#include <linux/ctype.h>
#include <linux/if_arp.h>
+#include "net-sysfs.h"
+
/*
* The list of packet types we will receive (as opposed to discard)
* and the routines to invoke.
* 86DD IPv6
*/
+#define PTYPE_HASH_SIZE (16)
+#define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1)
+
static DEFINE_SPINLOCK(ptype_lock);
-static struct list_head ptype_base[16] __read_mostly; /* 16 way hashed list */
+static struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
static struct list_head ptype_all __read_mostly; /* Taps */
#ifdef CONFIG_NET_DMA
DEFINE_PER_CPU(struct softnet_data, softnet_data);
-extern int netdev_kobject_init(void);
-extern int netdev_register_kobject(struct net_device *);
-extern void netdev_unregister_kobject(struct net_device *);
-
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
* register_netdevice() inits dev->_xmit_lock and sets lockdep class
if (pt->type == htons(ETH_P_ALL))
list_add_rcu(&pt->list, &ptype_all);
else {
- hash = ntohs(pt->type) & 15;
+ hash = ntohs(pt->type) & PTYPE_HASH_MASK;
list_add_rcu(&pt->list, &ptype_base[hash]);
}
spin_unlock_bh(&ptype_lock);
if (pt->type == htons(ETH_P_ALL))
head = &ptype_all;
else
- head = &ptype_base[ntohs(pt->type) & 15];
+ head = &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK];
list_for_each_entry(pt1, head, list) {
if (pt == pt1) {
ASSERT_RTNL();
- for_each_netdev(&init_net, dev)
+ for_each_netdev(net, dev)
if (dev->type == type &&
!memcmp(dev->dev_addr, ha, dev->addr_len))
return dev;
if (!dev_valid_name(newname))
return -EINVAL;
+ if (strncmp(newname, dev->name, IFNAMSIZ) == 0)
+ return 0;
+
memcpy(oldname, dev->name, IFNAMSIZ);
if (strchr(newname, '%')) {
* Call device private open method
*/
set_bit(__LINK_STATE_START, &dev->state);
- if (dev->open) {
+
+ if (dev->validate_addr)
+ ret = dev->validate_addr(dev);
+
+ if (!ret && dev->open)
ret = dev->open(dev);
- if (ret)
- clear_bit(__LINK_STATE_START, &dev->state);
- }
/*
* If it went open OK then:
*/
- if (!ret) {
+ if (ret)
+ clear_bit(__LINK_STATE_START, &dev->state);
+ else {
/*
* Set the flags.
*/
*/
call_netdevice_notifiers(NETDEV_UP, dev);
}
+
return ret;
}
nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
}
}
+
+ raw_notifier_chain_unregister(&netdev_chain, nb);
goto unlock;
}
}
rcu_read_lock();
- list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & 15], list) {
+ list_for_each_entry_rcu(ptype,
+ &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
if (ptype->type == type && !ptype->dev && ptype->gso_segment) {
if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
err = ptype->gso_send_check(skb);
return rc;
}
if (unlikely((netif_queue_stopped(dev) ||
- netif_subqueue_stopped(dev, skb->queue_mapping)) &&
+ netif_subqueue_stopped(dev, skb)) &&
skb->next))
return NETDEV_TX_BUSY;
} while (skb->next);
q = dev->qdisc;
if (q->enqueue) {
/* reset queue_mapping to zero */
- skb->queue_mapping = 0;
+ skb_set_queue_mapping(skb, 0);
rc = q->enqueue(skb, q);
qdisc_run(dev);
spin_unlock(&dev->queue_lock);
HARD_TX_LOCK(dev, cpu);
if (!netif_queue_stopped(dev) &&
- !netif_subqueue_stopped(dev, skb->queue_mapping)) {
+ !netif_subqueue_stopped(dev, skb)) {
rc = 0;
if (!dev_hard_start_xmit(skb, dev)) {
HARD_TX_UNLOCK(dev);
*
* return values:
* NET_RX_SUCCESS (no congestion)
- * NET_RX_CN_LOW (low congestion)
- * NET_RX_CN_MOD (moderate congestion)
- * NET_RX_CN_HIGH (high congestion)
* NET_RX_DROP (packet was dropped)
*
*/
}
#endif
+/**
+ * netif_receive_skb - process receive buffer from network
+ * @skb: buffer to process
+ *
+ * netif_receive_skb() is the main receive data processing function.
