netdevice.h 62.4 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)

E
Eric Dumazet 已提交
271
struct hh_cache {
L
Linus Torvalds 已提交
272 273
	struct hh_cache *hh_next;	/* Next entry			     */
	atomic_t	hh_refcnt;	/* number of users                   */
274 275 276 277 278 279 280 281
/*
 * 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
282 283 284
                                         *  NOTE:  For VLANs, this will be the
                                         *  encapuslated type. --BLG
                                         */
285
	u16		hh_len;		/* length of header */
L
Linus Torvalds 已提交
286
	int		(*hh_output)(struct sk_buff *skb);
287
	seqlock_t	hh_lock;
L
Linus Torvalds 已提交
288 289 290 291

	/* cached hardware header; allow for machine alignment needs.        */
#define HH_DATA_MOD	16
#define HH_DATA_OFF(__len) \
J
Jiri Benc 已提交
292
	(HH_DATA_MOD - (((__len - 1) & (HH_DATA_MOD - 1)) + 1))
L
Linus Torvalds 已提交
293 294 295 296 297 298 299 300 301 302 303 304
#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.
305 306 307
 *
 * LL_ALLOCATED_SPACE also takes into account the tailroom the device
 * may need.
L
Linus Torvalds 已提交
308 309
 */
#define LL_RESERVED_SPACE(dev) \
310
	((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
L
Linus Torvalds 已提交
311
#define LL_RESERVED_SPACE_EXTRA(dev,extra) \
312 313 314
	((((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
315

316 317 318 319 320 321 322 323 324 325 326 327 328
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
329 330 331 332 333
/* 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
334
enum netdev_state_t {
L
Linus Torvalds 已提交
335 336 337
	__LINK_STATE_START,
	__LINK_STATE_PRESENT,
	__LINK_STATE_NOCARRIER,
S
Stefan Rompf 已提交
338 339
	__LINK_STATE_LINKWATCH_PENDING,
	__LINK_STATE_DORMANT,
L
Linus Torvalds 已提交
340 341 342 343 344
};


/*
 * This structure holds at boot time configured netdevice settings. They
G
Graf Yang 已提交
345
 * are then used in the device probing.
L
Linus Torvalds 已提交
346 347 348 349 350 351 352
 */
struct netdev_boot_setup {
	char name[IFNAMSIZ];
	struct ifmap map;
};
#define NETDEV_BOOT_SETUP_MAX 8

353
extern int __init netdev_boot_setup(char *str);
L
Linus Torvalds 已提交
354

355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373
/*
 * 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
374 375 376

	unsigned int		gro_count;

H
Herbert Xu 已提交
377
	struct net_device	*dev;
378 379
	struct list_head	dev_list;
	struct sk_buff		*gro_list;
H
Herbert Xu 已提交
380
	struct sk_buff		*skb;
381 382
};

E
Eric Dumazet 已提交
383
enum {
384
	NAPI_STATE_SCHED,	/* Poll is scheduled */
D
David S. Miller 已提交
385
	NAPI_STATE_DISABLE,	/* Disable pending */
386
	NAPI_STATE_NPSVC,	/* Netpoll - don't dequeue from poll_list */
387 388
};

389
enum gro_result {
390 391 392 393 394 395
	GRO_MERGED,
	GRO_MERGED_FREE,
	GRO_HELD,
	GRO_NORMAL,
	GRO_DROP,
};
396
typedef enum gro_result gro_result_t;
397

398
extern void __napi_schedule(struct napi_struct *n);
399

D
David S. Miller 已提交
400 401 402 403 404
static inline int napi_disable_pending(struct napi_struct *n)
{
	return test_bit(NAPI_STATE_DISABLE, &n->state);
}

405 406 407 408 409 410
/**
 *	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
411 412
 * insure only one NAPI poll instance runs.  We also make
 * sure there is no pending NAPI disable.
413 414 415
 */
static inline int napi_schedule_prep(struct napi_struct *n)
{
D
David S. Miller 已提交
416 417
	return !napi_disable_pending(n) &&
		!test_and_set_bit(NAPI_STATE_SCHED, &n->state);
418 419 420 421 422 423 424 425 426 427 428 429 430 431 432
}

/**
 *	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);
}

433 434 435 436 437 438 439 440 441 442
/* 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;
}

443 444 445 446 447 448
/**
 *	napi_complete - NAPI processing complete
 *	@n: napi context
 *
 * Mark NAPI processing as complete.
 */
449 450
extern void __napi_complete(struct napi_struct *n);
extern void napi_complete(struct napi_struct *n);
451 452 453 454 455 456 457 458 459 460

/**
 *	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
461
	set_bit(NAPI_STATE_DISABLE, &n->state);
462
	while (test_and_set_bit(NAPI_STATE_SCHED, &n->state))
463
		msleep(1);
D
David S. Miller 已提交
464
	clear_bit(NAPI_STATE_DISABLE, &n->state);
465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480
}

/**
 *	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);
}

481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498
#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
499
enum netdev_queue_state_t {
500
	__QUEUE_STATE_XOFF,
501
	__QUEUE_STATE_FROZEN,
502 503
};

504
struct netdev_queue {
505 506 507
/*
 * read mostly part
 */
508
	struct net_device	*dev;
509
	struct Qdisc		*qdisc;
510
	unsigned long		state;
511
	struct Qdisc		*qdisc_sleeping;
512 513 514 515 516
/*
 * write mostly part
 */
	spinlock_t		_xmit_lock ____cacheline_aligned_in_smp;
	int			xmit_lock_owner;
517 518 519 520
	/*
	 * please use this field instead of dev->trans_start
	 */
	unsigned long		trans_start;
521 522 523
	unsigned long		tx_bytes;
	unsigned long		tx_packets;
	unsigned long		tx_dropped;
524
} ____cacheline_aligned_in_smp;
525

