Skip to content
Snippets Groups Projects
dev.c 161 KiB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
/*
 * 	NET3	Protocol independent device support routines.
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 *
 *	Derived from the non IP parts of dev.c 1.0.19
 * 		Authors:	Ross Biro
Linus Torvalds's avatar
Linus Torvalds committed
 *				Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *				Mark Evans, <evansmp@uhura.aston.ac.uk>
 *
 *	Additional Authors:
 *		Florian la Roche <rzsfl@rz.uni-sb.de>
 *		Alan Cox <gw4pts@gw4pts.ampr.org>
 *		David Hinds <dahinds@users.sourceforge.net>
 *		Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
 *		Adam Sulmicki <adam@cfar.umd.edu>
 *              Pekka Riikonen <priikone@poesidon.pspt.fi>
 *
 *	Changes:
 *              D.J. Barrow     :       Fixed bug where dev->refcnt gets set
 *              			to 2 if register_netdev gets called
 *              			before net_dev_init & also removed a
 *              			few lines of code in the process.
 *		Alan Cox	:	device private ioctl copies fields back.
 *		Alan Cox	:	Transmit queue code does relevant
 *					stunts to keep the queue safe.
 *		Alan Cox	:	Fixed double lock.
 *		Alan Cox	:	Fixed promisc NULL pointer trap
 *		????????	:	Support the full private ioctl range
 *		Alan Cox	:	Moved ioctl permission check into
 *					drivers
 *		Tim Kordas	:	SIOCADDMULTI/SIOCDELMULTI
 *		Alan Cox	:	100 backlog just doesn't cut it when
 *					you start doing multicast video 8)
 *		Alan Cox	:	Rewrote net_bh and list manager.
 *		Alan Cox	: 	Fix ETH_P_ALL echoback lengths.
 *		Alan Cox	:	Took out transmit every packet pass
 *					Saved a few bytes in the ioctl handler
 *		Alan Cox	:	Network driver sets packet type before
 *					calling netif_rx. Saves a function
 *					call a packet.
 *		Alan Cox	:	Hashed net_bh()
 *		Richard Kooijman:	Timestamp fixes.
 *		Alan Cox	:	Wrong field in SIOCGIFDSTADDR
 *		Alan Cox	:	Device lock protection.
 *		Alan Cox	: 	Fixed nasty side effect of device close
 *					changes.
 *		Rudi Cilibrasi	:	Pass the right thing to
 *					set_mac_address()
 *		Dave Miller	:	32bit quantity for the device lock to
 *					make it work out on a Sparc.
 *		Bjorn Ekwall	:	Added KERNELD hack.
 *		Alan Cox	:	Cleaned up the backlog initialise.
 *		Craig Metz	:	SIOCGIFCONF fix if space for under
 *					1 device.
 *	    Thomas Bogendoerfer :	Return ENODEV for dev_open, if there
 *					is no device open function.
 *		Andi Kleen	:	Fix error reporting for SIOCGIFCONF
 *	    Michael Chastain	:	Fix signed/unsigned for SIOCGIFCONF
 *		Cyrus Durgin	:	Cleaned for KMOD
 *		Adam Sulmicki   :	Bug Fix : Network Device Unload
 *					A network device unload needs to purge
 *					the backlog queue.
 *	Paul Rusty Russell	:	SIOCSIFNAME
 *              Pekka Riikonen  :	Netdev boot-time settings code
 *              Andrew Morton   :       Make unregister_netdevice wait
 *              			indefinitely on dev->refcnt
 * 		J Hadi Salim	:	- Backlog queue sampling
 *				        - netif_rx() feedback
 */

#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/capability.h>
Linus Torvalds's avatar
Linus Torvalds committed
#include <linux/cpu.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/hash.h>
Linus Torvalds's avatar
Linus Torvalds committed
#include <linux/sched.h>
Arjan van de Ven's avatar
Arjan van de Ven committed
#include <linux/mutex.h>
Linus Torvalds's avatar
Linus Torvalds committed
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/if_ether.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
Linus Torvalds's avatar
Linus Torvalds committed
#include <linux/notifier.h>
#include <linux/skbuff.h>
#include <net/net_namespace.h>
Linus Torvalds's avatar
Linus Torvalds committed
#include <net/sock.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/stat.h>
#include <net/dst.h>
#include <net/pkt_sched.h>
#include <net/checksum.h>
#include <net/xfrm.h>
Linus Torvalds's avatar
Linus Torvalds committed
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/module.h>
#include <linux/netpoll.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
#include <net/wext.h>
Linus Torvalds's avatar
Linus Torvalds committed
#include <net/iw_handler.h>
#include <asm/current.h>
Steve Grubb's avatar
Steve Grubb committed
#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 <trace/events/net.h>
#include <trace/events/skb.h>
#include <linux/pci.h>
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
#include <linux/net_tstamp.h>
#include <linux/jump_label.h>
#include <net/flow_keys.h>
Linus Torvalds's avatar
Linus Torvalds committed

/* Instead of increasing this, you should create a hash table. */
#define MAX_GRO_SKBS 8

Herbert Xu's avatar
Herbert Xu committed
/* This should be increased if a protocol with a bigger head is added. */
#define GRO_MAX_HEAD (MAX_HEADER + 128)

Linus Torvalds's avatar
Linus Torvalds committed
/*
 *	The list of packet types we will receive (as opposed to discard)
 *	and the routines to invoke.
 *
 *	Why 16. Because with 16 the only overlap we get on a hash of the
 *	low nibble of the protocol value is RARP/SNAP/X.25.
 *
 *      NOTE:  That is no longer true with the addition of VLAN tags.  Not
 *             sure which should go first, but I bet it won't make much
 *             difference if we are running VLANs.  The good news is that
 *             this protocol won't be in the list unless compiled in, so
 *             the average user (w/out VLANs) will not be adversely affected.
Linus Torvalds's avatar
Linus Torvalds committed
 *             --BLG
 *
 *		0800	IP
 *		8100    802.1Q VLAN
 *		0001	802.3
 *		0002	AX.25
 *		0004	802.2
 *		8035	RARP
 *		0005	SNAP
 *		0805	X.25
 *		0806	ARP
 *		8137	IPX
 *		0009	Localtalk
 *		86DD	IPv6
 */

#define PTYPE_HASH_SIZE	(16)
#define PTYPE_HASH_MASK	(PTYPE_HASH_SIZE - 1)

Linus Torvalds's avatar
Linus Torvalds committed
static DEFINE_SPINLOCK(ptype_lock);
static struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
static struct list_head ptype_all __read_mostly;	/* Taps */
Linus Torvalds's avatar
Linus Torvalds committed

/*
 * The @dev_base_head list is protected by @dev_base_lock and the rtnl
Linus Torvalds's avatar
Linus Torvalds committed
 * semaphore.
 *
 * Pure readers hold dev_base_lock for reading, or rcu_read_lock()
Linus Torvalds's avatar
Linus Torvalds committed
 *
 * Writers must hold the rtnl semaphore while they loop through the
 * dev_base_head list, and hold dev_base_lock for writing when they do the
Linus Torvalds's avatar
Linus Torvalds committed
 * actual updates.  This allows pure readers to access the list even
 * while a writer is preparing to update it.
 *
 * To put it another way, dev_base_lock is held for writing only to
 * protect against pure readers; the rtnl semaphore provides the
 * protection against other writers.
 *
 * See, for example usages, register_netdevice() and
 * unregister_netdevice(), which must be called with the rtnl
 * semaphore held.
Linus Torvalds's avatar
Linus Torvalds committed
 */
DEFINE_RWLOCK(dev_base_lock);
EXPORT_SYMBOL(dev_base_lock);

static inline void dev_base_seq_inc(struct net *net)
{
	while (++net->dev_base_seq == 0);
}

static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
Linus Torvalds's avatar
Linus Torvalds committed
{
	unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
	return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)];
static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex)
Linus Torvalds's avatar
Linus Torvalds committed
{
	return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)];
Eric Dumazet's avatar
Eric Dumazet committed
static inline void rps_lock(struct softnet_data *sd)
Eric Dumazet's avatar
Eric Dumazet committed
	spin_lock(&sd->input_pkt_queue.lock);
Eric Dumazet's avatar
Eric Dumazet committed
static inline void rps_unlock(struct softnet_data *sd)
Eric Dumazet's avatar
Eric Dumazet committed
	spin_unlock(&sd->input_pkt_queue.lock);
/* 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_rcu(&dev->dev_list, &net->dev_base_head);
	hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
	hlist_add_head_rcu(&dev->index_hlist,
			   dev_index_hash(net, dev->ifindex));
	write_unlock_bh(&dev_base_lock);

	dev_base_seq_inc(net);

/* Device list removal
 * caller must respect a RCU grace period before freeing/reusing dev
 */
static void unlist_netdevice(struct net_device *dev)
{
	ASSERT_RTNL();

	/* Unlink dev from the device chain */
	write_lock_bh(&dev_base_lock);
	list_del_rcu(&dev->dev_list);
	hlist_del_rcu(&dev->name_hlist);
	hlist_del_rcu(&dev->index_hlist);
	write_unlock_bh(&dev_base_lock);

	dev_base_seq_inc(dev_net(dev));
Linus Torvalds's avatar
Linus Torvalds committed
/*
 *	Our notifier list
 */

static RAW_NOTIFIER_HEAD(netdev_chain);
Linus Torvalds's avatar
Linus Torvalds committed

/*
 *	Device drivers call our routines to queue packets here. We empty the
 *	queue in the local softnet handler.
 */
DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
EXPORT_PER_CPU_SYMBOL(softnet_data);
Linus Torvalds's avatar
Linus Torvalds committed

 * 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_PHONET,
	 ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154,
	 ARPHRD_VOID, ARPHRD_NONE};
static const char *const netdev_lock_name[] =
	{"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
	 "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
	 "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
	 "_xmit_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_PHONET",
	 "_xmit_PHONET_PIPE", "_xmit_IEEE802154",
	 "_xmit_VOID", "_xmit_NONE"};

static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];

static inline unsigned short netdev_lock_pos(unsigned short dev_type)
{
	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]);
}
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)
Linus Torvalds's avatar
Linus Torvalds committed

/*******************************************************************************

		Protocol management and registration routines

*******************************************************************************/

/*
 *	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.
 *
 *	BEWARE!!! Protocol handlers, mangling input packets,
 *	MUST BE last in hash buckets and checking protocol handlers
 *	MUST start from promiscuous ptype_all chain in net_bh.
 *	It is true now, do not change it.
 *	Explanation follows: if protocol handler, mangling packet, will
 *	be the first on list, it is not able to sense, that packet
 *	is cloned and should be copied-on-write, so that it will
 *	change it and subsequent readers will get broken packet.
 *							--ANK (980803)
 */

static inline struct list_head *ptype_head(const struct packet_type *pt)
{
	if (pt->type == htons(ETH_P_ALL))
		return &ptype_all;
	else
		return &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK];
}

Linus Torvalds's avatar
Linus Torvalds committed
/**
 *	dev_add_pack - add packet handler
 *	@pt: packet type declaration
 *
 *	Add a protocol handler to the networking stack. The passed &packet_type
 *	is linked into kernel lists and may not be freed until it has been
 *	removed from the kernel lists.
 *
 *	This call does not sleep therefore it can not
Linus Torvalds's avatar
Linus Torvalds committed
 *	guarantee all CPU's that are in middle of receiving packets
 *	will see the new packet type (until the next received packet).
 */

void dev_add_pack(struct packet_type *pt)
{
	struct list_head *head = ptype_head(pt);
Linus Torvalds's avatar
Linus Torvalds committed

	spin_lock(&ptype_lock);
	list_add_rcu(&pt->list, head);
	spin_unlock(&ptype_lock);
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(dev_add_pack);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	__dev_remove_pack	 - remove packet handler
 *	@pt: packet type declaration
 *
 *	Remove a protocol handler that was previously added to the kernel
 *	protocol handlers by dev_add_pack(). The passed &packet_type is removed
 *	from the kernel lists and can be freed or reused once this function
Linus Torvalds's avatar
Linus Torvalds committed
 *
 *      The packet type might still be in use by receivers
 *	and must not be freed until after all the CPU's have gone
 *	through a quiescent state.
 */
void __dev_remove_pack(struct packet_type *pt)
{
	struct list_head *head = ptype_head(pt);
Linus Torvalds's avatar
Linus Torvalds committed
	struct packet_type *pt1;

	spin_lock(&ptype_lock);
Linus Torvalds's avatar
Linus Torvalds committed

	list_for_each_entry(pt1, head, list) {
		if (pt == pt1) {
			list_del_rcu(&pt->list);
			goto out;
		}
	}

	printk(KERN_WARNING "dev_remove_pack: %p not found.\n", pt);
out:
	spin_unlock(&ptype_lock);
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(__dev_remove_pack);

Linus Torvalds's avatar
Linus Torvalds committed
/**
 *	dev_remove_pack	 - remove packet handler
 *	@pt: packet type declaration
 *
 *	Remove a protocol handler that was previously added to the kernel
 *	protocol handlers by dev_add_pack(). The passed &packet_type is removed
 *	from the kernel lists and can be freed or reused once this function
 *	returns.
 *
 *	This call sleeps to guarantee that no CPU is looking at the packet
 *	type after return.
 */
void dev_remove_pack(struct packet_type *pt)
{
	__dev_remove_pack(pt);
Linus Torvalds's avatar
Linus Torvalds committed
	synchronize_net();
}
EXPORT_SYMBOL(dev_remove_pack);
Linus Torvalds's avatar
Linus Torvalds committed

/******************************************************************************

		      Device Boot-time Settings Routines

*******************************************************************************/

/* Boot time configuration table */
static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX];

/**
 *	netdev_boot_setup_add	- add new setup entry
 *	@name: name of the device
 *	@map: configured settings for the device
 *
 *	Adds new setup entry to the dev_boot_setup list.  The function
 *	returns 0 on error and 1 on success.  This is a generic routine to
 *	all netdevices.
 */
static int netdev_boot_setup_add(char *name, struct ifmap *map)
{
	struct netdev_boot_setup *s;
	int i;

	s = dev_boot_setup;
	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));
			strlcpy(s[i].name, name, IFNAMSIZ);
Linus Torvalds's avatar
Linus Torvalds committed
			memcpy(&s[i].map, map, sizeof(s[i].map));
			break;
		}
	}

	return i >= NETDEV_BOOT_SETUP_MAX ? 0 : 1;
}

/**
 *	netdev_boot_setup_check	- check boot time settings
 *	@dev: the netdevice
 *
 * 	Check boot time settings for the device.
 *	The found settings are set for the device to be used
 *	later in the device probing.
 *	Returns 0 if no settings found, 1 if they are.
 */
int netdev_boot_setup_check(struct net_device *dev)
{
	struct netdev_boot_setup *s = dev_boot_setup;
	int i;

	for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
		if (s[i].name[0] != '\0' && s[i].name[0] != ' ' &&
		    !strcmp(dev->name, s[i].name)) {
Linus Torvalds's avatar
Linus Torvalds committed
			dev->irq 	= s[i].map.irq;
			dev->base_addr 	= s[i].map.base_addr;
			dev->mem_start 	= s[i].map.mem_start;
			dev->mem_end 	= s[i].map.mem_end;
			return 1;
		}
	}
	return 0;
}
EXPORT_SYMBOL(netdev_boot_setup_check);
Linus Torvalds's avatar
Linus Torvalds committed


/**
 *	netdev_boot_base	- get address from boot time settings
 *	@prefix: prefix for network device
 *	@unit: id for network device
 *
 * 	Check boot time settings for the base address of device.
 *	The found settings are set for the device to be used
 *	later in the device probing.
 *	Returns 0 if no settings found.
 */
unsigned long netdev_boot_base(const char *prefix, int unit)
{
	const struct netdev_boot_setup *s = dev_boot_setup;
	char name[IFNAMSIZ];
	int i;

	sprintf(name, "%s%d", prefix, unit);

	/*
	 * If device already registered then return base of 1
	 * to indicate not to probe for this interface
	 */
	if (__dev_get_by_name(&init_net, name))
Linus Torvalds's avatar
Linus Torvalds committed
		return 1;

	for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++)
		if (!strcmp(name, s[i].name))
			return s[i].map.base_addr;
	return 0;
}

/*
 * Saves at boot time configured settings for any netdevice.
 */
int __init netdev_boot_setup(char *str)
{
	int ints[5];
	struct ifmap map;

	str = get_options(str, ARRAY_SIZE(ints), ints);
	if (!str || !*str)
		return 0;

	/* Save settings */
	memset(&map, 0, sizeof(map));
	if (ints[0] > 0)
		map.irq = ints[1];
	if (ints[0] > 1)
		map.base_addr = ints[2];
	if (ints[0] > 2)
		map.mem_start = ints[3];
	if (ints[0] > 3)
		map.mem_end = ints[4];

	/* Add new entry to the list */
	return netdev_boot_setup_add(str, &map);
}

__setup("netdev=", netdev_boot_setup);

/*******************************************************************************

			    Device Interface Subroutines

*******************************************************************************/

/**
 *	__dev_get_by_name	- find a device by its name
 *	@net: the applicable net namespace
Linus Torvalds's avatar
Linus Torvalds committed
 *	@name: name to find
 *
 *	Find an interface by name. Must be called under RTNL semaphore
 *	or @dev_base_lock. If the name is found a pointer to the device
 *	is returned. If the name is not found then %NULL is returned. The
 *	reference counters are not incremented so the caller must be
 *	careful with locks.
 */

struct net_device *__dev_get_by_name(struct net *net, const char *name)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct hlist_node *p;
	struct net_device *dev;
	struct hlist_head *head = dev_name_hash(net, name);
Linus Torvalds's avatar
Linus Torvalds committed

	hlist_for_each_entry(dev, p, head, name_hlist)
Linus Torvalds's avatar
Linus Torvalds committed
		if (!strncmp(dev->name, name, IFNAMSIZ))
			return dev;
Linus Torvalds's avatar
Linus Torvalds committed
	return NULL;
}
EXPORT_SYMBOL(__dev_get_by_name);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	dev_get_by_name_rcu	- find a device by its name
 *	@net: the applicable net namespace
 *	@name: name to find
 *
 *	Find an interface by name.
 *	If the name is found a pointer to the device is returned.
 * 	If the name is not found then %NULL is returned.
 *	The reference counters are not incremented so the caller must be
 *	careful with locks. The caller must hold RCU lock.
 */

struct net_device *dev_get_by_name_rcu(struct net *net, const char *name)
{
	struct hlist_node *p;
	struct net_device *dev;
	struct hlist_head *head = dev_name_hash(net, name);

	hlist_for_each_entry_rcu(dev, p, head, name_hlist)
		if (!strncmp(dev->name, name, IFNAMSIZ))
			return dev;

	return NULL;
}
EXPORT_SYMBOL(dev_get_by_name_rcu);

Linus Torvalds's avatar
Linus Torvalds committed
/**
 *	dev_get_by_name		- find a device by its name
 *	@net: the applicable net namespace
Linus Torvalds's avatar
Linus Torvalds committed
 *	@name: name to find
 *
 *	Find an interface by name. This can be called from any
 *	context and does its own locking. The returned handle has
 *	the usage count incremented and the caller must use dev_put() to
 *	release it when it is no longer needed. %NULL is returned if no
 *	matching device is found.
 */

struct net_device *dev_get_by_name(struct net *net, const char *name)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct net_device *dev;

	rcu_read_lock();
	dev = dev_get_by_name_rcu(net, name);
Linus Torvalds's avatar
Linus Torvalds committed
	if (dev)
		dev_hold(dev);
	rcu_read_unlock();
Linus Torvalds's avatar
Linus Torvalds committed
	return dev;
}
EXPORT_SYMBOL(dev_get_by_name);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	__dev_get_by_index - find a device by its ifindex
 *	@net: the applicable net namespace
Linus Torvalds's avatar
Linus Torvalds committed
 *	@ifindex: index of device
 *
 *	Search for an interface by index. Returns %NULL if the device
 *	is not found or a pointer to the device. The device has not
 *	had its reference counter increased so the caller must be careful
 *	about locking. The caller must hold either the RTNL semaphore
 *	or @dev_base_lock.
 */

struct net_device *__dev_get_by_index(struct net *net, int ifindex)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct hlist_node *p;
	struct net_device *dev;
	struct hlist_head *head = dev_index_hash(net, ifindex);
Linus Torvalds's avatar
Linus Torvalds committed

	hlist_for_each_entry(dev, p, head, index_hlist)
Linus Torvalds's avatar
Linus Torvalds committed
		if (dev->ifindex == ifindex)
			return dev;
Linus Torvalds's avatar
Linus Torvalds committed
	return NULL;
}
EXPORT_SYMBOL(__dev_get_by_index);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	dev_get_by_index_rcu - 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
 *	is not found or a pointer to the device. The device has not
 *	had its reference counter increased so the caller must be careful
 *	about locking. The caller must hold RCU lock.
 */

struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex)
{
	struct hlist_node *p;
	struct net_device *dev;
	struct hlist_head *head = dev_index_hash(net, ifindex);

	hlist_for_each_entry_rcu(dev, p, head, index_hlist)
		if (dev->ifindex == ifindex)
			return dev;

	return NULL;
}
EXPORT_SYMBOL(dev_get_by_index_rcu);

Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	dev_get_by_index - find a device by its ifindex
 *	@net: the applicable net namespace
Linus Torvalds's avatar
Linus Torvalds committed
 *	@ifindex: index of device
 *
 *	Search for an interface by index. Returns NULL if the device
 *	is not found or a pointer to the device. The device returned has
 *	had a reference added and the pointer is safe until the user calls
 *	dev_put to indicate they have finished with it.
 */

struct net_device *dev_get_by_index(struct net *net, int ifindex)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct net_device *dev;

	rcu_read_lock();
	dev = dev_get_by_index_rcu(net, ifindex);
Linus Torvalds's avatar
Linus Torvalds committed
	if (dev)
		dev_hold(dev);
	rcu_read_unlock();
Linus Torvalds's avatar
Linus Torvalds committed
	return dev;
}
EXPORT_SYMBOL(dev_get_by_index);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	dev_getbyhwaddr_rcu - find a device by its hardware address
 *	@net: the applicable net namespace
Linus Torvalds's avatar
Linus Torvalds committed
 *	@type: media type of device
 *	@ha: hardware address
 *
 *	Search for an interface by MAC address. Returns NULL if the device
 *	is not found or a pointer to the device.
 *	The caller must hold RCU or RTNL.
 *	The returned device has not had its ref count increased
Linus Torvalds's avatar
Linus Torvalds committed
 *	and the caller must therefore be careful about locking
 *
 */

struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
				       const char *ha)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct net_device *dev;

	for_each_netdev_rcu(net, dev)
Linus Torvalds's avatar
Linus Torvalds committed
		if (dev->type == type &&
		    !memcmp(dev->dev_addr, ha, dev->addr_len))
			return dev;

	return NULL;
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(dev_getbyhwaddr_rcu);
struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct net_device *dev;

	ASSERT_RTNL();
		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, *ret = NULL;
	rcu_read_lock();
	for_each_netdev_rcu(net, dev)
		if (dev->type == type) {
			dev_hold(dev);
			ret = dev;
			break;
		}
	rcu_read_unlock();
	return ret;
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(dev_getfirstbyhwtype);

