netdevice.h 121.0 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
 *		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

A
Al Viro 已提交
28
#include <linux/timer.h>
29
#include <linux/bug.h>
30
#include <linux/delay.h>
A
Arun Sharma 已提交
31
#include <linux/atomic.h>
32
#include <linux/prefetch.h>
L
Linus Torvalds 已提交
33 34 35 36
#include <asm/cache.h>
#include <asm/byteorder.h>

#include <linux/percpu.h>
37
#include <linux/rculist.h>
38
#include <linux/dmaengine.h>
39
#include <linux/workqueue.h>
T
Tom Herbert 已提交
40
#include <linux/dynamic_queue_limits.h>
L
Linus Torvalds 已提交
41

42
#include <linux/ethtool.h>
43
#include <net/net_namespace.h>
44
#include <net/dsa.h>
J
Jeff Kirsher 已提交
45
#ifdef CONFIG_DCB
46 47
#include <net/dcbnl.h>
#endif
48
#include <net/netprio_cgroup.h>
49

50
#include <linux/netdev_features.h>
51
#include <linux/neighbour.h>
52
#include <uapi/linux/netdevice.h>
53
#include <uapi/linux/if_bonding.h>
54

55
struct netpoll_info;
56
struct device;
57
struct phy_device;
58 59
/* 802.11 specific */
struct wireless_dev;
60 61
/* 802.15.4 specific */
struct wpan_dev;
R
Robert Shearman 已提交
62
struct mpls_dev;
L
Linus Torvalds 已提交
63

64 65
void netdev_set_default_ethtool_ops(struct net_device *dev,
				    const struct ethtool_ops *ops);
66

67 68 69 70
/* Backlog congestion levels */
#define NET_RX_SUCCESS		0	/* keep 'em coming, baby */
#define NET_RX_DROP		1	/* packet dropped */

71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89
/*
 * 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
90 91 92 93
#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
94

95 96 97
/* 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. */
98
#define net_xmit_eval(e)	((e) == NET_XMIT_CN ? 0 : (e))
L
Linus Torvalds 已提交
99 100
#define net_xmit_errno(e)	((e) != NET_XMIT_CN ? -ENOBUFS : 0)

101
/* Driver transmit return codes */
102
#define NETDEV_TX_MASK		0xf0
103

104
enum netdev_tx {
105
	__NETDEV_TX_MIN	 = INT_MIN,	/* make sure enum is signed */
106 107 108
	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 */
109 110 111
};
typedef enum netdev_tx netdev_tx_t;

112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129
/*
 * 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
130 131 132 133
/*
 *	Compute the worst case header length according to the protocols
 *	used.
 */
G
Graf Yang 已提交
134

135
#if defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25)
136 137 138 139 140
# if defined(CONFIG_MAC80211_MESH)
#  define LL_MAX_HEADER 128
# else
#  define LL_MAX_HEADER 96
# endif
L
Linus Torvalds 已提交
141
#else
142
# define LL_MAX_HEADER 32
L
Linus Torvalds 已提交
143 144
#endif

145 146
#if !IS_ENABLED(CONFIG_NET_IPIP) && !IS_ENABLED(CONFIG_NET_IPGRE) && \
    !IS_ENABLED(CONFIG_IPV6_SIT) && !IS_ENABLED(CONFIG_IPV6_TUNNEL)
L
Linus Torvalds 已提交
147 148 149 150 151 152
#define MAX_HEADER LL_MAX_HEADER
#else
#define MAX_HEADER (LL_MAX_HEADER + 48)
#endif

/*
153 154
 *	Old network device statistics. Fields are native words
 *	(unsigned long) so they can be read and written atomically.
L
Linus Torvalds 已提交
155
 */
G
Graf Yang 已提交
156

E
Eric Dumazet 已提交
157
struct net_device_stats {
158 159 160 161 162 163 164 165 166
	unsigned long	rx_packets;
	unsigned long	tx_packets;
	unsigned long	rx_bytes;
	unsigned long	tx_bytes;
	unsigned long	rx_errors;
	unsigned long	tx_errors;
	unsigned long	rx_dropped;
	unsigned long	tx_dropped;
	unsigned long	multicast;
L
Linus Torvalds 已提交
167 168
	unsigned long	collisions;
	unsigned long	rx_length_errors;
169 170 171 172 173
	unsigned long	rx_over_errors;
	unsigned long	rx_crc_errors;
	unsigned long	rx_frame_errors;
	unsigned long	rx_fifo_errors;
	unsigned long	rx_missed_errors;
L
Linus Torvalds 已提交
174 175 176 177 178 179 180 181 182 183 184 185 186
	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;
	unsigned long	rx_compressed;
	unsigned long	tx_compressed;
};


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

187
#ifdef CONFIG_RPS
188 189
#include <linux/static_key.h>
extern struct static_key rps_needed;
190 191
#endif

L
Linus Torvalds 已提交
192 193 194 195
struct neighbour;
struct neigh_parms;
struct sk_buff;

196 197 198 199
struct netdev_hw_addr {
	struct list_head	list;
	unsigned char		addr[MAX_ADDR_LEN];
	unsigned char		type;
J
Jiri Pirko 已提交
200 201 202 203
#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
204 205
#define NETDEV_HW_ADDR_T_MULTICAST	5
	bool			global_use;
206
	int			sync_cnt;
207
	int			refcount;
208
	int			synced;
209 210 211
	struct rcu_head		rcu_head;
};

212 213 214 215 216
struct netdev_hw_addr_list {
	struct list_head	list;
	int			count;
};

217 218 219 220
#define netdev_hw_addr_list_count(l) ((l)->count)
#define netdev_hw_addr_list_empty(l) (netdev_hw_addr_list_count(l) == 0)
#define netdev_hw_addr_list_for_each(ha, l) \
	list_for_each_entry(ha, &(l)->list, list)
221

222 223 224 225
#define netdev_uc_count(dev) netdev_hw_addr_list_count(&(dev)->uc)
#define netdev_uc_empty(dev) netdev_hw_addr_list_empty(&(dev)->uc)
#define netdev_for_each_uc_addr(ha, dev) \
	netdev_hw_addr_list_for_each(ha, &(dev)->uc)
226

227 228
#define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc)
#define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc)
229
#define netdev_for_each_mc_addr(ha, dev) \
230
	netdev_hw_addr_list_for_each(ha, &(dev)->mc)
231

E
Eric Dumazet 已提交
232
struct hh_cache {
233
	u16		hh_len;
234
	u16		__pad;
235
	seqlock_t	hh_lock;
L
Linus Torvalds 已提交
236 237 238 239

	/* cached hardware header; allow for machine alignment needs.        */
#define HH_DATA_MOD	16
#define HH_DATA_OFF(__len) \
J
Jiri Benc 已提交
240
	(HH_DATA_MOD - (((__len - 1) & (HH_DATA_MOD - 1)) + 1))
L
Linus Torvalds 已提交
241 242 243 244 245 246 247 248 249 250 251 252 253 254
#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.
 */
#define LL_RESERVED_SPACE(dev) \
255
	((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
L
Linus Torvalds 已提交
256
#define LL_RESERVED_SPACE_EXTRA(dev,extra) \
257
	((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
L
Linus Torvalds 已提交
258

259 260 261
struct header_ops {
	int	(*create) (struct sk_buff *skb, struct net_device *dev,
			   unsigned short type, const void *daddr,
262
			   const void *saddr, unsigned int len);
263
	int	(*parse)(const struct sk_buff *skb, unsigned char *haddr);
264
	int	(*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type);
265 266 267 268 269
	void	(*cache_update)(struct hh_cache *hh,
				const struct net_device *dev,
				const unsigned char *haddr);
};

L
Linus Torvalds 已提交
270 271 272 273 274
/* 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
275
enum netdev_state_t {
L
Linus Torvalds 已提交
276 277 278
	__LINK_STATE_START,
	__LINK_STATE_PRESENT,
	__LINK_STATE_NOCARRIER,
S
Stefan Rompf 已提交
279 280
	__LINK_STATE_LINKWATCH_PENDING,
	__LINK_STATE_DORMANT,
L
Linus Torvalds 已提交
281 282 283 284 285
};


/*
 * This structure holds at boot time configured netdevice settings. They
G
Graf Yang 已提交
286
 * are then used in the device probing.
L
Linus Torvalds 已提交
287 288 289 290 291 292 293
 */
struct netdev_boot_setup {
	char name[IFNAMSIZ];
	struct ifmap map;
};
#define NETDEV_BOOT_SETUP_MAX 8

294
int __init netdev_boot_setup(char *str);
L
Linus Torvalds 已提交
295

296 297 298 299 300 301 302 303 304 305 306 307 308 309
/*
 * 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;
310
	unsigned int		gro_count;
311 312 313 314 315
	int			(*poll)(struct napi_struct *, int);
#ifdef CONFIG_NETPOLL
	spinlock_t		poll_lock;
	int			poll_owner;
#endif
H
Herbert Xu 已提交
316
	struct net_device	*dev;
317
	struct sk_buff		*gro_list;
H
Herbert Xu 已提交
318
	struct sk_buff		*skb;
319
	struct hrtimer		timer;
320
	struct list_head	dev_list;
E
Eliezer Tamir 已提交
321 322
	struct hlist_node	napi_hash_node;
	unsigned int		napi_id;
323 324
};

E
Eric Dumazet 已提交
325
enum {
326
	NAPI_STATE_SCHED,	/* Poll is scheduled */
D
David S. Miller 已提交
327
	NAPI_STATE_DISABLE,	/* Disable pending */
328
	NAPI_STATE_NPSVC,	/* Netpoll - don't dequeue from poll_list */
E
Eliezer Tamir 已提交
329
	NAPI_STATE_HASHED,	/* In NAPI hash */
330 331
};

332
enum gro_result {
333 334 335 336 337 338
	GRO_MERGED,
	GRO_MERGED_FREE,
	GRO_HELD,
	GRO_NORMAL,
	GRO_DROP,
};
339
typedef enum gro_result gro_result_t;
340

341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372
/*
 * enum rx_handler_result - Possible return values for rx_handlers.
 * @RX_HANDLER_CONSUMED: skb was consumed by rx_handler, do not process it
 * further.
 * @RX_HANDLER_ANOTHER: Do another round in receive path. This is indicated in
 * case skb->dev was changed by rx_handler.
 * @RX_HANDLER_EXACT: Force exact delivery, no wildcard.
 * @RX_HANDLER_PASS: Do nothing, passe the skb as if no rx_handler was called.
 *
 * rx_handlers are functions called from inside __netif_receive_skb(), to do
 * special processing of the skb, prior to delivery to protocol handlers.
 *
 * Currently, a net_device can only have a single rx_handler registered. Trying
 * to register a second rx_handler will return -EBUSY.
 *
 * To register a rx_handler on a net_device, use netdev_rx_handler_register().
 * To unregister a rx_handler on a net_device, use
 * netdev_rx_handler_unregister().
 *
 * Upon return, rx_handler is expected to tell __netif_receive_skb() what to
 * do with the skb.
 *
 * If the rx_handler consumed to skb in some way, it should return
 * RX_HANDLER_CONSUMED. This is appropriate when the rx_handler arranged for
 * the skb to be delivered in some other ways.
 *
 * If the rx_handler changed skb->dev, to divert the skb to another
 * net_device, it should return RX_HANDLER_ANOTHER. The rx_handler for the
 * new device will be called if it exists.
 *
 * If the rx_handler consider the skb should be ignored, it should return
 * RX_HANDLER_EXACT. The skb will only be delivered to protocol handlers that
373
 * are registered on exact device (ptype->dev == skb->dev).
374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389
 *
 * If the rx_handler didn't changed skb->dev, but want the skb to be normally
 * delivered, it should return RX_HANDLER_PASS.
 *
 * A device without a registered rx_handler will behave as if rx_handler
 * returned RX_HANDLER_PASS.
 */

enum rx_handler_result {
	RX_HANDLER_CONSUMED,
	RX_HANDLER_ANOTHER,
	RX_HANDLER_EXACT,
	RX_HANDLER_PASS,
};
typedef enum rx_handler_result rx_handler_result_t;
typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb);
390

391
void __napi_schedule(struct napi_struct *n);
392
void __napi_schedule_irqoff(struct napi_struct *n);
393

394
static inline bool napi_disable_pending(struct napi_struct *n)
D
David S. Miller 已提交
395 396 397 398
{
	return test_bit(NAPI_STATE_DISABLE, &n->state);
}

399 400 401 402 403 404
/**
 *	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
405 406
 * insure only one NAPI poll instance runs.  We also make
 * sure there is no pending NAPI disable.
407
 */
408
static inline bool napi_schedule_prep(struct napi_struct *n)
409
{
D
David S. Miller 已提交
410 411
	return !napi_disable_pending(n) &&
		!test_and_set_bit(NAPI_STATE_SCHED, &n->state);
412 413 414 415 416 417 418 419 420 421 422 423 424 425 426
}

/**
 *	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);
}

427 428 429 430 431 432 433 434 435 436 437 438
/**
 *	napi_schedule_irqoff - schedule NAPI poll
 *	@n: napi context
 *
 * Variant of napi_schedule(), assuming hard irqs are masked.
 */
static inline void napi_schedule_irqoff(struct napi_struct *n)
{
	if (napi_schedule_prep(n))
		__napi_schedule_irqoff(n);
}

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

449 450
void __napi_complete(struct napi_struct *n);
void napi_complete_done(struct napi_struct *n, int work_done);
451 452 453 454 455
/**
 *	napi_complete - NAPI processing complete
 *	@n: napi context
 *
 * Mark NAPI processing as complete.
456
 * Consider using napi_complete_done() instead.
457
 */
458 459 460 461
static inline void napi_complete(struct napi_struct *n)
{
	return napi_complete_done(n, 0);
}
462

E
Eliezer Tamir 已提交
463 464 465 466 467 468 469
/**
 *	napi_by_id - lookup a NAPI by napi_id
 *	@napi_id: hashed napi_id
 *
 * lookup @napi_id in napi_hash table
 * must be called under rcu_read_lock()
 */
470
struct napi_struct *napi_by_id(unsigned int napi_id);
E
Eliezer Tamir 已提交
471 472 473 474 475 476 477

/**
 *	napi_hash_add - add a NAPI to global hashtable
 *	@napi: napi context
 *
 * generate a new napi_id and store a @napi under it in napi_hash
 */
478
void napi_hash_add(struct napi_struct *napi);
E
Eliezer Tamir 已提交
479 480 481 482 483 484 485 486

/**
 *	napi_hash_del - remove a NAPI from global table
 *	@napi: napi context
 *
 * Warning: caller must observe rcu grace period
 * before freeing memory containing @napi
 */
487
void napi_hash_del(struct napi_struct *napi);
E
Eliezer Tamir 已提交
488

489 490 491 492 493 494 495
/**
 *	napi_disable - prevent NAPI from scheduling
 *	@n: napi context
 *
 * Stop NAPI from being scheduled on this context.
 * Waits till any outstanding processing completes.
 */
496
void napi_disable(struct napi_struct *n);
497 498 499 500 501 502 503 504 505 506 507

/**
 *	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));
508
	smp_mb__before_atomic();
509 510 511
	clear_bit(NAPI_STATE_SCHED, &n->state);
}

512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529
#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
530
enum netdev_queue_state_t {
531 532
	__QUEUE_STATE_DRV_XOFF,
	__QUEUE_STATE_STACK_XOFF,
533
	__QUEUE_STATE_FROZEN,
534
};
535 536 537 538 539 540 541 542 543 544 545

