Newer
Older
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
* These ioctl calls:
* - require superuser power.
* - require strict serialization.
* - do not return a value
*/
case SIOCSIFFLAGS:
case SIOCSIFMETRIC:
case SIOCSIFMTU:
case SIOCSIFMAP:
case SIOCSIFHWADDR:
case SIOCSIFSLAVE:
case SIOCADDMULTI:
case SIOCDELMULTI:
case SIOCSIFHWBROADCAST:
case SIOCSIFTXQLEN:
case SIOCSMIIREG:
case SIOCBONDENSLAVE:
case SIOCBONDRELEASE:
case SIOCBONDSETHWADDR:
case SIOCBONDCHANGEACTIVE:
case SIOCBRADDIF:
case SIOCBRDELIF:
case SIOCSHWTSTAMP:
if (!capable(CAP_NET_ADMIN))
return -EPERM;
/* fall through */
case SIOCBONDSLAVEINFOQUERY:
case SIOCBONDINFOQUERY:
dev_load(net, ifr.ifr_name);
rtnl_lock();
ret = dev_ifsioc(net, &ifr, cmd);
rtnl_unlock();
return ret;
case SIOCGIFMEM:
/* Get the per device memory space. We can add this but
* currently do not support it */
case SIOCSIFMEM:
/* Set the per device memory buffer space.
* Not applicable in our case */
case SIOCSIFLINK:
return -EINVAL;
/*
* Unknown or private ioctl.
*/
default:
if (cmd == SIOCWANDEV ||
(cmd >= SIOCDEVPRIVATE &&
cmd <= SIOCDEVPRIVATE + 15)) {
dev_load(net, ifr.ifr_name);
ret = dev_ifsioc(net, &ifr, cmd);
if (!ret && copy_to_user(arg, &ifr,
sizeof(struct ifreq)))
ret = -EFAULT;
}
/* Take care of Wireless Extensions */
if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)
return wext_handle_ioctl(net, &ifr, cmd, arg);
return -EINVAL;
}
}
/**
* dev_new_index - allocate an ifindex
* @net: the applicable net namespace
*
* Returns a suitable unique value for a new device interface
* number. The caller must hold the rtnl semaphore or the
* dev_base_lock to be sure it remains unique.
*/
static int dev_new_index(struct net *net)
{
static int ifindex;
for (;;) {
if (++ifindex <= 0)
ifindex = 1;
if (!__dev_get_by_index(net, ifindex))
return ifindex;
}
}
/* Delayed registration/unregisteration */
static LIST_HEAD(net_todo_list);
static void net_set_todo(struct net_device *dev)
{
list_add_tail(&dev->todo_list, &net_todo_list);
}
static void rollback_registered_many(struct list_head *head)
struct net_device *dev, *tmp;
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
list_for_each_entry_safe(dev, tmp, head, unreg_list) {
/* Some devices call without registering
* for initialization unwind. Remove those
* devices and proceed with the remaining.
*/
if (dev->reg_state == NETREG_UNINITIALIZED) {
pr_debug("unregister_netdevice: device %s/%p never "
"was registered\n", dev->name, dev);
list_del(&dev->unreg_list);
continue;
BUG_ON(dev->reg_state != NETREG_REGISTERED);
/* If device is running, close it first. */
dev_close(dev);
/* And unlink it from device chain. */
unlist_netdevice(dev);
dev->reg_state = NETREG_UNREGISTERING;
}
synchronize_net();
list_for_each_entry(dev, head, unreg_list) {
/* Shutdown queueing discipline. */
dev_shutdown(dev);
/* Notify protocols, that we are about to destroy
this device. They should clean all the things.
