[NET]: Make the device list and device lookups per namespace.

This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <[email protected]> Signed-off-by: David S. Miller <[email protected]>
syzer · Oct 10, 2007 · 881d966 · 881d966
1 parent b4b5102
commit 881d966
Show file tree

Hide file tree

Showing 99 changed files with 555 additions and 362 deletions.
diff --git a/arch/s390/appldata/appldata_net_sum.c b/arch/s390/appldata/appldata_net_sum.c
@@ -16,6 +16,7 @@
 #include <linux/errno.h>
 #include <linux/kernel_stat.h>
 #include <linux/netdevice.h>
+#include <net/net_namespace.h>
 
 #include "appldata.h"
 
@@ -107,7 +108,7 @@ static void appldata_get_net_sum_data(void *data)
 	tx_dropped = 0;
 	collisions = 0;
 	read_lock(&dev_base_lock);
-	for_each_netdev(dev) {
+	for_each_netdev(&init_net, dev) {
 		stats = dev->get_stats(dev);
 		rx_packets += stats->rx_packets;
 		tx_packets += stats->tx_packets;

diff --git a/arch/sparc64/solaris/ioctl.c b/arch/sparc64/solaris/ioctl.c
@@ -28,6 +28,7 @@
 #include <linux/compat.h>
 
 #include <net/sock.h>
+#include <net/net_namespace.h>
 
 #include <asm/uaccess.h>
 #include <asm/termios.h>
@@ -686,7 +687,7 @@ static inline int solaris_i(unsigned int fd, unsigned int cmd, u32 arg)
 			int i = 0;
 
 			read_lock_bh(&dev_base_lock);
-			for_each_netdev(d)
+			for_each_netdev(&init_net, d)
 				i++;
 			read_unlock_bh(&dev_base_lock);
 

diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
@@ -3576,7 +3576,7 @@ init_card(struct atm_dev *dev)
 	 * XXX: <hack>
 	 */
 	sprintf(tname, "eth%d", card->index);
-	tmp = dev_get_by_name(tname);	/* jhs: was "tmp = dev_get(tname);" */
+	tmp = dev_get_by_name(&init_net, tname);	/* jhs: was "tmp = dev_get(tname);" */
 	if (tmp) {
 		memcpy(card->atmdev->esi, tmp->dev_addr, 6);
 

diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
@@ -9,6 +9,7 @@
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/genhd.h>
+#include <net/net_namespace.h>
 #include <asm/unaligned.h>
 #include "aoe.h"
 
@@ -194,7 +195,7 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff **tail)
 	sl = sl_tail = NULL;
 
 	read_lock(&dev_base_lock);
-	for_each_netdev(ifp) {
+	for_each_netdev(&init_net, ifp) {
 		dev_hold(ifp);
 		if (!is_aoe_netif(ifp))
 			goto cont;

diff --git a/drivers/infiniband/hw/cxgb3/cxio_hal.c b/drivers/infiniband/hw/cxgb3/cxio_hal.c
@@ -37,6 +37,7 @@
 #include <linux/spinlock.h>
 #include <linux/pci.h>
 #include <linux/dma-mapping.h>
+#include <net/net_namespace.h>
 
 #include "cxio_resource.h"
 #include "cxio_hal.h"
@@ -894,7 +895,7 @@ int cxio_rdev_open(struct cxio_rdev *rdev_p)
 		if (cxio_hal_find_rdev_by_name(rdev_p->dev_name)) {
 			return -EBUSY;
 		}
-		netdev_p = dev_get_by_name(rdev_p->dev_name);
+		netdev_p = dev_get_by_name(&init_net, rdev_p->dev_name);
 		if (!netdev_p) {
 			return -EINVAL;
 		}

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
@@ -3719,7 +3719,7 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd
 	}
 
 	down_write(&(bonding_rwsem));
-	slave_dev = dev_get_by_name(ifr->ifr_slave);
+	slave_dev = dev_get_by_name(&init_net, ifr->ifr_slave);
 
 	dprintk("slave_dev=%p: \n", slave_dev);
 

diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
@@ -35,6 +35,7 @@
 #include <linux/ctype.h>
 #include <linux/inet.h>
 #include <linux/rtnetlink.h>
+#include <net/net_namespace.h>
 
 /* #define BONDING_DEBUG 1 */
 #include "bonding.h"
@@ -299,7 +300,7 @@ static ssize_t bonding_store_slaves(struct device *d,
 		read_unlock_bh(&bond->lock);
 		printk(KERN_INFO DRV_NAME ": %s: Adding slave %s.\n",
 		       bond->dev->name, ifname);
-		dev = dev_get_by_name(ifname);
+		dev = dev_get_by_name(&init_net, ifname);
 		if (!dev) {
 			printk(KERN_INFO DRV_NAME
 			       ": %s: Interface %s does not exist!\n",

diff --git a/drivers/net/eql.c b/drivers/net/eql.c
@@ -116,6 +116,7 @@
 #include <linux/init.h>
 #include <linux/timer.h>
 #include <linux/netdevice.h>
+#include <net/net_namespace.h>
 
