netdevice.h 64.8 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Definitions for the Interfaces handler.
 *
 * Version:	@(#)dev.h	1.0.10	08/12/93
 *
10
 * Authors:	Ross Biro
L
Linus Torvalds 已提交
11 12 13
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Corey Minyard <wf-rch!minyard@relay.EU.net>
 *		Donald J. Becker, <becker@cesdis.gsfc.nasa.gov>
14
 *		Alan Cox, <alan@lxorguk.ukuu.org.uk>
L
Linus Torvalds 已提交
15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32
 *		Bjorn Ekwall. <bj0rn@blox.se>
 *              Pekka Riikonen <priikone@poseidon.pspt.fi>
 *
 *		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.
 *
 *		Moved to /usr/include/linux for NET3
 */
#ifndef _LINUX_NETDEVICE_H
#define _LINUX_NETDEVICE_H

#include <linux/if.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>

#ifdef __KERNEL__
A
Al Viro 已提交
33
#include <linux/timer.h>
34
#include <linux/delay.h>
35
#include <linux/mm.h>
L
Linus Torvalds 已提交
36 37 38 39 40 41
#include <asm/atomic.h>
#include <asm/cache.h>
#include <asm/byteorder.h>

#include <linux/device.h>
#include <linux/percpu.h>
42
#include <linux/rculist.h>
43
#include <linux/dmaengine.h>
44
#include <linux/workqueue.h>
L
Linus Torvalds 已提交
45

46
#include <linux/ethtool.h>
47
#include <net/net_namespace.h>
48
#include <net/dsa.h>
J
Jeff Kirsher 已提交
49
#ifdef CONFIG_DCB
50 51
#include <net/dcbnl.h>
#endif
52

L
Linus Torvalds 已提交
53
struct vlan_group;
54
struct netpoll_info;
55 56
/* 802.11 specific */
struct wireless_dev;
L
Linus Torvalds 已提交
57 58 59 60 61 62 63 64 65
					/* source back-compat hooks */
#define SET_ETHTOOL_OPS(netdev,ops) \
	( (netdev)->ethtool_ops = (ops) )

#define HAVE_ALLOC_NETDEV		/* feature macro: alloc_xxxdev
					   functions are available. */
#define HAVE_FREE_NETDEV		/* free_netdev() */
#define HAVE_NETDEV_PRIV		/* netdev_priv() */

66 67 68 69
/* Backlog congestion levels */
#define NET_RX_SUCCESS		0	/* keep 'em coming, baby */
#define NET_RX_DROP		1	/* packet dropped */

70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88
/*
 * Transmit return codes: transmit return codes originate from three different
 * namespaces:
 *
 * - qdisc return codes
 * - driver transmit return codes
 * - errno values
 *
 * Drivers are allowed to return any one of those in their hard_start_xmit()
 * function. Real network devices commonly used with qdiscs should only return
 * the driver transmit return codes though - when qdiscs are used, the actual
 * transmission happens asynchronously, so the value is not propagated to
 * higher layers. Virtual network devices transmit synchronously, in this case
 * the driver transmit return codes are consumed by dev_queue_xmit(), all
 * others are propagated to higher layers.
 */

/* qdisc ->enqueue() return codes. */
#define NET_XMIT_SUCCESS	0x00
89 90 91 92
#define NET_XMIT_DROP		0x01	/* skb dropped			*/
#define NET_XMIT_CN		0x02	/* congestion notification	*/
#define NET_XMIT_POLICED	0x03	/* skb is shot by police	*/
#define NET_XMIT_MASK		0x0f	/* qdisc flags in net/sch_generic.h */
L
Linus Torvalds 已提交
93

94 95 96
/* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It
 * indicates that the device will soon be dropping packets, or already drops
 * some packets of the same priority; prompting us to send less aggressively. */
97
#define net_xmit_eval(e)	((e) == NET_XMIT_CN ? 0 : (e))
L
Linus Torvalds 已提交
98 99
#define net_xmit_errno(e)	((e) != NET_XMIT_CN ? -ENOBUFS : 0)

100
/* Driver transmit return codes */
101
#define NETDEV_TX_MASK		0xf0
102

103
enum netdev_tx {
104
	__NETDEV_TX_MIN	 = INT_MIN,	/* make sure enum is signed */
105 106 107
	NETDEV_TX_OK	 = 0x00,	/* driver took care of packet */
	NETDEV_TX_BUSY	 = 0x10,	/* driver tx path was busy*/
	NETDEV_TX_LOCKED = 0x20,	/* driver tx lock was already taken */
108 109 110
};
typedef enum netdev_tx netdev_tx_t;

111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128
/*
 * Current order: NETDEV_TX_MASK > NET_XMIT_MASK >= 0 is significant;
 * hard_start_xmit() return < NET_XMIT_MASK means skb was consumed.
 */
static inline bool dev_xmit_complete(int rc)
{
	/*
	 * Positive cases with an skb consumed by a driver:
	 * - successful transmission (rc == NETDEV_TX_OK)
	 * - error while transmitting (rc < 0)
	 * - error while queueing to a different device (rc & NET_XMIT_MASK)
	 */
	if (likely(rc < NET_XMIT_MASK))
		return true;

	return false;
}

L
Linus Torvalds 已提交
129 130 131 132
#endif

#define MAX_ADDR_LEN	32		/* Largest hardware address length */

133
#ifdef  __KERNEL__
L
Linus Torvalds 已提交
134 135 136 137
/*
 *	Compute the worst case header length according to the protocols
 *	used.
 */
G
Graf Yang 已提交
138

139 140 141 142 143 144
#if defined(CONFIG_WLAN_80211) || defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
# if defined(CONFIG_MAC80211_MESH)
#  define LL_MAX_HEADER 128
# else
#  define LL_MAX_HEADER 96
# endif
145
#elif defined(CONFIG_TR) || defined(CONFIG_TR_MODULE)
146
# define LL_MAX_HEADER 48
L
Linus Torvalds 已提交
147
#else
148
# define LL_MAX_HEADER 32
L
Linus Torvalds 已提交
149 150
#endif

D
David S. Miller 已提交
151 152 153 154
#if !defined(CONFIG_NET_IPIP) && !defined(CONFIG_NET_IPIP_MODULE) && \
    !defined(CONFIG_NET_IPGRE) &&  !defined(CONFIG_NET_IPGRE_MODULE) && \
    !defined(CONFIG_IPV6_SIT) && !defined(CONFIG_IPV6_SIT_MODULE) && \
    !defined(CONFIG_IPV6_TUNNEL) && !defined(CONFIG_IPV6_TUNNEL_MODULE)
L
Linus Torvalds 已提交
155 156 157 158 159
#define MAX_HEADER LL_MAX_HEADER
#else
#define MAX_HEADER (LL_MAX_HEADER + 48)
#endif

160 161
#endif  /*  __KERNEL__  */

L
Linus Torvalds 已提交
162 163 164 165
/*
 *	Network device statistics. Akin to the 2.0 ether stats but
 *	with byte counters.
 */
G
Graf Yang 已提交
166

E
Eric Dumazet 已提交
167
struct net_device_stats {
L
Linus Torvalds 已提交
168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219
	unsigned long	rx_packets;		/* total packets received	*/
	unsigned long	tx_packets;		/* total packets transmitted	*/
	unsigned long	rx_bytes;		/* total bytes received 	*/
	unsigned long	tx_bytes;		/* total bytes transmitted	*/
	unsigned long	rx_errors;		/* bad packets received		*/
	unsigned long	tx_errors;		/* packet transmit problems	*/
	unsigned long	rx_dropped;		/* no space in linux buffers	*/
	unsigned long	tx_dropped;		/* no space available in linux	*/
	unsigned long	multicast;		/* multicast packets received	*/
	unsigned long	collisions;

	/* detailed rx_errors: */
	unsigned long	rx_length_errors;
	unsigned long	rx_over_errors;		/* receiver ring buff overflow	*/
	unsigned long	rx_crc_errors;		/* recved pkt with crc error	*/
	unsigned long	rx_frame_errors;	/* recv'd frame alignment error */
	unsigned long	rx_fifo_errors;		/* recv'r fifo overrun		*/
	unsigned long	rx_missed_errors;	/* receiver missed packet	*/

	/* detailed tx_errors */
	unsigned long	tx_aborted_errors;
	unsigned long	tx_carrier_errors;
	unsigned long	tx_fifo_errors;
	unsigned long	tx_heartbeat_errors;
	unsigned long	tx_window_errors;
	
	/* for cslip etc */
	unsigned long	rx_compressed;
	unsigned long	tx_compressed;
};


/* Media selection options. */
enum {
        IF_PORT_UNKNOWN = 0,
        IF_PORT_10BASE2,
        IF_PORT_10BASET,
        IF_PORT_AUI,
        IF_PORT_100BASET,
        IF_PORT_100BASETX,
        IF_PORT_100BASEFX
};

#ifdef __KERNEL__

#include <linux/cache.h>
#include <linux/skbuff.h>

struct neighbour;
struct neigh_parms;
struct sk_buff;

E
Eric Dumazet 已提交
220
struct netif_rx_stats {
L
Linus Torvalds 已提交
221 222 223 224 225 226 227 228
	unsigned total;
	unsigned dropped;
	unsigned time_squeeze;
	unsigned cpu_collision;
};

DECLARE_PER_CPU(struct netif_rx_stats, netdev_rx_stat);

E
Eric Dumazet 已提交
229
struct dev_addr_list {
230 231 232
	struct dev_addr_list	*next;
	u8			da_addr[MAX_ADDR_LEN];
	u8			da_addrlen;
233
	u8			da_synced;
234 235 236
	int			da_users;
	int			da_gusers;
};
L
Linus Torvalds 已提交
237 238 239 240

/*
 *	We tag multicasts with these structures.
 */
241 242 243 244 245 246

#define dev_mc_list	dev_addr_list
#define dmi_addr	da_addr
#define dmi_addrlen	da_addrlen
#define dmi_users	da_users
#define dmi_gusers	da_gusers
L
Linus Torvalds 已提交
247

248 249 250 251
struct netdev_hw_addr {
	struct list_head	list;
	unsigned char		addr[MAX_ADDR_LEN];
	unsigned char		type;
J
Jiri Pirko 已提交
252 253 254 255 256 257
#define NETDEV_HW_ADDR_T_LAN		1
#define NETDEV_HW_ADDR_T_SAN		2
#define NETDEV_HW_ADDR_T_SLAVE		3
#define NETDEV_HW_ADDR_T_UNICAST	4
	int			refcount;
	bool			synced;
258 259 260
	struct rcu_head		rcu_head;
};

261 262 263 264 265
struct netdev_hw_addr_list {
	struct list_head	list;
	int			count;
};

266 267 268 269 270
#define netdev_uc_count(dev) ((dev)->uc.count)
#define netdev_uc_empty(dev) ((dev)->uc.count == 0)
#define netdev_for_each_uc_addr(ha, dev) \
	list_for_each_entry(ha, &dev->uc.list, list)

271 272 273 274 275 276
#define netdev_mc_count(dev) ((dev)->mc_count)
#define netdev_mc_empty(dev) (netdev_mc_count(dev) == 0)

#define netdev_for_each_mc_addr(mclist, dev) \
	for (mclist = dev->mc_list; mclist; mclist = mclist->next)

