Skip to contentSkip to conversation

: Make TUN devices work in net namespaces (v2).

PATCH In review Pavel Emelyanov 2 participants 5 messages Apr 15, 2008 – Apr 16, 2008

Subsystems (3)
Networking Network drivers TUN/TAP driver
lore
Share & tools
lore
author
#1 lore raw

PATCH 1/3 : Introduce the tun_net structure and init/exit net ops.

This is the first step in making tuntap devices work in net namespaces. The structure mentioned is pointed by generic net pointer with tun_net_id id, and tun driver fills one on its load. It will contain only the tun devices list.

So declare this structure and introduce net init and exit hooks.

Signed-off-by Pavel Emelyanov <[email protected]>
---
 drivers/net/tun.c |   53 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 52 insertions(+), 1 deletions(-)
drivers/net/tun.c +52 -1
index 5b5d875..f359d60 100644
@@ -63,6 +63,7 @@
 #include <linux/if_tun.h>
 #include <linux/crc32.h>
 #include <net/net_namespace.h>
+#include <net/netns/generic.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>

@@ -106,6 +107,11 @@ struct tun_struct {
 
 /* Network device part of the driver */
 
+static unsigned int tun_net_id;
+struct tun_net {
+	struct list_head dev_list;
+};
+
 static LIST_HEAD(tun_dev_list);
 static const struct ethtool_ops tun_ethtool_ops;
 

@@ -909,6 +915,37 @@ static const struct ethtool_ops tun_ethtool_ops = {
 	.set_rx_csum	= tun_set_rx_csum
 };
 
+static int tun_init_net(struct net *net)
+{
+	struct tun_net *tn;
+
+	tn = kmalloc(sizeof(*tn), GFP_KERNEL);
+	if (tn == NULL)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&tn->dev_list);
+
+	if (net_assign_generic(net, tun_net_id, tn)) {
+		kfree(tn);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void tun_exit_net(struct net *net)
+{
+	struct tun_net *tn;
+
+	tn = net_generic(net, tun_net_id);
+	kfree(tn);
+}
+
+static struct pernet_operations tun_net_ops = {
+	.init = tun_init_net,
+	.exit = tun_exit_net,
+};
+
 static int __init tun_init(void)
 {
 	int ret = 0;

@@ -916,9 +953,22 @@ static int __init tun_init(void)
 	printk(KERN_INFO "tun: %s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
 	printk(KERN_INFO "tun: %s\n", DRV_COPYRIGHT);
 
+	ret = register_pernet_gen_device(&tun_net_id, &tun_net_ops);
+	if (ret) {
+		printk(KERN_ERR "tun: Can't register pernet ops\n");
+		goto err_pernet;
+	}
+
 	ret = misc_register(&tun_miscdev);
-	if (ret)
+	if (ret) {
 		printk(KERN_ERR "tun: Can't register misc device %d\n", TUN_MINOR);
+		goto err_misc;
+	}
+	return 0;
+
+err_misc:
+	unregister_pernet_gen_device(tun_net_id, &tun_net_ops);
+err_pernet:
 	return ret;
 }
 

@@ -935,6 +985,7 @@ static void tun_cleanup(void)
 	}
 	rtnl_unlock();
 
+	unregister_pernet_gen_device(tun_net_id, &tun_net_ops);
 }
 
 module_init(tun_init);
Signature · 1 line
1.5.3.4
author
#2 lore raw

PATCH 2/3 : Make the tun_dev_list per-net.

In reply to Pavel Emelyanov

Remove the static tun_dev_list and replace its occurrences in driver with per-net one.

It is used in two places - in tun_set_iff and tun_cleanup. In the first case it's legal to use current net_ns. In the cleanup call - move the loop, that unregisters all devices in net exit hook.

Signed-off-by Pavel Emelyanov <[email protected]>
---
 drivers/net/tun.c |   37 +++++++++++++++++++------------------
 1 files changed, 19 insertions(+), 18 deletions(-)
drivers/net/tun.c +19 -18
index f359d60..1e655ea 100644
@@ -62,6 +62,7 @@
 #include <linux/if_ether.h>
 #include <linux/if_tun.h>
 #include <linux/crc32.h>
+#include <linux/nsproxy.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 

@@ -112,7 +113,6 @@ struct tun_net {
 	struct list_head dev_list;
 };
 
-static LIST_HEAD(tun_dev_list);
 static const struct ethtool_ops tun_ethtool_ops;
 
 /* Net device open. */

@@ -479,12 +479,12 @@ static void tun_setup(struct net_device *dev)
 	dev->destructor = free_netdev;
 }
 
-static struct tun_struct *tun_get_by_name(const char *name)
+static struct tun_struct *tun_get_by_name(struct tun_net *tn, const char *name)
 {
 	struct tun_struct *tun;
 
 	ASSERT_RTNL();
-	list_for_each_entry(tun, &tun_dev_list, list) {
+	list_for_each_entry(tun, &tn->dev_list, list) {
 		if (!strncmp(tun->dev->name, name, IFNAMSIZ))
 		    return tun;
 	}

@@ -492,13 +492,15 @@ static struct tun_struct *tun_get_by_name(const char *name)
 	return NULL;
 }
 