526 527 528

/*
 * This structure defines the management hooks for network devices.
529 530
 * The following hooks can be defined; unless noted otherwise, they are
 * optional and can be filled with a null pointer.
531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549
 *
 * 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.
 *
550 551
 * netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb,
 *                               struct net_device *dev);
552
 *	Called when a packet needs to be transmitted.
553 554
 *	Must return NETDEV_TX_OK , NETDEV_TX_BUSY.
 *        (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
555 556 557 558 559 560
 *	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.
 *
561 562 563 564 565 566 567 568 569 570 571 572
 * 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
573
 *	needs to be changed. If this interface is not defined, the
574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593
 *	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.
 *
594
 * void (*ndo_tx_timeout)(struct net_device *dev);
595 596 597
 *	Callback uses when the transmitter has not made any progress
 *	for dev->watchdog ticks.
 *
598
 * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618
 *	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);
 */
619
#define HAVE_NET_DEVICE_OPS
620 621 622 623 624
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);
625
	netdev_tx_t		(*ndo_start_xmit) (struct sk_buff *skb,
626 627 628
						   struct net_device *dev);
	u16			(*ndo_select_queue)(struct net_device *dev,
						    struct sk_buff *skb);
629 630 631 632 633 634 635 636 637 638 639
	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);
640 641 642 643
	int			(*ndo_change_mtu)(struct net_device *dev,
						  int new_mtu);
	int			(*ndo_neigh_setup)(struct net_device *dev,
						   struct neigh_parms *);
644 645 646 647 648 649 650 651 652 653 654 655 656
	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
657
#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
658 659
	int			(*ndo_fcoe_enable)(struct net_device *dev);
	int			(*ndo_fcoe_disable)(struct net_device *dev);
660 661 662 663 664 665
	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);
666 667 668 669
#define NETDEV_FCOE_WWNN 0
#define NETDEV_FCOE_WWPN 1
	int			(*ndo_fcoe_get_wwn)(struct net_device *dev,
						    u64 *wwn, int type);
670
#endif
671 672
};

L
Linus Torvalds 已提交
673 674 675 676 677 678 679 680 681 682
/*
 *	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
683
struct net_device {
L
Linus Torvalds 已提交
684 685 686 687 688 689 690

	/*
	 * 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];
691 692
	/* device name hash chain */
	struct hlist_node	name_hlist;
693 694
	/* snmp alias */
	char 			*ifalias;
L
Linus Torvalds 已提交
695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714

	/*
	 *	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;

715
	struct list_head	dev_list;
716
	struct list_head	napi_list;
717
	struct list_head	unreg_list;
L
Linus Torvalds 已提交
718

719 720 721
	/* Net device features */
	unsigned long		features;
#define NETIF_F_SG		1	/* Scatter/gather IO. */
722
#define NETIF_F_IP_CSUM		2	/* Can checksum TCP/UDP over IPv4. */
723 724
#define NETIF_F_NO_CSUM		4	/* Does not require checksum. F.e. loopack. */
#define NETIF_F_HW_CSUM		8	/* Can checksum all the packets. */
725
#define NETIF_F_IPV6_CSUM	16	/* Can checksum TCP/UDP over IPV6 */
726 727 728 729 730 731
#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
732
#define NETIF_F_GSO		2048	/* Enable software GSO. */
733 734
#define NETIF_F_LLTX		4096	/* LockLess TX - deprecated. Please */
					/* do not use LLTX in new drivers */
735
#define NETIF_F_NETNS_LOCAL	8192	/* Does not change network namespaces */
736
#define NETIF_F_GRO		16384	/* Generic receive offload */
737
#define NETIF_F_LRO		32768	/* large receive offload */
738

739
/* the GSO_MASK reserves bits 16 through 23 */
740
#define NETIF_F_FCOE_CRC	(1 << 24) /* FCoE CRC32 */
741
#define NETIF_F_SCTP_CSUM	(1 << 25) /* SCTP checksum offload */
742
#define NETIF_F_FCOE_MTU	(1 << 26) /* Supports max FCoE MTU, 2158 bytes*/
743

744
	/* Segmentation offload features */
745
#define NETIF_F_GSO_SHIFT	16
746
#define NETIF_F_GSO_MASK	0x00ff0000
747
#define NETIF_F_TSO		(SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT)
H
Herbert Xu 已提交
748
#define NETIF_F_UFO		(SKB_GSO_UDP << NETIF_F_GSO_SHIFT)
749
#define NETIF_F_GSO_ROBUST	(SKB_GSO_DODGY << NETIF_F_GSO_SHIFT)
H
Herbert Xu 已提交
750 751
#define NETIF_F_TSO_ECN		(SKB_GSO_TCP_ECN << NETIF_F_GSO_SHIFT)
#define NETIF_F_TSO6		(SKB_GSO_TCPV6 << NETIF_F_GSO_SHIFT)
752
#define NETIF_F_FSO		(SKB_GSO_FCOE << NETIF_F_GSO_SHIFT)
753

754 755 756
	/* List of features with software fallbacks. */
#define NETIF_F_GSO_SOFTWARE	(NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6)

757

758
#define NETIF_F_GEN_CSUM	(NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)
759 760 761
#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)
762

763 764 765 766 767
	/*
	 * 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 | \
768
				 NETIF_F_SG | NETIF_F_HIGHDMA |		\
769 770
				 NETIF_F_FRAGLIST)

L
Linus Torvalds 已提交
771 772 773 774
	/* Interface index. Unique device identifier	*/
	int			ifindex;
	int			iflink;

R
Rusty Russell 已提交
775
	struct net_device_stats	stats;
L
Linus Torvalds 已提交
776

777
#ifdef CONFIG_WIRELESS_EXT
L
Linus Torvalds 已提交
778 779 780 781 782
	/* 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;
783
#endif
784 785
	/* Management operations */
	const struct net_device_ops *netdev_ops;
786
	const struct ethtool_ops *ethtool_ops;
L
Linus Torvalds 已提交
787

