Received-SPF: pass (google.com: domain of linux-kernel+bounces-15663-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
Message-ID: <504130f6-b56c-4dcc-882c-97942c59f5b7@gmail.com>
Date: Wed, 3 Jan 2024 15:44:21 +0100
Precedence: bulk
MIME-Version: 1.0
Subject: [PATCH net-next v3 2/3] net: gro: parse ipv6 ext headers without
 frag0 invalidation
From: Richard Gobert <richardbgobert@gmail.com>
To: davem@davemloft.net, dsahern@kernel.org, edumazet@google.com,
 kuba@kernel.org, pabeni@redhat.com, shuah@kernel.org,
 netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
 linux-kselftest@vger.kernel.org
References: <ac6fb684-c00e-449c-92c3-99358a927ade@gmail.com>
In-Reply-To: <ac6fb684-c00e-449c-92c3-99358a927ade@gmail.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit

The existing code always pulls the IPv6 header and sets the transport
offset initially. Then optionally again pulls any extension headers in
ipv6_gso_pull_exthdrs and sets the transport offset again on return from
that call. skb->data is set at the start of the first extension header
before calling ipv6_gso_pull_exthdrs, and must disable the frag0
optimization because that function uses pskb_may_pull/pskb_pull instead of
skb_gro_ helpers. It sets the GRO offset to the TCP header with
skb_gro_pull and sets the transport header. Then returns skb->data to its
position before this block.

This commit introduces a new helper function - ipv6_gro_pull_exthdrs -
which is used in ipv6_gro_receive to pull ipv6 ext headers instead of
ipv6_gso_pull_exthdrs. Thus, there is no modification of skb->data, all
operations use skb_gro_* helpers, and the frag0 fast path can be taken for
IPv6 packets with ext headers.

Signed-off-by: Richard Gobert <richardbgobert@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
---
 net/ipv6/ip6_offload.c | 51 +++++++++++++++++++++++++++++++++---------
 1 file changed, 41 insertions(+), 10 deletions(-)

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 0e0b5fed0995..cca64c7809be 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -37,6 +37,40 @@
 		INDIRECT_CALL_L4(cb, f2, f1, head, skb);	\
 })
 
+static int ipv6_gro_pull_exthdrs(struct sk_buff *skb, int off, int proto)
+{
+	const struct net_offload *ops = NULL;
+	struct ipv6_opt_hdr *opth;
+
+	for (;;) {
+		int len;
+
+		ops = rcu_dereference(inet6_offloads[proto]);
+
+		if (unlikely(!ops))
+			break;
+
+		if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
+			break;
+
+		opth = skb_gro_header(skb, off + sizeof(*opth), off);
+		if (unlikely(!opth))
+			break;
+
+		len = ipv6_optlen(opth);
+
+		opth = skb_gro_header(skb, off + len, off);
+		if (unlikely(!opth))
+			break;
+		proto = opth->nexthdr;
+
+		off += len;
+	}
+
+	skb_gro_pull(skb, off - skb_network_offset(skb));
+	return proto;
+}
+
 static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
 {
 	const struct net_offload *ops = NULL;
@@ -203,28 +237,25 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
 		goto out;
 
 	skb_set_network_header(skb, off);
-	skb_gro_pull(skb, sizeof(*iph));
-	skb_set_transport_header(skb, skb_gro_offset(skb));
 
-	flush += ntohs(iph->payload_len) != skb_gro_len(skb);
+	flush += ntohs(iph->payload_len) != skb->len - hlen;
 
 	proto = iph->nexthdr;
 	ops = rcu_dereference(inet6_offloads[proto]);
 	if (!ops || !ops->callbacks.gro_receive) {
-		pskb_pull(skb, skb_gro_offset(skb));
-		skb_gro_frag0_invalidate(skb);
-		proto = ipv6_gso_pull_exthdrs(skb, proto);
-		skb_gro_pull(skb, -skb_transport_offset(skb));
-		skb_reset_transport_header(skb);
-		__skb_push(skb, skb_gro_offset(skb));
+		proto = ipv6_gro_pull_exthdrs(skb, hlen, proto);
 
 		ops = rcu_dereference(inet6_offloads[proto]);
 		if (!ops || !ops->callbacks.gro_receive)
 			goto out;
 
-		iph = ipv6_hdr(skb);
+		iph = skb_gro_network_header(skb);
+	} else {
+		skb_gro_pull(skb, sizeof(*iph));
 	}
 
+	skb_set_transport_header(skb, skb_gro_offset(skb));
+
 	NAPI_GRO_CB(skb)->proto = proto;
 
 	flush--;
-- 
2.36.1