packet: Protect packet sk list with mutex (v2)

xemul · davem330 · commit 0fa7fa98dbcc · 2012-08-22T22:58:27.000-07:00
Change since v1: * Fixed inuse counters access spotted by Eric In patch eea68e2 (packet: Report socket mclist info via diag module) I've introduced a "scheduling in atomic" problem in packet diag module -- the socket list is traversed under rcu_read_lock() while performed under it sk mclist access requires rtnl lock (i.e. -- mutex) to be taken. [152363.820563] BUG: scheduling while atomic: crtools/12517/0x10000002 [152363.820573] 4 locks held by crtools/12517: [152363.820581] #0: (sock_diag_mutex){+.+.+.}, at: [<ffffffff81a2dcb5>] sock_diag_rcv+0x1f/0x3e [152363.820613] #1: (sock_diag_table_mutex){+.+.+.}, at: [<ffffffff81a2de70>] sock_diag_rcv_msg+0xdb/0x11a [152363.820644] #2: (nlk->cb_mutex){+.+.+.}, at: [<ffffffff81a67d01>] netlink_dump+0x23/0x1ab [152363.820693] #3: (rcu_read_lock){.+.+..}, at: [<ffffffff81b6a049>] packet_diag_dump+0x0/0x1af Similar thing was then re-introduced by further packet diag patches (fanount mutex and pgvec mutex for rings) :( Apart from being terribly sorry for the above, I propose to change the packet sk list protection from spinlock to mutex. This lock currently protects two modifications: * sklist * prot inuse counters The sklist modifications can be just reprotected with mutex since they already occur in a sleeping context. The inuse counters modifications are trickier -- the __this_cpu_-s are used inside, thus requiring the caller to handle the potential issues with contexts himself. Since packet sockets' counters are modified in two places only (packet_create and packet_release) we only need to protect the context from being preempted. BH disabling is not required in this case. Signed-off-by: Pavel Emelyanov <xemul@parallels.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/net/netns/packet.h b/include/net/netns/packet.h
@@ -8,7 +8,7 @@
 #include <linux/spinlock.h>
 
 struct netns_packet {
-	spinlock_t		sklist_lock;
+	struct mutex		sklist_lock;
 	struct hlist_head	sklist;
 };
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
@@ -2317,10 +2317,13 @@ static int packet_release(struct socket *sock)
 	net = sock_net(sk);
 	po = pkt_sk(sk);
 
-	spin_lock_bh(&net->packet.sklist_lock);
+	mutex_lock(&net->packet.sklist_lock);
 	sk_del_node_init_rcu(sk);
+	mutex_unlock(&net->packet.sklist_lock);
+
+	preempt_disable();
 	sock_prot_inuse_add(net, sk->sk_prot, -1);
-	spin_unlock_bh(&net->packet.sklist_lock);
+	preempt_enable();
 
 	spin_lock(&po->bind_lock);
 	unregister_prot_hook(sk, false);
@@ -2519,10 +2522,13 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 		register_prot_hook(sk);
 	}
 
-	spin_lock_bh(&net->packet.sklist_lock);
+	mutex_lock(&net->packet.sklist_lock);
 	sk_add_node_rcu(sk, &net->packet.sklist);
+	mutex_unlock(&net->packet.sklist_lock);
+
+	preempt_disable();
 	sock_prot_inuse_add(net, &packet_proto, 1);
-	spin_unlock_bh(&net->packet.sklist_lock);
+	preempt_enable();
 
 	return 0;
 out:
@@ -3775,7 +3781,7 @@ static const struct file_operations packet_seq_fops = {
 
 static int __net_init packet_net_init(struct net *net)
 {
-	spin_lock_init(&net->packet.sklist_lock);
+	mutex_init(&net->packet.sklist_lock);
 	INIT_HLIST_HEAD(&net->packet.sklist);
 
 	if (!proc_net_fops_create(net, "packet", 0, &packet_seq_fops))
diff --git a/net/packet/diag.c b/net/packet/diag.c
@@ -177,8 +177,8 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	net = sock_net(skb->sk);
 	req = nlmsg_data(cb->nlh);
 
-	rcu_read_lock();
-	sk_for_each_rcu(sk, node, &net->packet.sklist) {
+	mutex_lock(&net->packet.sklist_lock);
+	sk_for_each(sk, node, &net->packet.sklist) {
 		if (!net_eq(sock_net(sk), net))
 			continue;
 		if (num < s_num)
@@ -192,7 +192,7 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		num++;
 	}
 done:
-	rcu_read_unlock();
+	mutex_unlock(&net->packet.sklist_lock);
 	cb->args[0] = num;
 
 	return skb->len;
