netdev - [RFC PATCH 03/11] udp: do not touch socket refcount in early demux

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Fri, 22 Sep 2017 23:06:27 +0200
From:   Paolo Abeni <pabeni@...hat.com>
To:     netdev@...r.kernel.org
Cc:     "David S. Miller" <davem@...emloft.net>,
        Pablo Neira Ayuso <pablo@...filter.org>,
        Florian Westphal <fw@...len.de>,
        Eric Dumazet <edumazet@...gle.com>,
        Hannes Frederic Sowa <hannes@...essinduktion.org>
Subject: [RFC PATCH 03/11] udp: do not touch socket refcount in early demux

use noref sockets instead. This gives some small performance
improvements and will allow efficient early demux for unconnected
sockets in a later patch.

Signed-off-by: Paolo Abeni <pabeni@...hat.com>
---
 net/ipv4/udp.c | 18 ++++++++++--------
 net/ipv6/udp.c | 10 ++++++----
 2 files changed, 16 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 784ced0b9150..ba49d5aa9f09 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2050,12 +2050,13 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		   int proto)
 {
-	struct sock *sk;
-	struct udphdr *uh;
-	unsigned short ulen;
+	struct net *net = dev_net(skb->dev);
 	struct rtable *rt = skb_rtable(skb);
+	unsigned short ulen;
 	__be32 saddr, daddr;
-	struct net *net = dev_net(skb->dev);
+	struct udphdr *uh;
+	struct sock *sk;
+	bool noref_sk;
 
 	/*
 	 *  Validate the packet.
@@ -2081,6 +2082,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (udp4_csum_init(skb, uh, proto))
 		goto csum_error;
 
+	noref_sk = skb_has_noref_sk(skb);
 	sk = skb_steal_sock(skb);
 	if (sk) {
 		struct dst_entry *dst = skb_dst(skb);
@@ -2090,7 +2092,8 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 			udp_sk_rx_dst_set(sk, dst);
 
 		ret = udp_queue_rcv_skb(sk, skb);
-		sock_put(sk);
+		if (!noref_sk)
+			sock_put(sk);
 		/* a return value > 0 means to resubmit the input, but
 		 * it wants the return to be -protocol, or 0
 		 */
@@ -2261,11 +2264,10 @@ void udp_v4_early_demux(struct sk_buff *skb)
 					     uh->source, iph->saddr, dif, sdif);
 	}
 
-	if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt))
+	if (!sk)
 		return;
 
-	skb->sk = sk;
-	skb->destructor = sock_efree;
+	skb_set_noref_sk(skb, sk);
 	dst = READ_ONCE(sk->sk_rx_dst);
 
 	if (dst)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e2ecfb137297..8f62392c4c35 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -787,6 +787,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	struct net *net = dev_net(skb->dev);
 	struct udphdr *uh;
 	struct sock *sk;
+	bool noref_sk;
 	u32 ulen = 0;
 
 	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
@@ -823,6 +824,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		goto csum_error;
 
 	/* Check if the socket is already available, e.g. due to early demux */
+	noref_sk = skb_has_noref_sk(skb);
 	sk = skb_steal_sock(skb);
 	if (sk) {
 		struct dst_entry *dst = skb_dst(skb);
@@ -832,7 +834,8 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 			udp6_sk_rx_dst_set(sk, dst);
 
 		ret = udpv6_queue_rcv_skb(sk, skb);
-		sock_put(sk);
+		if (!noref_sk)
+			sock_put(sk);
 
 		/* a return value > 0 means to resubmit the input */
 		if (ret > 0)
@@ -948,11 +951,10 @@ static void udp_v6_early_demux(struct sk_buff *skb)
 	else
 		return;
 
-	if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt))
+	if (!sk)
 		return;
 
-	skb->sk = sk;
-	skb->destructor = sock_efree;
+	skb_set_noref_sk(skb, sk);
 	dst = READ_ONCE(sk->sk_rx_dst);
 
 	if (dst)
-- 
2.13.5