/**
 *	dev_get_by_flags_rcu - find any device with given flags
 *	@net: the applicable net namespace
Linus Torvalds's avatar
Linus Torvalds committed
 *	@if_flags: IFF_* values
 *	@mask: bitmask of bits in if_flags to check
 *
 *	Search for any interface with the given flags. Returns NULL if a device
 *	is not found or a pointer to the device. Must be called inside
 *	rcu_read_lock(), and result refcount is unchanged.
Linus Torvalds's avatar
Linus Torvalds committed
 */

struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags,
				    unsigned short mask)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct net_device *dev, *ret;
Linus Torvalds's avatar
Linus Torvalds committed

	for_each_netdev_rcu(net, dev) {
Linus Torvalds's avatar
Linus Torvalds committed
		if (((dev->flags ^ if_flags) & mask) == 0) {
Linus Torvalds's avatar
Linus Torvalds committed
			break;
		}
	}
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(dev_get_by_flags_rcu);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	dev_valid_name - check if name is okay for network device
 *	@name: name string
 *
 *	Network device names need to be valid file names to
 *	to allow sysfs to work.  We also disallow any kind of
 *	whitespace.
Linus Torvalds's avatar
Linus Torvalds committed
 */
int dev_valid_name(const char *name)
Linus Torvalds's avatar
Linus Torvalds committed
{
	if (*name == '\0')
		return 0;
	if (strlen(name) >= IFNAMSIZ)
		return 0;
	if (!strcmp(name, ".") || !strcmp(name, ".."))
		return 0;

	while (*name) {
		if (*name == '/' || isspace(*name))
			return 0;
		name++;
	}
	return 1;
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(dev_valid_name);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	__dev_alloc_name - allocate a name for a device
 *	@net: network namespace to allocate the device name in
Linus Torvalds's avatar
Linus Torvalds committed
 *	@name: name format string
 *	@buf:  scratch buffer and result name string
Linus Torvalds's avatar
Linus Torvalds committed
 *
 *	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.
Linus Torvalds's avatar
Linus Torvalds committed
 */

static int __dev_alloc_name(struct net *net, const char *name, char *buf)
Linus Torvalds's avatar
Linus Torvalds committed
{
	int i = 0;
	const char *p;
	const int max_netdevices = 8*PAGE_SIZE;
	unsigned long *inuse;
Linus Torvalds's avatar
Linus Torvalds committed
	struct net_device *d;

	p = strnchr(name, IFNAMSIZ-1, '%');
	if (p) {
		/*
		 * Verify the string as this thing may have come from
		 * the user.  There must be either one "%d" and no other "%"
		 * characters.
		 */
		if (p[1] != 'd' || strchr(p + 2, '%'))
			return -EINVAL;

		/* Use one page as a bit array of possible slots */
		inuse = (unsigned long *) get_zeroed_page(GFP_ATOMIC);
Linus Torvalds's avatar
Linus Torvalds committed
		if (!inuse)
			return -ENOMEM;

Linus Torvalds's avatar
Linus Torvalds committed
			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, IFNAMSIZ, name, i);
Linus Torvalds's avatar
Linus Torvalds committed
			if (!strncmp(buf, d->name, IFNAMSIZ))
				set_bit(i, inuse);
		}

		i = find_first_zero_bit(inuse, max_netdevices);
		free_page((unsigned long) inuse);
	}

	if (buf != name)
		snprintf(buf, IFNAMSIZ, name, i);
	if (!__dev_get_by_name(net, buf))
Linus Torvalds's avatar
Linus Torvalds committed
		return i;

	/* It is possible to run out of possible slots
	 * when the name is long and there isn't enough space left
	 * for the digits, or if all bits are used.
	 */
	return -ENFILE;
}

/**
 *	dev_alloc_name - allocate a name for a device
 *	@dev: device
 *	@name: name format string
 *
 *	Passed a format string - eg "lt%d" it will try and find a suitable
 *	id. It scans list of devices to build up a free map, then chooses
 *	the first empty slot. The caller must hold the dev_base or rtnl lock
 *	while allocating the name and adding the device in order to avoid
 *	duplicates.
 *	Limited to bits_per_byte * page size devices (ie 32K on most platforms).
 *	Returns the number of the unit assigned or a negative errno code.
 */

int dev_alloc_name(struct net_device *dev, const char *name)
{
	char buf[IFNAMSIZ];
	struct net *net;
	int ret;

	BUG_ON(!dev_net(dev));
	net = dev_net(dev);
	ret = __dev_alloc_name(net, name, buf);
	if (ret >= 0)
		strlcpy(dev->name, buf, IFNAMSIZ);
	return ret;
}
EXPORT_SYMBOL(dev_alloc_name);
static int dev_get_valid_name(struct net_device *dev, const char *name)
	struct net *net;

	BUG_ON(!dev_net(dev));
	net = dev_net(dev);

	if (!dev_valid_name(name))
		return -EINVAL;

	if (strchr(name, '%'))
		return dev_alloc_name(dev, name);
	else if (__dev_get_by_name(net, name))
		return -EEXIST;
	else if (dev->name != name)
		strlcpy(dev->name, name, IFNAMSIZ);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	dev_change_name - change name of a device
 *	@dev: device
 *	@newname: name (or format string) must be at least IFNAMSIZ
 *
 *	Change name of a device, can pass format strings "eth%d".
 *	for wildcarding.
 */
int dev_change_name(struct net_device *dev, const char *newname)
Linus Torvalds's avatar
Linus Torvalds committed
{
	char oldname[IFNAMSIZ];
Linus Torvalds's avatar
Linus Torvalds committed
	int err = 0;
Linus Torvalds's avatar
Linus Torvalds committed

	ASSERT_RTNL();
Linus Torvalds's avatar
Linus Torvalds committed

Linus Torvalds's avatar
Linus Torvalds committed
	if (dev->flags & IFF_UP)
		return -EBUSY;

	if (strncmp(newname, dev->name, IFNAMSIZ) == 0)
		return 0;

	memcpy(oldname, dev->name, IFNAMSIZ);

	err = dev_get_valid_name(dev, newname);
	if (err < 0)
		return err;
Linus Torvalds's avatar
Linus Torvalds committed

	ret = device_rename(&dev->dev, dev->name);
	if (ret) {
		memcpy(dev->name, oldname, IFNAMSIZ);
		return ret;
	hlist_del_rcu(&dev->name_hlist);
	write_unlock_bh(&dev_base_lock);

	synchronize_rcu();

	write_lock_bh(&dev_base_lock);
	hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
	ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev);
	ret = notifier_to_errno(ret);

	if (ret) {
		/* err >= 0 after dev_alloc_name() or stores the first errno */
		if (err >= 0) {
			err = ret;
			memcpy(dev->name, oldname, IFNAMSIZ);
			goto rollback;
		} else {
			printk(KERN_ERR
			       "%s: name change rollback failed: %d.\n",
			       dev->name, ret);
Linus Torvalds's avatar
Linus Torvalds committed

	return err;
}

/**
 *	dev_set_alias - change ifalias of a device
 *	@dev: device
 *	@alias: name up to IFALIASZ
 *	@len: limit of bytes to copy from info
 *
 *	Set ifalias for a device,
 */
int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
{
	ASSERT_RTNL();

	if (len >= IFALIASZ)
		return -EINVAL;

	if (!len) {
		if (dev->ifalias) {
			kfree(dev->ifalias);
			dev->ifalias = NULL;
		}
		return 0;
	}

	dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
	if (!dev->ifalias)
		return -ENOMEM;

	strlcpy(dev->ifalias, alias, len+1);
	return len;
}


 *	netdev_features_change - device changes features
 *	@dev: device to cause notification
 *
 *	Called to indicate a device has changed features.
 */
void netdev_features_change(struct net_device *dev)
{
	call_netdevice_notifiers(NETDEV_FEAT_CHANGE, dev);
}
EXPORT_SYMBOL(netdev_features_change);

Linus Torvalds's avatar
Linus Torvalds committed
/**
 *	netdev_state_change - device changes state
 *	@dev: device to cause notification
 *
 *	Called to indicate a device has changed state. This function calls
 *	the notifier chains for netdev_chain and sends a NEWLINK message
 *	to the routing socket.
 */
void netdev_state_change(struct net_device *dev)
{
	if (dev->flags & IFF_UP) {
		call_netdevice_notifiers(NETDEV_CHANGE, dev);
Linus Torvalds's avatar
Linus Torvalds committed
		rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
	}
}
EXPORT_SYMBOL(netdev_state_change);
Linus Torvalds's avatar
Linus Torvalds committed

int netdev_bonding_change(struct net_device *dev, unsigned long event)
	return call_netdevice_notifiers(event, dev);
}
EXPORT_SYMBOL(netdev_bonding_change);

Linus Torvalds's avatar
Linus Torvalds committed
/**
 *	dev_load 	- load a network module
 *	@net: the applicable net namespace
Linus Torvalds's avatar
Linus Torvalds committed
 *	@name: name of interface
 *
 *	If a network interface is not present and the process has suitable
 *	privileges this function loads the module. If module loading is not
 *	available in this kernel then it becomes a nop.
 */

void dev_load(struct net *net, const char *name)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct net_device *dev;
Linus Torvalds's avatar
Linus Torvalds committed

	rcu_read_lock();
	dev = dev_get_by_name_rcu(net, name);
	rcu_read_unlock();
Linus Torvalds's avatar
Linus Torvalds committed

	no_module = !dev;
	if (no_module && capable(CAP_NET_ADMIN))
		no_module = request_module("netdev-%s", name);
	if (no_module && capable(CAP_SYS_MODULE)) {
		if (!request_module("%s", name))
			pr_err("Loading kernel module for a network device "
"with CAP_SYS_MODULE (deprecated).  Use CAP_NET_ADMIN and alias netdev-%s "
"instead\n", name);
	}
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(dev_load);
Linus Torvalds's avatar
Linus Torvalds committed

static int __dev_open(struct net_device *dev)
Linus Torvalds's avatar
Linus Torvalds committed
{
	const struct net_device_ops *ops = dev->netdev_ops;
Linus Torvalds's avatar
Linus Torvalds committed

Linus Torvalds's avatar
Linus Torvalds committed
	if (!netif_device_present(dev))
		return -ENODEV;

	ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
	ret = notifier_to_errno(ret);
	if (ret)
		return ret;

Linus Torvalds's avatar
Linus Torvalds committed
	set_bit(__LINK_STATE_START, &dev->state);
	if (ops->ndo_validate_addr)
		ret = ops->ndo_validate_addr(dev);
	if (!ret && ops->ndo_open)
		ret = ops->ndo_open(dev);
Linus Torvalds's avatar
Linus Torvalds committed

	if (ret)
		clear_bit(__LINK_STATE_START, &dev->state);
	else {
Linus Torvalds's avatar
Linus Torvalds committed
		dev->flags |= IFF_UP;
		dev_set_rx_mode(dev);
Linus Torvalds's avatar
Linus Torvalds committed
		dev_activate(dev);
	}
Linus Torvalds's avatar
Linus Torvalds committed
	return ret;
}

/**
 *	dev_open	- prepare an interface for use.
 *	@dev:	device to open
Linus Torvalds's avatar
Linus Torvalds committed
 *
 *	Takes a device from down to up state. The device's private open
 *	function is invoked and then the multicast lists are loaded. Finally
 *	the device is moved into the up state and a %NETDEV_UP message is
 *	sent to the netdev notifier chain.
 *
 *	Calling this function on an active interface is a nop. On a failure
 *	a negative errno code is returned.
Linus Torvalds's avatar
Linus Torvalds committed
 */
int dev_open(struct net_device *dev)
{
	int ret;

	if (dev->flags & IFF_UP)
		return 0;

	ret = __dev_open(dev);
	if (ret < 0)
		return ret;

	rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
	call_netdevice_notifiers(NETDEV_UP, dev);

	return ret;
}
EXPORT_SYMBOL(dev_open);

static int __dev_close_many(struct list_head *head)
Linus Torvalds's avatar
Linus Torvalds committed
{
	list_for_each_entry(dev, head, unreg_list) {
		call_netdevice_notifiers(NETDEV_GOING_DOWN, dev);
Linus Torvalds's avatar
Linus Torvalds committed

		clear_bit(__LINK_STATE_START, &dev->state);
Linus Torvalds's avatar
Linus Torvalds committed

		/* Synchronize to scheduled poll. We cannot touch poll list, 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(). */
	}
Linus Torvalds's avatar
Linus Torvalds committed

	list_for_each_entry(dev, head, unreg_list) {
		const struct net_device_ops *ops = dev->netdev_ops;
Linus Torvalds's avatar
Linus Torvalds committed

		/*
		 *	Call the device specific close. This cannot fail.
		 *	Only if device is UP
		 *
		 *	We allow it to be called even after a DETACH hot-plug
		 *	event.
		 */
		if (ops->ndo_stop)
			ops->ndo_stop(dev);

		dev->flags &= ~IFF_UP;
		net_dmaengine_put();
	}

	return 0;
}

static int __dev_close(struct net_device *dev)
{
	LIST_HEAD(single);

	list_add(&dev->unreg_list, &single);
	retval = __dev_close_many(&single);
	list_del(&single);
	return retval;
static int dev_close_many(struct list_head *head)
{
	struct net_device *dev, *tmp;
	LIST_HEAD(tmp_list);
Linus Torvalds's avatar
Linus Torvalds committed

	list_for_each_entry_safe(dev, tmp, head, unreg_list)
		if (!(dev->flags & IFF_UP))
			list_move(&dev->unreg_list, &tmp_list);

	__dev_close_many(head);
Linus Torvalds's avatar
Linus Torvalds committed

	list_for_each_entry(dev, head, unreg_list) {
		rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
		call_netdevice_notifiers(NETDEV_DOWN, dev);
	}
	/* rollback_registered_many needs the complete original list */
	list_splice(&tmp_list, head);
	return 0;
}

/**
 *	dev_close - shutdown an interface.
 *	@dev: device to shutdown
 *
 *	This function moves an active device into down state. A
 *	%NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device
 *	is then deactivated and finally a %NETDEV_DOWN is sent to the notifier
 *	chain.
 */
int dev_close(struct net_device *dev)
{
	if (dev->flags & IFF_UP) {
		LIST_HEAD(single);
Linus Torvalds's avatar
Linus Torvalds committed

		list_add(&dev->unreg_list, &single);
		dev_close_many(&single);
		list_del(&single);
	}
Linus Torvalds's avatar
Linus Torvalds committed
	return 0;
}
EXPORT_SYMBOL(dev_close);
/**
 *	dev_disable_lro - disable Large Receive Offload on a device
 *	@dev: device
 *
 *	Disable Large Receive Offload (LRO) on a net device.  Must be
 *	called under RTNL.  This is needed if received packets may be
 *	forwarded to another interface.
 */
void dev_disable_lro(struct net_device *dev)
{
	/*
	 * If we're trying to disable lro on a vlan device
	 * use the underlying physical device instead
	 */
	if (is_vlan_dev(dev))
		dev = vlan_dev_real_dev(dev);

	dev->wanted_features &= ~NETIF_F_LRO;
	netdev_update_features(dev);
	if (unlikely(dev->features & NETIF_F_LRO))
		netdev_WARN(dev, "failed to disable LRO!\n");
Linus Torvalds's avatar
Linus Torvalds committed
/**
 *	register_netdevice_notifier - register a network notifier block
 *	@nb: notifier
 *
 *	Register a notifier to be called when network device events occur.
 *	The notifier passed is linked into the kernel structures and must
 *	not be reused until it has been unregistered. A negative errno code
 *	is returned on a failure.
 *
 * 	When registered all registration and up events are replayed
 *	to the new notifier to allow device to have a race free
Linus Torvalds's avatar
Linus Torvalds committed
 *	view of the network device list.
 */

int register_netdevice_notifier(struct notifier_block *nb)
{
	struct net_device *dev;
	struct net_device *last;
Linus Torvalds's avatar
Linus Torvalds committed
	int err;

	rtnl_lock();
	err = raw_notifier_chain_register(&netdev_chain, nb);
	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;
Linus Torvalds's avatar
Linus Torvalds committed

			nb->notifier_call(nb, NETDEV_UP, dev);
		}
Linus Torvalds's avatar
Linus Torvalds committed
	}
Linus Torvalds's avatar
Linus Torvalds committed
	rtnl_unlock();
	return err;
	for_each_net(net) {
		for_each_netdev(net, dev) {
			if (dev == last)
			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);
			nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev);
	raw_notifier_chain_unregister(&netdev_chain, nb);
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(register_netdevice_notifier);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	unregister_netdevice_notifier - unregister a network notifier block
 *	@nb: notifier
 *
 *	Unregister a notifier previously registered by
 *	register_netdevice_notifier(). The notifier is unlinked into the
 *	kernel structures and may then be reused. A negative errno code
 *	is returned on a failure.
 */

int unregister_netdevice_notifier(struct notifier_block *nb)
{
	err = raw_notifier_chain_unregister(&netdev_chain, nb);
	rtnl_unlock();
	return err;
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(unregister_netdevice_notifier);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	call_netdevice_notifiers - call all network notifier blocks
 *      @val: value passed unmodified to notifier function
 *      @dev: net_device pointer passed unmodified to notifier function
Linus Torvalds's avatar
Linus Torvalds committed
 *
 *	Call all network notifier blocks.  Parameters and return value
 *	are as for raw_notifier_call_chain().
int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
Linus Torvalds's avatar
Linus Torvalds committed
{
	return raw_notifier_call_chain(&netdev_chain, val, dev);
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(call_netdevice_notifiers);
Linus Torvalds's avatar
Linus Torvalds committed

static struct jump_label_key netstamp_needed __read_mostly;
#ifdef HAVE_JUMP_LABEL
/* We are not allowed to call jump_label_dec() from irq context
 * If net_disable_timestamp() is called from irq context, defer the
 * jump_label_dec() calls.
 */
static atomic_t netstamp_needed_deferred;
#endif
Linus Torvalds's avatar
Linus Torvalds committed

void net_enable_timestamp(void)
{
#ifdef HAVE_JUMP_LABEL
	int deferred = atomic_xchg(&netstamp_needed_deferred, 0);

	if (deferred) {
		while (--deferred)
			jump_label_dec(&netstamp_needed);
		return;
	}
#endif
	WARN_ON(in_interrupt());
	jump_label_inc(&netstamp_needed);
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(net_enable_timestamp);
Linus Torvalds's avatar
Linus Torvalds committed

void net_disable_timestamp(void)
{
#ifdef HAVE_JUMP_LABEL
	if (in_interrupt()) {
		atomic_inc(&netstamp_needed_deferred);
		return;
	}
#endif
	jump_label_dec(&netstamp_needed);
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(net_disable_timestamp);
Linus Torvalds's avatar
Linus Torvalds committed

static inline void net_timestamp_set(struct sk_buff *skb)
Linus Torvalds's avatar
Linus Torvalds committed
{
	skb->tstamp.tv64 = 0;
	if (static_branch(&netstamp_needed))
#define net_timestamp_check(COND, SKB)			\
	if (static_branch(&netstamp_needed)) {		\
		if ((COND) && !(SKB)->tstamp.tv64)	\
			__net_timestamp(SKB);		\
	}						\
static int net_hwtstamp_validate(struct ifreq *ifr)
{
	struct hwtstamp_config cfg;
	enum hwtstamp_tx_types tx_type;
	enum hwtstamp_rx_filters rx_filter;
	int tx_type_valid = 0;
	int rx_filter_valid = 0;

	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
		return -EFAULT;

	if (cfg.flags) /* reserved for future extensions */
		return -EINVAL;

	tx_type = cfg.tx_type;
	rx_filter = cfg.rx_filter;

	switch (tx_type) {
	case HWTSTAMP_TX_OFF:
	case HWTSTAMP_TX_ON:
	case HWTSTAMP_TX_ONESTEP_SYNC:
		tx_type_valid = 1;
		break;
	}

	switch (rx_filter) {
	case HWTSTAMP_FILTER_NONE:
	case HWTSTAMP_FILTER_ALL:
	case HWTSTAMP_FILTER_SOME:
	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
		rx_filter_valid = 1;
		break;
	}

	if (!tx_type_valid || !rx_filter_valid)
		return -ERANGE;

	return 0;
}

static inline bool is_skb_forwardable(struct net_device *dev,
				      struct sk_buff *skb)
{
	unsigned int len;

	if (!(dev->flags & IFF_UP))
		return false;

	len = dev->mtu + dev->hard_header_len + VLAN_HLEN;
	if (skb->len <= len)
		return true;

	/* if TSO is enabled, we don't care about the length as the packet
	 * could be forwarded without being segmented before
	 */
	if (skb_is_gso(skb))
		return true;

	return false;
}

/**
 * dev_forward_skb - loopback an skb to another netif
 *
 * @dev: destination network device
 * @skb: buffer to forward
 *
 * return values:
 *	NET_RX_SUCCESS	(no congestion)
 *	NET_RX_DROP     (packet was dropped, but freed)
 *
 * dev_forward_skb can be used for injecting an skb from the
 * start_xmit function of one device into the receive queue
 * of another device.
 *
 * The receiving device may be in another namespace, so
 * we have to clear all information in the skb that could
 * impact namespace isolation.
 */
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
{
	if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
		if (skb_copy_ubufs(skb, GFP_ATOMIC)) {
			atomic_long_inc(&dev->rx_dropped);
			kfree_skb(skb);
			return NET_RX_DROP;
		}
	}

	nf_reset(skb);
	if (unlikely(!is_skb_forwardable(dev, skb))) {
		atomic_long_inc(&dev->rx_dropped);
		return NET_RX_DROP;
	skb->tstamp.tv64 = 0;
	skb->pkt_type = PACKET_HOST;
	skb->protocol = eth_type_trans(skb, dev);
	return netif_rx(skb);
}
EXPORT_SYMBOL_GPL(dev_forward_skb);

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);
}

Linus Torvalds's avatar
Linus Torvalds committed
/*
 *	Support routine. Sends outgoing frames to any network
 *	taps currently in use.
 */

static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct packet_type *ptype;
	struct sk_buff *skb2 = NULL;
	struct packet_type *pt_prev = NULL;
Linus Torvalds's avatar
Linus Torvalds committed
	rcu_read_lock();
	list_for_each_entry_rcu(ptype, &ptype_all, list) {
		/* Never send packets back to the socket
		 * they originated from - MvS (miquels@drinkel.ow.org)
		 */
		if ((ptype->dev == dev || !ptype->dev) &&
		    (ptype->af_packet_priv == NULL ||
		     (struct sock *)ptype->af_packet_priv != skb->sk)) {
			if (pt_prev) {
				deliver_skb(skb2, pt_prev, skb->dev);
				pt_prev = ptype;
				continue;
			}

			skb2 = skb_clone(skb, GFP_ATOMIC);
Linus Torvalds's avatar
Linus Torvalds committed
			if (!skb2)
				break;