E
Eric Dumazet 已提交
277
struct hh_cache {
L
Linus Torvalds 已提交
278 279
	struct hh_cache *hh_next;	/* Next entry			     */
	atomic_t	hh_refcnt;	/* number of users                   */
280 281 282 283 284 285 286 287
/*
 * We want hh_output, hh_len, hh_lock and hh_data be a in a separate
 * cache line on SMP.
 * They are mostly read, but hh_refcnt may be changed quite frequently,
 * incurring cache line ping pongs.
 */
	__be16		hh_type ____cacheline_aligned_in_smp;
					/* protocol identifier, f.e ETH_P_IP
L
Linus Torvalds 已提交
288 289 290
                                         *  NOTE:  For VLANs, this will be the
                                         *  encapuslated type. --BLG
                                         */
291
	u16		hh_len;		/* length of header */
L
Linus Torvalds 已提交
292
	int		(*hh_output)(struct sk_buff *skb);
293
	seqlock_t	hh_lock;
L
Linus Torvalds 已提交
294 295 296 297

	/* cached hardware header; allow for machine alignment needs.        */
#define HH_DATA_MOD	16
#define HH_DATA_OFF(__len) \
J
Jiri Benc 已提交
298
	(HH_DATA_MOD - (((__len - 1) & (HH_DATA_MOD - 1)) + 1))
L
Linus Torvalds 已提交
299 300 301 302 303 304 305 306 307 308 309 310
#define HH_DATA_ALIGN(__len) \
	(((__len)+(HH_DATA_MOD-1))&~(HH_DATA_MOD - 1))
	unsigned long	hh_data[HH_DATA_ALIGN(LL_MAX_HEADER) / sizeof(long)];
};

/* Reserve HH_DATA_MOD byte aligned hard_header_len, but at least that much.
 * Alternative is:
 *   dev->hard_header_len ? (dev->hard_header_len +
 *                           (HH_DATA_MOD - 1)) & ~(HH_DATA_MOD - 1) : 0
 *
 * We could use other alignment values, but we must maintain the
 * relationship HH alignment <= LL alignment.
311 312 313
 *
 * LL_ALLOCATED_SPACE also takes into account the tailroom the device
 * may need.
L
Linus Torvalds 已提交
314 315
 */
#define LL_RESERVED_SPACE(dev) \
316
	((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
L
Linus Torvalds 已提交
317
#define LL_RESERVED_SPACE_EXTRA(dev,extra) \
318 319 320
	((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
#define LL_ALLOCATED_SPACE(dev) \
	((((dev)->hard_header_len+(dev)->needed_headroom+(dev)->needed_tailroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
L
Linus Torvalds 已提交
321

322 323 324 325 326 327 328 329 330 331 332 333 334
struct header_ops {
	int	(*create) (struct sk_buff *skb, struct net_device *dev,
			   unsigned short type, const void *daddr,
			   const void *saddr, unsigned len);
	int	(*parse)(const struct sk_buff *skb, unsigned char *haddr);
	int	(*rebuild)(struct sk_buff *skb);
#define HAVE_HEADER_CACHE
	int	(*cache)(const struct neighbour *neigh, struct hh_cache *hh);
	void	(*cache_update)(struct hh_cache *hh,
				const struct net_device *dev,
				const unsigned char *haddr);
};

L
Linus Torvalds 已提交
335 336 337 338 339
/* These flag bits are private to the generic network queueing
 * layer, they may not be explicitly referenced by any other
 * code.
 */

E
Eric Dumazet 已提交
340
enum netdev_state_t {
L
Linus Torvalds 已提交
341 342 343
	__LINK_STATE_START,
	__LINK_STATE_PRESENT,
	__LINK_STATE_NOCARRIER,
S
Stefan Rompf 已提交
344 345
	__LINK_STATE_LINKWATCH_PENDING,
	__LINK_STATE_DORMANT,
L
Linus Torvalds 已提交
346 347 348 349 350
};


/*
 * This structure holds at boot time configured netdevice settings. They
G
Graf Yang 已提交
351
 * are then used in the device probing.
L
Linus Torvalds 已提交
352 353 354 355 356 357 358
 */
struct netdev_boot_setup {
	char name[IFNAMSIZ];
	struct ifmap map;
};
#define NETDEV_BOOT_SETUP_MAX 8

359
extern int __init netdev_boot_setup(char *str);
L
Linus Torvalds 已提交
360

361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379
/*
 * Structure for NAPI scheduling similar to tasklet but with weighting
 */
struct napi_struct {
	/* The poll_list must only be managed by the entity which
	 * changes the state of the NAPI_STATE_SCHED bit.  This means
	 * whoever atomically sets that bit can add this napi_struct
	 * to the per-cpu poll_list, and whoever clears that bit
	 * can remove from the list right before clearing the bit.
	 */
	struct list_head	poll_list;

	unsigned long		state;
	int			weight;
	int			(*poll)(struct napi_struct *, int);
#ifdef CONFIG_NETPOLL
	spinlock_t		poll_lock;
	int			poll_owner;
#endif
380 381 382

	unsigned int		gro_count;

H
Herbert Xu 已提交
383
	struct net_device	*dev;
384 385
	struct list_head	dev_list;
	struct sk_buff		*gro_list;
H
Herbert Xu 已提交
386
	struct sk_buff		*skb;
387 388
};

E
Eric Dumazet 已提交
389
enum {
390
	NAPI_STATE_SCHED,	/* Poll is scheduled */
D
David S. Miller 已提交
391
	NAPI_STATE_DISABLE,	/* Disable pending */
392
	NAPI_STATE_NPSVC,	/* Netpoll - don't dequeue from poll_list */
393 394
};

395
enum gro_result {
396 397 398 399 400 401
	GRO_MERGED,
	GRO_MERGED_FREE,
	GRO_HELD,
	GRO_NORMAL,
	GRO_DROP,
};
402
typedef enum gro_result gro_result_t;
403

404
extern void __napi_schedule(struct napi_struct *n);
405

D
David S. Miller 已提交
406 407 408 409 410
static inline int napi_disable_pending(struct napi_struct *n)
{
	return test_bit(NAPI_STATE_DISABLE, &n->state);
}

411 412 413 414 415 416
/**
 *	napi_schedule_prep - check if napi can be scheduled
 *	@n: napi context
 *
 * Test if NAPI routine is already running, and if not mark
 * it as running.  This is used as a condition variable
D
David S. Miller 已提交
417 418
 * insure only one NAPI poll instance runs.  We also make
 * sure there is no pending NAPI disable.
419 420 421
 */
static inline int napi_schedule_prep(struct napi_struct *n)
{
D
David S. Miller 已提交
422 423
	return !napi_disable_pending(n) &&
		!test_and_set_bit(NAPI_STATE_SCHED, &n->state);
424 425 426 427 428 429 430 431 432 433 434 435 436 437 438
}

/**
 *	napi_schedule - schedule NAPI poll
 *	@n: napi context
 *
 * Schedule NAPI poll routine to be called if it is not already
 * running.
 */
static inline void napi_schedule(struct napi_struct *n)
{
	if (napi_schedule_prep(n))
		__napi_schedule(n);
}

439 440 441 442 443 444 445 446 447 448
/* Try to reschedule poll. Called by dev->poll() after napi_complete().  */
static inline int napi_reschedule(struct napi_struct *napi)
{
	if (napi_schedule_prep(napi)) {
		__napi_schedule(napi);
		return 1;
	}
	return 0;
}

449 450 451 452 453 454
/**
 *	napi_complete - NAPI processing complete
 *	@n: napi context
 *
 * Mark NAPI processing as complete.
 */
455 456
extern void __napi_complete(struct napi_struct *n);
extern void napi_complete(struct napi_struct *n);
457 458 459 460 461 462 463 464 465 466

/**
 *	napi_disable - prevent NAPI from scheduling
 *	@n: napi context
 *
 * Stop NAPI from being scheduled on this context.
 * Waits till any outstanding processing completes.
 */
static inline void napi_disable(struct napi_struct *n)
{
D
David S. Miller 已提交
467
	set_bit(NAPI_STATE_DISABLE, &n->state);
468
	while (test_and_set_bit(NAPI_STATE_SCHED, &n->state))
469
		msleep(1);
D
David S. Miller 已提交
470
	clear_bit(NAPI_STATE_DISABLE, &n->state);
471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486
}

/**
 *	napi_enable - enable NAPI scheduling
 *	@n: napi context
 *
 * Resume NAPI from being scheduled on this context.
 * Must be paired with napi_disable.
 */
static inline void napi_enable(struct napi_struct *n)
{
	BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
	smp_mb__before_clear_bit();
	clear_bit(NAPI_STATE_SCHED, &n->state);
}

487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504
#ifdef CONFIG_SMP
/**
 *	napi_synchronize - wait until NAPI is not running
 *	@n: napi context
 *
 * Wait until NAPI is done being scheduled on this context.
 * Waits till any outstanding processing completes but
 * does not disable future activations.
 */
static inline void napi_synchronize(const struct napi_struct *n)
{
	while (test_bit(NAPI_STATE_SCHED, &n->state))
		msleep(1);
}
#else
# define napi_synchronize(n)	barrier()
#endif

E
Eric Dumazet 已提交
505
enum netdev_queue_state_t {
506
	__QUEUE_STATE_XOFF,
507
	__QUEUE_STATE_FROZEN,
508 509
};

510
struct netdev_queue {
511 512 513
/*
 * read mostly part
 */
514
	struct net_device	*dev;
515
	struct Qdisc		*qdisc;
516
	unsigned long		state;
517
	struct Qdisc		*qdisc_sleeping;
518 519 520 521 522
/*
 * write mostly part
 */
	spinlock_t		_xmit_lock ____cacheline_aligned_in_smp;
	int			xmit_lock_owner;
523 524 525 526
	/*
	 * please use this field instead of dev->trans_start
	 */
	unsigned long		trans_start;
527 528 529
	unsigned long		tx_bytes;
	unsigned long		tx_packets;
	unsigned long		tx_dropped;
530
} ____cacheline_aligned_in_smp;
531