#define QUEUE_STATE_DRV_XOFF	(1 << __QUEUE_STATE_DRV_XOFF)
#define QUEUE_STATE_STACK_XOFF	(1 << __QUEUE_STATE_STACK_XOFF)
#define QUEUE_STATE_FROZEN	(1 << __QUEUE_STATE_FROZEN)

#define QUEUE_STATE_ANY_XOFF	(QUEUE_STATE_DRV_XOFF | QUEUE_STATE_STACK_XOFF)
#define QUEUE_STATE_ANY_XOFF_OR_FROZEN (QUEUE_STATE_ANY_XOFF | \
					QUEUE_STATE_FROZEN)
#define QUEUE_STATE_DRV_XOFF_OR_FROZEN (QUEUE_STATE_DRV_XOFF | \
					QUEUE_STATE_FROZEN)

546 547 548 549 550 551 552 553 554
/*
 * __QUEUE_STATE_DRV_XOFF is used by drivers to stop the transmit queue.  The
 * netif_tx_* functions below are used to manipulate this flag.  The
 * __QUEUE_STATE_STACK_XOFF flag is used by the stack to stop the transmit
 * queue independently.  The netif_xmit_*stopped functions below are called
 * to check if the queue has been stopped by the driver or stack (either
 * of the XOFF bits are set in the state).  Drivers should not need to call
 * netif_xmit*stopped functions, they should only be using netif_tx_*.
 */
555

556
struct netdev_queue {
557 558 559
/*
 * read mostly part
 */
560
	struct net_device	*dev;
561
	struct Qdisc __rcu	*qdisc;
562
	struct Qdisc		*qdisc_sleeping;
563
#ifdef CONFIG_SYSFS
T
Tom Herbert 已提交
564 565
	struct kobject		kobj;
#endif
566 567 568
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
	int			numa_node;
#endif
569 570 571 572 573
/*
 * write mostly part
 */
	spinlock_t		_xmit_lock ____cacheline_aligned_in_smp;
	int			xmit_lock_owner;
574 575 576 577
	/*
	 * please use this field instead of dev->trans_start
	 */
	unsigned long		trans_start;
578 579 580 581 582 583

	/*
	 * Number of TX timeouts for this queue
	 * (/sys/class/net/DEV/Q/trans_timeout)
	 */
	unsigned long		trans_timeout;
T
Tom Herbert 已提交
584 585 586 587 588 589

	unsigned long		state;

#ifdef CONFIG_BQL
	struct dql		dql;
#endif
590
	unsigned long		tx_maxrate;
591
} ____cacheline_aligned_in_smp;
592

593 594 595 596 597
static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
{
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
	return q->numa_node;
#else
598
	return NUMA_NO_NODE;
599 600 601 602 603 604 605 606 607 608
#endif
}

static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node)
{
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
	q->numa_node = node;
#endif
}

E
Eric Dumazet 已提交
609
#ifdef CONFIG_RPS
T
Tom Herbert 已提交
610 611 612 613 614 615 616 617 618
/*
 * This structure holds an RPS map which can be of variable length.  The
 * map is an array of CPUs.
 */
struct rps_map {
	unsigned int len;
	struct rcu_head rcu;
	u16 cpus[0];
};
619
#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16)))
T
Tom Herbert 已提交
620

T
Tom Herbert 已提交
621
/*
622 623 624
 * The rps_dev_flow structure contains the mapping of a flow to a CPU, the
 * tail pointer for that CPU's input queue at the time of last enqueue, and
 * a hardware filter index.
T
Tom Herbert 已提交
625 626 627
 */
struct rps_dev_flow {
	u16 cpu;
628
	u16 filter;
T
Tom Herbert 已提交
629 630
	unsigned int last_qtail;
};
631
#define RPS_NO_FILTER 0xffff
T
Tom Herbert 已提交
632 633 634 635 636 637 638 639 640 641

/*
 * The rps_dev_flow_table structure contains a table of flow mappings.
 */
struct rps_dev_flow_table {
	unsigned int mask;
	struct rcu_head rcu;
	struct rps_dev_flow flows[0];
};
#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \
642
    ((_num) * sizeof(struct rps_dev_flow)))
T
Tom Herbert 已提交
643 644 645 646

/*
 * The rps_sock_flow_table contains mappings of flows to the last CPU
 * on which they were processed by the application (set in recvmsg).
647 648 649 650 651 652
 * Each entry is a 32bit value. Upper part is the high order bits
 * of flow hash, lower part is cpu number.
 * rps_cpu_mask is used to partition the space, depending on number of
 * possible cpus : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1
 * For example, if 64 cpus are possible, rps_cpu_mask = 0x3f,
 * meaning we use 32-6=26 bits for the hash.
T
Tom Herbert 已提交
653 654
 */
struct rps_sock_flow_table {
655
	u32	mask;
656 657

	u32	ents[0] ____cacheline_aligned_in_smp;
T
Tom Herbert 已提交
658
};
659
#define	RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num]))
T
Tom Herbert 已提交
660 661 662

#define RPS_NO_CPU 0xffff

663 664 665
extern u32 rps_cpu_mask;
extern struct rps_sock_flow_table __rcu *rps_sock_flow_table;

T
Tom Herbert 已提交
666 667 668 669
static inline void rps_record_sock_flow(struct rps_sock_flow_table *table,
					u32 hash)
{
	if (table && hash) {
670 671
		unsigned int index = hash & table->mask;
		u32 val = hash & ~rps_cpu_mask;
T
Tom Herbert 已提交
672 673

		/* We only give a hint, preemption can change cpu under us */
674
		val |= raw_smp_processor_id();
T
Tom Herbert 已提交
675

676 677
		if (table->ents[index] != val)
			table->ents[index] = val;
T
Tom Herbert 已提交
678 679 680
	}
}

681
#ifdef CONFIG_RFS_ACCEL
682 683
bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
			 u16 filter_id);
684
#endif
685
#endif /* CONFIG_RPS */
686

T
Tom Herbert 已提交
687 688
/* This structure contains an instance of an RX queue. */
struct netdev_rx_queue {
689
#ifdef CONFIG_RPS
E
Eric Dumazet 已提交
690 691
	struct rps_map __rcu		*rps_map;
	struct rps_dev_flow_table __rcu	*rps_flow_table;
692
#endif
E
Eric Dumazet 已提交
693
	struct kobject			kobj;
T
Tom Herbert 已提交
694
	struct net_device		*dev;
T
Tom Herbert 已提交
695
} ____cacheline_aligned_in_smp;
696 697 698 699 700 701 702 703 704 705 706

/*
 * RX queue sysfs structures and functions.
 */
struct rx_queue_attribute {
	struct attribute attr;
	ssize_t (*show)(struct netdev_rx_queue *queue,
	    struct rx_queue_attribute *attr, char *buf);
	ssize_t (*store)(struct netdev_rx_queue *queue,
	    struct rx_queue_attribute *attr, const char *buf, size_t len);
};
707

T
Tom Herbert 已提交
708 709 710 711 712 713 714 715 716 717 718
#ifdef CONFIG_XPS
/*
 * This structure holds an XPS map which can be of variable length.  The
 * map is an array of queues.
 */
struct xps_map {
	unsigned int len;
	unsigned int alloc_len;
	struct rcu_head rcu;
	u16 queues[0];
};
719
#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + ((_num) * sizeof(u16)))
T
Tom Herbert 已提交
720 721 722 723 724 725 726 727
#define XPS_MIN_MAP_ALLOC ((L1_CACHE_BYTES - sizeof(struct xps_map))	\
    / sizeof(u16))

/*
 * This structure holds all XPS maps for device.  Maps are indexed by CPU.
 */
struct xps_dev_maps {
	struct rcu_head rcu;
E
Eric Dumazet 已提交
728
	struct xps_map __rcu *cpu_map[0];
T
Tom Herbert 已提交
729 730 731 732 733
};
#define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) +		\
    (nr_cpu_ids * sizeof(struct xps_map *)))
#endif /* CONFIG_XPS */

734 735 736 737 738 739 740 741
#define TC_MAX_QUEUE	16
#define TC_BITMASK	15
/* HW offloaded queuing disciplines txq count and offset maps */
struct netdev_tc_txq {
	u16 count;
	u16 offset;
};

742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758
#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
/*
 * This structure is to hold information about the device
 * configured to run FCoE protocol stack.
 */
struct netdev_fcoe_hbainfo {
	char	manufacturer[64];
	char	serial_number[64];
	char	hardware_version[64];
	char	driver_version[64];
	char	optionrom_version[64];
	char	firmware_version[64];
	char	model[256];
	char	model_description[256];
};
#endif

759
#define MAX_PHYS_ITEM_ID_LEN 32
760

761 762
/* This structure holds a unique identifier to identify some
 * physical item (port for example) used by a netdevice.
763
 */
764 765
struct netdev_phys_item_id {
	unsigned char id[MAX_PHYS_ITEM_ID_LEN];
766 767 768
	unsigned char id_len;
};

769 770 771
typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
				       struct sk_buff *skb);

772 773
/*
 * This structure defines the management hooks for network devices.
774 775
 * The following hooks can be defined; unless noted otherwise, they are
 * optional and can be filled with a null pointer.
776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794
 *
 * 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.
 *
795 796
 * netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb,
 *                               struct net_device *dev);
797
 *	Called when a packet needs to be transmitted.
798 799 800 801
 *	Returns NETDEV_TX_OK.  Can return NETDEV_TX_BUSY, but you should stop
 *	the queue before that can happen; it's for obsolete devices and weird
 *	corner cases, but the stack really does a non-trivial amount
 *	of useless work if you return NETDEV_TX_BUSY.
802
 *        (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
803 804
 *	Required can not be NULL.
 *
805
 * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
806
 *                         void *accel_priv, select_queue_fallback_t fallback);
807 808 809
 *	Called to decide which queue to when device supports multiple
 *	transmit queues.
 *
810 811 812 813 814 815
 * 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.
816 817
 *	If driver handles unicast address filtering, it should set
 *	IFF_UNICAST_FLT to its priv_flags.
818 819 820
 *
 * int (*ndo_set_mac_address)(struct net_device *dev, void *addr);
 *	This function  is called when the Media Access Control address
821
 *	needs to be changed. If this interface is not defined, the
822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841
 *	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.
 *
842
 * void (*ndo_tx_timeout)(struct net_device *dev);
843 844 845
 *	Callback uses when the transmitter has not made any progress
 *	for dev->watchdog ticks.
 *
846
 * struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev,
847
 *                      struct rtnl_link_stats64 *storage);
848
 * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
849
 *	Called when a user wants to get the network device usage
850
 *	statistics. Drivers must do one of the following:
851 852
 *	1. Define @ndo_get_stats64 to fill in a zero-initialised
 *	   rtnl_link_stats64 structure passed by the caller.
853
 *	2. Define @ndo_get_stats to update a net_device_stats structure
854 855 856 857 858
 *	   (which should normally be dev->stats) and return a pointer to
 *	   it. The structure may be changed asynchronously only if each
 *	   field is written atomically.
 *	3. Update dev->stats asynchronously and atomically, and define
 *	   neither operation.
859
 *
860
 * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid);
861 862
 *	If device support VLAN filtering this function is called when a
 *	VLAN id is registered.
863
 *
864
 * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid);
865 866
 *	If device support VLAN filtering this function is called when a
 *	VLAN id is unregistered.
867 868
 *
 * void (*ndo_poll_controller)(struct net_device *dev);
869 870 871 872
 *
 *	SR-IOV management functions.
 * int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac);
 * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, u8 qos);
873 874
 * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate,
 *			  int max_tx_rate);
875
 * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting);
876 877
 * int (*ndo_get_vf_config)(struct net_device *dev,
 *			    int vf, struct ifla_vf_info *ivf);
878
 * int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state);
879 880
 * int (*ndo_set_vf_port)(struct net_device *dev, int vf,
 *			  struct nlattr *port[]);
881 882 883 884 885
 *
 *      Enable or disable the VF ability to query its RSS Redirection Table and
 *      Hash Key. This is needed since on some devices VF share this information
 *      with PF and querying it may adduce a theoretical security risk.
 * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting);
886
 * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb);
887 888 889 890 891
 * int (*ndo_setup_tc)(struct net_device *dev, u8 tc)
 * 	Called to setup 'tc' number of traffic classes in the net device. This
 * 	is always called from the stack with the rtnl lock held and netif tx
 * 	queues stopped. This allows the netdevice to perform queue management
 * 	safely.
892
 *
893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922
 *	Fiber Channel over Ethernet (FCoE) offload functions.
 * int (*ndo_fcoe_enable)(struct net_device *dev);
 *	Called when the FCoE protocol stack wants to start using LLD for FCoE
 *	so the underlying device can perform whatever needed configuration or
 *	initialization to support acceleration of FCoE traffic.
 *
 * int (*ndo_fcoe_disable)(struct net_device *dev);
 *	Called when the FCoE protocol stack wants to stop using LLD for FCoE
 *	so the underlying device can perform whatever needed clean-ups to
 *	stop supporting acceleration of FCoE traffic.
 *
 * int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid,
 *			     struct scatterlist *sgl, unsigned int sgc);
 *	Called when the FCoE Initiator wants to initialize an I/O that
 *	is a possible candidate for Direct Data Placement (DDP). The LLD can
 *	perform necessary setup and returns 1 to indicate the device is set up
 *	successfully to perform DDP on this I/O, otherwise this returns 0.
 *
 * int (*ndo_fcoe_ddp_done)(struct net_device *dev,  u16 xid);
 *	Called when the FCoE Initiator/Target is done with the DDPed I/O as
 *	indicated by the FC exchange id 'xid', so the underlying device can
 *	clean up and reuse resources for later DDP requests.
 *
 * int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid,
 *			      struct scatterlist *sgl, unsigned int sgc);
 *	Called when the FCoE Target wants to initialize an I/O that
 *	is a possible candidate for Direct Data Placement (DDP). The LLD can
 *	perform necessary setup and returns 1 to indicate the device is set up
 *	successfully to perform DDP on this I/O, otherwise this returns 0.
 *
923 924 925 926 927 928 929
 * int (*ndo_fcoe_get_hbainfo)(struct net_device *dev,
 *			       struct netdev_fcoe_hbainfo *hbainfo);
 *	Called when the FCoE Protocol stack wants information on the underlying
 *	device. This information is utilized by the FCoE protocol stack to
 *	register attributes with Fiber Channel management service as per the
 *	FC-GS Fabric Device Management Information(FDMI) specification.
 *
930 931 932 933 934 935
 * int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type);
 *	Called when the underlying device wants to override default World Wide
 *	Name (WWN) generation mechanism in FCoE protocol stack to pass its own
 *	World Wide Port Name (WWPN) or World Wide Node Name (WWNN) to the FCoE
 *	protocol stack to use.
 *
936 937 938 939 940 941
 *	RFS acceleration.
 * int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb,
 *			    u16 rxq_index, u32 flow_id);
 *	Set hardware filter for RFS.  rxq_index is the target queue index;
 *	flow_id is a flow ID to be passed to rps_may_expire_flow() later.
 *	Return the filter ID on success, or a negative error code.
942
 *
943
 *	Slave management functions (for bridge, bonding, etc).
944 945 946 947 948
 * int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev);
 *	Called to make another netdev an underling.
 *
 * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev);
 *	Called to release previously enslaved netdev.
949 950
 *
 *      Feature/offload setting functions.
951 952
 * netdev_features_t (*ndo_fix_features)(struct net_device *dev,
 *		netdev_features_t features);
953 954 955 956
 *	Adjusts the requested feature flags according to device-specific
 *	constraints, and returns the resulting flags. Must not modify
 *	the device state.
 *
957
 * int (*ndo_set_features)(struct net_device *dev, netdev_features_t features);
958 959 960 961
 *	Called to update device configuration to new features. Passed
 *	feature set might be less than what was returned by ndo_fix_features()).
 *	Must return >0 or -errno if it changed dev->features itself.
 *
962 963
 * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[],
 *		      struct net_device *dev,
964
 *		      const unsigned char *addr, u16 vid, u16 flags)
965
 *	Adds an FDB entry to dev for addr.
966 967
 * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[],
 *		      struct net_device *dev,
968
 *		      const unsigned char *addr, u16 vid)
969 970
 *	Deletes the FDB entry from dev coresponding to addr.
 * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb,
971 972
 *		       struct net_device *dev, struct net_device *filter_dev,
 *		       int idx)
973 974
 *	Used to add FDB entries to dump requests. Implementers should add
 *	entries to skb and update idx with the number of entries.
J
John Fastabend 已提交
975
 *
976 977
 * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh,
 *			     u16 flags)
J
John Fastabend 已提交
978
 * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq,
979 980
 *			     struct net_device *dev, u32 filter_mask,
 *			     int nlflags)
981 982
 * int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh,
 *			     u16 flags);
J
Jiri Pirko 已提交
983 984 985 986 987 988 989 990
 *
 * int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier);
 *	Called to change device carrier. Soft-devices (like dummy, team, etc)
 *	which do not represent real hardware may define this to allow their
 *	userspace components to manage their virtual carrier state. Devices
 *	that determine carrier state from physical hardware properties (eg
 *	network cables) or protocol-dependent mechanisms (eg
 *	USB_CDC_NOTIFY_NETWORK_CONNECTION) should NOT implement this function.
991 992
 *
 * int (*ndo_get_phys_port_id)(struct net_device *dev,
993
 *			       struct netdev_phys_item_id *ppid);
994 995 996
 *	Called to get ID of physical port of this device. If driver does
 *	not implement this, it is assumed that the hw is not able to have
 *	multiple net devices on single physical port.
997 998
 *
 * void (*ndo_add_vxlan_port)(struct  net_device *dev,
J
Joseph Gasparakis 已提交
999
 *			      sa_family_t sa_family, __be16 port);
1000 1001 1002 1003 1004 1005
 *	Called by vxlan to notiy a driver about the UDP port and socket
 *	address family that vxlan is listnening to. It is called only when
 *	a new port starts listening. The operation is protected by the
 *	vxlan_net->sock_lock.
 *
 * void (*ndo_del_vxlan_port)(struct  net_device *dev,
J
Joseph Gasparakis 已提交
1006
 *			      sa_family_t sa_family, __be16 port);
1007 1008 1009
 *	Called by vxlan to notify the driver about a UDP port and socket
 *	address family that vxlan is not listening to anymore. The operation
 *	is protected by the vxlan_net->sock_lock.
1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028
 *
 * void* (*ndo_dfwd_add_station)(struct net_device *pdev,
 *				 struct net_device *dev)
 *	Called by upper layer devices to accelerate switching or other
 *	station functionality into hardware. 'pdev is the lowerdev
 *	to use for the offload and 'dev' is the net device that will
 *	back the offload. Returns a pointer to the private structure
 *	the upper layer will maintain.
 * void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv)
 *	Called by upper layer device to delete the station created
 *	by 'ndo_dfwd_add_station'. 'pdev' is the net device backing
 *	the station and priv is the structure returned by the add
 *	operation.
 * netdev_tx_t (*ndo_dfwd_start_xmit)(struct sk_buff *skb,
 *				      struct net_device *dev,
 *				      void *priv);
 *	Callback to use for xmit over the accelerated station. This
 *	is used in place of ndo_start_xmit on accelerated net
 *	devices.
1029 1030 1031
 * netdev_features_t (*ndo_features_check) (struct sk_buff *skb,
 *					    struct net_device *dev
 *					    netdev_features_t features);
T
Tom Herbert 已提交
1032
 *	Called by core transmit path to determine if device is capable of
1033 1034 1035 1036 1037
 *	performing offload operations on a given packet. This is to give
 *	the device an opportunity to implement any restrictions that cannot
 *	be otherwise expressed by feature flags. The check is called with
 *	the set of features that the stack has calculated and it returns
 *	those the driver believes to be appropriate.
1038 1039 1040 1041
 * int (*ndo_set_tx_maxrate)(struct net_device *dev,
 *			     int queue_index, u32 maxrate);
 *	Called when a user wants to set a max-rate limitation of specific
 *	TX queue.
1042 1043
 * int (*ndo_get_iflink)(const struct net_device *dev);
 *	Called to get the iflink value of this device.
1044 1045 1046 1047 1048 1049
 */
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);
1050
	netdev_tx_t		(*ndo_start_xmit) (struct sk_buff *skb,
1051 1052
						   struct net_device *dev);
	u16			(*ndo_select_queue)(struct net_device *dev,
1053
						    struct sk_buff *skb,
1054 1055
						    void *accel_priv,
						    select_queue_fallback_t fallback);
1056 1057 1058 1059 1060 1061 1062 1063 1064 1065
	void			(*ndo_change_rx_flags)(struct net_device *dev,
						       int flags);
	void			(*ndo_set_rx_mode)(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);
1066 1067 1068 1069
	int			(*ndo_change_mtu)(struct net_device *dev,
						  int new_mtu);
	int			(*ndo_neigh_setup)(struct net_device *dev,
						   struct neigh_parms *);
1070 1071
	void			(*ndo_tx_timeout) (struct net_device *dev);

