#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/netpoll.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
-#include <linux/wireless.h>
+#include <net/wext.h>
#include <net/iw_handler.h>
#include <asm/current.h>
#include <linux/audit.h>
#include <linux/dmaengine.h>
#include <linux/err.h>
#include <linux/ctype.h>
+#include <linux/if_arp.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/jhash.h>
+#include <linux/random.h>
+
+#include "net-sysfs.h"
/*
* 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]; /* 16 way hashed list */
-static struct list_head ptype_all; /* Taps */
+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;
+struct net_dma {
+ struct dma_client client;
+ spinlock_t lock;
+ cpumask_t channel_mask;
+ struct dma_chan **channels;
+};
+
+static enum dma_state_client
+netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
+ enum dma_state state);
+
+static struct net_dma net_dma = {
+ .client = {
+ .event_callback = netdev_dma_event,
+ },
+};
#endif
/*
- * The @dev_base list is protected by @dev_base_lock and the rtnl
+ * The @dev_base_head list is protected by @dev_base_lock and the rtnl
* semaphore.
*
* Pure readers hold dev_base_lock for reading.
*
* Writers must hold the rtnl semaphore while they loop through the
- * dev_base list, and hold dev_base_lock for writing when they do the
+ * dev_base_head list, and hold dev_base_lock for writing when they do the
* actual updates. This allows pure readers to access the list even
* while a writer is preparing to update it.
*
* unregister_netdevice(), which must be called with the rtnl
* semaphore held.
*/
-struct net_device *dev_base;
-static struct net_device **dev_tail = &dev_base;
DEFINE_RWLOCK(dev_base_lock);
-EXPORT_SYMBOL(dev_base);
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 *);
+DEFINE_PER_CPU(struct softnet_data, softnet_data);
+
+#ifdef CONFIG_LOCKDEP
+/*
+ * register_netdevice() inits txq->_xmit_lock and sets lockdep class
+ * according to dev->type
+ */
+static const unsigned short netdev_lock_type[] =
+ {ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25,
+ ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET,
+ ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM,
+ ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP,
+ ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD,
+ ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25,
+ ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP,
+ ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD,
+ ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI,
+ ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE,
+ 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};
+
+static const char *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_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP",
+ "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD",
+ "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25",
+ "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP",
+ "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",
+ "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI",
+ "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
+ "_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"};
+
+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)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++)
+ if (netdev_lock_type[i] == dev_type)
+ return i;
+ /* the last key is used by default */
+ return ARRAY_SIZE(netdev_lock_type) - 1;
+}
+
+static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
+ unsigned short dev_type)
+{
+ int i;
+
+ i = netdev_lock_pos(dev_type);
+ 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
-#define netdev_sysfs_init() (0)
-#define netdev_register_sysfs(dev) (0)
-#define netdev_unregister_sysfs(dev) do { } while(0)
+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
-
/*******************************************************************************
Protocol management and registration routines
*******************************************************************************/
/*
- * For efficiency
- */
-
-static int netdev_nit;
-
-/*
* Add a protocol ID to the list. Now that the input handler is
* smarter we can dispense with all the messy stuff that used to be
* here.
int hash;
spin_lock_bh(&ptype_lock);
- if (pt->type == htons(ETH_P_ALL)) {
- netdev_nit++;
+ if (pt->type == htons(ETH_P_ALL))
list_add_rcu(&pt->list, &ptype_all);
- } else {
- hash = ntohs(pt->type) & 15;
+ else {
+ hash = ntohs(pt->type) & PTYPE_HASH_MASK;
list_add_rcu(&pt->list, &ptype_base[hash]);
}
spin_unlock_bh(&ptype_lock);
spin_lock_bh(&ptype_lock);
- if (pt->type == htons(ETH_P_ALL)) {
- netdev_nit--;
+ if (pt->type == htons(ETH_P_ALL))
head = &ptype_all;
- } else
- head = &ptype_base[ntohs(pt->type) & 15];
+ else
+ head = &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK];
list_for_each_entry(pt1, head, list) {
if (pt == pt1) {
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;
* 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))
/**
* 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);
/**
* __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)
/**
* 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);
/**
* 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 (dev = dev_base; dev; dev = dev->next)
+ for_each_netdev(net, dev)
if (dev->type == type &&
!memcmp(dev->dev_addr, ha, dev->addr_len))
- break;
- return dev;
+ 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(net, dev)
+ if (dev->type == type)
+ return dev;
+
+ return NULL;
+}
+
+EXPORT_SYMBOL(__dev_getfirstbyhwtype);
+
+struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
{
struct net_device *dev;
rtnl_lock();
- for (dev = dev_base; dev; dev = dev->next) {
- if (dev->type == type) {
- dev_hold(dev);
- break;
- }
- }
+ dev = __dev_getfirstbyhwtype(net, type);
+ if (dev)
+ dev_hold(dev);
rtnl_unlock();
return dev;
}
/**
* 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;
+ struct net_device *dev, *ret;
+ ret = NULL;
read_lock(&dev_base_lock);
- for (dev = dev_base; dev != NULL; dev = dev->next) {
+ for_each_netdev(net, dev) {
if (((dev->flags ^ if_flags) & mask) == 0) {
dev_hold(dev);
+ ret = dev;
break;
}
}
read_unlock(&dev_base_lock);
- return dev;
+ return ret;
}
/**
}
/**
- * 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 (d = dev_base; d; d = d->next) {
+ 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;
+}
+
/**
* 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);
+rollback:
err = device_rename(&dev->dev, dev->name);
- if (!err) {
- 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);
+ if (err) {
+ memcpy(dev->name, oldname, IFNAMSIZ);
+ return err;
+ }
+
+ write_lock_bh(&dev_base_lock);
+ hlist_del(&dev->name_hlist);
+ 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) {
+ if (err) {
+ printk(KERN_ERR
+ "%s: name change rollback failed: %d.\n",
+ dev->name, ret);
+ } else {
+ err = ret;
+ memcpy(dev->name, oldname, IFNAMSIZ);
+ goto rollback;
+ }
}
return err;
}
/**
+ * dev_set_alias - change ifalias of a device
+ * @dev: device
+ * @alias: name up to IFALIASZ
+ *
+ * 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);
}
}
+void netdev_bonding_change(struct net_device *dev)
+{
+ call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, 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))
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;
-}
-
-
/**
* dev_open - prepare an interface for use.
* @dev: device to open
{
int ret = 0;
+ ASSERT_RTNL();
+
/*
* Is it already up?
*/
* Call device private open method
*/
set_bit(__LINK_STATE_START, &dev->state);
- if (dev->open) {
+
+ if (dev->validate_addr)
+ ret = dev->validate_addr(dev);
+
+ if (!ret && dev->open)
ret = dev->open(dev);
- if (ret)
- clear_bit(__LINK_STATE_START, &dev->state);
- }
/*
* If it went open OK then:
*/
- if (!ret) {
+ if (ret)
+ clear_bit(__LINK_STATE_START, &dev->state);
+ else {
/*
* Set the flags.