532 533 534

/*
 * This structure defines the management hooks for network devices.
535 536
 * The following hooks can be defined; unless noted otherwise, they are
 * optional and can be filled with a null pointer.
537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555
 *
 * int (*ndo_init)(struct net_device *dev);
 *     This function is called once when network device is registered.
 *     The network device can use this to any late stage initializaton
 *     or semantic validattion. It can fail with an error code which will
 *     be propogated back to register_netdev
 *
 * void (*ndo_uninit)(struct net_device *dev);
 *     This function is called when device is unregistered or when registration
 *     fails. It is not called if init fails.
 *
 * int (*ndo_open)(struct net_device *dev);
 *     This function is called when network device transistions to the up
 *     state.
 *
 * int (*ndo_stop)(struct net_device *dev);
 *     This function is called when network device transistions to the down
 *     state.
 *
556 557
 * netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb,
 *                               struct net_device *dev);
558
 *	Called when a packet needs to be transmitted.
559 560
 *	Must return NETDEV_TX_OK , NETDEV_TX_BUSY.
 *        (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
561 562 563 564 565 566
 *	Required can not be NULL.
 *
 * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb);
 *	Called to decide which queue to when device supports multiple
 *	transmit queues.
 *
567 568 569 570 571 572 573 574 575 576 577 578
 * void (*ndo_change_rx_flags)(struct net_device *dev, int flags);
 *	This function is called to allow device receiver to make
 *	changes to configuration when multicast or promiscious is enabled.
 *
 * void (*ndo_set_rx_mode)(struct net_device *dev);
 *	This function is called device changes address list filtering.
 *
 * void (*ndo_set_multicast_list)(struct net_device *dev);
 *	This function is called when the multicast address list changes.
 *
 * int (*ndo_set_mac_address)(struct net_device *dev, void *addr);
 *	This function  is called when the Media Access Control address
579
 *	needs to be changed. If this interface is not defined, the
580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599
 *	mac address can not be changed.
 *
 * int (*ndo_validate_addr)(struct net_device *dev);
 *	Test if Media Access Control address is valid for the device.
 *
 * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd);
 *	Called when a user request an ioctl which can't be handled by
 *	the generic interface code. If not defined ioctl's return
 *	not supported error code.
 *
 * int (*ndo_set_config)(struct net_device *dev, struct ifmap *map);
 *	Used to set network devices bus interface parameters. This interface
 *	is retained for legacy reason, new devices should use the bus
 *	interface (PCI) for low level management.
 *
 * int (*ndo_change_mtu)(struct net_device *dev, int new_mtu);
 *	Called when a user wants to change the Maximum Transfer Unit
 *	of a device. If not defined, any request to change MTU will
 *	will return an error.
 *
600
 * void (*ndo_tx_timeout)(struct net_device *dev);
601 602 603
 *	Callback uses when the transmitter has not made any progress
 *	for dev->watchdog ticks.
 *
604
 * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624
 *	Called when a user wants to get the network device usage
 *	statistics. If not defined, the counters in dev->stats will
 *	be used.
 *
 * void (*ndo_vlan_rx_register)(struct net_device *dev, struct vlan_group *grp);
 *	If device support VLAN receive accleration
 *	(ie. dev->features & NETIF_F_HW_VLAN_RX), then this function is called
 *	when vlan groups for the device changes.  Note: grp is NULL
 *	if no vlan's groups are being used.
 *
 * void (*ndo_vlan_rx_add_vid)(struct net_device *dev, unsigned short vid);
 *	If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER)
 *	this function is called when a VLAN id is registered.
 *
 * void (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid);
 *	If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER)
 *	this function is called when a VLAN id is unregistered.
 *
 * void (*ndo_poll_controller)(struct net_device *dev);
 */
625
#define HAVE_NET_DEVICE_OPS
626 627 628 629 630
struct net_device_ops {
	int			(*ndo_init)(struct net_device *dev);
	void			(*ndo_uninit)(struct net_device *dev);
	int			(*ndo_open)(struct net_device *dev);
	int			(*ndo_stop)(struct net_device *dev);
631
	netdev_tx_t		(*ndo_start_xmit) (struct sk_buff *skb,
632 633 634
						   struct net_device *dev);
	u16			(*ndo_select_queue)(struct net_device *dev,
						    struct sk_buff *skb);
635 636 637 638 639 640 641 642 643 644 645
	void			(*ndo_change_rx_flags)(struct net_device *dev,
						       int flags);
	void			(*ndo_set_rx_mode)(struct net_device *dev);
	void			(*ndo_set_multicast_list)(struct net_device *dev);
	int			(*ndo_set_mac_address)(struct net_device *dev,
						       void *addr);
	int			(*ndo_validate_addr)(struct net_device *dev);
	int			(*ndo_do_ioctl)(struct net_device *dev,
					        struct ifreq *ifr, int cmd);
	int			(*ndo_set_config)(struct net_device *dev,
					          struct ifmap *map);
646 647 648 649
	int			(*ndo_change_mtu)(struct net_device *dev,
						  int new_mtu);
	int			(*ndo_neigh_setup)(struct net_device *dev,
						   struct neigh_parms *);
650 651 652 653 654 655 656 657 658 659 660 661 662
	void			(*ndo_tx_timeout) (struct net_device *dev);

	struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);

	void			(*ndo_vlan_rx_register)(struct net_device *dev,
						        struct vlan_group *grp);
	void			(*ndo_vlan_rx_add_vid)(struct net_device *dev,
						       unsigned short vid);
	void			(*ndo_vlan_rx_kill_vid)(struct net_device *dev,
						        unsigned short vid);
#ifdef CONFIG_NET_POLL_CONTROLLER
	void                    (*ndo_poll_controller)(struct net_device *dev);
#endif
663
#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
664 665
	int			(*ndo_fcoe_enable)(struct net_device *dev);
	int			(*ndo_fcoe_disable)(struct net_device *dev);
666 667 668 669 670 671
	int			(*ndo_fcoe_ddp_setup)(struct net_device *dev,
						      u16 xid,
						      struct scatterlist *sgl,
						      unsigned int sgc);
	int			(*ndo_fcoe_ddp_done)(struct net_device *dev,
						     u16 xid);
672 673 674 675
#define NETDEV_FCOE_WWNN 0
#define NETDEV_FCOE_WWPN 1
	int			(*ndo_fcoe_get_wwn)(struct net_device *dev,
						    u64 *wwn, int type);
676
#endif
677 678
};

L
Linus Torvalds 已提交
679 680 681 682 683 684 685 686 687 688
/*
 *	The DEVICE structure.
 *	Actually, this whole structure is a big mistake.  It mixes I/O
 *	data with strictly "high-level" data, and it has to know about
 *	almost every data structure used in the INET module.
 *
 *	FIXME: cleanup struct net_device such that network protocol info
 *	moves out.
 */

E
Eric Dumazet 已提交
689
struct net_device {
L
Linus Torvalds 已提交
690 691 692 693 694 695 696

	/*
	 * This is the first field of the "visible" part of this structure
	 * (i.e. as seen by users in the "Space.c" file).  It is the name
	 * the interface.
	 */
	char			name[IFNAMSIZ];
697 698
	/* device name hash chain */
	struct hlist_node	name_hlist;
699 700
	/* snmp alias */
	char 			*ifalias;
L
Linus Torvalds 已提交
701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720

	/*
	 *	I/O specific fields
	 *	FIXME: Merge these and struct ifmap into one
	 */
	unsigned long		mem_end;	/* shared mem end	*/
	unsigned long		mem_start;	/* shared mem start	*/
	unsigned long		base_addr;	/* device I/O address	*/
	unsigned int		irq;		/* device IRQ number	*/

	/*
	 *	Some hardware also needs these fields, but they are not
	 *	part of the usual set specified in Space.c.
	 */

	unsigned char		if_port;	/* Selectable AUI, TP,..*/
	unsigned char		dma;		/* DMA channel		*/

	unsigned long		state;

721
	struct list_head	dev_list;
722
	struct list_head	napi_list;
723
	struct list_head	unreg_list;
L
Linus Torvalds 已提交
724

725 726 727
	/* Net device features */
	unsigned long		features;
#define NETIF_F_SG		1	/* Scatter/gather IO. */
728
#define NETIF_F_IP_CSUM		2	/* Can checksum TCP/UDP over IPv4. */
729 730
#define NETIF_F_NO_CSUM		4	/* Does not require checksum. F.e. loopack. */
#define NETIF_F_HW_CSUM		8	/* Can checksum all the packets. */
731
#define NETIF_F_IPV6_CSUM	16	/* Can checksum TCP/UDP over IPV6 */
732 733 734 735 736 737
#define NETIF_F_HIGHDMA		32	/* Can DMA to high memory. */
#define NETIF_F_FRAGLIST	64	/* Scatter/gather IO. */
#define NETIF_F_HW_VLAN_TX	128	/* Transmit VLAN hw acceleration */
#define NETIF_F_HW_VLAN_RX	256	/* Receive VLAN hw acceleration */
#define NETIF_F_HW_VLAN_FILTER	512	/* Receive filtering on VLAN */
#define NETIF_F_VLAN_CHALLENGED	1024	/* Device cannot handle VLAN packets */
H
Herbert Xu 已提交
738
#define NETIF_F_GSO		2048	/* Enable software GSO. */
739 740
#define NETIF_F_LLTX		4096	/* LockLess TX - deprecated. Please */
					/* do not use LLTX in new drivers */
741
#define NETIF_F_NETNS_LOCAL	8192	/* Does not change network namespaces */
742
#define NETIF_F_GRO		16384	/* Generic receive offload */
743
#define NETIF_F_LRO		32768	/* large receive offload */
744

745
/* the GSO_MASK reserves bits 16 through 23 */
746
#define NETIF_F_FCOE_CRC	(1 << 24) /* FCoE CRC32 */
747
#define NETIF_F_SCTP_CSUM	(1 << 25) /* SCTP checksum offload */
748
#define NETIF_F_FCOE_MTU	(1 << 26) /* Supports max FCoE MTU, 2158 bytes*/
749
#define NETIF_F_NTUPLE		(1 << 27) /* N-tuple filters supported */
750

751
	/* Segmentation offload features */
752
#define NETIF_F_GSO_SHIFT	16
753
#define NETIF_F_GSO_MASK	0x00ff0000
754
#define NETIF_F_TSO		(SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT)
H
Herbert Xu 已提交
755
#define NETIF_F_UFO		(SKB_GSO_UDP << NETIF_F_GSO_SHIFT)
756
#define NETIF_F_GSO_ROBUST	(SKB_GSO_DODGY << NETIF_F_GSO_SHIFT)
H
Herbert Xu 已提交
757 758
#define NETIF_F_TSO_ECN		(SKB_GSO_TCP_ECN << NETIF_F_GSO_SHIFT)
#define NETIF_F_TSO6		(SKB_GSO_TCPV6 << NETIF_F_GSO_SHIFT)
759
#define NETIF_F_FSO		(SKB_GSO_FCOE << NETIF_F_GSO_SHIFT)
760

761 762 763
	/* List of features with software fallbacks. */
#define NETIF_F_GSO_SOFTWARE	(NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6)

764

765
#define NETIF_F_GEN_CSUM	(NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)
766 767 768
#define NETIF_F_V4_CSUM		(NETIF_F_GEN_CSUM | NETIF_F_IP_CSUM)
#define NETIF_F_V6_CSUM		(NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM)
#define NETIF_F_ALL_CSUM	(NETIF_F_V4_CSUM | NETIF_F_V6_CSUM)
769

770 771 772 773 774
	/*
	 * If one device supports one of these features, then enable them
	 * for all in netdev_increment_features.
	 */
#define NETIF_F_ONE_FOR_ALL	(NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \
775
				 NETIF_F_SG | NETIF_F_HIGHDMA |		\
776 777
				 NETIF_F_FRAGLIST)

L
Linus Torvalds 已提交
778 779 780 781
	/* Interface index. Unique device identifier	*/
	int			ifindex;
	int			iflink;

R
Rusty Russell 已提交
782
	struct net_device_stats	stats;
L
Linus Torvalds 已提交
783

784
#ifdef CONFIG_WIRELESS_EXT
L
Linus Torvalds 已提交
785 786 787 788 789
	/* List of functions to handle Wireless Extensions (instead of ioctl).
	 * See <net/iw_handler.h> for details. Jean II */
	const struct iw_handler_def *	wireless_handlers;
	/* Instance data managed by the core of Wireless Extensions. */
	struct iw_public_data *	wireless_data;
790
#endif
791 792
	/* Management operations */
	const struct net_device_ops *netdev_ops;
793
	const struct ethtool_ops *ethtool_ops;
L
Linus Torvalds 已提交
794