1072 1073
	struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev,
						     struct rtnl_link_stats64 *storage);
1074 1075
	struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);

1076
	int			(*ndo_vlan_rx_add_vid)(struct net_device *dev,
1077
						       __be16 proto, u16 vid);
1078
	int			(*ndo_vlan_rx_kill_vid)(struct net_device *dev,
1079
						        __be16 proto, u16 vid);
1080 1081
#ifdef CONFIG_NET_POLL_CONTROLLER
	void                    (*ndo_poll_controller)(struct net_device *dev);
H
Herbert Xu 已提交
1082
	int			(*ndo_netpoll_setup)(struct net_device *dev,
1083
						     struct netpoll_info *info);
1084
	void			(*ndo_netpoll_cleanup)(struct net_device *dev);
E
Eliezer Tamir 已提交
1085
#endif
1086
#ifdef CONFIG_NET_RX_BUSY_POLL
1087
	int			(*ndo_busy_poll)(struct napi_struct *dev);
1088
#endif
1089 1090 1091 1092
	int			(*ndo_set_vf_mac)(struct net_device *dev,
						  int queue, u8 *mac);
	int			(*ndo_set_vf_vlan)(struct net_device *dev,
						   int queue, u16 vlan, u8 qos);
1093 1094 1095
	int			(*ndo_set_vf_rate)(struct net_device *dev,
						   int vf, int min_tx_rate,
						   int max_tx_rate);
1096 1097
	int			(*ndo_set_vf_spoofchk)(struct net_device *dev,
						       int vf, bool setting);
1098 1099 1100
	int			(*ndo_get_vf_config)(struct net_device *dev,
						     int vf,
						     struct ifla_vf_info *ivf);
1101 1102
	int			(*ndo_set_vf_link_state)(struct net_device *dev,
							 int vf, int link_state);
1103 1104 1105 1106 1107
	int			(*ndo_set_vf_port)(struct net_device *dev,
						   int vf,
						   struct nlattr *port[]);
	int			(*ndo_get_vf_port)(struct net_device *dev,
						   int vf, struct sk_buff *skb);
1108 1109 1110
	int			(*ndo_set_vf_rss_query_en)(
						   struct net_device *dev,
						   int vf, bool setting);
1111
	int			(*ndo_setup_tc)(struct net_device *dev, u8 tc);
1112
#if IS_ENABLED(CONFIG_FCOE)
1113 1114
	int			(*ndo_fcoe_enable)(struct net_device *dev);
	int			(*ndo_fcoe_disable)(struct net_device *dev);
1115 1116 1117 1118 1119 1120
	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);
1121 1122 1123 1124
	int			(*ndo_fcoe_ddp_target)(struct net_device *dev,
						       u16 xid,
						       struct scatterlist *sgl,
						       unsigned int sgc);
1125 1126
	int			(*ndo_fcoe_get_hbainfo)(struct net_device *dev,
							struct netdev_fcoe_hbainfo *hbainfo);
1127 1128
#endif

1129
#if IS_ENABLED(CONFIG_LIBFCOE)
1130 1131 1132 1133
#define NETDEV_FCOE_WWNN 0
#define NETDEV_FCOE_WWPN 1
	int			(*ndo_fcoe_get_wwn)(struct net_device *dev,
						    u64 *wwn, int type);
1134
#endif
1135

1136 1137 1138 1139 1140 1141
#ifdef CONFIG_RFS_ACCEL
	int			(*ndo_rx_flow_steer)(struct net_device *dev,
						     const struct sk_buff *skb,
						     u16 rxq_index,
						     u32 flow_id);
#endif
1142 1143 1144 1145
	int			(*ndo_add_slave)(struct net_device *dev,
						 struct net_device *slave_dev);
	int			(*ndo_del_slave)(struct net_device *dev,
						 struct net_device *slave_dev);
1146 1147
	netdev_features_t	(*ndo_fix_features)(struct net_device *dev,
						    netdev_features_t features);
1148
	int			(*ndo_set_features)(struct net_device *dev,
1149
						    netdev_features_t features);
1150
	int			(*ndo_neigh_construct)(struct neighbour *n);
1151
	void			(*ndo_neigh_destroy)(struct neighbour *n);
1152 1153

	int			(*ndo_fdb_add)(struct ndmsg *ndm,
1154
					       struct nlattr *tb[],
1155
					       struct net_device *dev,
1156
					       const unsigned char *addr,
1157
					       u16 vid,
1158 1159
					       u16 flags);
	int			(*ndo_fdb_del)(struct ndmsg *ndm,
1160
					       struct nlattr *tb[],
1161
					       struct net_device *dev,
1162 1163
					       const unsigned char *addr,
					       u16 vid);
1164 1165 1166
	int			(*ndo_fdb_dump)(struct sk_buff *skb,
						struct netlink_callback *cb,
						struct net_device *dev,
1167
						struct net_device *filter_dev,
1168
						int idx);
J
John Fastabend 已提交
1169 1170

	int			(*ndo_bridge_setlink)(struct net_device *dev,
1171 1172
						      struct nlmsghdr *nlh,
						      u16 flags);
J
John Fastabend 已提交
1173 1174
	int			(*ndo_bridge_getlink)(struct sk_buff *skb,
						      u32 pid, u32 seq,
1175
						      struct net_device *dev,
1176 1177
						      u32 filter_mask,
						      int nlflags);
1178
	int			(*ndo_bridge_dellink)(struct net_device *dev,
1179 1180
						      struct nlmsghdr *nlh,
						      u16 flags);
J
Jiri Pirko 已提交
1181 1182
	int			(*ndo_change_carrier)(struct net_device *dev,
						      bool new_carrier);
1183
	int			(*ndo_get_phys_port_id)(struct net_device *dev,
1184
							struct netdev_phys_item_id *ppid);
1185 1186
	int			(*ndo_get_phys_port_name)(struct net_device *dev,
							  char *name, size_t len);
1187 1188
	void			(*ndo_add_vxlan_port)(struct  net_device *dev,
						      sa_family_t sa_family,
J
Joseph Gasparakis 已提交
1189
						      __be16 port);
1190 1191
	void			(*ndo_del_vxlan_port)(struct  net_device *dev,
						      sa_family_t sa_family,
J
Joseph Gasparakis 已提交
1192
						      __be16 port);
1193 1194 1195 1196 1197 1198 1199 1200 1201

	void*			(*ndo_dfwd_add_station)(struct net_device *pdev,
							struct net_device *dev);
	void			(*ndo_dfwd_del_station)(struct net_device *pdev,
							void *priv);

	netdev_tx_t		(*ndo_dfwd_start_xmit) (struct sk_buff *skb,
							struct net_device *dev,
							void *priv);
1202
	int			(*ndo_get_lock_subclass)(struct net_device *dev);
1203 1204 1205
	netdev_features_t	(*ndo_features_check) (struct sk_buff *skb,
						       struct net_device *dev,
						       netdev_features_t features);
1206 1207 1208
	int			(*ndo_set_tx_maxrate)(struct net_device *dev,
						      int queue_index,
						      u32 maxrate);
1209
	int			(*ndo_get_iflink)(const struct net_device *dev);
1210 1211
};

1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269
/**
 * enum net_device_priv_flags - &struct net_device priv_flags
 *
 * These are the &struct net_device, they are only set internally
 * by drivers and used in the kernel. These flags are invisible to
 * userspace, this means that the order of these flags can change
 * during any kernel release.
 *
 * You should have a pretty good reason to be extending these flags.
 *
 * @IFF_802_1Q_VLAN: 802.1Q VLAN device
 * @IFF_EBRIDGE: Ethernet bridging device
 * @IFF_SLAVE_INACTIVE: bonding slave not the curr. active
 * @IFF_MASTER_8023AD: bonding master, 802.3ad
 * @IFF_MASTER_ALB: bonding master, balance-alb
 * @IFF_BONDING: bonding master or slave
 * @IFF_SLAVE_NEEDARP: need ARPs for validation
 * @IFF_ISATAP: ISATAP interface (RFC4214)
 * @IFF_MASTER_ARPMON: bonding master, ARP mon in use
 * @IFF_WAN_HDLC: WAN HDLC device
 * @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to
 *	release skb->dst
 * @IFF_DONT_BRIDGE: disallow bridging this ether dev
 * @IFF_DISABLE_NETPOLL: disable netpoll at run-time
 * @IFF_MACVLAN_PORT: device used as macvlan port
 * @IFF_BRIDGE_PORT: device used as bridge port
 * @IFF_OVS_DATAPATH: device used as Open vSwitch datapath port
 * @IFF_TX_SKB_SHARING: The interface supports sharing skbs on transmit
 * @IFF_UNICAST_FLT: Supports unicast filtering
 * @IFF_TEAM_PORT: device used as team port
 * @IFF_SUPP_NOFCS: device supports sending custom FCS
 * @IFF_LIVE_ADDR_CHANGE: device supports hardware address
 *	change when it's running
 * @IFF_MACVLAN: Macvlan device
 */
enum netdev_priv_flags {
	IFF_802_1Q_VLAN			= 1<<0,
	IFF_EBRIDGE			= 1<<1,
	IFF_SLAVE_INACTIVE		= 1<<2,
	IFF_MASTER_8023AD		= 1<<3,
	IFF_MASTER_ALB			= 1<<4,
	IFF_BONDING			= 1<<5,
	IFF_SLAVE_NEEDARP		= 1<<6,
	IFF_ISATAP			= 1<<7,
	IFF_MASTER_ARPMON		= 1<<8,
	IFF_WAN_HDLC			= 1<<9,
	IFF_XMIT_DST_RELEASE		= 1<<10,
	IFF_DONT_BRIDGE			= 1<<11,
	IFF_DISABLE_NETPOLL		= 1<<12,
	IFF_MACVLAN_PORT		= 1<<13,
	IFF_BRIDGE_PORT			= 1<<14,
	IFF_OVS_DATAPATH		= 1<<15,
	IFF_TX_SKB_SHARING		= 1<<16,
	IFF_UNICAST_FLT			= 1<<17,
	IFF_TEAM_PORT			= 1<<18,
	IFF_SUPP_NOFCS			= 1<<19,
	IFF_LIVE_ADDR_CHANGE		= 1<<20,
	IFF_MACVLAN			= 1<<21,
1270
	IFF_XMIT_DST_RELEASE_PERM	= 1<<22,
1271 1272
	IFF_IPVLAN_MASTER		= 1<<23,
	IFF_IPVLAN_SLAVE		= 1<<24,
1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296
};

