#include <linux/if_ether.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
#include <linux/notifier.h>
#include <linux/skbuff.h>
+#include <net/net_namespace.h>
#include <net/sock.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/stat.h>
#include <linux/if_bridge.h>
+#include <linux/if_macvlan.h>
#include <net/dst.h>
#include <net/pkt_sched.h>
#include <net/checksum.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/module.h>
-#include <linux/kallsyms.h>
#include <linux/netpoll.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
#include <linux/err.h>
#include <linux/ctype.h>
#include <linux/if_arp.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <net/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/jhash.h>
+#include <linux/random.h>
+#include <trace/events/napi.h>
+
+#include "net-sysfs.h"
+
+/* Instead of increasing this, you should create a hash table. */
+#define MAX_GRO_SKBS 8
+
+/* This should be increased if a protocol with a bigger head is added. */
+#define GRO_MAX_HEAD (MAX_HEADER + 128)
/*
* The list of packet types we will receive (as opposed to discard)
* 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
-static struct dma_client *net_dma_client;
-static unsigned int net_dma_count;
-static spinlock_t net_dma_event_lock;
-#endif
-
/*
* The @dev_base_head list is protected by @dev_base_lock and the rtnl
* semaphore.
* unregister_netdevice(), which must be called with the rtnl
* semaphore held.
*/
-LIST_HEAD(dev_base_head);
DEFINE_RWLOCK(dev_base_lock);
-
-EXPORT_SYMBOL(dev_base_head);
EXPORT_SYMBOL(dev_base_lock);
#define NETDEV_HASHBITS 8
-static struct hlist_head dev_name_head[1<<NETDEV_HASHBITS];
-static struct hlist_head dev_index_head[1<<NETDEV_HASHBITS];
+#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS)
-static inline struct hlist_head *dev_name_hash(const char *name)
+static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
{
unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
- return &dev_name_head[hash & ((1<<NETDEV_HASHBITS)-1)];
+ return &net->dev_name_head[hash & ((1 << NETDEV_HASHBITS) - 1)];
+}
+
+static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex)
+{
+ return &net->dev_index_head[ifindex & ((1 << NETDEV_HASHBITS) - 1)];
+}
+
+/* Device list insertion */
+static int list_netdevice(struct net_device *dev)
+{
+ struct net *net = dev_net(dev);
+
+ ASSERT_RTNL();
+
+ write_lock_bh(&dev_base_lock);
+ list_add_tail(&dev->dev_list, &net->dev_base_head);
+ hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name));
+ hlist_add_head(&dev->index_hlist, dev_index_hash(net, dev->ifindex));
+ write_unlock_bh(&dev_base_lock);
+ return 0;
}
-static inline struct hlist_head *dev_index_hash(int ifindex)
+/* Device list removal */
+static void unlist_netdevice(struct net_device *dev)
{
- return &dev_index_head[ifindex & ((1<<NETDEV_HASHBITS)-1)];
+ ASSERT_RTNL();
+
+ /* Unlink dev from the device chain */
+ write_lock_bh(&dev_base_lock);
+ list_del(&dev->dev_list);
+ hlist_del(&dev->name_hlist);
+ hlist_del(&dev->index_hlist);
+ write_unlock_bh(&dev_base_lock);
}
/*
* Device drivers call our routines to queue packets here. We empty the
* queue in the local softnet handler.
*/
-DEFINE_PER_CPU(struct softnet_data, softnet_data) = { NULL };
-#ifdef CONFIG_SYSFS
-extern int netdev_sysfs_init(void);
-extern int netdev_register_sysfs(struct net_device *);
-extern void netdev_unregister_sysfs(struct net_device *);
-#else
-#define netdev_sysfs_init() (0)
-#define netdev_register_sysfs(dev) (0)
-#define netdev_unregister_sysfs(dev) do { } while(0)
-#endif
+DEFINE_PER_CPU(struct softnet_data, softnet_data);
+EXPORT_PER_CPU_SYMBOL(softnet_data);
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#ifdef CONFIG_LOCKDEP
/*
- * register_netdevice() inits dev->_xmit_lock and sets lockdep class
+ * register_netdevice() inits txq->_xmit_lock and sets lockdep class
* according to dev->type
*/
static const unsigned short netdev_lock_type[] =
ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
ARPHRD_FCFABRIC, ARPHRD_IEEE802_TR, ARPHRD_IEEE80211,
- ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_VOID,
- ARPHRD_NONE};
+ ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET,
+ ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154,
+ ARPHRD_VOID, ARPHRD_NONE};
-static const char *netdev_lock_name[] =
+static const char *const netdev_lock_name[] =
{"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
"_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
"_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
"_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
"_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
"_xmit_FCFABRIC", "_xmit_IEEE802_TR", "_xmit_IEEE80211",
- "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_VOID",
- "_xmit_NONE"};
+ "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET",
+ "_xmit_PHONET_PIPE", "_xmit_IEEE802154",
+ "_xmit_VOID", "_xmit_NONE"};
static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
+static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
static inline unsigned short netdev_lock_pos(unsigned short dev_type)
{
return ARRAY_SIZE(netdev_lock_type) - 1;
}
-static inline void netdev_set_lockdep_class(spinlock_t *lock,
- unsigned short dev_type)
+static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
+ unsigned short dev_type)
{
int i;
lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i],
netdev_lock_name[i]);
}
+
+static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
+{
+ int i;
+
+ i = netdev_lock_pos(dev->type);
+ lockdep_set_class_and_name(&dev->addr_list_lock,
+ &netdev_addr_lock_key[i],
+ netdev_lock_name[i]);
+}
#else
-static inline void netdev_set_lockdep_class(spinlock_t *lock,
- unsigned short dev_type)
+static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
+ unsigned short dev_type)
+{
+}
+static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
{
}
#endif
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);
}
+EXPORT_SYMBOL(dev_add_pack);
/**
* __dev_remove_pack - remove packet handler
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) {
out:
spin_unlock_bh(&ptype_lock);
}
+EXPORT_SYMBOL(__dev_remove_pack);
+
/**
* dev_remove_pack - remove packet handler
* @pt: packet type declaration
synchronize_net();
}
+EXPORT_SYMBOL(dev_remove_pack);
/******************************************************************************
for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
if (s[i].name[0] == '\0' || s[i].name[0] == ' ') {
memset(s[i].name, 0, sizeof(s[i].name));
- strcpy(s[i].name, name);
+ strlcpy(s[i].name, name, IFNAMSIZ);
memcpy(&s[i].map, map, sizeof(s[i].map));
break;
}
for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
if (s[i].name[0] != '\0' && s[i].name[0] != ' ' &&
- !strncmp(dev->name, s[i].name, strlen(s[i].name))) {
+ !strcmp(dev->name, s[i].name)) {
dev->irq = s[i].map.irq;
dev->base_addr = s[i].map.base_addr;
dev->mem_start = s[i].map.mem_start;
}
return 0;
}
+EXPORT_SYMBOL(netdev_boot_setup_check);
/**
* If device already registered then return base of 1
* to indicate not to probe for this interface
*/
- if (__dev_get_by_name(name))
+ if (__dev_get_by_name(&init_net, name))
return 1;
for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++)
/**
* __dev_get_by_name - find a device by its name
+ * @net: the applicable net namespace
* @name: name to find
*
* Find an interface by name. Must be called under RTNL semaphore
* careful with locks.
*/
-struct net_device *__dev_get_by_name(const char *name)
+struct net_device *__dev_get_by_name(struct net *net, const char *name)
{
struct hlist_node *p;
- hlist_for_each(p, dev_name_hash(name)) {
+ hlist_for_each(p, dev_name_hash(net, name)) {
struct net_device *dev
= hlist_entry(p, struct net_device, name_hlist);
if (!strncmp(dev->name, name, IFNAMSIZ))
}
return NULL;
}
+EXPORT_SYMBOL(__dev_get_by_name);
/**
* dev_get_by_name - find a device by its name
+ * @net: the applicable net namespace
* @name: name to find
*
* Find an interface by name. This can be called from any
* matching device is found.
*/
-struct net_device *dev_get_by_name(const char *name)
+struct net_device *dev_get_by_name(struct net *net, const char *name)
{
struct net_device *dev;
read_lock(&dev_base_lock);
- dev = __dev_get_by_name(name);
+ dev = __dev_get_by_name(net, name);
if (dev)
dev_hold(dev);
read_unlock(&dev_base_lock);
return dev;
}
+EXPORT_SYMBOL(dev_get_by_name);
/**
* __dev_get_by_index - find a device by its ifindex
+ * @net: the applicable net namespace
* @ifindex: index of device
*
* Search for an interface by index. Returns %NULL if the device
* or @dev_base_lock.
*/
-struct net_device *__dev_get_by_index(int ifindex)
+struct net_device *__dev_get_by_index(struct net *net, int ifindex)
{
struct hlist_node *p;
- hlist_for_each(p, dev_index_hash(ifindex)) {
+ hlist_for_each(p, dev_index_hash(net, ifindex)) {
struct net_device *dev
= hlist_entry(p, struct net_device, index_hlist);
if (dev->ifindex == ifindex)
}
return NULL;
}
+EXPORT_SYMBOL(__dev_get_by_index);
/**
* dev_get_by_index - find a device by its ifindex
+ * @net: the applicable net namespace
* @ifindex: index of device
*
* Search for an interface by index. Returns NULL if the device
* dev_put to indicate they have finished with it.
*/
-struct net_device *dev_get_by_index(int ifindex)
+struct net_device *dev_get_by_index(struct net *net, int ifindex)
{
struct net_device *dev;
read_lock(&dev_base_lock);
- dev = __dev_get_by_index(ifindex);
+ dev = __dev_get_by_index(net, ifindex);
if (dev)
dev_hold(dev);
read_unlock(&dev_base_lock);
return dev;
}
+EXPORT_SYMBOL(dev_get_by_index);
/**
* dev_getbyhwaddr - find a device by its hardware address
+ * @net: the applicable net namespace
* @type: media type of device
* @ha: hardware address
*
* If the API was consistent this would be __dev_get_by_hwaddr
*/
-struct net_device *dev_getbyhwaddr(unsigned short type, char *ha)
+struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, char *ha)
{
struct net_device *dev;
ASSERT_RTNL();
- for_each_netdev(dev)
+ for_each_netdev(net, dev)
if (dev->type == type &&
!memcmp(dev->dev_addr, ha, dev->addr_len))
return dev;
return NULL;
}
-
EXPORT_SYMBOL(dev_getbyhwaddr);
-struct net_device *__dev_getfirstbyhwtype(unsigned short type)
+struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type)
{
struct net_device *dev;
ASSERT_RTNL();
- for_each_netdev(dev)
+ for_each_netdev(net, dev)
if (dev->type == type)
return dev;
return NULL;
}
-
EXPORT_SYMBOL(__dev_getfirstbyhwtype);
-struct net_device *dev_getfirstbyhwtype(unsigned short type)
+struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
{
struct net_device *dev;
rtnl_lock();
- dev = __dev_getfirstbyhwtype(type);
+ dev = __dev_getfirstbyhwtype(net, type);
if (dev)
dev_hold(dev);
rtnl_unlock();
return dev;
}
-
EXPORT_SYMBOL(dev_getfirstbyhwtype);
/**
* dev_get_by_flags - find any device with given flags
+ * @net: the applicable net namespace
* @if_flags: IFF_* values
* @mask: bitmask of bits in if_flags to check
*
* dev_put to indicate they have finished with it.
*/
-struct net_device * dev_get_by_flags(unsigned short if_flags, unsigned short mask)
+struct net_device *dev_get_by_flags(struct net *net, unsigned short if_flags,
+ unsigned short mask)
{
struct net_device *dev, *ret;
ret = NULL;
read_lock(&dev_base_lock);
- for_each_netdev(dev) {
+ for_each_netdev(net, dev) {
if (((dev->flags ^ if_flags) & mask) == 0) {
dev_hold(dev);
ret = dev;
read_unlock(&dev_base_lock);
return ret;
}
+EXPORT_SYMBOL(dev_get_by_flags);
/**
* dev_valid_name - check if name is okay for network device
}
return 1;
}
+EXPORT_SYMBOL(dev_valid_name);
/**
- * dev_alloc_name - allocate a name for a device
- * @dev: device
+ * __dev_alloc_name - allocate a name for a device
+ * @net: network namespace to allocate the device name in
* @name: name format string
+ * @buf: scratch buffer and result name string
*
* Passed a format string - eg "lt%d" it will try and find a suitable
* id. It scans list of devices to build up a free map, then chooses
* Returns the number of the unit assigned or a negative errno code.
*/
-int dev_alloc_name(struct net_device *dev, const char *name)
+static int __dev_alloc_name(struct net *net, const char *name, char *buf)
{
int i = 0;
- char buf[IFNAMSIZ];
const char *p;
const int max_netdevices = 8*PAGE_SIZE;
- long *inuse;
+ unsigned long *inuse;
struct net_device *d;
p = strnchr(name, IFNAMSIZ-1, '%');
return -EINVAL;
/* Use one page as a bit array of possible slots */
- inuse = (long *) get_zeroed_page(GFP_ATOMIC);
+ inuse = (unsigned long *) get_zeroed_page(GFP_ATOMIC);
if (!inuse)
return -ENOMEM;
- for_each_netdev(d) {
+ for_each_netdev(net, d) {
if (!sscanf(d->name, name, &i))
continue;
if (i < 0 || i >= max_netdevices)
continue;
/* avoid cases where sscanf is not exact inverse of printf */
- snprintf(buf, sizeof(buf), name, i);
+ snprintf(buf, IFNAMSIZ, name, i);
if (!strncmp(buf, d->name, IFNAMSIZ))
set_bit(i, inuse);
}
free_page((unsigned long) inuse);
}
- snprintf(buf, sizeof(buf), name, i);
- if (!__dev_get_by_name(buf)) {
- strlcpy(dev->name, buf, IFNAMSIZ);
+ snprintf(buf, IFNAMSIZ, name, i);
+ if (!__dev_get_by_name(net, buf))
return i;
- }
/* It is possible to run out of possible slots
* when the name is long and there isn't enough space left
return -ENFILE;
}
+/**
+ * dev_alloc_name - allocate a name for a device
+ * @dev: device
+ * @name: name format string
+ *
+ * Passed a format string - eg "lt%d" it will try and find a suitable
+ * id. It scans list of devices to build up a free map, then chooses
+ * the first empty slot. The caller must hold the dev_base or rtnl lock
+ * while allocating the name and adding the device in order to avoid
+ * duplicates.
+ * Limited to bits_per_byte * page size devices (ie 32K on most platforms).
+ * Returns the number of the unit assigned or a negative errno code.
+ */
+
+int dev_alloc_name(struct net_device *dev, const char *name)
+{
+ char buf[IFNAMSIZ];
+ struct net *net;
+ int ret;
+
+ BUG_ON(!dev_net(dev));
+ net = dev_net(dev);
+ ret = __dev_alloc_name(net, name, buf);
+ if (ret >= 0)
+ strlcpy(dev->name, buf, IFNAMSIZ);
+ return ret;
+}
+EXPORT_SYMBOL(dev_alloc_name);
+
/**
* dev_change_name - change name of a device
* Change name of a device, can pass format strings "eth%d".
* for wildcarding.
*/
-int dev_change_name(struct net_device *dev, char *newname)
+int dev_change_name(struct net_device *dev, const char *newname)
{
+ char oldname[IFNAMSIZ];
int err = 0;
+ int ret;
+ struct net *net;
ASSERT_RTNL();
+ BUG_ON(!dev_net(dev));
+ net = dev_net(dev);
if (dev->flags & IFF_UP)
return -EBUSY;
if (!dev_valid_name(newname))
return -EINVAL;
+ if (strncmp(newname, dev->name, IFNAMSIZ) == 0)
+ return 0;
+
+ memcpy(oldname, dev->name, IFNAMSIZ);
+
if (strchr(newname, '%')) {
err = dev_alloc_name(dev, newname);
if (err < 0)
return err;
- strcpy(newname, dev->name);
- }
- else if (__dev_get_by_name(newname))
+ } else if (__dev_get_by_name(net, newname))
return -EEXIST;
else
strlcpy(dev->name, newname, IFNAMSIZ);
- device_rename(&dev->dev, dev->name);
+rollback:
+ /* For now only devices in the initial network namespace
+ * are in sysfs.