795 796 797
	/* Hardware header description */
	const struct header_ops *header_ops;

S
Stefan Rompf 已提交
798
	unsigned int		flags;	/* interface flags (a la BSD)	*/
L
Linus Torvalds 已提交
799 800 801 802
	unsigned short		gflags;
        unsigned short          priv_flags; /* Like 'flags' but invisible to userspace. */
	unsigned short		padded;	/* How much padding added by alloc_netdev() */

S
Stefan Rompf 已提交
803 804 805
	unsigned char		operstate; /* RFC2863 operstate */
	unsigned char		link_mode; /* mapping policy to operstate */

L
Linus Torvalds 已提交
806 807 808 809
	unsigned		mtu;	/* interface MTU value		*/
	unsigned short		type;	/* interface hardware type	*/
	unsigned short		hard_header_len;	/* hardware hdr length	*/

810 811 812 813 814 815 816
	/* extra head- and tailroom the hardware may need, but not in all cases
	 * can this be guaranteed, especially tailroom. Some cases also use
	 * LL_MAX_HEADER instead to allocate the skb.
	 */
	unsigned short		needed_headroom;
	unsigned short		needed_tailroom;

L
Linus Torvalds 已提交
817 818 819 820 821
	struct net_device	*master; /* Pointer to master device of a group,
					  * which this device is member of.
					  */

	/* Interface address info. */
822
	unsigned char		perm_addr[MAX_ADDR_LEN]; /* permanent hw address */
L
Linus Torvalds 已提交
823 824 825
	unsigned char		addr_len;	/* hardware address length	*/
	unsigned short          dev_id;		/* for shared network cards */

826 827
	struct netdev_hw_addr_list	uc;	/* Secondary unicast
						   mac addresses */
828
	int			uc_promisc;
J
Jiri Pirko 已提交
829
	spinlock_t		addr_list_lock;
830
	struct dev_addr_list	*mc_list;	/* Multicast mac addresses	*/
L
Linus Torvalds 已提交
831
	int			mc_count;	/* Number of installed mcasts	*/
832 833
	unsigned int		promiscuity;
	unsigned int		allmulti;
L
Linus Torvalds 已提交
834 835 836 837


	/* Protocol specific pointers */
	
838 839 840
#ifdef CONFIG_NET_DSA
	void			*dsa_ptr;	/* dsa specific data */
#endif
L
Linus Torvalds 已提交
841
	void 			*atalk_ptr;	/* AppleTalk link 	*/
G
Graf Yang 已提交
842
	void			*ip_ptr;	/* IPv4 specific data	*/
L
Linus Torvalds 已提交
843 844 845 846
	void                    *dn_ptr;        /* DECnet specific data */
	void                    *ip6_ptr;       /* IPv6 specific data */
	void			*ec_ptr;	/* Econet specific data	*/
	void			*ax25_ptr;	/* AX.25 specific data */
847 848
	struct wireless_dev	*ieee80211_ptr;	/* IEEE 802.11 specific data,
						   assign before registering */
L
Linus Torvalds 已提交
849

850 851 852 853 854
/*
 * Cache line mostly used on receive path (including eth_type_trans())
 */
	unsigned long		last_rx;	/* Time of last Rx	*/
	/* Interface address info used in eth_type_trans() */
855 856 857 858
	unsigned char		*dev_addr;	/* hw address, (before bcast
						   because most packets are
						   unicast) */

859 860
	struct netdev_hw_addr_list	dev_addrs; /* list of device
						      hw addresses */
861 862

	unsigned char		broadcast[MAX_ADDR_LEN];	/* hw bcast add	*/
L
Linus Torvalds 已提交
863

864
	struct netdev_queue	rx_queue;
865 866

	struct netdev_queue	*_tx ____cacheline_aligned_in_smp;
867 868

	/* Number of TX queues allocated at alloc_netdev_mq() time  */
869
	unsigned int		num_tx_queues;
870 871 872 873

	/* Number of TX queues currently active in device  */
	unsigned int		real_num_tx_queues;

874 875 876
	/* root qdisc from userspace point of view */
	struct Qdisc		*qdisc;

L
Linus Torvalds 已提交
877
	unsigned long		tx_queue_len;	/* Max frames per queue allowed */
878
	spinlock_t		tx_global_lock;
879 880 881 882
/*
 * One part is mostly used on xmit path (device)
 */
	/* These may be needed for future network-power-down code. */
883 884 885 886 887

	/*
	 * trans_start here is expensive for high speed devices on SMP,
	 * please use netdev_queue->trans_start instead.
	 */
888 889 890 891 892
	unsigned long		trans_start;	/* Time (in jiffies) of last Tx	*/

	int			watchdog_timeo; /* used by dev_watchdog() */
	struct timer_list	watchdog_timer;

L
Linus Torvalds 已提交
893
	/* Number of references to this device */
894 895
	atomic_t		refcnt ____cacheline_aligned_in_smp;

L
Linus Torvalds 已提交
896 897 898 899 900
	/* delayed register/unregister */
	struct list_head	todo_list;
	/* device index hash chain */
	struct hlist_node	index_hlist;

901
	struct list_head	link_watch_list;
902

L
Linus Torvalds 已提交
903 904
	/* register/unregister state machine */
	enum { NETREG_UNINITIALIZED=0,
905
	       NETREG_REGISTERED,	/* completed register_netdevice */
L
Linus Torvalds 已提交
906 907 908
	       NETREG_UNREGISTERING,	/* called unregister_netdevice */
	       NETREG_UNREGISTERED,	/* completed unregister todo */
	       NETREG_RELEASED,		/* called free_netdev */
909
	       NETREG_DUMMY,		/* dummy device for NAPI poll */
L
Linus Torvalds 已提交
910 911
	} reg_state;

912 913
	/* Called from unregister, can be used to call free_netdev */
	void (*destructor)(struct net_device *dev);
L
Linus Torvalds 已提交
914 915

#ifdef CONFIG_NETPOLL
916
	struct netpoll_info	*npinfo;
L
Linus Torvalds 已提交
917
#endif
918

919
#ifdef CONFIG_NET_NS
920 921
	/* Network namespace this network device is inside */
	struct net		*nd_net;
922
#endif
923

D
David S. Miller 已提交
924 925 926
	/* mid-layer private */
	void			*ml_priv;

L
Linus Torvalds 已提交
927 928
	/* bridge stuff */
	struct net_bridge_port	*br_port;
P
Patrick McHardy 已提交
929 930
	/* macvlan */
	struct macvlan_port	*macvlan_port;
931 932
	/* GARP */
	struct garp_port	*garp_port;
L
Linus Torvalds 已提交
933 934

	/* class/net/name entry */
935
	struct device		dev;
936 937
	/* space for optional device, statistics, and wireless sysfs groups */
	const struct attribute_group *sysfs_groups[4];
P
Patrick McHardy 已提交
938 939 940

	/* rtnetlink link ops */
	const struct rtnl_link_ops *rtnl_link_ops;
941

942 943 944
	/* VLAN feature mask */
	unsigned long vlan_features;

945 946 947
	/* for setting kernel sock attribute on TCP connection setup */
#define GSO_MAX_SIZE		65536
	unsigned int		gso_max_size;
948

J
Jeff Kirsher 已提交
949
#ifdef CONFIG_DCB
950
	/* Data Center Bridging netlink ops */
951
	const struct dcbnl_rtnl_ops *dcbnl_ops;
952 953
#endif

954 955 956 957
#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
	/* max exchange id for FCoE LRO by ddp */
	unsigned int		fcoe_ddp_xid;
#endif
958 959
	/* n-tuple filter list attached to this device */
	struct ethtool_rx_ntuple_list ethtool_ntuple_list;
L
Linus Torvalds 已提交
960
};
961
#define to_net_dev(d) container_of(d, struct net_device, dev)
L
Linus Torvalds 已提交
962 963 964

#define	NETDEV_ALIGN		32

965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983
static inline
struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
					 unsigned int index)
{
	return &dev->_tx[index];
}

static inline void netdev_for_each_tx_queue(struct net_device *dev,
					    void (*f)(struct net_device *,
						      struct netdev_queue *,
						      void *),
					    void *arg)
{
	unsigned int i;

	for (i = 0; i < dev->num_tx_queues; i++)
		f(dev, &dev->_tx[i], arg);
}

984 985 986 987 988 989 990 991 992 993 994 995 996 997
/*
 * Net namespace inlines
 */
static inline
struct net *dev_net(const struct net_device *dev)
{
#ifdef CONFIG_NET_NS
	return dev->nd_net;
#else
	return &init_net;
#endif
}

static inline
998
void dev_net_set(struct net_device *dev, struct net *net)
999 1000
{
#ifdef CONFIG_NET_NS
1001 1002
	release_net(dev->nd_net);
	dev->nd_net = hold_net(net);
1003 1004 1005
#endif
}

1006 1007 1008 1009 1010 1011 1012 1013 1014 1015
static inline bool netdev_uses_dsa_tags(struct net_device *dev)
{
#ifdef CONFIG_NET_DSA_TAG_DSA
	if (dev->dsa_ptr != NULL)
		return dsa_uses_dsa_tags(dev->dsa_ptr);
#endif

	return 0;
}

1016 1017 1018 1019 1020 1021 1022 1023 1024
#ifndef CONFIG_NET_NS
static inline void skb_set_dev(struct sk_buff *skb, struct net_device *dev)
{
	skb->dev = dev;
}
#else /* CONFIG_NET_NS */
void skb_set_dev(struct sk_buff *skb, struct net_device *dev);
#endif

1025 1026 1027 1028 1029 1030 1031 1032 1033 1034
static inline bool netdev_uses_trailer_tags(struct net_device *dev)
{
#ifdef CONFIG_NET_DSA_TAG_TRAILER
	if (dev->dsa_ptr != NULL)
		return dsa_uses_trailer_tags(dev->dsa_ptr);
#endif

	return 0;
}

1035 1036 1037 1038 1039 1040
/**
 *	netdev_priv - access network device private data
 *	@dev: network device
 *
 * Get network device private data
 */
1041
static inline void *netdev_priv(const struct net_device *dev)
L
Linus Torvalds 已提交
1042
{
1043
	return (char *)dev + ALIGN(sizeof(struct net_device), NETDEV_ALIGN);
L
Linus Torvalds 已提交
1044 1045 1046 1047 1048
}

/* Set the sysfs physical device reference for the network logical device
 * if set prior to registration will cause a symlink during initialization.
 */
1049
#define SET_NETDEV_DEV(net, pdev)	((net)->dev.parent = (pdev))
L
Linus Torvalds 已提交
1050

1051 1052 1053 1054 1055 1056
/* Set the sysfs device type for the network logical device to allow
 * fin grained indentification of different network device types. For
 * example Ethernet, Wirelss LAN, Bluetooth, WiMAX etc.
 */
#define SET_NETDEV_DEVTYPE(net, devtype)	((net)->dev.type = (devtype))