#define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
#define IFF_EBRIDGE			IFF_EBRIDGE
#define IFF_SLAVE_INACTIVE		IFF_SLAVE_INACTIVE
#define IFF_MASTER_8023AD		IFF_MASTER_8023AD
#define IFF_MASTER_ALB			IFF_MASTER_ALB
#define IFF_BONDING			IFF_BONDING
#define IFF_SLAVE_NEEDARP		IFF_SLAVE_NEEDARP
#define IFF_ISATAP			IFF_ISATAP
#define IFF_MASTER_ARPMON		IFF_MASTER_ARPMON
#define IFF_WAN_HDLC			IFF_WAN_HDLC
#define IFF_XMIT_DST_RELEASE		IFF_XMIT_DST_RELEASE
#define IFF_DONT_BRIDGE			IFF_DONT_BRIDGE
#define IFF_DISABLE_NETPOLL		IFF_DISABLE_NETPOLL
#define IFF_MACVLAN_PORT		IFF_MACVLAN_PORT
#define IFF_BRIDGE_PORT			IFF_BRIDGE_PORT
#define IFF_OVS_DATAPATH		IFF_OVS_DATAPATH
#define IFF_TX_SKB_SHARING		IFF_TX_SKB_SHARING
#define IFF_UNICAST_FLT			IFF_UNICAST_FLT
#define IFF_TEAM_PORT			IFF_TEAM_PORT
#define IFF_SUPP_NOFCS			IFF_SUPP_NOFCS
#define IFF_LIVE_ADDR_CHANGE		IFF_LIVE_ADDR_CHANGE
#define IFF_MACVLAN			IFF_MACVLAN
1297
#define IFF_XMIT_DST_RELEASE_PERM	IFF_XMIT_DST_RELEASE_PERM
1298 1299
#define IFF_IPVLAN_MASTER		IFF_IPVLAN_MASTER
#define IFF_IPVLAN_SLAVE		IFF_IPVLAN_SLAVE
1300

1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317
/**
 *	struct net_device - 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.
 *
 *	@name:	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
 *	 	of the interface.
 *
 *	@name_hlist: 	Device name hash chain, please keep it close to name[]
 *	@ifalias:	SNMP alias
 *	@mem_end:	Shared memory end
 *	@mem_start:	Shared memory start
 *	@base_addr:	Device I/O address
 *	@irq:		Device IRQ number
 *
1318 1319
 *	@carrier_changes:	Stats to monitor carrier on<->off transitions
 *
1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342
 *	@state:		Generic network queuing layer state, see netdev_state_t
 *	@dev_list:	The global list of network devices
 *	@napi_list:	List entry, that is used for polling napi devices
 *	@unreg_list:	List entry, that is used, when we are unregistering the
 *			device, see the function unregister_netdev
 *	@close_list:	List entry, that is used, when we are closing the device
 *
 *	@adj_list:	Directly linked devices, like slaves for bonding
 *	@all_adj_list:	All linked devices, *including* neighbours
 *	@features:	Currently active device features
 *	@hw_features:	User-changeable features
 *
 *	@wanted_features:	User-requested features
 *	@vlan_features:		Mask of features inheritable by VLAN devices
 *
 *	@hw_enc_features:	Mask of features inherited by encapsulating devices
 *				This field indicates what encapsulation
 *				offloads the hardware is capable of doing,
 *				and drivers will need to set them appropriately.
 *
 *	@mpls_features:	Mask of features inheritable by MPLS
 *
 *	@ifindex:	interface index
1343
 *	@group:		The group, that the device belongs to
1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360
 *
 *	@stats:		Statistics struct, which was left as a legacy, use
 *			rtnl_link_stats64 instead
 *
 *	@rx_dropped:	Dropped packets by core network,
 *			do not use this in drivers
 *	@tx_dropped:	Dropped packets by core network,
 *			do not use this in drivers
 *
 *	@wireless_handlers:	List of functions to handle Wireless Extensions,
 *				instead of ioctl,
 *				see <net/iw_handler.h> for details.
 *	@wireless_data:	Instance data managed by the core of wireless extensions
 *
 *	@netdev_ops:	Includes several pointers to callbacks,
 *			if one wants to override the ndo_*() functions
 *	@ethtool_ops:	Management operations
E
Eric W. Biederman 已提交
1361
 *	@header_ops:	Includes callbacks for creating,parsing,caching,etc
1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398
 *			of Layer 2 headers.
 *
 *	@flags:		Interface flags (a la BSD)
 *	@priv_flags:	Like 'flags' but invisible to userspace,
 *			see if.h for the definitions
 *	@gflags:	Global flags ( kept as legacy )
 *	@padded:	How much padding added by alloc_netdev()
 *	@operstate:	RFC2863 operstate
 *	@link_mode:	Mapping policy to operstate
 *	@if_port:	Selectable AUI, TP, ...
 *	@dma:		DMA channel
 *	@mtu:		Interface MTU value
 *	@type:		Interface hardware type
 *	@hard_header_len: Hardware header length
 *
 *	@needed_headroom: Extra headroom the hardware may need, but not in all
 *			  cases can this be guaranteed
 *	@needed_tailroom: Extra tailroom the hardware may need, but not in all
 *			  cases can this be guaranteed. Some cases also use
 *			  LL_MAX_HEADER instead to allocate the skb
 *
 *	interface address info:
 *
 * 	@perm_addr:		Permanent hw address
 * 	@addr_assign_type:	Hw address assignment type
 * 	@addr_len:		Hardware address length
 * 	@neigh_priv_len;	Used in neigh_alloc(),
 * 				initialized only in atm/clip.c
 * 	@dev_id:		Used to differentiate devices that share
 * 				the same link layer address
 * 	@dev_port:		Used to differentiate devices that share
 * 				the same function
 *	@addr_list_lock:	XXX: need comments on this one
 *	@uc_promisc:		Counter, that indicates, that promiscuous mode
 *				has been enabled due to the need to listen to
 *				additional unicast addresses in a device that
 *				does not implement ndo_set_rx_mode()
1399 1400 1401 1402
 *	@uc:			unicast mac addresses
 *	@mc:			multicast mac addresses
 *	@dev_addrs:		list of device hw addresses
 *	@queues_kset:		Group of all Kobjects in the Tx and RX queues
1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431
 *	@promiscuity:		Number of times, the NIC is told to work in
 *				Promiscuous mode, if it becomes 0 the NIC will
 *				exit from working in Promiscuous mode
 *	@allmulti:		Counter, enables or disables allmulticast mode
 *
 *	@vlan_info:	VLAN info
 *	@dsa_ptr:	dsa specific data
 *	@tipc_ptr:	TIPC specific data
 *	@atalk_ptr:	AppleTalk link
 *	@ip_ptr:	IPv4 specific data
 *	@dn_ptr:	DECnet specific data
 *	@ip6_ptr:	IPv6 specific data
 *	@ax25_ptr:	AX.25 specific data
 *	@ieee80211_ptr:	IEEE 802.11 specific data, assign before registering
 *
 *	@last_rx:	Time of last Rx
 *	@dev_addr:	Hw address (before bcast,
 *			because most packets are unicast)
 *
 *	@_rx:			Array of RX queues
 *	@num_rx_queues:		Number of RX queues
 *				allocated at register_netdev() time
 *	@real_num_rx_queues: 	Number of RX queues currently active in device
 *
 *	@rx_handler:		handler for received packets
 *	@rx_handler_data: 	XXX: need comments on this one
 *	@ingress_queue:		XXX: need comments on this one
 *	@broadcast:		hw bcast address
 *
1432 1433 1434 1435 1436 1437
 *	@rx_cpu_rmap:	CPU reverse-mapping for RX completion interrupts,
 *			indexed by RX queue number. Assigned by driver.
 *			This must only be set if the ndo_rx_flow_steer
 *			operation is defined
 *	@index_hlist:		Device index hash chain
 *
1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484
 *	@_tx:			Array of TX queues
 *	@num_tx_queues:		Number of TX queues allocated at alloc_netdev_mq() time
 *	@real_num_tx_queues: 	Number of TX queues currently active in device
 *	@qdisc:			Root qdisc from userspace point of view
 *	@tx_queue_len:		Max frames per queue allowed
 *	@tx_global_lock: 	XXX: need comments on this one
 *
 *	@xps_maps:	XXX: need comments on this one
 *
 *	@trans_start:		Time (in jiffies) of last Tx
 *	@watchdog_timeo:	Represents the timeout that is used by
 *				the watchdog ( see dev_watchdog() )
 *	@watchdog_timer:	List of timers
 *
 *	@pcpu_refcnt:		Number of references to this device
 *	@todo_list:		Delayed register/unregister
 *	@link_watch_list:	XXX: need comments on this one
 *
 *	@reg_state:		Register/unregister state machine
 *	@dismantle:		Device is going to be freed
 *	@rtnl_link_state:	This enum represents the phases of creating
 *				a new link
 *
 *	@destructor:		Called from unregister,
 *				can be used to call free_netdev
 *	@npinfo:		XXX: need comments on this one
 * 	@nd_net:		Network namespace this network device is inside
 *
 * 	@ml_priv:	Mid-layer private
 * 	@lstats:	Loopback statistics
 * 	@tstats:	Tunnel statistics
 * 	@dstats:	Dummy statistics
 * 	@vstats:	Virtual ethernet statistics
 *
 *	@garp_port:	GARP
 *	@mrp_port:	MRP
 *
 *	@dev:		Class/net/name entry
 *	@sysfs_groups:	Space for optional device, statistics and wireless
 *			sysfs groups
 *
 *	@sysfs_rx_queue_group:	Space for optional per-rx queue attributes
 *	@rtnl_link_ops:	Rtnl_link_ops
 *
 *	@gso_max_size:	Maximum size of generic segmentation offload
 *	@gso_max_segs:	Maximum number of segments that can be passed to the
 *			NIC for GSO
1485 1486
 *	@gso_min_segs:	Minimum number of segments that can be passed to the
 *			NIC for GSO
1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500
 *
 *	@dcbnl_ops:	Data Center Bridging netlink ops
 *	@num_tc:	Number of traffic classes in the net device
 *	@tc_to_txq:	XXX: need comments on this one
 *	@prio_tc_map	XXX: need comments on this one
 *
 *	@fcoe_ddp_xid:	Max exchange id for FCoE LRO by ddp
 *
 *	@priomap:	XXX: need comments on this one
 *	@phydev:	Physical device may attach itself
 *			for hardware timestamping
 *
 *	@qdisc_tx_busylock:	XXX: need comments on this one
 *
L
Linus Torvalds 已提交
1501 1502 1503 1504
 *	FIXME: cleanup struct net_device such that network protocol info
 *	moves out.
 */

E
Eric Dumazet 已提交
1505
struct net_device {
L
Linus Torvalds 已提交
1506
	char			name[IFNAMSIZ];
1507
	struct hlist_node	name_hlist;
1508
	char 			*ifalias;
L
Linus Torvalds 已提交
1509 1510 1511 1512
	/*
	 *	I/O specific fields
	 *	FIXME: Merge these and struct ifmap into one
	 */
1513 1514 1515 1516
	unsigned long		mem_end;
	unsigned long		mem_start;
	unsigned long		base_addr;
	int			irq;
L
Linus Torvalds 已提交
1517

1518 1519
	atomic_t		carrier_changes;

L
Linus Torvalds 已提交
1520
	/*
1521 1522
	 *	Some hardware also needs these fields (state,dev_list,
	 *	napi_list,unreg_list,close_list) but they are not
L
Linus Torvalds 已提交
1523 1524 1525 1526 1527
	 *	part of the usual set specified in Space.c.
	 */

	unsigned long		state;

1528
	struct list_head	dev_list;
1529
	struct list_head	napi_list;
1530
	struct list_head	unreg_list;
1531
	struct list_head	close_list;
1532 1533
	struct list_head	ptype_all;
	struct list_head	ptype_specific;
1534 1535 1536 1537 1538 1539 1540 1541 1542 1543

	struct {
		struct list_head upper;
		struct list_head lower;
	} adj_list;

	struct {
		struct list_head upper;
		struct list_head lower;
	} all_adj_list;
1544

1545 1546 1547 1548
	netdev_features_t	features;
	netdev_features_t	hw_features;
	netdev_features_t	wanted_features;
	netdev_features_t	vlan_features;
1549
	netdev_features_t	hw_enc_features;
S
Simon Horman 已提交
1550
	netdev_features_t	mpls_features;
1551

L
Linus Torvalds 已提交
1552
	int			ifindex;
1553
	int			group;
L
Linus Torvalds 已提交
1554

R
Rusty Russell 已提交
1555
	struct net_device_stats	stats;
1556 1557 1558

	atomic_long_t		rx_dropped;
	atomic_long_t		tx_dropped;
L
Linus Torvalds 已提交
1559

1560
#ifdef CONFIG_WIRELESS_EXT
L
Linus Torvalds 已提交
1561 1562
	const struct iw_handler_def *	wireless_handlers;
	struct iw_public_data *	wireless_data;
1563
#endif
1564
	const struct net_device_ops *netdev_ops;
1565
	const struct ethtool_ops *ethtool_ops;
S
Scott Feldman 已提交
1566
#ifdef CONFIG_NET_SWITCHDEV
J
Jiri Pirko 已提交
1567
	const struct switchdev_ops *switchdev_ops;
S
Scott Feldman 已提交
1568
#endif
L
Linus Torvalds 已提交
1569

1570 1571
	const struct header_ops *header_ops;

1572 1573 1574
	unsigned int		flags;
	unsigned int		priv_flags;

L
Linus Torvalds 已提交
1575
	unsigned short		gflags;
1576
	unsigned short		padded;
L
Linus Torvalds 已提交
1577

1578 1579
	unsigned char		operstate;
	unsigned char		link_mode;
S
Stefan Rompf 已提交
1580

1581 1582
	unsigned char		if_port;
	unsigned char		dma;
1583

1584 1585 1586
	unsigned int		mtu;
	unsigned short		type;
	unsigned short		hard_header_len;
L
Linus Torvalds 已提交
1587

1588 1589 1590
	unsigned short		needed_headroom;
	unsigned short		needed_tailroom;

L
Linus Torvalds 已提交
1591
	/* Interface address info. */
1592 1593 1594
	unsigned char		perm_addr[MAX_ADDR_LEN];
	unsigned char		addr_assign_type;
	unsigned char		addr_len;
1595
	unsigned short		neigh_priv_len;
1596 1597
	unsigned short          dev_id;
	unsigned short          dev_port;
J
Jiri Pirko 已提交
1598
	spinlock_t		addr_list_lock;
1599 1600
	unsigned char		name_assign_type;
	bool			uc_promisc;
1601 1602 1603 1604
	struct netdev_hw_addr_list	uc;
	struct netdev_hw_addr_list	mc;
	struct netdev_hw_addr_list	dev_addrs;

1605 1606 1607
#ifdef CONFIG_SYSFS
	struct kset		*queues_kset;
#endif
1608 1609
	unsigned int		promiscuity;
	unsigned int		allmulti;
L
Linus Torvalds 已提交
1610 1611 1612