+ */
+ if (net == &init_net) {
+ ret = device_rename(&dev->dev, dev->name);
+ if (ret) {
+ memcpy(dev->name, oldname, IFNAMSIZ);
+ return ret;
+ }
+ }
+
+ write_lock_bh(&dev_base_lock);
hlist_del(&dev->name_hlist);
- hlist_add_head(&dev->name_hlist, dev_name_hash(dev->name));
- raw_notifier_call_chain(&netdev_chain, NETDEV_CHANGENAME, dev);
+ hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name));
+ write_unlock_bh(&dev_base_lock);
+
+ ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev);
+ ret = notifier_to_errno(ret);
+
+ if (ret) {
+ /* err >= 0 after dev_alloc_name() or stores the first errno */
+ if (err >= 0) {
+ err = ret;
+ memcpy(dev->name, oldname, IFNAMSIZ);
+ goto rollback;
+ } else {
+ printk(KERN_ERR
+ "%s: name change rollback failed: %d.\n",
+ dev->name, ret);
+ }
+ }
return err;
}
/**
+ * dev_set_alias - change ifalias of a device
+ * @dev: device
+ * @alias: name up to IFALIASZ
+ * @len: limit of bytes to copy from info
+ *
+ * Set ifalias for a device,
+ */
+int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
+{
+ ASSERT_RTNL();
+
+ if (len >= IFALIASZ)
+ return -EINVAL;
+
+ if (!len) {
+ if (dev->ifalias) {
+ kfree(dev->ifalias);
+ dev->ifalias = NULL;
+ }
+ return 0;
+ }
+
+ dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
+ if (!dev->ifalias)
+ return -ENOMEM;
+
+ strlcpy(dev->ifalias, alias, len+1);
+ return len;
+}
+
+
+/**
* netdev_features_change - device changes features
* @dev: device to cause notification
*
*/
void netdev_features_change(struct net_device *dev)
{
- raw_notifier_call_chain(&netdev_chain, NETDEV_FEAT_CHANGE, dev);
+ call_netdevice_notifiers(NETDEV_FEAT_CHANGE, dev);
}
EXPORT_SYMBOL(netdev_features_change);
void netdev_state_change(struct net_device *dev)
{
if (dev->flags & IFF_UP) {
- raw_notifier_call_chain(&netdev_chain,
- NETDEV_CHANGE, dev);
+ call_netdevice_notifiers(NETDEV_CHANGE, dev);
rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
}
}
+EXPORT_SYMBOL(netdev_state_change);
+
+void netdev_bonding_change(struct net_device *dev, unsigned long event)
+{
+ call_netdevice_notifiers(event, dev);
+}
+EXPORT_SYMBOL(netdev_bonding_change);
/**
* dev_load - load a network module
+ * @net: the applicable net namespace
* @name: name of interface
*
* If a network interface is not present and the process has suitable
* available in this kernel then it becomes a nop.
*/
-void dev_load(const char *name)
+void dev_load(struct net *net, const char *name)
{
struct net_device *dev;
read_lock(&dev_base_lock);
- dev = __dev_get_by_name(name);
+ dev = __dev_get_by_name(net, name);
read_unlock(&dev_base_lock);
- if (!dev && capable(CAP_SYS_MODULE))
+ if (!dev && capable(CAP_NET_ADMIN))
request_module("%s", name);
}
-
-static int default_rebuild_header(struct sk_buff *skb)
-{
- printk(KERN_DEBUG "%s: default_rebuild_header called -- BUG!\n",
- skb->dev ? skb->dev->name : "NULL!!!");
- kfree_skb(skb);
- return 1;
-}
+EXPORT_SYMBOL(dev_load);
/**
* dev_open - prepare an interface for use.
*/
int dev_open(struct net_device *dev)
{
- int ret = 0;
+ const struct net_device_ops *ops = dev->netdev_ops;
+ int ret;
+
+ ASSERT_RTNL();
/*
* Is it already up?
if (!netif_device_present(dev))
return -ENODEV;
+ ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
+ ret = notifier_to_errno(ret);
+ if (ret)
+ return ret;
+
/*
* Call device private open method
*/
set_bit(__LINK_STATE_START, &dev->state);
- if (dev->open) {
- ret = dev->open(dev);
- if (ret)
- clear_bit(__LINK_STATE_START, &dev->state);
- }
+
+ if (ops->ndo_validate_addr)
+ ret = ops->ndo_validate_addr(dev);
+
+ if (!ret && ops->ndo_open)
+ ret = ops->ndo_open(dev);
/*
* If it went open OK then:
*/
- if (!ret) {
+ if (ret)
+ clear_bit(__LINK_STATE_START, &dev->state);
+ else {
/*
* Set the flags.
*/
dev->flags |= IFF_UP;
/*
+ * Enable NET_DMA
+ */
+ net_dmaengine_get();
+
+ /*
* Initialize multicasting status
*/
- dev_mc_upload(dev);
+ dev_set_rx_mode(dev);
/*
* Wakeup transmit queue engine
/*
* ... and announce new interface.
*/
- raw_notifier_call_chain(&netdev_chain, NETDEV_UP, dev);
+ call_netdevice_notifiers(NETDEV_UP, dev);
}
+
return ret;
}
+EXPORT_SYMBOL(dev_open);
/**
* dev_close - shutdown an interface.
*/
int dev_close(struct net_device *dev)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ ASSERT_RTNL();
+
+ might_sleep();
+
if (!(dev->flags & IFF_UP))
return 0;
* Tell people we are going down, so that they can
* prepare to death, when device is still operating.
*/
- raw_notifier_call_chain(&netdev_chain, NETDEV_GOING_DOWN, dev);
-
- dev_deactivate(dev);
+ call_netdevice_notifiers(NETDEV_GOING_DOWN, dev);
clear_bit(__LINK_STATE_START, &dev->state);
/* Synchronize to scheduled poll. We cannot touch poll list,
- * it can be even on different cpu. So just clear netif_running(),
- * and wait when poll really will happen. Actually, the best place
- * for this is inside dev->stop() after device stopped its irq
- * engine, but this requires more changes in devices. */
-
+ * it can be even on different cpu. So just clear netif_running().
+ *
+ * dev->stop() will invoke napi_disable() on all of it's
+ * napi_struct instances on this device.
+ */
smp_mb__after_clear_bit(); /* Commit netif_running(). */
- while (test_bit(__LINK_STATE_RX_SCHED, &dev->state)) {
- /* No hurry. */
- msleep(1);
- }
+
+ dev_deactivate(dev);
/*
* Call the device specific close. This cannot fail.
* We allow it to be called even after a DETACH hot-plug
* event.
*/
- if (dev->stop)
- dev->stop(dev);
+ if (ops->ndo_stop)
+ ops->ndo_stop(dev);
/*
* Device is now down.
/*
* Tell people we are down
*/
- raw_notifier_call_chain(&netdev_chain, NETDEV_DOWN, dev);
+ call_netdevice_notifiers(NETDEV_DOWN, dev);
+
+ /*
+ * Shutdown NET_DMA
+ */
+ net_dmaengine_put();
return 0;
}
+EXPORT_SYMBOL(dev_close);
+
+
+/**
+ * dev_disable_lro - disable Large Receive Offload on a device
+ * @dev: device
+ *
+ * Disable Large Receive Offload (LRO) on a net device. Must be
+ * called under RTNL. This is needed if received packets may be
+ * forwarded to another interface.
+ */
+void dev_disable_lro(struct net_device *dev)
+{
+ if (dev->ethtool_ops && dev->ethtool_ops->get_flags &&
+ dev->ethtool_ops->set_flags) {
+ u32 flags = dev->ethtool_ops->get_flags(dev);
+ if (flags & ETH_FLAG_LRO) {
+ flags &= ~ETH_FLAG_LRO;
+ dev->ethtool_ops->set_flags(dev, flags);
+ }
+ }
+ WARN_ON(dev->features & NETIF_F_LRO);
+}
+EXPORT_SYMBOL(dev_disable_lro);
+static int dev_boot_phase = 1;
+
/*
* Device change register/unregister. These are not inline or static
* as we export them to the world.
int register_netdevice_notifier(struct notifier_block *nb)
{
struct net_device *dev;
+ struct net_device *last;
+ struct net *net;
int err;
rtnl_lock();
err = raw_notifier_chain_register(&netdev_chain, nb);
- if (!err) {
- for_each_netdev(dev) {
- nb->notifier_call(nb, NETDEV_REGISTER, dev);
+ if (err)
+ goto unlock;
+ if (dev_boot_phase)
+ goto unlock;
+ for_each_net(net) {
+ for_each_netdev(net, dev) {
+ err = nb->notifier_call(nb, NETDEV_REGISTER, dev);
+ err = notifier_to_errno(err);
+ if (err)
+ goto rollback;
+
+ if (!(dev->flags & IFF_UP))
+ continue;
- if (dev->flags & IFF_UP)
- nb->notifier_call(nb, NETDEV_UP, dev);
+ nb->notifier_call(nb, NETDEV_UP, dev);
}
}
+
+unlock:
rtnl_unlock();
return err;
+
+rollback:
+ last = dev;
+ for_each_net(net) {
+ for_each_netdev(net, dev) {
+ if (dev == last)
+ break;
+
+ if (dev->flags & IFF_UP) {
+ nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
+ nb->notifier_call(nb, NETDEV_DOWN, dev);
+ }
+ nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+ }
+ }
+
+ raw_notifier_chain_unregister(&netdev_chain, nb);
+ goto unlock;
}
+EXPORT_SYMBOL(register_netdevice_notifier);
/**
* unregister_netdevice_notifier - unregister a network notifier block
rtnl_unlock();
return err;
}
+EXPORT_SYMBOL(unregister_netdevice_notifier);
/**
* call_netdevice_notifiers - call all network notifier blocks
* @val: value passed unmodified to notifier function
- * @v: pointer passed unmodified to notifier function
+ * @dev: net_device pointer passed unmodified to notifier function
*
* Call all network notifier blocks. Parameters and return value
* are as for raw_notifier_call_chain().
*/
-int call_netdevice_notifiers(unsigned long val, void *v)
+int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
{
- return raw_notifier_call_chain(&netdev_chain, val, v);
+ return raw_notifier_call_chain(&netdev_chain, val, dev);
}
/* When > 0 there are consumers of rx skb time stamps */
{
atomic_inc(&netstamp_needed);
}
+EXPORT_SYMBOL(net_enable_timestamp);
void net_disable_timestamp(void)
{
atomic_dec(&netstamp_needed);
}
+EXPORT_SYMBOL(net_disable_timestamp);
static inline void net_timestamp(struct sk_buff *skb)
{
{
struct packet_type *ptype;
+#ifdef CONFIG_NET_CLS_ACT
+ if (!(skb->tstamp.tv64 && (G_TC_FROM(skb->tc_verd) & AT_INGRESS)))
+ net_timestamp(skb);
+#else
net_timestamp(skb);
+#endif
rcu_read_lock();
list_for_each_entry_rcu(ptype, &ptype_all, list) {
if ((ptype->dev == dev || !ptype->dev) &&
(ptype->af_packet_priv == NULL ||
(struct sock *)ptype->af_packet_priv != skb->sk)) {
- struct sk_buff *skb2= skb_clone(skb, GFP_ATOMIC);
+ struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
break;
}
-void __netif_schedule(struct net_device *dev)
+static inline void __netif_reschedule(struct Qdisc *q)
{
- if (!test_and_set_bit(__LINK_STATE_SCHED, &dev->state)) {
- unsigned long flags;
+ struct softnet_data *sd;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ sd = &__get_cpu_var(softnet_data);
+ q->next_sched = sd->output_queue;
+ sd->output_queue = q;
+ raise_softirq_irqoff(NET_TX_SOFTIRQ);
+ local_irq_restore(flags);
+}
+
+void __netif_schedule(struct Qdisc *q)
+{
+ if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state))
+ __netif_reschedule(q);
+}
+EXPORT_SYMBOL(__netif_schedule);
+
+void dev_kfree_skb_irq(struct sk_buff *skb)
+{
+ if (atomic_dec_and_test(&skb->users)) {
struct softnet_data *sd;
+ unsigned long flags;
local_irq_save(flags);
sd = &__get_cpu_var(softnet_data);
- dev->next_sched = sd->output_queue;
- sd->output_queue = dev;
+ skb->next = sd->completion_queue;
+ sd->completion_queue = skb;
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_restore(flags);
}
}
-EXPORT_SYMBOL(__netif_schedule);
-
-void __netif_rx_schedule(struct net_device *dev)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- dev_hold(dev);
- list_add_tail(&dev->poll_list, &__get_cpu_var(softnet_data).poll_list);
- if (dev->quota < 0)
- dev->quota += dev->weight;
- else
- dev->quota = dev->weight;
- __raise_softirq_irqoff(NET_RX_SOFTIRQ);
- local_irq_restore(flags);
-}
-EXPORT_SYMBOL(__netif_rx_schedule);
+EXPORT_SYMBOL(dev_kfree_skb_irq);
void dev_kfree_skb_any(struct sk_buff *skb)
{
EXPORT_SYMBOL(dev_kfree_skb_any);
-/* Hot-plugging. */
+/**
+ * netif_device_detach - mark device as removed
+ * @dev: network device
+ *
+ * Mark device as removed from system and therefore no longer available.
+ */
void netif_device_detach(struct net_device *dev)
{
if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) &&
netif_running(dev)) {
- netif_stop_queue(dev);
+ netif_tx_stop_all_queues(dev);
}
}
EXPORT_SYMBOL(netif_device_detach);
+/**
+ * netif_device_attach - mark device as attached
+ * @dev: network device
+ *
+ * Mark device as attached from system and restart if needed.
+ */
void netif_device_attach(struct net_device *dev)
{
if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) &&
netif_running(dev)) {
- netif_wake_queue(dev);
+ netif_tx_wake_all_queues(dev);
__netdev_watchdog_up(dev);
}
}
EXPORT_SYMBOL(netif_device_attach);
+static bool can_checksum_protocol(unsigned long features, __be16 protocol)
+{
+ return ((features & NETIF_F_GEN_CSUM) ||
+ ((features & NETIF_F_IP_CSUM) &&
+ protocol == htons(ETH_P_IP)) ||
+ ((features & NETIF_F_IPV6_CSUM) &&
+ protocol == htons(ETH_P_IPV6)) ||
+ ((features & NETIF_F_FCOE_CRC) &&
+ protocol == htons(ETH_P_FCOE)));
+}
+
+static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb)
+{
+ if (can_checksum_protocol(dev->features, skb->protocol))
+ return true;
+
+ if (skb->protocol == htons(ETH_P_8021Q)) {
+ struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
+ if (can_checksum_protocol(dev->features & dev->vlan_features,
+ veh->h_vlan_encapsulated_proto))
+ return true;
+ }
+
+ return false;
+}
/*
* Invalidate hardware checksum when packet is to be mangled, and
goto out_set_summed;
}
- if (skb_cloned(skb)) {
+ offset = skb->csum_start - skb_headroom(skb);
+ BUG_ON(offset >= skb_headlen(skb));
+ csum = skb_checksum(skb, offset, skb->len - offset, 0);
+
+ offset += skb->csum_offset;
+ BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb));
+
+ if (skb_cloned(skb) &&
+ !skb_clone_writable(skb, offset + sizeof(__sum16))) {
ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
if (ret)
goto out;
}
- offset = skb->csum_start - skb_headroom(skb);
- BUG_ON(offset > (int)skb->len);
- csum = skb_checksum(skb, offset, skb->len-offset, 0);
-
- offset = skb_headlen(skb) - offset;
- BUG_ON(offset <= 0);
- BUG_ON(skb->csum_offset + 2 > offset);
-
- *(__sum16 *)(skb->head + skb->csum_start + skb->csum_offset) =
- csum_fold(csum);
+ *(__sum16 *)(skb->data + offset) = csum_fold(csum);
out_set_summed:
skb->ip_summed = CHECKSUM_NONE;
out:
return ret;
}
+EXPORT_SYMBOL(skb_checksum_help);
/**
* skb_gso_segment - Perform segmentation on skb.
__be16 type = skb->protocol;
int err;
- BUG_ON(skb_shinfo(skb)->frag_list);
-
skb_reset_mac_header(skb);
skb->mac_len = skb->network_header - skb->mac_header;
__skb_pull(skb, skb->mac_len);
- if (WARN_ON(skb->ip_summed != CHECKSUM_PARTIAL)) {
+ if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
+ struct net_device *dev = skb->dev;
+ struct ethtool_drvinfo info = {};
+
+ if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo)
+ dev->ethtool_ops->get_drvinfo(dev, &info);
+
+ WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d "
+ "ip_summed=%d",
+ info.driver, dev ? dev->features : 0L,
+ skb->sk ? skb->sk->sk_route_caps : 0L,
+ skb->len, skb->data_len, skb->ip_summed);
+
if (skb_header_cloned(skb) &&
(err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
return ERR_PTR(err);
}
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 segs;
}
-
EXPORT_SYMBOL(skb_gso_segment);
/* Take action when hardware reception checksum errors are detected. */
if (!segs)
return 0;
- if (unlikely(IS_ERR(segs)))
+ if (IS_ERR(segs))
return PTR_ERR(segs);
skb->next = segs;
return 0;
}
-int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
+int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
+ struct netdev_queue *txq)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ int rc;
+
if (likely(!skb->next)) {
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(skb, dev);
goto gso;
}
- return dev->hard_start_xmit(skb, dev);
+ /*
+ * If device doesnt need skb->dst, release it right now while
+ * its hot in this cpu cache
+ */
+ if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
+ skb_dst_drop(skb);
+
+ rc = ops->ndo_start_xmit(skb, dev);
+ if (rc == NETDEV_TX_OK)
+ txq_trans_update(txq);
+ /*
+ * TODO: if skb_orphan() was called by
+ * dev->hard_start_xmit() (for example, the unmodified
+ * igb driver does that; bnx2 doesn't), then
+ * skb_tx_software_timestamp() will be unable to send
+ * back the time stamp.
+ *
+ * How can this be prevented? Always create another
+ * reference to the socket before calling
+ * dev->hard_start_xmit()? Prevent that skb_orphan()
+ * does anything in dev->hard_start_xmit() by clearing
+ * the skb destructor before the call and restoring it
+ * afterwards, then doing the skb_orphan() ourselves?