788 789 790
	/* Hardware header description */
	const struct header_ops *header_ops;

S
Stefan Rompf 已提交
791
	unsigned int		flags;	/* interface flags (a la BSD)	*/
L
Linus Torvalds 已提交
792 793 794 795
	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
796 797 798
	unsigned char		operstate; /* RFC2863 operstate */
	unsigned char		link_mode; /* mapping policy to operstate */

L
Linus Torvalds 已提交
799 800 801 802
	unsigned		mtu;	/* interface MTU value		*/
	unsigned short		type;	/* interface hardware type	*/
	unsigned short		hard_header_len;	/* hardware hdr length	*/

803 804 805 806 807 808 809
	/* 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
810 811 812 813 814
	struct net_device	*master; /* Pointer to master device of a group,
					  * which this device is member of.
					  */

	/* Interface address info. */
815
	unsigned char		perm_addr[MAX_ADDR_LEN]; /* permanent hw address */
L
Linus Torvalds 已提交
816 817 818
	unsigned char		addr_len;	/* hardware address length	*/
	unsigned short          dev_id;		/* for shared network cards */

819 820
	struct netdev_hw_addr_list	uc;	/* Secondary unicast
						   mac addresses */
821
	int			uc_promisc;
J
Jiri Pirko 已提交
822
	spinlock_t		addr_list_lock;
823
	struct dev_addr_list	*mc_list;	/* Multicast mac addresses	*/
L
Linus Torvalds 已提交
824
	int			mc_count;	/* Number of installed mcasts	*/
825 826
	unsigned int		promiscuity;
	unsigned int		allmulti;
L
Linus Torvalds 已提交
827 828 829 830


	/* Protocol specific pointers */
	
831 832 833
#ifdef CONFIG_NET_DSA
	void			*dsa_ptr;	/* dsa specific data */
#endif
L
Linus Torvalds 已提交
834
	void 			*atalk_ptr;	/* AppleTalk link 	*/
G
Graf Yang 已提交
835
	void			*ip_ptr;	/* IPv4 specific data	*/
L
Linus Torvalds 已提交
836 837 838 839
	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 */
840 841
	struct wireless_dev	*ieee80211_ptr;	/* IEEE 802.11 specific data,
						   assign before registering */
L
Linus Torvalds 已提交
842

843 844 845 846 847
/*
 * 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() */
848 849 850 851
	unsigned char		*dev_addr;	/* hw address, (before bcast
						   because most packets are
						   unicast) */

852 853
	struct netdev_hw_addr_list	dev_addrs; /* list of device
						      hw addresses */
854 855

	unsigned char		broadcast[MAX_ADDR_LEN];	/* hw bcast add	*/
L
Linus Torvalds 已提交
856

857
	struct netdev_queue	rx_queue;
858 859

	struct netdev_queue	*_tx ____cacheline_aligned_in_smp;
860 861

	/* Number of TX queues allocated at alloc_netdev_mq() time  */
862
	unsigned int		num_tx_queues;
863 864 865 866

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

867 868 869
	/* root qdisc from userspace point of view */
	struct Qdisc		*qdisc;

L
Linus Torvalds 已提交
870
	unsigned long		tx_queue_len;	/* Max frames per queue allowed */
871
	spinlock_t		tx_global_lock;
872 873 874 875
/*
 * One part is mostly used on xmit path (device)
 */
	/* These may be needed for future network-power-down code. */
876 877 878 879 880

	/*
	 * trans_start here is expensive for high speed devices on SMP,
	 * please use netdev_queue->trans_start instead.
	 */
881 882 883 884 885
	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
886
	/* Number of references to this device */
887 888
	atomic_t		refcnt ____cacheline_aligned_in_smp;

L
Linus Torvalds 已提交
889 890 891 892 893
	/* delayed register/unregister */
	struct list_head	todo_list;
	/* device index hash chain */
	struct hlist_node	index_hlist;

894
	struct list_head	link_watch_list;
895

L
Linus Torvalds 已提交
896 897
	/* register/unregister state machine */
	enum { NETREG_UNINITIALIZED=0,
898
	       NETREG_REGISTERED,	/* completed register_netdevice */
L
Linus Torvalds 已提交
899 900 901
	       NETREG_UNREGISTERING,	/* called unregister_netdevice */
	       NETREG_UNREGISTERED,	/* completed unregister todo */
	       NETREG_RELEASED,		/* called free_netdev */
902
	       NETREG_DUMMY,		/* dummy device for NAPI poll */
L
Linus Torvalds 已提交
903 904
	} reg_state;

905 906
	/* Called from unregister, can be used to call free_netdev */
	void (*destructor)(struct net_device *dev);
L
Linus Torvalds 已提交
907 908

#ifdef CONFIG_NETPOLL
909
	struct netpoll_info	*npinfo;
L
Linus Torvalds 已提交
910
#endif
911

912
#ifdef CONFIG_NET_NS
913 914
	/* Network namespace this network device is inside */
	struct net		*nd_net;
915
#endif
916

D
David S. Miller 已提交
917 918 919
	/* mid-layer private */
	void			*ml_priv;

L
Linus Torvalds 已提交
920 921
	/* bridge stuff */
	struct net_bridge_port	*br_port;
P
Patrick McHardy 已提交
922 923
	/* macvlan */
	struct macvlan_port	*macvlan_port;
924 925
	/* GARP */
	struct garp_port	*garp_port;
L
Linus Torvalds 已提交
926 927

	/* class/net/name entry */
928
	struct device		dev;
929 930
	/* space for optional device, statistics, and wireless sysfs groups */
	const struct attribute_group *sysfs_groups[4];
P
Patrick McHardy 已提交
931 932 933

