net: RCU conversion of dev_getbyhwaddr() and arp_ioctl()

Le dimanche 05 décembre 2010 à 09:19 +0100, Eric Dumazet a écrit :

> Hmm..
>
> If somebody can explain why RTNL is held in arp_ioctl() (and therefore
> in arp_req_delete()), we might first remove RTNL use in arp_ioctl() so
> that your patch can be applied.
>
> Right now it is not good, because RTNL wont be necessarly held when you
> are going to call arp_invalidate() ?

While doing this analysis, I found a refcount bug in llc, I'll send a
patch for net-2.6

Meanwhile, here is the patch for net-next-2.6

Your patch then can be applied after mine.

Thanks

[PATCH] net: RCU conversion of dev_getbyhwaddr() and arp_ioctl()

dev_getbyhwaddr() was called under RTNL.

Rename it to dev_getbyhwaddr_rcu() and change all its caller to now use
RCU locking instead of RTNL.

Change arp_ioctl() to use RCU instead of RTNL locking.

Note: this fix a dev refcount bug in llc
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netdevice.h

@@ -1360,7 +1360,8 @@ static inline struct net_device *first_net_device(struct net *net)
 
 extern int 			netdev_boot_setup_check(struct net_device *dev);
 extern unsigned long		netdev_boot_base(const char *prefix, int unit);
-extern struct net_device    *dev_getbyhwaddr(struct net *net, unsigned short type, char *hwaddr);
+extern struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
+					      const char *hwaddr);
 extern struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type);
 extern struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type);
 extern void		dev_add_pack(struct packet_type *pt);

net/core/dev.c

@@ -743,34 +743,31 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex)
 EXPORT_SYMBOL(dev_get_by_index);
 
 /**
- *	dev_getbyhwaddr - find a device by its hardware address
+ *	dev_getbyhwaddr_rcu - find a device by its hardware address
  *	@net: the applicable net namespace
  *	@type: media type of device
  *	@ha: hardware address
  *
  *	Search for an interface by MAC address. Returns NULL if the device
- *	is not found or a pointer to the device. The caller must hold the
- *	rtnl semaphore. The returned device has not had its ref count increased
+ *	is not found or a pointer to the device. The caller must hold RCU
+ *	The returned device has not had its ref count increased
  *	and the caller must therefore be careful about locking
  *
- *	BUGS:
- *	If the API was consistent this would be __dev_get_by_hwaddr
  */
 
-struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, char *ha)
+struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
+				       const char *ha)
 {
 	struct net_device *dev;
 
-	ASSERT_RTNL();
-
-	for_each_netdev(net, dev)
+	for_each_netdev_rcu(net, dev)
 		if (dev->type == type &&
 		    !memcmp(dev->dev_addr, ha, dev->addr_len))
 			return dev;
 
 	return NULL;
 }
-EXPORT_SYMBOL(dev_getbyhwaddr);
+EXPORT_SYMBOL(dev_getbyhwaddr_rcu);
 
 struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type)
 {

net/ieee802154/af_ieee802154.c

@@ -52,11 +52,11 @@ struct net_device *ieee802154_get_dev(struct net *net,
 
 	switch (addr->addr_type) {
 	case IEEE802154_ADDR_LONG:
-		rtnl_lock();
-		dev = dev_getbyhwaddr(net, ARPHRD_IEEE802154, addr->hwaddr);
+		rcu_read_lock();
+		dev = dev_getbyhwaddr_rcu(net, ARPHRD_IEEE802154, addr->hwaddr);
 		if (dev)
 			dev_hold(dev);
-		rtnl_unlock();
+		rcu_read_unlock();
 		break;
 	case IEEE802154_ADDR_SHORT:
 		if (addr->pan_id == 0xffff ||

net/ipv4/arp.c

@@ -1017,13 +1017,14 @@ static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on)
 		IPV4_DEVCONF_ALL(net, PROXY_ARP) = on;
 		return 0;
 	}
-	if (__in_dev_get_rtnl(dev)) {
-		IN_DEV_CONF_SET(__in_dev_get_rtnl(dev), PROXY_ARP, on);
+	if (__in_dev_get_rcu(dev)) {
+		IN_DEV_CONF_SET(__in_dev_get_rcu(dev), PROXY_ARP, on);
 		return 0;
 	}
 	return -ENXIO;
 }
 
+/* must be called with rcu_read_lock() */
 static int arp_req_set_public(struct net *net, struct arpreq *r,
 		struct net_device *dev)
 {
@@ -1033,7 +1034,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r,
 	if (mask && mask != htonl(0xFFFFFFFF))
 		return -EINVAL;
 	if (!dev && (r->arp_flags & ATF_COM)) {
-		dev = dev_getbyhwaddr(net, r->arp_ha.sa_family,
+		dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family,
 				      r->arp_ha.sa_data);
 		if (!dev)
 			return -ENODEV;
@@ -1225,10 +1226,10 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 	if (!(r.arp_flags & ATF_NETMASK))
 		((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr =
 							   htonl(0xFFFFFFFFUL);
-	rtnl_lock();
+	rcu_read_lock();
 	if (r.arp_dev[0]) {
 		err = -ENODEV;
-		dev = __dev_get_by_name(net, r.arp_dev);
+		dev = dev_get_by_name_rcu(net, r.arp_dev);
 		if (dev == NULL)
 			goto out;
 
@@ -1252,12 +1253,12 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 		break;
 	case SIOCGARP:
 		err = arp_req_get(&r, dev);
-		if (!err && copy_to_user(arg, &r, sizeof(r)))
-			err = -EFAULT;
 		break;
 	}
 out:
-	rtnl_unlock();
+	rcu_read_unlock();
+	if (cmd == SIOCGARP && !err && copy_to_user(arg, &r, sizeof(r)))
+		err = -EFAULT;
 	return err;
 }
 

net/llc/af_llc.c

@@ -316,9 +316,9 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
 	if (unlikely(addr->sllc_family != AF_LLC))
 		goto out;
 	rc = -ENODEV;
-	rtnl_lock();
+	rcu_read_lock();
 	if (sk->sk_bound_dev_if) {
-		llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if);
+		llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if);
 		if (llc->dev) {
 			if (!addr->sllc_arphrd)
 				addr->sllc_arphrd = llc->dev->type;
@@ -329,14 +329,15 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
 			    !llc_mac_match(addr->sllc_mac,
 					   llc->dev->dev_addr)) {
 				rc = -EINVAL;
-				dev_put(llc->dev);
 				llc->dev = NULL;
 			}
 		}
 	} else
-		llc->dev = dev_getbyhwaddr(&init_net, addr->sllc_arphrd,
+		llc->dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd,
 					   addr->sllc_mac);
-	rtnl_unlock();
+	if (llc->dev)
+		dev_hold(llc->dev);
+	rcu_read_unlock();
 	if (!llc->dev)
 		goto out;
 	if (!addr->sllc_sap) {