netdev - [PATCH net-next 1/5] net: Revert "ipv4: get rid of ip_ra

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]

Message-ID: <152112000563.30586.17131455905597040175.stgit@localhost.localdomain>
Date:   Thu, 15 Mar 2018 16:20:05 +0300
From:   Kirill Tkhai <ktkhai@...tuozzo.com>
To:     davem@...emloft.net, yoshfuji@...ux-ipv6.org, edumazet@...gle.com,
        yanhaishuang@...s.chinamobile.com, nikolay@...ulusnetworks.com,
        yotamg@...lanox.com, soheil@...gle.com, ktkhai@...tuozzo.com,
        avagin@...tuozzo.com, nicolas.dichtel@...nd.com,
        ebiederm@...ssion.com, fw@...len.de, roman.kapl@...go.com,
        netdev@...r.kernel.org, xiyou.wangcong@...il.com,
        dvyukov@...gle.com, andreyknvl@...gle.com
Subject: [PATCH net-next 1/5] net: Revert "ipv4: get rid of ip_ra_lock"

This reverts commit ba3f571d5dde. The commit was made
after 1215e51edad1 "ipv4: fix a deadlock in ip_ra_control",
and killed ip_ra_lock, which became useless after rtnl_lock()
made used to destroy every raw ipv4 socket. This scales
very bad, and next patch in series reverts 1215e51edad1.
ip_ra_lock will be used again.

Signed-off-by: Kirill Tkhai <ktkhai@...tuozzo.com>
---
 net/ipv4/ip_sockglue.c |   12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 74c962b9b09c..be7c3b71914d 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -334,6 +334,7 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
    sent to multicast group to reach destination designated router.
  */
 struct ip_ra_chain __rcu *ip_ra_chain;
+static DEFINE_SPINLOCK(ip_ra_lock);
 
 
 static void ip_ra_destroy_rcu(struct rcu_head *head)
@@ -355,17 +356,21 @@ 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);
 	for (rap = &ip_ra_chain;
-	     (ra = rtnl_dereference(*rap)) != NULL;
+	     (ra = rcu_dereference_protected(*rap,
+			lockdep_is_held(&ip_ra_lock))) != NULL;
 	     rap = &ra->next) {
 		if (ra->sk == sk) {
 			if (on) {
+				spin_unlock_bh(&ip_ra_lock);
 				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);
 
 			if (ra->destructor)
 				ra->destructor(sk);
@@ -379,14 +384,17 @@ int ip_ra_control(struct sock *sk, unsigned char on,
 			return 0;
 		}
 	}
-	if (!new_ra)
+	if (!new_ra) {
+		spin_unlock_bh(&ip_ra_lock);
 		return -ENOBUFS;
+	}
 	new_ra->sk = sk;
 	new_ra->destructor = destructor;
 
 	RCU_INIT_POINTER(new_ra->next, ra);
 	rcu_assign_pointer(*rap, new_ra);
 	sock_hold(sk);
+	spin_unlock_bh(&ip_ra_lock);
 
 	return 0;
 }