	/* rtnetlink link ops */
	const struct rtnl_link_ops *rtnl_link_ops;
934

935 936 937
	/* VLAN feature mask */
	unsigned long vlan_features;

938 939 940
	/* for setting kernel sock attribute on TCP connection setup */
#define GSO_MAX_SIZE		65536
	unsigned int		gso_max_size;
941

J
Jeff Kirsher 已提交
942
#ifdef CONFIG_DCB
943
	/* Data Center Bridging netlink ops */
944
	const struct dcbnl_rtnl_ops *dcbnl_ops;
945 946
#endif

947 948 949 950
#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
	/* max exchange id for FCoE LRO by ddp */
	unsigned int		fcoe_ddp_xid;
#endif
L
Linus Torvalds 已提交
951
};
952
#define to_net_dev(d) container_of(d, struct net_device, dev)
L
Linus Torvalds 已提交
953 954 955

#define	NETDEV_ALIGN		32

956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974
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);
}

975 976 977 978 979 980 981 982 983 984 985 986 987 988
/*
 * 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
989
void dev_net_set(struct net_device *dev, struct net *net)
990 991
{
#ifdef CONFIG_NET_NS
992 993
	release_net(dev->nd_net);
	dev->nd_net = hold_net(net);
994 995 996
#endif
}

997 998 999 1000 1001 1002 1003 1004 1005 1006
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;
}

1007 1008 1009 1010 1011 1012 1013 1014 1015
#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

1016 1017 1018 1019 1020 1021 1022 1023 1024 1025
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;
}

1026 1027 1028 1029 1030 1031
/**
 *	netdev_priv - access network device private data
 *	@dev: network device
 *
 * Get network device private data
 */
1032
static inline void *netdev_priv(const struct net_device *dev)
L
Linus Torvalds 已提交
1033
{
1034
	return (char *)dev + ALIGN(sizeof(struct net_device), NETDEV_ALIGN);
L
Linus Torvalds 已提交
1035 1036 1037 1038 1039
}

/* Set the sysfs physical device reference for the network logical device
 * if set prior to registration will cause a symlink during initialization.
 */
1040
#define SET_NETDEV_DEV(net, pdev)	((net)->dev.parent = (pdev))
L
Linus Torvalds 已提交
1041

1042 1043 1044 1045 1046 1047
/* 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))

1048 1049 1050 1051 1052 1053 1054 1055 1056 1057
/**
 *	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.
 */
1058 1059
void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
		    int (*poll)(struct napi_struct *, int), int weight);
1060

1061 1062 1063 1064 1065 1066
/**
 *  netif_napi_del - remove a napi context
 *  @napi: napi context
 *
 *  netif_napi_del() removes a napi context from the network device napi list
 */
1067 1068 1069
void netif_napi_del(struct napi_struct *napi);

struct napi_gro_cb {
1070 1071 1072
	/* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */
	void *frag0;

1073 1074 1075
	/* Length of frag0. */
	unsigned int frag0_len;

1076 1077 1078
	/* This indicates where we are processing relative to skb->data. */
	int data_offset;

1079 1080 1081 1082 1083 1084 1085 1086
	/* 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
1087 1088 1089

	/* Free the skb? */
	int free;
1090 1091 1092
};

#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
1093

L
Linus Torvalds 已提交
1094
struct packet_type {
D
David S. Miller 已提交
1095 1096 1097 1098 1099 1100
	__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 *);
1101 1102
	struct sk_buff		*(*gso_segment)(struct sk_buff *skb,
						int features);
1103
	int			(*gso_send_check)(struct sk_buff *skb);
1104 1105 1106
	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
1107 1108 1109 1110 1111 1112 1113 1114 1115
	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 */

1116

1117 1118
#define for_each_netdev(net, d)		\
		list_for_each_entry(d, &(net)->dev_base_head, dev_list)
1119 1120
#define for_each_netdev_reverse(net, d)	\
		list_for_each_entry_reverse(d, &(net)->dev_base_head, dev_list)
1121 1122
#define for_each_netdev_rcu(net, d)		\
		list_for_each_entry_rcu(d, &(net)->dev_base_head, dev_list)
1123 1124 1125 1126
#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)
1127 1128
#define for_each_netdev_continue_rcu(net, d)		\
	list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list)
1129
#define net_device_entry(lh)	list_entry(lh, struct net_device, dev_list)
1130

1131 1132 1133 1134 1135
static inline struct net_device *next_net_device(struct net_device *dev)
{
	struct list_head *lh;
	struct net *net;

1136
	net = dev_net(dev);
1137 1138 1139 1140
	lh = dev->dev_list.next;
	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
}

1141 1142 1143 1144 1145 1146 1147 1148 1149 1150
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);
}

1151 1152 1153 1154 1155
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);
}
1156

L
Linus Torvalds 已提交
1157 1158
extern int 			netdev_boot_setup_check(struct net_device *dev);
extern unsigned long		netdev_boot_base(const char *prefix, int unit);
1159 1160 1161
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
1162 1163 1164 1165
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);

1166
extern struct net_device	*dev_get_by_flags(struct net *net, unsigned short flags,
L
Linus Torvalds 已提交
1167
						  unsigned short mask);
1168
extern struct net_device	*dev_get_by_name(struct net *net, const char *name);
1169
extern struct net_device	*dev_get_by_name_rcu(struct net *net, const char *name);
1170
extern struct net_device	*__dev_get_by_name(struct net *net, const char *name);
L
Linus Torvalds 已提交
1171 1172 1173
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);
1174
extern void		dev_disable_lro(struct net_device *dev);
L
Linus Torvalds 已提交
1175 1176
extern int		dev_queue_xmit(struct sk_buff *skb);
extern int		register_netdevice(struct net_device *dev);
1177 1178
extern void		unregister_netdevice_queue(struct net_device *dev,
						   struct list_head *head);
1179
extern void		unregister_netdevice_many(struct list_head *head);
1180 1181 1182 1183 1184
static inline void unregister_netdevice(struct net_device *dev)
{
	unregister_netdevice_queue(dev, NULL);
}

