dev.c

linux 内核源代码

/*
 * 	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
 *				Fred N. van Kempen, <[e-mail]>
 *				Mark Evans, <[e-mail]>
 *
 *	Additional Authors:
 *		Florian la Roche <[e-mail]>
 *		Alan Cox <[e-mail]>
 *		David Hinds <[e-mail]>
 *		Alexey Kuznetsov <[e-mail]>
 *		Adam Sulmicki <[e-mail]>
 *              Pekka Riikonen <[e-mail]>
 *
 *	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>
#include <linux/cpu.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mutex.h>
#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/notifier.h>
#include <linux/skbuff.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/stat.h>
#include <linux/if_bridge.h>
#include <linux/if_macvlan.h>
#include <net/dst.h>
#include <net/pkt_sched.h>
#include <net/checksum.h>
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/netpoll.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
#include <net/wext.h>
#include <net/iw_handler.h>
#include <asm/current.h>
#include <linux/audit.h>
#include <linux/dmaengine.h>
#include <linux/err.h>
#include <linux/ctype.h>
#include <linux/if_arp.h>

#include "net-sysfs.h"

/*
 *	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.
 *             --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
 */

static DEFINE_SPINLOCK(ptype_lock);
static struct list_head ptype_base[16] __read_mostly;	/* 16 way hashed list */
static struct list_head ptype_all __read_mostly;	/* Taps */

#ifdef CONFIG_NET_DMA
struct net_dma {
	struct dma_client client;
	spinlock_t lock;
	cpumask_t channel_mask;
	struct dma_chan *channels[NR_CPUS];
};

static enum dma_state_client
netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
	enum dma_state state);

static struct net_dma net_dma = {
	.client = {
		.event_callback = netdev_dma_event,
	},
};
#endif

/*
 * The @dev_base_head list is protected by @dev_base_lock and the rtnl
 * semaphore.
 *
 * Pure readers hold dev_base_lock for reading.
 *
 * Writers must hold the rtnl semaphore while they loop through the
 * dev_base_head list, and hold dev_base_lock for writing when they do the
 * actual updates.  This allows pure readers to access the list even
 * while a writer is preparing to update it.
 *
 * 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.
 */
DEFINE_RWLOCK(dev_base_lock);

EXPORT_SYMBOL(dev_base_lock);

#define NETDEV_HASHBITS	8
#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS)

static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
{
	unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
	return &net->dev_name_head[hash & ((1 << NETDEV_HASHBITS) - 1)];
}

static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex)
{
	return &net->dev_index_head[ifindex & ((1 << NETDEV_HASHBITS) - 1)];
}

/* Device list insertion */
static int list_netdevice(struct net_device *dev)
{
	struct net *net = dev->nd_net;

	ASSERT_RTNL();

	write_lock_bh(&dev_base_lock);
	list_add_tail(&dev->dev_list, &net->dev_base_head);
	hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name));
	hlist_add_head(&dev->index_hlist, dev_index_hash(net, dev->ifindex));
	write_unlock_bh(&dev_base_lock);
	return 0;
}

/* Device list removal */
static void unlist_netdevice(struct net_device *dev)
{
	ASSERT_RTNL();

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

/*
 *	Our notifier list
 */

static RAW_NOTIFIER_HEAD(netdev_chain);

/*
 *	Device drivers call our routines to queue packets here. We empty the
 *	queue in the local softnet handler.
 */

DEFINE_PER_CPU(struct softnet_data, softnet_data);

#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
 * register_netdevice() inits dev->_xmit_lock and sets lockdep class
 * according to dev->type
 */
static const unsigned short netdev_lock_type[] =
	{ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25,
	 ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET,
	 ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM,
	 ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP,
	 ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD,
	 ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25,
	 ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP,
	 ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD,
	 ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI,
	 ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE,
	 ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
	 ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
	 ARPHRD_FCFABRIC, ARPHRD_IEEE802_TR, ARPHRD_IEEE80211,
	 ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_VOID,
	 ARPHRD_NONE};

static const char *netdev_lock_name[] =
	{"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
	 "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
	 "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
	 "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP",
	 "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD",
	 "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25",
	 "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP",
	 "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",
	 "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI",
	 "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
	 "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
	 "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
	 "_xmit_FCFABRIC", "_xmit_IEEE802_TR", "_xmit_IEEE80211",
	 "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_VOID",
	 "_xmit_NONE"};

static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];

static 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_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]);
}
#else
static inline void netdev_set_lockdep_class(spinlock_t *lock,
					    unsigned short dev_type)
{
}
#endif

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

		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)
 */

/**
 *	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
 *	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)
{
	int hash;

	spin_lock_bh(&ptype_lock);
	if (pt->type == htons(ETH_P_ALL))
		list_add_rcu(&pt->list, &ptype_all);
	else {
		hash = ntohs(pt->type) & 15;
		list_add_rcu(&pt->list, &ptype_base[hash]);
	}
	spin_unlock_bh(&ptype_lock);
}

/**
 *	__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.
 *
 *      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;
	struct packet_type *pt1;

	spin_lock_bh(&ptype_lock);

	if (pt->type == htons(ETH_P_ALL))
		head = &ptype_all;
	else
		head = &ptype_base[ntohs(pt->type) & 15];

	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_bh(&ptype_lock);
}
/**
 *	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);

	synchronize_net();
}

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

		      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));
			strcpy(s[i].name, name);
			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] != ' ' &&
		    !strncmp(dev->name, s[i].name, strlen(s[i].name))) {
			dev->irq 	= s[i].map.irq;
			dev->base_addr 	= s[i].map.base_addr;
			dev->mem_start 	= s[i].map.mem_start;
			dev->mem_end 	= s[i].map.mem_end;
			return 1;
		}
	}
	return 0;
}


/**
 *	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))
		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.