*/
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
if (!dev->rtnl_link_ops ||
dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
rtmsg_ifinfo(RTM_DELLINK, dev, ~0U);
/*
* Flush the unicast and multicast chains
*/
dev_unicast_flush(dev);
dev_addr_discard(dev);
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
/* Notifier chain MUST detach us from master device. */
WARN_ON(dev->master);
/* Remove entries from kobject tree */
netdev_unregister_kobject(dev);
}
/* Process any work delayed until the end of the batch */
dev = list_first_entry(head, struct net_device, unreg_list);
call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
synchronize_net();
list_for_each_entry(dev, head, unreg_list)
dev_put(dev);
}
static void rollback_registered(struct net_device *dev)
{
LIST_HEAD(single);
list_add(&dev->unreg_list, &single);
rollback_registered_many(&single);
static void __netdev_init_queue_locks_one(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_unused)
{
spin_lock_init(&dev_queue->_xmit_lock);
netdev_set_xmit_lockdep_class(&dev_queue->_xmit_lock, dev->type);
dev_queue->xmit_lock_owner = -1;
}
static void netdev_init_queue_locks(struct net_device *dev)
{
netdev_for_each_tx_queue(dev, __netdev_init_queue_locks_one, NULL);
__netdev_init_queue_locks_one(dev, &dev->rx_queue, NULL);
}
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
unsigned long netdev_fix_features(unsigned long features, const char *name)
{
/* Fix illegal SG+CSUM combinations. */
if ((features & NETIF_F_SG) &&
!(features & NETIF_F_ALL_CSUM)) {
if (name)
printk(KERN_NOTICE "%s: Dropping NETIF_F_SG since no "
"checksum feature.\n", name);
features &= ~NETIF_F_SG;
}
/* TSO requires that SG is present as well. */
if ((features & NETIF_F_TSO) && !(features & NETIF_F_SG)) {
if (name)
printk(KERN_NOTICE "%s: Dropping NETIF_F_TSO since no "
"SG feature.\n", name);
features &= ~NETIF_F_TSO;
}
if (features & NETIF_F_UFO) {
if (!(features & NETIF_F_GEN_CSUM)) {
if (name)
printk(KERN_ERR "%s: Dropping NETIF_F_UFO "
"since no NETIF_F_HW_CSUM feature.\n",
name);
features &= ~NETIF_F_UFO;
}
if (!(features & NETIF_F_SG)) {
if (name)
printk(KERN_ERR "%s: Dropping NETIF_F_UFO "
"since no NETIF_F_SG feature.\n", name);
features &= ~NETIF_F_UFO;
}
}
return features;
}
EXPORT_SYMBOL(netdev_fix_features);

Patrick Mullaney
committed
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
/**
* netif_stacked_transfer_operstate - transfer operstate
* @rootdev: the root or lower level device to transfer state from
* @dev: the device to transfer operstate to
*
* Transfer operational state from root to device. This is normally
* called when a stacking relationship exists between the root
* device and the device(a leaf device).
*/
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
struct net_device *dev)
{
if (rootdev->operstate == IF_OPER_DORMANT)
netif_dormant_on(dev);
else
netif_dormant_off(dev);
if (netif_carrier_ok(rootdev)) {
if (!netif_carrier_ok(dev))
netif_carrier_on(dev);
} else {
if (netif_carrier_ok(dev))
netif_carrier_off(dev);
}
}
EXPORT_SYMBOL(netif_stacked_transfer_operstate);
/**
* register_netdevice - register a network device
* @dev: device to register
*
* Take a completed network device structure and add it to the kernel
* interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier
* chain. 0 is returned on success. A negative errno code is returned
* on a failure to set up the device, or if the name is a duplicate.
*
* Callers must hold the rtnl semaphore. You may want
* register_netdev() instead of this.
*
* BUGS:
* The locking appears insufficient to guarantee two parallel registers
* will not get the same name.