*/
/*
* 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;
}
*/
int dev_close(struct net_device *dev)
{
+ 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.
/*
* Tell people we are down
*/
- raw_notifier_call_chain(&netdev_chain, NETDEV_DOWN, dev);
+ call_netdevice_notifiers(NETDEV_DOWN, dev);
return 0;
}
+/**
+ * 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 (dev = dev_base; dev; dev = dev->next) {
- 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;
}
/**
/**
* 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_dec(&netstamp_needed);
}
-void __net_timestamp(struct sk_buff *skb)
-{
- struct timeval tv;
-
- do_gettimeofday(&tv);
- skb_set_timestamp(skb, &tv);
-}
-EXPORT_SYMBOL(__net_timestamp);
-
static inline void net_timestamp(struct sk_buff *skb)
{
if (atomic_read(&netstamp_needed))
__net_timestamp(skb);
- else {
- skb->tstamp.off_sec = 0;
- skb->tstamp.off_usec = 0;
- }
+ else
+ skb->tstamp.tv64 = 0;
}
/*
set by sender, so that the second statement is
just protection against buggy protocols.
*/
- skb2->mac.raw = skb2->data;
+ skb_reset_mac_header(skb2);
- if (skb2->nh.raw < skb2->data ||
- skb2->nh.raw > skb2->tail) {
+ if (skb_network_header(skb2) < skb2->data ||
+ skb2->network_header > skb2->tail) {
if (net_ratelimit())
printk(KERN_CRIT "protocol %04x is "
"buggy, dev %s\n",
skb2->protocol, dev->name);
- skb2->nh.raw = skb2->data;
+ skb_reset_network_header(skb2);
}
- skb2->h.raw = skb2->nh.raw;
+ skb2->transport_header = skb2->network_header;
skb2->pkt_type = PACKET_OUTGOING;
ptype->func(skb2, skb->dev, ptype, skb->dev);
}
}
-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) &&
}
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) &&
}
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)));
+}
+
+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
int skb_checksum_help(struct sk_buff *skb)
{
__wsum csum;
- int ret = 0, offset = skb->h.raw - skb->data;
+ int ret = 0, offset;
if (skb->ip_summed == CHECKSUM_COMPLETE)
goto out_set_summed;
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;
}
- BUG_ON(offset > (int)skb->len);
- csum = skb_checksum(skb, offset, skb->len-offset, 0);
-
- offset = skb->tail - skb->h.raw;
- BUG_ON(offset <= 0);
- BUG_ON(skb->csum_offset + 2 > offset);
-
- *(__sum16*)(skb->h.raw + skb->csum_offset) = csum_fold(csum);
-
+ *(__sum16 *)(skb->data + offset) = csum_fold(csum);
out_set_summed:
skb->ip_summed = CHECKSUM_NONE;
out:
BUG_ON(skb_shinfo(skb)->frag_list);
- skb->mac.raw = skb->data;
- skb->mac_len = skb->nh.raw - skb->data;
+ skb_reset_mac_header(skb);
+ skb->mac_len = skb->network_header - skb->mac_header;
__skb_pull(skb, skb->mac_len);
- if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
+ if (WARN_ON(skb->ip_summed != CHECKSUM_PARTIAL)) {
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);
segs = ERR_PTR(err);
if (err || skb_gso_ok(skb, features))
break;
- __skb_push(skb, skb->data - skb->nh.raw);
+ __skb_push(skb, (skb->data -
+ skb_network_header(skb)));
}
segs = ptype->gso_segment(skb, features);
break;
}
rcu_read_unlock();
- __skb_push(skb, skb->data - skb->mac.raw);
+ __skb_push(skb, skb->data - skb_mac_header(skb));
return segs;
}
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)
{
if (likely(!skb->next)) {
- if (netdev_nit)
+ if (!list_empty(&ptype_all))
dev_queue_xmit_nit(skb, dev);
if (netif_needs_gso(dev, skb)) {
skb->next = nskb;
return rc;
}
- if (unlikely(netif_queue_stopped(dev) && skb->next))
+ if (unlikely(netif_tx_queue_stopped(txq) && skb->next))
return NETDEV_TX_BUSY;
} while (skb->next);
return 0;
}
-#define HARD_TX_LOCK(dev, cpu) { \
- if ((dev->features & NETIF_F_LLTX) == 0) { \
- netif_tx_lock(dev); \
- } \
-}
+static u32 simple_tx_hashrnd;
+static int simple_tx_hashrnd_initialized = 0;
-#define HARD_TX_UNLOCK(dev) { \
- if ((dev->features & NETIF_F_LLTX) == 0) { \
- netif_tx_unlock(dev); \
- } \
-}
+static u16 simple_tx_hash(struct net_device *dev, struct sk_buff *skb)
+{
+ u32 addr1, addr2, ports;
+ u32 hash, ihl;
+ u8 ip_proto;
-/**
- * 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.
- *
- * A negative errno code is returned on a failure. A success does not
- * guarantee the frame will be transmitted as it may be dropped due
- * to congestion or traffic shaping.
- *
- * -----------------------------------------------------------------------------------
- * I notice this method can also return errors from the queue disciplines,
- * including NET_XMIT_DROP, which is a positive value. So, errors can also
+ if (unlikely(!simple_tx_hashrnd_initialized)) {
+ get_random_bytes(&simple_tx_hashrnd, 4);
+ simple_tx_hashrnd_initialized = 1;
+ }
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ ip_proto = ip_hdr(skb)->protocol;
+ addr1 = ip_hdr(skb)->saddr;
+ addr2 = ip_hdr(skb)->daddr;
+ ihl = ip_hdr(skb)->ihl;
+ break;
+ case htons(ETH_P_IPV6):
+ ip_proto = ipv6_hdr(skb)->nexthdr;
+ addr1 = ipv6_hdr(skb)->saddr.s6_addr32[3];
+ addr2 = ipv6_hdr(skb)->daddr.s6_addr32[3];
+ ihl = (40 >> 2);
+ break;
+ default:
+ return 0;
+ }
+
+
+ switch (ip_proto) {
+ case IPPROTO_TCP:
+ case IPPROTO_UDP:
+ case IPPROTO_DCCP:
+ case IPPROTO_ESP:
+ case IPPROTO_AH:
+ case IPPROTO_SCTP:
+ case IPPROTO_UDPLITE:
+ ports = *((u32 *) (skb_network_header(skb) + (ihl * 4)));
+ break;
+
+ default:
+ ports = 0;
+ break;
+ }
+
+ hash = jhash_3words(addr1, addr2, ports, simple_tx_hashrnd);
+
+ return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32);
+}
+
+static struct netdev_queue *dev_pick_tx(struct net_device *dev,
+ struct sk_buff *skb)
+{
+ u16 queue_index = 0;
+
+ if (dev->select_queue)
+ queue_index = dev->select_queue(dev, skb);
+ else if (dev->real_num_tx_queues > 1)
+ queue_index = simple_tx_hash(dev, skb);
+
+ skb_set_queue_mapping(skb, queue_index);
+ return netdev_get_tx_queue(dev, queue_index);
+}
+
+/**
+ * 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.