1057 1058 1059 1060 1061 1062 1063 1064 1065 1066
/**
 *	netif_napi_add - initialize a napi context
 *	@dev:  network device
 *	@napi: napi context
 *	@poll: polling function
 *	@weight: default weight
 *
 * netif_napi_add() must be used to initialize a napi context prior to calling
 * *any* of the other napi related functions.
 */
1067 1068
void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
		    int (*poll)(struct napi_struct *, int), int weight);
1069

1070 1071 1072 1073 1074 1075
/**
 *  netif_napi_del - remove a napi context
 *  @napi: napi context
 *
 *  netif_napi_del() removes a napi context from the network device napi list
 */
1076 1077 1078
void netif_napi_del(struct napi_struct *napi);

struct napi_gro_cb {
1079 1080 1081
	/* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */
	void *frag0;

1082 1083 1084
	/* Length of frag0. */
	unsigned int frag0_len;

1085 1086 1087
	/* This indicates where we are processing relative to skb->data. */
	int data_offset;

1088 1089 1090 1091 1092 1093 1094 1095
	/* This is non-zero if the packet may be of the same flow. */
	int same_flow;

	/* This is non-zero if the packet cannot be merged with the new skb. */
	int flush;

	/* Number of segments aggregated. */
	int count;
H
Herbert Xu 已提交
1096 1097 1098

	/* Free the skb? */
	int free;
1099 1100 1101
};

#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
1102

L
Linus Torvalds 已提交
1103
struct packet_type {
D
David S. Miller 已提交
1104 1105 1106 1107 1108 1109
	__be16			type;	/* This is really htons(ether_type). */
	struct net_device	*dev;	/* NULL is wildcarded here	     */
	int			(*func) (struct sk_buff *,
					 struct net_device *,
					 struct packet_type *,
					 struct net_device *);
1110 1111
	struct sk_buff		*(*gso_segment)(struct sk_buff *skb,
						int features);
1112
	int			(*gso_send_check)(struct sk_buff *skb);
1113 1114 1115
	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
					       struct sk_buff *skb);
	int			(*gro_complete)(struct sk_buff *skb);
L
Linus Torvalds 已提交
1116 1117 1118 1119 1120 1121 1122 1123 1124
	void			*af_packet_priv;
	struct list_head	list;
};

#include <linux/interrupt.h>
#include <linux/notifier.h>

extern rwlock_t				dev_base_lock;		/* Device list lock */

1125

1126 1127
#define for_each_netdev(net, d)		\
		list_for_each_entry(d, &(net)->dev_base_head, dev_list)
1128 1129
#define for_each_netdev_reverse(net, d)	\
		list_for_each_entry_reverse(d, &(net)->dev_base_head, dev_list)
1130 1131
#define for_each_netdev_rcu(net, d)		\
		list_for_each_entry_rcu(d, &(net)->dev_base_head, dev_list)
1132 1133 1134 1135
#define for_each_netdev_safe(net, d, n)	\
		list_for_each_entry_safe(d, n, &(net)->dev_base_head, dev_list)
#define for_each_netdev_continue(net, d)		\
		list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list)
1136 1137
#define for_each_netdev_continue_rcu(net, d)		\
	list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list)
1138
#define net_device_entry(lh)	list_entry(lh, struct net_device, dev_list)
1139

1140 1141 1142 1143 1144
static inline struct net_device *next_net_device(struct net_device *dev)
{
	struct list_head *lh;
	struct net *net;

1145
	net = dev_net(dev);
1146 1147 1148 1149
	lh = dev->dev_list.next;
	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
}

1150 1151 1152 1153 1154 1155 1156 1157 1158 1159
static inline struct net_device *next_net_device_rcu(struct net_device *dev)
{
	struct list_head *lh;
	struct net *net;

	net = dev_net(dev);
	lh = rcu_dereference(dev->dev_list.next);
	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
}

1160 1161 1162 1163 1164
static inline struct net_device *first_net_device(struct net *net)
{
	return list_empty(&net->dev_base_head) ? NULL :
		net_device_entry(net->dev_base_head.next);
}
1165

L
Linus Torvalds 已提交
1166 1167
extern int 			netdev_boot_setup_check(struct net_device *dev);
extern unsigned long		netdev_boot_base(const char *prefix, int unit);
1168 1169 1170
extern struct net_device    *dev_getbyhwaddr(struct net *net, unsigned short type, char *hwaddr);
extern struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type);
extern struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type);
L
Linus Torvalds 已提交
1171 1172 1173 1174
extern void		dev_add_pack(struct packet_type *pt);
extern void		dev_remove_pack(struct packet_type *pt);
extern void		__dev_remove_pack(struct packet_type *pt);

1175
extern struct net_device	*dev_get_by_flags(struct net *net, unsigned short flags,
L
Linus Torvalds 已提交
1176
						  unsigned short mask);
1177
extern struct net_device	*dev_get_by_name(struct net *net, const char *name);
1178
extern struct net_device	*dev_get_by_name_rcu(struct net *net, const char *name);
1179
extern struct net_device	*__dev_get_by_name(struct net *net, const char *name);
L
Linus Torvalds 已提交
1180 1181 1182
extern int		dev_alloc_name(struct net_device *dev, const char *name);
extern int		dev_open(struct net_device *dev);
extern int		dev_close(struct net_device *dev);
1183
extern void		dev_disable_lro(struct net_device *dev);
L
Linus Torvalds 已提交
1184 1185
extern int		dev_queue_xmit(struct sk_buff *skb);
extern int		register_netdevice(struct net_device *dev);
1186 1187
extern void		unregister_netdevice_queue(struct net_device *dev,
						   struct list_head *head);
1188
extern void		unregister_netdevice_many(struct list_head *head);
1189 1190 1191 1192 1193
static inline void unregister_netdevice(struct net_device *dev)
{
	unregister_netdevice_queue(dev, NULL);
}

L
Linus Torvalds 已提交
1194 1195 1196 1197
extern void		free_netdev(struct net_device *dev);
extern void		synchronize_net(void);
extern int 		register_netdevice_notifier(struct notifier_block *nb);
extern int		unregister_netdevice_notifier(struct notifier_block *nb);
1198
extern int		init_dummy_netdev(struct net_device *dev);
1199
extern void		netdev_resync_ops(struct net_device *dev);
1200

1201
extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
1202 1203
extern struct net_device	*dev_get_by_index(struct net *net, int ifindex);
extern struct net_device	*__dev_get_by_index(struct net *net, int ifindex);
1204
extern struct net_device	*dev_get_by_index_rcu(struct net *net, int ifindex);
L
Linus Torvalds 已提交
1205 1206 1207 1208
extern int		dev_restart(struct net_device *dev);
#ifdef CONFIG_NETPOLL_TRAP
extern int		netpoll_trap(void);
#endif
1209 1210
extern int	       skb_gro_receive(struct sk_buff **head,
				       struct sk_buff *skb);
1211
extern void	       skb_gro_reset_offset(struct sk_buff *skb);
1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227

static inline unsigned int skb_gro_offset(const struct sk_buff *skb)
{
	return NAPI_GRO_CB(skb)->data_offset;
}

static inline unsigned int skb_gro_len(const struct sk_buff *skb)
{
	return skb->len - NAPI_GRO_CB(skb)->data_offset;
}

static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len)
{
	NAPI_GRO_CB(skb)->data_offset += len;
}

1228 1229
static inline void *skb_gro_header_fast(struct sk_buff *skb,
					unsigned int offset)
1230
{
1231 1232
	return NAPI_GRO_CB(skb)->frag0 + offset;
}
1233

1234 1235 1236 1237
static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen)
{
	return NAPI_GRO_CB(skb)->frag0_len < hlen;
}
1238

1239 1240 1241 1242 1243 1244
static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen,
					unsigned int offset)
{
	NAPI_GRO_CB(skb)->frag0 = NULL;
	NAPI_GRO_CB(skb)->frag0_len = 0;
	return pskb_may_pull(skb, hlen) ? skb->data + offset : NULL;
1245
}
L
Linus Torvalds 已提交
1246

1247 1248
static inline void *skb_gro_mac_header(struct sk_buff *skb)
{
1249
	return NAPI_GRO_CB(skb)->frag0 ?: skb_mac_header(skb);
1250 1251
}

H
Herbert Xu 已提交
1252 1253
static inline void *skb_gro_network_header(struct sk_buff *skb)
{
1254 1255
	return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) +
	       skb_network_offset(skb);
H
Herbert Xu 已提交
1256 1257
}

1258 1259
static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
				  unsigned short type,
1260 1261
				  const void *daddr, const void *saddr,
				  unsigned len)
1262
{
1263
	if (!dev->header_ops || !dev->header_ops->create)
1264
		return 0;
1265 1266

	return dev->header_ops->create(skb, dev, type, daddr, saddr, len);
1267 1268
}

S
Stephen Hemminger 已提交
1269 1270 1271 1272 1273
static inline int dev_parse_header(const struct sk_buff *skb,
				   unsigned char *haddr)
{
	const struct net_device *dev = skb->dev;

1274
	if (!dev->header_ops || !dev->header_ops->parse)
S
Stephen Hemminger 已提交
1275
		return 0;
1276
	return dev->header_ops->parse(skb, haddr);
S
Stephen Hemminger 已提交
1277 1278
}

L
Linus Torvalds 已提交
1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289
typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
extern int		register_gifconf(unsigned int family, gifconf_func_t * gifconf);
static inline int unregister_gifconf(unsigned int family)
{
	return register_gifconf(family, NULL);
}

/*
 * Incoming packets are placed on per-cpu queues so that
 * no locking is needed.
 */
E
Eric Dumazet 已提交
1290
struct softnet_data {
1291
	struct Qdisc		*output_queue;
L
Linus Torvalds 已提交
1292 1293 1294 1295
	struct sk_buff_head	input_pkt_queue;
	struct list_head	poll_list;
	struct sk_buff		*completion_queue;

1296
	struct napi_struct	backlog;
L
Linus Torvalds 已提交
1297 1298 1299 1300 1301 1302
};

DECLARE_PER_CPU(struct softnet_data,softnet_data);

#define HAVE_NETIF_QUEUE

1303
extern void __netif_schedule(struct Qdisc *q);
L
Linus Torvalds 已提交
1304

1305
static inline void netif_schedule_queue(struct netdev_queue *txq)
L
Linus Torvalds 已提交
1306
{
1307
	if (!test_bit(__QUEUE_STATE_XOFF, &txq->state))
1308
		__netif_schedule(txq->qdisc);
1309 1310
}

1311 1312 1313 1314 1315 1316 1317 1318
static inline void netif_tx_schedule_all(struct net_device *dev)
{
	unsigned int i;

	for (i = 0; i < dev->num_tx_queues; i++)
		netif_schedule_queue(netdev_get_tx_queue(dev, i));
}

1319 1320 1321 1322 1323
static inline void netif_tx_start_queue(struct netdev_queue *dev_queue)
{
	clear_bit(__QUEUE_STATE_XOFF, &dev_queue->state);
}

1324 1325 1326 1327 1328 1329
/**
 *	netif_start_queue - allow transmit
 *	@dev: network device
 *
 *	Allow upper layers to call the device hard_start_xmit routine.
 */
L
Linus Torvalds 已提交
1330 1331
static inline void netif_start_queue(struct net_device *dev)
{
1332
	netif_tx_start_queue(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
1333 1334
}