Linus Torvalds's avatar
Linus Torvalds committed
			/* skb->nh should be correctly
			   set by sender, so that the second statement is
			   just protection against buggy protocols.
			 */
			skb_reset_mac_header(skb2);
Linus Torvalds's avatar
Linus Torvalds committed

			if (skb_network_header(skb2) < skb2->data ||
			    skb2->network_header > skb2->tail) {
Linus Torvalds's avatar
Linus Torvalds committed
				if (net_ratelimit())
					printk(KERN_CRIT "protocol %04x is "
					       "buggy, dev %s\n",
					       ntohs(skb2->protocol),
					       dev->name);
				skb_reset_network_header(skb2);
			skb2->transport_header = skb2->network_header;
Linus Torvalds's avatar
Linus Torvalds committed
			skb2->pkt_type = PACKET_OUTGOING;
Linus Torvalds's avatar
Linus Torvalds committed
		}
	}
	if (pt_prev)
		pt_prev->func(skb2, skb->dev, pt_prev, skb->dev);
Linus Torvalds's avatar
Linus Torvalds committed
	rcu_read_unlock();
}

/* netif_setup_tc - Handle tc mappings on real_num_tx_queues change
 * @dev: Network device
 * @txq: number of queues available
 *
 * If real_num_tx_queues is changed the tc mappings may no longer be
 * valid. To resolve this verify the tc mapping remains valid and if
 * not NULL the mapping. With no priorities mapping to this
 * offset/count pair it will no longer be used. In the worst case TC0
 * is invalid nothing can be done so disable priority mappings. If is
 * expected that drivers will fix this mapping if they can before
 * calling netif_set_real_num_tx_queues.
 */
static void netif_setup_tc(struct net_device *dev, unsigned int txq)
{
	int i;
	struct netdev_tc_txq *tc = &dev->tc_to_txq[0];

	/* If TC0 is invalidated disable TC mapping */
	if (tc->offset + tc->count > txq) {
		pr_warning("Number of in use tx queues changed "
			   "invalidating tc mappings. Priority "
			   "traffic classification disabled!\n");
		dev->num_tc = 0;
		return;
	}

	/* Invalidated prio to tc mappings set to TC0 */
	for (i = 1; i < TC_BITMASK + 1; i++) {
		int q = netdev_get_prio_tc_map(dev, i);

		tc = &dev->tc_to_txq[q];
		if (tc->offset + tc->count > txq) {
			pr_warning("Number of in use tx queues "
				   "changed. Priority %i to tc "
				   "mapping %i is no longer valid "
				   "setting map to 0\n",
				   i, q);
			netdev_set_prio_tc_map(dev, i, 0);
		}
	}
}

/*
 * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues
 * greater then real_num_tx_queues stale skbs on the qdisc must be flushed.
 */
int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
	if (txq < 1 || txq > dev->num_tx_queues)
		return -EINVAL;
	if (dev->reg_state == NETREG_REGISTERED ||
	    dev->reg_state == NETREG_UNREGISTERING) {
		rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues,
						  txq);
Tom Herbert's avatar
Tom Herbert committed
		if (rc)
			return rc;

		if (dev->num_tc)
			netif_setup_tc(dev, txq);

		if (txq < dev->real_num_tx_queues)
			qdisc_reset_all_tx_gt(dev, txq);

	dev->real_num_tx_queues = txq;
	return 0;
}
EXPORT_SYMBOL(netif_set_real_num_tx_queues);
#ifdef CONFIG_RPS
/**
 *	netif_set_real_num_rx_queues - set actual number of RX queues used
 *	@dev: Network device
 *	@rxq: Actual number of RX queues
 *
 *	This must be called either with the rtnl_lock held or before
 *	registration of the net device.  Returns 0 on success, or a
 *	negative error code.  If called before registration, it always
 *	succeeds.
 */
int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq)
{
	int rc;

	if (rxq < 1 || rxq > dev->num_rx_queues)
		return -EINVAL;

	if (dev->reg_state == NETREG_REGISTERED) {
		ASSERT_RTNL();

		rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues,
						  rxq);
		if (rc)
			return rc;
	}

	dev->real_num_rx_queues = rxq;
	return 0;
}
EXPORT_SYMBOL(netif_set_real_num_rx_queues);
#endif

static inline void __netif_reschedule(struct Qdisc *q)
	struct softnet_data *sd;
	unsigned long flags;
	local_irq_save(flags);
	sd = &__get_cpu_var(softnet_data);
	q->next_sched = NULL;
	*sd->output_queue_tailp = q;
	sd->output_queue_tailp = &q->next_sched;
	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);
		skb->next = sd->completion_queue;
		sd->completion_queue = skb;
		raise_softirq_irqoff(NET_TX_SOFTIRQ);
		local_irq_restore(flags);
	}

void dev_kfree_skb_any(struct sk_buff *skb)
{
	if (in_irq() || irqs_disabled())
		dev_kfree_skb_irq(skb);
	else
		dev_kfree_skb(skb);
}
EXPORT_SYMBOL(dev_kfree_skb_any);


/**
 * netif_device_detach - mark device as removed
 * @dev: network device
 *
 * Mark device as removed from system and therefore no longer available.
 */
void netif_device_detach(struct net_device *dev)
{
	if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) &&
	    netif_running(dev)) {
		netif_tx_stop_all_queues(dev);
	}
}
EXPORT_SYMBOL(netif_device_detach);

/**
 * netif_device_attach - mark device as attached
 * @dev: network device
 *
 * Mark device as attached from system and restart if needed.
 */
void netif_device_attach(struct net_device *dev)
{
	if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) &&
	    netif_running(dev)) {
		netif_tx_wake_all_queues(dev);
		__netdev_watchdog_up(dev);
	}
}
EXPORT_SYMBOL(netif_device_attach);

/**
 * skb_dev_set -- assign a new device to a buffer
 * @skb: buffer for the new device
 * @dev: network device
 *
 * If an skb is owned by a device already, we have to reset
 * all data private to the namespace a device belongs to
 * before assigning it a new device.
 */
#ifdef CONFIG_NET_NS
void skb_set_dev(struct sk_buff *skb, struct net_device *dev)
{
	skb_dst_drop(skb);
	if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) {
		secpath_reset(skb);
		nf_reset(skb);
		skb_init_secmark(skb);
		skb->mark = 0;
		skb->priority = 0;
		skb->nf_trace = 0;
		skb->ipvs_property = 0;
#ifdef CONFIG_NET_SCHED
		skb->tc_index = 0;
#endif
	}
	skb->dev = dev;
}
EXPORT_SYMBOL(skb_set_dev);
#endif /* CONFIG_NET_NS */

static void skb_warn_bad_offload(const struct sk_buff *skb)
{
	static const netdev_features_t null_features = 0;
	struct net_device *dev = skb->dev;
	const char *driver = "";

	if (dev && dev->dev.parent)
		driver = dev_driver_string(dev->dev.parent);

	WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d gso_size=%d "
	     "gso_type=%d ip_summed=%d\n",
	     driver, dev ? &dev->features : &null_features,
	     skb->sk ? &skb->sk->sk_route_caps : &null_features,
	     skb->len, skb->data_len, skb_shinfo(skb)->gso_size,
	     skb_shinfo(skb)->gso_type, skb->ip_summed);
}

Linus Torvalds's avatar
Linus Torvalds committed
/*
 * Invalidate hardware checksum when packet is to be mangled, and
 * complete checksum manually on outgoing path.
 */
int skb_checksum_help(struct sk_buff *skb)
Linus Torvalds's avatar
Linus Torvalds committed
{
Linus Torvalds's avatar
Linus Torvalds committed

	if (skb->ip_summed == CHECKSUM_COMPLETE)
		goto out_set_summed;

	if (unlikely(skb_shinfo(skb)->gso_size)) {
		skb_warn_bad_offload(skb);
		return -EINVAL;
	offset = skb_checksum_start_offset(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))) {
Linus Torvalds's avatar
Linus Torvalds committed
		ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
		if (ret)
			goto out;
	}

	*(__sum16 *)(skb->data + offset) = csum_fold(csum);
Linus Torvalds's avatar
Linus Torvalds committed
	skb->ip_summed = CHECKSUM_NONE;
Linus Torvalds's avatar
Linus Torvalds committed
	return ret;
}
EXPORT_SYMBOL(skb_checksum_help);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	skb_gso_segment - Perform segmentation on skb.
 *	@skb: buffer to segment
 *	@features: features for the output path (see dev->features)
 *
 *	This function segments the given skb and returns a list of segments.
 *
 *	It may return NULL if the skb requires no segmentation.  This is
 *	only possible when GSO is used for verifying header integrity.
struct sk_buff *skb_gso_segment(struct sk_buff *skb,
	netdev_features_t features)
{
	struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
	struct packet_type *ptype;
Al Viro's avatar
Al Viro committed
	__be16 type = skb->protocol;
	int vlan_depth = ETH_HLEN;
	while (type == htons(ETH_P_8021Q)) {
		struct vlan_hdr *vh;
		if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN)))
		vh = (struct vlan_hdr *)(skb->data + vlan_depth);
		type = vh->h_vlan_encapsulated_proto;
		vlan_depth += VLAN_HLEN;
	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 (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) & 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_network_header(skb)));
			segs = ptype->gso_segment(skb, features);
	__skb_push(skb, skb->data - skb_mac_header(skb));
	return segs;
}
EXPORT_SYMBOL(skb_gso_segment);

/* Take action when hardware reception checksum errors are detected. */
#ifdef CONFIG_BUG
void netdev_rx_csum_fault(struct net_device *dev)
{
	if (net_ratelimit()) {
		printk(KERN_ERR "%s: hw csum failure.\n",
			dev ? dev->name : "<unknown>");
		dump_stack();
	}
}
EXPORT_SYMBOL(netdev_rx_csum_fault);
#endif

Linus Torvalds's avatar
Linus Torvalds committed
/* Actually, we should eliminate this check as soon as we know, that:
 * 1. IOMMU is present and allows to map all the memory.
 * 2. No high memory really exists on this machine.
 */

Eric Dumazet's avatar
Eric Dumazet committed
static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
Linus Torvalds's avatar
Linus Torvalds committed
{
#ifdef CONFIG_HIGHMEM
Linus Torvalds's avatar
Linus Torvalds committed
	int i;
	if (!(dev->features & NETIF_F_HIGHDMA)) {
		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
			if (PageHighMem(skb_frag_page(frag)))
Linus Torvalds's avatar
Linus Torvalds committed

	if (PCI_DMA_BUS_IS_PHYS) {
		struct device *pdev = dev->dev.parent;
Linus Torvalds's avatar
Linus Torvalds committed

Eric Dumazet's avatar
Eric Dumazet committed
		if (!pdev)
			return 0;
		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
			dma_addr_t addr = page_to_phys(skb_frag_page(frag));
			if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask)
				return 1;
		}
	}
Linus Torvalds's avatar
Linus Torvalds committed
	return 0;
}

struct dev_gso_cb {
	void (*destructor)(struct sk_buff *skb);
};

#define DEV_GSO_CB(skb) ((struct dev_gso_cb *)(skb)->cb)

static void dev_gso_skb_destructor(struct sk_buff *skb)
{
	struct dev_gso_cb *cb;

	do {
		struct sk_buff *nskb = skb->next;

		skb->next = nskb->next;
		nskb->next = NULL;
		kfree_skb(nskb);
	} while (skb->next);

	cb = DEV_GSO_CB(skb);
	if (cb->destructor)
		cb->destructor(skb);
}

/**
 *	dev_gso_segment - Perform emulated hardware segmentation on skb.
 *	@skb: buffer to segment
 *	@features: device features as applicable to this skb
 *
 *	This function segments the given skb and stores the list of segments
 *	in skb->next.
 */
static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
{
	struct sk_buff *segs;

	segs = skb_gso_segment(skb, features);

	/* Verifying header integrity only. */
	if (!segs)
		return 0;
	if (IS_ERR(segs))
		return PTR_ERR(segs);

	skb->next = segs;
	DEV_GSO_CB(skb)->destructor = skb->destructor;
	skb->destructor = dev_gso_skb_destructor;

	return 0;
}

/*
 * Try to orphan skb early, right before transmission by the device.
 * We cannot orphan skb if tx timestamp is requested or the sk-reference
 * is needed on driver level for other reasons, e.g. see net/can/raw.c
 */
static inline void skb_orphan_try(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;

	if (sk && !skb_shinfo(skb)->tx_flags) {
		/* skb_tx_hash() wont be able to get sk.
		 * We copy sk_hash into skb->rxhash
		 */
		if (!skb->rxhash)
			skb->rxhash = sk->sk_hash;
		skb_orphan(skb);
static bool can_checksum_protocol(netdev_features_t features, __be16 protocol)
{
	return ((features & NETIF_F_GEN_CSUM) ||
		((features & NETIF_F_V4_CSUM) &&
		 protocol == htons(ETH_P_IP)) ||
		((features & NETIF_F_V6_CSUM) &&
		 protocol == htons(ETH_P_IPV6)) ||
		((features & NETIF_F_FCOE_CRC) &&
		 protocol == htons(ETH_P_FCOE)));
}

static netdev_features_t harmonize_features(struct sk_buff *skb,
	__be16 protocol, netdev_features_t features)
	if (!can_checksum_protocol(features, protocol)) {
		features &= ~NETIF_F_ALL_CSUM;
		features &= ~NETIF_F_SG;
	} else if (illegal_highdma(skb->dev, skb)) {
		features &= ~NETIF_F_SG;
	}

	return features;
}

netdev_features_t netif_skb_features(struct sk_buff *skb)
{
	__be16 protocol = skb->protocol;
	netdev_features_t features = skb->dev->features;

	if (protocol == htons(ETH_P_8021Q)) {
		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
		protocol = veh->h_vlan_encapsulated_proto;
	} else if (!vlan_tx_tag_present(skb)) {
		return harmonize_features(skb, protocol, features);
	}
	features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_TX);

	if (protocol != htons(ETH_P_8021Q)) {
		return harmonize_features(skb, protocol, features);
	} else {
		features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST |
				NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_TX;
		return harmonize_features(skb, protocol, features);
	}
EXPORT_SYMBOL(netif_skb_features);
/*
 * Returns true if either:
 *	1. skb has frag_list and the device doesn't support FRAGLIST, or
 *	2. skb is fragmented and the device does not support SG, or if
 *	   at least one of fragments is in highmem and device does not
 *	   support DMA from it.
 */
static inline int skb_needs_linearize(struct sk_buff *skb,
	return skb_is_nonlinear(skb) &&
			((skb_has_frag_list(skb) &&
				!(features & NETIF_F_FRAGLIST)) ||
			(skb_shinfo(skb)->nr_frags &&
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
			struct netdev_queue *txq)
	const struct net_device_ops *ops = dev->netdev_ops;
	if (likely(!skb->next)) {
Lucas De Marchi's avatar
Lucas De Marchi committed
		 * If device doesn't need skb->dst, release it right now while
		 * its hot in this cpu cache
		 */
Eric Dumazet's avatar
Eric Dumazet committed
		if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
			skb_dst_drop(skb);

		if (!list_empty(&ptype_all))
			dev_queue_xmit_nit(skb, dev);

		skb_orphan_try(skb);
		features = netif_skb_features(skb);

		if (vlan_tx_tag_present(skb) &&
		    !(features & NETIF_F_HW_VLAN_TX)) {
			skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb));
			if (unlikely(!skb))
				goto out;

			skb->vlan_tci = 0;
		}

		if (netif_needs_gso(skb, features)) {
			if (unlikely(dev_gso_segment(skb, features)))
				goto out_kfree_skb;
			if (skb->next)
				goto gso;
			if (skb_needs_linearize(skb, features) &&
			    __skb_linearize(skb))
				goto out_kfree_skb;

			/* If packet is not checksummed and device does not
			 * support checksumming for this protocol, complete
			 * checksumming here.
			 */
			if (skb->ip_summed == CHECKSUM_PARTIAL) {
				skb_set_transport_header(skb,
					skb_checksum_start_offset(skb));
				if (!(features & NETIF_F_ALL_CSUM) &&
				     skb_checksum_help(skb))
					goto out_kfree_skb;
			}
		rc = ops->ndo_start_xmit(skb, dev);
		trace_net_dev_xmit(skb, rc, dev, skb_len);
			txq_trans_update(txq);
	do {
		struct sk_buff *nskb = skb->next;

		skb->next = nskb->next;
		nskb->next = NULL;
Lucas De Marchi's avatar
Lucas De Marchi committed
		 * If device doesn't need nskb->dst, release it right now while
		 * its hot in this cpu cache
		 */
		if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
			skb_dst_drop(nskb);

		rc = ops->ndo_start_xmit(nskb, dev);
		trace_net_dev_xmit(nskb, rc, dev, skb_len);
			if (rc & ~NETDEV_TX_MASK)
				goto out_kfree_gso_skb;
			nskb->next = skb->next;
			skb->next = nskb;
			return rc;
		}
		txq_trans_update(txq);
		if (unlikely(netif_xmit_stopped(txq) && skb->next))
			return NETDEV_TX_BUSY;
	} while (skb->next);
out_kfree_gso_skb:
	if (likely(skb->next == NULL))
		skb->destructor = DEV_GSO_CB(skb)->destructor;
out_kfree_skb:
	kfree_skb(skb);
static u32 hashrnd __read_mostly;
/*
 * Returns a Tx hash based on the given packet descriptor a Tx queues' number
 * to be used as a distribution range.
 */
u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
		  unsigned int num_tx_queues)
	u16 qoffset = 0;
	u16 qcount = num_tx_queues;
	if (skb_rx_queue_recorded(skb)) {
		hash = skb_get_rx_queue(skb);
		while (unlikely(hash >= num_tx_queues))
			hash -= num_tx_queues;
	if (dev->num_tc) {
		u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
		qoffset = dev->tc_to_txq[tc].offset;
		qcount = dev->tc_to_txq[tc].count;
	}

	if (skb->sk && skb->sk->sk_hash)
		hash = skb->sk->sk_hash;
		hash = (__force u16) skb->protocol ^ skb->rxhash;
	hash = jhash_1word(hash, hashrnd);
	return (u16) (((u64) hash * qcount) >> 32) + qoffset;
static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
{
	if (unlikely(queue_index >= dev->real_num_tx_queues)) {
		if (net_ratelimit()) {
			pr_warning("%s selects TX queue %d, but "
				"real number of TX queues is %d\n",
				dev->name, queue_index, dev->real_num_tx_queues);
static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
{
Tom Herbert's avatar
Tom Herbert committed
#ifdef CONFIG_XPS
	struct xps_dev_maps *dev_maps;
	struct xps_map *map;
	int queue_index = -1;

	rcu_read_lock();
	dev_maps = rcu_dereference(dev->xps_maps);
	if (dev_maps) {
		map = rcu_dereference(
		    dev_maps->cpu_map[raw_smp_processor_id()]);
		if (map) {
			if (map->len == 1)
				queue_index = map->queues[0];
			else {
				u32 hash;
				if (skb->sk && skb->sk->sk_hash)
					hash = skb->sk->sk_hash;
				else
					hash = (__force u16) skb->protocol ^
					    skb->rxhash;
				hash = jhash_1word(hash, hashrnd);
				queue_index = map->queues[
				    ((u64)hash * map->len) >> 32];
			}
			if (unlikely(queue_index >= dev->real_num_tx_queues))
				queue_index = -1;
		}
	}
	rcu_read_unlock();

	return queue_index;
#else
	return -1;
#endif
}

static struct netdev_queue *dev_pick_tx(struct net_device *dev,
					struct sk_buff *skb)
{
	int queue_index;
	const struct net_device_ops *ops = dev->netdev_ops;
	if (dev->real_num_tx_queues == 1)
		queue_index = 0;
	else if (ops->ndo_select_queue) {
		queue_index = ops->ndo_select_queue(dev, skb);
		queue_index = dev_cap_txqueue(dev, queue_index);
	} else {
		struct sock *sk = skb->sk;
		queue_index = sk_tx_queue_get(sk);
		if (queue_index < 0 || skb->ooo_okay ||
		    queue_index >= dev->real_num_tx_queues) {
			int old_index = queue_index;
			queue_index = get_xps_queue(dev, skb);
			if (queue_index < 0)
				queue_index = skb_tx_hash(dev, skb);

			if (queue_index != old_index && sk) {
				struct dst_entry *dst =
				    rcu_dereference_check(sk->sk_dst_cache, 1);
Eric Dumazet's avatar
Eric Dumazet committed

				if (dst && skb_dst(skb) == dst)
					sk_tx_queue_set(sk, queue_index);
			}
	skb_set_queue_mapping(skb, queue_index);
	return netdev_get_tx_queue(dev, queue_index);
static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
				 struct net_device *dev,
				 struct netdev_queue *txq)
{
	spinlock_t *root_lock = qdisc_lock(q);
	bool contended;
	qdisc_skb_cb(skb)->pkt_len = skb->len;
	qdisc_calculate_pkt_len(skb, q);
	/*
	 * Heuristic to force contended enqueues to serialize on a
	 * separate lock before trying to get qdisc main lock.
	 * This permits __QDISC_STATE_RUNNING owner to get the lock more often
	 * and dequeue packets faster.
	 */
	contended = qdisc_is_running(q);
	if (unlikely(contended))
		spin_lock(&q->busylock);

	spin_lock(root_lock);
	if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
		kfree_skb(skb);
		rc = NET_XMIT_DROP;
	} else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
		/*
		 * This is a work-conserving queue; there are no old skbs
		 * waiting to be sent out; and the qdisc is not running -
		 * xmit the skb directly.
		 */
		if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE))
			skb_dst_force(skb);

		qdisc_bstats_update(q, skb);

		if (sch_direct_xmit(skb, q, dev, txq, root_lock)) {
			if (unlikely(contended)) {
				spin_unlock(&q->busylock);
				contended = false;
			}

		rc = NET_XMIT_SUCCESS;
	} else {
		skb_dst_force(skb);
		rc = q->enqueue(skb, q) & NET_XMIT_MASK;
		if (qdisc_run_begin(q)) {
			if (unlikely(contended)) {
				spin_unlock(&q->busylock);
				contended = false;
			}
			__qdisc_run(q);
		}
	}
	spin_unlock(root_lock);
	if (unlikely(contended))
		spin_unlock(&q->busylock);
#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
static void skb_update_prio(struct sk_buff *skb)
{
	struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap);

	if ((!skb->priority) && (skb->sk) && map)
		skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx];
}
#else
#define skb_update_prio(skb)
#endif

static DEFINE_PER_CPU(int, xmit_recursion);
#define RECURSION_LIMIT 10
/**
 *	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
 *      difficult to retry a send to this method.  (You can bump the ref count
 *      before sending to hold a reference for retry if you are careful.)
 *
 *      When calling this method, interrupts MUST be enabled.  This is because
 *      the BH enable code must have IRQs enabled so that it will not deadlock.
 *          --BLG
 */
Linus Torvalds's avatar
Linus Torvalds committed
int dev_queue_xmit(struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	struct netdev_queue *txq;
Linus Torvalds's avatar
Linus Torvalds committed
	struct Qdisc *q;
	int rc = -ENOMEM;

	/* Disable soft irqs for various locks below. Also
	 * stops preemption for RCU.
Linus Torvalds's avatar
Linus Torvalds committed
	 */
	rcu_read_lock_bh();
Linus Torvalds's avatar
Linus Torvalds committed

	txq = dev_pick_tx(dev, skb);
	q = rcu_dereference_bh(txq->qdisc);
Linus Torvalds's avatar
Linus Torvalds committed
#ifdef CONFIG_NET_CLS_ACT
	skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS);
Linus Torvalds's avatar
Linus Torvalds committed
#endif
	trace_net_dev_queue(skb);
Linus Torvalds's avatar
Linus Torvalds committed
	if (q->enqueue) {
		rc = __dev_xmit_skb(skb, q, dev, txq);
Linus Torvalds's avatar
Linus Torvalds committed
	}

	/* The device has no queue. Common case for software devices:
	   loopback, all the sorts of tunnels...