+ *
+ * A negative errno code is returned on a failure. A success does not
+ * guarantee the frame will be transmitted as it may be dropped due
+ * to congestion or traffic shaping.
+ *
+ * -----------------------------------------------------------------------------------
+ * I notice this method can also return errors from the queue disciplines,
+ * including NET_XMIT_DROP, which is a positive value. So, errors can also
* be positive.
*
* Regardless of the return value, the skb is consumed, so it is currently
* 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 packet is not checksummed and device does not support
* checksumming for this protocol, complete checksumming here.
*/
- if (skb->ip_summed == CHECKSUM_PARTIAL &&
- (!(dev->features & NETIF_F_GEN_CSUM) &&
- (!(dev->features & NETIF_F_IP_CSUM) ||
- skb->protocol != htons(ETH_P_IP))))
- if (skb_checksum_help(skb))
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ skb_set_transport_header(skb, skb->csum_start -
+ skb_headroom(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);
#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;
+ spinlock_t *root_lock = qdisc_lock(q);
+
+ spin_lock(root_lock);
+
+ if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
+ kfree_skb(skb);
+ rc = NET_XMIT_DROP;
+ } else {
+ rc = qdisc_enqueue_root(skb, q);
+ qdisc_run(q);
}
- spin_unlock(&dev->queue_lock);
+ spin_unlock(root_lock);
+
+ 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)) {
+ if (!netif_tx_queue_stopped(txq)) {
rc = 0;
- if (!dev_hard_start_xmit(skb, dev)) {
- HARD_TX_UNLOCK(dev);
+ 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);
Receiver routines
=======================================================================*/
-int netdev_max_backlog = 1000;
-int netdev_budget = 300;
-int weight_p = 64; /* old backlog weight */
+int netdev_max_backlog __read_mostly = 1000;
+int netdev_budget __read_mostly = 300;
+int weight_p __read_mostly = 64; /* old backlog weight */
DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
*
* 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 (netpoll_rx(skb))
return NET_RX_DROP;
- if (!skb->tstamp.off_sec)
+ if (!skb->tstamp.tv64)
net_timestamp(skb);
/*
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;
}
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);
+ }
}
}
}
}
-static __inline__ int deliver_skb(struct sk_buff *skb,
- struct packet_type *pt_prev,
- struct net_device *orig_dev)
+static inline int deliver_skb(struct sk_buff *skb,
+ struct packet_type *pt_prev,
+ struct net_device *orig_dev)
{
atomic_inc(&skb->users);
return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}
#if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE)
-int (*br_handle_frame_hook)(struct net_bridge_port *p, struct sk_buff **pskb);
+/* 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);
+void (*br_fdb_put_hook)(struct net_bridge_fdb_entry *ent) __read_mostly;
-static __inline__ int handle_bridge(struct sk_buff **pskb,
- struct packet_type **pt_prev, int *ret,
- struct net_device *orig_dev)
+/*
+ * If bridge module is loaded call bridging hook.
+ * returns NULL if packet was consumed.
+ */
+struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p,
+ struct sk_buff *skb) __read_mostly;
+static inline struct sk_buff *handle_bridge(struct sk_buff *skb,
+ struct packet_type **pt_prev, int *ret,
+ struct net_device *orig_dev)
{
struct net_bridge_port *port;
- if ((*pskb)->pkt_type == PACKET_LOOPBACK ||
- (port = rcu_dereference((*pskb)->dev->br_port)) == NULL)
- return 0;
+ if (skb->pkt_type == PACKET_LOOPBACK ||
+ (port = rcu_dereference(skb->dev->br_port)) == NULL)
+ return skb;
if (*pt_prev) {
- *ret = deliver_skb(*pskb, *pt_prev, orig_dev);
+ *ret = deliver_skb(skb, *pt_prev, orig_dev);
*pt_prev = NULL;
}
- return br_handle_frame_hook(port, pskb);
+ return br_handle_frame_hook(port, skb);
+}
+#else
+#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_bridge(skb, pt_prev, ret, orig_dev) (0)
+#define handle_macvlan(skb, pt_prev, ret, orig_dev) (skb)
#endif
#ifdef CONFIG_NET_CLS_ACT
*/
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 (%s->%s)\n",
- skb->input_dev->name, skb->dev->name);
- 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))
+ if (netpoll_receive_skb(skb))
return NET_RX_DROP;
- if (!skb->tstamp.off_sec)
+ if (!skb->tstamp.tv64)
net_timestamp(skb);
- if (!skb->input_dev)
- skb->input_dev = skb->dev;
-
- orig_dev = skb_bond(skb);
+ if (!skb->iif)
+ skb->iif = skb->dev->ifindex;
- 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++;
- skb->h.raw = skb->nh.raw = skb->data;
- skb->mac_len = skb->nh.raw - skb->mac.raw;
+ skb_reset_network_header(skb);
+ skb_reset_transport_header(skb);
+ skb->mac_len = skb->network_header - skb->mac_header;
pt_prev = NULL;
rcu_read_lock();
+ /* Don't receive packets in an exiting network namespace */
+ if (!net_alive(dev_net(skb->dev)))
+ goto out;
+
#ifdef CONFIG_NET_CLS_ACT
if (skb->tc_verd & TC_NCLS) {
skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
#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
- if (handle_bridge(&skb, &pt_prev, &ret, orig_dev))
+ 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;
return ret;
}
-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)
+{
+ struct net_device *dev = arg;
+ struct softnet_data *queue = &__get_cpu_var(softnet_data);
+ struct sk_buff *skb, *tmp;
+
+ skb_queue_walk_safe(&queue->input_pkt_queue, skb, tmp)
+ if (skb->dev == dev) {
+ __skb_unlink(skb, &queue->input_pkt_queue);
+ kfree_skb(skb);
+ }
+}
+
+static int process_backlog(struct napi_struct *napi, int quota)
{
int work = 0;
- int quota = min(backlog_dev->quota, *budget);
struct softnet_data *queue = &__get_cpu_var(softnet_data);
unsigned long start_time = jiffies;
- backlog_dev->weight = weight_p;
- for (;;) {
+ napi->weight = weight_p;
+ do {
struct sk_buff *skb;
- struct net_device *dev;
local_irq_disable();
skb = __skb_dequeue(&queue->input_pkt_queue);
- if (!skb)
- goto job_done;
+ if (!skb) {
+ __napi_complete(napi);
+ local_irq_enable();
+ break;
+ }
local_irq_enable();
- dev = skb->dev;
-
netif_receive_skb(skb);
+ } while (++work < quota && jiffies == start_time);
- dev_put(dev);
-
- work++;
-
- if (work >= quota || jiffies - start_time > 1)
- break;
-
- }
-
- backlog_dev->quota -= work;
- *budget -= work;
- return -1;
-
-job_done:
- backlog_dev->quota -= work;
- *budget -= work;
+ return work;
+}
- list_del(&backlog_dev->poll_list);
- smp_mb__before_clear_bit();
- netif_poll_enable(backlog_dev);
+/**
+ * __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_enable();
- return 0;
+ 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);
+
static void net_rx_action(struct softirq_action *h)
{
- struct softnet_data *queue = &__get_cpu_var(softnet_data);
+ struct list_head *list = &__get_cpu_var(softnet_data).poll_list;
unsigned long start_time = jiffies;
int budget = netdev_budget;
void *have;
local_irq_disable();
- while (!list_empty(&queue->poll_list)) {
- struct net_device *dev;
+ while (!list_empty(list)) {
+ struct napi_struct *n;
+ int work, weight;
- if (budget <= 0 || jiffies - start_time > 1)
+ /* If softirq window is exhuasted then punt.