+ */
+ return rc;
}
gso:
do {
struct sk_buff *nskb = skb->next;
- int rc;
skb->next = nskb->next;
nskb->next = NULL;
- rc = dev->hard_start_xmit(nskb, dev);
- if (unlikely(rc)) {
+ rc = ops->ndo_start_xmit(nskb, dev);
+ if (unlikely(rc != NETDEV_TX_OK)) {
nskb->next = skb->next;
skb->next = nskb;
return rc;
}
- if (unlikely(netif_queue_stopped(dev) && skb->next))
+ txq_trans_update(txq);
+ if (unlikely(netif_tx_queue_stopped(txq) && skb->next))
return NETDEV_TX_BUSY;
} while (skb->next);
out_kfree_skb:
kfree_skb(skb);
- return 0;
+ return NETDEV_TX_OK;
}
-#define HARD_TX_LOCK(dev, cpu) { \
- if ((dev->features & NETIF_F_LLTX) == 0) { \
- netif_tx_lock(dev); \
- } \
-}
+static u32 skb_tx_hashrnd;
-#define HARD_TX_UNLOCK(dev) { \
- if ((dev->features & NETIF_F_LLTX) == 0) { \
- netif_tx_unlock(dev); \
- } \
-}
+u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
+{
+ u32 hash;
-/**
- * dev_queue_xmit - transmit a buffer
- * @skb: buffer to transmit
- *
+ if (skb_rx_queue_recorded(skb)) {
+ hash = skb_get_rx_queue(skb);
+ while (unlikely(hash >= dev->real_num_tx_queues))
+ hash -= dev->real_num_tx_queues;
+ return hash;
+ }
+
+ if (skb->sk && skb->sk->sk_hash)
+ hash = skb->sk->sk_hash;
+ else
+ hash = skb->protocol;
+
+ hash = jhash_1word(hash, skb_tx_hashrnd);
+
+ return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32);
+}
+EXPORT_SYMBOL(skb_tx_hash);
+
+static struct netdev_queue *dev_pick_tx(struct net_device *dev,
+ struct sk_buff *skb)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ u16 queue_index = 0;
+
+ if (ops->ndo_select_queue)
+ queue_index = ops->ndo_select_queue(dev, skb);
+ else if (dev->real_num_tx_queues > 1)
+ queue_index = skb_tx_hash(dev, skb);
+
+ skb_set_queue_mapping(skb, queue_index);
+ return netdev_get_tx_queue(dev, queue_index);
+}
+
+static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
+ struct net_device *dev,
+ struct netdev_queue *txq)
+{
+ spinlock_t *root_lock = qdisc_lock(q);
+ int rc;
+
+ spin_lock(root_lock);
+ if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
+ kfree_skb(skb);
+ rc = NET_XMIT_DROP;
+ } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
+ !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) {
+ /*
+ * This is a work-conserving queue; there are no old skbs
+ * waiting to be sent out; and the qdisc is not running -
+ * xmit the skb directly.
+ */
+ __qdisc_update_bstats(q, skb->len);
+ if (sch_direct_xmit(skb, q, dev, txq, root_lock))
+ __qdisc_run(q);
+ else
+ clear_bit(__QDISC_STATE_RUNNING, &q->state);
+
+ rc = NET_XMIT_SUCCESS;
+ } else {
+ rc = qdisc_enqueue_root(skb, q);
+ qdisc_run(q);
+ }
+ spin_unlock(root_lock);
+
+ return rc;
+}
+
+/**
+ * dev_queue_xmit - transmit a buffer
+ * @skb: buffer to transmit
+ *
* Queue a buffer for transmission to a network device. The caller must
* have set the device and priority and built the buffer before calling
* this function. The function can be called from an interrupt.
* the BH enable code must have IRQs enabled so that it will not deadlock.
* --BLG
*/
-
int dev_queue_xmit(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
+ struct netdev_queue *txq;
struct Qdisc *q;
int rc = -ENOMEM;
if (netif_needs_gso(dev, skb))
goto gso;
- if (skb_shinfo(skb)->frag_list &&
+ if (skb_has_frags(skb) &&
!(dev->features & NETIF_F_FRAGLIST) &&
__skb_linearize(skb))
goto out_kfree_skb;
if (skb->ip_summed == CHECKSUM_PARTIAL) {
skb_set_transport_header(skb, skb->csum_start -
skb_headroom(skb));
-
- if (!(dev->features & NETIF_F_GEN_CSUM) &&
- (!(dev->features & NETIF_F_IP_CSUM) ||
- skb->protocol != htons(ETH_P_IP)))
- if (skb_checksum_help(skb))
- goto out_kfree_skb;
+ if (!dev_can_checksum(dev, skb) && skb_checksum_help(skb))
+ goto out_kfree_skb;
}
gso:
- spin_lock_prefetch(&dev->queue_lock);
-
/* Disable soft irqs for various locks below. Also
* stops preemption for RCU.
*/
rcu_read_lock_bh();
- /* Updates of qdisc are serialized by queue_lock.
- * The struct Qdisc which is pointed to by qdisc is now a
- * rcu structure - it may be accessed without acquiring
- * a lock (but the structure may be stale.) The freeing of the
- * qdisc will be deferred until it's known that there are no
- * more references to it.
- *
- * If the qdisc has an enqueue function, we still need to
- * hold the queue_lock before calling it, since queue_lock
- * also serializes access to the device queue.
- */
+ txq = dev_pick_tx(dev, skb);
+ q = rcu_dereference(txq->qdisc);
- q = rcu_dereference(dev->qdisc);
#ifdef CONFIG_NET_CLS_ACT
- skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS);
+ skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS);
#endif
if (q->enqueue) {
- /* Grab device queue */
- spin_lock(&dev->queue_lock);
- q = dev->qdisc;
- if (q->enqueue) {
- rc = q->enqueue(skb, q);
- qdisc_run(dev);
- spin_unlock(&dev->queue_lock);
-
- rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc;
- goto out;
- }
- spin_unlock(&dev->queue_lock);
+ rc = __dev_xmit_skb(skb, q, dev, txq);
+ goto out;
}
/* The device has no queue. Common case for software devices:
if (dev->flags & IFF_UP) {
int cpu = smp_processor_id(); /* ok because BHs are off */
- if (dev->xmit_lock_owner != cpu) {
+ if (txq->xmit_lock_owner != cpu) {
- HARD_TX_LOCK(dev, cpu);
+ HARD_TX_LOCK(dev, txq, cpu);
- if (!netif_queue_stopped(dev)) {
- rc = 0;
- if (!dev_hard_start_xmit(skb, dev)) {
- HARD_TX_UNLOCK(dev);
+ if (!netif_tx_queue_stopped(txq)) {
+ rc = NET_XMIT_SUCCESS;
+ if (!dev_hard_start_xmit(skb, dev, txq)) {
+ HARD_TX_UNLOCK(dev, txq);
goto out;
}
}
- HARD_TX_UNLOCK(dev);
+ HARD_TX_UNLOCK(dev, txq);
if (net_ratelimit())
printk(KERN_CRIT "Virtual device %s asks to "
"queue packet!\n", dev->name);
rcu_read_unlock_bh();
return rc;
}
+EXPORT_SYMBOL(dev_queue_xmit);
/*=======================================================================
*
* 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)
*
*/
if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
if (queue->input_pkt_queue.qlen) {
enqueue:
- dev_hold(skb->dev);
__skb_queue_tail(&queue->input_pkt_queue, skb);
local_irq_restore(flags);
return NET_RX_SUCCESS;
}
- netif_rx_schedule(&queue->backlog_dev);
+ napi_schedule(&queue->backlog);
goto enqueue;
}
kfree_skb(skb);
return NET_RX_DROP;
}
+EXPORT_SYMBOL(netif_rx);
int netif_rx_ni(struct sk_buff *skb)
{
return err;
}
-
EXPORT_SYMBOL(netif_rx_ni);
-static inline struct net_device *skb_bond(struct sk_buff *skb)
-{
- struct net_device *dev = skb->dev;
-
- if (dev->master) {
- if (skb_bond_should_drop(skb)) {
- kfree_skb(skb);
- return NULL;
- }
- skb->dev = dev->master;
- }
-
- return dev;
-}
-
static void net_tx_action(struct softirq_action *h)
{
struct softnet_data *sd = &__get_cpu_var(softnet_data);
struct sk_buff *skb = clist;
clist = clist->next;
- BUG_TRAP(!atomic_read(&skb->users));
+ WARN_ON(atomic_read(&skb->users));
__kfree_skb(skb);
}
}
if (sd->output_queue) {
- struct net_device *head;
+ struct Qdisc *head;
local_irq_disable();
head = sd->output_queue;
local_irq_enable();
while (head) {
- struct net_device *dev = head;
- head = head->next_sched;
+ struct Qdisc *q = head;
+ spinlock_t *root_lock;
- smp_mb__before_clear_bit();
- clear_bit(__LINK_STATE_SCHED, &dev->state);
+ head = head->next_sched;
- if (spin_trylock(&dev->queue_lock)) {
- qdisc_run(dev);
- spin_unlock(&dev->queue_lock);
+ root_lock = qdisc_lock(q);
+ if (spin_trylock(root_lock)) {
+ smp_mb__before_clear_bit();
+ clear_bit(__QDISC_STATE_SCHED,
+ &q->state);
+ qdisc_run(q);
+ spin_unlock(root_lock);
} else {
- netif_schedule(dev);
+ if (!test_bit(__QDISC_STATE_DEACTIVATED,
+ &q->state)) {
+ __netif_reschedule(q);
+ } else {
+ smp_mb__before_clear_bit();
+ clear_bit(__QDISC_STATE_SCHED,
+ &q->state);
+ }
}
}
}
}
#if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE)
-/* These hooks defined here for ATM */
-struct net_bridge;
-struct net_bridge_fdb_entry *(*br_fdb_get_hook)(struct net_bridge *br,
- unsigned char *addr);
-void (*br_fdb_put_hook)(struct net_bridge_fdb_entry *ent) __read_mostly;
+
+#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
+/* This hook is defined here for ATM LANE */
+int (*br_fdb_test_addr_hook)(struct net_device *dev,
+ unsigned char *addr) __read_mostly;
+EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
+#endif
/*
* If bridge module is loaded call bridging hook.
*/
struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p,
struct sk_buff *skb) __read_mostly;
+EXPORT_SYMBOL_GPL(br_handle_frame_hook);
+
static inline struct sk_buff *handle_bridge(struct sk_buff *skb,
struct packet_type **pt_prev, int *ret,
struct net_device *orig_dev)
#define handle_bridge(skb, pt_prev, ret, orig_dev) (skb)
#endif
+#if defined(CONFIG_MACVLAN) || defined(CONFIG_MACVLAN_MODULE)
+struct sk_buff *(*macvlan_handle_frame_hook)(struct sk_buff *skb) __read_mostly;
+EXPORT_SYMBOL_GPL(macvlan_handle_frame_hook);
+
+static inline struct sk_buff *handle_macvlan(struct sk_buff *skb,
+ struct packet_type **pt_prev,
+ int *ret,
+ struct net_device *orig_dev)
+{
+ if (skb->dev->macvlan_port == NULL)
+ return skb;
+
+ if (*pt_prev) {
+ *ret = deliver_skb(skb, *pt_prev, orig_dev);
+ *pt_prev = NULL;
+ }
+ return macvlan_handle_frame_hook(skb);
+}
+#else
+#define handle_macvlan(skb, pt_prev, ret, orig_dev) (skb)
+#endif
+
#ifdef CONFIG_NET_CLS_ACT
/* TODO: Maybe we should just force sch_ingress to be compiled in
* when CONFIG_NET_CLS_ACT is? otherwise some useless instructions
*/
static int ing_filter(struct sk_buff *skb)
{
- struct Qdisc *q;
struct net_device *dev = skb->dev;
+ u32 ttl = G_TC_RTTL(skb->tc_verd);
+ struct netdev_queue *rxq;
int result = TC_ACT_OK;
+ struct Qdisc *q;
- if (dev->qdisc_ingress) {
- __u32 ttl = (__u32) G_TC_RTTL(skb->tc_verd);
- if (MAX_RED_LOOP < ttl++) {
- printk(KERN_WARNING "Redir loop detected Dropping packet (%d->%d)\n",
- skb->iif, skb->dev->ifindex);
- return TC_ACT_SHOT;
- }
-
- skb->tc_verd = SET_TC_RTTL(skb->tc_verd,ttl);
+ if (MAX_RED_LOOP < ttl++) {
+ printk(KERN_WARNING
+ "Redir loop detected Dropping packet (%d->%d)\n",
+ skb->iif, dev->ifindex);
+ return TC_ACT_SHOT;
+ }
- skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_INGRESS);
+ skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl);
+ skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
- spin_lock(&dev->ingress_lock);
- if ((q = dev->qdisc_ingress) != NULL)
- result = q->enqueue(skb, q);
- spin_unlock(&dev->ingress_lock);
+ rxq = &dev->rx_queue;
+ q = rxq->qdisc;
+ if (q != &noop_qdisc) {
+ spin_lock(qdisc_lock(q));
+ if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
+ result = qdisc_enqueue_root(skb, q);
+ spin_unlock(qdisc_lock(q));
}
return result;
}
+
+static inline struct sk_buff *handle_ing(struct sk_buff *skb,
+ struct packet_type **pt_prev,
+ int *ret, struct net_device *orig_dev)
+{
+ if (skb->dev->rx_queue.qdisc == &noop_qdisc)
+ goto out;
+
+ if (*pt_prev) {
+ *ret = deliver_skb(skb, *pt_prev, orig_dev);
+ *pt_prev = NULL;
+ } else {
+ /* Huh? Why does turning on AF_PACKET affect this? */
+ skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
+ }
+
+ switch (ing_filter(skb)) {
+ case TC_ACT_SHOT:
+ case TC_ACT_STOLEN:
+ kfree_skb(skb);
+ return NULL;
+ }
+
+out:
+ skb->tc_verd = 0;
+ return skb;
+}
#endif
+/*
+ * netif_nit_deliver - deliver received packets to network taps
+ * @skb: buffer
+ *
+ * This function is used to deliver incoming packets to network
+ * taps. It should be used when the normal netif_receive_skb path
+ * is bypassed, for example because of VLAN acceleration.
