NIC's socket   6.468   6.976  (+7.9%)
  16      10 + 6 on two sockets    6.931  10.128  (+46.1%)

With the default rules, fib6_rule_lookup() tries the local table
first, and the miss takes and drops a reference on ip6_null_entry,
one route shared by every CPU.  At 16 queues that cache line bounces
between the sockets, and ip6_hold_safe() and dst_release() together
take more than a third of the cycles.

Assisted-by: LLM
Signed-off-by: Yuya Kusakabe <redacted>
---
 net/ipv6/seg6_local.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 0c3d1be7f129..4bde3669d0dd 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c

@@ -342,6 +342,7 @@ seg6_lookup_any_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
 		fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH;
 
 	if (!tbl_id && !oif) {
+		flags |= RT6_LOOKUP_F_DST_NOREF;
 		dst = ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags);
 	} else if (tbl_id) {
 		struct fib6_table *table;

@@ -350,6 +351,7 @@ seg6_lookup_any_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
 		if (!table)
 			goto out;
 
+		flags |= RT6_LOOKUP_F_DST_NOREF;
 		rt = ip6_pol_route(net, table, oif, &fl6, skb, flags);
 		dst = &rt->dst;
 	} else {

@@ -363,7 +365,7 @@ seg6_lookup_any_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
 		dev_flags |= IFF_LOOPBACK;
 
 	if (dst && (dst_dev(dst)->flags & dev_flags) && !dst->error) {
-		dst_release(dst);
+		ip6_rt_put_flags(dst_rt6_info(dst), flags);
 		dst = NULL;
 	}
 

@@ -372,10 +374,14 @@ seg6_lookup_any_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
 		rt = net->ipv6.ip6_blk_hole_entry;
 		dst = &rt->dst;
 		dst_hold(dst);
+		flags &= ~RT6_LOOKUP_F_DST_NOREF;
 	}
 
 	skb_dst_drop(skb);
-	skb_dst_set(skb, dst);
+	if ((flags & RT6_LOOKUP_F_DST_NOREF) && !dst->rt_uncached_list)
+		skb_dst_set_noref(skb, dst);
+	else
+		skb_dst_set(skb, dst);
 	return dst->error;
 }
 

-- 
2.50.1