Herbert Xu's avatar
Herbert Xu committed
	   Really, it is unlikely that netif_tx_lock protection is necessary
	   here.  (f.e. loopback and IP tunnels are clean ignoring statistics
Linus Torvalds's avatar
Linus Torvalds committed
	   counters.)
	   However, it is possible, that they rely on protection
	   made by us here.

	   Check this and shot the lock. It is not prone from deadlocks.
	   Either shot noqueue qdisc, it is even simpler 8)
	 */
	if (dev->flags & IFF_UP) {
		int cpu = smp_processor_id(); /* ok because BHs are off */

		if (txq->xmit_lock_owner != cpu) {
Linus Torvalds's avatar
Linus Torvalds committed

			if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
				goto recursion_alert;

Linus Torvalds's avatar
Linus Torvalds committed

			if (!netif_xmit_stopped(txq)) {
				__this_cpu_inc(xmit_recursion);
				rc = dev_hard_start_xmit(skb, dev, txq);
				__this_cpu_dec(xmit_recursion);
Linus Torvalds's avatar
Linus Torvalds committed
					goto out;
				}
			}
Linus Torvalds's avatar
Linus Torvalds committed
			if (net_ratelimit())
				printk(KERN_CRIT "Virtual device %s asks to "
				       "queue packet!\n", dev->name);
		} else {
			/* Recursion is detected! It is possible,
			 * unfortunately
			 */
recursion_alert:
Linus Torvalds's avatar
Linus Torvalds committed
			if (net_ratelimit())
				printk(KERN_CRIT "Dead loop on virtual device "
				       "%s, fix it urgently!\n", dev->name);
		}
	}

	rc = -ENETDOWN;
	rcu_read_unlock_bh();
Linus Torvalds's avatar
Linus Torvalds committed

	kfree_skb(skb);
	return rc;
out:
	rcu_read_unlock_bh();
Linus Torvalds's avatar
Linus Torvalds committed
	return rc;
}
EXPORT_SYMBOL(dev_queue_xmit);
Linus Torvalds's avatar
Linus Torvalds committed


/*=======================================================================
			Receiver routines
  =======================================================================*/

int netdev_max_backlog __read_mostly = 1000;
int netdev_tstamp_prequeue __read_mostly = 1;
int netdev_budget __read_mostly = 300;
int weight_p __read_mostly = 64;            /* old backlog weight */
Linus Torvalds's avatar
Linus Torvalds committed

Eric Dumazet's avatar
Eric Dumazet committed
/* Called with irq disabled */
static inline void ____napi_schedule(struct softnet_data *sd,
				     struct napi_struct *napi)
{
	list_add_tail(&napi->poll_list, &sd->poll_list);
	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
}

 * __skb_get_rxhash: calculate a flow hash based on src/dst addresses
 * and src/dst port numbers.  Sets rxhash in skb to non-zero hash value
 * on success, zero indicates no valid hash.  Also, sets l4_rxhash in skb
 * if hash is a canonical 4-tuple hash over transport ports.
void __skb_get_rxhash(struct sk_buff *skb)
	struct flow_keys keys;
	u32 hash;
	if (!skb_flow_dissect(skb, &keys))
		return;
	if (keys.ports) {
		if ((__force u16)keys.port16[1] < (__force u16)keys.port16[0])
			swap(keys.port16[0], keys.port16[1]);
		skb->l4_rxhash = 1;
Eric Dumazet's avatar
Eric Dumazet committed
	/* get a consistent hash (same value on both flow directions) */
	if ((__force u32)keys.dst < (__force u32)keys.src)
		swap(keys.dst, keys.src);
	hash = jhash_3words((__force u32)keys.dst,
			    (__force u32)keys.src,
			    (__force u32)keys.ports, hashrnd);
}
EXPORT_SYMBOL(__skb_get_rxhash);

#ifdef CONFIG_RPS

/* One global table that all flow-based protocols share. */
Eric Dumazet's avatar
Eric Dumazet committed
struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly;
EXPORT_SYMBOL(rps_sock_flow_table);

struct jump_label_key rps_needed __read_mostly;

static struct rps_dev_flow *
set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
	    struct rps_dev_flow *rflow, u16 next_cpu)
{
#ifdef CONFIG_RFS_ACCEL
		struct netdev_rx_queue *rxqueue;
		struct rps_dev_flow_table *flow_table;
		struct rps_dev_flow *old_rflow;
		u32 flow_id;
		u16 rxq_index;
		int rc;

		/* Should we steer this flow to a different hardware queue? */
		if (!skb_rx_queue_recorded(skb) || !dev->rx_cpu_rmap ||
		    !(dev->features & NETIF_F_NTUPLE))
			goto out;
		rxq_index = cpu_rmap_lookup_index(dev->rx_cpu_rmap, next_cpu);
		if (rxq_index == skb_get_rx_queue(skb))
			goto out;

		rxqueue = dev->_rx + rxq_index;
		flow_table = rcu_dereference(rxqueue->rps_flow_table);
		if (!flow_table)
			goto out;
		flow_id = skb->rxhash & flow_table->mask;
		rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb,
							rxq_index, flow_id);
		if (rc < 0)
			goto out;
		old_rflow = rflow;
		rflow = &flow_table->flows[flow_id];
		rflow->filter = rc;
		if (old_rflow->filter == rflow->filter)
			old_rflow->filter = RPS_NO_FILTER;
	out:
#endif
		rflow->last_qtail =
			per_cpu(softnet_data, next_cpu).input_queue_head;
/*
 * get_rps_cpu is called from netif_receive_skb and returns the target
 * CPU from the RPS map of the receiving queue for a given skb.
 * rcu_read_lock must be held on entry.
 */
static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
		       struct rps_dev_flow **rflowp)
{
	struct netdev_rx_queue *rxqueue;
Eric Dumazet's avatar
Eric Dumazet committed
	struct rps_map *map;
	struct rps_dev_flow_table *flow_table;
	struct rps_sock_flow_table *sock_flow_table;
	int cpu = -1;
	u16 tcpu;

	if (skb_rx_queue_recorded(skb)) {
		u16 index = skb_get_rx_queue(skb);
		if (unlikely(index >= dev->real_num_rx_queues)) {
			WARN_ONCE(dev->real_num_rx_queues > 1,
				  "%s received packet on queue %u, but number "
				  "of RX queues is %u\n",
				  dev->name, index, dev->real_num_rx_queues);
			goto done;
		}
		rxqueue = dev->_rx + index;
	} else
		rxqueue = dev->_rx;

Eric Dumazet's avatar
Eric Dumazet committed
	map = rcu_dereference(rxqueue->rps_map);
	if (map) {
		if (map->len == 1 &&
		    !rcu_access_pointer(rxqueue->rps_flow_table)) {
			tcpu = map->cpus[0];
			if (cpu_online(tcpu))
				cpu = tcpu;
			goto done;
		}
	} else if (!rcu_access_pointer(rxqueue->rps_flow_table)) {
	skb_reset_network_header(skb);
	if (!skb_get_rxhash(skb))
		goto done;

Tom Herbert's avatar
Tom Herbert committed
	flow_table = rcu_dereference(rxqueue->rps_flow_table);
	sock_flow_table = rcu_dereference(rps_sock_flow_table);
	if (flow_table && sock_flow_table) {
		u16 next_cpu;
		struct rps_dev_flow *rflow;

		rflow = &flow_table->flows[skb->rxhash & flow_table->mask];
		tcpu = rflow->cpu;

		next_cpu = sock_flow_table->ents[skb->rxhash &
		    sock_flow_table->mask];

		/*
		 * If the desired CPU (where last recvmsg was done) is
		 * different from current CPU (one in the rx-queue flow
		 * table entry), switch if one of the following holds:
		 *   - Current CPU is unset (equal to RPS_NO_CPU).
		 *   - Current CPU is offline.
		 *   - The current CPU's queue tail has advanced beyond the
		 *     last packet that was enqueued using this table entry.
		 *     This guarantees that all previous packets for the flow
		 *     have been dequeued, thus preserving in order delivery.
		 */
		if (unlikely(tcpu != next_cpu) &&
		    (tcpu == RPS_NO_CPU || !cpu_online(tcpu) ||
		     ((int)(per_cpu(softnet_data, tcpu).input_queue_head -
		      rflow->last_qtail)) >= 0))
			rflow = set_rps_cpu(dev, skb, rflow, next_cpu);

Tom Herbert's avatar
Tom Herbert committed
		if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) {
			*rflowp = rflow;
			cpu = tcpu;
			goto done;
		}
	}

	if (map) {
Tom Herbert's avatar
Tom Herbert committed
		tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];

		if (cpu_online(tcpu)) {
			cpu = tcpu;
			goto done;
		}
	}

done:
	return cpu;
}

#ifdef CONFIG_RFS_ACCEL

/**
 * rps_may_expire_flow - check whether an RFS hardware filter may be removed
 * @dev: Device on which the filter was set
 * @rxq_index: RX queue index
 * @flow_id: Flow ID passed to ndo_rx_flow_steer()
 * @filter_id: Filter ID returned by ndo_rx_flow_steer()
 *
 * Drivers that implement ndo_rx_flow_steer() should periodically call
 * this function for each installed filter and remove the filters for
 * which it returns %true.
 */
bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index,
			 u32 flow_id, u16 filter_id)
{
	struct netdev_rx_queue *rxqueue = dev->_rx + rxq_index;
	struct rps_dev_flow_table *flow_table;
	struct rps_dev_flow *rflow;
	bool expire = true;
	int cpu;

	rcu_read_lock();
	flow_table = rcu_dereference(rxqueue->rps_flow_table);
	if (flow_table && flow_id <= flow_table->mask) {
		rflow = &flow_table->flows[flow_id];
		cpu = ACCESS_ONCE(rflow->cpu);
		if (rflow->filter == filter_id && cpu != RPS_NO_CPU &&
		    ((int)(per_cpu(softnet_data, cpu).input_queue_head -
			   rflow->last_qtail) <
		     (int)(10 * flow_table->mask)))
			expire = false;
	}
	rcu_read_unlock();
	return expire;
}
EXPORT_SYMBOL(rps_may_expire_flow);

#endif /* CONFIG_RFS_ACCEL */

/* Called from hardirq (IPI) context */
Eric Dumazet's avatar
Eric Dumazet committed
static void rps_trigger_softirq(void *data)
Eric Dumazet's avatar
Eric Dumazet committed
	struct softnet_data *sd = data;

Eric Dumazet's avatar
Eric Dumazet committed
	____napi_schedule(sd, &sd->backlog);
Changli Gao's avatar
Changli Gao committed
	sd->received_rps++;
Eric Dumazet's avatar
Eric Dumazet committed

Tom Herbert's avatar
Tom Herbert committed
#endif /* CONFIG_RPS */
Eric Dumazet's avatar
Eric Dumazet committed
/*
 * Check if this softnet_data structure is another cpu one
 * If yes, queue it to our IPI list and return 1
 * If no, return 0
 */
static int rps_ipi_queued(struct softnet_data *sd)
{
#ifdef CONFIG_RPS
	struct softnet_data *mysd = &__get_cpu_var(softnet_data);

	if (sd != mysd) {
		sd->rps_ipi_next = mysd->rps_ipi_list;
		mysd->rps_ipi_list = sd;

		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
		return 1;
	}
#endif /* CONFIG_RPS */
	return 0;
}

/*
 * enqueue_to_backlog is called to queue an skb to a per CPU backlog
 * queue (may be a remote CPU queue).
 */
Tom Herbert's avatar
Tom Herbert committed
static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
			      unsigned int *qtail)
Eric Dumazet's avatar
Eric Dumazet committed
	struct softnet_data *sd;
	unsigned long flags;

Eric Dumazet's avatar
Eric Dumazet committed
	sd = &per_cpu(softnet_data, cpu);

	local_irq_save(flags);

Eric Dumazet's avatar
Eric Dumazet committed
	rps_lock(sd);
	if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) {
		if (skb_queue_len(&sd->input_pkt_queue)) {
enqueue:
Eric Dumazet's avatar
Eric Dumazet committed
			__skb_queue_tail(&sd->input_pkt_queue, skb);
			input_queue_tail_incr_save(sd, qtail);
Eric Dumazet's avatar
Eric Dumazet committed
			rps_unlock(sd);
			local_irq_restore(flags);
			return NET_RX_SUCCESS;
		}

		/* Schedule NAPI for backlog device
		 * We can use non atomic operation since we own the queue lock
		 */
		if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) {
Eric Dumazet's avatar
Eric Dumazet committed
			if (!rps_ipi_queued(sd))
Eric Dumazet's avatar
Eric Dumazet committed
				____napi_schedule(sd, &sd->backlog);
Changli Gao's avatar
Changli Gao committed
	sd->dropped++;
Eric Dumazet's avatar
Eric Dumazet committed
	rps_unlock(sd);

	local_irq_restore(flags);

	atomic_long_inc(&skb->dev->rx_dropped);
	kfree_skb(skb);
	return NET_RX_DROP;
}
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	netif_rx	-	post buffer to the network code
 *	@skb: buffer to post
 *
 *	This function receives a packet from a device driver and queues it for
 *	the upper (protocol) levels to process.  It always succeeds. The buffer
 *	may be dropped during processing for congestion control or by the
 *	protocol layers.
 *
 *	return values:
 *	NET_RX_SUCCESS	(no congestion)
 *	NET_RX_DROP     (packet was dropped)
 *
 */

int netif_rx(struct sk_buff *skb)
{
Linus Torvalds's avatar
Linus Torvalds committed

	/* if netpoll wants it, pretend we never saw it */
	if (netpoll_rx(skb))
		return NET_RX_DROP;

	net_timestamp_check(netdev_tstamp_prequeue, skb);
Linus Torvalds's avatar
Linus Torvalds committed

	trace_netif_rx(skb);
Eric Dumazet's avatar
Eric Dumazet committed
#ifdef CONFIG_RPS
	if (static_branch(&rps_needed))	{
Tom Herbert's avatar
Tom Herbert committed
		struct rps_dev_flow voidflow, *rflow = &voidflow;
		rcu_read_lock();
Tom Herbert's avatar
Tom Herbert committed

		cpu = get_rps_cpu(skb->dev, skb, &rflow);
		if (cpu < 0)
			cpu = smp_processor_id();
Tom Herbert's avatar
Tom Herbert committed

		ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);

		rcu_read_unlock();
Tom Herbert's avatar
Tom Herbert committed
	{
		unsigned int qtail;
		ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
		put_cpu();
	}
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(netif_rx);
Linus Torvalds's avatar
Linus Torvalds committed

int netif_rx_ni(struct sk_buff *skb)
{
	int err;

	preempt_disable();
	err = netif_rx(skb);
	if (local_softirq_pending())
		do_softirq();
	preempt_enable();

	return err;
}
EXPORT_SYMBOL(netif_rx_ni);

static void net_tx_action(struct softirq_action *h)
{
	struct softnet_data *sd = &__get_cpu_var(softnet_data);

	if (sd->completion_queue) {
		struct sk_buff *clist;

		local_irq_disable();
		clist = sd->completion_queue;
		sd->completion_queue = NULL;
		local_irq_enable();

		while (clist) {
			struct sk_buff *skb = clist;
			clist = clist->next;

			WARN_ON(atomic_read(&skb->users));
			trace_kfree_skb(skb, net_tx_action);
Linus Torvalds's avatar
Linus Torvalds committed
			__kfree_skb(skb);
		}
	}

	if (sd->output_queue) {
Linus Torvalds's avatar
Linus Torvalds committed

		local_irq_disable();
		head = sd->output_queue;
		sd->output_queue = NULL;
		sd->output_queue_tailp = &sd->output_queue;
Linus Torvalds's avatar
Linus Torvalds committed
		local_irq_enable();

		while (head) {
			struct Qdisc *q = head;
			spinlock_t *root_lock;

Linus Torvalds's avatar
Linus Torvalds committed
			head = head->next_sched;

			if (spin_trylock(root_lock)) {
				smp_mb__before_clear_bit();
				clear_bit(__QDISC_STATE_SCHED,
					  &q->state);
				qdisc_run(q);
				spin_unlock(root_lock);
Linus Torvalds's avatar
Linus Torvalds committed
			} else {
				if (!test_bit(__QDISC_STATE_DEACTIVATED,
					__netif_reschedule(q);
				} else {
					smp_mb__before_clear_bit();
					clear_bit(__QDISC_STATE_SCHED,
						  &q->state);
				}
#if (defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)) && \
    (defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE))
/* This hook is defined here for ATM LANE */
int (*br_fdb_test_addr_hook)(struct net_device *dev,
			     unsigned char *addr) __read_mostly;
EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
Linus Torvalds's avatar
Linus Torvalds committed

#ifdef CONFIG_NET_CLS_ACT
/* TODO: Maybe we should just force sch_ingress to be compiled in
 * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions
 * a compare and 2 stores extra right now if we dont have it on
 * but have CONFIG_NET_CLS_ACT
Lucas De Marchi's avatar
Lucas De Marchi committed
 * NOTE: This doesn't stop any functionality; if you dont have
 * the ingress scheduler, you just can't add policies on ingress.
Linus Torvalds's avatar
Linus Torvalds committed
 *
 */
static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct net_device *dev = skb->dev;
	u32 ttl = G_TC_RTTL(skb->tc_verd);
	int result = TC_ACT_OK;
	struct Qdisc *q;
	if (unlikely(MAX_RED_LOOP < ttl++)) {
		if (net_ratelimit())
			pr_warning( "Redir loop detected Dropping packet (%d->%d)\n",
			       skb->skb_iif, dev->ifindex);
Linus Torvalds's avatar
Linus Torvalds committed

	skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl);
	skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
Linus Torvalds's avatar
Linus Torvalds committed

	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));
	}
static inline struct sk_buff *handle_ing(struct sk_buff *skb,
					 struct packet_type **pt_prev,
					 int *ret, struct net_device *orig_dev)
{
	struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue);

	if (!rxq || rxq->qdisc == &noop_qdisc)
Linus Torvalds's avatar
Linus Torvalds committed

	if (*pt_prev) {
		*ret = deliver_skb(skb, *pt_prev, orig_dev);
		*pt_prev = NULL;
	switch (ing_filter(skb, rxq)) {
	case TC_ACT_SHOT:
	case TC_ACT_STOLEN:
		kfree_skb(skb);
		return NULL;
	}

out:
	skb->tc_verd = 0;
	return skb;
Linus Torvalds's avatar
Linus Torvalds committed
}
#endif

/**
 *	netdev_rx_handler_register - register receive handler
 *	@dev: device to register a handler for
 *	@rx_handler: receive handler to register
 *	@rx_handler_data: data pointer that is used by rx handler
 *
 *	Register a receive hander for a device. This handler will then be
 *	called from __netif_receive_skb. A negative errno code is returned
 *	on a failure.
 *
 *	The caller must hold the rtnl_mutex.
 *
 *	For a general description of rx_handler, see enum rx_handler_result.
 */
int netdev_rx_handler_register(struct net_device *dev,
			       rx_handler_func_t *rx_handler,
			       void *rx_handler_data)
{
	ASSERT_RTNL();

	if (dev->rx_handler)
		return -EBUSY;

	rcu_assign_pointer(dev->rx_handler_data, rx_handler_data);
	rcu_assign_pointer(dev->rx_handler, rx_handler);

	return 0;
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_register);

/**
 *	netdev_rx_handler_unregister - unregister receive handler
 *	@dev: device to unregister a handler from
 *
 *	Unregister a receive hander from a device.
 *
 *	The caller must hold the rtnl_mutex.
 */
void netdev_rx_handler_unregister(struct net_device *dev)
{

	ASSERT_RTNL();
	RCU_INIT_POINTER(dev->rx_handler, NULL);
	RCU_INIT_POINTER(dev->rx_handler_data, NULL);
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);

static int __netif_receive_skb(struct sk_buff *skb)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct packet_type *ptype, *pt_prev;
	rx_handler_func_t *rx_handler;
	struct net_device *orig_dev;
	bool deliver_exact = false;
Linus Torvalds's avatar
Linus Torvalds committed
	int ret = NET_RX_DROP;
Al Viro's avatar
Al Viro committed
	__be16 type;
Linus Torvalds's avatar
Linus Torvalds committed

	net_timestamp_check(!netdev_tstamp_prequeue, skb);
	trace_netif_receive_skb(skb);
Linus Torvalds's avatar
Linus Torvalds committed
	/* if we've gotten here through NAPI, check netpoll */
Linus Torvalds's avatar
Linus Torvalds committed
		return NET_RX_DROP;

	if (!skb->skb_iif)
		skb->skb_iif = skb->dev->ifindex;
	orig_dev = skb->dev;
	skb_reset_network_header(skb);
	skb_reset_transport_header(skb);
	skb_reset_mac_len(skb);
Linus Torvalds's avatar
Linus Torvalds committed

	pt_prev = NULL;

	rcu_read_lock();

another_round:

	__this_cpu_inc(softnet_data.processed);

	if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
		skb = vlan_untag(skb);
		if (unlikely(!skb))
			goto out;
	}

Linus Torvalds's avatar
Linus Torvalds committed
#ifdef CONFIG_NET_CLS_ACT
	if (skb->tc_verd & TC_NCLS) {
		skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
		goto ncls;
	}
#endif

	list_for_each_entry_rcu(ptype, &ptype_all, list) {
		if (!ptype->dev || ptype->dev == skb->dev) {
				ret = deliver_skb(skb, pt_prev, orig_dev);
Linus Torvalds's avatar
Linus Torvalds committed
			pt_prev = ptype;
		}
	}

#ifdef CONFIG_NET_CLS_ACT
	skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
	if (!skb)
Linus Torvalds's avatar
Linus Torvalds committed
		goto out;
ncls:
#endif

	rx_handler = rcu_dereference(skb->dev->rx_handler);
	if (vlan_tx_tag_present(skb)) {
		if (pt_prev) {
			ret = deliver_skb(skb, pt_prev, orig_dev);
			pt_prev = NULL;
		}
		if (vlan_do_receive(&skb, !rx_handler))
			goto another_round;
		else if (unlikely(!skb))
			goto out;
	}

	if (rx_handler) {
		if (pt_prev) {
			ret = deliver_skb(skb, pt_prev, orig_dev);
			pt_prev = NULL;
		}
		switch (rx_handler(&skb)) {
		case RX_HANDLER_CONSUMED:
		case RX_HANDLER_ANOTHER:
		case RX_HANDLER_EXACT:
			deliver_exact = true;
		case RX_HANDLER_PASS:
			break;
		default:
			BUG();
		}
Linus Torvalds's avatar
Linus Torvalds committed

