Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:8 as permitted sender) client-ip=2620:137:e000::3:8;
Date:   Mon, 16 Oct 2023 11:23:38 -0700
From:   Yan Zhai <yan@cloudflare.com>
To:     netdev@vger.kernel.org
Cc:     "David S. Miller" <davem@davemloft.net>,
        David Ahern <dsahern@kernel.org>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>, Aya Levin <ayal@nvidia.com>,
        Tariq Toukan <tariqt@nvidia.com>, linux-kernel@vger.kernel.org,
        kernel-team@cloudflare.com, Florian Westphal <fw@strlen.de>,
        Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Subject: [PATCH v2 net-next] ipv6: avoid atomic fragment on GSO packets
Message-ID: <ZS1/qtr0dZJ35VII@debian.debian>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Precedence: bulk

GSO packets can contain a trailing segment that is smaller than
gso_size. When examining the dst MTU for such packet, if its gso_size is
too large, then all segments would be fragmented. However, there is a
good chance the trailing segment has smaller actual size than both
gso_size as well as the MTU, which leads to an "atomic fragment". It is
considered harmful in RFC-8021. An Existing report from APNIC also shows
that atomic fragments are more likely to be dropped even it is
equivalent to a no-op [1].

Refactor __ip6_finish_output code to separate GSO and non-GSO packet
processing. It mirrors __ip_finish_output logic now. Add an extra check
in GSO handling to avoid atomic fragments. Lastly, drop dst_allfrag
check, which is no longer true since commit 9d289715eb5c ("ipv6: stop
sending PTB packets for MTU < 1280").

Link: https://www.potaroo.net/presentations/2022-03-01-ipv6-frag.pdf [1]
Fixes: b210de4f8c97 ("net: ipv6: Validate GSO SKB before finish IPv6 processing")
Suggested-by: Florian Westphal <fw@strlen.de>
Reported-by: David Wragg <dwragg@cloudflare.com>
Signed-off-by: Yan Zhai <yan@cloudflare.com>
---
 net/ipv6/ip6_output.c | 33 +++++++++++++++++++++++----------
 1 file changed, 23 insertions(+), 10 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a471c7e91761..1de6f3c11655 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -162,7 +162,14 @@ ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
 		int err;
 
 		skb_mark_not_on_list(segs);
-		err = ip6_fragment(net, sk, segs, ip6_finish_output2);
+		/* Last gso segment might be smaller than actual MTU. Adding
+		 * a fragment header to it would produce an "atomic fragment",
+		 * which is considered harmful (RFC-8021)
+		 */
+		err = segs->len > mtu ?
+			ip6_fragment(net, sk, segs, ip6_finish_output2) :
+			ip6_finish_output2(net, sk, segs);
+
 		if (err && ret == 0)
 			ret = err;
 	}
@@ -170,10 +177,19 @@ ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
 	return ret;
 }
 
+static int ip6_finish_output_gso(struct net *net, struct sock *sk,
+				 struct sk_buff *skb, unsigned int mtu)
+{
+	if (!(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
+	    !skb_gso_validate_network_len(skb, mtu))
+		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
+
+	return ip6_finish_output2(net, sk, skb);
+}
+
 static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	unsigned int mtu;
-
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
 	if (skb_dst(skb)->xfrm) {
@@ -183,17 +199,14 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
 #endif
 
 	mtu = ip6_skb_dst_mtu(skb);
-	if (skb_is_gso(skb) &&
-	    !(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
-	    !skb_gso_validate_network_len(skb, mtu))
-		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
+	if (skb_is_gso(skb))
+		return ip6_finish_output_gso(net, sk, skb, mtu);
 
-	if ((skb->len > mtu && !skb_is_gso(skb)) ||
-	    dst_allfrag(skb_dst(skb)) ||
+	if (skb->len > mtu ||
 	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
 		return ip6_fragment(net, sk, skb, ip6_finish_output2);
-	else
-		return ip6_finish_output2(net, sk, skb);
+
+	return ip6_finish_output2(net, sk, skb);
 }
 
 static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
-- 
2.30.2