+ *
+ * Note that this is a slight policy change from the
+ * previous NAPI code, which would allow up to 2
+ * jiffies to pass before breaking out. The test
+ * used to be "jiffies - start_time > 1".
+ */
+ if (unlikely(budget <= 0 || jiffies != start_time))
goto softnet_break;
local_irq_enable();
- dev = list_entry(queue->poll_list.next,
- struct net_device, poll_list);
- have = netpoll_poll_lock(dev);
+ /* 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);
+
+ WARN_ON_ONCE(work > weight);
+
+ budget -= work;
+
+ local_irq_disable();
- 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;
+ /* 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)))
+ __napi_complete(n);
else
- dev->quota = dev->weight;
- } else {
- netpoll_poll_unlock(have);
- dev_put(dev);
- local_irq_disable();
+ 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
*/
- 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();
+ if (!cpus_empty(net_dma.channel_mask)) {
+ int chan_idx;
+ for_each_cpu_mask_nr(chan_idx, net_dma.channel_mask) {
+ struct dma_chan *chan = net_dma.channels[chan_idx];
+ if (chan)
+ dma_async_memcpy_issue_pending(chan);
+ }
}
#endif
- local_irq_enable();
+
return;
softnet_break:
* match. --pb
*/
-static int dev_ifname(struct ifreq __user *arg)
+static int dev_ifname(struct net *net, struct ifreq __user *arg)
{
struct net_device *dev;
struct ifreq ifr;
return -EFAULT;
read_lock(&dev_base_lock);
- dev = __dev_get_by_index(ifr.ifr_ifindex);
+ dev = __dev_get_by_index(net, ifr.ifr_ifindex);
if (!dev) {
read_unlock(&dev_base_lock);
return -ENODEV;
* 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 (dev = dev_base; dev; dev = dev->next) {
+ for_each_netdev(net, dev) {
for (i = 0; i < NPROTO; i++) {
if (gifconf_list[i]) {
int done;
* This is invoked by the /proc filesystem handler to display a device
* in detail.
*/
-static __inline__ struct net_device *dev_get_idx(loff_t pos)
+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;
- loff_t i;
- for (i = 0, dev = dev_base; dev && i < pos; ++i, dev = dev->next);
+ read_lock(&dev_base_lock);
+ if (!*pos)
+ return SEQ_START_TOKEN;
- return i == pos ? dev : NULL;
-}
+ off = 1;
+ for_each_netdev(net, dev)
+ if (off++ == *pos)
+ return dev;
-void *dev_seq_start(struct seq_file *seq, loff_t *pos)
-{
- read_lock(&dev_base_lock);
- return *pos ? dev_get_idx(*pos - 1) : SEQ_START_TOKEN;
+ return NULL;
}
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 ? dev_base : ((struct net_device *)v)->next;
+ return v == SEQ_START_TOKEN ?
+ first_net_device(net) : next_net_device((struct net_device *)v);
}
void dev_seq_stop(struct seq_file *seq, void *v)
+ __releases(dev_base_lock)
{
read_unlock(&dev_base_lock);
}
static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
{
- if (dev->get_stats) {
- 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",
- dev->name, stats->rx_bytes, stats->rx_packets,
- stats->rx_errors,
- stats->rx_dropped + stats->rx_missed_errors,
- stats->rx_fifo_errors,
- stats->rx_length_errors + stats->rx_over_errors +
- stats->rx_crc_errors + stats->rx_frame_errors,
- stats->rx_compressed, stats->multicast,
- stats->tx_bytes, stats->tx_packets,
- stats->tx_errors, stats->tx_dropped,
- stats->tx_fifo_errors, stats->collisions,
- stats->tx_carrier_errors +
- stats->tx_aborted_errors +
- stats->tx_window_errors +
- stats->tx_heartbeat_errors,
- stats->tx_compressed);
- } else
- seq_printf(seq, "%6s: No statistics available.\n", dev->name);
+ 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",
+ dev->name, stats->rx_bytes, stats->rx_packets,
+ stats->rx_errors,
+ stats->rx_dropped + stats->rx_missed_errors,
+ stats->rx_fifo_errors,
+ stats->rx_length_errors + stats->rx_over_errors +
+ stats->rx_crc_errors + stats->rx_frame_errors,
+ stats->rx_compressed, stats->multicast,
+ stats->tx_bytes, stats->tx_packets,
+ stats->tx_errors, stats->tx_dropped,
+ stats->tx_fifo_errors, stats->collisions,
+ stats->tx_carrier_errors +
+ stats->tx_aborted_errors +
+ stats->tx_window_errors +
+ stats->tx_heartbeat_errors,
+ stats->tx_compressed);
}
/*
{
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;
return 0;
}
-static struct seq_operations dev_seq_ops = {
+static const struct seq_operations dev_seq_ops = {
.start = dev_seq_start,
.next = dev_seq_next,
.stop = dev_seq_stop,
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 struct seq_operations softnet_seq_ops = {
+static const struct seq_operations softnet_seq_ops = {
.start = softnet_seq_start,
.next = softnet_seq_next,
.stop = softnet_seq_stop,
.release = seq_release,
};
-#ifdef CONFIG_WIRELESS_EXT
-extern int wireless_proc_init(void);
-#else
-#define wireless_proc_init() 0
+static void *ptype_get_idx(loff_t pos)
+{
+ struct packet_type *pt = NULL;
+ loff_t i = 0;
+ int t;
+
+ list_for_each_entry_rcu(pt, &ptype_all, list) {
+ if (i == pos)
+ return pt;
+ ++i;
+ }
+
+ for (t = 0; t < PTYPE_HASH_SIZE; t++) {
+ list_for_each_entry_rcu(pt, &ptype_base[t], list) {
+ if (i == pos)
+ return pt;
+ ++i;
+ }
+ }
+ return NULL;
+}
+
+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;
+}
+
+static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ struct packet_type *pt;
+ struct list_head *nxt;
+ int hash;
+
+ ++*pos;
+ if (v == SEQ_START_TOKEN)
+ return ptype_get_idx(0);
+
+ pt = v;
+ nxt = pt->list.next;
+ if (pt->type == htons(ETH_P_ALL)) {
+ if (nxt != &ptype_all)
+ goto found;
+ hash = 0;
+ nxt = ptype_base[0].next;
+ } else
+ hash = ntohs(pt->type) & PTYPE_HASH_MASK;
+
+ while (nxt == &ptype_base[hash]) {