	/* deliver only exact match when indicated */
	null_or_dev = deliver_exact ? skb->dev : NULL;
Linus Torvalds's avatar
Linus Torvalds committed
	type = skb->protocol;
	list_for_each_entry_rcu(ptype,
			&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
		    (ptype->dev == null_or_dev || ptype->dev == skb->dev ||
		     ptype->dev == orig_dev)) {
				ret = deliver_skb(skb, pt_prev, orig_dev);
Linus Torvalds's avatar
Linus Torvalds committed
			pt_prev = ptype;
		}
	}

	if (pt_prev) {
		ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
Linus Torvalds's avatar
Linus Torvalds committed
	} else {
		atomic_long_inc(&skb->dev->rx_dropped);
Linus Torvalds's avatar
Linus Torvalds committed
		kfree_skb(skb);
		/* Jamal, now you will not able to escape explaining
		 * me how you were going to use this. :-)
		 */
		ret = NET_RX_DROP;
	}

out:
	rcu_read_unlock();
	return ret;
}

/**
 *	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)
{
	net_timestamp_check(netdev_tstamp_prequeue, skb);
	if (skb_defer_rx_timestamp(skb))
		return NET_RX_SUCCESS;

Eric Dumazet's avatar
Eric Dumazet committed
#ifdef CONFIG_RPS
	if (static_branch(&rps_needed)) {
		struct rps_dev_flow voidflow, *rflow = &voidflow;
		int cpu, ret;
		rcu_read_lock();

		cpu = get_rps_cpu(skb->dev, skb, &rflow);
		if (cpu >= 0) {
			ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
			rcu_read_unlock();
	return __netif_receive_skb(skb);
EXPORT_SYMBOL(netif_receive_skb);
Linus Torvalds's avatar
Linus Torvalds committed

/* Network device is going away, flush any packets still pending
 * Called with irqs disabled.
 */
static void flush_backlog(void *arg)
	struct net_device *dev = arg;
Eric Dumazet's avatar
Eric Dumazet committed
	struct softnet_data *sd = &__get_cpu_var(softnet_data);
	struct sk_buff *skb, *tmp;

Eric Dumazet's avatar
Eric Dumazet committed
	rps_lock(sd);
	skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
		if (skb->dev == dev) {
Eric Dumazet's avatar
Eric Dumazet committed
			__skb_unlink(skb, &sd->input_pkt_queue);
			input_queue_head_incr(sd);
Eric Dumazet's avatar
Eric Dumazet committed
	rps_unlock(sd);

	skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
		if (skb->dev == dev) {
			__skb_unlink(skb, &sd->process_queue);
			kfree_skb(skb);
			input_queue_head_incr(sd);
static int napi_gro_complete(struct sk_buff *skb)
{
	struct packet_type *ptype;
	__be16 type = skb->protocol;
	struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
	int err = -ENOENT;

	if (NAPI_GRO_CB(skb)->count == 1) {
		skb_shinfo(skb)->gso_size = 0;

	rcu_read_lock();
	list_for_each_entry_rcu(ptype, head, list) {
		if (ptype->type != type || ptype->dev || !ptype->gro_complete)
			continue;

		err = ptype->gro_complete(skb);
		break;
	}
	rcu_read_unlock();

	if (err) {
		WARN_ON(&ptype->list == head);
		kfree_skb(skb);
		return NET_RX_SUCCESS;
	}

out:
	return netif_receive_skb(skb);
}

Eric Dumazet's avatar
Eric Dumazet committed
inline void napi_gro_flush(struct napi_struct *napi)
{
	struct sk_buff *skb, *next;

	for (skb = napi->gro_list; skb; skb = next) {
		next = skb->next;
		skb->next = NULL;
		napi_gro_complete(skb);
	}

	napi->gro_list = NULL;
}
Eric Dumazet's avatar
Eric Dumazet committed
EXPORT_SYMBOL(napi_gro_flush);
enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
	struct sk_buff **pp = NULL;
	struct packet_type *ptype;
	__be16 type = skb->protocol;
	struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
	int same_flow;
	enum gro_result ret;
	if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb))
	if (skb_is_gso(skb) || skb_has_frag_list(skb))
	rcu_read_lock();
	list_for_each_entry_rcu(ptype, head, list) {
		if (ptype->type != type || ptype->dev || !ptype->gro_receive)
			continue;

		skb_set_network_header(skb, skb_gro_offset(skb));
		mac_len = skb->network_header - skb->mac_header;
		skb->mac_len = mac_len;
		NAPI_GRO_CB(skb)->same_flow = 0;
		NAPI_GRO_CB(skb)->flush = 0;
Herbert Xu's avatar
Herbert Xu committed
		NAPI_GRO_CB(skb)->free = 0;

		pp = ptype->gro_receive(&napi->gro_list, skb);
		break;
	}
	rcu_read_unlock();

	if (&ptype->list == head)
		goto normal;

	same_flow = NAPI_GRO_CB(skb)->same_flow;
	ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED;
	if (pp) {
		struct sk_buff *nskb = *pp;

		*pp = nskb->next;
		nskb->next = NULL;
		napi_gro_complete(nskb);
	if (same_flow)
	if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS)
	NAPI_GRO_CB(skb)->count = 1;
	skb_shinfo(skb)->gso_size = skb_gro_len(skb);
	skb->next = napi->gro_list;
	napi->gro_list = skb;
	ret = GRO_HELD;
	if (skb_headlen(skb) < skb_gro_offset(skb)) {
		int grow = skb_gro_offset(skb) - skb_headlen(skb);

		BUG_ON(skb->end - skb->tail < grow);

		memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow);

		skb->tail += grow;
		skb->data_len -= grow;

		skb_shinfo(skb)->frags[0].page_offset += grow;
		skb_frag_size_sub(&skb_shinfo(skb)->frags[0], grow);
		if (unlikely(!skb_frag_size(&skb_shinfo(skb)->frags[0]))) {
			skb_frag_unref(skb, 0);
			memmove(skb_shinfo(skb)->frags,
				skb_shinfo(skb)->frags + 1,
				--skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
	ret = GRO_NORMAL;
	goto pull;
EXPORT_SYMBOL(dev_gro_receive);

static inline gro_result_t
__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
	struct sk_buff *p;

	for (p = napi->gro_list; p; p = p->next) {
		unsigned long diffs;

		diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
		diffs |= p->vlan_tci ^ skb->vlan_tci;
		diffs |= compare_ether_header(skb_mac_header(p),
					      skb_gro_mac_header(skb));
		NAPI_GRO_CB(p)->same_flow = !diffs;
		NAPI_GRO_CB(p)->flush = 0;
	}

	return dev_gro_receive(napi, skb);
}
gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
	switch (ret) {
	case GRO_NORMAL:
		if (netif_receive_skb(skb))
			ret = GRO_DROP;
		break;
	case GRO_DROP:
	case GRO_MERGED_FREE:
Herbert Xu's avatar
Herbert Xu committed
		kfree_skb(skb);
		break;

	case GRO_HELD:
	case GRO_MERGED:
		break;
}
EXPORT_SYMBOL(napi_skb_finish);

void skb_gro_reset_offset(struct sk_buff *skb)
{
	NAPI_GRO_CB(skb)->data_offset = 0;
	NAPI_GRO_CB(skb)->frag0 = NULL;
	NAPI_GRO_CB(skb)->frag0_len = 0;
	if (skb->mac_header == skb->tail &&
	    !PageHighMem(skb_frag_page(&skb_shinfo(skb)->frags[0]))) {
		NAPI_GRO_CB(skb)->frag0 =
			skb_frag_address(&skb_shinfo(skb)->frags[0]);
		NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(&skb_shinfo(skb)->frags[0]);
}
EXPORT_SYMBOL(skb_gro_reset_offset);

gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
	skb_gro_reset_offset(skb);

	return napi_skb_finish(__napi_gro_receive(napi, skb), skb);
}
EXPORT_SYMBOL(napi_gro_receive);

static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
{
	__skb_pull(skb, skb_headlen(skb));
	skb_reserve(skb, NET_IP_ALIGN - skb_headroom(skb));
	skb->dev = napi->dev;
	skb->skb_iif = 0;
struct sk_buff *napi_get_frags(struct napi_struct *napi)
Herbert Xu's avatar
Herbert Xu committed
{
	struct sk_buff *skb = napi->skb;

	if (!skb) {
		skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD);
		if (skb)
			napi->skb = skb;
EXPORT_SYMBOL(napi_get_frags);
gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
			       gro_result_t ret)
	switch (ret) {
	case GRO_NORMAL:
		skb->protocol = eth_type_trans(skb, skb->dev);
		if (ret == GRO_HELD)
			skb_gro_pull(skb, -ETH_HLEN);
		else if (netif_receive_skb(skb))
			ret = GRO_DROP;
	case GRO_DROP:
	case GRO_MERGED_FREE:
		napi_reuse_skb(napi, skb);
		break;
EXPORT_SYMBOL(napi_frags_finish);

struct sk_buff *napi_frags_skb(struct napi_struct *napi)
{
	struct sk_buff *skb = napi->skb;
	struct ethhdr *eth;
	unsigned int hlen;
	unsigned int off;

	napi->skb = NULL;

	skb_reset_mac_header(skb);
	skb_gro_reset_offset(skb);

	off = skb_gro_offset(skb);
	hlen = off + sizeof(*eth);
	eth = skb_gro_header_fast(skb, off);
	if (skb_gro_header_hard(skb, hlen)) {
		eth = skb_gro_header_slow(skb, hlen, off);
		if (unlikely(!eth)) {
			napi_reuse_skb(napi, skb);
			skb = NULL;
			goto out;
		}
	}

	skb_gro_pull(skb, sizeof(*eth));

	/*
	 * This works because the only protocols we care about don't require
	 * special handling.  We'll fix it up properly at the end.
	 */
	skb->protocol = eth->h_proto;

out:
	return skb;
}
EXPORT_SYMBOL(napi_frags_skb);

gro_result_t napi_gro_frags(struct napi_struct *napi)
	struct sk_buff *skb = napi_frags_skb(napi);

	return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb));
}
Herbert Xu's avatar
Herbert Xu committed
EXPORT_SYMBOL(napi_gro_frags);

/*
 * net_rps_action sends any pending IPI's for rps.
 * Note: called with local irq disabled, but exits with local irq enabled.
 */
static void net_rps_action_and_irq_enable(struct softnet_data *sd)
{
#ifdef CONFIG_RPS
	struct softnet_data *remsd = sd->rps_ipi_list;

	if (remsd) {
		sd->rps_ipi_list = NULL;

		local_irq_enable();

		/* Send pending IPI's to kick RPS processing on remote cpus. */
		while (remsd) {
			struct softnet_data *next = remsd->rps_ipi_next;

			if (cpu_online(remsd->cpu))
				__smp_call_function_single(remsd->cpu,
							   &remsd->csd, 0);
			remsd = next;
		}
	} else
#endif
		local_irq_enable();
}

static int process_backlog(struct napi_struct *napi, int quota)
Linus Torvalds's avatar
Linus Torvalds committed
{
	int work = 0;
Eric Dumazet's avatar
Eric Dumazet committed
	struct softnet_data *sd = container_of(napi, struct softnet_data, backlog);
Linus Torvalds's avatar
Linus Torvalds committed

#ifdef CONFIG_RPS
	/* Check if we have pending ipi, its better to send them now,
	 * not waiting net_rx_action() end.
	 */
	if (sd->rps_ipi_list) {
		local_irq_disable();
		net_rps_action_and_irq_enable(sd);
	}
#endif
	local_irq_disable();
	while (work < quota) {
Linus Torvalds's avatar
Linus Torvalds committed
		struct sk_buff *skb;
		unsigned int qlen;

		while ((skb = __skb_dequeue(&sd->process_queue))) {
			local_irq_enable();
			__netif_receive_skb(skb);
			local_irq_disable();
			input_queue_head_incr(sd);
			if (++work >= quota) {
				local_irq_enable();
				return work;
			}
Linus Torvalds's avatar
Linus Torvalds committed

Eric Dumazet's avatar
Eric Dumazet committed
		rps_lock(sd);
		qlen = skb_queue_len(&sd->input_pkt_queue);
			skb_queue_splice_tail_init(&sd->input_pkt_queue,
						   &sd->process_queue);
		if (qlen < quota - work) {
Eric Dumazet's avatar
Eric Dumazet committed
			/*
			 * Inline a custom version of __napi_complete().
			 * only current cpu owns and manipulates this napi,
			 * and NAPI_STATE_SCHED is the only possible flag set on backlog.
			 * we can use a plain write instead of clear_bit(),
			 * and we dont need an smp_mb() memory barrier.
			 */
			list_del(&napi->poll_list);
			napi->state = 0;

Eric Dumazet's avatar
Eric Dumazet committed
		rps_unlock(sd);
Linus Torvalds's avatar
Linus Torvalds committed

Linus Torvalds's avatar
Linus Torvalds committed

/**
 * __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)
Linus Torvalds's avatar
Linus Torvalds committed

Eric Dumazet's avatar
Eric Dumazet committed
	____napi_schedule(&__get_cpu_var(softnet_data), n);
Linus Torvalds's avatar
Linus Torvalds committed
}
void __napi_complete(struct napi_struct *n)
{
	BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
	BUG_ON(n->gro_list);

	list_del(&n->poll_list);
	smp_mb__before_clear_bit();
	clear_bit(NAPI_STATE_SCHED, &n->state);
}
EXPORT_SYMBOL(__napi_complete);

void napi_complete(struct napi_struct *n)
{
	unsigned long flags;

	/*
	 * don't let napi dequeue from the cpu poll list
	 * just in case its running on a different cpu
	 */
	if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
		return;

	napi_gro_flush(n);
	local_irq_save(flags);
	__napi_complete(n);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(napi_complete);

void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
		    int (*poll)(struct napi_struct *, int), int weight)
{
	INIT_LIST_HEAD(&napi->poll_list);
	napi->gro_list = NULL;
Herbert Xu's avatar
Herbert Xu committed
	napi->skb = NULL;
	napi->poll = poll;
	napi->weight = weight;
	list_add(&napi->dev_list, &dev->napi_list);
	napi->dev = dev;
Herbert Xu's avatar
Herbert Xu committed
#ifdef CONFIG_NETPOLL
	spin_lock_init(&napi->poll_lock);
	napi->poll_owner = -1;
#endif
	set_bit(NAPI_STATE_SCHED, &napi->state);
}
EXPORT_SYMBOL(netif_napi_add);

void netif_napi_del(struct napi_struct *napi)
{
	struct sk_buff *skb, *next;

	list_del_init(&napi->dev_list);
	napi_free_frags(napi);

	for (skb = napi->gro_list; skb; skb = next) {
		next = skb->next;
		skb->next = NULL;
		kfree_skb(skb);
	}

	napi->gro_list = NULL;
}
EXPORT_SYMBOL(netif_napi_del);

Linus Torvalds's avatar
Linus Torvalds committed
static void net_rx_action(struct softirq_action *h)
{
	struct softnet_data *sd = &__get_cpu_var(softnet_data);
	unsigned long time_limit = jiffies + 2;
	int budget = netdev_budget;
Linus Torvalds's avatar
Linus Torvalds committed
	local_irq_disable();

	while (!list_empty(&sd->poll_list)) {
		struct napi_struct *n;
		int work, weight;
Linus Torvalds's avatar
Linus Torvalds committed

		/* If softirq window is exhuasted then punt.
		 * Allow this to run for 2 jiffies since which will allow
		 * an average latency of 1.5/HZ.
		if (unlikely(budget <= 0 || time_after(jiffies, time_limit)))
Linus Torvalds's avatar
Linus Torvalds committed
			goto softnet_break;

		local_irq_enable();

		/* Even though interrupts have been re-enabled, this
		 * access is safe because interrupts can only add new
		 * entries to the tail of this list, and only ->poll()
		 * calls can remove this head entry from the list.
		 */
		n = list_first_entry(&sd->poll_list, struct napi_struct, poll_list);
Linus Torvalds's avatar
Linus Torvalds committed

		/* 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
Lucas De Marchi's avatar
Lucas De Marchi committed
		 * accidentally calling ->poll() when NAPI is not scheduled.
		if (test_bit(NAPI_STATE_SCHED, &n->state)) {
			work = n->poll(n, weight);

		WARN_ON_ONCE(work > weight);

		budget -= work;

		local_irq_disable();

		/* Drivers must not modify the NAPI state if they
		 * consume the entire weight.  In such cases this code
		 * still "owns" the NAPI instance and therefore can
		 * move the instance around on the list at-will.
		 */
		if (unlikely(work == weight)) {
			if (unlikely(napi_disable_pending(n))) {
				local_irq_enable();
				napi_complete(n);
				local_irq_disable();
			} else
				list_move_tail(&n->poll_list, &sd->poll_list);
Linus Torvalds's avatar
Linus Torvalds committed
	}
out:
	net_rps_action_and_irq_enable(sd);
#ifdef CONFIG_NET_DMA
	/*
	 * There may not be any more sk_buffs coming right now, so push
	 * any pending DMA copies to hardware
	 */
Linus Torvalds's avatar
Linus Torvalds committed
	return;

softnet_break:
Changli Gao's avatar
Changli Gao committed
	sd->time_squeeze++;
Linus Torvalds's avatar
Linus Torvalds committed
	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
	goto out;
}

static gifconf_func_t *gifconf_list[NPROTO];
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	register_gifconf	-	register a SIOCGIF handler
 *	@family: Address family
 *	@gifconf: Function handler
 *
 *	Register protocol dependent address dumping routines. The handler
 *	that is passed must not be freed or reused until it has been replaced
 *	by another handler.
 */
int register_gifconf(unsigned int family, gifconf_func_t *gifconf)
Linus Torvalds's avatar
Linus Torvalds committed
{
	if (family >= NPROTO)
		return -EINVAL;
	gifconf_list[family] = gifconf;
	return 0;
}
EXPORT_SYMBOL(register_gifconf);
Linus Torvalds's avatar
Linus Torvalds committed


/*
 *	Map an interface index to its name (SIOCGIFNAME)
 */

/*
 *	We need this ioctl for efficient implementation of the
 *	if_indextoname() function required by the IPv6 API.  Without
 *	it, we would have to search all the interfaces to find a
 *	match.  --pb
 */

static int dev_ifname(struct net *net, struct ifreq __user *arg)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct net_device *dev;
	struct ifreq ifr;

	/*
	 *	Fetch the caller's info block.
	 */

	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
		return -EFAULT;

	rcu_read_lock();
	dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex);
Linus Torvalds's avatar
Linus Torvalds committed
	if (!dev) {
		rcu_read_unlock();
Linus Torvalds's avatar
Linus Torvalds committed
		return -ENODEV;
	}

	strcpy(ifr.ifr_name, dev->name);
	rcu_read_unlock();
Linus Torvalds's avatar
Linus Torvalds committed

	if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
		return -EFAULT;
	return 0;
}

/*
 *	Perform a SIOCGIFCONF call. This structure will change
 *	size eventually, and there is nothing I can do about it.
 *	Thus we will need a 'compatibility mode'.
 */

static int dev_ifconf(struct net *net, char __user *arg)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct ifconf ifc;
	struct net_device *dev;
	char __user *pos;
	int len;
	int total;
	int i;

	/*
	 *	Fetch the caller's info block.
	 */

	if (copy_from_user(&ifc, arg, sizeof(struct ifconf)))
		return -EFAULT;

	pos = ifc.ifc_buf;
	len = ifc.ifc_len;

	/*
	 *	Loop over the interfaces, and write an info block for each.
	 */

	total = 0;
Linus Torvalds's avatar
Linus Torvalds committed
		for (i = 0; i < NPROTO; i++) {
			if (gifconf_list[i]) {
				int done;
				if (!pos)
					done = gifconf_list[i](dev, NULL, 0);
				else
					done = gifconf_list[i](dev, pos + total,
							       len - total);
				if (done < 0)
					return -EFAULT;
				total += done;
			}
		}
Linus Torvalds's avatar
Linus Torvalds committed

	/*
	 *	All done.  Write the updated control block back to the caller.
	 */
	ifc.ifc_len = total;

	/*
	 * 	Both BSD and Solaris return 0 here, so we do too.
	 */
	return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0;
}

#ifdef CONFIG_PROC_FS

#define BUCKET_SPACE (32 - NETDEV_HASHBITS)

struct dev_iter_state {
	struct seq_net_private p;
	unsigned int pos; /* bucket << BUCKET_SPACE + offset */
};

#define get_bucket(x) ((x) >> BUCKET_SPACE)
#define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1))
#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o))

static inline struct net_device *dev_from_same_bucket(struct seq_file *seq)
{
	struct dev_iter_state *state = seq->private;
	struct net *net = seq_file_net(seq);
	struct net_device *dev;
	struct hlist_node *p;
	struct hlist_head *h;
	unsigned int count, bucket, offset;

	bucket = get_bucket(state->pos);
	offset = get_offset(state->pos);
	h = &net->dev_name_head[bucket];
	count = 0;
	hlist_for_each_entry_rcu(dev, p, h, name_hlist) {
		if (count++ == offset) {
			state->pos = set_bucket_offset(bucket, count);
			return dev;
		}
	}

	return NULL;
}

static inline struct net_device *dev_from_new_bucket(struct seq_file *seq)
{
	struct dev_iter_state *state = seq->private;
	struct net_device *dev;
	unsigned int bucket;

	bucket = get_bucket(state->pos);
	do {
		dev = dev_from_same_bucket(seq);
		if (dev)
			return dev;

		bucket++;
		state->pos = set_bucket_offset(bucket, 0);
	} while (bucket < NETDEV_HASHENTRIES);

	return NULL;
}

Linus Torvalds's avatar
Linus Torvalds committed
/*
 *	This is invoked by the /proc filesystem handler to display a device
 *	in detail.
 */
void *dev_seq_start(struct seq_file *seq, loff_t *pos)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct dev_iter_state *state = seq->private;
Linus Torvalds's avatar
Linus Torvalds committed

	if (!*pos)
		return SEQ_START_TOKEN;
Linus Torvalds's avatar
Linus Torvalds committed

	/* check for end of the hash */
	if (state->pos == 0 && *pos > 1)
		return NULL;
Linus Torvalds's avatar
Linus Torvalds committed

	return dev_from_new_bucket(seq);
Linus Torvalds's avatar
Linus Torvalds committed
}

void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct net_device *dev;

	++*pos;
Eric Dumazet's avatar
Eric Dumazet committed

	if (v == SEQ_START_TOKEN)
		return dev_from_new_bucket(seq);
	dev = dev_from_same_bucket(seq);
	if (dev)
		return dev;

	return dev_from_new_bucket(seq);
Linus Torvalds's avatar
Linus Torvalds committed
}

void dev_seq_stop(struct seq_file *seq, void *v)
Linus Torvalds's avatar
Linus Torvalds committed
{
	rcu_read_unlock();
Linus Torvalds's avatar
Linus Torvalds committed
}

static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
{
	struct rtnl_link_stats64 temp;
	const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp);
Linus Torvalds's avatar
Linus Torvalds committed

	seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu "
		   "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\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);
Linus Torvalds's avatar
Linus Torvalds committed
}