+ * It always succeeds. The buffer may be dropped during processing
+ * for congestion control or by the protocol layers.
+ *
+ * This function may only be called from softirq context and interrupts
+ * should be enabled.
+ *
+ * Return values (usually ignored):
+ * NET_RX_SUCCESS: no congestion
+ * NET_RX_DROP: packet was dropped
+ */
int netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
goto out;
type = skb->protocol;
- list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type)&15], list) {
+ list_for_each_entry_rcu(ptype,
+ &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
if (ptype->type == type &&
(!ptype->dev || ptype->dev == skb->dev)) {
if (pt_prev)
weight = n->weight;
- work = n->poll(n, weight);
+ /* This NAPI_STATE_SCHED test is for avoiding a race
+ * with netpoll's poll_napi(). Only the entity which
+ * obtains the lock and sees NAPI_STATE_SCHED set will
+ * actually make the ->poll() call. Therefore we avoid
+ * accidently calling ->poll() when NAPI is not scheduled.
+ */
+ work = 0;
+ if (test_bit(NAPI_STATE_SCHED, &n->state))
+ work = n->poll(n, weight);
WARN_ON_ONCE(work > weight);
* still "owns" the NAPI instance and therefore can
* move the instance around on the list at-will.
*/
- if (unlikely(work == weight))
- list_move_tail(&n->poll_list, list);
+ if (unlikely(work == weight)) {
+ if (unlikely(napi_disable_pending(n)))
+ __napi_complete(n);
+ else
+ list_move_tail(&n->poll_list, list);
+ }
netpoll_poll_unlock(have);
}
* in detail.
*/
void *dev_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(dev_base_lock)
{
- struct net *net = seq->private;
+ struct net *net = seq_file_net(seq);
loff_t off;
struct net_device *dev;
void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct net *net = seq->private;
+ struct net *net = seq_file_net(seq);
++*pos;
return v == SEQ_START_TOKEN ?
first_net_device(net) : next_net_device((struct net_device *)v);
}
void dev_seq_stop(struct seq_file *seq, void *v)
+ __releases(dev_base_lock)
{
read_unlock(&dev_base_lock);
}
static int dev_seq_open(struct inode *inode, struct file *file)
{
- struct seq_file *seq;
- int res;
- res = seq_open(file, &dev_seq_ops);
- if (!res) {
- seq = file->private_data;
- seq->private = get_proc_net(inode);
- if (!seq->private) {
- seq_release(inode, file);
- res = -ENXIO;
- }
- }
- return res;
-}
-
-static int dev_seq_release(struct inode *inode, struct file *file)
-{
- struct seq_file *seq = file->private_data;
- struct net *net = seq->private;
- put_net(net);
- return seq_release(inode, file);
+ return seq_open_net(inode, file, &dev_seq_ops,
+ sizeof(struct seq_net_private));
}
static const struct file_operations dev_seq_fops = {
.open = dev_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = dev_seq_release,
+ .release = seq_release_net,
};
static const struct seq_operations softnet_seq_ops = {
++i;
}
- for (t = 0; t < 16; t++) {
+ for (t = 0; t < PTYPE_HASH_SIZE; t++) {
list_for_each_entry_rcu(pt, &ptype_base[t], list) {
if (i == pos)
return pt;
}
static void *ptype_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(RCU)
{
rcu_read_lock();
return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN;
hash = 0;
nxt = ptype_base[0].next;
} else
- hash = ntohs(pt->type) & 15;
+ hash = ntohs(pt->type) & PTYPE_HASH_MASK;
while (nxt == &ptype_base[hash]) {
- if (++hash >= 16)
+ if (++hash >= PTYPE_HASH_SIZE)
return NULL;
nxt = ptype_base[hash].next;
}
}
static void ptype_seq_stop(struct seq_file *seq, void *v)
+ __releases(RCU)
{
rcu_read_unlock();
}
printk(KERN_INFO "device %s %s promiscuous mode\n",
dev->name, (dev->flags & IFF_PROMISC) ? "entered" :
"left");
- audit_log(current->audit_context, GFP_ATOMIC,
- AUDIT_ANOM_PROMISCUOUS,
- "dev=%s prom=%d old_prom=%d auid=%u",
- dev->name, (dev->flags & IFF_PROMISC),
- (old_flags & IFF_PROMISC),
- audit_get_loginuid(current->audit_context));
+ if (audit_enabled)
+ audit_log(current->audit_context, GFP_ATOMIC,
+ AUDIT_ANOM_PROMISCUOUS,
+ "dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u",
+ dev->name, (dev->flags & IFF_PROMISC),
+ (old_flags & IFF_PROMISC),
+ audit_get_loginuid(current),
+ current->uid, current->gid,
+ audit_get_sessionid(current));
if (dev->change_rx_flags)
dev->change_rx_flags(dev, IFF_PROMISC);
/*
* Upload unicast and multicast address lists to device and
* configure RX filtering. When the device doesn't support unicast
- * filtering it is put in promiscous mode while unicast addresses
+ * filtering it is put in promiscuous mode while unicast addresses
* are present.