1335 1336 1337 1338 1339 1340 1341 1342 1343 1344
static inline void netif_tx_start_all_queues(struct net_device *dev)
{
	unsigned int i;

	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
		netif_tx_start_queue(txq);
	}
}

1345
static inline void netif_tx_wake_queue(struct netdev_queue *dev_queue)
L
Linus Torvalds 已提交
1346 1347
{
#ifdef CONFIG_NETPOLL_TRAP
1348
	if (netpoll_trap()) {
1349
		netif_tx_start_queue(dev_queue);
L
Linus Torvalds 已提交
1350
		return;
1351
	}
L
Linus Torvalds 已提交
1352
#endif
1353
	if (test_and_clear_bit(__QUEUE_STATE_XOFF, &dev_queue->state))
1354
		__netif_schedule(dev_queue->qdisc);
1355 1356
}

1357 1358 1359 1360 1361 1362 1363
/**
 *	netif_wake_queue - restart transmit
 *	@dev: network device
 *
 *	Allow upper layers to call the device hard_start_xmit routine.
 *	Used for flow control when transmit resources are available.
 */
1364 1365
static inline void netif_wake_queue(struct net_device *dev)
{
1366
	netif_tx_wake_queue(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
1367 1368
}

1369 1370 1371 1372 1373 1374 1375 1376 1377 1378
static inline void netif_tx_wake_all_queues(struct net_device *dev)
{
	unsigned int i;

	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
		netif_tx_wake_queue(txq);
	}
}

1379 1380 1381 1382 1383
static inline void netif_tx_stop_queue(struct netdev_queue *dev_queue)
{
	set_bit(__QUEUE_STATE_XOFF, &dev_queue->state);
}

1384 1385 1386 1387 1388 1389 1390
/**
 *	netif_stop_queue - stop transmitted packets
 *	@dev: network device
 *
 *	Stop upper layers calling the device hard_start_xmit routine.
 *	Used for flow control when transmit resources are unavailable.
 */
L
Linus Torvalds 已提交
1391 1392
static inline void netif_stop_queue(struct net_device *dev)
{
1393
	netif_tx_stop_queue(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
1394 1395
}

1396 1397 1398 1399 1400 1401 1402 1403 1404 1405
static inline void netif_tx_stop_all_queues(struct net_device *dev)
{
	unsigned int i;

	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
		netif_tx_stop_queue(txq);
	}
}

1406 1407 1408 1409 1410
static inline int netif_tx_queue_stopped(const struct netdev_queue *dev_queue)
{
	return test_bit(__QUEUE_STATE_XOFF, &dev_queue->state);
}

1411 1412 1413 1414 1415 1416
/**
 *	netif_queue_stopped - test if transmit queue is flowblocked
 *	@dev: network device
 *
 *	Test if transmit queue on device is currently unable to send.
 */
L
Linus Torvalds 已提交
1417 1418
static inline int netif_queue_stopped(const struct net_device *dev)
{
1419
	return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
1420 1421
}

1422 1423 1424 1425 1426
static inline int netif_tx_queue_frozen(const struct netdev_queue *dev_queue)
{
	return test_bit(__QUEUE_STATE_FROZEN, &dev_queue->state);
}

1427 1428 1429 1430 1431 1432
/**
 *	netif_running - test if up
 *	@dev: network device
 *
 *	Test if the device has been brought up.
 */
L
Linus Torvalds 已提交
1433 1434 1435 1436 1437
static inline int netif_running(const struct net_device *dev)
{
	return test_bit(__LINK_STATE_START, &dev->state);
}

1438 1439 1440 1441 1442 1443
/*
 * Routines to manage the subqueues on a device.  We only need start
 * stop, and a check if it's stopped.  All other device management is
 * done at the overall netdevice level.
 * Also test the device if we're multiqueue.
 */
1444 1445 1446 1447 1448 1449 1450 1451

/**
 *	netif_start_subqueue - allow sending packets on subqueue
 *	@dev: network device
 *	@queue_index: sub queue index
 *
 * Start individual transmit queue of a device with multiple transmit queues.
 */
1452 1453
static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index)
{
1454
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
1455 1456

	netif_tx_start_queue(txq);
1457 1458
}

1459 1460 1461 1462 1463 1464 1465
/**
 *	netif_stop_subqueue - stop sending packets on subqueue
 *	@dev: network device
 *	@queue_index: sub queue index
 *
 * Stop individual transmit queue of a device with multiple transmit queues.
 */
1466 1467
static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index)
{
1468
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
1469 1470 1471 1472
#ifdef CONFIG_NETPOLL_TRAP
	if (netpoll_trap())
		return;
#endif
1473
	netif_tx_stop_queue(txq);
1474 1475
}

1476 1477 1478 1479 1480 1481 1482
/**
 *	netif_subqueue_stopped - test status of subqueue
 *	@dev: network device
 *	@queue_index: sub queue index
 *
 * Check individual transmit queue of a device with multiple transmit queues.
 */
1483
static inline int __netif_subqueue_stopped(const struct net_device *dev,
1484 1485
					 u16 queue_index)
{
1486
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
1487 1488

	return netif_tx_queue_stopped(txq);
1489 1490
}

1491 1492 1493 1494 1495
static inline int netif_subqueue_stopped(const struct net_device *dev,
					 struct sk_buff *skb)
{
	return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb));
}
1496 1497 1498 1499 1500 1501 1502 1503

/**
 *	netif_wake_subqueue - allow sending packets on subqueue
 *	@dev: network device
 *	@queue_index: sub queue index
 *
 * Resume individual transmit queue of a device with multiple transmit queues.
 */
1504 1505
static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
{
1506
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
1507 1508 1509 1510
#ifdef CONFIG_NETPOLL_TRAP
	if (netpoll_trap())
		return;
#endif
1511
	if (test_and_clear_bit(__QUEUE_STATE_XOFF, &txq->state))
1512
		__netif_schedule(txq->qdisc);
1513 1514
}

1515 1516 1517 1518 1519 1520
/**
 *	netif_is_multiqueue - test if device has multiple transmit queues
 *	@dev: network device
 *
 * Check if device has multiple transmit queues
 */
1521 1522
static inline int netif_is_multiqueue(const struct net_device *dev)
{
1523
	return (dev->num_tx_queues > 1);
1524
}
L
Linus Torvalds 已提交
1525 1526

/* Use this variant when it is known for sure that it
1527 1528
 * is executing from hardware interrupt context or with hardware interrupts
 * disabled.
L
Linus Torvalds 已提交
1529
 */
1530
extern void dev_kfree_skb_irq(struct sk_buff *skb);
L
Linus Torvalds 已提交
1531 1532

/* Use this variant in places where it could be invoked
1533 1534
 * from either hardware interrupt or other context, with hardware interrupts
 * either disabled or enabled.
L
Linus Torvalds 已提交
1535
 */
1536
extern void dev_kfree_skb_any(struct sk_buff *skb);
L
Linus Torvalds 已提交
1537 1538 1539 1540 1541 1542

#define HAVE_NETIF_RX 1
extern int		netif_rx(struct sk_buff *skb);
extern int		netif_rx_ni(struct sk_buff *skb);
#define HAVE_NETIF_RECEIVE_SKB 1
extern int		netif_receive_skb(struct sk_buff *skb);
1543
extern gro_result_t	dev_gro_receive(struct napi_struct *napi,
1544
					struct sk_buff *skb);
1545 1546
extern gro_result_t	napi_skb_finish(gro_result_t ret, struct sk_buff *skb);
extern gro_result_t	napi_gro_receive(struct napi_struct *napi,
1547
					 struct sk_buff *skb);
1548 1549
extern void		napi_reuse_skb(struct napi_struct *napi,
				       struct sk_buff *skb);
1550
extern struct sk_buff *	napi_get_frags(struct napi_struct *napi);
1551
extern gro_result_t	napi_frags_finish(struct napi_struct *napi,
1552 1553
					  struct sk_buff *skb,
					  gro_result_t ret);
1554
extern struct sk_buff *	napi_frags_skb(struct napi_struct *napi);
1555
extern gro_result_t	napi_gro_frags(struct napi_struct *napi);
1556 1557 1558 1559 1560 1561 1562

static inline void napi_free_frags(struct napi_struct *napi)
{
	kfree_skb(napi->skb);
	napi->skb = NULL;
}

1563
extern void		netif_nit_deliver(struct sk_buff *skb);
1564
extern int		dev_valid_name(const char *name);
1565 1566
extern int		dev_ioctl(struct net *net, unsigned int cmd, void __user *);
extern int		dev_ethtool(struct net *net, struct ifreq *);
L
Linus Torvalds 已提交
1567 1568
extern unsigned		dev_get_flags(const struct net_device *);
extern int		dev_change_flags(struct net_device *, unsigned);
1569
extern int		dev_change_name(struct net_device *, const char *);
1570
extern int		dev_set_alias(struct net_device *, const char *, size_t);
1571 1572
extern int		dev_change_net_namespace(struct net_device *,
						 struct net *, const char *);
L
Linus Torvalds 已提交
1573 1574 1575
extern int		dev_set_mtu(struct net_device *, int);
extern int		dev_set_mac_address(struct net_device *,
					    struct sockaddr *);
1576
extern int		dev_hard_start_xmit(struct sk_buff *skb,
1577 1578
					    struct net_device *dev,
					    struct netdev_queue *txq);
1579 1580
extern int		dev_forward_skb(struct net_device *dev,
					struct sk_buff *skb);
L
Linus Torvalds 已提交
1581

1582
extern int		netdev_budget;
L
Linus Torvalds 已提交
1583 1584 1585 1586

/* Called by rtnetlink.c:rtnl_unlock() */
extern void netdev_run_todo(void);

1587 1588 1589 1590
/**
 *	dev_put - release reference to device
 *	@dev: network device
 *
1591
 * Release reference to device to allow it to be freed.
1592
 */
L
Linus Torvalds 已提交
1593 1594 1595 1596 1597
static inline void dev_put(struct net_device *dev)
{
	atomic_dec(&dev->refcnt);
}

1598 1599 1600 1601
/**
 *	dev_hold - get reference to device
 *	@dev: network device
 *
1602
 * Hold reference to device to keep it from being freed.
1603
 */
1604 1605 1606 1607
static inline void dev_hold(struct net_device *dev)
{
	atomic_inc(&dev->refcnt);
}
L
Linus Torvalds 已提交
1608 1609 1610 1611

/* Carrier loss detection, dial on demand. The functions netif_carrier_on
 * and _off may be called from IRQ context, but it is caller
 * who is responsible for serialization of these calls.
S
Stefan Rompf 已提交
1612 1613 1614 1615
 *
 * The name carrier is inappropriate, these functions should really be
 * called netif_lowerlayer_*() because they represent the state of any
 * kind of lower layer not just hardware media.
L
Linus Torvalds 已提交
1616 1617 1618
 */

extern void linkwatch_fire_event(struct net_device *dev);
1619
extern void linkwatch_forget_dev(struct net_device *dev);
L
Linus Torvalds 已提交
1620