L
Linus Torvalds 已提交
1185 1186 1187 1188
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);
1189
extern int		init_dummy_netdev(struct net_device *dev);
1190
extern void		netdev_resync_ops(struct net_device *dev);
1191

1192
extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
1193 1194
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);
1195
extern struct net_device	*dev_get_by_index_rcu(struct net *net, int ifindex);
L
Linus Torvalds 已提交
1196 1197 1198 1199
extern int		dev_restart(struct net_device *dev);
#ifdef CONFIG_NETPOLL_TRAP
extern int		netpoll_trap(void);
#endif
1200 1201
extern int	       skb_gro_receive(struct sk_buff **head,
				       struct sk_buff *skb);
1202
extern void	       skb_gro_reset_offset(struct sk_buff *skb);
1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218

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;
}

1219 1220
static inline void *skb_gro_header_fast(struct sk_buff *skb,
					unsigned int offset)
1221
{
1222 1223
	return NAPI_GRO_CB(skb)->frag0 + offset;
}
1224

1225 1226 1227 1228
static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen)
{
	return NAPI_GRO_CB(skb)->frag0_len < hlen;
}
1229

1230 1231 1232 1233 1234 1235
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;
1236
}
L
Linus Torvalds 已提交
1237

1238 1239
static inline void *skb_gro_mac_header(struct sk_buff *skb)
{
1240
	return NAPI_GRO_CB(skb)->frag0 ?: skb_mac_header(skb);
1241 1242
}

H
Herbert Xu 已提交
1243 1244
static inline void *skb_gro_network_header(struct sk_buff *skb)
{
1245 1246
	return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) +
	       skb_network_offset(skb);
H
Herbert Xu 已提交
1247 1248
}

1249 1250
static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
				  unsigned short type,
1251 1252
				  const void *daddr, const void *saddr,
				  unsigned len)
1253
{
1254
	if (!dev->header_ops || !dev->header_ops->create)
1255
		return 0;
1256 1257

	return dev->header_ops->create(skb, dev, type, daddr, saddr, len);
1258 1259
}

S
Stephen Hemminger 已提交
1260 1261 1262 1263 1264
static inline int dev_parse_header(const struct sk_buff *skb,
				   unsigned char *haddr)
{
	const struct net_device *dev = skb->dev;

1265
	if (!dev->header_ops || !dev->header_ops->parse)
S
Stephen Hemminger 已提交
1266
		return 0;
1267
	return dev->header_ops->parse(skb, haddr);
S
Stephen Hemminger 已提交
1268 1269
}

L
Linus Torvalds 已提交
1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280
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
1281
struct softnet_data {
1282
	struct Qdisc		*output_queue;
L
Linus Torvalds 已提交
1283 1284 1285 1286
	struct sk_buff_head	input_pkt_queue;
	struct list_head	poll_list;
	struct sk_buff		*completion_queue;

1287
	struct napi_struct	backlog;
L
Linus Torvalds 已提交
1288 1289 1290 1291 1292 1293
};

DECLARE_PER_CPU(struct softnet_data,softnet_data);

#define HAVE_NETIF_QUEUE

1294
extern void __netif_schedule(struct Qdisc *q);
L
Linus Torvalds 已提交
1295

1296
static inline void netif_schedule_queue(struct netdev_queue *txq)
L
Linus Torvalds 已提交
1297
{
1298
	if (!test_bit(__QUEUE_STATE_XOFF, &txq->state))
1299
		__netif_schedule(txq->qdisc);
1300 1301
}

1302 1303 1304 1305 1306 1307 1308 1309
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));
}

1310 1311 1312 1313 1314
static inline void netif_tx_start_queue(struct netdev_queue *dev_queue)
{
	clear_bit(__QUEUE_STATE_XOFF, &dev_queue->state);
}

1315 1316 1317 1318 1319 1320
/**
 *	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
1321 1322
static inline void netif_start_queue(struct net_device *dev)
{
1323
	netif_tx_start_queue(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
1324 1325
}

1326 1327 1328 1329 1330 1331 1332 1333 1334 1335
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);
	}
}

1336
static inline void netif_tx_wake_queue(struct netdev_queue *dev_queue)
L
Linus Torvalds 已提交
1337 1338
{
#ifdef CONFIG_NETPOLL_TRAP
1339
	if (netpoll_trap()) {
1340
		netif_tx_start_queue(dev_queue);
L
Linus Torvalds 已提交
1341
		return;
1342
	}
L
Linus Torvalds 已提交
1343
#endif
1344
	if (test_and_clear_bit(__QUEUE_STATE_XOFF, &dev_queue->state))
1345
		__netif_schedule(dev_queue->qdisc);
1346 1347
}

1348 1349 1350 1351 1352 1353 1354
/**
 *	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.
 */
1355 1356
static inline void netif_wake_queue(struct net_device *dev)
{
1357
	netif_tx_wake_queue(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
1358 1359
}

1360 1361 1362 1363 1364 1365 1366 1367 1368 1369
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);
	}
}

1370 1371 1372 1373 1374
static inline void netif_tx_stop_queue(struct netdev_queue *dev_queue)
{
	set_bit(__QUEUE_STATE_XOFF, &dev_queue->state);
}

1375 1376 1377 1378 1379 1380 1381
/**
 *	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
1382 1383
static inline void netif_stop_queue(struct net_device *dev)
{
1384
	netif_tx_stop_queue(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
1385 1386
}

1387 1388 1389 1390 1391 1392 1393 1394 1395 1396
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);
	}
}