-static int tun_set_iff(struct file *file, struct ifreq *ifr)
+static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 {
+	struct tun_net *tn;
 	struct tun_struct *tun;
 	struct net_device *dev;
 	int err;
 
-	tun = tun_get_by_name(ifr->ifr_name);
+	tn = net_generic(net, tun_net_id);
+	tun = tun_get_by_name(tn, ifr->ifr_name);
 	if (tun) {
 		if (tun->attached)
 			return -EBUSY;

@@ -511,7 +513,7 @@ static int tun_set_iff(struct file *file, struct ifreq *ifr)
 		     !capable(CAP_NET_ADMIN))
 			return -EPERM;
 	}
-	else if (__dev_get_by_name(&init_net, ifr->ifr_name))
+	else if (__dev_get_by_name(net, ifr->ifr_name))
 		return -EINVAL;
 	else {
 		char *name;

@@ -564,7 +566,7 @@ static int tun_set_iff(struct file *file, struct ifreq *ifr)
 		if (err < 0)
 			goto err_free_dev;
 
-		list_add(&tun->list, &tun_dev_list);
+		list_add(&tun->list, &tn->dev_list);
 	}
 
 	DBG(KERN_INFO "%s: tun_set_iff\n", tun->dev->name);

@@ -609,7 +611,7 @@ static int tun_chr_ioctl(struct inode *inode, struct file *file,
 		ifr.ifr_name[IFNAMSIZ-1] = '\0';
 
 		rtnl_lock();
-		err = tun_set_iff(file, &ifr);
+		err = tun_set_iff(current->nsproxy->net_ns, file, &ifr);
 		rtnl_unlock();
 
 		if (err)

@@ -936,8 +938,17 @@ static int tun_init_net(struct net *net)
 static void tun_exit_net(struct net *net)
 {
 	struct tun_net *tn;
+	struct tun_struct *tun, *nxt;
 
 	tn = net_generic(net, tun_net_id);
+
+	rtnl_lock();
+	list_for_each_entry_safe(tun, nxt, &tn->dev_list, list) {
+		DBG(KERN_INFO "%s cleaned up\n", tun->dev->name);
+		unregister_netdevice(tun->dev);
+	}
+	rtnl_unlock();
+
 	kfree(tn);
 }
 

@@ -974,17 +985,7 @@ err_pernet:
 
 static void tun_cleanup(void)
 {
-	struct tun_struct *tun, *nxt;
-
 	misc_deregister(&tun_miscdev);
-
-	rtnl_lock();
-	list_for_each_entry_safe(tun, nxt, &tun_dev_list, list) {
-		DBG(KERN_INFO "%s cleaned up\n", tun->dev->name);
-		unregister_netdevice(tun->dev);
-	}
-	rtnl_unlock();
-
 	unregister_pernet_gen_device(tun_net_id, &tun_net_ops);
 }
Signature · 1 line
1.5.3.4
author
#3 lore raw

PATCH 3/3 : Allow to register tun devices in namespace.

In reply to Pavel Emelyanov

This is basically means that a net is set for a new device, but actually also involves two more steps:

1. mark the tun device as "local", i.e. do not allow for it to move across namespaces.

This is done so, since tun device is most often associated to some file (and thus to some process) and moving the device alone is not valid while keeping the file and the process outside. The need in ability to move a detached persistent device is to be investigated later.

2. get the tun device's net when tun becomes attached and put one when it becomes detached.

This is needed to handle the case when a task owning the tun dies, but a files lives for some more time - in this case we must not allow for net to be freed, since its exit hook will spoil that file's private data by unregistering the tun from under tun_chr_close.

Signed-off-by Pavel Emelyanov <[email protected]>
---
 drivers/net/tun.c |    4 ++++
 1 files changed, 4 insertions(+), 0 deletions(-)
drivers/net/tun.c +4 -0
index 1e655ea..d91856b 100644
@@ -477,6 +477,7 @@ static void tun_setup(struct net_device *dev)
 	dev->stop = tun_net_close;
 	dev->ethtool_ops = &tun_ethtool_ops;
 	dev->destructor = free_netdev;
+	dev->features |= NETIF_F_NETNS_LOCAL;
 }
 
 static struct tun_struct *tun_get_by_name(struct tun_net *tn, const char *name)

@@ -544,6 +545,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		if (!dev)
 			return -ENOMEM;
 
+		dev_net_set(dev, net);
 		tun = netdev_priv(dev);
 		tun->dev = dev;
 		tun->flags = flags;

@@ -583,6 +585,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 	file->private_data = tun;
 	tun->attached = 1;
+	get_net(dev_net(tun->dev));
 
 	strcpy(ifr->ifr_name, tun->dev->name);
 	return 0;

@@ -798,6 +801,7 @@ static int tun_chr_close(struct inode *inode, struct file *file)
 	/* Detach from net device */
 	file->private_data = NULL;
 	tun->attached = 0;
+	put_net(dev_net(tun->dev));
 
 	/* Drop read queue */
 	skb_queue_purge(&tun->readq);
Signature · 1 line
1.5.3.4