/*
 *	Called from the PROCfs module. This now uses the new arbitrary sized
 *	/proc/net interface to create /proc/net/dev
 */
static int dev_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN)
		seq_puts(seq, "Inter-|   Receive                            "
			      "                    |  Transmit\n"
			      " face |bytes    packets errs drop fifo frame "
			      "compressed multicast|bytes    packets errs "
			      "drop fifo colls carrier compressed\n");
	else
		dev_seq_printf_stats(seq, v);
	return 0;
}

Changli Gao's avatar
Changli Gao committed
static struct softnet_data *softnet_get_online(loff_t *pos)
Linus Torvalds's avatar
Linus Torvalds committed
{
Changli Gao's avatar
Changli Gao committed
	struct softnet_data *sd = NULL;
Linus Torvalds's avatar
Linus Torvalds committed

	while (*pos < nr_cpu_ids)
		if (cpu_online(*pos)) {
Changli Gao's avatar
Changli Gao committed
			sd = &per_cpu(softnet_data, *pos);
Linus Torvalds's avatar
Linus Torvalds committed
			break;
		} else
			++*pos;
Changli Gao's avatar
Changli Gao committed
	return sd;
Linus Torvalds's avatar
Linus Torvalds committed
}

static void *softnet_seq_start(struct seq_file *seq, loff_t *pos)
{
	return softnet_get_online(pos);
}

static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	++*pos;
	return softnet_get_online(pos);
}

static void softnet_seq_stop(struct seq_file *seq, void *v)
{
}

static int softnet_seq_show(struct seq_file *seq, void *v)
{
Changli Gao's avatar
Changli Gao committed
	struct softnet_data *sd = v;
Linus Torvalds's avatar
Linus Torvalds committed

	seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
Changli Gao's avatar
Changli Gao committed
		   sd->processed, sd->dropped, sd->time_squeeze, 0,
		   0, 0, 0, 0, /* was fastroute */
Changli Gao's avatar
Changli Gao committed
		   sd->cpu_collision, sd->received_rps);
Linus Torvalds's avatar
Linus Torvalds committed
	return 0;
}

static const struct seq_operations dev_seq_ops = {
Linus Torvalds's avatar
Linus Torvalds committed
	.start = dev_seq_start,
	.next  = dev_seq_next,
	.stop  = dev_seq_stop,
	.show  = dev_seq_show,
};

static int dev_seq_open(struct inode *inode, struct file *file)
{
	return seq_open_net(inode, file, &dev_seq_ops,
			    sizeof(struct dev_iter_state));
int dev_seq_open_ops(struct inode *inode, struct file *file,
		     const struct seq_operations *ops)
{
	return seq_open_net(inode, file, ops, sizeof(struct dev_iter_state));
}

static const struct file_operations dev_seq_fops = {
Linus Torvalds's avatar
Linus Torvalds committed
	.owner	 = THIS_MODULE,
	.open    = dev_seq_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
static const struct seq_operations softnet_seq_ops = {
Linus Torvalds's avatar
Linus Torvalds committed
	.start = softnet_seq_start,
	.next  = softnet_seq_next,
	.stop  = softnet_seq_stop,
	.show  = softnet_seq_show,
};

static int softnet_seq_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &softnet_seq_ops);
}

static const struct file_operations softnet_seq_fops = {
Linus Torvalds's avatar
Linus Torvalds committed
	.owner	 = THIS_MODULE,
	.open    = softnet_seq_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release,
};

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)
{
	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)
{
	rcu_read_unlock();
}

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 %pF\n",
			   pt->dev ? pt->dev->name : "", pt->func);
	}

	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)
Linus Torvalds's avatar
Linus Torvalds committed
{
	int rc = -ENOMEM;

	if (!proc_net_fops_create(net, "dev", S_IRUGO, &dev_seq_fops))
Linus Torvalds's avatar
Linus Torvalds committed
		goto out;
	if (!proc_net_fops_create(net, "softnet_stat", S_IRUGO, &softnet_seq_fops))
Linus Torvalds's avatar
Linus Torvalds committed
		goto out_dev;
	if (!proc_net_fops_create(net, "ptype", S_IRUGO, &ptype_seq_fops))
Linus Torvalds's avatar
Linus Torvalds committed
	rc = 0;
out:
	return rc;
Linus Torvalds's avatar
Linus Torvalds committed
out_softnet:
	proc_net_remove(net, "softnet_stat");
Linus Torvalds's avatar
Linus Torvalds committed
out_dev:
Linus Torvalds's avatar
Linus Torvalds committed
	goto out;
}
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);
}
Linus Torvalds's avatar
Linus Torvalds committed
#else
#define dev_proc_init() 0
#endif	/* CONFIG_PROC_FS */


/**
 *	netdev_set_master	-	set up master pointer
Linus Torvalds's avatar
Linus Torvalds committed
 *	@slave: slave device
 *	@master: new master device
 *
 *	Changes the master device of the slave. Pass %NULL to break the
 *	bonding. The caller must hold the RTNL semaphore. On a failure
 *	a negative errno code is returned. On success the reference counts
 *	are adjusted and the function returns zero.
Linus Torvalds's avatar
Linus Torvalds committed
 */
int netdev_set_master(struct net_device *slave, struct net_device *master)
{
	struct net_device *old = slave->master;

	ASSERT_RTNL();

	if (master) {
		if (old)
			return -EBUSY;
		dev_hold(master);
	}

	slave->master = master;
Linus Torvalds's avatar
Linus Torvalds committed
		dev_put(old);
	return 0;
}
EXPORT_SYMBOL(netdev_set_master);

/**
 *	netdev_set_bond_master	-	set up bonding master/slave pair
 *	@slave: slave device
 *	@master: new master device
 *
 *	Changes the master device of the slave. Pass %NULL to break the
 *	bonding. The caller must hold the RTNL semaphore. On a failure
 *	a negative errno code is returned. On success %RTM_NEWLINK is sent
 *	to the routing socket and the function returns zero.
 */
int netdev_set_bond_master(struct net_device *slave, struct net_device *master)
{
	int err;

	ASSERT_RTNL();

	err = netdev_set_master(slave, master);
	if (err)
		return err;
Linus Torvalds's avatar
Linus Torvalds committed
	if (master)
		slave->flags |= IFF_SLAVE;
	else
		slave->flags &= ~IFF_SLAVE;

	rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE);
	return 0;
}
EXPORT_SYMBOL(netdev_set_bond_master);
Linus Torvalds's avatar
Linus Torvalds committed

static void dev_change_rx_flags(struct net_device *dev, int flags)
{
	const struct net_device_ops *ops = dev->netdev_ops;

	if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags)
		ops->ndo_change_rx_flags(dev, flags);
static int __dev_set_promiscuity(struct net_device *dev, int inc)
Linus Torvalds's avatar
Linus Torvalds committed
{
	unsigned int old_flags = dev->flags;
Linus Torvalds's avatar
Linus Torvalds committed

	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;
		}
	}
Linus Torvalds's avatar
Linus Torvalds committed
		printk(KERN_INFO "device %s %s promiscuous mode\n",
		       dev->name, (dev->flags & IFF_PROMISC) ? "entered" :
		if (audit_enabled) {
			current_uid_gid(&uid, &gid);
			audit_log(current->audit_context, GFP_ATOMIC,
				AUDIT_ANOM_PROMISCUOUS,
				"dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u",
				dev->name, (dev->flags & IFF_PROMISC),
				(old_flags & IFF_PROMISC),
				audit_get_loginuid(current),
				audit_get_sessionid(current));
		dev_change_rx_flags(dev, IFF_PROMISC);
Linus Torvalds's avatar
Linus Torvalds committed
	}
/**
 *	dev_set_promiscuity	- update promiscuity count on a device
 *	@dev: device
 *	@inc: modifier
 *
 *	Add or remove promiscuity from a device. While the count in the 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.
int dev_set_promiscuity(struct net_device *dev, int inc)
	unsigned int old_flags = dev->flags;
	err = __dev_set_promiscuity(dev, inc);
	if (dev->flags != old_flags)
		dev_set_rx_mode(dev);
EXPORT_SYMBOL(dev_set_promiscuity);
Linus Torvalds's avatar
Linus Torvalds committed
/**
 *	dev_set_allmulti	- update allmulti count on a device
 *	@dev: device
 *	@inc: modifier
 *
 *	Add or remove reception of all multicast frames to a device. While the
 *	count in the device remains above zero the interface remains listening
 *	to all interfaces. Once it hits zero the device reverts back to normal
 *	filtering operation. A negative @inc value is used to drop the counter
 *	when releasing a resource needing all multicasts.
 *	Return 0 if successful or a negative errno code on error.
int dev_set_allmulti(struct net_device *dev, int inc)
Linus Torvalds's avatar
Linus Torvalds committed
{
	unsigned int old_flags = dev->flags;
Linus Torvalds's avatar
Linus Torvalds committed

Linus Torvalds's avatar
Linus Torvalds committed
	dev->flags |= IFF_ALLMULTI;
	dev->allmulti += inc;
	if (dev->allmulti == 0) {
		/*
		 * Avoid overflow.
		 * If inc causes overflow, untouch allmulti and return error.
		 */
		if (inc < 0)
			dev->flags &= ~IFF_ALLMULTI;
		else {
			dev->allmulti -= inc;
			printk(KERN_WARNING "%s: allmulti touches roof, "
				"set allmulti failed, allmulti feature of "
				"device might be broken.\n", dev->name);
			return -EOVERFLOW;
		}
	}
	if (dev->flags ^ old_flags) {
		dev_change_rx_flags(dev, IFF_ALLMULTI);
		dev_set_rx_mode(dev);
EXPORT_SYMBOL(dev_set_allmulti);

/*
 *	Upload unicast and multicast address lists to device and
 *	configure RX filtering. When the device doesn't support unicast
 *	filtering it is put in promiscuous mode while unicast addresses
 *	are present.
 */
void __dev_set_rx_mode(struct net_device *dev)
{
	const struct net_device_ops *ops = dev->netdev_ops;

	/* dev_open will call this function so the list will stay sane. */
	if (!(dev->flags&IFF_UP))
		return;

	if (!netif_device_present(dev))
	if (!(dev->priv_flags & IFF_UNICAST_FLT)) {
		/* Unicast addresses changes may only happen under the rtnl,
		 * therefore calling __dev_set_promiscuity here is safe.
		 */
		if (!netdev_uc_empty(dev) && !dev->uc_promisc) {
			__dev_set_promiscuity(dev, 1);
			dev->uc_promisc = true;
		} else if (netdev_uc_empty(dev) && dev->uc_promisc) {
			__dev_set_promiscuity(dev, -1);
			dev->uc_promisc = false;

	if (ops->ndo_set_rx_mode)
		ops->ndo_set_rx_mode(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);
/**
 *	dev_get_flags - get flags reported to userspace
 *	@dev: device
 *
 *	Get the combination of flag bits exported through APIs to userspace.
 */
Linus Torvalds's avatar
Linus Torvalds committed
unsigned dev_get_flags(const struct net_device *dev)
{
	unsigned flags;

	flags = (dev->flags & ~(IFF_PROMISC |
				IFF_ALLMULTI |
				IFF_RUNNING |
				IFF_LOWER_UP |
				IFF_DORMANT)) |
Linus Torvalds's avatar
Linus Torvalds committed
		(dev->gflags & (IFF_PROMISC |
				IFF_ALLMULTI));

	if (netif_running(dev)) {
		if (netif_oper_up(dev))
			flags |= IFF_RUNNING;
		if (netif_carrier_ok(dev))
			flags |= IFF_LOWER_UP;
		if (netif_dormant(dev))
			flags |= IFF_DORMANT;
	}
Linus Torvalds's avatar
Linus Torvalds committed

	return flags;
}
EXPORT_SYMBOL(dev_get_flags);
Linus Torvalds's avatar
Linus Torvalds committed

int __dev_change_flags(struct net_device *dev, unsigned int flags)
Linus Torvalds's avatar
Linus Torvalds committed
{
	unsigned int old_flags = dev->flags;
Linus Torvalds's avatar
Linus Torvalds committed

Linus Torvalds's avatar
Linus Torvalds committed
	/*
	 *	Set the flags on our device.
	 */

	dev->flags = (flags & (IFF_DEBUG | IFF_NOTRAILERS | IFF_NOARP |
			       IFF_DYNAMIC | IFF_MULTICAST | IFF_PORTSEL |
			       IFF_AUTOMEDIA)) |
		     (dev->flags & (IFF_UP | IFF_VOLATILE | IFF_PROMISC |
				    IFF_ALLMULTI));

	/*
	 *	Load in the correct multicast list now the flags have changed.
	 */

	if ((old_flags ^ flags) & IFF_MULTICAST)
		dev_change_rx_flags(dev, IFF_MULTICAST);
	dev_set_rx_mode(dev);
Linus Torvalds's avatar
Linus Torvalds committed

	/*
	 *	Have we downed the interface. We handle IFF_UP ourselves
	 *	according to user attempts to set it, rather than blindly
	 *	setting it.
	 */

	ret = 0;
	if ((old_flags ^ flags) & IFF_UP) {	/* Bit is different  ? */
		ret = ((old_flags & IFF_UP) ? __dev_close : __dev_open)(dev);
Linus Torvalds's avatar
Linus Torvalds committed

		if (!ret)
			dev_set_rx_mode(dev);
Linus Torvalds's avatar
Linus Torvalds committed
	}

	if ((flags ^ dev->gflags) & IFF_PROMISC) {
		int inc = (flags & IFF_PROMISC) ? 1 : -1;

Linus Torvalds's avatar
Linus Torvalds committed
		dev->gflags ^= IFF_PROMISC;
		dev_set_promiscuity(dev, inc);
	}

	/* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI
	   is important. Some (broken) drivers set IFF_PROMISC, when
	   IFF_ALLMULTI is requested not asking us and not reporting.
	 */
	if ((flags ^ dev->gflags) & IFF_ALLMULTI) {
		int inc = (flags & IFF_ALLMULTI) ? 1 : -1;

Linus Torvalds's avatar
Linus Torvalds committed
		dev->gflags ^= IFF_ALLMULTI;
		dev_set_allmulti(dev, inc);
	}

	return ret;
}

void __dev_notify_flags(struct net_device *dev, unsigned int old_flags)
{
	unsigned int changes = dev->flags ^ old_flags;

	if (changes & IFF_UP) {
		if (dev->flags & IFF_UP)
			call_netdevice_notifiers(NETDEV_UP, dev);
		else
			call_netdevice_notifiers(NETDEV_DOWN, dev);
	}

	if (dev->flags & IFF_UP &&
	    (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE)))
		call_netdevice_notifiers(NETDEV_CHANGE, dev);
}

/**
 *	dev_change_flags - change device settings
 *	@dev: device
 *	@flags: device state flags
 *
 *	Change settings on device based state flags. The flags are
 *	in the userspace exported format.
 */
int dev_change_flags(struct net_device *dev, unsigned int flags)
	int ret;
	unsigned int changes, old_flags = dev->flags;

	ret = __dev_change_flags(dev, flags);
	if (ret < 0)
		return ret;

	changes = old_flags ^ dev->flags;
	if (changes)
		rtmsg_ifinfo(RTM_NEWLINK, dev, changes);
Linus Torvalds's avatar
Linus Torvalds committed

	__dev_notify_flags(dev, old_flags);
Linus Torvalds's avatar
Linus Torvalds committed
	return ret;
}
EXPORT_SYMBOL(dev_change_flags);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	dev_set_mtu - Change maximum transfer unit
 *	@dev: device
 *	@new_mtu: new transfer unit
 *
 *	Change the maximum transfer size of the network device.
 */
Linus Torvalds's avatar
Linus Torvalds committed
int dev_set_mtu(struct net_device *dev, int new_mtu)
{
	const struct net_device_ops *ops = dev->netdev_ops;
Linus Torvalds's avatar
Linus Torvalds committed
	int err;

	if (new_mtu == dev->mtu)
		return 0;

	/*	MTU must be positive.	 */
	if (new_mtu < 0)
		return -EINVAL;

	if (!netif_device_present(dev))
		return -ENODEV;

	err = 0;
	if (ops->ndo_change_mtu)
		err = ops->ndo_change_mtu(dev, new_mtu);
Linus Torvalds's avatar
Linus Torvalds committed
	else
		dev->mtu = new_mtu;
Linus Torvalds's avatar
Linus Torvalds committed
	if (!err && dev->flags & IFF_UP)
		call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
Linus Torvalds's avatar
Linus Torvalds committed
	return err;
}
EXPORT_SYMBOL(dev_set_mtu);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	dev_set_group - Change group this device belongs to
 *	@dev: device
 *	@new_group: group this device should belong to
 */
void dev_set_group(struct net_device *dev, int new_group)
{
	dev->group = new_group;
}
EXPORT_SYMBOL(dev_set_group);

/**
 *	dev_set_mac_address - Change Media Access Control Address
 *	@dev: device
 *	@sa: new address
 *
 *	Change the hardware (MAC) address of the device
 */
Linus Torvalds's avatar
Linus Torvalds committed
int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
{
	const struct net_device_ops *ops = dev->netdev_ops;
Linus Torvalds's avatar
Linus Torvalds committed
	int err;

	if (!ops->ndo_set_mac_address)
Linus Torvalds's avatar
Linus Torvalds committed
		return -EOPNOTSUPP;
	if (sa->sa_family != dev->type)
		return -EINVAL;
	if (!netif_device_present(dev))
		return -ENODEV;
	err = ops->ndo_set_mac_address(dev, sa);
Linus Torvalds's avatar
Linus Torvalds committed
	if (!err)
		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
Linus Torvalds's avatar
Linus Torvalds committed
	return err;
}
EXPORT_SYMBOL(dev_set_mac_address);
 *	Perform the SIOCxIFxxx calls, inside rcu_read_lock()
Linus Torvalds's avatar
Linus Torvalds committed
 */
static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd)
Linus Torvalds's avatar
Linus Torvalds committed
{
	int err;
	struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name);
Linus Torvalds's avatar
Linus Torvalds committed

	if (!dev)
		return -ENODEV;

	switch (cmd) {
	case SIOCGIFFLAGS:	/* Get interface flags */
		ifr->ifr_flags = (short) dev_get_flags(dev);
		return 0;
Linus Torvalds's avatar
Linus Torvalds committed

	case SIOCGIFMETRIC:	/* Get the metric on the interface
				   (currently unused) */
		ifr->ifr_metric = 0;
		return 0;
Linus Torvalds's avatar
Linus Torvalds committed

	case SIOCGIFMTU:	/* Get the MTU of a device */
		ifr->ifr_mtu = dev->mtu;
		return 0;
Linus Torvalds's avatar
Linus Torvalds committed

	case SIOCGIFHWADDR:
		if (!dev->addr_len)
			memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
		else
			memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
			       min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
		ifr->ifr_hwaddr.sa_family = dev->type;
		return 0;
Linus Torvalds's avatar
Linus Torvalds committed

	case SIOCGIFSLAVE:
		err = -EINVAL;
		break;
	case SIOCGIFMAP:
		ifr->ifr_map.mem_start = dev->mem_start;
		ifr->ifr_map.mem_end   = dev->mem_end;
		ifr->ifr_map.base_addr = dev->base_addr;
		ifr->ifr_map.irq       = dev->irq;
		ifr->ifr_map.dma       = dev->dma;
		ifr->ifr_map.port      = dev->if_port;
		return 0;
	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);
		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);
	const struct net_device_ops *ops;
	ops = dev->netdev_ops;

	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);
Linus Torvalds's avatar
Linus Torvalds committed

	case SIOCSIFHWADDR:
		return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
Linus Torvalds's avatar
Linus Torvalds committed

	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;
Linus Torvalds's avatar
Linus Torvalds committed

	case SIOCSIFMAP:
		if (ops->ndo_set_config) {
Linus Torvalds's avatar
Linus Torvalds committed
			if (!netif_device_present(dev))
				return -ENODEV;
			return ops->ndo_set_config(dev, &ifr->ifr_map);
		}
		return -EOPNOTSUPP;
Linus Torvalds's avatar
Linus Torvalds committed

	case SIOCADDMULTI:
		if (!ops->ndo_set_rx_mode ||
		    ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
			return -EINVAL;
		if (!netif_device_present(dev))
			return -ENODEV;
		return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data);

	case SIOCDELMULTI:
		if (!ops->ndo_set_rx_mode ||
		    ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
			return -EINVAL;
		if (!netif_device_present(dev))
			return -ENODEV;
		return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data);
Linus Torvalds's avatar
Linus Torvalds committed

	case SIOCSIFTXQLEN:
		if (ifr->ifr_qlen < 0)
			return -EINVAL;
		dev->tx_queue_len = ifr->ifr_qlen;
		return 0;
Linus Torvalds's avatar
Linus Torvalds committed

	case SIOCSIFNAME:
		ifr->ifr_newname[IFNAMSIZ-1] = '\0';
		return dev_change_name(dev, ifr->ifr_newname);
Linus Torvalds's avatar
Linus Torvalds committed

	case SIOCSHWTSTAMP:
		err = net_hwtstamp_validate(ifr);
		if (err)
			return err;
		/* fall through */

	/*
	 *	Unknown or private ioctl
	 */
	default:
		if ((cmd >= SIOCDEVPRIVATE &&
		    cmd <= SIOCDEVPRIVATE + 15) ||
		    cmd == SIOCBONDENSLAVE ||
		    cmd == SIOCBONDRELEASE ||
		    cmd == SIOCBONDSETHWADDR ||
		    cmd == SIOCBONDSLAVEINFOQUERY ||
		    cmd == SIOCBONDINFOQUERY ||
		    cmd == SIOCBONDCHANGEACTIVE ||
		    cmd == SIOCGMIIPHY ||
		    cmd == SIOCGMIIREG ||
		    cmd == SIOCSMIIREG ||
		    cmd == SIOCBRADDIF ||
		    cmd == SIOCBRDELIF ||
		    cmd == SIOCSHWTSTAMP ||
		    cmd == SIOCWANDEV) {
			err = -EOPNOTSUPP;
			if (ops->ndo_do_ioctl) {
				if (netif_device_present(dev))
					err = ops->ndo_do_ioctl(dev, ifr, cmd);
				else
					err = -ENODEV;
			}
		} else
			err = -EINVAL;
Linus Torvalds's avatar
Linus Torvalds committed

	}
	return err;
}

/*
 *	This function handles all "interface"-type I/O control requests. The actual
 *	'doing' part of this is dev_ifsioc above.
 */

/**
 *	dev_ioctl	-	network device ioctl
 *	@net: the applicable net namespace
Linus Torvalds's avatar
Linus Torvalds committed
 *	@cmd: command to issue
 *	@arg: pointer to a struct ifreq in user space
 *
 *	Issue ioctl functions to devices. This is normally called by the
 *	user space syscall interfaces but can sometimes be useful for
 *	other purposes. The return value is the return from the syscall if
 *	positive or a negative errno code on error.
 */

int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct ifreq ifr;
	int ret;
	char *colon;