	/* Protocol specific pointers */
1613

1614
#if IS_ENABLED(CONFIG_VLAN_8021Q)
1615
	struct vlan_info __rcu	*vlan_info;
1616
#endif
1617
#if IS_ENABLED(CONFIG_NET_DSA)
1618
	struct dsa_switch_tree	*dsa_ptr;
1619 1620
#endif
#if IS_ENABLED(CONFIG_TIPC)
1621
	struct tipc_bearer __rcu *tipc_ptr;
1622
#endif
1623 1624 1625 1626 1627 1628
	void 			*atalk_ptr;
	struct in_device __rcu	*ip_ptr;
	struct dn_dev __rcu     *dn_ptr;
	struct inet6_dev __rcu	*ip6_ptr;
	void			*ax25_ptr;
	struct wireless_dev	*ieee80211_ptr;
1629
	struct wpan_dev		*ieee802154_ptr;
R
Robert Shearman 已提交
1630 1631 1632
#if IS_ENABLED(CONFIG_MPLS_ROUTING)
	struct mpls_dev __rcu	*mpls_ptr;
#endif
L
Linus Torvalds 已提交
1633

1634
/*
E
Eric Dumazet 已提交
1635
 * Cache lines mostly used on receive path (including eth_type_trans())
1636
 */
1637
	unsigned long		last_rx;
1638

1639
	/* Interface address info used in eth_type_trans() */
1640
	unsigned char		*dev_addr;
1641

T
Tom Herbert 已提交
1642

1643
#ifdef CONFIG_SYSFS
T
Tom Herbert 已提交
1644 1645 1646
	struct netdev_rx_queue	*_rx;

	unsigned int		num_rx_queues;
1647
	unsigned int		real_num_rx_queues;
1648

E
Eric Dumazet 已提交
1649
#endif
T
Tom Herbert 已提交
1650

1651
	unsigned long		gro_flush_timeout;
1652 1653
	rx_handler_func_t __rcu	*rx_handler;
	void __rcu		*rx_handler_data;
1654

1655
#ifdef CONFIG_NET_CLS_ACT
1656 1657
	struct tcf_proto __rcu  *ingress_cl_list;
#endif
1658
	struct netdev_queue __rcu *ingress_queue;
1659 1660 1661
#ifdef CONFIG_NETFILTER_INGRESS
	struct list_head	nf_hooks_ingress;
#endif
1662

1663
	unsigned char		broadcast[MAX_ADDR_LEN];
1664 1665 1666 1667
#ifdef CONFIG_RFS_ACCEL
	struct cpu_rmap		*rx_cpu_rmap;
#endif
	struct hlist_node	index_hlist;
E
Eric Dumazet 已提交
1668 1669 1670 1671

/*
 * Cache lines mostly used on transmit path
 */
1672 1673
	struct netdev_queue	*_tx ____cacheline_aligned_in_smp;
	unsigned int		num_tx_queues;
1674
	unsigned int		real_num_tx_queues;
1675
	struct Qdisc		*qdisc;
1676
	unsigned long		tx_queue_len;
1677
	spinlock_t		tx_global_lock;
1678
	int			watchdog_timeo;
E
Eric Dumazet 已提交
1679

T
Tom Herbert 已提交
1680
#ifdef CONFIG_XPS
E
Eric Dumazet 已提交
1681
	struct xps_dev_maps __rcu *xps_maps;
T
Tom Herbert 已提交
1682
#endif
T
Tom Herbert 已提交
1683

1684
	/* These may be needed for future network-power-down code. */
1685 1686 1687 1688 1689

	/*
	 * trans_start here is expensive for high speed devices on SMP,
	 * please use netdev_queue->trans_start instead.
	 */
1690
	unsigned long		trans_start;
1691 1692 1693

	struct timer_list	watchdog_timer;

E
Eric Dumazet 已提交
1694
	int __percpu		*pcpu_refcnt;
L
Linus Torvalds 已提交
1695 1696
	struct list_head	todo_list;

1697
	struct list_head	link_watch_list;
1698

L
Linus Torvalds 已提交
1699
	enum { NETREG_UNINITIALIZED=0,
1700
	       NETREG_REGISTERED,	/* completed register_netdevice */
L
Linus Torvalds 已提交
1701 1702 1703
	       NETREG_UNREGISTERING,	/* called unregister_netdevice */
	       NETREG_UNREGISTERED,	/* completed unregister todo */
	       NETREG_RELEASED,		/* called free_netdev */
1704
	       NETREG_DUMMY,		/* dummy device for NAPI poll */
1705 1706
	} reg_state:8;

1707
	bool dismantle;
1708 1709 1710 1711 1712

	enum {
		RTNL_LINK_INITIALIZED,
		RTNL_LINK_INITIALIZING,
	} rtnl_link_state:16;
L
Linus Torvalds 已提交
1713

1714
	void (*destructor)(struct net_device *dev);
L
Linus Torvalds 已提交
1715 1716

#ifdef CONFIG_NETPOLL
1717
	struct netpoll_info __rcu	*npinfo;
L
Linus Torvalds 已提交
1718
#endif
1719

1720
	possible_net_t			nd_net;
1721

D
David S. Miller 已提交
1722
	/* mid-layer private */
E
Eric Dumazet 已提交
1723
	union {
1724 1725
		void					*ml_priv;
		struct pcpu_lstats __percpu		*lstats;
1726
		struct pcpu_sw_netstats __percpu	*tstats;
1727 1728
		struct pcpu_dstats __percpu		*dstats;
		struct pcpu_vstats __percpu		*vstats;
E
Eric Dumazet 已提交
1729
	};
1730

E
Eric Dumazet 已提交
1731
	struct garp_port __rcu	*garp_port;
1732
	struct mrp_port __rcu	*mrp_port;
L
Linus Torvalds 已提交
1733

1734
	struct device	dev;
1735
	const struct attribute_group *sysfs_groups[4];
1736
	const struct attribute_group *sysfs_rx_queue_group;
P
Patrick McHardy 已提交
1737 1738

	const struct rtnl_link_ops *rtnl_link_ops;
1739

1740 1741 1742
	/* for setting kernel sock attribute on TCP connection setup */
#define GSO_MAX_SIZE		65536
	unsigned int		gso_max_size;
1743 1744
#define GSO_MAX_SEGS		65535
	u16			gso_max_segs;
1745
	u16			gso_min_segs;
J
Jeff Kirsher 已提交
1746
#ifdef CONFIG_DCB
1747
	const struct dcbnl_rtnl_ops *dcbnl_ops;
1748
#endif
1749 1750 1751
	u8 num_tc;
	struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
	u8 prio_tc_map[TC_BITMASK + 1];
1752

1753
#if IS_ENABLED(CONFIG_FCOE)
1754
	unsigned int		fcoe_ddp_xid;
1755
#endif
1756
#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
1757
	struct netprio_map __rcu *priomap;
1758
#endif
1759
	struct phy_device *phydev;
1760
	struct lock_class_key *qdisc_tx_busylock;
L
Linus Torvalds 已提交
1761
};
1762
#define to_net_dev(d) container_of(d, struct net_device, dev)
L
Linus Torvalds 已提交
1763 1764 1765

#define	NETDEV_ALIGN		32

1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816
static inline
int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio)
{
	return dev->prio_tc_map[prio & TC_BITMASK];
}

static inline
int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc)
{
	if (tc >= dev->num_tc)
		return -EINVAL;

	dev->prio_tc_map[prio & TC_BITMASK] = tc & TC_BITMASK;
	return 0;
}

static inline
void netdev_reset_tc(struct net_device *dev)
{
	dev->num_tc = 0;
	memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq));
	memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map));
}

static inline
int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset)
{
	if (tc >= dev->num_tc)
		return -EINVAL;

	dev->tc_to_txq[tc].count = count;
	dev->tc_to_txq[tc].offset = offset;
	return 0;
}

static inline
int netdev_set_num_tc(struct net_device *dev, u8 num_tc)
{
	if (num_tc > TC_MAX_QUEUE)
		return -EINVAL;

	dev->num_tc = num_tc;
	return 0;
}

static inline
int netdev_get_num_tc(struct net_device *dev)
{
	return dev->num_tc;
}

1817 1818 1819 1820 1821 1822 1823
static inline
struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
					 unsigned int index)
{
	return &dev->_tx[index];
}

1824 1825 1826 1827 1828 1829
static inline struct netdev_queue *skb_get_tx_queue(const struct net_device *dev,
						    const struct sk_buff *skb)
{
	return netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
}

1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841
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);
}

1842
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
1843 1844
				    struct sk_buff *skb,
				    void *accel_priv);
1845

1846 1847 1848 1849 1850 1851
/*
 * Net namespace inlines
 */
static inline
struct net *dev_net(const struct net_device *dev)
{
E
Eric Dumazet 已提交
1852
	return read_pnet(&dev->nd_net);
1853 1854 1855
}

static inline
1856
void dev_net_set(struct net_device *dev, struct net *net)
1857
{
1858
	write_pnet(&dev->nd_net, net);
1859 1860
}

1861
static inline bool netdev_uses_dsa(struct net_device *dev)
1862
{
1863
#if IS_ENABLED(CONFIG_NET_DSA)
1864 1865
	if (dev->dsa_ptr != NULL)
		return dsa_uses_tagged_protocol(dev->dsa_ptr);
1866
#endif
1867
	return false;
1868 1869
}

1870 1871 1872 1873 1874 1875
/**
 *	netdev_priv - access network device private data
 *	@dev: network device
 *
 * Get network device private data
 */
1876
static inline void *netdev_priv(const struct net_device *dev)
L
Linus Torvalds 已提交
1877
{
1878
	return (char *)dev + ALIGN(sizeof(struct net_device), NETDEV_ALIGN);
L
Linus Torvalds 已提交
1879 1880 1881 1882 1883
}

/* Set the sysfs physical device reference for the network logical device
 * if set prior to registration will cause a symlink during initialization.
 */
1884
#define SET_NETDEV_DEV(net, pdev)	((net)->dev.parent = (pdev))
L
Linus Torvalds 已提交
1885

1886
/* Set the sysfs device type for the network logical device to allow
1887
 * fine-grained identification of different network device types. For
1888 1889 1890 1891
 * example Ethernet, Wirelss LAN, Bluetooth, WiMAX etc.
 */
#define SET_NETDEV_DEVTYPE(net, devtype)	((net)->dev.type = (devtype))

E
Eric Dumazet 已提交
1892 1893 1894 1895 1896
/* Default NAPI poll() weight
 * Device drivers are strongly advised to not use bigger value
 */
#define NAPI_POLL_WEIGHT 64

1897 1898 1899 1900 1901 1902 1903 1904 1905 1906
/**
 *	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.
 */
1907 1908
void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
		    int (*poll)(struct napi_struct *, int), int weight);
1909

1910 1911 1912 1913 1914 1915
/**
 *  netif_napi_del - remove a napi context
 *  @napi: napi context
 *
 *  netif_napi_del() removes a napi context from the network device napi list
 */
1916 1917 1918
void netif_napi_del(struct napi_struct *napi);

struct napi_gro_cb {
1919 1920 1921
	/* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */
	void *frag0;

1922 1923 1924
	/* Length of frag0. */
	unsigned int frag0_len;

1925 1926 1927
	/* This indicates where we are processing relative to skb->data. */
	int data_offset;

1928
	/* This is non-zero if the packet cannot be merged with the new skb. */
1929 1930 1931 1932
	u16	flush;

	/* Save the IP ID here and check when we get to the transport layer */
	u16	flush_id;
1933 1934

	/* Number of segments aggregated. */
1935 1936
	u16	count;

1937 1938 1939
	/* Start offset for remote checksum offload */
	u16	gro_remcsum_start;

1940 1941
	/* jiffies when first packet was created/queued */
	unsigned long age;
1942

T
Tom Herbert 已提交
1943
	/* Used in ipv6_gro_receive() and foo-over-udp */
1944 1945
	u16	proto;

1946 1947 1948
	/* This is non-zero if the packet may be of the same flow. */
	u8	same_flow:1;

1949
	/* Used in udp_gro_receive */
T
Tom Herbert 已提交
1950 1951 1952 1953 1954
	u8	udp_mark:1;

	/* GRO checksum is valid */
	u8	csum_valid:1;

1955 1956
	/* Number of checksums via CHECKSUM_UNNECESSARY */
	u8	csum_cnt:3;
1957

1958 1959 1960 1961 1962
	/* Free the skb? */
	u8	free:2;
#define NAPI_GRO_FREE		  1
#define NAPI_GRO_FREE_STOLEN_HEAD 2

1963 1964 1965
	/* Used in foo-over-udp, set in udp[46]_gro_receive */
	u8	is_ipv6:1;

1966 1967
	/* 7 bit hole */

1968 1969 1970
	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
	__wsum	csum;

1971 1972
	/* used in skb_gro_receive() slow path */
	struct sk_buff *last;
1973 1974 1975
};

#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
1976

L
Linus Torvalds 已提交
1977
struct packet_type {
D
David S. Miller 已提交
1978 1979 1980 1981 1982 1983
	__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 *);
1984 1985
	bool			(*id_match)(struct packet_type *ptype,
					    struct sock *sk);
L
Linus Torvalds 已提交
1986 1987 1988 1989
	void			*af_packet_priv;
	struct list_head	list;
};

1990
struct offload_callbacks {
1991
	struct sk_buff		*(*gso_segment)(struct sk_buff *skb,
1992
						netdev_features_t features);
1993
	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
1994
						 struct sk_buff *skb);
1995
	int			(*gro_complete)(struct sk_buff *skb, int nhoff);
1996 1997 1998 1999
};

struct packet_offload {
	__be16			 type;	/* This is really htons(ether_type). */
2000
	u16			 priority;
2001 2002
	struct offload_callbacks callbacks;
	struct list_head	 list;
L
Linus Torvalds 已提交
2003 2004
};

2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015
struct udp_offload;

struct udp_offload_callbacks {
	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
						 struct sk_buff *skb,
						 struct udp_offload *uoff);
	int			(*gro_complete)(struct sk_buff *skb,
						int nhoff,
						struct udp_offload *uoff);
};

2016 2017
struct udp_offload {
	__be16			 port;
T
Tom Herbert 已提交
2018
	u8			 ipproto;
2019
	struct udp_offload_callbacks callbacks;
2020 2021
};

2022 2023 2024 2025 2026 2027 2028 2029 2030
/* often modified stats are per cpu, other are shared (netdev->stats) */
struct pcpu_sw_netstats {
	u64     rx_packets;
	u64     rx_bytes;
	u64     tx_packets;
	u64     tx_bytes;
	struct u64_stats_sync   syncp;
};

2031 2032
#define netdev_alloc_pcpu_stats(type)				\
({								\
2033
	typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \
2034
	if (pcpu_stats)	{					\
2035 2036
		int __cpu;					\
		for_each_possible_cpu(__cpu) {			\
2037
			typeof(type) *stat;			\
2038
			stat = per_cpu_ptr(pcpu_stats, __cpu);	\
2039 2040 2041 2042 2043 2044
			u64_stats_init(&stat->syncp);		\
		}						\
	}							\
	pcpu_stats;						\
})