+ if (++hash >= PTYPE_HASH_SIZE)
+ return NULL;
+ nxt = ptype_base[hash].next;
+ }
+found:
+ return list_entry(nxt, struct packet_type, list);
+}
+
+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
-static int __init dev_proc_init(void)
+ 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 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');
+ }
+
+ return 0;
+}
+
+static const struct seq_operations ptype_seq_ops = {
+ .start = ptype_seq_start,
+ .next = ptype_seq_next,
+ .stop = ptype_seq_stop,
+ .show = ptype_seq_show,
+};
+
+static int ptype_seq_open(struct inode *inode, struct file *file)
+{
+ return seq_open_net(inode, file, &ptype_seq_ops,
+ sizeof(struct seq_net_private));
+}
+
+static const struct file_operations ptype_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = ptype_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_net,
+};
+
+
+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 (wireless_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("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
-#endif /* CONFIG_PROC_FS */
+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 */
+
+
+/**
* netdev_set_master - set up master/slave pair
* @slave: slave device
* @master: new master device
return 0;
}
+static int __dev_set_promiscuity(struct net_device *dev, int inc)
+{
+ unsigned short old_flags = dev->flags;
+
+ 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)
+ audit_log(current->audit_context, GFP_ATOMIC,
+ AUDIT_ANOM_PROMISCUOUS,
+ "dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u",
+ dev->name, (dev->flags & IFF_PROMISC),
+ (old_flags & IFF_PROMISC),
+ audit_get_loginuid(current),
+ current->uid, current->gid,
+ audit_get_sessionid(current));
+
+ if (dev->change_rx_flags)
+ dev->change_rx_flags(dev, IFF_PROMISC);
+ }
+ return 0;
+}
+
/**
* dev_set_promiscuity - update promiscuity count on a device
* @dev: 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;
}
/**
* 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.
*/
-void dev_set_allmulti(struct net_device *dev, int inc)
+int dev_set_allmulti(struct net_device *dev, int inc)
{
unsigned short old_flags = dev->flags;
+ ASSERT_RTNL();
+
dev->flags |= IFF_ALLMULTI;
- if ((dev->allmulti += inc) == 0)
- dev->flags &= ~IFF_ALLMULTI;
- if (dev->flags ^ old_flags)
- dev_mc_upload(dev);
+ 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) {
+ if (dev->change_rx_flags)
+ dev->change_rx_flags(dev, IFF_ALLMULTI);
+ dev_set_rx_mode(dev);
+ }
+ return 0;
+}
+
+/*
+ * 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)
+{
+ /* 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 (dev->set_rx_mode)
+ dev->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 (dev->set_multicast_list)
+ dev->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);
+}
+
+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
+ * @alen: length of @addr
+ *
+ * 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 alen)
+{
+ int err;
+
+ ASSERT_RTNL();
+
+ netif_addr_lock_bh(dev);
+ err = __dev_addr_delete(&dev->uc_list, &dev->uc_count, addr, alen, 0);
+ 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
+ * @alen: length of @addr
+ *
+ * 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 alen)
+{
+ int err;
+
+ ASSERT_RTNL();
+
+ netif_addr_lock_bh(dev);
+ err = __dev_addr_add(&dev->uc_list, &dev->uc_count, addr, alen, 0);
+ 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;
+}
+
+void __dev_addr_unsync(struct dev_addr_list **to, int *to_count,
+ struct dev_addr_list **from, int *from_count)
+{
+ struct dev_addr_list *da, *next;
+
+ da = *from;
+ while (da != NULL) {
+ next = da->next;
+ if (da->da_synced) {
+ __dev_addr_delete(to, to_count,
+ da->da_addr, da->da_addrlen, 0);
+ da->da_synced = 0;
+ __dev_addr_delete(from, from_count,
+ da->da_addr, da->da_addrlen, 0);
+ }
+ da = next;
+ }
+}
+
+/**
+ * dev_unicast_sync - Synchronize device's unicast list to another device
+ * @to: destination device
+ * @from: source device
+ *
+ * Add newly added addresses to the destination device and release
+ * addresses that have no users left. The source device must be
+ * locked by netif_tx_lock_bh.
+ *
+ * This function is intended to be called from the dev->set_rx_mode
+ * function of layered software devices.
+ */
+int dev_unicast_sync(struct net_device *to, struct net_device *from)
+{
+ int err = 0;
+
+ netif_addr_lock_bh(to);
+ err = __dev_addr_sync(&to->uc_list, &to->uc_count,
+ &from->uc_list, &from->uc_count);
+ if (!err)
+ __dev_set_rx_mode(to);
+ netif_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)
+{
+ netif_addr_lock_bh(from);
+ netif_addr_lock(to);
+
+ __dev_addr_unsync(&to->uc_list, &to->uc_count,
+ &from->uc_list, &from->uc_count);
+ __dev_set_rx_mode(to);
+
+ netif_addr_unlock(to);
+ netif_addr_unlock_bh(from);
+}
+EXPORT_SYMBOL(dev_unicast_unsync);
+
+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);
+ }
+}
+
+static void dev_addr_discard(struct net_device *dev)
+{
+ netif_addr_lock_bh(dev);
+
+ __dev_addr_discard(&dev->uc_list);
+ dev->uc_count = 0;
+
+ __dev_addr_discard(&dev->mc_list);
+ dev->mc_count = 0;
+
+ netif_addr_unlock_bh(dev);
}
unsigned dev_get_flags(const struct net_device *dev)
int dev_change_flags(struct net_device *dev, unsigned flags)
{
- int ret;
+ 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 (dev->change_rx_flags && (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 |
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;