	/* One special case: SIOCGIFCONF takes ifconf argument
	   and requires shared lock, because it sleeps writing
	   to user space.
	 */

	if (cmd == SIOCGIFCONF) {
		rtnl_lock();
		ret = dev_ifconf(net, (char __user *) arg);
		rtnl_unlock();
Linus Torvalds's avatar
Linus Torvalds committed
		return ret;
	}
	if (cmd == SIOCGIFNAME)
		return dev_ifname(net, (struct ifreq __user *)arg);
Linus Torvalds's avatar
Linus Torvalds committed

	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
		return -EFAULT;

	ifr.ifr_name[IFNAMSIZ-1] = 0;

	colon = strchr(ifr.ifr_name, ':');
	if (colon)
		*colon = 0;

	/*
	 *	See which interface the caller is talking about.
	 */

	switch (cmd) {
	/*
	 *	These ioctl calls:
	 *	- can be done by all.
	 *	- atomic and do not require locking.
	 *	- return a value
	 */
	case SIOCGIFFLAGS:
	case SIOCGIFMETRIC:
	case SIOCGIFMTU:
	case SIOCGIFHWADDR:
	case SIOCGIFSLAVE:
	case SIOCGIFMAP:
	case SIOCGIFINDEX:
	case SIOCGIFTXQLEN:
		dev_load(net, ifr.ifr_name);
		rcu_read_lock();
		ret = dev_ifsioc_locked(net, &ifr, cmd);
		rcu_read_unlock();
		if (!ret) {
			if (colon)
				*colon = ':';
			if (copy_to_user(arg, &ifr,
					 sizeof(struct ifreq)))
				ret = -EFAULT;
		}
		return ret;
Linus Torvalds's avatar
Linus Torvalds committed

	case SIOCETHTOOL:
		dev_load(net, ifr.ifr_name);
		rtnl_lock();
		ret = dev_ethtool(net, &ifr);
		rtnl_unlock();
		if (!ret) {
			if (colon)
				*colon = ':';
			if (copy_to_user(arg, &ifr,
					 sizeof(struct ifreq)))
				ret = -EFAULT;
		}
		return ret;
Linus Torvalds's avatar
Linus Torvalds committed

	/*
	 *	These ioctl calls:
	 *	- require superuser power.
	 *	- require strict serialization.
	 *	- return a value
	 */
	case SIOCGMIIPHY:
	case SIOCGMIIREG:
	case SIOCSIFNAME:
		if (!capable(CAP_NET_ADMIN))
			return -EPERM;
		dev_load(net, ifr.ifr_name);
		rtnl_lock();
		ret = dev_ifsioc(net, &ifr, cmd);
		rtnl_unlock();
		if (!ret) {
			if (colon)
				*colon = ':';
			if (copy_to_user(arg, &ifr,
					 sizeof(struct ifreq)))
				ret = -EFAULT;
		}
		return ret;
Linus Torvalds's avatar
Linus Torvalds committed

	/*
	 *	These ioctl calls:
	 *	- require superuser power.
	 *	- require strict serialization.
	 *	- do not return a value
	 */
	case SIOCSIFFLAGS:
	case SIOCSIFMETRIC:
	case SIOCSIFMTU:
	case SIOCSIFMAP:
	case SIOCSIFHWADDR:
	case SIOCSIFSLAVE:
	case SIOCADDMULTI:
	case SIOCDELMULTI:
	case SIOCSIFHWBROADCAST:
	case SIOCSIFTXQLEN:
	case SIOCSMIIREG:
	case SIOCBONDENSLAVE:
	case SIOCBONDRELEASE:
	case SIOCBONDSETHWADDR:
	case SIOCBONDCHANGEACTIVE:
	case SIOCBRADDIF:
	case SIOCBRDELIF:
	case SIOCSHWTSTAMP:
		if (!capable(CAP_NET_ADMIN))
			return -EPERM;
		/* fall through */
	case SIOCBONDSLAVEINFOQUERY:
	case SIOCBONDINFOQUERY:
		dev_load(net, ifr.ifr_name);
		rtnl_lock();
		ret = dev_ifsioc(net, &ifr, cmd);
		rtnl_unlock();
		return ret;

	case SIOCGIFMEM:
		/* Get the per device memory space. We can add this but
		 * currently do not support it */
	case SIOCSIFMEM:
		/* Set the per device memory buffer space.
		 * Not applicable in our case */
	case SIOCSIFLINK:

	/*
	 *	Unknown or private ioctl.
	 */
	default:
		if (cmd == SIOCWANDEV ||
		    (cmd >= SIOCDEVPRIVATE &&
		     cmd <= SIOCDEVPRIVATE + 15)) {
Linus Torvalds's avatar
Linus Torvalds committed
			rtnl_lock();
			ret = dev_ifsioc(net, &ifr, cmd);
Linus Torvalds's avatar
Linus Torvalds committed
			rtnl_unlock();
			if (!ret && copy_to_user(arg, &ifr,
						 sizeof(struct ifreq)))
				ret = -EFAULT;
Linus Torvalds's avatar
Linus Torvalds committed
			return ret;
		}
		/* Take care of Wireless Extensions */
		if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)
			return wext_handle_ioctl(net, &ifr, cmd, arg);
Linus Torvalds's avatar
Linus Torvalds committed
	}
}


/**
 *	dev_new_index	-	allocate an ifindex
 *	@net: the applicable net namespace
Linus Torvalds's avatar
Linus Torvalds committed
 *
 *	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)
Linus Torvalds's avatar
Linus Torvalds committed
{
	static int ifindex;
	for (;;) {
		if (++ifindex <= 0)
			ifindex = 1;
		if (!__dev_get_by_index(net, ifindex))
Linus Torvalds's avatar
Linus Torvalds committed
			return ifindex;
	}
}

/* Delayed registration/unregisteration */
static LIST_HEAD(net_todo_list);
Linus Torvalds's avatar
Linus Torvalds committed

static void net_set_todo(struct net_device *dev)
Linus Torvalds's avatar
Linus Torvalds committed
{
	list_add_tail(&dev->todo_list, &net_todo_list);
}

static void rollback_registered_many(struct list_head *head)
	struct net_device *dev, *tmp;
	BUG_ON(dev_boot_phase);
	ASSERT_RTNL();

	list_for_each_entry_safe(dev, tmp, head, unreg_list) {
		/* Some devices call without registering
		 * for initialization unwind. Remove those
		 * devices and proceed with the remaining.
		 */
		if (dev->reg_state == NETREG_UNINITIALIZED) {
			pr_debug("unregister_netdevice: device %s/%p never "
				 "was registered\n", dev->name, dev);
			list_del(&dev->unreg_list);
			continue;
		dev->dismantle = true;
		BUG_ON(dev->reg_state != NETREG_REGISTERED);
	/* If device is running, close it first. */
	dev_close_many(head);
	list_for_each_entry(dev, head, unreg_list) {
		/* And unlink it from device chain. */
		unlist_netdevice(dev);
		dev->reg_state = NETREG_UNREGISTERING;
	}
	list_for_each_entry(dev, head, unreg_list) {
		/* Shutdown queueing discipline. */
		dev_shutdown(dev);
		/* Notify protocols, that we are about to destroy
		   this device. They should clean all the things.
		*/
		call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
		if (!dev->rtnl_link_ops ||
		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
			rtmsg_ifinfo(RTM_DELLINK, dev, ~0U);

		/*
		 *	Flush the unicast and multicast chains
		 */
		dev_mc_flush(dev);
		if (dev->netdev_ops->ndo_uninit)
			dev->netdev_ops->ndo_uninit(dev);
		/* Notifier chain MUST detach us from master device. */
		WARN_ON(dev->master);
		/* Remove entries from kobject tree */
		netdev_unregister_kobject(dev);
	}
	/* Process any work delayed until the end of the batch */
	dev = list_first_entry(head, struct net_device, unreg_list);
	call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
	list_for_each_entry(dev, head, unreg_list)
		dev_put(dev);
}

static void rollback_registered(struct net_device *dev)
{
	LIST_HEAD(single);

	list_add(&dev->unreg_list, &single);
	rollback_registered_many(&single);
	list_del(&single);
static netdev_features_t netdev_fix_features(struct net_device *dev,
	netdev_features_t features)
	/* Fix illegal checksum combinations */
	if ((features & NETIF_F_HW_CSUM) &&
	    (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
		netdev_warn(dev, "mixed HW and IP checksum settings.\n");
		features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
	}

	/* Fix illegal SG+CSUM combinations. */
	if ((features & NETIF_F_SG) &&
	    !(features & NETIF_F_ALL_CSUM)) {
		netdev_dbg(dev,
			"Dropping NETIF_F_SG since no checksum feature.\n");
		features &= ~NETIF_F_SG;
	}

	/* TSO requires that SG is present as well. */
	if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) {
		netdev_dbg(dev, "Dropping TSO features since no SG feature.\n");
		features &= ~NETIF_F_ALL_TSO;
	/* TSO ECN requires that TSO is present as well. */
	if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN)
		features &= ~NETIF_F_TSO_ECN;

	/* Software GSO depends on SG. */
	if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) {
		netdev_dbg(dev, "Dropping NETIF_F_GSO since no SG feature.\n");
		features &= ~NETIF_F_GSO;
	}

	/* UFO needs SG and checksumming */
	if (features & NETIF_F_UFO) {
		/* maybe split UFO into V4 and V6? */
		if (!((features & NETIF_F_GEN_CSUM) ||
		    (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))
			    == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
				"Dropping NETIF_F_UFO since no checksum offload features.\n");
			features &= ~NETIF_F_UFO;
		}

		if (!(features & NETIF_F_SG)) {
				"Dropping NETIF_F_UFO since no NETIF_F_SG feature.\n");
			features &= ~NETIF_F_UFO;
		}
	}

	return features;
}

int __netdev_update_features(struct net_device *dev)
	features = netdev_get_wanted_features(dev);

	if (dev->netdev_ops->ndo_fix_features)
		features = dev->netdev_ops->ndo_fix_features(dev, features);

	/* driver might be less strict about feature dependencies */
	features = netdev_fix_features(dev, features);

	if (dev->features == features)
	netdev_dbg(dev, "Features changed: %pNF -> %pNF\n",
		&dev->features, &features);

	if (dev->netdev_ops->ndo_set_features)
		err = dev->netdev_ops->ndo_set_features(dev, features);

		netdev_err(dev,
			"set_features() failed (%d); wanted %pNF, left %pNF\n",
			err, &features, &dev->features);
/**
 *	netdev_update_features - recalculate device features
 *	@dev: the device to check
 *
 *	Recalculate dev->features set and send notifications if it
 *	has changed. Should be called after driver or hardware dependent
 *	conditions might have changed that influence the features.
 */
void netdev_update_features(struct net_device *dev)
{
	if (__netdev_update_features(dev))
		netdev_features_change(dev);
}
EXPORT_SYMBOL(netdev_update_features);

/**
 *	netdev_change_features - recalculate device features
 *	@dev: the device to check
 *
 *	Recalculate dev->features set and send notifications even
 *	if they have not changed. Should be called instead of
 *	netdev_update_features() if also dev->vlan_features might
 *	have changed to allow the changes to be propagated to stacked
 *	VLAN devices.
 */
void netdev_change_features(struct net_device *dev)
{
	__netdev_update_features(dev);
	netdev_features_change(dev);
}
EXPORT_SYMBOL(netdev_change_features);

/**
 *	netif_stacked_transfer_operstate -	transfer operstate
 *	@rootdev: the root or lower level device to transfer state from
 *	@dev: the device to transfer operstate to
 *
 *	Transfer operational state from root to device. This is normally
 *	called when a stacking relationship exists between the root
 *	device and the device(a leaf device).
 */
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
					struct net_device *dev)
{
	if (rootdev->operstate == IF_OPER_DORMANT)
		netif_dormant_on(dev);
	else
		netif_dormant_off(dev);

	if (netif_carrier_ok(rootdev)) {
		if (!netif_carrier_ok(dev))
			netif_carrier_on(dev);
	} else {
		if (netif_carrier_ok(dev))
			netif_carrier_off(dev);
	}
}
EXPORT_SYMBOL(netif_stacked_transfer_operstate);

Tom Herbert's avatar
Tom Herbert committed
#ifdef CONFIG_RPS
static int netif_alloc_rx_queues(struct net_device *dev)
{
	unsigned int i, count = dev->num_rx_queues;
	struct netdev_rx_queue *rx;
	BUG_ON(count < 1);
	rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL);
	if (!rx) {
		pr_err("netdev: Unable to allocate %u rx queues.\n", count);
		return -ENOMEM;
	dev->_rx = rx;

	for (i = 0; i < count; i++)
		rx[i].dev = dev;
Tom Herbert's avatar
Tom Herbert committed
#endif
Changli Gao's avatar
Changli Gao committed
static void netdev_init_one_queue(struct net_device *dev,
				  struct netdev_queue *queue, void *_unused)
{
	/* Initialize queue lock */
	spin_lock_init(&queue->_xmit_lock);
	netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type);
	queue->xmit_lock_owner = -1;
	netdev_queue_numa_node_write(queue, NUMA_NO_NODE);
Changli Gao's avatar
Changli Gao committed
	queue->dev = dev;
Tom Herbert's avatar
Tom Herbert committed
#ifdef CONFIG_BQL
	dql_init(&queue->dql, HZ);
#endif
static int netif_alloc_netdev_queues(struct net_device *dev)
{
	unsigned int count = dev->num_tx_queues;
	struct netdev_queue *tx;

	BUG_ON(count < 1);

	tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL);
	if (!tx) {
		pr_err("netdev: Unable to allocate %u tx queues.\n",
		       count);
		return -ENOMEM;
	}
	dev->_tx = tx;
	netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
	spin_lock_init(&dev->tx_global_lock);
Changli Gao's avatar
Changli Gao committed

	return 0;
Linus Torvalds's avatar
Linus Torvalds committed
/**
 *	register_netdevice	- register a network device
 *	@dev: device to register
 *
 *	Take a completed network device structure and add it to the kernel
 *	interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier
 *	chain. 0 is returned on success. A negative errno code is returned
 *	on a failure to set up the device, or if the name is a duplicate.
 *
 *	Callers must hold the rtnl semaphore. You may want
 *	register_netdev() instead of this.
 *
 *	BUGS:
 *	The locking appears insufficient to guarantee two parallel registers
 *	will not get the same name.
 */

int register_netdevice(struct net_device *dev)
{
	int ret;
	struct net *net = dev_net(dev);
Linus Torvalds's avatar
Linus Torvalds committed

	BUG_ON(dev_boot_phase);
	ASSERT_RTNL();

Linus Torvalds's avatar
Linus Torvalds committed
	/* When net_device's are persistent, this will be fatal. */
	BUG_ON(dev->reg_state != NETREG_UNINITIALIZED);
Linus Torvalds's avatar
Linus Torvalds committed

	spin_lock_init(&dev->addr_list_lock);
	netdev_set_addr_lockdep_class(dev);
Linus Torvalds's avatar
Linus Torvalds committed

	dev->iflink = -1;

	ret = dev_get_valid_name(dev, dev->name);
	if (ret < 0)
		goto out;

Linus Torvalds's avatar
Linus Torvalds committed
	/* Init, if this function is available */
	if (dev->netdev_ops->ndo_init) {
		ret = dev->netdev_ops->ndo_init(dev);
Linus Torvalds's avatar
Linus Torvalds committed
		if (ret) {
			if (ret > 0)
				ret = -EIO;
Linus Torvalds's avatar
Linus Torvalds committed
		}
	}
	dev->ifindex = dev_new_index(net);
Linus Torvalds's avatar
Linus Torvalds committed
	if (dev->iflink == -1)
		dev->iflink = dev->ifindex;

	/* Transfer changeable features to wanted_features and enable
	 * software offloads (GSO and GRO).
	 */
	dev->hw_features |= NETIF_F_SOFT_FEATURES;
	dev->features |= NETIF_F_SOFT_FEATURES;
	dev->wanted_features = dev->features & dev->hw_features;
Linus Torvalds's avatar
Linus Torvalds committed

	/* Turn on no cache copy if HW is doing checksum */
	if (!(dev->flags & IFF_LOOPBACK)) {
		dev->hw_features |= NETIF_F_NOCACHE_COPY;
		if (dev->features & NETIF_F_ALL_CSUM) {
			dev->wanted_features |= NETIF_F_NOCACHE_COPY;
			dev->features |= NETIF_F_NOCACHE_COPY;
		}
	/* Make NETIF_F_HIGHDMA inheritable to VLAN devices.
	dev->vlan_features |= NETIF_F_HIGHDMA;
	ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
	ret = notifier_to_errno(ret);
	if (ret)
		goto err_uninit;

	ret = netdev_register_kobject(dev);
	dev->reg_state = NETREG_REGISTERED;

Linus Torvalds's avatar
Linus Torvalds committed
	/*
	 *	Default initial state at registry is that the
	 *	device is present.
	 */

	set_bit(__LINK_STATE_PRESENT, &dev->state);

	dev_init_scheduler(dev);
	dev_hold(dev);
Linus Torvalds's avatar
Linus Torvalds committed

	/* Notify protocols, that a new device appeared. */
	ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
	ret = notifier_to_errno(ret);
	if (ret) {
		rollback_registered(dev);
		dev->reg_state = NETREG_UNREGISTERED;
	}
	/*
	 *	Prevent userspace races by waiting until the network
	 *	device is fully setup before sending notifications.
	 */
	if (!dev->rtnl_link_ops ||
	    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
		rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
Linus Torvalds's avatar
Linus Torvalds committed

out:
	return ret;
	if (dev->netdev_ops->ndo_uninit)
		dev->netdev_ops->ndo_uninit(dev);
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(register_netdevice);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	init_dummy_netdev	- init a dummy network device for NAPI
 *	@dev: device to init
 *
 *	This takes a network device structure and initialize the minimum
 *	amount of fields so it can be used to schedule NAPI polls without
 *	registering a full blown interface. This is to be used by drivers
 *	that need to tie several hardware interfaces to a single NAPI
 *	poll scheduler due to HW limitations.
 */
int init_dummy_netdev(struct net_device *dev)
{
	/* Clear everything. Note we don't initialize spinlocks
	 * are they aren't supposed to be taken by any of the
	 * NAPI code and this dummy netdev is supposed to be
	 * only ever used for NAPI polls
	 */
	memset(dev, 0, sizeof(struct net_device));

	/* make sure we BUG if trying to hit standard
	 * register/unregister code path
	 */
	dev->reg_state = NETREG_DUMMY;

	/* NAPI wants this */
	INIT_LIST_HEAD(&dev->napi_list);

	/* a dummy interface is started by default */
	set_bit(__LINK_STATE_PRESENT, &dev->state);
	set_bit(__LINK_STATE_START, &dev->state);

	/* Note : We dont allocate pcpu_refcnt for dummy devices,
	 * because users of this 'device' dont need to change
	 * its refcount.
	 */

Linus Torvalds's avatar
Linus Torvalds committed
/**
 *	register_netdev	- register a network device
 *	@dev: device to register
 *
 *	Take a completed network device structure and add it to the kernel
 *	interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier
 *	chain. 0 is returned on success. A negative errno code is returned
 *	on a failure to set up the device, or if the name is a duplicate.
 *
 *	This is a wrapper around register_netdevice that takes the rtnl semaphore
Linus Torvalds's avatar
Linus Torvalds committed
 *	and expands the device name if you passed a format string to
 *	alloc_netdev.
 */
int register_netdev(struct net_device *dev)
{
	int err;

	rtnl_lock();
	err = register_netdevice(dev);
	rtnl_unlock();
	return err;
}
EXPORT_SYMBOL(register_netdev);

int netdev_refcnt_read(const struct net_device *dev)
{
	int i, refcnt = 0;

	for_each_possible_cpu(i)
		refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i);
	return refcnt;
}
EXPORT_SYMBOL(netdev_refcnt_read);

Linus Torvalds's avatar
Linus Torvalds committed
/*
 * netdev_wait_allrefs - wait until all references are gone.
 *
 * This is called when unregistering network devices.
 *
 * Any protocol or device that holds a reference should register
 * for netdevice notification, and cleanup and put back the
 * reference if they receive an UNREGISTER event.
 * We can get stuck here if buggy protocols don't correctly
 * call dev_put.
Linus Torvalds's avatar
Linus Torvalds committed
 */
static void netdev_wait_allrefs(struct net_device *dev)
{
	unsigned long rebroadcast_time, warning_time;
	int refcnt;
Linus Torvalds's avatar
Linus Torvalds committed

Linus Torvalds's avatar
Linus Torvalds committed
	rebroadcast_time = warning_time = jiffies;
	refcnt = netdev_refcnt_read(dev);

	while (refcnt != 0) {
Linus Torvalds's avatar
Linus Torvalds committed
		if (time_after(jiffies, rebroadcast_time + 1 * HZ)) {
			rtnl_lock();
Linus Torvalds's avatar
Linus Torvalds committed

			/* Rebroadcast unregister notification */
			call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
			/* don't resend NETDEV_UNREGISTER_BATCH, _BATCH users
			 * should have already handle it the first time */
Linus Torvalds's avatar
Linus Torvalds committed

			if (test_bit(__LINK_STATE_LINKWATCH_PENDING,
				     &dev->state)) {
				/* We must not have linkwatch events
				 * pending on unregister. If this
				 * happens, we simply run the queue
				 * unscheduled, resulting in a noop
				 * for this device.
				 */
				linkwatch_run_queue();
			}

			__rtnl_unlock();
Linus Torvalds's avatar
Linus Torvalds committed

			rebroadcast_time = jiffies;
		}

		msleep(250);

		refcnt = netdev_refcnt_read(dev);

Linus Torvalds's avatar
Linus Torvalds committed
		if (time_after(jiffies, warning_time + 10 * HZ)) {
			printk(KERN_EMERG "unregister_netdevice: "
			       "waiting for %s to become free. Usage "
			       "count = %d\n",
			       dev->name, refcnt);
Linus Torvalds's avatar
Linus Torvalds committed
			warning_time = jiffies;
		}
	}
}

/* The sequence is:
 *
 *	rtnl_lock();
 *	...
 *	register_netdevice(x1);
 *	register_netdevice(x2);
 *	...
 *	unregister_netdevice(y1);
 *	unregister_netdevice(y2);
 *      ...
 *	rtnl_unlock();
 *	free_netdev(y1);
 *	free_netdev(y2);
 *
 * We are invoked by rtnl_unlock().
Linus Torvalds's avatar
Linus Torvalds committed
 * This allows us to deal with problems:
 * 1) We can delete sysfs objects which invoke hotplug
Linus Torvalds's avatar
Linus Torvalds committed
 *    without deadlocking with linkwatch via keventd.
 * 2) Since we run with the RTNL semaphore not held, we can sleep
 *    safely in order to wait for the netdev refcnt to drop to zero.
 *
 * We must not return until all unregister events added during
 * the interval the lock was held have been completed.
Linus Torvalds's avatar
Linus Torvalds committed
 */
void netdev_run_todo(void)
{
Linus Torvalds's avatar
Linus Torvalds committed

	/* Snapshot list, allow later requests */
	list_replace_init(&net_todo_list, &list);

	__rtnl_unlock();
	/* Wait for rcu callbacks to finish before attempting to drain
	 * the device list.  This usually avoids a 250ms wait.
	 */
	if (!list_empty(&list))
		rcu_barrier();