*/
void __dev_set_rx_mode(struct net_device *dev)
}
EXPORT_SYMBOL(dev_unicast_add);
+int __dev_addr_sync(struct dev_addr_list **to, int *to_count,
+ struct dev_addr_list **from, int *from_count)
+{
+ struct dev_addr_list *da, *next;
+ int err = 0;
+
+ da = *from;
+ while (da != NULL) {
+ next = da->next;
+ if (!da->da_synced) {
+ err = __dev_addr_add(to, to_count,
+ da->da_addr, da->da_addrlen, 0);
+ if (err < 0)
+ break;
+ da->da_synced = 1;
+ da->da_users++;
+ } else if (da->da_users == 1) {
+ __dev_addr_delete(to, to_count,
+ da->da_addr, da->da_addrlen, 0);
+ __dev_addr_delete(from, from_count,
+ da->da_addr, da->da_addrlen, 0);
+ }
+ da = next;
+ }
+ return err;
+}
+
+void __dev_addr_unsync(struct dev_addr_list **to, int *to_count,
+ struct dev_addr_list **from, int *from_count)
+{
+ struct dev_addr_list *da, *next;
+
+ da = *from;
+ while (da != NULL) {
+ next = da->next;
+ if (da->da_synced) {
+ __dev_addr_delete(to, to_count,
+ da->da_addr, da->da_addrlen, 0);
+ da->da_synced = 0;
+ __dev_addr_delete(from, from_count,
+ da->da_addr, da->da_addrlen, 0);
+ }
+ da = next;
+ }
+}
+
+/**
+ * dev_unicast_sync - Synchronize device's unicast list to another device
+ * @to: destination device
+ * @from: source device
+ *
+ * Add newly added addresses to the destination device and release
+ * addresses that have no users left. The source device must be
+ * locked by netif_tx_lock_bh.
+ *
+ * This function is intended to be called from the dev->set_rx_mode
+ * function of layered software devices.
+ */
+int dev_unicast_sync(struct net_device *to, struct net_device *from)
+{
+ int err = 0;
+
+ netif_tx_lock_bh(to);
+ err = __dev_addr_sync(&to->uc_list, &to->uc_count,
+ &from->uc_list, &from->uc_count);
+ if (!err)
+ __dev_set_rx_mode(to);
+ netif_tx_unlock_bh(to);
+ return err;
+}
+EXPORT_SYMBOL(dev_unicast_sync);
+
+/**
+ * dev_unicast_unsync - Remove synchronized addresses from the destination
+ * device
+ * @to: destination device
+ * @from: source device
+ *
+ * Remove all addresses that were added to the destination device by
+ * dev_unicast_sync(). This function is intended to be called from the
+ * dev->stop function of layered software devices.