*/
int register_netdevice(struct net_device *dev)
{
int ret;
struct net *net = dev_net(dev);
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
might_sleep();
/* When net_device's are persistent, this will be fatal. */
BUG_ON(dev->reg_state != NETREG_UNINITIALIZED);
spin_lock_init(&dev->addr_list_lock);
netdev_set_addr_lockdep_class(dev);
netdev_init_queue_locks(dev);
if (!dev->num_rx_queues) {
/*
* Allocate a single RX queue if driver never called
* alloc_netdev_mq
*/
dev->_rx = kzalloc(sizeof(struct netdev_rx_queue), GFP_KERNEL);
if (!dev->_rx) {
ret = -ENOMEM;
goto out;
}
dev->_rx->first = dev->_rx;
atomic_set(&dev->_rx->count, 1);
dev->num_rx_queues = 1;
}
if (dev->netdev_ops->ndo_init) {
ret = dev->netdev_ops->ndo_init(dev);
ret = dev_get_valid_name(net, dev->name, dev->name, 0);
if (ret)
dev->ifindex = dev_new_index(net);
if (dev->iflink == -1)
dev->iflink = dev->ifindex;
/* Fix illegal checksum combinations */
if ((dev->features & NETIF_F_HW_CSUM) &&
(dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
printk(KERN_NOTICE "%s: mixed HW and IP checksum settings.\n",
dev->name);
dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
}
if ((dev->features & NETIF_F_NO_CSUM) &&
(dev->features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
printk(KERN_NOTICE "%s: mixed no checksumming and other settings.\n",
dev->name);
dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM);
}
dev->features = netdev_fix_features(dev->features, dev->name);
/* Enable software GSO if SG is supported. */
if (dev->features & NETIF_F_SG)
dev->features |= NETIF_F_GSO;
ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
ret = notifier_to_errno(ret);
if (ret)
goto err_uninit;
ret = netdev_register_kobject(dev);
if (ret)
dev->reg_state = NETREG_REGISTERED;
/*
* Default initial state at registry is that the
* device is present.
*/
set_bit(__LINK_STATE_PRESENT, &dev->state);
dev_init_scheduler(dev);
dev_hold(dev);
list_netdevice(dev);
/* Notify protocols, that a new device appeared. */
ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
ret = notifier_to_errno(ret);
if (ret) {
rollback_registered(dev);
dev->reg_state = NETREG_UNREGISTERED;
}
/*
* Prevent userspace races by waiting until the network
* device is fully setup before sending notifications.
*/
if (!dev->rtnl_link_ops ||
dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
/**
* init_dummy_netdev - init a dummy network device for NAPI
* @dev: device to init
*
* This takes a network device structure and initialize the minimum
* amount of fields so it can be used to schedule NAPI polls without
* registering a full blown interface. This is to be used by drivers
* that need to tie several hardware interfaces to a single NAPI
* poll scheduler due to HW limitations.
*/
int init_dummy_netdev(struct net_device *dev)
{
/* Clear everything. Note we don't initialize spinlocks
* are they aren't supposed to be taken by any of the
* NAPI code and this dummy netdev is supposed to be
* only ever used for NAPI polls
*/
memset(dev, 0, sizeof(struct net_device));
/* make sure we BUG if trying to hit standard
* register/unregister code path
*/
dev->reg_state = NETREG_DUMMY;
/* initialize the ref count */
atomic_set(&dev->refcnt, 1);
/* NAPI wants this */
INIT_LIST_HEAD(&dev->napi_list);
/* a dummy interface is started by default */
set_bit(__LINK_STATE_PRESENT, &dev->state);
set_bit(__LINK_STATE_START, &dev->state);
return 0;
}
EXPORT_SYMBOL_GPL(init_dummy_netdev);
/**
* register_netdev - register a network device
* @dev: device to register
*
* Take a completed network device structure and add it to the kernel
* interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier
* chain. 0 is returned on success. A negative errno code is returned
* on a failure to set up the device, or if the name is a duplicate.
*
* This is a wrapper around register_netdevice that takes the rtnl semaphore
* and expands the device name if you passed a format string to
* alloc_netdev.
*/
int register_netdev(struct net_device *dev)
{
int err;
rtnl_lock();
/*
* If the name is a format string the caller wants us to do a
* name allocation.
*/
if (strchr(dev->name, '%')) {
err = dev_alloc_name(dev, dev->name);
if (err < 0)
goto out;
}
err = register_netdevice(dev);
out:
rtnl_unlock();
return err;
}
EXPORT_SYMBOL(register_netdev);
/*
* netdev_wait_allrefs - wait until all references are gone.
*
* This is called when unregistering network devices.