Linus Torvalds's avatar
Linus Torvalds committed
	while (!list_empty(&list)) {
		struct net_device *dev
			= list_first_entry(&list, struct net_device, todo_list);
Linus Torvalds's avatar
Linus Torvalds committed
		list_del(&dev->todo_list);

		if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) {
			printk(KERN_ERR "network todo '%s' but state %d\n",
			       dev->name, dev->reg_state);
			dump_stack();
			continue;
		}
Linus Torvalds's avatar
Linus Torvalds committed

		dev->reg_state = NETREG_UNREGISTERED;
Linus Torvalds's avatar
Linus Torvalds committed

		on_each_cpu(flush_backlog, dev, 1);
Linus Torvalds's avatar
Linus Torvalds committed

		BUG_ON(netdev_refcnt_read(dev));
		WARN_ON(rcu_access_pointer(dev->ip_ptr));
		WARN_ON(rcu_access_pointer(dev->ip6_ptr));
		WARN_ON(dev->dn_ptr);
Linus Torvalds's avatar
Linus Torvalds committed

		if (dev->destructor)
			dev->destructor(dev);

		/* Free network device */
		kobject_put(&dev->dev.kobj);
/* Convert net_device_stats to rtnl_link_stats64.  They have the same
 * fields in the same order, with only the type differing.
 */
static void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
				    const struct net_device_stats *netdev_stats)
{
#if BITS_PER_LONG == 64
        BUILD_BUG_ON(sizeof(*stats64) != sizeof(*netdev_stats));
        memcpy(stats64, netdev_stats, sizeof(*stats64));
#else
	size_t i, n = sizeof(*stats64) / sizeof(u64);
	const unsigned long *src = (const unsigned long *)netdev_stats;
	u64 *dst = (u64 *)stats64;

	BUILD_BUG_ON(sizeof(*netdev_stats) / sizeof(unsigned long) !=
		     sizeof(*stats64) / sizeof(u64));
	for (i = 0; i < n; i++)
		dst[i] = src[i];
#endif
}

/**
 *	dev_get_stats	- get network device statistics
 *	@dev: device to get statistics from
 *	@storage: place to store stats
 *	Get network statistics from device. Return @storage.
 *	The device driver may provide its own method by setting
 *	dev->netdev_ops->get_stats64 or dev->netdev_ops->get_stats;
 *	otherwise the internal statistics structure is used.
struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
					struct rtnl_link_stats64 *storage)
	const struct net_device_ops *ops = dev->netdev_ops;

	if (ops->ndo_get_stats64) {
		memset(storage, 0, sizeof(*storage));
		ops->ndo_get_stats64(dev, storage);
	} else if (ops->ndo_get_stats) {
		netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev));
	} else {
		netdev_stats_to_stats64(storage, &dev->stats);
	storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
	return storage;
EXPORT_SYMBOL(dev_get_stats);
struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
	struct netdev_queue *queue = dev_ingress_queue(dev);
#ifdef CONFIG_NET_CLS_ACT
	if (queue)
		return queue;
	queue = kzalloc(sizeof(*queue), GFP_KERNEL);
	if (!queue)
		return NULL;
	netdev_init_one_queue(dev, queue, NULL);
	queue->qdisc = &noop_qdisc;
	queue->qdisc_sleeping = &noop_qdisc;
	rcu_assign_pointer(dev->ingress_queue, queue);
#endif
	return queue;
Linus Torvalds's avatar
Linus Torvalds committed
/**
 *	alloc_netdev_mqs - allocate network device
Linus Torvalds's avatar
Linus Torvalds committed
 *	@sizeof_priv:	size of private data to allocate space for
 *	@name:		device name format string
 *	@setup:		callback to initialize device
 *	@txqs:		the number of TX subqueues to allocate
 *	@rxqs:		the number of RX subqueues to allocate
Linus Torvalds's avatar
Linus Torvalds committed
 *
 *	Allocates a struct net_device with private data area for driver use
 *	and performs basic initialization.  Also allocates subquue structs
 *	for each queue on the device.
Linus Torvalds's avatar
Linus Torvalds committed
 */
struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
		void (*setup)(struct net_device *),
		unsigned int txqs, unsigned int rxqs)
Linus Torvalds's avatar
Linus Torvalds committed
{
	struct net_device *dev;
	size_t alloc_size;
Linus Torvalds's avatar
Linus Torvalds committed

	BUG_ON(strlen(name) >= sizeof(dev->name));

	if (txqs < 1) {
		pr_err("alloc_netdev: Unable to allocate device "
		       "with zero queues.\n");
		return NULL;
	}

#ifdef CONFIG_RPS
	if (rxqs < 1) {
		pr_err("alloc_netdev: Unable to allocate device "
		       "with zero RX queues.\n");
		return NULL;
	}
#endif

	alloc_size = sizeof(struct net_device);
	if (sizeof_priv) {
		/* ensure 32-byte alignment of private area */
		alloc_size = ALIGN(alloc_size, NETDEV_ALIGN);
		alloc_size += sizeof_priv;
	}
	/* ensure 32-byte alignment of whole construct */
	alloc_size += NETDEV_ALIGN - 1;
Linus Torvalds's avatar
Linus Torvalds committed

	p = kzalloc(alloc_size, GFP_KERNEL);
Linus Torvalds's avatar
Linus Torvalds committed
	if (!p) {
		printk(KERN_ERR "alloc_netdev: Unable to allocate device.\n");
Linus Torvalds's avatar
Linus Torvalds committed
		return NULL;
	}

	dev = PTR_ALIGN(p, NETDEV_ALIGN);
Linus Torvalds's avatar
Linus Torvalds committed
	dev->padded = (char *)dev - (char *)p;
	dev->pcpu_refcnt = alloc_percpu(int);
	if (!dev->pcpu_refcnt)

	if (dev_addr_init(dev))
		goto free_pcpu;
	dev_mc_init(dev);
Linus Torvalds's avatar
Linus Torvalds committed

	dev->gso_max_size = GSO_MAX_SIZE;

	INIT_LIST_HEAD(&dev->napi_list);
	INIT_LIST_HEAD(&dev->unreg_list);
	INIT_LIST_HEAD(&dev->link_watch_list);
	dev->priv_flags = IFF_XMIT_DST_RELEASE;
	setup(dev);

	dev->num_tx_queues = txqs;
	dev->real_num_tx_queues = txqs;
	if (netif_alloc_netdev_queues(dev))
Eric Dumazet's avatar
Eric Dumazet committed
#ifdef CONFIG_RPS
	dev->num_rx_queues = rxqs;
	dev->real_num_rx_queues = rxqs;
	if (netif_alloc_rx_queues(dev))
Eric Dumazet's avatar
Eric Dumazet committed
#endif
Linus Torvalds's avatar
Linus Torvalds committed
	strcpy(dev->name, name);
	dev->group = INIT_NETDEV_GROUP;
Linus Torvalds's avatar
Linus Torvalds committed
	return dev;
free_pcpu:
	free_percpu(dev->pcpu_refcnt);
#ifdef CONFIG_RPS
	kfree(dev->_rx);
#endif

free_p:
	kfree(p);
	return NULL;
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(alloc_netdev_mqs);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	free_netdev - free network device
 *	@dev: device
 *
 *	This function does the last stage of destroying an allocated device
 * 	interface. The reference to the device object is released.
Linus Torvalds's avatar
Linus Torvalds committed
 *	If this is the last reference then it will be freed.
 */
void free_netdev(struct net_device *dev)
{
	struct napi_struct *p, *n;

	kfree(dev->_tx);
#ifdef CONFIG_RPS
	kfree(dev->_rx);
#endif
	kfree(rcu_dereference_protected(dev->ingress_queue, 1));
	/* Flush device addresses */
	dev_addr_flush(dev);

	list_for_each_entry_safe(p, n, &dev->napi_list, dev_list)
		netif_napi_del(p);

	free_percpu(dev->pcpu_refcnt);
	dev->pcpu_refcnt = NULL;

	/*  Compatibility with error handling in drivers */
Linus Torvalds's avatar
Linus Torvalds committed
	if (dev->reg_state == NETREG_UNINITIALIZED) {
		kfree((char *)dev - dev->padded);
		return;
	}

	BUG_ON(dev->reg_state != NETREG_UNREGISTERED);
	dev->reg_state = NETREG_RELEASED;

	/* will free via device release */
	put_device(&dev->dev);
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(free_netdev);
/**
 *	synchronize_net -  Synchronize with packet receive processing
 *
 *	Wait for packets currently being received to be done.
 *	Does not block later packets from starting.
 */
void synchronize_net(void)
Linus Torvalds's avatar
Linus Torvalds committed
{
	might_sleep();
	if (rtnl_is_locked())
		synchronize_rcu_expedited();
	else
		synchronize_rcu();
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(synchronize_net);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	unregister_netdevice_queue - remove device from the kernel
Linus Torvalds's avatar
Linus Torvalds committed
 *	@dev: device
Linus Torvalds's avatar
Linus Torvalds committed
 *	This function shuts down a device interface and removes it
 *	from the kernel tables.
 *	If head not NULL, device is queued to be unregistered later.
Linus Torvalds's avatar
Linus Torvalds committed
 *
 *	Callers must hold the rtnl semaphore.  You may want
 *	unregister_netdev() instead of this.
 */

void unregister_netdevice_queue(struct net_device *dev, struct list_head *head)
Linus Torvalds's avatar
Linus Torvalds committed
{
		list_move_tail(&dev->unreg_list, head);
	} else {
		rollback_registered(dev);
		/* Finish processing unregister after unlock */
		net_set_todo(dev);
	}
Linus Torvalds's avatar
Linus Torvalds committed
}
EXPORT_SYMBOL(unregister_netdevice_queue);
Linus Torvalds's avatar
Linus Torvalds committed

/**
 *	unregister_netdevice_many - unregister many devices
 *	@head: list of devices
 */
void unregister_netdevice_many(struct list_head *head)
{
	struct net_device *dev;

	if (!list_empty(head)) {
		rollback_registered_many(head);
		list_for_each_entry(dev, head, unreg_list)
			net_set_todo(dev);
	}
}
EXPORT_SYMBOL(unregister_netdevice_many);
Linus Torvalds's avatar
Linus Torvalds committed
/**
 *	unregister_netdev - remove device from the kernel
 *	@dev: device
 *
 *	This function shuts down a device interface and removes it
 *	from the kernel tables.
Linus Torvalds's avatar
Linus Torvalds committed
 *
 *	This is just a wrapper for unregister_netdevice that takes
 *	the rtnl semaphore.  In general you want to use this and not
 *	unregister_netdevice.
 */
void unregister_netdev(struct net_device *dev)
{
	rtnl_lock();
	unregister_netdevice(dev);
	rtnl_unlock();
}
EXPORT_SYMBOL(unregister_netdev);

/**
 *	dev_change_net_namespace - move device to different nethost namespace
 *	@dev: device
 *	@net: network namespace
 *	@pat: If not NULL name pattern to try if the current device name
 *	      is already taken in the destination network namespace.
 *
 *	This function shuts down a device interface and moves it
 *	to a new network namespace. On success 0 is returned, on
 *	a failure a netagive errno code is returned.
 *
 *	Callers must hold the rtnl semaphore.
 */

int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat)
{
	int err;

	ASSERT_RTNL();

	/* Don't allow namespace local devices to be moved. */
	err = -EINVAL;
	if (dev->features & NETIF_F_NETNS_LOCAL)
		goto out;

	/* 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;
		goto out;

	/* Pick the destination device name, and ensure
	 * we can use it in the destination network namespace.
	 */
	err = -EEXIST;
	if (__dev_get_by_name(net, dev->name)) {
		/* We get here if we can't use the current device name */
		if (!pat)
			goto out;
		if (dev_get_valid_name(dev, pat) < 0)
			goto out;
	}

	/*
	 * And now a mini version of register_netdevice unregister_netdevice.
	 */

	/* If device is running close it first. */

	/* 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.

	   Note that dev->reg_state stays at NETREG_REGISTERED.
	   This is wanted because this way 8021q and macvlan know
	   the device is just moving and can keep their slaves up.
	*/
	call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
	call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);

	/*
	 *	Flush the unicast and multicast chains
	 */
	dev_mc_flush(dev);

	/* Actually switch the network namespace */

	/* 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;
	}

	/* Fixup kobjects */
	err = device_rename(&dev->dev, dev->name);
	WARN_ON(err);

	/* Add the device back in the hashes */
	list_netdevice(dev);

	/* Notify protocols, that a new device appeared. */
	call_netdevice_notifiers(NETDEV_REGISTER, dev);

	/*
	 *	Prevent userspace races by waiting until the network
	 *	device is fully setup before sending notifications.
	 */
	rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);

EXPORT_SYMBOL_GPL(dev_change_net_namespace);
Linus Torvalds's avatar
Linus Torvalds committed
static int dev_cpu_callback(struct notifier_block *nfb,
			    unsigned long action,
			    void *ocpu)
{
	struct sk_buff **list_skb;
	struct sk_buff *skb;
	unsigned int cpu, oldcpu = (unsigned long)ocpu;
	struct softnet_data *sd, *oldsd;

	if (action != CPU_DEAD && action != CPU_DEAD_FROZEN)
Linus Torvalds's avatar
Linus Torvalds committed
		return NOTIFY_OK;

	local_irq_disable();
	cpu = smp_processor_id();
	sd = &per_cpu(softnet_data, cpu);
	oldsd = &per_cpu(softnet_data, oldcpu);

	/* Find end of our completion_queue. */
	list_skb = &sd->completion_queue;
	while (*list_skb)
		list_skb = &(*list_skb)->next;
	/* Append completion queue from offline CPU. */
	*list_skb = oldsd->completion_queue;
	oldsd->completion_queue = NULL;

	/* Append output queue from offline CPU. */
	if (oldsd->output_queue) {
		*sd->output_queue_tailp = oldsd->output_queue;
		sd->output_queue_tailp = oldsd->output_queue_tailp;
		oldsd->output_queue = NULL;
		oldsd->output_queue_tailp = &oldsd->output_queue;
	}
	/* Append NAPI poll list from offline CPU. */
	if (!list_empty(&oldsd->poll_list)) {
		list_splice_init(&oldsd->poll_list, &sd->poll_list);
		raise_softirq_irqoff(NET_RX_SOFTIRQ);
	}
Linus Torvalds's avatar
Linus Torvalds committed

	raise_softirq_irqoff(NET_TX_SOFTIRQ);
	local_irq_enable();

	/* Process offline CPU's input_pkt_queue */
	while ((skb = __skb_dequeue(&oldsd->process_queue))) {
Linus Torvalds's avatar
Linus Torvalds committed
		netif_rx(skb);
		input_queue_head_incr(oldsd);
	while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
		input_queue_head_incr(oldsd);
	}
Linus Torvalds's avatar
Linus Torvalds committed

	return NOTIFY_OK;
}


 *	netdev_increment_features - increment feature set by one
 *	@all: current feature set
 *	@one: new feature set
 *	@mask: mask feature set
 *
 *	Computes a new feature set after adding a device with feature set
 *	@one to the master device with current feature set @all.  Will not
 *	enable anything that is off in @mask. Returns the new feature set.
netdev_features_t netdev_increment_features(netdev_features_t all,
	netdev_features_t one, netdev_features_t mask)
	if (mask & NETIF_F_GEN_CSUM)
		mask |= NETIF_F_ALL_CSUM;
	mask |= NETIF_F_VLAN_CHALLENGED;
	all |= one & (NETIF_F_ONE_FOR_ALL|NETIF_F_ALL_CSUM) & mask;
	all &= one | ~NETIF_F_ALL_FOR_ALL;
	/* If one device supports hw checksumming, set for all. */
	if (all & NETIF_F_GEN_CSUM)
		all &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM);
EXPORT_SYMBOL(netdev_increment_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)
	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;

err_idx:
	kfree(net->dev_name_head);
err_name:
	return -ENOMEM;
/**
 *	netdev_drivername - network driver for the device
 *	@dev: network device
 *
 *	Determine network driver for device.
 */
const char *netdev_drivername(const struct net_device *dev)
	const struct device_driver *driver;
	const struct device *parent;
	const char *empty = "";

	parent = dev->dev.parent;
	if (!parent)

	driver = parent->driver;
	if (driver && driver->name)
		return driver->name;
	return empty;
int __netdev_printk(const char *level, const struct net_device *dev,
			   struct va_format *vaf)
{
	int r;

	if (dev && dev->dev.parent)
		r = dev_printk(level, dev->dev.parent, "%s: %pV",
			       netdev_name(dev), vaf);
	else if (dev)
		r = printk("%s%s: %pV", level, netdev_name(dev), vaf);
	else
		r = printk("%s(NULL net_device): %pV", level, vaf);

	return r;
}
EXPORT_SYMBOL(__netdev_printk);

int netdev_printk(const char *level, const struct net_device *dev,
		  const char *format, ...)
{
	struct va_format vaf;
	va_list args;
	int r;

	va_start(args, format);

	vaf.fmt = format;
	vaf.va = &args;

	r = __netdev_printk(level, dev, &vaf);
	va_end(args);

	return r;
}
EXPORT_SYMBOL(netdev_printk);

#define define_netdev_printk_level(func, level)			\
int func(const struct net_device *dev, const char *fmt, ...)	\
{								\
	int r;							\
	struct va_format vaf;					\
	va_list args;						\
								\
	va_start(args, fmt);					\
								\
	vaf.fmt = fmt;						\
	vaf.va = &args;						\
								\
	r = __netdev_printk(level, dev, &vaf);			\
	va_end(args);						\
								\
	return r;						\
}								\
EXPORT_SYMBOL(func);

define_netdev_printk_level(netdev_emerg, KERN_EMERG);
define_netdev_printk_level(netdev_alert, KERN_ALERT);
define_netdev_printk_level(netdev_crit, KERN_CRIT);
define_netdev_printk_level(netdev_err, KERN_ERR);
define_netdev_printk_level(netdev_warn, KERN_WARNING);
define_netdev_printk_level(netdev_notice, KERN_NOTICE);
define_netdev_printk_level(netdev_info, KERN_INFO);

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 = {
static void __net_exit default_device_exit(struct net *net)
	struct net_device *dev, *aux;
	 * Push all migratable network devices back to the
	 * initial network namespace
	 */
	rtnl_lock();
	for_each_netdev_safe(net, dev, aux) {

		/* Ignore unmoveable devices (i.e. loopback) */
		if (dev->features & NETIF_F_NETNS_LOCAL)
			continue;

		/* Leave virtual devices for the generic cleanup */
		if (dev->rtnl_link_ops)
			continue;
Lucas De Marchi's avatar
Lucas De Marchi committed
		/* Push remaining network devices to init_net */
		snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
		err = dev_change_net_namespace(dev, &init_net, fb_name);
			printk(KERN_EMERG "%s: failed to move %s to init_net: %d\n",
static void __net_exit default_device_exit_batch(struct list_head *net_list)
{
	/* At exit all network devices most be removed from a network
	 * namespace.  Do this in the reverse order of registration.
	 * Do this across as many network namespaces as possible to
	 * improve batching efficiency.
	 */
	struct net_device *dev;
	struct net *net;
	LIST_HEAD(dev_kill_list);

	rtnl_lock();
	list_for_each_entry(net, net_list, exit_list) {
		for_each_netdev_reverse(net, dev) {
			if (dev->rtnl_link_ops)
				dev->rtnl_link_ops->dellink(dev, &dev_kill_list);
			else
				unregister_netdevice_queue(dev, &dev_kill_list);
		}
	}
	unregister_netdevice_many(&dev_kill_list);
	list_del(&dev_kill_list);
static struct pernet_operations __net_initdata default_device_ops = {
	.exit_batch = default_device_exit_batch,
Linus Torvalds's avatar
Linus Torvalds committed
/*
 *	Initialize the DEV module. At boot time this walks the device list and
 *	unhooks any devices that fail to initialise (normally hardware not
 *	present) and leaves us with a valid list of present and active devices.
 *
 */

/*
 *       This is called single threaded during boot, so no need
 *       to take the rtnl semaphore.
 */
static int __init net_dev_init(void)
{
	int i, rc = -ENOMEM;

	BUG_ON(!dev_boot_phase);

	if (dev_proc_init())
		goto out;

	if (netdev_kobject_init())
Linus Torvalds's avatar
Linus Torvalds committed
		goto out;

	INIT_LIST_HEAD(&ptype_all);
	for (i = 0; i < PTYPE_HASH_SIZE; i++)
Linus Torvalds's avatar
Linus Torvalds committed
		INIT_LIST_HEAD(&ptype_base[i]);

	if (register_pernet_subsys(&netdev_net_ops))
		goto out;
Linus Torvalds's avatar
Linus Torvalds committed

	/*
	 *	Initialise the packet receive queues.
	 */

	for_each_possible_cpu(i) {
Eric Dumazet's avatar
Eric Dumazet committed
		struct softnet_data *sd = &per_cpu(softnet_data, i);
Linus Torvalds's avatar
Linus Torvalds committed

Changli Gao's avatar
Changli Gao committed
		memset(sd, 0, sizeof(*sd));
Eric Dumazet's avatar
Eric Dumazet committed
		skb_queue_head_init(&sd->input_pkt_queue);
		skb_queue_head_init(&sd->process_queue);
Eric Dumazet's avatar
Eric Dumazet committed
		sd->completion_queue = NULL;
		INIT_LIST_HEAD(&sd->poll_list);
		sd->output_queue = NULL;
		sd->output_queue_tailp = &sd->output_queue;
Eric Dumazet's avatar
Eric Dumazet committed
#ifdef CONFIG_RPS
Eric Dumazet's avatar
Eric Dumazet committed
		sd->csd.func = rps_trigger_softirq;
		sd->csd.info = sd;
		sd->csd.flags = 0;
		sd->cpu = i;
Eric Dumazet's avatar
Eric Dumazet committed
		sd->backlog.poll = process_backlog;
		sd->backlog.weight = weight_p;
		sd->backlog.gro_list = NULL;
		sd->backlog.gro_count = 0;
Linus Torvalds's avatar
Linus Torvalds committed
	}

	dev_boot_phase = 0;

	/* The loopback device is special if any other network devices
	 * is present in a network namespace the loopback device must
	 * be present. Since we now dynamically allocate and free the
	 * loopback device ensure this invariant is maintained by
	 * keeping the loopback device as the first device on the
	 * list of network devices.  Ensuring the loopback devices
	 * is the first device that appears and the last network device
	 * that disappears.
	 */
	if (register_pernet_device(&loopback_net_ops))
		goto out;

	if (register_pernet_device(&default_device_ops))
		goto out;

	open_softirq(NET_TX_SOFTIRQ, net_tx_action);
	open_softirq(NET_RX_SOFTIRQ, net_rx_action);
Linus Torvalds's avatar
Linus Torvalds committed

	hotcpu_notifier(dev_cpu_callback, 0);
	dst_init();
	dev_mcast_init();
	rc = 0;
out:
	return rc;
}

subsys_initcall(net_dev_init);

static int __init initialize_hashrnd(void)
{
	get_random_bytes(&hashrnd, sizeof(hashrnd));
	return 0;
}

late_initcall_sync(initialize_hashrnd);