Netdev List

* [PATCH net-next 5/5] net: Replace ip_ra_lock with per-net mutex
From: Kirill Tkhai @ 2018-03-15 13:20 UTC (permalink / raw)
  To: davem, yoshfuji, edumazet, yanhaishuang, nikolay, yotamg, soheil,
	ktkhai, avagin, nicolas.dichtel, ebiederm, fw, roman.kapl, netdev,
	xiyou.wangcong, dvyukov, andreyknvl
In-Reply-To: <152111892326.30586.3742839588131331286.stgit@localhost.localdomain>

Since ra_chain is per-net, we may use per-net mutexes
to protect them in ip_ra_control(). This improves
scalability.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
---
 include/net/netns/ipv4.h |    1 +
 net/core/net_namespace.c |    1 +
 net/ipv4/ip_sockglue.c   |   15 ++++++---------
 3 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 23c208fcf1a0..7295429732c6 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -50,6 +50,7 @@ struct netns_ipv4 {
 	struct ipv4_devconf	*devconf_all;
 	struct ipv4_devconf	*devconf_dflt;
 	struct ip_ra_chain	*ra_chain;
+	struct mutex		ra_mutex;
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	struct fib_rules_ops	*rules_ops;
 	bool			fib_has_custom_rules;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index c340d5cfbdec..95ba2c53bd9a 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -301,6 +301,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 	net->user_ns = user_ns;
 	idr_init(&net->netns_ids);
 	spin_lock_init(&net->nsid_lock);
+	mutex_init(&net->ipv4.ra_mutex);
 
 	list_for_each_entry(ops, &pernet_list, list) {
 		error = ops_init(ops, net);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index f36d35fe924b..5ad2d8ed3a3f 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -322,9 +322,6 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
 	return 0;
 }
 
-static DEFINE_SPINLOCK(ip_ra_lock);
-
-
 static void ip_ra_destroy_rcu(struct rcu_head *head)
 {
 	struct ip_ra_chain *ra = container_of(head, struct ip_ra_chain, rcu);
@@ -345,21 +342,21 @@ int ip_ra_control(struct sock *sk, unsigned char on,
 
 	new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;
 
-	spin_lock_bh(&ip_ra_lock);
+	mutex_lock(&net->ipv4.ra_mutex);
 	for (rap = &net->ipv4.ra_chain;
 	     (ra = rcu_dereference_protected(*rap,
-			lockdep_is_held(&ip_ra_lock))) != NULL;
+			lockdep_is_held(&net->ipv4.ra_mutex))) != NULL;
 	     rap = &ra->next) {
 		if (ra->sk == sk) {
 			if (on) {
-				spin_unlock_bh(&ip_ra_lock);
+				mutex_unlock(&net->ipv4.ra_mutex);
 				kfree(new_ra);
 				return -EADDRINUSE;
 			}
 			/* dont let ip_call_ra_chain() use sk again */
 			ra->sk = NULL;
 			RCU_INIT_POINTER(*rap, ra->next);
-			spin_unlock_bh(&ip_ra_lock);
+			mutex_unlock(&net->ipv4.ra_mutex);
 
 			if (ra->destructor)
 				ra->destructor(sk);
@@ -374,7 +371,7 @@ int ip_ra_control(struct sock *sk, unsigned char on,
 		}
 	}
 	if (!new_ra) {
-		spin_unlock_bh(&ip_ra_lock);
+		mutex_unlock(&net->ipv4.ra_mutex);
 		return -ENOBUFS;
 	}
 	new_ra->sk = sk;
@@ -383,7 +380,7 @@ int ip_ra_control(struct sock *sk, unsigned char on,
 	RCU_INIT_POINTER(new_ra->next, ra);
 	rcu_assign_pointer(*rap, new_ra);
 	sock_hold(sk);
-	spin_unlock_bh(&ip_ra_lock);
+	mutex_unlock(&net->ipv4.ra_mutex);
 
 	return 0;
 }

^ permalink raw reply related