*
* Any protocol or device that holds a reference should register
* for netdevice notification, and cleanup and put back the
* reference if they receive an UNREGISTER event.
* We can get stuck here if buggy protocols don't correctly
*/
static void netdev_wait_allrefs(struct net_device *dev)
{
unsigned long rebroadcast_time, warning_time;
linkwatch_forget_dev(dev);
rebroadcast_time = warning_time = jiffies;
while (atomic_read(&dev->refcnt) != 0) {
if (time_after(jiffies, rebroadcast_time + 1 * HZ)) {
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
/* don't resend NETDEV_UNREGISTER_BATCH, _BATCH users
* should have already handle it the first time */
if (test_bit(__LINK_STATE_LINKWATCH_PENDING,
&dev->state)) {
/* We must not have linkwatch events
* pending on unregister. If this
* happens, we simply run the queue
* unscheduled, resulting in a noop
* for this device.
*/
linkwatch_run_queue();
}
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
rebroadcast_time = jiffies;
}
msleep(250);
if (time_after(jiffies, warning_time + 10 * HZ)) {
printk(KERN_EMERG "unregister_netdevice: "
"waiting for %s to become free. Usage "
"count = %d\n",
dev->name, atomic_read(&dev->refcnt));
warning_time = jiffies;
}
}
}
/* The sequence is:
*
* rtnl_lock();
* ...
* register_netdevice(x1);
* register_netdevice(x2);
* ...
* unregister_netdevice(y1);
* unregister_netdevice(y2);
* ...
* rtnl_unlock();
* free_netdev(y1);
* free_netdev(y2);
*
* 1) We can delete sysfs objects which invoke hotplug
* without deadlocking with linkwatch via keventd.
* 2) Since we run with the RTNL semaphore not held, we can sleep
* safely in order to wait for the netdev refcnt to drop to zero.
*
* We must not return until all unregister events added during
* the interval the lock was held have been completed.
struct list_head list;
list_replace_init(&net_todo_list, &list);
while (!list_empty(&list)) {
struct net_device *dev
= list_first_entry(&list, struct net_device, todo_list);
if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) {
printk(KERN_ERR "network todo '%s' but state %d\n",
dev->name, dev->reg_state);
dump_stack();
continue;
}
dev->reg_state = NETREG_UNREGISTERED;
on_each_cpu(flush_backlog, dev, 1);
netdev_wait_allrefs(dev);
/* paranoia */
BUG_ON(atomic_read(&dev->refcnt));
WARN_ON(dev->ip_ptr);
WARN_ON(dev->ip6_ptr);
WARN_ON(dev->dn_ptr);
if (dev->destructor)
dev->destructor(dev);
/* Free network device */
kobject_put(&dev->dev.kobj);
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
/**
* dev_txq_stats_fold - fold tx_queues stats
* @dev: device to get statistics from
* @stats: struct net_device_stats to hold results
*/
void dev_txq_stats_fold(const struct net_device *dev,
struct net_device_stats *stats)
{
unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0;
unsigned int i;
struct netdev_queue *txq;
for (i = 0; i < dev->num_tx_queues; i++) {
txq = netdev_get_tx_queue(dev, i);
tx_bytes += txq->tx_bytes;
tx_packets += txq->tx_packets;
tx_dropped += txq->tx_dropped;
}
if (tx_bytes || tx_packets || tx_dropped) {
stats->tx_bytes = tx_bytes;
stats->tx_packets = tx_packets;
stats->tx_dropped = tx_dropped;
}
}
EXPORT_SYMBOL(dev_txq_stats_fold);
/**
* dev_get_stats - get network device statistics
* @dev: device to get statistics from
*
* Get network statistics from device. The device driver may provide
* its own method by setting dev->netdev_ops->get_stats; otherwise
* the internal statistics structure is used.