L
Linus Torvalds 已提交
2045 2046
#include <linux/notifier.h>

2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059
/* netdevice notifier chain. Please remember to update the rtnetlink
 * notification exclusion list in rtnetlink_event() when adding new
 * types.
 */
#define NETDEV_UP	0x0001	/* For now you can't veto a device up/down */
#define NETDEV_DOWN	0x0002
#define NETDEV_REBOOT	0x0003	/* Tell a protocol stack a network interface
				   detected a hardware crash and restarted
				   - we can use this eg to kick tcp sessions
				   once done */
#define NETDEV_CHANGE	0x0004	/* Notify device state change */
#define NETDEV_REGISTER 0x0005
#define NETDEV_UNREGISTER	0x0006
2060
#define NETDEV_CHANGEMTU	0x0007 /* notify after mtu change happened */
2061 2062 2063 2064 2065 2066 2067 2068 2069
#define NETDEV_CHANGEADDR	0x0008
#define NETDEV_GOING_DOWN	0x0009
#define NETDEV_CHANGENAME	0x000A
#define NETDEV_FEAT_CHANGE	0x000B
#define NETDEV_BONDING_FAILOVER 0x000C
#define NETDEV_PRE_UP		0x000D
#define NETDEV_PRE_TYPE_CHANGE	0x000E
#define NETDEV_POST_TYPE_CHANGE	0x000F
#define NETDEV_POST_INIT	0x0010
2070
#define NETDEV_UNREGISTER_FINAL 0x0011
2071 2072 2073
#define NETDEV_RELEASE		0x0012
#define NETDEV_NOTIFY_PEERS	0x0013
#define NETDEV_JOIN		0x0014
2074
#define NETDEV_CHANGEUPPER	0x0015
2075
#define NETDEV_RESEND_IGMP	0x0016
2076
#define NETDEV_PRECHANGEMTU	0x0017 /* notify before mtu change happened */
2077
#define NETDEV_CHANGEINFODATA	0x0018
2078
#define NETDEV_BONDING_INFO	0x0019
2079

2080 2081
int register_netdevice_notifier(struct notifier_block *nb);
int unregister_netdevice_notifier(struct notifier_block *nb);
2082 2083 2084 2085 2086

struct netdev_notifier_info {
	struct net_device *dev;
};

2087 2088 2089 2090 2091
struct netdev_notifier_change_info {
	struct netdev_notifier_info info; /* must be first */
	unsigned int flags_changed;
};

2092 2093 2094 2095 2096 2097
static inline void netdev_notifier_info_init(struct netdev_notifier_info *info,
					     struct net_device *dev)
{
	info->dev = dev;
}

2098 2099 2100 2101 2102 2103
static inline struct net_device *
netdev_notifier_info_to_dev(const struct netdev_notifier_info *info)
{
	return info->dev;
}

2104
int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
2105 2106


L
Linus Torvalds 已提交
2107 2108
extern rwlock_t				dev_base_lock;		/* Device list lock */

2109 2110
#define for_each_netdev(net, d)		\
		list_for_each_entry(d, &(net)->dev_base_head, dev_list)
2111 2112
#define for_each_netdev_reverse(net, d)	\
		list_for_each_entry_reverse(d, &(net)->dev_base_head, dev_list)
2113 2114
#define for_each_netdev_rcu(net, d)		\
		list_for_each_entry_rcu(d, &(net)->dev_base_head, dev_list)
2115 2116 2117 2118
#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)
2119 2120
#define for_each_netdev_continue_rcu(net, d)		\
	list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list)
2121 2122
#define for_each_netdev_in_bond_rcu(bond, slave)	\
		for_each_netdev_rcu(&init_net, slave)	\
2123
			if (netdev_master_upper_dev_get_rcu(slave) == (bond))
2124
#define net_device_entry(lh)	list_entry(lh, struct net_device, dev_list)
2125

2126 2127 2128 2129 2130
static inline struct net_device *next_net_device(struct net_device *dev)
{
	struct list_head *lh;
	struct net *net;

2131
	net = dev_net(dev);
2132 2133 2134 2135
	lh = dev->dev_list.next;
	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
}

2136 2137 2138 2139 2140 2141
static inline struct net_device *next_net_device_rcu(struct net_device *dev)
{
	struct list_head *lh;
	struct net *net;

	net = dev_net(dev);
E
Eric Dumazet 已提交
2142
	lh = rcu_dereference(list_next_rcu(&dev->dev_list));
2143 2144 2145
	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
}

2146 2147 2148 2149 2150
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);
}
2151

E
Eric Dumazet 已提交
2152 2153 2154 2155 2156 2157 2158
static inline struct net_device *first_net_device_rcu(struct net *net)
{
	struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head));

	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
}

2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170
int netdev_boot_setup_check(struct net_device *dev);
unsigned long netdev_boot_base(const char *prefix, int unit);
struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
				       const char *hwaddr);
struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type);
struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type);
void dev_add_pack(struct packet_type *pt);
void dev_remove_pack(struct packet_type *pt);
void __dev_remove_pack(struct packet_type *pt);
void dev_add_offload(struct packet_offload *po);
void dev_remove_offload(struct packet_offload *po);

2171
int dev_get_iflink(const struct net_device *dev);
2172 2173
struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
				      unsigned short mask);
2174 2175 2176 2177 2178 2179
struct net_device *dev_get_by_name(struct net *net, const char *name);
struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
struct net_device *__dev_get_by_name(struct net *net, const char *name);
int dev_alloc_name(struct net_device *dev, const char *name);
int dev_open(struct net_device *dev);
int dev_close(struct net_device *dev);
2180
int dev_close_many(struct list_head *head, bool unlink);
2181
void dev_disable_lro(struct net_device *dev);
2182 2183 2184 2185 2186 2187
int dev_loopback_xmit(struct sock *sk, struct sk_buff *newskb);
int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb);
static inline int dev_queue_xmit(struct sk_buff *skb)
{
	return dev_queue_xmit_sk(skb->sk, skb);
}
2188
int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv);
2189 2190 2191
int register_netdevice(struct net_device *dev);
void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
void unregister_netdevice_many(struct list_head *head);
2192 2193 2194 2195 2196
static inline void unregister_netdevice(struct net_device *dev)
{
	unregister_netdevice_queue(dev, NULL);
}

2197 2198
int netdev_refcnt_read(const struct net_device *dev);
void free_netdev(struct net_device *dev);
2199
void netdev_freemem(struct net_device *dev);
2200 2201
void synchronize_net(void);
int init_dummy_netdev(struct net_device *dev);
2202

2203 2204 2205 2206 2207 2208
DECLARE_PER_CPU(int, xmit_recursion);
static inline int dev_recursion_level(void)
{
	return this_cpu_read(xmit_recursion);
}

2209 2210 2211 2212 2213 2214
struct net_device *dev_get_by_index(struct net *net, int ifindex);
struct net_device *__dev_get_by_index(struct net *net, int ifindex);
struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
int netdev_get_name(struct net *net, char *name, int ifindex);
int dev_restart(struct net_device *dev);
int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb);
2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230

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;
}

2231 2232
static inline void *skb_gro_header_fast(struct sk_buff *skb,
					unsigned int offset)
2233
{
2234 2235
	return NAPI_GRO_CB(skb)->frag0 + offset;
}
2236

2237 2238 2239 2240
static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen)
{
	return NAPI_GRO_CB(skb)->frag0_len < hlen;
}
2241

2242 2243 2244
static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen,
					unsigned int offset)
{
2245 2246 2247
	if (!pskb_may_pull(skb, hlen))
		return NULL;

2248 2249
	NAPI_GRO_CB(skb)->frag0 = NULL;
	NAPI_GRO_CB(skb)->frag0_len = 0;
2250
	return skb->data + offset;
2251
}
L
Linus Torvalds 已提交
2252

H
Herbert Xu 已提交
2253 2254
static inline void *skb_gro_network_header(struct sk_buff *skb)
{
2255 2256
	return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) +
	       skb_network_offset(skb);
H
Herbert Xu 已提交
2257 2258
}

2259 2260 2261
static inline void skb_gro_postpull_rcsum(struct sk_buff *skb,
					const void *start, unsigned int len)
{
T
Tom Herbert 已提交
2262
	if (NAPI_GRO_CB(skb)->csum_valid)
2263 2264 2265 2266
		NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum,
						  csum_partial(start, len, 0));
}

T
Tom Herbert 已提交
2267 2268 2269 2270 2271 2272 2273
/* GRO checksum functions. These are logical equivalents of the normal
 * checksum functions (in skbuff.h) except that they operate on the GRO
 * offsets and fields in sk_buff.
 */

__sum16 __skb_gro_checksum_complete(struct sk_buff *skb);

2274 2275 2276 2277 2278 2279
static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb)
{
	return (NAPI_GRO_CB(skb)->gro_remcsum_start - skb_headroom(skb) ==
		skb_gro_offset(skb));
}

T
Tom Herbert 已提交
2280 2281 2282 2283
static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb,
						      bool zero_okay,
						      __sum16 check)
{
2284 2285 2286
	return ((skb->ip_summed != CHECKSUM_PARTIAL ||
		skb_checksum_start_offset(skb) <
		 skb_gro_offset(skb)) &&
2287
		!skb_at_gro_remcsum_start(skb) &&
2288
		NAPI_GRO_CB(skb)->csum_cnt == 0 &&
T
Tom Herbert 已提交
2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305
		(!zero_okay || check));
}

static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb,
							   __wsum psum)
{
	if (NAPI_GRO_CB(skb)->csum_valid &&
	    !csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum)))
		return 0;

	NAPI_GRO_CB(skb)->csum = psum;

	return __skb_gro_checksum_complete(skb);
}

static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb)
{
2306 2307 2308 2309 2310 2311 2312 2313 2314
	if (NAPI_GRO_CB(skb)->csum_cnt > 0) {
		/* Consume a checksum from CHECKSUM_UNNECESSARY */
		NAPI_GRO_CB(skb)->csum_cnt--;
	} else {
		/* Update skb for CHECKSUM_UNNECESSARY and csum_level when we
		 * verified a new top level checksum or an encapsulated one
		 * during GRO. This saves work if we fallback to normal path.
		 */
		__skb_incr_checksum_unnecessary(skb);
T
Tom Herbert 已提交
2315 2316 2317 2318 2319 2320 2321 2322 2323 2324
	}
}

#define __skb_gro_checksum_validate(skb, proto, zero_okay, check,	\
				    compute_pseudo)			\
({									\
	__sum16 __ret = 0;						\
	if (__skb_gro_checksum_validate_needed(skb, zero_okay, check))	\
		__ret = __skb_gro_checksum_validate_complete(skb,	\
				compute_pseudo(skb, proto));		\
2325 2326 2327
	if (__ret)							\
		__skb_mark_checksum_bad(skb);				\
	else								\
T
Tom Herbert 已提交
2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341
		skb_gro_incr_csum_unnecessary(skb);			\
	__ret;								\
})

#define skb_gro_checksum_validate(skb, proto, compute_pseudo)		\
	__skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo)

#define skb_gro_checksum_validate_zero_check(skb, proto, check,		\
					     compute_pseudo)		\
	__skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo)

#define skb_gro_checksum_simple_validate(skb)				\
	__skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo)

2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361
static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb)
{
	return (NAPI_GRO_CB(skb)->csum_cnt == 0 &&
		!NAPI_GRO_CB(skb)->csum_valid);
}

static inline void __skb_gro_checksum_convert(struct sk_buff *skb,
					      __sum16 check, __wsum pseudo)
{
	NAPI_GRO_CB(skb)->csum = ~pseudo;
	NAPI_GRO_CB(skb)->csum_valid = 1;
}

#define skb_gro_checksum_try_convert(skb, proto, check, compute_pseudo)	\
do {									\
	if (__skb_gro_checksum_convert_check(skb))			\
		__skb_gro_checksum_convert(skb, check,			\
					   compute_pseudo(skb, proto));	\
} while (0)

2362 2363 2364 2365 2366 2367 2368
struct gro_remcsum {
	int offset;
	__wsum delta;
};

static inline void skb_gro_remcsum_init(struct gro_remcsum *grc)
{
2369
	grc->offset = 0;
2370 2371 2372
	grc->delta = 0;
}

2373
static inline void skb_gro_remcsum_process(struct sk_buff *skb, void *ptr,
2374
					   int start, int offset,
2375 2376
					   struct gro_remcsum *grc,
					   bool nopartial)
2377 2378 2379 2380 2381
{
	__wsum delta;

	BUG_ON(!NAPI_GRO_CB(skb)->csum_valid);

2382 2383 2384 2385 2386 2387
	if (!nopartial) {
		NAPI_GRO_CB(skb)->gro_remcsum_start =
		    ((unsigned char *)ptr + start) - skb->head;
		return;
	}

2388 2389 2390 2391
	delta = remcsum_adjust(ptr, NAPI_GRO_CB(skb)->csum, start, offset);

	/* Adjust skb->csum since we changed the packet */
	NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta);
2392 2393 2394

	grc->offset = (ptr + offset) - (void *)skb->head;
	grc->delta = delta;
2395 2396
}

2397 2398 2399 2400 2401 2402 2403 2404
static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb,
					   struct gro_remcsum *grc)
{
	if (!grc->delta)
		return;

	remcsum_unadjust((__sum16 *)(skb->head + grc->offset), grc->delta);
}
2405

2406 2407
static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
				  unsigned short type,
2408
				  const void *daddr, const void *saddr,
2409
				  unsigned int len)
2410
{
2411
	if (!dev->header_ops || !dev->header_ops->create)
2412
		return 0;
2413 2414

	return dev->header_ops->create(skb, dev, type, daddr, saddr, len);
2415 2416
}

S
Stephen Hemminger 已提交
2417 2418 2419 2420 2421
static inline int dev_parse_header(const struct sk_buff *skb,
				   unsigned char *haddr)
{
	const struct net_device *dev = skb->dev;

2422
	if (!dev->header_ops || !dev->header_ops->parse)
S
Stephen Hemminger 已提交
2423
		return 0;
2424
	return dev->header_ops->parse(skb, haddr);
S
Stephen Hemminger 已提交
2425 2426
}

L
Linus Torvalds 已提交
2427
typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
2428
int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
L
Linus Torvalds 已提交
2429 2430 2431 2432 2433
static inline int unregister_gifconf(unsigned int family)
{
	return register_gifconf(family, NULL);
}

2434
#ifdef CONFIG_NET_FLOW_LIMIT
2435
#define FLOW_LIMIT_HISTORY	(1 << 7)  /* must be ^2 and !overflow buckets */
2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446
struct sd_flow_limit {
	u64			count;
	unsigned int		num_buckets;
	unsigned int		history_head;
	u16			history[FLOW_LIMIT_HISTORY];
	u8			buckets[];
};

extern int netdev_flow_limit_table_len;
#endif /* CONFIG_NET_FLOW_LIMIT */

L
Linus Torvalds 已提交
2447
/*
E
Eric Dumazet 已提交
2448
 * Incoming packets are placed on per-cpu queues
L
Linus Torvalds 已提交
2449
 */
E
Eric Dumazet 已提交
2450
struct softnet_data {
L
Linus Torvalds 已提交
2451
	struct list_head	poll_list;
2452
	struct sk_buff_head	process_queue;
L
Linus Torvalds 已提交
2453

C
Changli Gao 已提交
2454
	/* stats */
2455 2456 2457 2458
	unsigned int		processed;
	unsigned int		time_squeeze;
	unsigned int		cpu_collision;
	unsigned int		received_rps;
2459
#ifdef CONFIG_RPS
E
Eric Dumazet 已提交
2460
	struct softnet_data	*rps_ipi_list;
E
Eric Dumazet 已提交
2461 2462 2463 2464 2465 2466 2467
#endif
#ifdef CONFIG_NET_FLOW_LIMIT
	struct sd_flow_limit __rcu *flow_limit;
#endif
	struct Qdisc		*output_queue;
	struct Qdisc		**output_queue_tailp;
	struct sk_buff		*completion_queue;
E
Eric Dumazet 已提交
2468