+ */
+void netif_nit_deliver(struct sk_buff *skb)
+{
+ struct packet_type *ptype;
+
+ if (list_empty(&ptype_all))
+ return;
+
+ skb_reset_network_header(skb);
+ skb_reset_transport_header(skb);
+ skb->mac_len = skb->network_header - skb->mac_header;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ptype, &ptype_all, list) {
+ if (!ptype->dev || ptype->dev == skb->dev)
+ deliver_skb(skb, ptype, skb->dev);
+ }
+ rcu_read_unlock();
+}
+
+/**
+ * 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;
struct net_device *orig_dev;
+ struct net_device *null_or_orig;
int ret = NET_RX_DROP;
__be16 type;
- /* if we've gotten here through NAPI, check netpoll */
- if (skb->dev->poll && netpoll_rx(skb))
- return NET_RX_DROP;
-
if (!skb->tstamp.tv64)
net_timestamp(skb);
+ if (skb->vlan_tci && vlan_hwaccel_do_receive(skb))
+ return NET_RX_SUCCESS;
+
+ /* if we've gotten here through NAPI, check netpoll */
+ if (netpoll_receive_skb(skb))
+ return NET_RX_DROP;
+
if (!skb->iif)
skb->iif = skb->dev->ifindex;
- orig_dev = skb_bond(skb);
-
- if (!orig_dev)
- return NET_RX_DROP;
+ null_or_orig = NULL;
+ orig_dev = skb->dev;
+ if (orig_dev->master) {
+ if (skb_bond_should_drop(skb))
+ null_or_orig = orig_dev; /* deliver only exact match */
+ else
+ skb->dev = orig_dev->master;
+ }
__get_cpu_var(netdev_rx_stat).total++;
#endif
list_for_each_entry_rcu(ptype, &ptype_all, list) {
- if (!ptype->dev || ptype->dev == skb->dev) {
+ if (ptype->dev == null_or_orig || ptype->dev == skb->dev ||
+ ptype->dev == orig_dev) {
if (pt_prev)
ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
}
#ifdef CONFIG_NET_CLS_ACT
- if (pt_prev) {
- ret = deliver_skb(skb, pt_prev, orig_dev);
- pt_prev = NULL; /* noone else should process this after*/
- } else {
- skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
- }
-
- ret = ing_filter(skb);
-
- if (ret == TC_ACT_SHOT || (ret == TC_ACT_STOLEN)) {
- kfree_skb(skb);
+ skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
+ if (!skb)
goto out;
- }
-
- skb->tc_verd = 0;
ncls:
#endif
skb = handle_bridge(skb, &pt_prev, &ret, orig_dev);
if (!skb)
goto out;
+ skb = handle_macvlan(skb, &pt_prev, &ret, orig_dev);
+ if (!skb)
+ 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)) {
+ (ptype->dev == null_or_orig || ptype->dev == skb->dev ||
+ ptype->dev == orig_dev)) {
if (pt_prev)
ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
rcu_read_unlock();
return ret;
}
+EXPORT_SYMBOL(netif_receive_skb);
-static int process_backlog(struct net_device *backlog_dev, int *budget)
+/* Network device is going away, flush any packets still pending */
+static void flush_backlog(void *arg)
{
- int work = 0;
- int quota = min(backlog_dev->quota, *budget);
+ struct net_device *dev = arg;
struct softnet_data *queue = &__get_cpu_var(softnet_data);
- unsigned long start_time = jiffies;
-
- backlog_dev->weight = weight_p;
- for (;;) {
- struct sk_buff *skb;
- struct net_device *dev;
-
- local_irq_disable();
- skb = __skb_dequeue(&queue->input_pkt_queue);
- if (!skb)
- goto job_done;
- local_irq_enable();
+ struct sk_buff *skb, *tmp;
- dev = skb->dev;
+ skb_queue_walk_safe(&queue->input_pkt_queue, skb, tmp)
+ if (skb->dev == dev) {
+ __skb_unlink(skb, &queue->input_pkt_queue);
+ kfree_skb(skb);
+ }
+}
- netif_receive_skb(skb);
+static int napi_gro_complete(struct sk_buff *skb)
+{
+ struct packet_type *ptype;
+ __be16 type = skb->protocol;
+ struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
+ int err = -ENOENT;
- dev_put(dev);
+ if (NAPI_GRO_CB(skb)->count == 1) {
+ skb_shinfo(skb)->gso_size = 0;
+ goto out;
+ }
- work++;
+ rcu_read_lock();
+ list_for_each_entry_rcu(ptype, head, list) {
+ if (ptype->type != type || ptype->dev || !ptype->gro_complete)
+ continue;
- if (work >= quota || jiffies - start_time > 1)
- break;
+ err = ptype->gro_complete(skb);
+ break;
+ }
+ rcu_read_unlock();
+ if (err) {
+ WARN_ON(&ptype->list == head);
+ kfree_skb(skb);
+ return NET_RX_SUCCESS;
}
- backlog_dev->quota -= work;
- *budget -= work;
- return -1;
+out:
+ return netif_receive_skb(skb);
+}
-job_done:
- backlog_dev->quota -= work;
- *budget -= work;
+void napi_gro_flush(struct napi_struct *napi)
+{
+ struct sk_buff *skb, *next;
- list_del(&backlog_dev->poll_list);
- smp_mb__before_clear_bit();
- netif_poll_enable(backlog_dev);
+ for (skb = napi->gro_list; skb; skb = next) {
+ next = skb->next;
+ skb->next = NULL;
+ napi_gro_complete(skb);
+ }
- local_irq_enable();
- return 0;
+ napi->gro_count = 0;
+ napi->gro_list = NULL;
}
+EXPORT_SYMBOL(napi_gro_flush);
-static void net_rx_action(struct softirq_action *h)
+int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
- struct softnet_data *queue = &__get_cpu_var(softnet_data);
- unsigned long start_time = jiffies;
- int budget = netdev_budget;
- void *have;
+ struct sk_buff **pp = NULL;
+ struct packet_type *ptype;
+ __be16 type = skb->protocol;
+ struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
+ int same_flow;
+ int mac_len;
+ int ret;
- local_irq_disable();
+ if (!(skb->dev->features & NETIF_F_GRO))
+ goto normal;
- while (!list_empty(&queue->poll_list)) {
- struct net_device *dev;
+ if (skb_is_gso(skb) || skb_has_frags(skb))
+ goto normal;
- if (budget <= 0 || jiffies - start_time > 1)
- goto softnet_break;
+ rcu_read_lock();
+ list_for_each_entry_rcu(ptype, head, list) {
+ if (ptype->type != type || ptype->dev || !ptype->gro_receive)
+ continue;
- local_irq_enable();
+ skb_set_network_header(skb, skb_gro_offset(skb));
+ mac_len = skb->network_header - skb->mac_header;
+ skb->mac_len = mac_len;
+ NAPI_GRO_CB(skb)->same_flow = 0;
+ NAPI_GRO_CB(skb)->flush = 0;
+ NAPI_GRO_CB(skb)->free = 0;
- dev = list_entry(queue->poll_list.next,
- struct net_device, poll_list);
- have = netpoll_poll_lock(dev);
-
- if (dev->quota <= 0 || dev->poll(dev, &budget)) {
- netpoll_poll_unlock(have);
- local_irq_disable();
- list_move_tail(&dev->poll_list, &queue->poll_list);
- if (dev->quota < 0)
- dev->quota += dev->weight;
- else
- dev->quota = dev->weight;
- } else {
- netpoll_poll_unlock(have);
- dev_put(dev);
- local_irq_disable();
- }
- }
-out:
- local_irq_enable();
-#ifdef CONFIG_NET_DMA
- /*
- * There may not be any more sk_buffs coming right now, so push
- * any pending DMA copies to hardware
- */
- if (net_dma_client) {
- struct dma_chan *chan;
- rcu_read_lock();
- list_for_each_entry_rcu(chan, &net_dma_client->channels, client_node)
- dma_async_memcpy_issue_pending(chan);
- rcu_read_unlock();
+ pp = ptype->gro_receive(&napi->gro_list, skb);
+ break;
}
-#endif
- return;
+ rcu_read_unlock();
-softnet_break:
- __get_cpu_var(netdev_rx_stat).time_squeeze++;
- __raise_softirq_irqoff(NET_RX_SOFTIRQ);
- goto out;
-}
+ if (&ptype->list == head)
+ goto normal;
-static gifconf_func_t * gifconf_list [NPROTO];
+ same_flow = NAPI_GRO_CB(skb)->same_flow;
+ ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED;
-/**
- * register_gifconf - register a SIOCGIF handler
- * @family: Address family
- * @gifconf: Function handler
- *
- * Register protocol dependent address dumping routines. The handler
- * that is passed must not be freed or reused until it has been replaced
- * by another handler.
- */
-int register_gifconf(unsigned int family, gifconf_func_t * gifconf)
-{
- if (family >= NPROTO)
- return -EINVAL;
- gifconf_list[family] = gifconf;
- return 0;
-}
+ if (pp) {
+ struct sk_buff *nskb = *pp;
+ *pp = nskb->next;
+ nskb->next = NULL;
+ napi_gro_complete(nskb);
+ napi->gro_count--;
+ }
-/*
- * Map an interface index to its name (SIOCGIFNAME)
- */
+ if (same_flow)
+ goto ok;
-/*
- * We need this ioctl for efficient implementation of the
- * if_indextoname() function required by the IPv6 API. Without
- * it, we would have to search all the interfaces to find a
- * match. --pb
- */
+ if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS)
+ goto normal;
-static int dev_ifname(struct ifreq __user *arg)
-{
- struct net_device *dev;
- struct ifreq ifr;
+ napi->gro_count++;
+ NAPI_GRO_CB(skb)->count = 1;
+ skb_shinfo(skb)->gso_size = skb_gro_len(skb);
+ skb->next = napi->gro_list;
+ napi->gro_list = skb;
+ ret = GRO_HELD;
- /*
- * Fetch the caller's info block.
- */
+pull:
+ if (skb_headlen(skb) < skb_gro_offset(skb)) {
+ int grow = skb_gro_offset(skb) - skb_headlen(skb);
- if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
- return -EFAULT;
+ BUG_ON(skb->end - skb->tail < grow);
- read_lock(&dev_base_lock);
- dev = __dev_get_by_index(ifr.ifr_ifindex);
- if (!dev) {
- read_unlock(&dev_base_lock);
- return -ENODEV;
+ memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow);
+
+ skb->tail += grow;
+ skb->data_len -= grow;
+
+ skb_shinfo(skb)->frags[0].page_offset += grow;
+ skb_shinfo(skb)->frags[0].size -= grow;
+
+ if (unlikely(!skb_shinfo(skb)->frags[0].size)) {
+ put_page(skb_shinfo(skb)->frags[0].page);
+ memmove(skb_shinfo(skb)->frags,
+ skb_shinfo(skb)->frags + 1,
+ --skb_shinfo(skb)->nr_frags);
+ }
}
- strcpy(ifr.ifr_name, dev->name);
- read_unlock(&dev_base_lock);
+ok:
+ return ret;
- if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
- return -EFAULT;
- return 0;
+normal:
+ ret = GRO_NORMAL;
+ goto pull;
}
+EXPORT_SYMBOL(dev_gro_receive);
-/*
- * Perform a SIOCGIFCONF call. This structure will change
+static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+{
+ struct sk_buff *p;
+
+ if (netpoll_rx_on(skb))
+ return GRO_NORMAL;
+
+ for (p = napi->gro_list; p; p = p->next) {
+ NAPI_GRO_CB(p)->same_flow = (p->dev == skb->dev)
+ && !compare_ether_header(skb_mac_header(p),
+ skb_gro_mac_header(skb));
+ NAPI_GRO_CB(p)->flush = 0;
+ }
+
+ return dev_gro_receive(napi, skb);
+}
+
+int napi_skb_finish(int ret, struct sk_buff *skb)
+{
+ int err = NET_RX_SUCCESS;
+
+ switch (ret) {
+ case GRO_NORMAL:
+ return netif_receive_skb(skb);
+
+ case GRO_DROP:
+ err = NET_RX_DROP;
+ /* fall through */
+
+ case GRO_MERGED_FREE:
+ kfree_skb(skb);
+ break;
+ }
+
+ return err;
+}
+EXPORT_SYMBOL(napi_skb_finish);
+
+void skb_gro_reset_offset(struct sk_buff *skb)
+{
+ NAPI_GRO_CB(skb)->data_offset = 0;
+ NAPI_GRO_CB(skb)->frag0 = NULL;
+ NAPI_GRO_CB(skb)->frag0_len = 0;
+
+ if (skb->mac_header == skb->tail &&
+ !PageHighMem(skb_shinfo(skb)->frags[0].page)) {
+ NAPI_GRO_CB(skb)->frag0 =
+ page_address(skb_shinfo(skb)->frags[0].page) +
+ skb_shinfo(skb)->frags[0].page_offset;
+ NAPI_GRO_CB(skb)->frag0_len = skb_shinfo(skb)->frags[0].size;
+ }
+}
+EXPORT_SYMBOL(skb_gro_reset_offset);
+
+int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+{
+ skb_gro_reset_offset(skb);
+
+ return napi_skb_finish(__napi_gro_receive(napi, skb), skb);
+}
+EXPORT_SYMBOL(napi_gro_receive);
+
+void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
+{
+ __skb_pull(skb, skb_headlen(skb));
+ skb_reserve(skb, NET_IP_ALIGN - skb_headroom(skb));
+
+ napi->skb = skb;
+}
+EXPORT_SYMBOL(napi_reuse_skb);
+
+struct sk_buff *napi_get_frags(struct napi_struct *napi)
+{
+ struct net_device *dev = napi->dev;
+ struct sk_buff *skb = napi->skb;
+
+ if (!skb) {
+ skb = netdev_alloc_skb(dev, GRO_MAX_HEAD + NET_IP_ALIGN);
+ if (!skb)
+ goto out;
+
+ skb_reserve(skb, NET_IP_ALIGN);
+
+ napi->skb = skb;
+ }
+
+out:
+ return skb;
+}
+EXPORT_SYMBOL(napi_get_frags);
+
+int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret)
+{
+ int err = NET_RX_SUCCESS;
+
+ switch (ret) {
+ case GRO_NORMAL:
+ case GRO_HELD:
+ skb->protocol = eth_type_trans(skb, napi->dev);
+
+ if (ret == GRO_NORMAL)
+ return netif_receive_skb(skb);
+
+ skb_gro_pull(skb, -ETH_HLEN);
+ break;
+
+ case GRO_DROP:
+ err = NET_RX_DROP;
+ /* fall through */
+
+ case GRO_MERGED_FREE:
+ napi_reuse_skb(napi, skb);
+ break;
+ }
+
+ return err;
+}
+EXPORT_SYMBOL(napi_frags_finish);
+
+struct sk_buff *napi_frags_skb(struct napi_struct *napi)
+{
+ struct sk_buff *skb = napi->skb;
+ struct ethhdr *eth;
+ unsigned int hlen;
+ unsigned int off;
+
+ napi->skb = NULL;
+
+ skb_reset_mac_header(skb);
+ skb_gro_reset_offset(skb);
+
+ off = skb_gro_offset(skb);
+ hlen = off + sizeof(*eth);
+ eth = skb_gro_header_fast(skb, off);
+ if (skb_gro_header_hard(skb, hlen)) {
+ eth = skb_gro_header_slow(skb, hlen, off);
+ if (unlikely(!eth)) {
+ napi_reuse_skb(napi, skb);
+ skb = NULL;
+ goto out;
+ }
+ }
+
+ skb_gro_pull(skb, sizeof(*eth));
+
+ /*
+ * This works because the only protocols we care about don't require
+ * special handling. We'll fix it up properly at the end.
+ */
+ skb->protocol = eth->h_proto;
+
+out:
+ return skb;
+}
+EXPORT_SYMBOL(napi_frags_skb);
+
+int napi_gro_frags(struct napi_struct *napi)
+{
+ struct sk_buff *skb = napi_frags_skb(napi);
+
+ if (!skb)
+ return NET_RX_DROP;
+
+ return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb));
+}
+EXPORT_SYMBOL(napi_gro_frags);
+
+static int process_backlog(struct napi_struct *napi, int quota)
+{
+ int work = 0;
+ struct softnet_data *queue = &__get_cpu_var(softnet_data);
+ unsigned long start_time = jiffies;
+
+ napi->weight = weight_p;
+ do {
+ struct sk_buff *skb;
+
+ local_irq_disable();
+ skb = __skb_dequeue(&queue->input_pkt_queue);
+ if (!skb) {
+ __napi_complete(napi);
+ local_irq_enable();
+ break;
+ }
+ local_irq_enable();
+
+ netif_receive_skb(skb);
+ } while (++work < quota && jiffies == start_time);
+
+ return work;
+}
+
+/**
+ * __napi_schedule - schedule for receive
+ * @n: entry to schedule
+ *
+ * The entry's receive function will be scheduled to run
+ */
+void __napi_schedule(struct napi_struct *n)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ list_add_tail(&n->poll_list, &__get_cpu_var(softnet_data).poll_list);
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(__napi_schedule);
+
+void __napi_complete(struct napi_struct *n)
+{
+ BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
+ BUG_ON(n->gro_list);
+
+ list_del(&n->poll_list);
+ smp_mb__before_clear_bit();
+ clear_bit(NAPI_STATE_SCHED, &n->state);
+}
+EXPORT_SYMBOL(__napi_complete);
+
+void napi_complete(struct napi_struct *n)
+{
+ unsigned long flags;
+
+ /*
+ * don't let napi dequeue from the cpu poll list
+ * just in case its running on a different cpu
+ */
+ if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
+ return;
+
+ napi_gro_flush(n);
+ local_irq_save(flags);
+ __napi_complete(n);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(napi_complete);
+
+void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
+ int (*poll)(struct napi_struct *, int), int weight)
+{
+ INIT_LIST_HEAD(&napi->poll_list);
+ napi->gro_count = 0;
+ napi->gro_list = NULL;
+ napi->skb = NULL;
+ napi->poll = poll;
+ napi->weight = weight;
+ list_add(&napi->dev_list, &dev->napi_list);
+ napi->dev = dev;
+#ifdef CONFIG_NETPOLL
+ spin_lock_init(&napi->poll_lock);
+ napi->poll_owner = -1;
+#endif
+ set_bit(NAPI_STATE_SCHED, &napi->state);
+}
+EXPORT_SYMBOL(netif_napi_add);
+
+void netif_napi_del(struct napi_struct *napi)
+{
+ struct sk_buff *skb, *next;
+
+ list_del_init(&napi->dev_list);
+ napi_free_frags(napi);
+
+ for (skb = napi->gro_list; skb; skb = next) {
+ next = skb->next;
+ skb->next = NULL;
+ kfree_skb(skb);
+ }
+
+ napi->gro_list = NULL;
+ napi->gro_count = 0;
+}
+EXPORT_SYMBOL(netif_napi_del);
+
+
+static void net_rx_action(struct softirq_action *h)
+{
+ struct list_head *list = &__get_cpu_var(softnet_data).poll_list;
+ unsigned long time_limit = jiffies + 2;
+ int budget = netdev_budget;
+ void *have;
+
+ local_irq_disable();
+
+ while (!list_empty(list)) {
+ struct napi_struct *n;
+ int work, weight;
+
+ /* If softirq window is exhuasted then punt.
+ * Allow this to run for 2 jiffies since which will allow
+ * an average latency of 1.5/HZ.
+ */
+ if (unlikely(budget <= 0 || time_after(jiffies, time_limit)))
+ goto softnet_break;
+
+ local_irq_enable();
+
+ /* Even though interrupts have been re-enabled, this
+ * access is safe because interrupts can only add new
+ * entries to the tail of this list, and only ->poll()
+ * calls can remove this head entry from the list.
+ */
+ n = list_entry(list->next, struct napi_struct, poll_list);
+
+ have = netpoll_poll_lock(n);
+
+ weight = 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);
+ trace_napi_poll(n);
+ }
+
+ WARN_ON_ONCE(work > weight);
+
+ budget -= work;
+
+ local_irq_disable();
+
+ /* Drivers must not modify the NAPI state if they
+ * consume the entire weight. In such cases this code
+ * still "owns" the NAPI instance and therefore can
+ * move the instance around on the list at-will.