dev_set_allmulti(dev, inc);
}
- if (old_flags ^ dev->flags)
- rtmsg_ifinfo(RTM_NEWLINK, dev, old_flags ^ dev->flags);
+ /* Exclude state transition flags, already notified */
+ changes = (old_flags ^ dev->flags) & ~(IFF_UP | IFF_RUNNING);
+ if (changes)
+ rtmsg_ifinfo(RTM_NEWLINK, dev, changes);
return ret;
}
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;
}
return -ENODEV;
err = dev->set_mac_address(dev, sa);
if (!err)
- raw_notifier_call_chain(&netdev_chain,
- NETDEV_CHANGEADDR, dev);
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
return err;
}
/*
- * 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;
ifr->ifr_flags = 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 SIOCSIFMETRIC: /* Set the metric on the interface
- (currently unused) */
- return -EOPNOTSUPP;
-
case SIOCGIFMTU: /* Get the MTU of a device */
ifr->ifr_mtu = dev->mtu;
return 0;
- case SIOCSIFMTU: /* Set the MTU of a device */
- return dev_set_mtu(dev, ifr->ifr_mtu);
-
case SIOCGIFHWADDR:
if (!dev->addr_len)
memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
ifr->ifr_hwaddr.sa_family = dev->type;
return 0;
- case SIOCSIFHWADDR:
- return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
-
- 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;
+ case SIOCGIFSLAVE:
+ err = -EINVAL;
+ break;
case SIOCGIFMAP:
ifr->ifr_map.mem_start = dev->mem_start;
ifr->ifr_map.port = dev->if_port;
return 0;
+ case SIOCGIFINDEX:
+ ifr->ifr_ifindex = dev->ifindex;
+ return 0;
+
+ case SIOCGIFTXQLEN:
+ ifr->ifr_qlen = dev->tx_queue_len;
+ return 0;
+
+ default:
+ /* dev_ioctl() should ensure this case
+ * is never reached
+ */
+ WARN_ON(1);
+ err = -EINVAL;
+ break;
+
+ }
+ return err;
+}
+
+/*
+ * 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);
+
+ if (!dev)
+ return -ENODEV;
+
+ switch (cmd) {
+ case SIOCSIFFLAGS: /* Set interface flags */
+ return dev_change_flags(dev, ifr->ifr_flags);
+
+ case SIOCSIFMETRIC: /* Set the metric on the interface
+ (currently unused) */
+ return -EOPNOTSUPP;
+
+ case SIOCSIFMTU: /* Set the MTU of a device */
+ return dev_set_mtu(dev, ifr->ifr_mtu);
+
+ case SIOCSIFHWADDR:
+ return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
+
+ 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;
+
case SIOCSIFMAP:
if (dev->set_config) {
if (!netif_device_present(dev))
return -EOPNOTSUPP;
case SIOCADDMULTI:
- if (!dev->set_multicast_list ||
+ if ((!dev->set_multicast_list && !dev->set_rx_mode) ||
ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
return -EINVAL;
if (!netif_device_present(dev))
dev->addr_len, 1);
case SIOCDELMULTI:
- if (!dev->set_multicast_list ||
+ if ((!dev->set_multicast_list && !dev->set_rx_mode) ||
ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
return -EINVAL;
if (!netif_device_present(dev))
return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data,
dev->addr_len, 1);
- case SIOCGIFINDEX:
- ifr->ifr_ifindex = dev->ifindex;
- return 0;
-
- case SIOCGIFTXQLEN:
- ifr->ifr_qlen = dev->tx_queue_len;
- return 0;
-
case SIOCSIFTXQLEN:
if (ifr->ifr_qlen < 0)
return -EINVAL;
/**
* 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;
case SIOCGIFMAP:
case SIOCGIFINDEX:
case SIOCGIFTXQLEN:
- dev_load(ifr.ifr_name);
+ dev_load(net, ifr.ifr_name);
read_lock(&dev_base_lock);
- ret = dev_ifsioc(&ifr, cmd);
+ ret = dev_ifsioc_locked(net, &ifr, cmd);
read_unlock(&dev_base_lock);
if (!ret) {
if (colon)
return ret;
case SIOCETHTOOL:
- dev_load(ifr.ifr_name);
+ dev_load(net, ifr.ifr_name);
rtnl_lock();
- ret = dev_ethtool(&ifr);
+ ret = dev_ethtool(net, &ifr);
rtnl_unlock();
if (!ret) {
if (colon)
case SIOCSIFNAME:
if (!capable(CAP_NET_ADMIN))
return -EPERM;
- dev_load(ifr.ifr_name);
+ dev_load(net, ifr.ifr_name);
rtnl_lock();
- ret = dev_ifsioc(&ifr, cmd);
+ ret = dev_ifsioc(net, &ifr, cmd);
rtnl_unlock();
if (!ret) {
if (colon)
/* fall through */
case SIOCBONDSLAVEINFOQUERY:
case SIOCBONDINFOQUERY:
- dev_load(ifr.ifr_name);
+ dev_load(net, ifr.ifr_name);
rtnl_lock();
- ret = dev_ifsioc(&ifr, cmd);
+ ret = dev_ifsioc(net, &ifr, cmd);
rtnl_unlock();
return ret;
if (cmd == SIOCWANDEV ||
(cmd >= SIOCDEVPRIVATE &&
cmd <= SIOCDEVPRIVATE + 15)) {
- dev_load(ifr.ifr_name);
+ 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;
}
-#ifdef CONFIG_WIRELESS_EXT
/* Take care of Wireless Extensions */
- if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) {
- /* If command is `set a parameter', or
- * `get the encoding parameters', check if
- * the user has the right to do it */
- if (IW_IS_SET(cmd) || cmd == SIOCGIWENCODE
- || cmd == SIOCGIWENCODEEXT) {
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
- }
- dev_load(ifr.ifr_name);
- rtnl_lock();
- /* Follow me in net/core/wireless.c */
- ret = wireless_process_ioctl(&ifr, cmd);
- rtnl_unlock();
- if (IW_IS_GET(cmd) &&
- copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- return ret;
- }
-#endif /* CONFIG_WIRELESS_EXT */
+ if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)
+ return wext_handle_ioctl(net, &ifr, cmd, arg);
return -EINVAL;
}
}
-/**
- * dev_new_index - allocate an ifindex
- *
- * 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 ifindex;
- for (;;) {
- if (++ifindex <= 0)
- ifindex = 1;
- if (!__dev_get_by_index(ifindex))
- return ifindex;
- }
-}
+/**
+ * dev_new_index - allocate an ifindex
+ * @net: the applicable net namespace
+ *
+ * Returns a suitable unique value for a new device interface
+ * number. The caller must hold the rtnl semaphore or the
+ * dev_base_lock to be sure it remains unique.