*/
const struct net_device_stats *dev_get_stats(struct net_device *dev)
{
const struct net_device_ops *ops = dev->netdev_ops;
if (ops->ndo_get_stats)
return ops->ndo_get_stats(dev);
dev_txq_stats_fold(dev, &dev->stats);
return &dev->stats;
static void netdev_init_one_queue(struct net_device *dev,
struct netdev_queue *queue,
void *_unused)
{
queue->dev = dev;
}
static void netdev_init_queues(struct net_device *dev)
{
netdev_init_one_queue(dev, &dev->rx_queue, NULL);
netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
spin_lock_init(&dev->tx_global_lock);
* alloc_netdev_mq - allocate network device
* @sizeof_priv: size of private data to allocate space for
* @name: device name format string
* @setup: callback to initialize device
* @queue_count: the number of subqueues to allocate
*
* Allocates a struct net_device with private data area for driver use
* and performs basic initialization. Also allocates subquue structs
* for each queue on the device at the end of the netdevice.
struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
void (*setup)(struct net_device *), unsigned int queue_count)
struct net_device *p;
BUG_ON(strlen(name) >= sizeof(dev->name));
alloc_size = sizeof(struct net_device);
if (sizeof_priv) {
/* ensure 32-byte alignment of private area */
alloc_size = ALIGN(alloc_size, NETDEV_ALIGN);
alloc_size += sizeof_priv;
}
/* ensure 32-byte alignment of whole construct */
alloc_size += NETDEV_ALIGN - 1;
p = kzalloc(alloc_size, GFP_KERNEL);
printk(KERN_ERR "alloc_netdev: Unable to allocate device.\n");
tx = kcalloc(queue_count, sizeof(struct netdev_queue), GFP_KERNEL);
if (!tx) {
printk(KERN_ERR "alloc_netdev: Unable to allocate "
"tx qdiscs.\n");
rx = kcalloc(queue_count, sizeof(struct netdev_rx_queue), GFP_KERNEL);
if (!rx) {
printk(KERN_ERR "alloc_netdev: Unable to allocate "
"rx queues.\n");
goto free_tx;
}
atomic_set(&rx->count, queue_count);
/*
* Set a pointer to first element in the array which holds the
* reference count.
*/
for (i = 0; i < queue_count; i++)
rx[i].first = rx;
dev = PTR_ALIGN(p, NETDEV_ALIGN);
dev_net_set(dev, &init_net);
dev->_tx = tx;
dev->num_tx_queues = queue_count;
dev->real_num_tx_queues = queue_count;
dev->_rx = rx;
dev->num_rx_queues = queue_count;
dev->gso_max_size = GSO_MAX_SIZE;
netdev_init_queues(dev);
INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list);
dev->ethtool_ntuple_list.count = 0;
INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list);
INIT_LIST_HEAD(&dev->link_watch_list);
dev->priv_flags = IFF_XMIT_DST_RELEASE;
setup(dev);
strcpy(dev->name, name);
return dev;
kfree(tx);
free_p:
kfree(p);
return NULL;
EXPORT_SYMBOL(alloc_netdev_mq);
/**
* free_netdev - free network device
* @dev: device
*
* This function does the last stage of destroying an allocated device
* interface. The reference to the device object is released.
* If this is the last reference then it will be freed.
*/
void free_netdev(struct net_device *dev)
{
struct napi_struct *p, *n;
release_net(dev_net(dev));
/* Flush device addresses */
dev_addr_flush(dev);
/* Clear ethtool n-tuple list */
ethtool_ntuple_flush(dev);
list_for_each_entry_safe(p, n, &dev->napi_list, dev_list)
netif_napi_del(p);
/* Compatibility with error handling in drivers */
if (dev->reg_state == NETREG_UNINITIALIZED) {
kfree((char *)dev - dev->padded);
return;
}
BUG_ON(dev->reg_state != NETREG_UNREGISTERED);
dev->reg_state = NETREG_RELEASED;

Greg Kroah-Hartman
committed
/* will free via device release */
put_device(&dev->dev);
/**
* synchronize_net - Synchronize with packet receive processing
*
* Wait for packets currently being received to be done.
* Does not block later packets from starting.
*/
synchronize_rcu();
* unregister_netdevice_queue - remove device from the kernel
* This function shuts down a device interface and removes it
* If head not NULL, device is queued to be unregistered later.
