diff mbox series

[net-next,8/9] ipv4: guard IP_MINTTL with a static key

Message ID 20211021162253.333616-11-eric.dumazet@gmail.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series tcp: receive path optimizations | expand

Checks

Context Check Description
netdev/apply fail Patch does not apply to net-next
netdev/tree_selection success Clearly marked for net-next

Commit Message

Eric Dumazet Oct. 21, 2021, 4:22 p.m. UTC 
From: Eric Dumazet <edumazet@google.com>

RFC 5082 IP_MINTTL option is rarely used on hosts.

Add a static key to remove from TCP fast path useless code,
and potential cache line miss to fetch inet_sk(sk)->min_ttl

Note that once ip4_min_ttl static key has been enabled,
it stays enabled until next boot.

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 include/net/ip.h       |  2 ++
 net/ipv4/ip_sockglue.c |  6 ++++++
 net/ipv4/tcp_ipv4.c    | 20 ++++++++++++--------
 3 files changed, 20 insertions(+), 8 deletions(-)
diff mbox series

Patch

diff --git a/include/net/ip.h b/include/net/ip.h
index cf229a53119428307da898af4b0dc23e1cecc053..b71e88507c4a0907011c41e1ed0148eb873b5186 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -24,6 +24,7 @@ 
 #include <linux/skbuff.h>
 #include <linux/jhash.h>
 #include <linux/sockptr.h>
+#include <linux/static_key.h>
 
 #include <net/inet_sock.h>
 #include <net/route.h>
@@ -750,6 +751,7 @@  void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
 			 struct sk_buff *skb, int tlen, int offset);
 int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
 		 struct ipcm_cookie *ipc, bool allow_ipv6);
+DECLARE_STATIC_KEY_FALSE(ip4_min_ttl);
 int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		  unsigned int optlen);
 int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d5487c8580674a01df8c7d8ce88f97c9add846b6..38d29b175ca6646c280e0626e8e935b348f00f08 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -886,6 +886,8 @@  static int compat_ip_mcast_join_leave(struct sock *sk, int optname,
 	return ip_mc_leave_group(sk, &mreq);
 }
 
+DEFINE_STATIC_KEY_FALSE(ip4_min_ttl);
+
 static int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		sockptr_t optval, unsigned int optlen)
 {
@@ -1352,6 +1354,10 @@  static int do_ip_setsockopt(struct sock *sk, int level, int optname,
 			goto e_inval;
 		if (val < 0 || val > 255)
 			goto e_inval;
+
+		if (val)
+			static_branch_enable(&ip4_min_ttl);
+
 		/* tcp_v4_err() and tcp_v4_rcv() might read min_ttl
 		 * while we are changint it.
 		 */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 97b8acf726d0cdcb6b87b6ef45e366591d997a2b..8e9f05d9c54c316e6f6d0603ad786399f9c6345c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -508,10 +508,12 @@  int tcp_v4_err(struct sk_buff *skb, u32 info)
 	if (sk->sk_state == TCP_CLOSE)
 		goto out;
 
-	/* min_ttl can be changed concurrently from do_ip_setsockopt() */
-	if (unlikely(iph->ttl < READ_ONCE(inet_sk(sk)->min_ttl))) {
-		__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
-		goto out;
+	if (static_branch_unlikely(&ip4_min_ttl)) {
+		/* min_ttl can be changed concurrently from do_ip_setsockopt() */
+		if (unlikely(iph->ttl < READ_ONCE(inet_sk(sk)->min_ttl))) {
+			__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
+			goto out;
+		}
 	}
 
 	tp = tcp_sk(sk);
@@ -2051,10 +2053,12 @@  int tcp_v4_rcv(struct sk_buff *skb)
 		}
 	}
 
-	/* min_ttl can be changed concurrently from do_ip_setsockopt() */
-	if (unlikely(iph->ttl < READ_ONCE(inet_sk(sk)->min_ttl))) {
-		__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
-		goto discard_and_relse;
+	if (static_branch_unlikely(&ip4_min_ttl)) {
+		/* min_ttl can be changed concurrently from do_ip_setsockopt() */
+		if (unlikely(iph->ttl < READ_ONCE(inet_sk(sk)->min_ttl))) {
+			__NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP);
+			goto discard_and_relse;
+		}
 	}
 
 	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))