+ */
+ if (unlikely(work == weight)) {
+ if (unlikely(napi_disable_pending(n))) {
+ local_irq_enable();
+ napi_complete(n);
+ local_irq_disable();
+ } else
+ list_move_tail(&n->poll_list, list);
+ }
+
+ netpoll_poll_unlock(have);
+ }
+out:
+ local_irq_enable();
+
+#ifdef CONFIG_NET_DMA
+ /*
+ * There may not be any more sk_buffs coming right now, so push
+ * any pending DMA copies to hardware
+ */
+ dma_issue_pending_all();
+#endif
+
+ return;
+
+softnet_break:
+ __get_cpu_var(netdev_rx_stat).time_squeeze++;
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ goto out;
+}
+
+static gifconf_func_t *gifconf_list[NPROTO];
+
+/**
+ * register_gifconf - register a SIOCGIF handler
+ * @family: Address family
+ * @gifconf: Function handler
+ *
+ * Register protocol dependent address dumping routines. The handler
+ * that is passed must not be freed or reused until it has been replaced
+ * by another handler.
+ */
+int register_gifconf(unsigned int family, gifconf_func_t *gifconf)
+{
+ if (family >= NPROTO)
+ return -EINVAL;
+ gifconf_list[family] = gifconf;
+ return 0;
+}
+EXPORT_SYMBOL(register_gifconf);
+
+
+/*
+ * Map an interface index to its name (SIOCGIFNAME)
+ */
+
+/*
+ * We need this ioctl for efficient implementation of the
+ * if_indextoname() function required by the IPv6 API. Without
+ * it, we would have to search all the interfaces to find a
+ * match. --pb
+ */
+
+static int dev_ifname(struct net *net, struct ifreq __user *arg)
+{
+ struct net_device *dev;
+ struct ifreq ifr;
+
+ /*
+ * Fetch the caller's info block.
+ */
+
+ if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
+ return -EFAULT;
+
+ read_lock(&dev_base_lock);
+ dev = __dev_get_by_index(net, ifr.ifr_ifindex);
+ if (!dev) {
+ read_unlock(&dev_base_lock);
+ return -ENODEV;
+ }
+
+ strcpy(ifr.ifr_name, dev->name);
+ read_unlock(&dev_base_lock);
+
+ if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
+ return -EFAULT;
+ return 0;
+}
+
+/*
+ * Perform a SIOCGIFCONF call. This structure will change
* size eventually, and there is nothing I can do about it.
* Thus we will need a 'compatibility mode'.
*/
-static int dev_ifconf(char __user *arg)
+static int dev_ifconf(struct net *net, char __user *arg)
{
struct ifconf ifc;
struct net_device *dev;
*/
total = 0;
- for_each_netdev(dev) {
+ for_each_netdev(net, dev) {
for (i = 0; i < NPROTO; i++) {
if (gifconf_list[i]) {
int done;
* in detail.
*/
void *dev_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(dev_base_lock)
{
+ struct net *net = seq_file_net(seq);
loff_t off;
struct net_device *dev;
return SEQ_START_TOKEN;
off = 1;
- for_each_netdev(dev)
+ for_each_netdev(net, dev)
if (off++ == *pos)
return dev;
void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
+ struct net *net = seq_file_net(seq);
++*pos;
return v == SEQ_START_TOKEN ?
- first_net_device() : next_net_device((struct net_device *)v);
+ 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 void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
{
- struct net_device_stats *stats = dev->get_stats(dev);
+ const struct net_device_stats *stats = dev_get_stats(dev);
seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
"%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
{
struct netif_rx_stats *rc = NULL;
- while (*pos < NR_CPUS)
+ while (*pos < nr_cpu_ids)
if (cpu_online(*pos)) {
rc = &per_cpu(netdev_rx_stat, *pos);
break;
seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
s->total, s->dropped, s->time_squeeze, 0,
0, 0, 0, 0, /* was fastroute */
- s->cpu_collision );
+ s->cpu_collision);
return 0;
}
static int dev_seq_open(struct inode *inode, struct file *file)
{
- return seq_open(file, &dev_seq_ops);
+ 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 = 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();
}
-static void ptype_seq_decode(struct seq_file *seq, void *sym)
-{
-#ifdef CONFIG_KALLSYMS
- unsigned long offset = 0, symsize;
- const char *symname;
- char *modname;
- char namebuf[128];
-
- symname = kallsyms_lookup((unsigned long)sym, &symsize, &offset,
- &modname, namebuf);
-
- if (symname) {
- char *delim = ":";
-
- if (!modname)
- modname = delim = "";
- seq_printf(seq, "%s%s%s%s+0x%lx", delim, modname, delim,
- symname, offset);
- return;
- }
-#endif
-
- seq_printf(seq, "[%p]", sym);
-}
-
static int ptype_seq_show(struct seq_file *seq, void *v)
{
struct packet_type *pt = v;
if (v == SEQ_START_TOKEN)
seq_puts(seq, "Type Device Function\n");
- else {
+ else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) {
if (pt->type == htons(ETH_P_ALL))
seq_puts(seq, "ALL ");
else
seq_printf(seq, "%04x", ntohs(pt->type));
- seq_printf(seq, " %-8s ",
- pt->dev ? pt->dev->name : "");
- ptype_seq_decode(seq, pt->func);
- seq_putc(seq, '\n');
+ seq_printf(seq, " %-8s %pF\n",
+ pt->dev ? pt->dev->name : "", pt->func);
}
return 0;
static int ptype_seq_open(struct inode *inode, struct file *file)
{
- return seq_open(file, &ptype_seq_ops);
+ return seq_open_net(inode, file, &ptype_seq_ops,
+ sizeof(struct seq_net_private));
}
static const struct file_operations ptype_seq_fops = {
.open = ptype_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release,
+ .release = seq_release_net,
};
-static int __init dev_proc_init(void)
+static int __net_init dev_proc_net_init(struct net *net)
{
int rc = -ENOMEM;
- if (!proc_net_fops_create("dev", S_IRUGO, &dev_seq_fops))
+ if (!proc_net_fops_create(net, "dev", S_IRUGO, &dev_seq_fops))
goto out;
- if (!proc_net_fops_create("softnet_stat", S_IRUGO, &softnet_seq_fops))
+ if (!proc_net_fops_create(net, "softnet_stat", S_IRUGO, &softnet_seq_fops))
goto out_dev;
- if (!proc_net_fops_create("ptype", S_IRUGO, &ptype_seq_fops))
- goto out_dev2;
-
- if (wext_proc_init())
+ if (!proc_net_fops_create(net, "ptype", S_IRUGO, &ptype_seq_fops))
goto out_softnet;
+
+ if (wext_proc_init(net))
+ goto out_ptype;
rc = 0;
out:
return rc;
+out_ptype:
+ proc_net_remove(net, "ptype");
out_softnet:
- proc_net_remove("ptype");
-out_dev2:
- proc_net_remove("softnet_stat");
+ proc_net_remove(net, "softnet_stat");
out_dev:
- proc_net_remove("dev");
+ proc_net_remove(net, "dev");
goto out;
}
-#else
-#define dev_proc_init() 0
+
+static void __net_exit dev_proc_net_exit(struct net *net)
+{
+ wext_proc_exit(net);
+
+ proc_net_remove(net, "ptype");
+ proc_net_remove(net, "softnet_stat");
+ proc_net_remove(net, "dev");
+}
+
+static struct pernet_operations __net_initdata dev_proc_ops = {
+ .init = dev_proc_net_init,
+ .exit = dev_proc_net_exit,
+};
+
+static int __init dev_proc_init(void)
+{
+ return register_pernet_subsys(&dev_proc_ops);
+}
+#else
+#define dev_proc_init() 0
#endif /* CONFIG_PROC_FS */
rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE);
return 0;
}
+EXPORT_SYMBOL(netdev_set_master);
+
+static void dev_change_rx_flags(struct net_device *dev, int flags)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags)
+ ops->ndo_change_rx_flags(dev, flags);
+}
+
+static int __dev_set_promiscuity(struct net_device *dev, int inc)
+{
+ unsigned short old_flags = dev->flags;
+ uid_t uid;
+ gid_t gid;
+
+ ASSERT_RTNL();
+
+ dev->flags |= IFF_PROMISC;
+ dev->promiscuity += inc;
+ if (dev->promiscuity == 0) {
+ /*
+ * Avoid overflow.
+ * If inc causes overflow, untouch promisc and return error.
+ */
+ if (inc < 0)
+ dev->flags &= ~IFF_PROMISC;
+ else {
+ dev->promiscuity -= inc;
+ printk(KERN_WARNING "%s: promiscuity touches roof, "
+ "set promiscuity failed, promiscuity feature "
+ "of device might be broken.\n", dev->name);
+ return -EOVERFLOW;
+ }
+ }
+ if (dev->flags != old_flags) {
+ printk(KERN_INFO "device %s %s promiscuous mode\n",
+ dev->name, (dev->flags & IFF_PROMISC) ? "entered" :
+ "left");
+ if (audit_enabled) {
+ current_uid_gid(&uid, &gid);
+ 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),
+ uid, gid,
+ audit_get_sessionid(current));
+ }
+
+ dev_change_rx_flags(dev, IFF_PROMISC);
+ }
+ return 0;
+}
/**
* dev_set_promiscuity - update promiscuity count on a device
* remains above zero the interface remains promiscuous. Once it hits zero
* the device reverts back to normal filtering operation. A negative inc
* value is used to drop promiscuity on the device.
+ * Return 0 if successful or a negative errno code on error.
*/
-void dev_set_promiscuity(struct net_device *dev, int inc)
+int dev_set_promiscuity(struct net_device *dev, int inc)
{
unsigned short old_flags = dev->flags;
+ int err;
- if ((dev->promiscuity += inc) == 0)
- dev->flags &= ~IFF_PROMISC;
- else
- dev->flags |= IFF_PROMISC;
- if (dev->flags != old_flags) {
- dev_mc_upload(dev);
- 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));
- }
+ err = __dev_set_promiscuity(dev, inc);
+ if (err < 0)
+ return err;
+ if (dev->flags != old_flags)
+ dev_set_rx_mode(dev);
+ return err;
}
+EXPORT_SYMBOL(dev_set_promiscuity);
/**
* dev_set_allmulti - update allmulti count on a device
* to all interfaces. Once it hits zero the device reverts back to normal
* filtering operation. A negative @inc value is used to drop the counter
* when releasing a resource needing all multicasts.
+ * Return 0 if successful or a negative errno code on error.
+ */
+
+int dev_set_allmulti(struct net_device *dev, int inc)
+{
+ unsigned short old_flags = dev->flags;
+
+ ASSERT_RTNL();
+
+ dev->flags |= IFF_ALLMULTI;
+ dev->allmulti += inc;
+ if (dev->allmulti == 0) {
+ /*
+ * Avoid overflow.
+ * If inc causes overflow, untouch allmulti and return error.
+ */
+ if (inc < 0)
+ dev->flags &= ~IFF_ALLMULTI;
+ else {
+ dev->allmulti -= inc;
+ printk(KERN_WARNING "%s: allmulti touches roof, "
+ "set allmulti failed, allmulti feature of "
+ "device might be broken.\n", dev->name);
+ return -EOVERFLOW;
+ }
+ }
+ if (dev->flags ^ old_flags) {
+ dev_change_rx_flags(dev, IFF_ALLMULTI);
+ dev_set_rx_mode(dev);
+ }
+ return 0;
+}
+EXPORT_SYMBOL(dev_set_allmulti);
+
+/*
+ * Upload unicast and multicast address lists to device and
+ * configure RX filtering. When the device doesn't support unicast
+ * filtering it is put in promiscuous mode while unicast addresses
+ * are present.
+ */
+void __dev_set_rx_mode(struct net_device *dev)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ /* dev_open will call this function so the list will stay sane. */
+ if (!(dev->flags&IFF_UP))
+ return;
+
+ if (!netif_device_present(dev))
+ return;
+
+ if (ops->ndo_set_rx_mode)
+ ops->ndo_set_rx_mode(dev);
+ else {
+ /* Unicast addresses changes may only happen under the rtnl,
+ * therefore calling __dev_set_promiscuity here is safe.
+ */
+ if (dev->uc.count > 0 && !dev->uc_promisc) {
+ __dev_set_promiscuity(dev, 1);
+ dev->uc_promisc = 1;
+ } else if (dev->uc.count == 0 && dev->uc_promisc) {
+ __dev_set_promiscuity(dev, -1);
+ dev->uc_promisc = 0;
+ }
+
+ if (ops->ndo_set_multicast_list)
+ ops->ndo_set_multicast_list(dev);
+ }
+}
+
+void dev_set_rx_mode(struct net_device *dev)
+{
+ netif_addr_lock_bh(dev);
+ __dev_set_rx_mode(dev);
+ netif_addr_unlock_bh(dev);
+}
+
+/* hw addresses list handling functions */
+
+static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr,
+ int addr_len, unsigned char addr_type)
+{
+ struct netdev_hw_addr *ha;
+ int alloc_size;
+
+ if (addr_len > MAX_ADDR_LEN)
+ return -EINVAL;
+
+ list_for_each_entry(ha, &list->list, list) {
+ if (!memcmp(ha->addr, addr, addr_len) &&
+ ha->type == addr_type) {
+ ha->refcount++;
+ return 0;
+ }
+ }
+
+
+ alloc_size = sizeof(*ha);
+ if (alloc_size < L1_CACHE_BYTES)
+ alloc_size = L1_CACHE_BYTES;
+ ha = kmalloc(alloc_size, GFP_ATOMIC);
+ if (!ha)
+ return -ENOMEM;
+ memcpy(ha->addr, addr, addr_len);
+ ha->type = addr_type;
+ ha->refcount = 1;
+ ha->synced = false;
+ list_add_tail_rcu(&ha->list, &list->list);
+ list->count++;
+ return 0;
+}
+
+static void ha_rcu_free(struct rcu_head *head)
+{
+ struct netdev_hw_addr *ha;
+
+ ha = container_of(head, struct netdev_hw_addr, rcu_head);
+ kfree(ha);
+}
+
+static int __hw_addr_del(struct netdev_hw_addr_list *list, unsigned char *addr,
+ int addr_len, unsigned char addr_type)
+{
+ struct netdev_hw_addr *ha;
+
+ list_for_each_entry(ha, &list->list, list) {
+ if (!memcmp(ha->addr, addr, addr_len) &&
+ (ha->type == addr_type || !addr_type)) {
+ if (--ha->refcount)
+ return 0;
+ list_del_rcu(&ha->list);
+ call_rcu(&ha->rcu_head, ha_rcu_free);
+ list->count--;
+ return 0;
+ }
+ }
+ return -ENOENT;
+}
+
+static int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list,
+ struct netdev_hw_addr_list *from_list,
+ int addr_len,
+ unsigned char addr_type)
+{
+ int err;
+ struct netdev_hw_addr *ha, *ha2;
+ unsigned char type;
+
+ list_for_each_entry(ha, &from_list->list, list) {
+ type = addr_type ? addr_type : ha->type;
+ err = __hw_addr_add(to_list, ha->addr, addr_len, type);
+ if (err)
+ goto unroll;
+ }
+ return 0;
+
+unroll:
+ list_for_each_entry(ha2, &from_list->list, list) {
+ if (ha2 == ha)
+ break;
+ type = addr_type ? addr_type : ha2->type;
+ __hw_addr_del(to_list, ha2->addr, addr_len, type);
+ }
+ return err;
+}
+
+static void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list,
+ struct netdev_hw_addr_list *from_list,
+ int addr_len,
+ unsigned char addr_type)
+{
+ struct netdev_hw_addr *ha;
+ unsigned char type;
+
+ list_for_each_entry(ha, &from_list->list, list) {
+ type = addr_type ? addr_type : ha->type;
+ __hw_addr_del(to_list, ha->addr, addr_len, addr_type);
+ }
+}
+
+static int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
+ struct netdev_hw_addr_list *from_list,
+ int addr_len)
+{
+ int err = 0;
+ struct netdev_hw_addr *ha, *tmp;
+
+ list_for_each_entry_safe(ha, tmp, &from_list->list, list) {
+ if (!ha->synced) {
+ err = __hw_addr_add(to_list, ha->addr,
+ addr_len, ha->type);
+ if (err)
+ break;
+ ha->synced = true;
+ ha->refcount++;
+ } else if (ha->refcount == 1) {
+ __hw_addr_del(to_list, ha->addr, addr_len, ha->type);
+ __hw_addr_del(from_list, ha->addr, addr_len, ha->type);
+ }
+ }
+ return err;
+}
+
+static void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
+ struct netdev_hw_addr_list *from_list,
+ int addr_len)
+{
+ struct netdev_hw_addr *ha, *tmp;
+
+ list_for_each_entry_safe(ha, tmp, &from_list->list, list) {
+ if (ha->synced) {
+ __hw_addr_del(to_list, ha->addr,
+ addr_len, ha->type);
+ ha->synced = false;
+ __hw_addr_del(from_list, ha->addr,
+ addr_len, ha->type);
+ }
+ }
+}
+
+static void __hw_addr_flush(struct netdev_hw_addr_list *list)
+{
+ struct netdev_hw_addr *ha, *tmp;
+
+ list_for_each_entry_safe(ha, tmp, &list->list, list) {
+ list_del_rcu(&ha->list);
+ call_rcu(&ha->rcu_head, ha_rcu_free);
+ }
+ list->count = 0;
+}
+
+static void __hw_addr_init(struct netdev_hw_addr_list *list)
+{
+ INIT_LIST_HEAD(&list->list);
+ list->count = 0;
+}
+
+/* Device addresses handling functions */
+
+static void dev_addr_flush(struct net_device *dev)
+{
+ /* rtnl_mutex must be held here */
+
+ __hw_addr_flush(&dev->dev_addrs);
+ dev->dev_addr = NULL;
+}
+
+static int dev_addr_init(struct net_device *dev)
+{
+ unsigned char addr[MAX_ADDR_LEN];
+ struct netdev_hw_addr *ha;
+ int err;
+
+ /* rtnl_mutex must be held here */
+
+ __hw_addr_init(&dev->dev_addrs);
+ memset(addr, 0, sizeof(addr));
+ err = __hw_addr_add(&dev->dev_addrs, addr, sizeof(addr),
+ NETDEV_HW_ADDR_T_LAN);
+ if (!err) {
+ /*
+ * Get the first (previously created) address from the list
+ * and set dev_addr pointer to this location.