1397 1398 1399 1400 1401
static inline int netif_tx_queue_stopped(const struct netdev_queue *dev_queue)
{
	return test_bit(__QUEUE_STATE_XOFF, &dev_queue->state);
}

1402 1403 1404 1405 1406 1407
/**
 *	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
1408 1409
static inline int netif_queue_stopped(const struct net_device *dev)
{
1410
	return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
1411 1412
}

1413 1414 1415 1416 1417
static inline int netif_tx_queue_frozen(const struct netdev_queue *dev_queue)
{
	return test_bit(__QUEUE_STATE_FROZEN, &dev_queue->state);
}

1418 1419 1420 1421 1422 1423
/**
 *	netif_running - test if up
 *	@dev: network device
 *
 *	Test if the device has been brought up.
 */
L
Linus Torvalds 已提交
1424 1425 1426 1427 1428
static inline int netif_running(const struct net_device *dev)
{
	return test_bit(__LINK_STATE_START, &dev->state);
}

1429 1430 1431 1432 1433 1434
/*
 * 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.
 */
1435 1436 1437 1438 1439 1440 1441 1442

/**
 *	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.
 */
1443 1444
static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index)
{
1445
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
1446 1447

	netif_tx_start_queue(txq);
1448 1449
}

1450 1451 1452 1453 1454 1455 1456
/**
 *	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.
 */
1457 1458
static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index)
{
1459
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
1460 1461 1462 1463
#ifdef CONFIG_NETPOLL_TRAP
	if (netpoll_trap())
		return;
#endif
1464
	netif_tx_stop_queue(txq);
1465 1466
}

1467 1468 1469 1470 1471 1472 1473
/**
 *	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.
 */
1474
static inline int __netif_subqueue_stopped(const struct net_device *dev,
1475 1476
					 u16 queue_index)
{
1477
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
1478 1479

	return netif_tx_queue_stopped(txq);
1480 1481
}

1482 1483 1484 1485 1486
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));
}
1487 1488 1489 1490 1491 1492 1493 1494

/**
 *	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.
 */
1495 1496
static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
{
1497
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
1498 1499 1500 1501
#ifdef CONFIG_NETPOLL_TRAP
	if (netpoll_trap())
		return;
#endif
1502
	if (test_and_clear_bit(__QUEUE_STATE_XOFF, &txq->state))
1503
		__netif_schedule(txq->qdisc);
1504 1505
}

1506 1507 1508 1509 1510 1511
/**
 *	netif_is_multiqueue - test if device has multiple transmit queues
 *	@dev: network device
 *
 * Check if device has multiple transmit queues
 */
1512 1513
static inline int netif_is_multiqueue(const struct net_device *dev)
{
1514
	return (dev->num_tx_queues > 1);
1515
}
L
Linus Torvalds 已提交
1516 1517

/* Use this variant when it is known for sure that it
1518 1519
 * is executing from hardware interrupt context or with hardware interrupts
 * disabled.
L
Linus Torvalds 已提交
1520
 */
1521
extern void dev_kfree_skb_irq(struct sk_buff *skb);
L
Linus Torvalds 已提交
1522 1523

/* Use this variant in places where it could be invoked
1524 1525
 * from either hardware interrupt or other context, with hardware interrupts
 * either disabled or enabled.
L
Linus Torvalds 已提交
1526
 */
1527
extern void dev_kfree_skb_any(struct sk_buff *skb);
L
Linus Torvalds 已提交
1528 1529 1530 1531 1532 1533

#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);
1534
extern gro_result_t	dev_gro_receive(struct napi_struct *napi,
1535
					struct sk_buff *skb);
1536 1537
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,
1538
					 struct sk_buff *skb);
1539 1540
extern void		napi_reuse_skb(struct napi_struct *napi,
				       struct sk_buff *skb);
1541
extern struct sk_buff *	napi_get_frags(struct napi_struct *napi);
1542
extern gro_result_t	napi_frags_finish(struct napi_struct *napi,
1543 1544
					  struct sk_buff *skb,
					  gro_result_t ret);
1545
extern struct sk_buff *	napi_frags_skb(struct napi_struct *napi);
1546
extern gro_result_t	napi_gro_frags(struct napi_struct *napi);
1547 1548 1549 1550 1551 1552 1553

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

1554
extern void		netif_nit_deliver(struct sk_buff *skb);
1555
extern int		dev_valid_name(const char *name);
1556 1557
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
1558 1559
extern unsigned		dev_get_flags(const struct net_device *);
extern int		dev_change_flags(struct net_device *, unsigned);
1560
extern int		dev_change_name(struct net_device *, const char *);
1561
extern int		dev_set_alias(struct net_device *, const char *, size_t);
1562 1563
extern int		dev_change_net_namespace(struct net_device *,
						 struct net *, const char *);
L
Linus Torvalds 已提交
1564 1565 1566
extern int		dev_set_mtu(struct net_device *, int);
extern int		dev_set_mac_address(struct net_device *,
					    struct sockaddr *);
1567
extern int		dev_hard_start_xmit(struct sk_buff *skb,
1568 1569
					    struct net_device *dev,
					    struct netdev_queue *txq);
1570 1571
extern int		dev_forward_skb(struct net_device *dev,
					struct sk_buff *skb);
L
Linus Torvalds 已提交
1572

1573
extern int		netdev_budget;
L
Linus Torvalds 已提交
1574 1575 1576 1577

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

1578 1579 1580 1581
/**
 *	dev_put - release reference to device
 *	@dev: network device
 *
1582
 * Release reference to device to allow it to be freed.
1583
 */
L
Linus Torvalds 已提交
1584 1585 1586 1587 1588
static inline void dev_put(struct net_device *dev)
{
	atomic_dec(&dev->refcnt);
}