 #include <linux/if.h>
 #include <linux/if_arp.h>
@@ -412,7 +413,7 @@ static int eql_enslave(struct net_device *master_dev, slaving_request_t __user *
 	if (copy_from_user(&srq, srqp, sizeof (slaving_request_t)))
 		return -EFAULT;
 
-	slave_dev  = dev_get_by_name(srq.slave_name);
+	slave_dev  = dev_get_by_name(&init_net, srq.slave_name);
 	if (slave_dev) {
 		if ((master_dev->flags & IFF_UP) == IFF_UP) {
 			/* slave is not a master & not already a slave: */
@@ -460,7 +461,7 @@ static int eql_emancipate(struct net_device *master_dev, slaving_request_t __use
 	if (copy_from_user(&srq, srqp, sizeof (slaving_request_t)))
 		return -EFAULT;
 
-	slave_dev = dev_get_by_name(srq.slave_name);
+	slave_dev = dev_get_by_name(&init_net, srq.slave_name);
 	ret = -EINVAL;
 	if (slave_dev) {
 		spin_lock_bh(&eql->queue.lock);
@@ -493,7 +494,7 @@ static int eql_g_slave_cfg(struct net_device *dev, slave_config_t __user *scp)
 	if (copy_from_user(&sc, scp, sizeof (slave_config_t)))
 		return -EFAULT;
 
-	slave_dev = dev_get_by_name(sc.slave_name);
+	slave_dev = dev_get_by_name(&init_net, sc.slave_name);
 	if (!slave_dev)
 		return -ENODEV;
 
@@ -528,7 +529,7 @@ static int eql_s_slave_cfg(struct net_device *dev, slave_config_t __user *scp)
 	if (copy_from_user(&sc, scp, sizeof (slave_config_t)))
 		return -EFAULT;
 
-	slave_dev = dev_get_by_name(sc.slave_name);
+	slave_dev = dev_get_by_name(&init_net, sc.slave_name);
 	if (!slave_dev)
 		return -ENODEV;
 

diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
@@ -34,6 +34,7 @@
 #include <linux/init.h>
 #include <linux/moduleparam.h>
 #include <net/pkt_sched.h>
+#include <net/net_namespace.h>
 
 #define TX_TIMEOUT  (2*HZ)
 
@@ -97,7 +98,7 @@ static void ri_tasklet(unsigned long dev)
 		stats->tx_packets++;
 		stats->tx_bytes +=skb->len;
 
-		skb->dev = __dev_get_by_index(skb->iif);
+		skb->dev = __dev_get_by_index(&init_net, skb->iif);
 		if (!skb->dev) {
 			dev_kfree_skb(skb);
 			stats->tx_dropped++;

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
@@ -376,7 +376,7 @@ static int macvlan_newlink(struct net_device *dev,
 	if (!tb[IFLA_LINK])
 		return -EINVAL;
 
-	lowerdev = __dev_get_by_index(nla_get_u32(tb[IFLA_LINK]));
+	lowerdev = __dev_get_by_index(dev->nd_net, nla_get_u32(tb[IFLA_LINK]));
 	if (lowerdev == NULL)
 		return -ENODEV;
 

diff --git a/drivers/net/pppoe.c b/drivers/net/pppoe.c
@@ -216,7 +216,7 @@ static inline struct pppox_sock *get_item_by_addr(struct sockaddr_pppox *sp)
 	struct net_device *dev;
 	int ifindex;
 
-	dev = dev_get_by_name(sp->sa_addr.pppoe.dev);
+	dev = dev_get_by_name(&init_net, sp->sa_addr.pppoe.dev);
 	if(!dev)
 		return NULL;
 	ifindex = dev->ifindex;
@@ -603,7 +603,7 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
 
 	/* Don't re-bind if sid==0 */
 	if (sp->sa_addr.pppoe.sid != 0) {
-		dev = dev_get_by_name(sp->sa_addr.pppoe.dev);
+		dev = dev_get_by_name(&init_net, sp->sa_addr.pppoe.dev);
 
 		error = -ENODEV;
 		if (!dev)

diff --git a/drivers/net/shaper.c b/drivers/net/shaper.c
@@ -86,6 +86,7 @@
 
 #include <net/dst.h>
 #include <net/arp.h>
+#include <net/net_namespace.h>
 
 struct shaper_cb {
 	unsigned long	shapeclock;		/* Time it should go out */
@@ -488,7 +489,7 @@ static int shaper_ioctl(struct net_device *dev,  struct ifreq *ifr, int cmd)
 	{
 		case SHAPER_SET_DEV:
 		{
-			struct net_device *them=__dev_get_by_name(ss->ss_name);
+			struct net_device *them=__dev_get_by_name(&init_net, ss->ss_name);
 			if(them==NULL)
 				return -ENODEV;
 			if(sh->dev)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
@@ -62,6 +62,7 @@
 #include <linux/if_ether.h>
 #include <linux/if_tun.h>
 #include <linux/crc32.h>
+#include <net/net_namespace.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -475,7 +476,7 @@ static int tun_set_iff(struct file *file, struct ifreq *ifr)
 		     !capable(CAP_NET_ADMIN))
 			return -EPERM;
 	}
-	else if (__dev_get_by_name(ifr->ifr_name))
+	else if (__dev_get_by_name(&init_net, ifr->ifr_name))
 		return -EINVAL;
 	else {
 		char *name;