+ */
+ ha = list_first_entry(&dev->dev_addrs.list,
+ struct netdev_hw_addr, list);
+ dev->dev_addr = ha->addr;
+ }
+ return err;
+}
+
+/**
+ * dev_addr_add - Add a device address
+ * @dev: device
+ * @addr: address to add
+ * @addr_type: address type
+ *
+ * Add a device address to the device or increase the reference count if
+ * it already exists.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+int dev_addr_add(struct net_device *dev, unsigned char *addr,
+ unsigned char addr_type)
+{
+ int err;
+
+ ASSERT_RTNL();
+
+ err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type);
+ if (!err)
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+ return err;
+}
+EXPORT_SYMBOL(dev_addr_add);
+
+/**
+ * dev_addr_del - Release a device address.
+ * @dev: device
+ * @addr: address to delete
+ * @addr_type: address type
+ *
+ * Release reference to a device address and remove it from the device
+ * if the reference count drops to zero.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+int dev_addr_del(struct net_device *dev, unsigned char *addr,
+ unsigned char addr_type)
+{
+ int err;
+ struct netdev_hw_addr *ha;
+
+ ASSERT_RTNL();
+
+ /*
+ * We can not remove the first address from the list because
+ * dev->dev_addr points to that.
+ */
+ ha = list_first_entry(&dev->dev_addrs.list,
+ struct netdev_hw_addr, list);
+ if (ha->addr == dev->dev_addr && ha->refcount == 1)
+ return -ENOENT;
+
+ err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len,
+ addr_type);
+ if (!err)
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+ return err;
+}
+EXPORT_SYMBOL(dev_addr_del);
+
+/**
+ * dev_addr_add_multiple - Add device addresses from another device
+ * @to_dev: device to which addresses will be added
+ * @from_dev: device from which addresses will be added
+ * @addr_type: address type - 0 means type will be used from from_dev
+ *
+ * Add device addresses of the one device to another.
+ **
+ * The caller must hold the rtnl_mutex.
*/
+int dev_addr_add_multiple(struct net_device *to_dev,
+ struct net_device *from_dev,
+ unsigned char addr_type)
+{
+ int err;
+
+ ASSERT_RTNL();
+
+ if (from_dev->addr_len != to_dev->addr_len)
+ return -EINVAL;
+ err = __hw_addr_add_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs,
+ to_dev->addr_len, addr_type);
+ if (!err)
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev);
+ return err;
+}
+EXPORT_SYMBOL(dev_addr_add_multiple);
+
+/**
+ * dev_addr_del_multiple - Delete device addresses by another device
+ * @to_dev: device where the addresses will be deleted
+ * @from_dev: device by which addresses the addresses will be deleted
+ * @addr_type: address type - 0 means type will used from from_dev
+ *
+ * Deletes addresses in to device by the list of addresses in from device.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+int dev_addr_del_multiple(struct net_device *to_dev,
+ struct net_device *from_dev,
+ unsigned char addr_type)
+{
+ ASSERT_RTNL();
+
+ if (from_dev->addr_len != to_dev->addr_len)
+ return -EINVAL;
+ __hw_addr_del_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs,
+ to_dev->addr_len, addr_type);
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev);
+ return 0;
+}
+EXPORT_SYMBOL(dev_addr_del_multiple);
+
+/* multicast addresses handling functions */
+
+int __dev_addr_delete(struct dev_addr_list **list, int *count,
+ void *addr, int alen, int glbl)
+{
+ struct dev_addr_list *da;
+
+ for (; (da = *list) != NULL; list = &da->next) {
+ if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 &&
+ alen == da->da_addrlen) {
+ if (glbl) {
+ int old_glbl = da->da_gusers;
+ da->da_gusers = 0;
+ if (old_glbl == 0)
+ break;
+ }
+ if (--da->da_users)
+ return 0;
+
+ *list = da->next;
+ kfree(da);
+ (*count)--;
+ return 0;
+ }
+ }
+ return -ENOENT;
+}
+
+int __dev_addr_add(struct dev_addr_list **list, int *count,
+ void *addr, int alen, int glbl)
+{
+ struct dev_addr_list *da;
+
+ for (da = *list; da != NULL; da = da->next) {
+ if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 &&
+ da->da_addrlen == alen) {
+ if (glbl) {
+ int old_glbl = da->da_gusers;
+ da->da_gusers = 1;
+ if (old_glbl)
+ return 0;
+ }
+ da->da_users++;
+ return 0;
+ }
+ }
+
+ da = kzalloc(sizeof(*da), GFP_ATOMIC);
+ if (da == NULL)
+ return -ENOMEM;
+ memcpy(da->da_addr, addr, alen);
+ da->da_addrlen = alen;
+ da->da_users = 1;
+ da->da_gusers = glbl ? 1 : 0;
+ da->next = *list;
+ *list = da;
+ (*count)++;
+ return 0;
+}
+
+/**
+ * dev_unicast_delete - Release secondary unicast address.
+ * @dev: device
+ * @addr: address to delete
+ *
+ * Release reference to a secondary unicast address and remove it
+ * from the device if the reference count drops to zero.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+int dev_unicast_delete(struct net_device *dev, void *addr)
+{
+ int err;
+
+ ASSERT_RTNL();
+
+ netif_addr_lock_bh(dev);
+ err = __hw_addr_del(&dev->uc, addr, dev->addr_len,
+ NETDEV_HW_ADDR_T_UNICAST);
+ if (!err)
+ __dev_set_rx_mode(dev);
+ netif_addr_unlock_bh(dev);
+ return err;
+}
+EXPORT_SYMBOL(dev_unicast_delete);
+
+/**
+ * dev_unicast_add - add a secondary unicast address
+ * @dev: device
+ * @addr: address to add
+ *
+ * Add a secondary unicast address to the device or increase
+ * the reference count if it already exists.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+int dev_unicast_add(struct net_device *dev, void *addr)
+{
+ int err;
+
+ ASSERT_RTNL();
+
+ netif_addr_lock_bh(dev);
+ err = __hw_addr_add(&dev->uc, addr, dev->addr_len,
+ NETDEV_HW_ADDR_T_UNICAST);
+ if (!err)
+ __dev_set_rx_mode(dev);
+ netif_addr_unlock_bh(dev);
+ return err;
+}
+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;
+}
+EXPORT_SYMBOL_GPL(__dev_addr_sync);
+
+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;
+ }
+}
+EXPORT_SYMBOL_GPL(__dev_addr_unsync);
+
+/**
+ * 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;
+
+ if (to->addr_len != from->addr_len)
+ return -EINVAL;
+
+ netif_addr_lock_bh(to);
+ err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
+ if (!err)
+ __dev_set_rx_mode(to);
+ netif_addr_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)
+{
+ if (to->addr_len != from->addr_len)
+ return;
+
+ netif_addr_lock_bh(from);
+ netif_addr_lock(to);
+ __hw_addr_unsync(&to->uc, &from->uc, to->addr_len);
+ __dev_set_rx_mode(to);
+ netif_addr_unlock(to);
+ netif_addr_unlock_bh(from);
+}
+EXPORT_SYMBOL(dev_unicast_unsync);
+
+static void dev_unicast_flush(struct net_device *dev)
+{
+ netif_addr_lock_bh(dev);
+ __hw_addr_flush(&dev->uc);
+ netif_addr_unlock_bh(dev);
+}
+
+static void dev_unicast_init(struct net_device *dev)
+{
+ __hw_addr_init(&dev->uc);
+}
+
+
+static void __dev_addr_discard(struct dev_addr_list **list)
+{
+ struct dev_addr_list *tmp;
+
+ while (*list != NULL) {
+ tmp = *list;
+ *list = tmp->next;
+ if (tmp->da_users > tmp->da_gusers)
+ printk("__dev_addr_discard: address leakage! "
+ "da_users=%d\n", tmp->da_users);
+ kfree(tmp);
+ }
+}
-void dev_set_allmulti(struct net_device *dev, int inc)
+static void dev_addr_discard(struct net_device *dev)
{
- unsigned short old_flags = dev->flags;
+ netif_addr_lock_bh(dev);
- dev->flags |= IFF_ALLMULTI;
- if ((dev->allmulti += inc) == 0)
- dev->flags &= ~IFF_ALLMULTI;
- if (dev->flags ^ old_flags)
- dev_mc_upload(dev);
+ __dev_addr_discard(&dev->mc_list);
+ dev->mc_count = 0;
+
+ netif_addr_unlock_bh(dev);
}
+/**
+ * dev_get_flags - get flags reported to userspace
+ * @dev: device
+ *
+ * Get the combination of flag bits exported through APIs to userspace.
+ */
unsigned dev_get_flags(const struct net_device *dev)
{
unsigned flags;
return flags;
}
+EXPORT_SYMBOL(dev_get_flags);
+/**
+ * dev_change_flags - change device settings
+ * @dev: device
+ * @flags: device state flags
+ *
+ * Change settings on device based state flags. The flags are
+ * in the userspace exported format.
+ */
int dev_change_flags(struct net_device *dev, unsigned flags)
{
int ret, changes;
int old_flags = dev->flags;
+ ASSERT_RTNL();
+
/*
* Set the flags on our device.
*/
* Load in the correct multicast list now the flags have changed.
*/
- dev_mc_upload(dev);
+ if ((old_flags ^ flags) & IFF_MULTICAST)
+ dev_change_rx_flags(dev, IFF_MULTICAST);
+
+ dev_set_rx_mode(dev);
/*
* Have we downed the interface. We handle IFF_UP ourselves
ret = ((old_flags & IFF_UP) ? dev_close : dev_open)(dev);
if (!ret)
- dev_mc_upload(dev);
+ dev_set_rx_mode(dev);
}
if (dev->flags & IFF_UP &&
- ((old_flags ^ dev->flags) &~ (IFF_UP | IFF_PROMISC | IFF_ALLMULTI |
+ ((old_flags ^ dev->flags) & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI |
IFF_VOLATILE)))
- raw_notifier_call_chain(&netdev_chain,
- NETDEV_CHANGE, dev);
+ call_netdevice_notifiers(NETDEV_CHANGE, dev);
if ((flags ^ dev->gflags) & IFF_PROMISC) {
- int inc = (flags & IFF_PROMISC) ? +1 : -1;
+ int inc = (flags & IFF_PROMISC) ? 1 : -1;
+
dev->gflags ^= IFF_PROMISC;
dev_set_promiscuity(dev, inc);
}
IFF_ALLMULTI is requested not asking us and not reporting.
*/
if ((flags ^ dev->gflags) & IFF_ALLMULTI) {
- int inc = (flags & IFF_ALLMULTI) ? +1 : -1;
+ int inc = (flags & IFF_ALLMULTI) ? 1 : -1;
+
dev->gflags ^= IFF_ALLMULTI;
dev_set_allmulti(dev, inc);
}
return ret;
}
+EXPORT_SYMBOL(dev_change_flags);
+/**
+ * dev_set_mtu - Change maximum transfer unit
+ * @dev: device
+ * @new_mtu: new transfer unit
+ *
+ * Change the maximum transfer size of the network device.
+ */
int dev_set_mtu(struct net_device *dev, int new_mtu)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
int err;
if (new_mtu == dev->mtu)
return -ENODEV;
err = 0;
- if (dev->change_mtu)
- err = dev->change_mtu(dev, new_mtu);
+ if (ops->ndo_change_mtu)
+ err = ops->ndo_change_mtu(dev, new_mtu);
else
dev->mtu = new_mtu;
+
if (!err && dev->flags & IFF_UP)
- raw_notifier_call_chain(&netdev_chain,
- NETDEV_CHANGEMTU, dev);
+ call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
return err;
}
+EXPORT_SYMBOL(dev_set_mtu);
+/**
+ * dev_set_mac_address - Change Media Access Control Address
+ * @dev: device
+ * @sa: new address
+ *
+ * Change the hardware (MAC) address of the device
+ */
int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
int err;
- if (!dev->set_mac_address)
+ if (!ops->ndo_set_mac_address)
return -EOPNOTSUPP;
if (sa->sa_family != dev->type)
return -EINVAL;
if (!netif_device_present(dev))
return -ENODEV;
- err = dev->set_mac_address(dev, sa);
+ err = ops->ndo_set_mac_address(dev, sa);
if (!err)
- raw_notifier_call_chain(&netdev_chain,
- NETDEV_CHANGEADDR, dev);
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
return err;
}
+EXPORT_SYMBOL(dev_set_mac_address);
/*
- * Perform the SIOCxIFxxx calls.