1589 1590 1591 1592
/**
 *	dev_hold - get reference to device
 *	@dev: network device
 *
1593
 * Hold reference to device to keep it from being freed.
1594
 */
1595 1596 1597 1598
static inline void dev_hold(struct net_device *dev)
{
	atomic_inc(&dev->refcnt);
}
L
Linus Torvalds 已提交
1599 1600 1601 1602

/* 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
1603 1604 1605 1606
 *
 * 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
1607 1608 1609
 */

extern void linkwatch_fire_event(struct net_device *dev);
1610
extern void linkwatch_forget_dev(struct net_device *dev);
L
Linus Torvalds 已提交
1611

1612 1613 1614 1615 1616 1617
/**
 *	netif_carrier_ok - test if carrier present
 *	@dev: network device
 *
 * Check if carrier is present on device
 */
L
Linus Torvalds 已提交
1618 1619 1620 1621 1622
static inline int netif_carrier_ok(const struct net_device *dev)
{
	return !test_bit(__LINK_STATE_NOCARRIER, &dev->state);
}

1623 1624
extern unsigned long dev_trans_start(struct net_device *dev);

L
Linus Torvalds 已提交
1625 1626
extern void __netdev_watchdog_up(struct net_device *dev);

1627
extern void netif_carrier_on(struct net_device *dev);
L
Linus Torvalds 已提交
1628

1629
extern void netif_carrier_off(struct net_device *dev);
L
Linus Torvalds 已提交
1630

1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643
/**
 *	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
1644 1645 1646 1647 1648 1649
static inline void netif_dormant_on(struct net_device *dev)
{
	if (!test_and_set_bit(__LINK_STATE_DORMANT, &dev->state))
		linkwatch_fire_event(dev);
}

1650 1651 1652 1653 1654 1655
/**
 *	netif_dormant_off - set device as not dormant.
 *	@dev: network device
 *
 * Device is not in dormant state.
 */
S
Stefan Rompf 已提交
1656 1657 1658 1659 1660 1661
static inline void netif_dormant_off(struct net_device *dev)
{
	if (test_and_clear_bit(__LINK_STATE_DORMANT, &dev->state))
		linkwatch_fire_event(dev);
}

1662 1663 1664 1665 1666 1667
/**
 *	netif_dormant - test if carrier present
 *	@dev: network device
 *
 * Check if carrier is present on device
 */
S
Stefan Rompf 已提交
1668 1669 1670 1671 1672 1673
static inline int netif_dormant(const struct net_device *dev)
{
	return test_bit(__LINK_STATE_DORMANT, &dev->state);
}


1674 1675 1676 1677 1678 1679
/**
 *	netif_oper_up - test if device is operational
 *	@dev: network device
 *
 * Check if carrier is operational
 */
E
Eric Dumazet 已提交
1680 1681
static inline int netif_oper_up(const struct net_device *dev)
{
S
Stefan Rompf 已提交
1682 1683 1684 1685
	return (dev->operstate == IF_OPER_UP ||
		dev->operstate == IF_OPER_UNKNOWN /* backward compat */);
}

1686 1687 1688 1689 1690 1691
/**
 *	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
1692 1693 1694 1695 1696
static inline int netif_device_present(struct net_device *dev)
{
	return test_bit(__LINK_STATE_PRESENT, &dev->state);
}

1697
extern void netif_device_detach(struct net_device *dev);
L
Linus Torvalds 已提交
1698

1699
extern void netif_device_attach(struct net_device *dev);
L
Linus Torvalds 已提交
1700 1701 1702 1703 1704 1705 1706 1707 1708 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

/*
 * 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;
}

1751
static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
H
Herbert Xu 已提交
1752
{
1753 1754
	spin_lock(&txq->_xmit_lock);
	txq->xmit_lock_owner = cpu;
1755 1756
}

1757 1758 1759 1760 1761 1762
static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
{
	spin_lock_bh(&txq->_xmit_lock);
	txq->xmit_lock_owner = smp_processor_id();
}

1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782
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
1783 1784 1785 1786 1787 1788
static inline void txq_trans_update(struct netdev_queue *txq)
{
	if (txq->xmit_lock_owner != -1)
		txq->trans_start = jiffies;
}

1789 1790 1791 1792 1793 1794
/**
 *	netif_tx_lock - grab network device transmit lock
 *	@dev: network device
 *
 * Get network device transmit lock
 */
1795 1796
static inline void netif_tx_lock(struct net_device *dev)
{
1797
	unsigned int i;
1798
	int cpu;
1799

1800 1801
	spin_lock(&dev->tx_global_lock);
	cpu = smp_processor_id();
1802 1803
	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
1804 1805 1806 1807 1808 1809 1810

		/* 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.
		 */
1811
		__netif_tx_lock(txq, cpu);
1812 1813
		set_bit(__QUEUE_STATE_FROZEN, &txq->state);
		__netif_tx_unlock(txq);
1814
	}
H
Herbert Xu 已提交
1815 1816 1817 1818
}

static inline void netif_tx_lock_bh(struct net_device *dev)
{
1819 1820
	local_bh_disable();
	netif_tx_lock(dev);
H
Herbert Xu 已提交
1821 1822 1823 1824
}

static inline void netif_tx_unlock(struct net_device *dev)
{
1825 1826 1827 1828
	unsigned int i;

	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
1829

1830 1831 1832 1833 1834
		/* 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);
1835
		netif_schedule_queue(txq);
1836 1837
	}
	spin_unlock(&dev->tx_global_lock);
H
Herbert Xu 已提交
1838 1839 1840 1841
}

static inline void netif_tx_unlock_bh(struct net_device *dev)
{
1842 1843
	netif_tx_unlock(dev);
	local_bh_enable();
H
Herbert Xu 已提交
1844 1845
}

1846
#define HARD_TX_LOCK(dev, txq, cpu) {			\
1847
	if ((dev->features & NETIF_F_LLTX) == 0) {	\
1848
		__netif_tx_lock(txq, cpu);		\
1849 1850 1851
	}						\
}