E
Eric Dumazet 已提交
2469
#ifdef CONFIG_RPS
E
Eric Dumazet 已提交
2470
	/* Elements below can be accessed between CPUs for RPS */
T
Tom Herbert 已提交
2471
	struct call_single_data	csd ____cacheline_aligned_in_smp;
E
Eric Dumazet 已提交
2472 2473
	struct softnet_data	*rps_ipi_next;
	unsigned int		cpu;
T
Tom Herbert 已提交
2474
	unsigned int		input_queue_head;
2475
	unsigned int		input_queue_tail;
2476
#endif
2477
	unsigned int		dropped;
T
Tom Herbert 已提交
2478
	struct sk_buff_head	input_pkt_queue;
2479
	struct napi_struct	backlog;
2480

L
Linus Torvalds 已提交
2481 2482
};

2483
static inline void input_queue_head_incr(struct softnet_data *sd)
T
Tom Herbert 已提交
2484 2485
{
#ifdef CONFIG_RPS
2486 2487 2488 2489 2490 2491 2492 2493 2494
	sd->input_queue_head++;
#endif
}

static inline void input_queue_tail_incr_save(struct softnet_data *sd,
					      unsigned int *qtail)
{
#ifdef CONFIG_RPS
	*qtail = ++sd->input_queue_tail;
T
Tom Herbert 已提交
2495 2496 2497
#endif
}

T
Tom Herbert 已提交
2498
DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
L
Linus Torvalds 已提交
2499

2500
void __netif_schedule(struct Qdisc *q);
2501
void netif_schedule_queue(struct netdev_queue *txq);
2502

2503 2504 2505 2506 2507 2508 2509 2510
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));
}

2511 2512
static inline void netif_tx_start_queue(struct netdev_queue *dev_queue)
{
2513
	clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
2514 2515
}

2516 2517 2518 2519 2520 2521
/**
 *	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
2522 2523
static inline void netif_start_queue(struct net_device *dev)
{
2524
	netif_tx_start_queue(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
2525 2526
}

2527 2528 2529 2530 2531 2532 2533 2534 2535 2536
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);
	}
}

2537
void netif_tx_wake_queue(struct netdev_queue *dev_queue);
2538

2539 2540 2541 2542 2543 2544 2545
/**
 *	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.
 */
2546 2547
static inline void netif_wake_queue(struct net_device *dev)
{
2548
	netif_tx_wake_queue(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
2549 2550
}

2551 2552 2553 2554 2555 2556 2557 2558 2559 2560
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);
	}
}

2561 2562
static inline void netif_tx_stop_queue(struct netdev_queue *dev_queue)
{
2563
	set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
2564 2565
}

2566 2567 2568 2569 2570 2571 2572
/**
 *	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
2573 2574
static inline void netif_stop_queue(struct net_device *dev)
{
2575
	netif_tx_stop_queue(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
2576 2577
}

2578
void netif_tx_stop_all_queues(struct net_device *dev);
2579

2580
static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue)
2581
{
2582
	return test_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
2583 2584
}

2585 2586 2587 2588 2589 2590
/**
 *	netif_queue_stopped - test if transmit queue is flowblocked
 *	@dev: network device
 *
 *	Test if transmit queue on device is currently unable to send.
 */
2591
static inline bool netif_queue_stopped(const struct net_device *dev)
L
Linus Torvalds 已提交
2592
{
2593
	return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
2594 2595
}

2596
static inline bool netif_xmit_stopped(const struct netdev_queue *dev_queue)
2597
{
2598 2599 2600
	return dev_queue->state & QUEUE_STATE_ANY_XOFF;
}

2601 2602
static inline bool
netif_xmit_frozen_or_stopped(const struct netdev_queue *dev_queue)
2603 2604 2605 2606
{
	return dev_queue->state & QUEUE_STATE_ANY_XOFF_OR_FROZEN;
}

2607 2608 2609 2610 2611 2612
static inline bool
netif_xmit_frozen_or_drv_stopped(const struct netdev_queue *dev_queue)
{
	return dev_queue->state & QUEUE_STATE_DRV_XOFF_OR_FROZEN;
}

2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640
/**
 *	netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write
 *	@dev_queue: pointer to transmit queue
 *
 * BQL enabled drivers might use this helper in their ndo_start_xmit(),
 * to give appropriate hint to the cpu.
 */
static inline void netdev_txq_bql_enqueue_prefetchw(struct netdev_queue *dev_queue)
{
#ifdef CONFIG_BQL
	prefetchw(&dev_queue->dql.num_queued);
#endif
}

/**
 *	netdev_txq_bql_complete_prefetchw - prefetch bql data for write
 *	@dev_queue: pointer to transmit queue
 *
 * BQL enabled drivers might use this helper in their TX completion path,
 * to give appropriate hint to the cpu.
 */
static inline void netdev_txq_bql_complete_prefetchw(struct netdev_queue *dev_queue)
{
#ifdef CONFIG_BQL
	prefetchw(&dev_queue->dql.limit);
#endif
}

2641 2642 2643
static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
					unsigned int bytes)
{
T
Tom Herbert 已提交
2644 2645
#ifdef CONFIG_BQL
	dql_queued(&dev_queue->dql, bytes);
2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661

	if (likely(dql_avail(&dev_queue->dql) >= 0))
		return;

	set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);

	/*
	 * The XOFF flag must be set before checking the dql_avail below,
	 * because in netdev_tx_completed_queue we update the dql_completed
	 * before checking the XOFF flag.
	 */
	smp_mb();

	/* check again in case another CPU has just made room avail */
	if (unlikely(dql_avail(&dev_queue->dql) >= 0))
		clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
T
Tom Herbert 已提交
2662
#endif
2663 2664
}

2665 2666 2667 2668 2669 2670 2671 2672 2673
/**
 * 	netdev_sent_queue - report the number of bytes queued to hardware
 * 	@dev: network device
 * 	@bytes: number of bytes queued to the hardware device queue
 *
 * 	Report the number of bytes queued for sending/completion to the network
 * 	device hardware queue. @bytes should be a good approximation and should
 * 	exactly match netdev_completed_queue() @bytes
 */
2674 2675 2676 2677 2678 2679
static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes)
{
	netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes);
}

static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue,
2680
					     unsigned int pkts, unsigned int bytes)
2681
{
T
Tom Herbert 已提交
2682
#ifdef CONFIG_BQL
2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699
	if (unlikely(!bytes))
		return;

	dql_completed(&dev_queue->dql, bytes);

	/*
	 * Without the memory barrier there is a small possiblity that
	 * netdev_tx_sent_queue will miss the update and cause the queue to
	 * be stopped forever
	 */
	smp_mb();

	if (dql_avail(&dev_queue->dql) < 0)
		return;

	if (test_and_clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state))
		netif_schedule_queue(dev_queue);
T
Tom Herbert 已提交
2700
#endif
2701 2702
}

2703 2704 2705 2706 2707 2708 2709 2710 2711 2712
/**
 * 	netdev_completed_queue - report bytes and packets completed by device
 * 	@dev: network device
 * 	@pkts: actual number of packets sent over the medium
 * 	@bytes: actual number of bytes sent over the medium
 *
 * 	Report the number of bytes and packets transmitted by the network device
 * 	hardware queue over the physical medium, @bytes must exactly match the
 * 	@bytes amount passed to netdev_sent_queue()
 */
2713
static inline void netdev_completed_queue(struct net_device *dev,
2714
					  unsigned int pkts, unsigned int bytes)
2715 2716 2717 2718 2719 2720
{
	netdev_tx_completed_queue(netdev_get_tx_queue(dev, 0), pkts, bytes);
}

static inline void netdev_tx_reset_queue(struct netdev_queue *q)
{
T
Tom Herbert 已提交
2721
#ifdef CONFIG_BQL
2722
	clear_bit(__QUEUE_STATE_STACK_XOFF, &q->state);
T
Tom Herbert 已提交
2723 2724
	dql_reset(&q->dql);
#endif
2725 2726
}

2727 2728 2729 2730 2731 2732 2733
/**
 * 	netdev_reset_queue - reset the packets and bytes count of a network device
 * 	@dev_queue: network device
 *
 * 	Reset the bytes and packet count of a network device and clear the
 * 	software flow control OFF bit for this network device
 */
2734 2735 2736
static inline void netdev_reset_queue(struct net_device *dev_queue)
{
	netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0));
2737 2738
}

2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758
/**
 * 	netdev_cap_txqueue - check if selected tx queue exceeds device queues
 * 	@dev: network device
 * 	@queue_index: given tx queue index
 *
 * 	Returns 0 if given tx queue index >= number of device tx queues,
 * 	otherwise returns the originally passed tx queue index.
 */
static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index)
{
	if (unlikely(queue_index >= dev->real_num_tx_queues)) {
		net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
				     dev->name, queue_index,
				     dev->real_num_tx_queues);
		return 0;
	}

	return queue_index;
}

2759 2760 2761 2762 2763 2764
/**
 *	netif_running - test if up
 *	@dev: network device
 *
 *	Test if the device has been brought up.
 */
2765
static inline bool netif_running(const struct net_device *dev)
L
Linus Torvalds 已提交
2766 2767 2768 2769
{
	return test_bit(__LINK_STATE_START, &dev->state);
}

2770 2771 2772 2773 2774 2775
/*
 * 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.
 */
2776 2777 2778 2779 2780 2781 2782 2783

/**
 *	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.
 */
2784 2785
static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index)
{
2786
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
2787 2788

	netif_tx_start_queue(txq);
2789 2790
}

2791 2792 2793 2794 2795 2796 2797
/**
 *	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.
 */
2798 2799
static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index)
{
2800
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
2801
	netif_tx_stop_queue(txq);
2802 2803
}

2804 2805 2806 2807 2808 2809 2810
/**
 *	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.
 */
2811 2812
static inline bool __netif_subqueue_stopped(const struct net_device *dev,
					    u16 queue_index)
2813
{
2814
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
2815 2816

	return netif_tx_queue_stopped(txq);
2817 2818
}

2819 2820
static inline bool netif_subqueue_stopped(const struct net_device *dev,
					  struct sk_buff *skb)
2821 2822 2823
{
	return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb));
}
2824

2825
void netif_wake_subqueue(struct net_device *dev, u16 queue_index);
2826

2827
#ifdef CONFIG_XPS
2828
int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
2829
			u16 index);
2830 2831
#else
static inline int netif_set_xps_queue(struct net_device *dev,
2832
				      const struct cpumask *mask,
2833 2834 2835 2836 2837 2838
				      u16 index)
{
	return 0;
}
#endif

J
Jiri Pirko 已提交
2839 2840 2841
u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
		  unsigned int num_tx_queues);

2842 2843 2844 2845 2846
/*
 * Returns a Tx hash for the given packet when dev->real_num_tx_queues is used
 * as a distribution range limit for the returned value.
 */
static inline u16 skb_tx_hash(const struct net_device *dev,
2847
			      struct sk_buff *skb)
2848 2849 2850 2851
{
	return __skb_tx_hash(dev, skb, dev->real_num_tx_queues);
}

2852 2853 2854 2855 2856 2857
/**
 *	netif_is_multiqueue - test if device has multiple transmit queues
 *	@dev: network device
 *
 * Check if device has multiple transmit queues
 */
2858
static inline bool netif_is_multiqueue(const struct net_device *dev)
2859
{
E
Eric Dumazet 已提交
2860
	return dev->num_tx_queues > 1;
2861
}
L
Linus Torvalds 已提交
2862

2863
int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq);
2864

2865
#ifdef CONFIG_SYSFS
2866
int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq);
2867 2868 2869 2870 2871 2872 2873 2874
#else
static inline int netif_set_real_num_rx_queues(struct net_device *dev,
						unsigned int rxq)
{
	return 0;
}
#endif

2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886
#ifdef CONFIG_SYSFS
static inline unsigned int get_netdev_rx_queue_index(
		struct netdev_rx_queue *queue)
{
	struct net_device *dev = queue->dev;
	int index = queue - dev->_rx;

	BUG_ON(index >= dev->num_rx_queues);
	return index;
}
#endif

2887
#define DEFAULT_MAX_NUM_RSS_QUEUES	(8)
2888
int netif_get_num_default_rss_queues(void);
2889

2890 2891 2892 2893 2894 2895 2896
enum skb_free_reason {
	SKB_REASON_CONSUMED,
	SKB_REASON_DROPPED,
};

void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason);
void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason);
L
Linus Torvalds 已提交
2897

2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915
/*
 * It is not allowed to call kfree_skb() or consume_skb() from hardware
 * interrupt context or with hardware interrupts being disabled.
 * (in_irq() || irqs_disabled())
 *
 * We provide four helpers that can be used in following contexts :
 *
 * dev_kfree_skb_irq(skb) when caller drops a packet from irq context,
 *  replacing kfree_skb(skb)
 *
 * dev_consume_skb_irq(skb) when caller consumes a packet from irq context.
 *  Typically used in place of consume_skb(skb) in TX completion path
 *
 * dev_kfree_skb_any(skb) when caller doesn't know its current irq context,
 *  replacing kfree_skb(skb)
 *
 * dev_consume_skb_any(skb) when caller doesn't know its current irq context,
 *  and consumed a packet. Used in place of consume_skb(skb)
L
Linus Torvalds 已提交
2916
 */
2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935
static inline void dev_kfree_skb_irq(struct sk_buff *skb)
{
	__dev_kfree_skb_irq(skb, SKB_REASON_DROPPED);
}

static inline void dev_consume_skb_irq(struct sk_buff *skb)
{
	__dev_kfree_skb_irq(skb, SKB_REASON_CONSUMED);
}

static inline void dev_kfree_skb_any(struct sk_buff *skb)
{
	__dev_kfree_skb_any(skb, SKB_REASON_DROPPED);
}

static inline void dev_consume_skb_any(struct sk_buff *skb)
{
	__dev_kfree_skb_any(skb, SKB_REASON_CONSUMED);
}
L
Linus Torvalds 已提交
2936

2937 2938
int netif_rx(struct sk_buff *skb);
int netif_rx_ni(struct sk_buff *skb);
2939 2940 2941 2942 2943
int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb);
static inline int netif_receive_skb(struct sk_buff *skb)
{
	return netif_receive_skb_sk(skb->sk, skb);
}
2944 2945 2946 2947
gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
void napi_gro_flush(struct napi_struct *napi, bool flush_old);
struct sk_buff *napi_get_frags(struct napi_struct *napi);
gro_result_t napi_gro_frags(struct napi_struct *napi);
2948 2949
struct packet_offload *gro_find_receive_by_type(__be16 type);
struct packet_offload *gro_find_complete_by_type(__be16 type);
2950 2951 2952 2953 2954 2955 2956

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

2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967
int netdev_rx_handler_register(struct net_device *dev,
			       rx_handler_func_t *rx_handler,
			       void *rx_handler_data);
void netdev_rx_handler_unregister(struct net_device *dev);

bool dev_valid_name(const char *name);
int dev_ioctl(struct net *net, unsigned int cmd, void __user *);
int dev_ethtool(struct net *net, struct ifreq *);
unsigned int dev_get_flags(const struct net_device *);
int __dev_change_flags(struct net_device *, unsigned int flags);
int dev_change_flags(struct net_device *, unsigned int);
2968 2969
void __dev_notify_flags(struct net_device *, unsigned int old_flags,
			unsigned int gchanges);
2970 2971 2972 2973 2974 2975 2976 2977
int dev_change_name(struct net_device *, const char *);
int dev_set_alias(struct net_device *, const char *, size_t);
int dev_change_net_namespace(struct net_device *, struct net *, const char *);
int dev_set_mtu(struct net_device *, int);
void dev_set_group(struct net_device *, int);
int dev_set_mac_address(struct net_device *, struct sockaddr *);
int dev_change_carrier(struct net_device *, bool new_carrier);
int dev_get_phys_port_id(struct net_device *dev,
2978
			 struct netdev_phys_item_id *ppid);
2979 2980
int dev_get_phys_port_name(struct net_device *dev,
			   char *name, size_t len);
2981
struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev);
2982 2983
struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
				    struct netdev_queue *txq, int *ret);
H
Herbert Xu 已提交
2984
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
2985
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
2986
bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb);
L
Linus Torvalds 已提交
2987