*
* Callers must hold the rtnl semaphore. You may want
* unregister_netdev() instead of this.
*/
void unregister_netdevice_queue(struct net_device *dev, struct list_head *head)
list_move_tail(&dev->unreg_list, head);
} else {
rollback_registered(dev);
/* Finish processing unregister after unlock */
net_set_todo(dev);
}
EXPORT_SYMBOL(unregister_netdevice_queue);
/**
* unregister_netdevice_many - unregister many devices
* @head: list of devices
*/
void unregister_netdevice_many(struct list_head *head)
{
struct net_device *dev;
if (!list_empty(head)) {
rollback_registered_many(head);
list_for_each_entry(dev, head, unreg_list)
net_set_todo(dev);
}
}
EXPORT_SYMBOL(unregister_netdevice_many);
/**
* unregister_netdev - remove device from the kernel
* @dev: device
*
* This function shuts down a device interface and removes it
*
* This is just a wrapper for unregister_netdevice that takes
* the rtnl semaphore. In general you want to use this and not
* unregister_netdevice.
*/
void unregister_netdev(struct net_device *dev)
{
rtnl_lock();
unregister_netdevice(dev);
rtnl_unlock();
}
EXPORT_SYMBOL(unregister_netdev);
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
/**
* dev_change_net_namespace - move device to different nethost namespace
* @dev: device
* @net: network namespace
* @pat: If not NULL name pattern to try if the current device name
* is already taken in the destination network namespace.
*
* This function shuts down a device interface and moves it
* to a new network namespace. On success 0 is returned, on
* a failure a netagive errno code is returned.
*
* Callers must hold the rtnl semaphore.
*/
int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat)
{
int err;
ASSERT_RTNL();
/* Don't allow namespace local devices to be moved. */
err = -EINVAL;
if (dev->features & NETIF_F_NETNS_LOCAL)
goto out;
#ifdef CONFIG_SYSFS
/* Don't allow real devices to be moved when sysfs
* is enabled.
*/
err = -EINVAL;
if (dev->dev.parent)
goto out;
#endif
/* Ensure the device has been registrered */
err = -EINVAL;
if (dev->reg_state != NETREG_REGISTERED)
goto out;
/* Get out if there is nothing todo */
err = 0;
if (net_eq(dev_net(dev), net))
goto out;
/* Pick the destination device name, and ensure
* we can use it in the destination network namespace.
*/
err = -EEXIST;
if (__dev_get_by_name(net, dev->name)) {
/* We get here if we can't use the current device name */
if (!pat)
goto out;
if (dev_get_valid_name(net, pat, dev->name, 1))
goto out;
}
/*
* And now a mini version of register_netdevice unregister_netdevice.
*/
/* If device is running close it first. */
dev_close(dev);
/* And unlink it from device chain */
err = -ENODEV;
unlist_netdevice(dev);
synchronize_net();
/* Shutdown queueing discipline. */
dev_shutdown(dev);
/* Notify protocols, that we are about to destroy
this device. They should clean all the things.
*/
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
/*
* Flush the unicast and multicast chains
*/
dev_addr_discard(dev);
netdev_unregister_kobject(dev);
/* Actually switch the network namespace */
dev_net_set(dev, net);
/* If there is an ifindex conflict assign a new one */
if (__dev_get_by_index(net, dev->ifindex)) {
int iflink = (dev->iflink == dev->ifindex);
dev->ifindex = dev_new_index(net);
if (iflink)
dev->iflink = dev->ifindex;
}
err = netdev_register_kobject(dev);
/* Add the device back in the hashes */
list_netdevice(dev);
/* Notify protocols, that a new device appeared. */
call_netdevice_notifiers(NETDEV_REGISTER, dev);
/*
* Prevent userspace races by waiting until the network
* device is fully setup before sending notifications.
*/
rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
synchronize_net();
err = 0;
out:
return err;
}
EXPORT_SYMBOL_GPL(dev_change_net_namespace);
static int dev_cpu_callback(struct notifier_block *nfb,