1852
#define HARD_TX_UNLOCK(dev, txq) {			\
1853
	if ((dev->features & NETIF_F_LLTX) == 0) {	\
1854
		__netif_tx_unlock(txq);			\
1855 1856 1857
	}						\
}

L
Linus Torvalds 已提交
1858 1859
static inline void netif_tx_disable(struct net_device *dev)
{
1860
	unsigned int i;
1861
	int cpu;
1862

1863 1864
	local_bh_disable();
	cpu = smp_processor_id();
1865 1866
	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
1867 1868

		__netif_tx_lock(txq, cpu);
1869
		netif_tx_stop_queue(txq);
1870
		__netif_tx_unlock(txq);
1871
	}
1872
	local_bh_enable();
L
Linus Torvalds 已提交
1873 1874
}

1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894
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);
}

1895
/*
1896
 * dev_addrs walker. Should be used only for read access. Call with
1897 1898 1899
 * rcu_read_lock held.
 */
#define for_each_dev_addr(dev, ha) \
1900
		list_for_each_entry_rcu(ha, &dev->dev_addrs.list, list)
1901

L
Linus Torvalds 已提交
1902 1903 1904 1905 1906
/* These functions live elsewhere (drivers/net/net_init.c, but related) */

extern void		ether_setup(struct net_device *dev);

/* Support for loadable net-drivers */
1907 1908 1909 1910 1911
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
1912 1913
extern int		register_netdev(struct net_device *dev);
extern void		unregister_netdev(struct net_device *dev);
1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926

/* 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);

1927 1928 1929
/* 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
1930 1931
extern int		dev_unicast_delete(struct net_device *dev, void *addr);
extern int		dev_unicast_add(struct net_device *dev, void *addr);
1932 1933
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
1934 1935
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);
1936 1937
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);
1938 1939
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);
1940 1941
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);
1942 1943
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
1944
extern void		netdev_state_change(struct net_device *dev);
1945 1946
extern void		netdev_bonding_change(struct net_device *dev,
					      unsigned long event);
1947
extern void		netdev_features_change(struct net_device *dev);
L
Linus Torvalds 已提交
1948
/* Load a device via the kmod */
1949
extern void		dev_load(struct net *net, const char *name);
L
Linus Torvalds 已提交
1950
extern void		dev_mcast_init(void);
1951
extern const struct net_device_stats *dev_get_stats(struct net_device *dev);
1952
extern void		dev_txq_stats_fold(const struct net_device *dev, struct net_device_stats *stats);
1953

L
Linus Torvalds 已提交
1954 1955 1956
extern int		netdev_max_backlog;
extern int		weight_p;
extern int		netdev_set_master(struct net_device *dev, struct net_device *master);
1957
extern int skb_checksum_help(struct sk_buff *skb);
1958
extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features);
1959 1960 1961 1962 1963 1964 1965
#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
1966 1967 1968 1969
/* rx skb timestamps */
extern void		net_enable_timestamp(void);
extern void		net_disable_timestamp(void);

1970 1971 1972 1973 1974 1975
#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

1976 1977 1978
extern int netdev_class_create_file(struct class_attribute *class_attr);
extern void netdev_class_remove_file(struct class_attribute *class_attr);

1979
extern char *netdev_drivername(const struct net_device *dev, char *buffer, int len);
1980

1981 1982
extern void linkwatch_run_queue(void);

1983 1984 1985
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);
1986

1987 1988 1989
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
					struct net_device *dev);

1990
static inline int net_gso_ok(int features, int gso_type)
1991
{
1992
	int feature = gso_type << NETIF_F_GSO_SHIFT;
1993
	return (features & feature) == feature;
1994 1995
}

1996 1997
static inline int skb_gso_ok(struct sk_buff *skb, int features)
{
H
Herbert Xu 已提交
1998
	return net_gso_ok(features, skb_shinfo(skb)->gso_type) &&
1999
	       (!skb_has_frags(skb) || (features & NETIF_F_FRAGLIST));
2000 2001
}

2002 2003
static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb)
{
2004 2005
	return skb_is_gso(skb) &&
	       (!skb_gso_ok(skb, dev->features) ||
2006
		unlikely(skb->ip_summed != CHECKSUM_PARTIAL));
2007 2008
}

2009 2010 2011 2012 2013 2014
static inline void netif_set_gso_max_size(struct net_device *dev,
					  unsigned int size)
{
	dev->gso_max_size = size;
}

2015 2016 2017 2018 2019 2020 2021 2022 2023 2024
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);
	}
}

2025
/* On bonding slaves other than the currently active slave, suppress
2026 2027
 * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and
 * ARP on active-backup slaves with arp_validate enabled.
2028 2029 2030 2031 2032 2033
 */
static inline int skb_bond_should_drop(struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	struct net_device *master = dev->master;

2034 2035 2036 2037
	if (master) {
		if (master->priv_flags & IFF_MASTER_ARPMON)
			dev->last_rx = jiffies;

2038 2039 2040 2041 2042 2043 2044 2045
		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);
		}

2046 2047
		if (dev->priv_flags & IFF_SLAVE_INACTIVE) {
			if ((dev->priv_flags & IFF_SLAVE_NEEDARP) &&
2048
			    skb->protocol == __cpu_to_be16(ETH_P_ARP))
2049 2050
				return 0;

2051 2052 2053 2054 2055 2056
			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 &&
2057
			    skb->protocol == __cpu_to_be16(ETH_P_SLOW))
2058 2059 2060 2061
				return 0;

			return 1;
		}
2062 2063 2064 2065
	}
	return 0;
}

2066
extern struct pernet_operations __net_initdata loopback_net_ops;
2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088

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);
}
L
Linus Torvalds 已提交
2089 2090
#endif /* __KERNEL__ */

2091
#endif	/* _LINUX_NETDEVICE_H */