+ */
+static int dev_new_index(struct net *net)
+{
+ static int ifindex;
+ for (;;) {
+ if (++ifindex <= 0)
+ ifindex = 1;
+ if (!__dev_get_by_index(net, ifindex))
+ return ifindex;
+ }
+}
+
+/* Delayed registration/unregisteration */
+static DEFINE_SPINLOCK(net_todo_list_lock);
+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_addr_discard(dev);
+
+ if (dev->uninit)
+ dev->uninit(dev);
-static int dev_boot_phase = 1;
+ /* Notifier chain MUST detach us from master device. */
+ WARN_ON(dev->master);
-/* Delayed registration/unregisteration */
-static DEFINE_SPINLOCK(net_todo_list_lock);
-static struct list_head net_todo_list = LIST_HEAD_INIT(net_todo_list);
+ /* Remove entries from kobject tree */
+ netdev_unregister_kobject(dev);
-static inline void net_set_todo(struct net_device *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(&net_todo_list_lock);
- list_add_tail(&dev->todo_list, &net_todo_list);
- spin_unlock(&net_todo_list_lock);
+ 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);
}
/**
struct hlist_head *head;
struct hlist_node *p;
int ret;
+ struct net *net;
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(!dev_net(dev));
+ net = dev_net(dev);
- spin_lock_init(&dev->queue_lock);
- spin_lock_init(&dev->_xmit_lock);
- dev->xmit_lock_owner = -1;
-#ifdef CONFIG_NET_CLS_ACT
- spin_lock_init(&dev->ingress_lock);
-#endif
+ spin_lock_init(&dev->addr_list_lock);
+ netdev_set_addr_lockdep_class(dev);
+ netdev_init_queue_locks(dev);
dev->iflink = -1;
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 checksum combinations */
+ if ((dev->features & NETIF_F_HW_CSUM) &&
+ (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
+ printk(KERN_NOTICE "%s: mixed HW and IP checksum settings.\n",
+ dev->name);
+ dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
+ }
+
+ if ((dev->features & NETIF_F_NO_CSUM) &&
+ (dev->features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
+ printk(KERN_NOTICE "%s: mixed no checksumming and other settings.\n",
+ dev->name);
+ dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM);
+ }
+
+
/* Fix illegal SG+CSUM combinations. */
if ((dev->features & NETIF_F_SG) &&
!(dev->features & NETIF_F_ALL_CSUM)) {
}
}
- /*
- * nil rebuild_header routine,
- * that should be never called and used as just bug trap.
- */
-
- 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->next = NULL;
dev_init_scheduler(dev);
- write_lock_bh(&dev_base_lock);
- *dev_tail = dev;
- dev_tail = &dev->next;
- 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->uninit)
+ dev->uninit(dev);
+ goto out;
}
/**
* chain. 0 is returned on success. A negative errno code is returned
* on a failure to set up the device, or if the name is a duplicate.
*
- * This is a wrapper around register_netdev that takes the rtnl semaphore
+ * This is a wrapper around register_netdevice that takes the rtnl semaphore
* and expands the device name if you passed a format string to
* alloc_netdev.
*/
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)) {
continue;
}
- netdev_unregister_sysfs(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);
- /* It must be the very last action,
- * after this 'dev' may point to freed up memory.
- */
if (dev->destructor)
dev->destructor(dev);
+
+ /* Free network device */
+ kobject_put(&dev->dev.kobj);
}
out:
mutex_unlock(&net_todo_run_mutex);
}
+static struct net_device_stats *internal_stats(struct net_device *dev)
+{
+ return &dev->stats;
+}
+
+static void netdev_init_one_queue(struct net_device *dev,
+ struct netdev_queue *queue,
+ void *_unused)
+{
+ queue->dev = dev;
+}
+
+static void netdev_init_queues(struct net_device *dev)
+{
+ netdev_init_one_queue(dev, &dev->rx_queue, NULL);
+ netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
+ spin_lock_init(&dev->tx_global_lock);
+}
+
/**
- * alloc_netdev - 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;
+ void *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 = (alloc_size + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST;
+ alloc_size += sizeof_priv;
+ }
+ /* ensure 32-byte alignment of whole construct */
+ alloc_size += NETDEV_ALIGN_CONST;
p = kzalloc(alloc_size, GFP_KERNEL);
if (!p) {
return NULL;
}
+ tx = kcalloc(queue_count, sizeof(struct netdev_queue), GFP_KERNEL);
+ if (!tx) {
+ printk(KERN_ERR "alloc_netdev: Unable to allocate "
+ "tx qdiscs.\n");
+ kfree(p);
+ return NULL;
+ }
+
dev = (struct net_device *)
(((long)p + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST);
dev->padded = (char *)dev - (char *)p;
+ dev_net_set(dev, &init_net);
+
+ dev->_tx = tx;
+ dev->num_tx_queues = queue_count;
+ dev->real_num_tx_queues = queue_count;
+
+ if (sizeof_priv) {
+ dev->priv = ((char *)dev +
+ ((sizeof(struct net_device) + NETDEV_ALIGN_CONST)
+ & ~NETDEV_ALIGN_CONST));
+ }
+
+ dev->gso_max_size = GSO_MAX_SIZE;
- if (sizeof_priv)
- dev->priv = netdev_priv(dev);
+ netdev_init_queues(dev);
+ dev->get_stats = internal_stats;
+ netpoll_netdev_init(dev);
setup(dev);
strcpy(dev->name, name);
return dev;
}
-EXPORT_SYMBOL(alloc_netdev);
+EXPORT_SYMBOL(alloc_netdev_mq);
/**
* free_netdev - free network device
*/
void free_netdev(struct net_device *dev)
{
-#ifdef CONFIG_SYSFS
+ release_net(dev_net(dev));
+
+ kfree(dev->_tx);
+
/* 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
}
/* Synchronize with packet receive processing. */
* @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)
{
- struct net_device *d, **dp;
-
- 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);
+}
- 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();
+}
- BUG_ON(dev->reg_state != NETREG_REGISTERED);
+EXPORT_SYMBOL(unregister_netdev);
- /* If device is running, close it first. */
- if (dev->flags & IFF_UP)
- dev_close(dev);
+/**
+ * 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.
+ */
- /* And unlink it from device chain. */
- for (dp = &dev_base; (d = *dp) != NULL; dp = &d->next) {
- if (d == dev) {
- write_lock_bh(&dev_base_lock);
- hlist_del(&dev->name_hlist);
- hlist_del(&dev->index_hlist);
- if (dev_tail == &dev->next)
- dev_tail = dp;
- *dp = d->next;
- write_unlock_bh(&dev_base_lock);
- break;
- }
+int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat)
+{
+ char buf[IFNAMSIZ];
+ const char *destname;
+ int err;
+
+ ASSERT_RTNL();
+
+ /* Don't allow namespace local devices to be moved. */
+ err = -EINVAL;
+ if (dev->features & NETIF_F_NETNS_LOCAL)
+ goto out;
+
+ /* 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;
}
- BUG_ON(!d);
- dev->reg_state = NETREG_UNREGISTERING;
+ /*
+ * 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_addr_discard(dev);
- if (dev->uninit)
- dev->uninit(dev);
+ /* Actually switch the network namespace */
+ dev_net_set(dev, net);
- /* Notifier chain MUST detach us from master device. */
- BUG_TRAP(!dev->master);
+ /* 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 */
+ netdev_unregister_kobject(dev);
+ 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;
+}
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;
- if (action != CPU_DEAD)
+ if (action != CPU_DEAD && action != CPU_DEAD_FROZEN)
return NOTIFY_OK;
local_irq_disable();
#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.
+ * net_dma_rebalance - try to maintain one DMA channel per CPU
+ * @net_dma: DMA client and associated data (lock, channels, channel_mask)
+ *
+ * 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.