+ */
+void dev_unicast_unsync(struct net_device *to, struct net_device *from)
+{
+ netif_tx_lock_bh(from);
+ netif_tx_lock_bh(to);
+
+ __dev_addr_unsync(&to->uc_list, &to->uc_count,
+ &from->uc_list, &from->uc_count);
+ __dev_set_rx_mode(to);
+
+ netif_tx_unlock_bh(to);
+ netif_tx_unlock_bh(from);
+}
+EXPORT_SYMBOL(dev_unicast_unsync);
+
static void __dev_addr_discard(struct dev_addr_list **list)
{
struct dev_addr_list *tmp;
/* Delayed registration/unregisteration */
static DEFINE_SPINLOCK(net_todo_list_lock);
-static struct list_head net_todo_list = LIST_HEAD_INIT(net_todo_list);
+static LIST_HEAD(net_todo_list);
static void net_set_todo(struct net_device *dev)
{
spin_unlock(&net_todo_list_lock);
}
+static void rollback_registered(struct net_device *dev)
+{
+ BUG_ON(dev_boot_phase);
+ ASSERT_RTNL();
+
+ /* Some devices call without registering for initialization unwind. */
+ if (dev->reg_state == NETREG_UNINITIALIZED) {
+ printk(KERN_DEBUG "unregister_netdevice: device %s/%p never "
+ "was registered\n", dev->name, dev);
+
+ WARN_ON(1);
+ return;
+ }
+
+ 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();
+
+ /* 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);
+
+ /*
+ * Flush the unicast and multicast chains
+ */
+ dev_addr_discard(dev);
+
+ if (dev->uninit)
+ dev->uninit(dev);
+
+ /* Notifier chain MUST detach us from master device. */
+ BUG_TRAP(!dev->master);
+
+ /* Remove entries from kobject tree */
+ netdev_unregister_kobject(dev);
+
+ synchronize_net();
+
+ dev_put(dev);
+}
+
/**
* register_netdevice - register a network device
* @dev: device to register
/* Notify protocols, that a new device appeared. */
ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
ret = notifier_to_errno(ret);
- if (ret)
- unregister_netdevice(dev);
+ if (ret) {
+ rollback_registered(dev);
+ dev->reg_state = NETREG_UNREGISTERED;
+ }
out:
return ret;
* @dev: device
*
* This function shuts down a device interface and removes it
- * from the kernel tables. On success 0 is returned, on a failure
- * a negative errno code is returned.
+ * from the kernel tables.
*
* Callers must hold the rtnl semaphore. You may want
* unregister_netdev() instead of this.
void unregister_netdevice(struct net_device *dev)
{
- BUG_ON(dev_boot_phase);
ASSERT_RTNL();
- /* Some devices call without registering for initialization unwind. */
- if (dev->reg_state == NETREG_UNINITIALIZED) {
- printk(KERN_DEBUG "unregister_netdevice: device %s/%p never "
- "was registered\n", dev->name, dev);
-
- WARN_ON(1);
- return;
- }
-
- 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();
-
- /* 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);
-
- /*
- * Flush the unicast and multicast chains
- */
- dev_addr_discard(dev);
-
- if (dev->uninit)
- dev->uninit(dev);
-
- /* Notifier chain MUST detach us from master device. */
- BUG_TRAP(!dev->master);
-
- /* Remove entries from kobject tree */
- netdev_unregister_kobject(dev);
-
+ rollback_registered(dev);
/* Finish processing unregister after unlock */
net_set_todo(dev);
-
- synchronize_net();
-
- dev_put(dev);
}
/**
* @dev: device
*
* This function shuts down a device interface and removes it
- * from the kernel tables. On success 0 is returned, on a failure
- * a negative errno code is returned.
+ * from the kernel tables.
*
* This is just a wrapper for unregister_netdevice that takes
* the rtnl semaphore. In general you want to use this and not
static int __net_init netdev_init(struct net *net)
{
INIT_LIST_HEAD(&net->dev_base_head);
- rwlock_init(&dev_base_lock);
net->dev_name_head = netdev_create_hash();
if (net->dev_name_head == NULL)
goto out;
INIT_LIST_HEAD(&ptype_all);
- for (i = 0; i < 16; i++)
+ for (i = 0; i < PTYPE_HASH_SIZE; i++)
INIT_LIST_HEAD(&ptype_base[i]);
if (register_pernet_subsys(&netdev_net_ops))