+ * Perform the SIOCxIFxxx calls, inside read_lock(dev_base_lock)
*/
-static int dev_ifsioc(struct ifreq *ifr, unsigned int cmd)
+static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd)
{
int err;
- struct net_device *dev = __dev_get_by_name(ifr->ifr_name);
+ struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
if (!dev)
return -ENODEV;
switch (cmd) {
- case SIOCGIFFLAGS: /* Get interface flags */
- ifr->ifr_flags = dev_get_flags(dev);
- return 0;
+ case SIOCGIFFLAGS: /* Get interface flags */
+ ifr->ifr_flags = (short) dev_get_flags(dev);
+ return 0;
- case SIOCSIFFLAGS: /* Set interface flags */
- return dev_change_flags(dev, ifr->ifr_flags);
+ case SIOCGIFMETRIC: /* Get the metric on the interface
+ (currently unused) */
+ ifr->ifr_metric = 0;
+ return 0;
- case SIOCGIFMETRIC: /* Get the metric on the interface
- (currently unused) */
- ifr->ifr_metric = 0;
- return 0;
+ case SIOCGIFMTU: /* Get the MTU of a device */
+ ifr->ifr_mtu = dev->mtu;
+ return 0;
- case SIOCSIFMETRIC: /* Set the metric on the interface
- (currently unused) */
- return -EOPNOTSUPP;
+ case SIOCGIFHWADDR:
+ if (!dev->addr_len)
+ memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
+ else
+ memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
+ min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+ ifr->ifr_hwaddr.sa_family = dev->type;
+ return 0;
- case SIOCGIFMTU: /* Get the MTU of a device */
- ifr->ifr_mtu = dev->mtu;
- return 0;
+ case SIOCGIFSLAVE:
+ err = -EINVAL;
+ break;
- case SIOCSIFMTU: /* Set the MTU of a device */
- return dev_set_mtu(dev, ifr->ifr_mtu);
+ case SIOCGIFMAP:
+ ifr->ifr_map.mem_start = dev->mem_start;
+ ifr->ifr_map.mem_end = dev->mem_end;
+ ifr->ifr_map.base_addr = dev->base_addr;
+ ifr->ifr_map.irq = dev->irq;
+ ifr->ifr_map.dma = dev->dma;
+ ifr->ifr_map.port = dev->if_port;
+ return 0;
- case SIOCGIFHWADDR:
- if (!dev->addr_len)
- memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
- else
- memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
- min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
- ifr->ifr_hwaddr.sa_family = dev->type;
- return 0;
+ case SIOCGIFINDEX:
+ ifr->ifr_ifindex = dev->ifindex;
+ return 0;
- case SIOCSIFHWADDR:
- return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
+ case SIOCGIFTXQLEN:
+ ifr->ifr_qlen = dev->tx_queue_len;
+ return 0;
- case SIOCSIFHWBROADCAST:
- if (ifr->ifr_hwaddr.sa_family != dev->type)
- return -EINVAL;
- memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
- min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
- raw_notifier_call_chain(&netdev_chain,
- NETDEV_CHANGEADDR, dev);
- return 0;
+ default:
+ /* dev_ioctl() should ensure this case
+ * is never reached
+ */
+ WARN_ON(1);
+ err = -EINVAL;
+ break;
- case SIOCGIFMAP:
- ifr->ifr_map.mem_start = dev->mem_start;
- ifr->ifr_map.mem_end = dev->mem_end;
- ifr->ifr_map.base_addr = dev->base_addr;
- ifr->ifr_map.irq = dev->irq;
- ifr->ifr_map.dma = dev->dma;
- ifr->ifr_map.port = dev->if_port;
- return 0;
+ }
+ return err;
+}
- case SIOCSIFMAP:
- if (dev->set_config) {
- if (!netif_device_present(dev))
- return -ENODEV;
- return dev->set_config(dev, &ifr->ifr_map);
- }
- return -EOPNOTSUPP;
+/*
+ * Perform the SIOCxIFxxx calls, inside rtnl_lock()
+ */
+static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
+{
+ int err;
+ struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
+ const struct net_device_ops *ops;
- case SIOCADDMULTI:
- if (!dev->set_multicast_list ||
- ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
- return -EINVAL;
- if (!netif_device_present(dev))
- return -ENODEV;
- return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data,
- dev->addr_len, 1);
+ if (!dev)
+ return -ENODEV;
- case SIOCDELMULTI:
- if (!dev->set_multicast_list ||
- ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
- return -EINVAL;
- if (!netif_device_present(dev))
- return -ENODEV;
- return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data,
- dev->addr_len, 1);
+ ops = dev->netdev_ops;
- case SIOCGIFINDEX:
- ifr->ifr_ifindex = dev->ifindex;
- return 0;
+ switch (cmd) {
+ case SIOCSIFFLAGS: /* Set interface flags */
+ return dev_change_flags(dev, ifr->ifr_flags);
- case SIOCGIFTXQLEN:
- ifr->ifr_qlen = dev->tx_queue_len;
- return 0;
+ case SIOCSIFMETRIC: /* Set the metric on the interface
+ (currently unused) */
+ return -EOPNOTSUPP;
- case SIOCSIFTXQLEN:
- if (ifr->ifr_qlen < 0)
- return -EINVAL;
- dev->tx_queue_len = ifr->ifr_qlen;
- return 0;
+ case SIOCSIFMTU: /* Set the MTU of a device */
+ return dev_set_mtu(dev, ifr->ifr_mtu);
- case SIOCSIFNAME:
- ifr->ifr_newname[IFNAMSIZ-1] = '\0';
- return dev_change_name(dev, ifr->ifr_newname);
+ case SIOCSIFHWADDR:
+ return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
- /*
- * Unknown or private ioctl
- */
+ case SIOCSIFHWBROADCAST:
+ if (ifr->ifr_hwaddr.sa_family != dev->type)
+ return -EINVAL;
+ memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
+ min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+ return 0;
- default:
- if ((cmd >= SIOCDEVPRIVATE &&
- cmd <= SIOCDEVPRIVATE + 15) ||
- cmd == SIOCBONDENSLAVE ||
- cmd == SIOCBONDRELEASE ||
- cmd == SIOCBONDSETHWADDR ||
- cmd == SIOCBONDSLAVEINFOQUERY ||
- cmd == SIOCBONDINFOQUERY ||
- cmd == SIOCBONDCHANGEACTIVE ||
- cmd == SIOCGMIIPHY ||
- cmd == SIOCGMIIREG ||
- cmd == SIOCSMIIREG ||
- cmd == SIOCBRADDIF ||
- cmd == SIOCBRDELIF ||
- cmd == SIOCWANDEV) {
- err = -EOPNOTSUPP;
- if (dev->do_ioctl) {
- if (netif_device_present(dev))
- err = dev->do_ioctl(dev, ifr,
- cmd);
- else
- err = -ENODEV;
- }
- } else
- err = -EINVAL;
+ case SIOCSIFMAP:
+ if (ops->ndo_set_config) {
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return ops->ndo_set_config(dev, &ifr->ifr_map);
+ }
+ return -EOPNOTSUPP;
+
+ case SIOCADDMULTI:
+ if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
+ ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+ return -EINVAL;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data,
+ dev->addr_len, 1);
+
+ case SIOCDELMULTI:
+ if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
+ ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+ return -EINVAL;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data,
+ dev->addr_len, 1);
+
+ case SIOCSIFTXQLEN:
+ if (ifr->ifr_qlen < 0)
+ return -EINVAL;
+ dev->tx_queue_len = ifr->ifr_qlen;
+ return 0;
+
+ case SIOCSIFNAME:
+ ifr->ifr_newname[IFNAMSIZ-1] = '\0';
+ return dev_change_name(dev, ifr->ifr_newname);
+
+ /*
+ * Unknown or private ioctl
+ */
+ default:
+ if ((cmd >= SIOCDEVPRIVATE &&
+ cmd <= SIOCDEVPRIVATE + 15) ||
+ cmd == SIOCBONDENSLAVE ||
+ cmd == SIOCBONDRELEASE ||
+ cmd == SIOCBONDSETHWADDR ||
+ cmd == SIOCBONDSLAVEINFOQUERY ||
+ cmd == SIOCBONDINFOQUERY ||
+ cmd == SIOCBONDCHANGEACTIVE ||
+ cmd == SIOCGMIIPHY ||
+ cmd == SIOCGMIIREG ||
+ cmd == SIOCSMIIREG ||
+ cmd == SIOCBRADDIF ||
+ cmd == SIOCBRDELIF ||
+ cmd == SIOCSHWTSTAMP ||
+ cmd == SIOCWANDEV) {
+ err = -EOPNOTSUPP;
+ if (ops->ndo_do_ioctl) {
+ if (netif_device_present(dev))
+ err = ops->ndo_do_ioctl(dev, ifr, cmd);
+ else
+ err = -ENODEV;
+ }
+ } else
+ err = -EINVAL;
}
return err;
/**
* dev_ioctl - network device ioctl
+ * @net: the applicable net namespace
* @cmd: command to issue
* @arg: pointer to a struct ifreq in user space
*
* positive or a negative errno code on error.
*/
-int dev_ioctl(unsigned int cmd, void __user *arg)
+int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
{
struct ifreq ifr;
int ret;
if (cmd == SIOCGIFCONF) {
rtnl_lock();
- ret = dev_ifconf((char __user *) arg);
+ ret = dev_ifconf(net, (char __user *) arg);
rtnl_unlock();
return ret;
}
if (cmd == SIOCGIFNAME)
- return dev_ifname((struct ifreq __user *)arg);
+ return dev_ifname(net, (struct ifreq __user *)arg);
if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
return -EFAULT;
*/
switch (cmd) {
- /*
- * These ioctl calls:
- * - can be done by all.
- * - atomic and do not require locking.
- * - return a value
- */
- case SIOCGIFFLAGS:
- case SIOCGIFMETRIC:
- case SIOCGIFMTU:
- case SIOCGIFHWADDR:
- case SIOCGIFSLAVE:
- case SIOCGIFMAP:
- case SIOCGIFINDEX:
- case SIOCGIFTXQLEN:
- dev_load(ifr.ifr_name);
- read_lock(&dev_base_lock);
- ret = dev_ifsioc(&ifr, cmd);
- read_unlock(&dev_base_lock);
- if (!ret) {
- if (colon)
- *colon = ':';
- if (copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- }
- return ret;
+ /*
+ * These ioctl calls:
+ * - can be done by all.
+ * - atomic and do not require locking.
+ * - return a value
+ */
+ case SIOCGIFFLAGS:
+ case SIOCGIFMETRIC:
+ case SIOCGIFMTU:
+ case SIOCGIFHWADDR:
+ case SIOCGIFSLAVE:
+ case SIOCGIFMAP:
+ case SIOCGIFINDEX:
+ case SIOCGIFTXQLEN:
+ dev_load(net, ifr.ifr_name);
+ read_lock(&dev_base_lock);
+ ret = dev_ifsioc_locked(net, &ifr, cmd);
+ read_unlock(&dev_base_lock);
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
- case SIOCETHTOOL:
- dev_load(ifr.ifr_name);
- rtnl_lock();
- ret = dev_ethtool(&ifr);
- rtnl_unlock();
- if (!ret) {
- if (colon)
- *colon = ':';
- if (copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- }
- return ret;
+ case SIOCETHTOOL:
+ dev_load(net, ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ethtool(net, &ifr);
+ rtnl_unlock();
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
- /*
- * These ioctl calls:
- * - require superuser power.
- * - require strict serialization.
- * - return a value
- */
- case SIOCGMIIPHY:
- case SIOCGMIIREG:
- case SIOCSIFNAME:
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
- dev_load(ifr.ifr_name);
- rtnl_lock();
- ret = dev_ifsioc(&ifr, cmd);
- rtnl_unlock();
- if (!ret) {
- if (colon)
- *colon = ':';
- if (copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- }
- return ret;
+ /*
+ * These ioctl calls:
+ * - require superuser power.
+ * - require strict serialization.
+ * - return a value
+ */
+ case SIOCGMIIPHY:
+ case SIOCGMIIREG:
+ case SIOCSIFNAME:
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ dev_load(net, ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ifsioc(net, &ifr, cmd);
+ rtnl_unlock();
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
- /*
- * 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:
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
- /* fall through */
- case SIOCBONDSLAVEINFOQUERY:
- case SIOCBONDINFOQUERY:
- dev_load(ifr.ifr_name);
+ /*
+ * 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);
rtnl_lock();
- ret = dev_ifsioc(&ifr, cmd);
+ ret = dev_ifsioc(net, &ifr, cmd);
rtnl_unlock();
+ if (!ret && copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
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(ifr.ifr_name);
- rtnl_lock();
- ret = dev_ifsioc(&ifr, cmd);
- rtnl_unlock();
- if (!ret && copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- return ret;
- }
- /* Take care of Wireless Extensions */
- if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)
- return wext_handle_ioctl(&ifr, cmd, arg);
- return -EINVAL;
+ }
+ /* 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(void)
+static int dev_new_index(struct net *net)
{
static int ifindex;
for (;;) {
if (++ifindex <= 0)
ifindex = 1;
- if (!__dev_get_by_index(ifindex))
+ if (!__dev_get_by_index(net, ifindex))
return ifindex;
}
}
-static int dev_boot_phase = 1;
-
/* 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_lock(&net_todo_list_lock);
list_add_tail(&dev->todo_list, &net_todo_list);
- 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_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);
+
+ synchronize_net();
+
+ dev_put(dev);
+}
+
+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);
+}
+
+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);
+
/**
* register_netdevice - register a network device
* @dev: device to register
struct hlist_head *head;
struct hlist_node *p;
int ret;
+ struct net *net = dev_net(dev);
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
/* When net_device's are persistent, this will be fatal. */
BUG_ON(dev->reg_state != NETREG_UNINITIALIZED);
+ BUG_ON(!net);
- spin_lock_init(&dev->queue_lock);
- spin_lock_init(&dev->_xmit_lock);
- netdev_set_lockdep_class(&dev->_xmit_lock, dev->type);
- dev->xmit_lock_owner = -1;
- spin_lock_init(&dev->ingress_lock);
+ spin_lock_init(&dev->addr_list_lock);
+ netdev_set_addr_lockdep_class(dev);
+ netdev_init_queue_locks(dev);
dev->iflink = -1;
/* Init, if this function is available */
- if (dev->init) {
- ret = dev->init(dev);
+ if (dev->netdev_ops->ndo_init) {
+ ret = dev->netdev_ops->ndo_init(dev);
if (ret) {
if (ret > 0)
ret = -EIO;
if (!dev_valid_name(dev->name)) {
ret = -EINVAL;
- goto out;
+ goto err_uninit;
}
- dev->ifindex = dev_new_index();
+ dev->ifindex = dev_new_index(net);
if (dev->iflink == -1)
dev->iflink = dev->ifindex;
/* Check for existence of name */
- head = dev_name_hash(dev->name);
+ head = dev_name_hash(net, dev->name);
hlist_for_each(p, head) {
struct net_device *d
= hlist_entry(p, struct net_device, name_hlist);
if (!strncmp(d->name, dev->name, IFNAMSIZ)) {
ret = -EEXIST;
- goto out;
+ goto err_uninit;
}
}
- /* Fix illegal SG+CSUM combinations. */
- if ((dev->features & NETIF_F_SG) &&
- !(dev->features & NETIF_F_ALL_CSUM)) {
- printk(KERN_NOTICE "%s: Dropping NETIF_F_SG since no checksum feature.\n",
+ /* 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_SG;
+ dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
}
- /* TSO requires that SG is present as well. */
- if ((dev->features & NETIF_F_TSO) &&
- !(dev->features & NETIF_F_SG)) {
- printk(KERN_NOTICE "%s: Dropping NETIF_F_TSO since no SG feature.\n",
+ 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_TSO;
- }
- if (dev->features & NETIF_F_UFO) {
- if (!(dev->features & NETIF_F_HW_CSUM)) {
- printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no "
- "NETIF_F_HW_CSUM feature.\n",
- dev->name);
- dev->features &= ~NETIF_F_UFO;
- }
- if (!(dev->features & NETIF_F_SG)) {
- printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no "
- "NETIF_F_SG feature.\n",
- dev->name);
- dev->features &= ~NETIF_F_UFO;
- }
+ dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM);
}
- /*
- * nil rebuild_header routine,
- * that should be never called and used as just bug trap.
- */
+ dev->features = netdev_fix_features(dev->features, dev->name);
- if (!dev->rebuild_header)
- dev->rebuild_header = default_rebuild_header;
+ /* Enable software GSO if SG is supported. */
+ if (dev->features & NETIF_F_SG)
+ dev->features |= NETIF_F_GSO;
- ret = netdev_register_sysfs(dev);
+ netdev_initialize_kobject(dev);
+ ret = netdev_register_kobject(dev);
if (ret)
- goto out;
+ goto err_uninit;
dev->reg_state = NETREG_REGISTERED;
/*
set_bit(__LINK_STATE_PRESENT, &dev->state);
dev_init_scheduler(dev);
- write_lock_bh(&dev_base_lock);
- list_add_tail(&dev->dev_list, &dev_base_head);
- hlist_add_head(&dev->name_hlist, head);
- hlist_add_head(&dev->index_hlist, dev_index_hash(dev->ifindex));
dev_hold(dev);
- write_unlock_bh(&dev_base_lock);
+ list_netdevice(dev);
/* Notify protocols, that a new device appeared. */
- raw_notifier_call_chain(&netdev_chain, NETDEV_REGISTER, dev);
-
- ret = 0;
+ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
+ ret = notifier_to_errno(ret);
+ if (ret) {
+ rollback_registered(dev);
+ dev->reg_state = NETREG_UNREGISTERED;
+ }
out:
return ret;
+
+err_uninit:
+ if (dev->netdev_ops->ndo_uninit)
+ dev->netdev_ops->ndo_uninit(dev);
+ goto out;
+}
+EXPORT_SYMBOL(register_netdevice);
+
+/**
+ * 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
rtnl_lock();
/* Rebroadcast unregister notification */
- raw_notifier_call_chain(&netdev_chain,
- NETDEV_UNREGISTER, dev);
+ call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
if (test_bit(__LINK_STATE_LINKWATCH_PENDING,
&dev->state)) {
* free_netdev(y1);
* free_netdev(y2);
*
- * We are invoked by rtnl_unlock() after it drops the semaphore.
+ * We are invoked by rtnl_unlock().
* This allows us to deal with problems:
* 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.
*/
-static DEFINE_MUTEX(net_todo_run_mutex);
-void netdev_run_todo(void)
-{
- struct list_head list;
-
- /* Need to guard against multiple cpu's getting out of order. */
- mutex_lock(&net_todo_run_mutex);
-
- /* Not safe to do outside the semaphore. We must not return
- * until all unregister events invoked by the local processor
- * have been completed (either by this todo run, or one on
- * another cpu).
- */
- if (list_empty(&net_todo_list))
- goto out;
+void netdev_run_todo(void)
+{
+ struct list_head list;
/* Snapshot list, allow later requests */
- spin_lock(&net_todo_list_lock);
list_replace_init(&net_todo_list, &list);
- spin_unlock(&net_todo_list_lock);
+
+ __rtnl_unlock();
while (!list_empty(&list)) {
struct net_device *dev
dev->reg_state = NETREG_UNREGISTERED;
+ on_each_cpu(flush_backlog, dev, 1);
+
netdev_wait_allrefs(dev);
/* paranoia */
BUG_ON(atomic_read(&dev->refcnt));
- BUG_TRAP(!dev->ip_ptr);
- BUG_TRAP(!dev->ip6_ptr);
- BUG_TRAP(!dev->dn_ptr);
+ 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);
}
+}
-out:
- mutex_unlock(&net_todo_run_mutex);
+/**
+ * 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);
+ else {
+ unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0;
+ struct net_device_stats *stats = &dev->stats;
+ 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;
+ }
+ return stats;
+ }
}
+EXPORT_SYMBOL(dev_get_stats);
-static struct net_device_stats *internal_stats(struct net_device *dev)
+static void netdev_init_one_queue(struct net_device *dev,
+ struct netdev_queue *queue,
+ void *_unused)
{
- return &dev->stats;
+ 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 - allocate network device
+ * 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.