1621 1622 1623 1624 1625 1626
/**
 *	netif_carrier_ok - test if carrier present
 *	@dev: network device
 *
 * Check if carrier is present on device
 */
L
Linus Torvalds 已提交
1627 1628 1629 1630 1631
static inline int netif_carrier_ok(const struct net_device *dev)
{
	return !test_bit(__LINK_STATE_NOCARRIER, &dev->state);
}

1632 1633
extern unsigned long dev_trans_start(struct net_device *dev);

L
Linus Torvalds 已提交
1634 1635
extern void __netdev_watchdog_up(struct net_device *dev);

1636
extern void netif_carrier_on(struct net_device *dev);
L
Linus Torvalds 已提交
1637

1638
extern void netif_carrier_off(struct net_device *dev);
L
Linus Torvalds 已提交
1639

1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652
/**
 *	netif_dormant_on - mark device as dormant.
 *	@dev: network device
 *
 * Mark device as dormant (as per RFC2863).
 *
 * The dormant state indicates that the relevant interface is not
 * actually in a condition to pass packets (i.e., it is not 'up') but is
 * in a "pending" state, waiting for some external event.  For "on-
 * demand" interfaces, this new state identifies the situation where the
 * interface is waiting for events to place it in the up state.
 *
 */
S
Stefan Rompf 已提交
1653 1654 1655 1656 1657 1658
static inline void netif_dormant_on(struct net_device *dev)
{
	if (!test_and_set_bit(__LINK_STATE_DORMANT, &dev->state))
		linkwatch_fire_event(dev);
}

1659 1660 1661 1662 1663 1664
/**
 *	netif_dormant_off - set device as not dormant.
 *	@dev: network device
 *
 * Device is not in dormant state.
 */
S
Stefan Rompf 已提交
1665 1666 1667 1668 1669 1670
static inline void netif_dormant_off(struct net_device *dev)
{
	if (test_and_clear_bit(__LINK_STATE_DORMANT, &dev->state))
		linkwatch_fire_event(dev);
}

1671 1672 1673 1674 1675 1676
/**
 *	netif_dormant - test if carrier present
 *	@dev: network device
 *
 * Check if carrier is present on device
 */
S
Stefan Rompf 已提交
1677 1678 1679 1680 1681 1682
static inline int netif_dormant(const struct net_device *dev)
{
	return test_bit(__LINK_STATE_DORMANT, &dev->state);
}


1683 1684 1685 1686 1687 1688
/**
 *	netif_oper_up - test if device is operational
 *	@dev: network device
 *
 * Check if carrier is operational
 */
E
Eric Dumazet 已提交
1689 1690
static inline int netif_oper_up(const struct net_device *dev)
{
S
Stefan Rompf 已提交
1691 1692 1693 1694
	return (dev->operstate == IF_OPER_UP ||
		dev->operstate == IF_OPER_UNKNOWN /* backward compat */);
}

1695 1696 1697 1698 1699 1700
/**
 *	netif_device_present - is device available or removed
 *	@dev: network device
 *
 * Check if device has not been removed from system.
 */
L
Linus Torvalds 已提交
1701 1702 1703 1704 1705
static inline int netif_device_present(struct net_device *dev)
{
	return test_bit(__LINK_STATE_PRESENT, &dev->state);
}

1706
extern void netif_device_detach(struct net_device *dev);
L
Linus Torvalds 已提交
1707

1708
extern void netif_device_attach(struct net_device *dev);
L
Linus Torvalds 已提交
1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759

/*
 * Network interface message level settings
 */
#define HAVE_NETIF_MSG 1

enum {
	NETIF_MSG_DRV		= 0x0001,
	NETIF_MSG_PROBE		= 0x0002,
	NETIF_MSG_LINK		= 0x0004,
	NETIF_MSG_TIMER		= 0x0008,
	NETIF_MSG_IFDOWN	= 0x0010,
	NETIF_MSG_IFUP		= 0x0020,
	NETIF_MSG_RX_ERR	= 0x0040,
	NETIF_MSG_TX_ERR	= 0x0080,
	NETIF_MSG_TX_QUEUED	= 0x0100,
	NETIF_MSG_INTR		= 0x0200,
	NETIF_MSG_TX_DONE	= 0x0400,
	NETIF_MSG_RX_STATUS	= 0x0800,
	NETIF_MSG_PKTDATA	= 0x1000,
	NETIF_MSG_HW		= 0x2000,
	NETIF_MSG_WOL		= 0x4000,
};

#define netif_msg_drv(p)	((p)->msg_enable & NETIF_MSG_DRV)
#define netif_msg_probe(p)	((p)->msg_enable & NETIF_MSG_PROBE)
#define netif_msg_link(p)	((p)->msg_enable & NETIF_MSG_LINK)
#define netif_msg_timer(p)	((p)->msg_enable & NETIF_MSG_TIMER)
#define netif_msg_ifdown(p)	((p)->msg_enable & NETIF_MSG_IFDOWN)
#define netif_msg_ifup(p)	((p)->msg_enable & NETIF_MSG_IFUP)
#define netif_msg_rx_err(p)	((p)->msg_enable & NETIF_MSG_RX_ERR)
#define netif_msg_tx_err(p)	((p)->msg_enable & NETIF_MSG_TX_ERR)
#define netif_msg_tx_queued(p)	((p)->msg_enable & NETIF_MSG_TX_QUEUED)
#define netif_msg_intr(p)	((p)->msg_enable & NETIF_MSG_INTR)
#define netif_msg_tx_done(p)	((p)->msg_enable & NETIF_MSG_TX_DONE)
#define netif_msg_rx_status(p)	((p)->msg_enable & NETIF_MSG_RX_STATUS)
#define netif_msg_pktdata(p)	((p)->msg_enable & NETIF_MSG_PKTDATA)
#define netif_msg_hw(p)		((p)->msg_enable & NETIF_MSG_HW)
#define netif_msg_wol(p)	((p)->msg_enable & NETIF_MSG_WOL)

static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits)
{
	/* use default */
	if (debug_value < 0 || debug_value >= (sizeof(u32) * 8))
		return default_msg_enable_bits;
	if (debug_value == 0)	/* no output */
		return 0;
	/* set low N bits */
	return (1 << debug_value) - 1;
}

1760
static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
H
Herbert Xu 已提交
1761
{
1762 1763
	spin_lock(&txq->_xmit_lock);
	txq->xmit_lock_owner = cpu;
1764 1765
}

1766 1767 1768 1769 1770 1771
static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
{
	spin_lock_bh(&txq->_xmit_lock);
	txq->xmit_lock_owner = smp_processor_id();
}

1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791
static inline int __netif_tx_trylock(struct netdev_queue *txq)
{
	int ok = spin_trylock(&txq->_xmit_lock);
	if (likely(ok))
		txq->xmit_lock_owner = smp_processor_id();
	return ok;
}

static inline void __netif_tx_unlock(struct netdev_queue *txq)
{
	txq->xmit_lock_owner = -1;
	spin_unlock(&txq->_xmit_lock);
}

static inline void __netif_tx_unlock_bh(struct netdev_queue *txq)
{
	txq->xmit_lock_owner = -1;
	spin_unlock_bh(&txq->_xmit_lock);
}

E
Eric Dumazet 已提交
1792 1793 1794 1795 1796 1797
static inline void txq_trans_update(struct netdev_queue *txq)
{
	if (txq->xmit_lock_owner != -1)
		txq->trans_start = jiffies;
}

1798 1799 1800 1801 1802 1803
/**
 *	netif_tx_lock - grab network device transmit lock
 *	@dev: network device
 *
 * Get network device transmit lock
 */
1804 1805
static inline void netif_tx_lock(struct net_device *dev)
{
1806
	unsigned int i;
1807
	int cpu;
1808

1809 1810
	spin_lock(&dev->tx_global_lock);
	cpu = smp_processor_id();
1811 1812
	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
1813 1814 1815 1816 1817 1818 1819

		/* We are the only thread of execution doing a
		 * freeze, but we have to grab the _xmit_lock in
		 * order to synchronize with threads which are in
		 * the ->hard_start_xmit() handler and already
		 * checked the frozen bit.
		 */
1820
		__netif_tx_lock(txq, cpu);
1821 1822
		set_bit(__QUEUE_STATE_FROZEN, &txq->state);
		__netif_tx_unlock(txq);
1823
	}
H
Herbert Xu 已提交
1824 1825 1826 1827
}

static inline void netif_tx_lock_bh(struct net_device *dev)
{
1828 1829
	local_bh_disable();
	netif_tx_lock(dev);
H
Herbert Xu 已提交
1830 1831 1832 1833
}

static inline void netif_tx_unlock(struct net_device *dev)
{
1834 1835 1836 1837
	unsigned int i;

	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
1838

1839 1840 1841 1842 1843
		/* No need to grab the _xmit_lock here.  If the
		 * queue is not stopped for another reason, we
		 * force a schedule.
		 */
		clear_bit(__QUEUE_STATE_FROZEN, &txq->state);
1844
		netif_schedule_queue(txq);
1845 1846
	}
	spin_unlock(&dev->tx_global_lock);
H
Herbert Xu 已提交
1847 1848 1849 1850
}

static inline void netif_tx_unlock_bh(struct net_device *dev)
{
1851 1852
	netif_tx_unlock(dev);
	local_bh_enable();
H
Herbert Xu 已提交
1853 1854
}

1855
#define HARD_TX_LOCK(dev, txq, cpu) {			\
1856
	if ((dev->features & NETIF_F_LLTX) == 0) {	\
1857
		__netif_tx_lock(txq, cpu);		\
1858 1859 1860
	}						\
}

1861
#define HARD_TX_UNLOCK(dev, txq) {			\
1862
	if ((dev->features & NETIF_F_LLTX) == 0) {	\
1863
		__netif_tx_unlock(txq);			\
1864 1865 1866
	}						\
}

L
Linus Torvalds 已提交
1867 1868
static inline void netif_tx_disable(struct net_device *dev)
{
1869
	unsigned int i;
1870
	int cpu;
1871

1872 1873
	local_bh_disable();
	cpu = smp_processor_id();
1874 1875
	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
1876 1877

		__netif_tx_lock(txq, cpu);
1878
		netif_tx_stop_queue(txq);
1879
		__netif_tx_unlock(txq);
1880
	}
1881
	local_bh_enable();
L
Linus Torvalds 已提交
1882 1883
}

1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903
static inline void netif_addr_lock(struct net_device *dev)
{
	spin_lock(&dev->addr_list_lock);
}

static inline void netif_addr_lock_bh(struct net_device *dev)
{
	spin_lock_bh(&dev->addr_list_lock);
}

static inline void netif_addr_unlock(struct net_device *dev)
{
	spin_unlock(&dev->addr_list_lock);
}

static inline void netif_addr_unlock_bh(struct net_device *dev)
{
	spin_unlock_bh(&dev->addr_list_lock);
}

1904
/*
1905
 * dev_addrs walker. Should be used only for read access. Call with
1906 1907 1908
 * rcu_read_lock held.
 */
#define for_each_dev_addr(dev, ha) \
1909
		list_for_each_entry_rcu(ha, &dev->dev_addrs.list, list)
1910

L
Linus Torvalds 已提交
1911 1912 1913 1914 1915
/* These functions live elsewhere (drivers/net/net_init.c, but related) */

extern void		ether_setup(struct net_device *dev);