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
@@ -345,7 +345,7 @@ static int veth_newlink(struct net_device *dev,
 	else
 		snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d");
 
-	peer = rtnl_create_link(ifname, &veth_link_ops, tbp);
+	peer = rtnl_create_link(dev->nd_net, ifname, &veth_link_ops, tbp);
 	if (IS_ERR(peer))
 		return PTR_ERR(peer);
 

diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c
@@ -361,7 +361,7 @@ static int dlci_add(struct dlci_add *dlci)
 
 
 	/* validate slave device */
-	slave = dev_get_by_name(dlci->devname);
+	slave = dev_get_by_name(&init_net, dlci->devname);
 	if (!slave)
 		return -ENODEV;
 
@@ -427,7 +427,7 @@ static int dlci_del(struct dlci_add *dlci)
 	int			err;
 
 	/* validate slave device */
-	master = __dev_get_by_name(dlci->devname);
+	master = __dev_get_by_name(&init_net, dlci->devname);
 	if (!master)
 		return(-ENODEV);
 

diff --git a/drivers/net/wan/sbni.c b/drivers/net/wan/sbni.c
@@ -54,6 +54,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 
+#include <net/net_namespace.h>
 #include <net/arp.h>
 
 #include <asm/io.h>
@@ -1361,7 +1362,7 @@ sbni_ioctl( struct net_device  *dev,  struct ifreq  *ifr,  int  cmd )
 
 		if (copy_from_user( slave_name, ifr->ifr_data, sizeof slave_name ))
 			return -EFAULT;
-		slave_dev = dev_get_by_name( slave_name );
+		slave_dev = dev_get_by_name(&init_net, slave_name );
 		if( !slave_dev  ||  !(slave_dev->flags & IFF_UP) ) {
 			printk( KERN_ERR "%s: trying to enslave non-active "
 				"device %s\n", dev->name, slave_name );

diff --git a/drivers/net/wireless/strip.c b/drivers/net/wireless/strip.c
@@ -1972,7 +1972,7 @@ static struct net_device *get_strip_dev(struct strip *strip_info)
 		      sizeof(zero_address))) {
 		struct net_device *dev;
 		read_lock_bh(&dev_base_lock);
-		for_each_netdev(dev) {
+		for_each_netdev(&init_net, dev) {
 			if (dev->type == strip_info->dev->type &&
 			    !memcmp(dev->dev_addr,
 				    &strip_info->true_dev_addr,

diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c
@@ -359,7 +359,7 @@ static __inline__ int led_get_net_activity(void)
 	 * for reading should be OK */
 	read_lock(&dev_base_lock);
 	rcu_read_lock();
-	for_each_netdev(dev) {
+	for_each_netdev(&init_net, dev) {
 	    struct net_device_stats *stats;
 	    struct in_device *in_dev = __in_dev_get_rcu(dev);
 	    if (!in_dev || !in_dev->ifa_list)

diff --git a/fs/afs/netdevices.c b/fs/afs/netdevices.c
@@ -8,6 +8,7 @@
 #include <linux/inetdevice.h>
 #include <linux/netdevice.h>
 #include <linux/if_arp.h>
+#include <net/net_namespace.h>
 #include "internal.h"
 
 /*
@@ -23,7 +24,7 @@ int afs_get_MAC_address(u8 *mac, size_t maclen)
 		BUG();
 
 	rtnl_lock();
-	dev = __dev_getfirstbyhwtype(ARPHRD_ETHER);
+	dev = __dev_getfirstbyhwtype(&init_net, ARPHRD_ETHER);
 	if (dev) {
 		memcpy(mac, dev->dev_addr, maclen);
 		ret = 0;
@@ -47,7 +48,7 @@ int afs_get_ipv4_interfaces(struct afs_interface *bufs, size_t maxbufs,
 	ASSERT(maxbufs > 0);
 
 	rtnl_lock();
-	for_each_netdev(dev) {
+	for_each_netdev(&init_net, dev) {
 		if (dev->type == ARPHRD_LOOPBACK && !wantloopback)
 			continue;
 		idev = __in_dev_get_rtnl(dev);

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
@@ -104,7 +104,7 @@ struct __fdb_entry
 
 #include <linux/netdevice.h>
 
-extern void brioctl_set(int (*ioctl_hook)(unsigned int, void __user *));
+extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *));
 extern struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p,
 					       struct sk_buff *skb);
 extern int (*br_should_route_hook)(struct sk_buff **pskb);

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
@@ -62,7 +62,7 @@ struct vlan_hdr {
 #define VLAN_VID_MASK	0xfff
 
 /* found in socket.c */
-extern void vlan_ioctl_set(int (*hook)(void __user *));
+extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *));
 
 #define VLAN_NAME "vlan"