*/
-static void net_dma_rebalance(void)
+
+static void net_dma_rebalance(struct net_dma *net_dma)
{
- unsigned int cpu, i, n;
+ unsigned int cpu, i, n, chan_idx;
struct dma_chan *chan;
- if (net_dma_count == 0) {
+ if (cpus_empty(net_dma->channel_mask)) {
for_each_online_cpu(cpu)
rcu_assign_pointer(per_cpu(softnet_data, cpu).net_dma, NULL);
return;
i = 0;
cpu = first_cpu(cpu_online_map);
- 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));
+ for_each_cpu_mask_nr(chan_idx, net_dma->channel_mask) {
+ chan = net_dma->channels[chan_idx];
+
+ n = ((num_online_cpus() / cpus_weight(net_dma->channel_mask))
+ + (i < (num_online_cpus() %
+ cpus_weight(net_dma->channel_mask)) ? 1 : 0));
while(n) {
per_cpu(softnet_data, cpu).net_dma = chan;
}
i++;
}
- rcu_read_unlock();
}
/**
* 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
+ * @state: DMA state to be handled
*/
-static void netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
- enum dma_event event)
+static enum dma_state_client
+netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
+ enum dma_state state)
{
- spin_lock(&net_dma_event_lock);
- switch (event) {
- case DMA_RESOURCE_ADDED:
- net_dma_count++;
- net_dma_rebalance();
+ int i, found = 0, pos = -1;
+ struct net_dma *net_dma =
+ container_of(client, struct net_dma, client);
+ enum dma_state_client ack = DMA_DUP; /* default: take no action */
+
+ spin_lock(&net_dma->lock);
+ switch (state) {
+ case DMA_RESOURCE_AVAILABLE:
+ for (i = 0; i < nr_cpu_ids; i++)
+ if (net_dma->channels[i] == chan) {
+ found = 1;
+ break;
+ } else if (net_dma->channels[i] == NULL && pos < 0)
+ pos = i;
+
+ if (!found && pos >= 0) {
+ ack = DMA_ACK;
+ net_dma->channels[pos] = chan;
+ cpu_set(pos, net_dma->channel_mask);
+ net_dma_rebalance(net_dma);
+ }
break;
case DMA_RESOURCE_REMOVED:
- net_dma_count--;
- net_dma_rebalance();
+ for (i = 0; i < nr_cpu_ids; i++)
+ if (net_dma->channels[i] == chan) {
+ found = 1;
+ pos = i;
+ break;
+ }
+
+ if (found) {
+ ack = DMA_ACK;
+ cpu_clear(pos, net_dma->channel_mask);
+ net_dma->channels[i] = NULL;
+ net_dma_rebalance(net_dma);
+ }
break;
default:
break;
}
- spin_unlock(&net_dma_event_lock);
+ spin_unlock(&net_dma->lock);
+
+ return ack;
}
/**
*/
static int __init netdev_dma_register(void)
{
- spin_lock_init(&net_dma_event_lock);
- net_dma_client = dma_async_client_register(netdev_dma_event);
- if (net_dma_client == NULL)
+ net_dma.channels = kzalloc(nr_cpu_ids * sizeof(struct net_dma),
+ GFP_KERNEL);
+ if (unlikely(!net_dma.channels)) {
+ printk(KERN_NOTICE
+ "netdev_dma: no memory for net_dma.channels\n");
return -ENOMEM;
-
- dma_async_client_chan_request(net_dma_client, num_online_cpus());
+ }
+ spin_lock_init(&net_dma.lock);
+ dma_cap_set(DMA_MEMCPY, net_dma.client.cap_mask);
+ dma_async_client_register(&net_dma.client);
+ dma_async_client_chan_request(&net_dma.client);
return 0;
}
static int __init netdev_dma_register(void) { return -ENODEV; }
#endif /* CONFIG_NET_DMA */
+/**
+ * netdev_compute_feature - compute conjunction of two feature sets
+ * @all: first feature set
+ * @one: second feature set
+ *
+ * Computes a new feature set after adding a device with feature set
+ * @one to the master device with current feature set @all. Returns
+ * the new feature set.
+ */
+int netdev_compute_features(unsigned long all, unsigned long one)
+{
+ /* if device needs checksumming, downgrade to hw checksumming */
+ if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM))
+ all ^= NETIF_F_NO_CSUM | NETIF_F_HW_CSUM;
+
+ /* if device can't do all checksum, downgrade to ipv4/ipv6 */
+ if (all & NETIF_F_HW_CSUM && !(one & NETIF_F_HW_CSUM))
+ all ^= NETIF_F_HW_CSUM
+ | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+
+ if (one & NETIF_F_GSO)
+ one |= NETIF_F_GSO_SOFTWARE;
+ one |= NETIF_F_GSO;
+
+ /*
+ * If even one device supports a GSO protocol with software fallback,
+ * enable it for all.
+ */
+ all |= one & NETIF_F_GSO_SOFTWARE;
+
+ /* If even one device supports robust GSO, enable it for all. */
+ if (one & NETIF_F_GSO_ROBUST)
+ all |= NETIF_F_GSO_ROBUST;
+
+ all &= one | NETIF_F_LLTX;
+
+ if (!(all & NETIF_F_ALL_CSUM))
+ all &= ~NETIF_F_SG;
+ if (!(all & NETIF_F_SG))
+ all &= ~NETIF_F_GSO_MASK;
+
+ return all;
+}
+EXPORT_SYMBOL(netdev_compute_features);
+
+static struct hlist_head *netdev_create_hash(void)
+{
+ 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;
+}
+
+char *netdev_drivername(const struct net_device *dev, char *buffer, int len)
+{
+ const struct device_driver *driver;
+ const struct device *parent;
+
+ 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;
+}
+
+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, *next;
+ /*
+ * Push all migratable of the network devices back to the
+ * initial network namespace
+ */
+ rtnl_lock();
+ for_each_netdev_safe(net, dev, next) {
+ int err;
+ char fb_name[IFNAMSIZ];
+
+ /* Ignore unmoveable devices (i.e. loopback) */
+ if (dev->features & NETIF_F_NETNS_LOCAL)
+ continue;
+
+ /* 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();
+ }
+ }
+ 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
* unhooks any devices that fail to initialise (normally hardware not
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]);
+ if (register_pernet_subsys(&netdev_net_ops))
+ goto out;
- for (i = 0; i < ARRAY_SIZE(dev_index_head); i++)
- INIT_HLIST_HEAD(&dev_index_head[i]);
+ if (register_pernet_device(&default_device_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);
+
+ queue->backlog.poll = process_backlog;
+ queue->backlog.weight = weight_p;
}
netdev_dma_register();
dev_boot_phase = 0;
- open_softirq(NET_TX_SOFTIRQ, net_tx_action, NULL);
- open_softirq(NET_RX_SOFTIRQ, net_rx_action, NULL);
+ open_softirq(NET_TX_SOFTIRQ, net_tx_action);
+ open_softirq(NET_RX_SOFTIRQ, net_rx_action);
hotcpu_notifier(dev_cpu_callback, 0);
dst_init();