/* Support for loadable net-drivers */
1916 1917 1918 1919 1920
extern struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
				       void (*setup)(struct net_device *),
				       unsigned int queue_count);
#define alloc_netdev(sizeof_priv, name, setup) \
	alloc_netdev_mq(sizeof_priv, name, setup, 1)
L
Linus Torvalds 已提交
1921 1922
extern int		register_netdev(struct net_device *dev);
extern void		unregister_netdev(struct net_device *dev);
1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935

/* Functions used for device addresses handling */
extern int dev_addr_add(struct net_device *dev, unsigned char *addr,
			unsigned char addr_type);
extern int dev_addr_del(struct net_device *dev, unsigned char *addr,
			unsigned char addr_type);
extern int dev_addr_add_multiple(struct net_device *to_dev,
				 struct net_device *from_dev,
				 unsigned char addr_type);
extern int dev_addr_del_multiple(struct net_device *to_dev,
				 struct net_device *from_dev,
				 unsigned char addr_type);

1936 1937 1938
/* Functions used for secondary unicast and multicast support */
extern void		dev_set_rx_mode(struct net_device *dev);
extern void		__dev_set_rx_mode(struct net_device *dev);
J
Jiri Pirko 已提交
1939 1940
extern int		dev_unicast_delete(struct net_device *dev, void *addr);
extern int		dev_unicast_add(struct net_device *dev, void *addr);
1941 1942
extern int		dev_unicast_sync(struct net_device *to, struct net_device *from);
extern void		dev_unicast_unsync(struct net_device *to, struct net_device *from);
L
Linus Torvalds 已提交
1943 1944
extern int 		dev_mc_delete(struct net_device *dev, void *addr, int alen, int all);
extern int		dev_mc_add(struct net_device *dev, void *addr, int alen, int newonly);
1945 1946
extern int		dev_mc_sync(struct net_device *to, struct net_device *from);
extern void		dev_mc_unsync(struct net_device *to, struct net_device *from);
1947 1948
extern int 		__dev_addr_delete(struct dev_addr_list **list, int *count, void *addr, int alen, int all);
extern int		__dev_addr_add(struct dev_addr_list **list, int *count, void *addr, int alen, int newonly);
1949 1950
extern int		__dev_addr_sync(struct dev_addr_list **to, int *to_count, struct dev_addr_list **from, int *from_count);
extern void		__dev_addr_unsync(struct dev_addr_list **to, int *to_count, struct dev_addr_list **from, int *from_count);
1951 1952
extern int		dev_set_promiscuity(struct net_device *dev, int inc);
extern int		dev_set_allmulti(struct net_device *dev, int inc);
L
Linus Torvalds 已提交
1953
extern void		netdev_state_change(struct net_device *dev);
1954 1955
extern void		netdev_bonding_change(struct net_device *dev,
					      unsigned long event);
1956
extern void		netdev_features_change(struct net_device *dev);
L
Linus Torvalds 已提交
1957
/* Load a device via the kmod */
1958
extern void		dev_load(struct net *net, const char *name);
L
Linus Torvalds 已提交
1959
extern void		dev_mcast_init(void);
1960
extern const struct net_device_stats *dev_get_stats(struct net_device *dev);
1961
extern void		dev_txq_stats_fold(const struct net_device *dev, struct net_device_stats *stats);
1962

L
Linus Torvalds 已提交
1963 1964 1965
extern int		netdev_max_backlog;
extern int		weight_p;
extern int		netdev_set_master(struct net_device *dev, struct net_device *master);
1966
extern int skb_checksum_help(struct sk_buff *skb);
1967
extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features);
1968 1969 1970 1971 1972 1973 1974
#ifdef CONFIG_BUG
extern void netdev_rx_csum_fault(struct net_device *dev);
#else
static inline void netdev_rx_csum_fault(struct net_device *dev)
{
}
#endif
L
Linus Torvalds 已提交
1975 1976 1977 1978
/* rx skb timestamps */
extern void		net_enable_timestamp(void);
extern void		net_disable_timestamp(void);

1979 1980 1981 1982 1983 1984
#ifdef CONFIG_PROC_FS
extern void *dev_seq_start(struct seq_file *seq, loff_t *pos);
extern void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos);
extern void dev_seq_stop(struct seq_file *seq, void *v);
#endif

1985 1986 1987
extern int netdev_class_create_file(struct class_attribute *class_attr);
extern void netdev_class_remove_file(struct class_attribute *class_attr);

1988
extern char *netdev_drivername(const struct net_device *dev, char *buffer, int len);
1989

1990 1991
extern void linkwatch_run_queue(void);

1992 1993 1994
unsigned long netdev_increment_features(unsigned long all, unsigned long one,
					unsigned long mask);
unsigned long netdev_fix_features(unsigned long features, const char *name);
1995

1996 1997 1998
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
					struct net_device *dev);

1999
static inline int net_gso_ok(int features, int gso_type)
2000
{
2001
	int feature = gso_type << NETIF_F_GSO_SHIFT;
2002
	return (features & feature) == feature;
2003 2004
}

2005 2006
static inline int skb_gso_ok(struct sk_buff *skb, int features)
{
H
Herbert Xu 已提交
2007
	return net_gso_ok(features, skb_shinfo(skb)->gso_type) &&
2008
	       (!skb_has_frags(skb) || (features & NETIF_F_FRAGLIST));
2009 2010
}

2011 2012
static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb)
{
2013 2014
	return skb_is_gso(skb) &&
	       (!skb_gso_ok(skb, dev->features) ||
2015
		unlikely(skb->ip_summed != CHECKSUM_PARTIAL));
2016 2017
}

2018 2019 2020 2021 2022 2023
static inline void netif_set_gso_max_size(struct net_device *dev,
					  unsigned int size)
{
	dev->gso_max_size = size;
}

2024 2025 2026 2027 2028 2029 2030 2031 2032 2033
static inline void skb_bond_set_mac_by_master(struct sk_buff *skb,
					      struct net_device *master)
{
	if (skb->pkt_type == PACKET_HOST) {
		u16 *dest = (u16 *) eth_hdr(skb)->h_dest;

		memcpy(dest, master->dev_addr, ETH_ALEN);
	}
}

2034
/* On bonding slaves other than the currently active slave, suppress
2035 2036
 * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and
 * ARP on active-backup slaves with arp_validate enabled.
2037 2038 2039 2040 2041 2042
 */
static inline int skb_bond_should_drop(struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	struct net_device *master = dev->master;

2043 2044 2045 2046
	if (master) {
		if (master->priv_flags & IFF_MASTER_ARPMON)
			dev->last_rx = jiffies;

2047 2048 2049 2050 2051 2052 2053 2054
		if ((master->priv_flags & IFF_MASTER_ALB) && master->br_port) {
			/* Do address unmangle. The local destination address
			 * will be always the one master has. Provides the right
			 * functionality in a bridge.
			 */
			skb_bond_set_mac_by_master(skb, master);
		}

2055 2056
		if (dev->priv_flags & IFF_SLAVE_INACTIVE) {
			if ((dev->priv_flags & IFF_SLAVE_NEEDARP) &&
2057
			    skb->protocol == __cpu_to_be16(ETH_P_ARP))
2058 2059
				return 0;

2060 2061 2062 2063 2064 2065
			if (master->priv_flags & IFF_MASTER_ALB) {
				if (skb->pkt_type != PACKET_BROADCAST &&
				    skb->pkt_type != PACKET_MULTICAST)
					return 0;
			}
			if (master->priv_flags & IFF_MASTER_8023AD &&
2066
			    skb->protocol == __cpu_to_be16(ETH_P_SLOW))
2067 2068 2069 2070
				return 0;

			return 1;
		}
2071 2072 2073 2074
	}
	return 0;
}

2075
extern struct pernet_operations __net_initdata loopback_net_ops;
2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097

static inline int dev_ethtool_get_settings(struct net_device *dev,
					   struct ethtool_cmd *cmd)
{
	if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings)
		return -EOPNOTSUPP;
	return dev->ethtool_ops->get_settings(dev, cmd);
}

static inline u32 dev_ethtool_get_rx_csum(struct net_device *dev)
{
	if (!dev->ethtool_ops || !dev->ethtool_ops->get_rx_csum)
		return 0;
	return dev->ethtool_ops->get_rx_csum(dev);
}

static inline u32 dev_ethtool_get_flags(struct net_device *dev)
{
	if (!dev->ethtool_ops || !dev->ethtool_ops->get_flags)
		return 0;
	return dev->ethtool_ops->get_flags(dev);
}
2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168

/* Logging, debugging and troubleshooting/diagnostic helpers. */

/* netdev_printk helpers, similar to dev_printk */

static inline const char *netdev_name(const struct net_device *dev)
{
	if (dev->reg_state != NETREG_REGISTERED)
		return "(unregistered net_device)";
	return dev->name;
}

#define netdev_printk(level, netdev, format, args...)		\
	dev_printk(level, (netdev)->dev.parent,			\
		   "%s: " format,				\
		   netdev_name(netdev), ##args)

#define netdev_emerg(dev, format, args...)			\
	netdev_printk(KERN_EMERG, dev, format, ##args)
#define netdev_alert(dev, format, args...)			\
	netdev_printk(KERN_ALERT, dev, format, ##args)
#define netdev_crit(dev, format, args...)			\
	netdev_printk(KERN_CRIT, dev, format, ##args)
#define netdev_err(dev, format, args...)			\
	netdev_printk(KERN_ERR, dev, format, ##args)
#define netdev_warn(dev, format, args...)			\
	netdev_printk(KERN_WARNING, dev, format, ##args)
#define netdev_notice(dev, format, args...)			\
	netdev_printk(KERN_NOTICE, dev, format, ##args)
#define netdev_info(dev, format, args...)			\
	netdev_printk(KERN_INFO, dev, format, ##args)

#if defined(DEBUG)
#define netdev_dbg(__dev, format, args...)			\
	netdev_printk(KERN_DEBUG, __dev, format, ##args)
#elif defined(CONFIG_DYNAMIC_DEBUG)
#define netdev_dbg(__dev, format, args...)			\
do {								\
	dynamic_dev_dbg((__dev)->dev.parent, "%s: " format,	\
			netdev_name(__dev), ##args);		\
} while (0)
#else
#define netdev_dbg(__dev, format, args...)			\
({								\
	if (0)							\
		netdev_printk(KERN_DEBUG, __dev, format, ##args); \
	0;							\
})
#endif

#if defined(VERBOSE_DEBUG)
#define netdev_vdbg	netdev_dbg
#else

#define netdev_vdbg(dev, format, args...)			\
({								\
	if (0)							\
		netdev_printk(KERN_DEBUG, dev, format, ##args);	\
	0;							\
})
#endif

/*
 * netdev_WARN() acts like dev_printk(), but with the key difference
 * of using a WARN/WARN_ON to get the message out, including the
 * file/line information and a backtrace.
 */
#define netdev_WARN(dev, format, args...)			\
	WARN(1, "netdevice: %s\n" format, netdev_name(dev), ##args);


L
Linus Torvalds 已提交
2169 2170
#endif /* __KERNEL__ */

2171
#endif	/* _LINUX_NETDEVICE_H */