+ * 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(int sizeof_priv, const char *name,
- void (*setup)(struct net_device *))
+struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
+ void (*setup)(struct net_device *), unsigned int queue_count)
{
- void *p;
+ struct netdev_queue *tx;
struct net_device *dev;
- int alloc_size;
+ size_t alloc_size;
+ struct net_device *p;
BUG_ON(strlen(name) >= sizeof(dev->name));
- /* ensure 32-byte alignment of both the device and private area */
- alloc_size = (sizeof(*dev) + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST;
- alloc_size += sizeof_priv + NETDEV_ALIGN_CONST;
+ 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);
if (!p) {
return NULL;
}
- dev = (struct net_device *)
- (((long)p + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST);
+ tx = kcalloc(queue_count, sizeof(struct netdev_queue), GFP_KERNEL);
+ if (!tx) {
+ printk(KERN_ERR "alloc_netdev: Unable to allocate "
+ "tx qdiscs.\n");
+ goto free_p;
+ }
+
+ dev = PTR_ALIGN(p, NETDEV_ALIGN);
dev->padded = (char *)dev - (char *)p;
- if (sizeof_priv)
- dev->priv = netdev_priv(dev);
+ if (dev_addr_init(dev))
+ goto free_tx;
+
+ dev_unicast_init(dev);
- dev->get_stats = internal_stats;
+ dev_net_set(dev, &init_net);
+
+ dev->_tx = tx;
+ dev->num_tx_queues = queue_count;
+ dev->real_num_tx_queues = queue_count;
+
+ dev->gso_max_size = GSO_MAX_SIZE;
+
+ netdev_init_queues(dev);
+
+ INIT_LIST_HEAD(&dev->napi_list);
+ dev->priv_flags = IFF_XMIT_DST_RELEASE;
setup(dev);
strcpy(dev->name, name);
return dev;
+
+free_tx:
+ kfree(tx);
+
+free_p:
+ kfree(p);
+ return NULL;
}
-EXPORT_SYMBOL(alloc_netdev);
+EXPORT_SYMBOL(alloc_netdev_mq);
/**
* free_netdev - free network device
*/
void free_netdev(struct net_device *dev)
{
-#ifdef CONFIG_SYSFS
+ struct napi_struct *p, *n;
+
+ release_net(dev_net(dev));
+
+ kfree(dev->_tx);
+
+ /* Flush device addresses */
+ dev_addr_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);
/* will free via device release */
put_device(&dev->dev);
-#else
- kfree((char *)dev - dev->padded);
-#endif
}
+EXPORT_SYMBOL(free_netdev);
-/* Synchronize with packet receive processing. */
+/**
+ * synchronize_net - Synchronize with packet receive processing
+ *
+ * Wait for packets currently being received to be done.
+ * Does not block later packets from starting.
+ */
void synchronize_net(void)
{
might_sleep();
synchronize_rcu();
}
+EXPORT_SYMBOL(synchronize_net);
/**
* unregister_netdevice - remove device from the kernel
* @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);
+ rollback_registered(dev);
+ /* Finish processing unregister after unlock */
+ net_set_todo(dev);
+}
+EXPORT_SYMBOL(unregister_netdevice);
- WARN_ON(1);
- return;
- }
+/**
+ * unregister_netdev - remove device from the kernel
+ * @dev: device
+ *
+ * This function shuts down a device interface and removes it
+ * 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
+ * unregister_netdevice.
+ */
+void unregister_netdev(struct net_device *dev)
+{
+ rtnl_lock();
+ unregister_netdevice(dev);
+ rtnl_unlock();
+}
+EXPORT_SYMBOL(unregister_netdev);
- BUG_ON(dev->reg_state != NETREG_REGISTERED);
+/**
+ * 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.
+ */
- /* If device is running, close it first. */
- if (dev->flags & IFF_UP)
- dev_close(dev);
+int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat)
+{
+ char buf[IFNAMSIZ];
+ const char *destname;
+ int err;
- /* And unlink it from device chain. */
- write_lock_bh(&dev_base_lock);
- list_del(&dev->dev_list);
- hlist_del(&dev->name_hlist);
- hlist_del(&dev->index_hlist);
- write_unlock_bh(&dev_base_lock);
+ ASSERT_RTNL();
- dev->reg_state = NETREG_UNREGISTERING;
+ /* 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;
+ destname = dev->name;
+ if (__dev_get_by_name(net, destname)) {
+ /* We get here if we can't use the current device name */
+ if (!pat)
+ goto out;
+ if (!dev_valid_name(pat))
+ goto out;
+ if (strchr(pat, '%')) {
+ if (__dev_alloc_name(net, pat, buf) < 0)
+ goto out;
+ destname = buf;
+ } else
+ destname = pat;
+ if (__dev_get_by_name(net, destname))
+ 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.
*/
- raw_notifier_call_chain(&netdev_chain, NETDEV_UNREGISTER, dev);
+ call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
/*
- * Flush the multicast chain
+ * Flush the unicast and multicast chains
*/
- dev_mc_discard(dev);
+ dev_unicast_flush(dev);
+ dev_addr_discard(dev);
- if (dev->uninit)
- dev->uninit(dev);
+ netdev_unregister_kobject(dev);
- /* Notifier chain MUST detach us from master device. */
- BUG_TRAP(!dev->master);
+ /* Actually switch the network namespace */
+ dev_net_set(dev, net);
- /* Remove entries from sysfs */
- netdev_unregister_sysfs(dev);
+ /* Assign the new device name */
+ if (destname != dev->name)
+ strcpy(dev->name, destname);
- /* Finish processing unregister after unlock */
- net_set_todo(dev);
+ /* 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;
+ }
- synchronize_net();
+ /* Fixup kobjects */
+ err = netdev_register_kobject(dev);
+ WARN_ON(err);
- dev_put(dev);
-}
+ /* Add the device back in the hashes */
+ list_netdevice(dev);
-/**
- * unregister_netdev - remove device from the kernel
- * @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.
- *
- * 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();
-}
+ /* Notify protocols, that a new device appeared. */
+ call_netdevice_notifiers(NETDEV_REGISTER, dev);
-EXPORT_SYMBOL(unregister_netdev);
+ synchronize_net();
+ err = 0;
+out:
+ return err;
+}
+EXPORT_SYMBOL_GPL(dev_change_net_namespace);
static int dev_cpu_callback(struct notifier_block *nfb,
unsigned long action,
void *ocpu)
{
struct sk_buff **list_skb;
- struct net_device **list_net;
+ struct Qdisc **list_net;
struct sk_buff *skb;
unsigned int cpu, oldcpu = (unsigned long)ocpu;
struct softnet_data *sd, *oldsd;
return NOTIFY_OK;
}
-#ifdef CONFIG_NET_DMA
+
/**
- * net_dma_rebalance -
- * This is called when the number of channels allocated to the net_dma_client
- * changes. The net_dma_client tries to have one DMA channel per CPU.
+ * netdev_increment_features - increment feature set by one
+ * @all: current feature set
+ * @one: new feature set
+ * @mask: mask feature set
+ *
+ * Computes a new feature set after adding a device with feature set
+ * @one to the master device with current feature set @all. Will not
+ * enable anything that is off in @mask. Returns the new feature set.
*/
-static void net_dma_rebalance(void)
+unsigned long netdev_increment_features(unsigned long all, unsigned long one,
+ unsigned long mask)
{
- unsigned int cpu, i, n;
- struct dma_chan *chan;
+ /* If device needs checksumming, downgrade to it. */
+ if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM))
+ all ^= NETIF_F_NO_CSUM | (one & NETIF_F_ALL_CSUM);
+ else if (mask & NETIF_F_ALL_CSUM) {
+ /* If one device supports v4/v6 checksumming, set for all. */
+ if (one & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM) &&
+ !(all & NETIF_F_GEN_CSUM)) {
+ all &= ~NETIF_F_ALL_CSUM;
+ all |= one & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
+ }
- if (net_dma_count == 0) {
- for_each_online_cpu(cpu)
- rcu_assign_pointer(per_cpu(softnet_data, cpu).net_dma, NULL);
- return;
+ /* If one device supports hw checksumming, set for all. */
+ if (one & NETIF_F_GEN_CSUM && !(all & NETIF_F_GEN_CSUM)) {
+ all &= ~NETIF_F_ALL_CSUM;
+ all |= NETIF_F_HW_CSUM;
+ }
}
- i = 0;
- cpu = first_cpu(cpu_online_map);
+ one |= NETIF_F_ALL_CSUM;
- rcu_read_lock();
- list_for_each_entry(chan, &net_dma_client->channels, client_node) {
- n = ((num_online_cpus() / net_dma_count)
- + (i < (num_online_cpus() % net_dma_count) ? 1 : 0));
-
- while(n) {
- per_cpu(softnet_data, cpu).net_dma = chan;
- cpu = next_cpu(cpu, cpu_online_map);
- n--;
- }
- i++;
- }
- rcu_read_unlock();
+ one |= all & NETIF_F_ONE_FOR_ALL;
+ all &= one | NETIF_F_LLTX | NETIF_F_GSO;
+ all |= one & mask & NETIF_F_ONE_FOR_ALL;
+
+ return all;
}
+EXPORT_SYMBOL(netdev_increment_features);
-/**
- * netdev_dma_event - event callback for the net_dma_client
- * @client: should always be net_dma_client
- * @chan: DMA channel for the event
- * @event: event type
- */
-static void netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
- enum dma_event event)
+static struct hlist_head *netdev_create_hash(void)
{
- spin_lock(&net_dma_event_lock);
- switch (event) {
- case DMA_RESOURCE_ADDED:
- net_dma_count++;
- net_dma_rebalance();
- break;
- case DMA_RESOURCE_REMOVED:
- net_dma_count--;
- net_dma_rebalance();
- break;
- default:
- break;
- }
- spin_unlock(&net_dma_event_lock);
+ int i;
+ struct hlist_head *hash;
+
+ hash = kmalloc(sizeof(*hash) * NETDEV_HASHENTRIES, GFP_KERNEL);
+ if (hash != NULL)
+ for (i = 0; i < NETDEV_HASHENTRIES; i++)
+ INIT_HLIST_HEAD(&hash[i]);
+
+ return hash;
+}
+
+/* Initialize per network namespace state */
+static int __net_init netdev_init(struct net *net)
+{
+ INIT_LIST_HEAD(&net->dev_base_head);
+
+ net->dev_name_head = netdev_create_hash();
+ if (net->dev_name_head == NULL)
+ goto err_name;
+
+ net->dev_index_head = netdev_create_hash();
+ if (net->dev_index_head == NULL)
+ goto err_idx;
+
+ return 0;
+
+err_idx:
+ kfree(net->dev_name_head);
+err_name:
+ return -ENOMEM;
}
/**
- * netdev_dma_regiser - register the networking subsystem as a DMA client
+ * netdev_drivername - network driver for the device
+ * @dev: network device
+ * @buffer: buffer for resulting name
+ * @len: size of buffer
+ *
+ * Determine network driver for device.
*/
-static int __init netdev_dma_register(void)
+char *netdev_drivername(const struct net_device *dev, char *buffer, int len)
{
- spin_lock_init(&net_dma_event_lock);
- net_dma_client = dma_async_client_register(netdev_dma_event);
- if (net_dma_client == NULL)
- return -ENOMEM;
+ const struct device_driver *driver;
+ const struct device *parent;
- dma_async_client_chan_request(net_dma_client, num_online_cpus());
- return 0;
+ if (len <= 0 || !buffer)
+ return buffer;
+ buffer[0] = 0;
+
+ parent = dev->dev.parent;
+
+ if (!parent)
+ return buffer;
+
+ driver = parent->driver;
+ if (driver && driver->name)
+ strlcpy(buffer, driver->name, len);
+ return buffer;
}
-#else
-static int __init netdev_dma_register(void) { return -ENODEV; }
-#endif /* CONFIG_NET_DMA */
+static void __net_exit netdev_exit(struct net *net)
+{
+ kfree(net->dev_name_head);
+ kfree(net->dev_index_head);
+}
+
+static struct pernet_operations __net_initdata netdev_net_ops = {
+ .init = netdev_init,
+ .exit = netdev_exit,
+};
+
+static void __net_exit default_device_exit(struct net *net)
+{
+ struct net_device *dev;
+ /*
+ * Push all migratable of the network devices back to the
+ * initial network namespace
+ */
+ rtnl_lock();
+restart:
+ for_each_netdev(net, dev) {
+ int err;
+ char fb_name[IFNAMSIZ];
+
+ /* Ignore unmoveable devices (i.e. loopback) */
+ if (dev->features & NETIF_F_NETNS_LOCAL)
+ continue;
+
+ /* Delete virtual devices */
+ if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) {
+ dev->rtnl_link_ops->dellink(dev);
+ goto restart;
+ }
+
+ /* Push remaing network devices to init_net */
+ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
+ err = dev_change_net_namespace(dev, &init_net, fb_name);
+ if (err) {
+ printk(KERN_EMERG "%s: failed to move %s to init_net: %d\n",
+ __func__, dev->name, err);
+ BUG();
+ }
+ goto restart;
+ }
+ rtnl_unlock();
+}
+
+static struct pernet_operations __net_initdata default_device_ops = {
+ .exit = default_device_exit,
+};
/*
* Initialize the DEV module. At boot time this walks the device list and
if (dev_proc_init())
goto out;
- if (netdev_sysfs_init())
+ if (netdev_kobject_init())
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]);
- for (i = 0; i < ARRAY_SIZE(dev_name_head); i++)
- INIT_HLIST_HEAD(&dev_name_head[i]);
-
- for (i = 0; i < ARRAY_SIZE(dev_index_head); i++)
- INIT_HLIST_HEAD(&dev_index_head[i]);
+ if (register_pernet_subsys(&netdev_net_ops))
+ goto out;
/*
* Initialise the packet receive queues.
skb_queue_head_init(&queue->input_pkt_queue);
queue->completion_queue = NULL;
INIT_LIST_HEAD(&queue->poll_list);
- set_bit(__LINK_STATE_START, &queue->backlog_dev.state);
- queue->backlog_dev.weight = weight_p;
- queue->backlog_dev.poll = process_backlog;
- atomic_set(&queue->backlog_dev.refcnt, 1);
- }
- netdev_dma_register();
+ queue->backlog.poll = process_backlog;
+ queue->backlog.weight = weight_p;
+ queue->backlog.gro_list = NULL;
+ queue->backlog.gro_count = 0;
+ }
dev_boot_phase = 0;
- open_softirq(NET_TX_SOFTIRQ, net_tx_action, NULL);
- open_softirq(NET_RX_SOFTIRQ, net_rx_action, NULL);
+ /* The loopback device is special if any other network devices
+ * is present in a network namespace the loopback device must
+ * be present. Since we now dynamically allocate and free the
+ * loopback device ensure this invariant is maintained by
+ * keeping the loopback device as the first device on the
+ * list of network devices. Ensuring the loopback devices
+ * is the first device that appears and the last network device
+ * that disappears.
+ */
+ if (register_pernet_device(&loopback_net_ops))
+ goto out;
+
+ if (register_pernet_device(&default_device_ops))
+ goto out;
+
+ open_softirq(NET_TX_SOFTIRQ, net_tx_action);
+ open_softirq(NET_RX_SOFTIRQ, net_rx_action);
hotcpu_notifier(dev_cpu_callback, 0);
dst_init();
subsys_initcall(net_dev_init);
-EXPORT_SYMBOL(__dev_get_by_index);
-EXPORT_SYMBOL(__dev_get_by_name);
-EXPORT_SYMBOL(__dev_remove_pack);
-EXPORT_SYMBOL(dev_valid_name);
-EXPORT_SYMBOL(dev_add_pack);
-EXPORT_SYMBOL(dev_alloc_name);
-EXPORT_SYMBOL(dev_close);
-EXPORT_SYMBOL(dev_get_by_flags);
-EXPORT_SYMBOL(dev_get_by_index);
-EXPORT_SYMBOL(dev_get_by_name);
-EXPORT_SYMBOL(dev_open);
-EXPORT_SYMBOL(dev_queue_xmit);
-EXPORT_SYMBOL(dev_remove_pack);
-EXPORT_SYMBOL(dev_set_allmulti);
-EXPORT_SYMBOL(dev_set_promiscuity);
-EXPORT_SYMBOL(dev_change_flags);
-EXPORT_SYMBOL(dev_set_mtu);
-EXPORT_SYMBOL(dev_set_mac_address);
-EXPORT_SYMBOL(free_netdev);
-EXPORT_SYMBOL(netdev_boot_setup_check);
-EXPORT_SYMBOL(netdev_set_master);
-EXPORT_SYMBOL(netdev_state_change);
-EXPORT_SYMBOL(netif_receive_skb);
-EXPORT_SYMBOL(netif_rx);
-EXPORT_SYMBOL(register_gifconf);
-EXPORT_SYMBOL(register_netdevice);
-EXPORT_SYMBOL(register_netdevice_notifier);
-EXPORT_SYMBOL(skb_checksum_help);
-EXPORT_SYMBOL(synchronize_net);
-EXPORT_SYMBOL(unregister_netdevice);
-EXPORT_SYMBOL(unregister_netdevice_notifier);
-EXPORT_SYMBOL(net_enable_timestamp);
-EXPORT_SYMBOL(net_disable_timestamp);
-EXPORT_SYMBOL(dev_get_flags);
-
-#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)
-EXPORT_SYMBOL(br_handle_frame_hook);
-EXPORT_SYMBOL(br_fdb_get_hook);
-EXPORT_SYMBOL(br_fdb_put_hook);
-#endif
+static int __init initialize_hashrnd(void)
+{
+ get_random_bytes(&skb_tx_hashrnd, sizeof(skb_tx_hashrnd));
+ return 0;
+}
-#ifdef CONFIG_KMOD
-EXPORT_SYMBOL(dev_load);
-#endif
+late_initcall_sync(initialize_hashrnd);
-EXPORT_PER_CPU_SYMBOL(softnet_data);