Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Thu, 18 Mar 2021 18:42:34 +0000
To:     "David S. Miller" <davem@davemloft.net>,
        Jakub Kicinski <kuba@kernel.org>
From:   Alexander Lobakin <alobakin@pm.me>
Cc:     Alexander Lobakin <alobakin@pm.me>,
        Mauro Carvalho Chehab <mchehab+huawei@kernel.org>,
        Kirill Tkhai <ktkhai@virtuozzo.com>,
        Bartosz Golaszewski <bgolaszewski@baylibre.com>,
        Leon Romanovsky <leon@kernel.org>,
        Eric Dumazet <edumazet@google.com>, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org
Reply-To: Alexander Lobakin <alobakin@pm.me>
Subject: [PATCH net-next 3/4] vlan/8021q: avoid retpoline overhead on GRO
Message-ID: <20210318184157.700604-4-alobakin@pm.me>
In-Reply-To: <20210318184157.700604-1-alobakin@pm.me>
References: <20210318184157.700604-1-alobakin@pm.me>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

The two most popular headers going after VLAN are IPv4 and IPv6.
Retpoline overhead for them is addressed only in dev_gro_receive(),
when they lie right after the outermost Ethernet header.
Use the indirect call wrappers in VLAN GRO receive code to reduce
the penalty on receiving tagged frames (when hardware stripping is
off or not available).

Signed-off-by: Alexander Lobakin <alobakin@pm.me>
---
 net/8021q/vlan_core.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 78ec2e1b14d1..59bc13b5f14f 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -4,6 +4,7 @@
 #include <linux/if_vlan.h>
 #include <linux/netpoll.h>
 #include <linux/export.h>
+#include <net/gro.h>
 #include "vlan.h"

 bool vlan_do_receive(struct sk_buff **skbp)
@@ -495,7 +496,10 @@ static struct sk_buff *vlan_gro_receive(struct list_he=
ad *head,

 =09skb_gro_pull(skb, sizeof(*vhdr));
 =09skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr));
-=09pp =3D call_gro_receive(ptype->callbacks.gro_receive, head, skb);
+
+=09pp =3D indirect_call_gro_receive_inet(ptype->callbacks.gro_receive,
+=09=09=09=09=09    ipv6_gro_receive, inet_gro_receive,
+=09=09=09=09=09    head, skb);

 out_unlock:
 =09rcu_read_unlock();
@@ -515,7 +519,9 @@ static int vlan_gro_complete(struct sk_buff *skb, int n=
hoff)
 =09rcu_read_lock();
 =09ptype =3D gro_find_complete_by_type(type);
 =09if (ptype)
-=09=09err =3D ptype->callbacks.gro_complete(skb, nhoff + sizeof(*vhdr));
+=09=09err =3D INDIRECT_CALL_INET(ptype->callbacks.gro_complete,
+=09=09=09=09=09 ipv6_gro_complete, inet_gro_complete,
+=09=09=09=09=09 skb, nhoff + sizeof(*vhdr));

 =09rcu_read_unlock();
 =09return err;
--
2.31.0