2988
extern int		netdev_budget;
L
Linus Torvalds 已提交
2989 2990

/* Called by rtnetlink.c:rtnl_unlock() */
2991
void netdev_run_todo(void);
L
Linus Torvalds 已提交
2992

2993 2994 2995 2996
/**
 *	dev_put - release reference to device
 *	@dev: network device
 *
2997
 * Release reference to device to allow it to be freed.
2998
 */
L
Linus Torvalds 已提交
2999 3000
static inline void dev_put(struct net_device *dev)
{
3001
	this_cpu_dec(*dev->pcpu_refcnt);
L
Linus Torvalds 已提交
3002 3003
}

3004 3005 3006 3007
/**
 *	dev_hold - get reference to device
 *	@dev: network device
 *
3008
 * Hold reference to device to keep it from being freed.
3009
 */
3010 3011
static inline void dev_hold(struct net_device *dev)
{
3012
	this_cpu_inc(*dev->pcpu_refcnt);
3013
}
L
Linus Torvalds 已提交
3014 3015 3016 3017

/* 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
3018 3019 3020 3021
 *
 * 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
3022 3023
 */

3024 3025 3026
void linkwatch_init_dev(struct net_device *dev);
void linkwatch_fire_event(struct net_device *dev);
void linkwatch_forget_dev(struct net_device *dev);
L
Linus Torvalds 已提交
3027

3028 3029 3030 3031 3032 3033
/**
 *	netif_carrier_ok - test if carrier present
 *	@dev: network device
 *
 * Check if carrier is present on device
 */
3034
static inline bool netif_carrier_ok(const struct net_device *dev)
L
Linus Torvalds 已提交
3035 3036 3037 3038
{
	return !test_bit(__LINK_STATE_NOCARRIER, &dev->state);
}

3039
unsigned long dev_trans_start(struct net_device *dev);
3040

3041
void __netdev_watchdog_up(struct net_device *dev);
L
Linus Torvalds 已提交
3042

3043
void netif_carrier_on(struct net_device *dev);
L
Linus Torvalds 已提交
3044

3045
void netif_carrier_off(struct net_device *dev);
L
Linus Torvalds 已提交
3046

3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059
/**
 *	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
3060 3061 3062 3063 3064 3065
static inline void netif_dormant_on(struct net_device *dev)
{
	if (!test_and_set_bit(__LINK_STATE_DORMANT, &dev->state))
		linkwatch_fire_event(dev);
}

3066 3067 3068 3069 3070 3071
/**
 *	netif_dormant_off - set device as not dormant.
 *	@dev: network device
 *
 * Device is not in dormant state.
 */
S
Stefan Rompf 已提交
3072 3073 3074 3075 3076 3077
static inline void netif_dormant_off(struct net_device *dev)
{
	if (test_and_clear_bit(__LINK_STATE_DORMANT, &dev->state))
		linkwatch_fire_event(dev);
}

3078 3079 3080 3081 3082 3083
/**
 *	netif_dormant - test if carrier present
 *	@dev: network device
 *
 * Check if carrier is present on device
 */
3084
static inline bool netif_dormant(const struct net_device *dev)
S
Stefan Rompf 已提交
3085 3086 3087 3088 3089
{
	return test_bit(__LINK_STATE_DORMANT, &dev->state);
}


3090 3091 3092 3093 3094 3095
/**
 *	netif_oper_up - test if device is operational
 *	@dev: network device
 *
 * Check if carrier is operational
 */
3096
static inline bool netif_oper_up(const struct net_device *dev)
E
Eric Dumazet 已提交
3097
{
S
Stefan Rompf 已提交
3098 3099 3100 3101
	return (dev->operstate == IF_OPER_UP ||
		dev->operstate == IF_OPER_UNKNOWN /* backward compat */);
}

3102 3103 3104 3105 3106 3107
/**
 *	netif_device_present - is device available or removed
 *	@dev: network device
 *
 * Check if device has not been removed from system.
 */
3108
static inline bool netif_device_present(struct net_device *dev)
L
Linus Torvalds 已提交
3109 3110 3111 3112
{
	return test_bit(__LINK_STATE_PRESENT, &dev->state);
}

3113
void netif_device_detach(struct net_device *dev);
L
Linus Torvalds 已提交
3114

3115
void netif_device_attach(struct net_device *dev);
L
Linus Torvalds 已提交
3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165

/*
 * Network interface message level settings
 */

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;
}

3166
static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
H
Herbert Xu 已提交
3167
{
3168 3169
	spin_lock(&txq->_xmit_lock);
	txq->xmit_lock_owner = cpu;
3170 3171
}

3172 3173 3174 3175 3176 3177
static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
{
	spin_lock_bh(&txq->_xmit_lock);
	txq->xmit_lock_owner = smp_processor_id();
}

3178
static inline bool __netif_tx_trylock(struct netdev_queue *txq)
3179
{
3180
	bool ok = spin_trylock(&txq->_xmit_lock);
3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197
	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
3198 3199 3200 3201 3202 3203
static inline void txq_trans_update(struct netdev_queue *txq)
{
	if (txq->xmit_lock_owner != -1)
		txq->trans_start = jiffies;
}

3204 3205 3206 3207 3208 3209
/**
 *	netif_tx_lock - grab network device transmit lock
 *	@dev: network device
 *
 * Get network device transmit lock
 */
3210 3211
static inline void netif_tx_lock(struct net_device *dev)
{
3212
	unsigned int i;
3213
	int cpu;
3214

3215 3216
	spin_lock(&dev->tx_global_lock);
	cpu = smp_processor_id();
3217 3218
	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
3219 3220 3221 3222 3223 3224 3225

		/* 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.
		 */
3226
		__netif_tx_lock(txq, cpu);
3227 3228
		set_bit(__QUEUE_STATE_FROZEN, &txq->state);
		__netif_tx_unlock(txq);
3229
	}
H
Herbert Xu 已提交
3230 3231 3232 3233
}

static inline void netif_tx_lock_bh(struct net_device *dev)
{
3234 3235
	local_bh_disable();
	netif_tx_lock(dev);
H
Herbert Xu 已提交
3236 3237 3238 3239
}

static inline void netif_tx_unlock(struct net_device *dev)
{
3240 3241 3242 3243
	unsigned int i;

	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
3244

3245 3246 3247 3248 3249
		/* 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);
3250
		netif_schedule_queue(txq);
3251 3252
	}
	spin_unlock(&dev->tx_global_lock);
H
Herbert Xu 已提交
3253 3254 3255 3256
}

static inline void netif_tx_unlock_bh(struct net_device *dev)
{
3257 3258
	netif_tx_unlock(dev);
	local_bh_enable();
H
Herbert Xu 已提交
3259 3260
}

3261
#define HARD_TX_LOCK(dev, txq, cpu) {			\
3262
	if ((dev->features & NETIF_F_LLTX) == 0) {	\
3263
		__netif_tx_lock(txq, cpu);		\
3264 3265 3266
	}						\
}

3267 3268 3269 3270 3271
#define HARD_TX_TRYLOCK(dev, txq)			\
	(((dev->features & NETIF_F_LLTX) == 0) ?	\
		__netif_tx_trylock(txq) :		\
		true )

3272
#define HARD_TX_UNLOCK(dev, txq) {			\
3273
	if ((dev->features & NETIF_F_LLTX) == 0) {	\
3274
		__netif_tx_unlock(txq);			\
3275 3276 3277
	}						\
}

L
Linus Torvalds 已提交
3278 3279
static inline void netif_tx_disable(struct net_device *dev)
{
3280
	unsigned int i;
3281
	int cpu;
3282

3283 3284
	local_bh_disable();
	cpu = smp_processor_id();
3285 3286
	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
3287 3288

		__netif_tx_lock(txq, cpu);
3289
		netif_tx_stop_queue(txq);
3290
		__netif_tx_unlock(txq);
3291
	}
3292
	local_bh_enable();
L
Linus Torvalds 已提交
3293 3294
}

3295 3296 3297 3298 3299
static inline void netif_addr_lock(struct net_device *dev)
{
	spin_lock(&dev->addr_list_lock);
}

3300 3301
static inline void netif_addr_lock_nested(struct net_device *dev)
{
3302 3303 3304 3305 3306 3307
	int subclass = SINGLE_DEPTH_NESTING;

	if (dev->netdev_ops->ndo_get_lock_subclass)
		subclass = dev->netdev_ops->ndo_get_lock_subclass(dev);

	spin_lock_nested(&dev->addr_list_lock, subclass);
3308 3309
}

3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324
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);
}

3325
/*
3326
 * dev_addrs walker. Should be used only for read access. Call with
3327 3328 3329
 * rcu_read_lock held.
 */
#define for_each_dev_addr(dev, ha) \
3330
		list_for_each_entry_rcu(ha, &dev->dev_addrs.list, list)
3331

L
Linus Torvalds 已提交
3332 3333
/* These functions live elsewhere (drivers/net/net_init.c, but related) */

3334
void ether_setup(struct net_device *dev);
L
Linus Torvalds 已提交
3335 3336

/* Support for loadable net-drivers */
3337
struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
3338
				    unsigned char name_assign_type,
3339 3340
				    void (*setup)(struct net_device *),
				    unsigned int txqs, unsigned int rxqs);
3341 3342
#define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \
	alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1)
T
Tom Herbert 已提交
3343

3344 3345 3346
#define alloc_netdev_mq(sizeof_priv, name, name_assign_type, setup, count) \
	alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, count, \
			 count)
T
Tom Herbert 已提交
3347

3348 3349
int register_netdev(struct net_device *dev);
void unregister_netdev(struct net_device *dev);
3350

3351
/* General hardware address lists handling functions */
3352 3353 3354 3355
int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
		   struct netdev_hw_addr_list *from_list, int addr_len);
void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
		      struct netdev_hw_addr_list *from_list, int addr_len);
3356 3357 3358 3359 3360 3361 3362 3363 3364
int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
		       struct net_device *dev,
		       int (*sync)(struct net_device *, const unsigned char *),
		       int (*unsync)(struct net_device *,
				     const unsigned char *));
void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list,
			  struct net_device *dev,
			  int (*unsync)(struct net_device *,
					const unsigned char *));
3365
void __hw_addr_init(struct netdev_hw_addr_list *list);
3366

3367
/* Functions used for device addresses handling */
3368 3369 3370 3371 3372 3373
int dev_addr_add(struct net_device *dev, const unsigned char *addr,
		 unsigned char addr_type);
int dev_addr_del(struct net_device *dev, const unsigned char *addr,
		 unsigned char addr_type);
void dev_addr_flush(struct net_device *dev);
int dev_addr_init(struct net_device *dev);
3374 3375

/* Functions used for unicast addresses handling */
3376 3377 3378 3379 3380 3381 3382 3383
int dev_uc_add(struct net_device *dev, const unsigned char *addr);
int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr);
int dev_uc_del(struct net_device *dev, const unsigned char *addr);
int dev_uc_sync(struct net_device *to, struct net_device *from);
int dev_uc_sync_multiple(struct net_device *to, struct net_device *from);
void dev_uc_unsync(struct net_device *to, struct net_device *from);
void dev_uc_flush(struct net_device *dev);
void dev_uc_init(struct net_device *dev);
3384

3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403
/**
 *  __dev_uc_sync - Synchonize device's unicast list
 *  @dev:  device to sync
 *  @sync: function to call if address should be added
 *  @unsync: function to call if address should be removed
 *
 *  Add newly added addresses to the interface, and release
 *  addresses that have been deleted.
 **/
static inline int __dev_uc_sync(struct net_device *dev,
				int (*sync)(struct net_device *,
					    const unsigned char *),
				int (*unsync)(struct net_device *,
					      const unsigned char *))
{
	return __hw_addr_sync_dev(&dev->uc, dev, sync, unsync);
}

/**
3404
 *  __dev_uc_unsync - Remove synchronized addresses from device
3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416
 *  @dev:  device to sync
 *  @unsync: function to call if address should be removed
 *
 *  Remove all addresses that were added to the device by dev_uc_sync().
 **/
static inline void __dev_uc_unsync(struct net_device *dev,
				   int (*unsync)(struct net_device *,
						 const unsigned char *))
{
	__hw_addr_unsync_dev(&dev->uc, dev, unsync);
}

3417
/* Functions used for multicast addresses handling */
3418 3419 3420 3421 3422 3423 3424 3425 3426 3427
int dev_mc_add(struct net_device *dev, const unsigned char *addr);
int dev_mc_add_global(struct net_device *dev, const unsigned char *addr);
int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr);
int dev_mc_del(struct net_device *dev, const unsigned char *addr);
int dev_mc_del_global(struct net_device *dev, const unsigned char *addr);
int dev_mc_sync(struct net_device *to, struct net_device *from);
int dev_mc_sync_multiple(struct net_device *to, struct net_device *from);
void dev_mc_unsync(struct net_device *to, struct net_device *from);
void dev_mc_flush(struct net_device *dev);
void dev_mc_init(struct net_device *dev);
3428

3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447
/**
 *  __dev_mc_sync - Synchonize device's multicast list
 *  @dev:  device to sync
 *  @sync: function to call if address should be added
 *  @unsync: function to call if address should be removed
 *
 *  Add newly added addresses to the interface, and release
 *  addresses that have been deleted.
 **/
static inline int __dev_mc_sync(struct net_device *dev,
				int (*sync)(struct net_device *,
					    const unsigned char *),
				int (*unsync)(struct net_device *,
					      const unsigned char *))
{
	return __hw_addr_sync_dev(&dev->mc, dev, sync, unsync);
}

/**
3448
 *  __dev_mc_unsync - Remove synchronized addresses from device
3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460
 *  @dev:  device to sync
 *  @unsync: function to call if address should be removed
 *
 *  Remove all addresses that were added to the device by dev_mc_sync().
 **/
static inline void __dev_mc_unsync(struct net_device *dev,
				   int (*unsync)(struct net_device *,
						 const unsigned char *))
{
	__hw_addr_unsync_dev(&dev->mc, dev, unsync);
}

3461
/* Functions used for secondary unicast and multicast support */
3462 3463 3464 3465 3466 3467 3468
void dev_set_rx_mode(struct net_device *dev);
void __dev_set_rx_mode(struct net_device *dev);
int dev_set_promiscuity(struct net_device *dev, int inc);
int dev_set_allmulti(struct net_device *dev, int inc);
void netdev_state_change(struct net_device *dev);
void netdev_notify_peers(struct net_device *dev);
void netdev_features_change(struct net_device *dev);
L
Linus Torvalds 已提交
3469
/* Load a device via the kmod */
3470 3471 3472 3473 3474
void dev_load(struct net *net, const char *name);
struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
					struct rtnl_link_stats64 *storage);
void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
			     const struct net_device_stats *netdev_stats);
3475

L
Linus Torvalds 已提交
3476
extern int		netdev_max_backlog;
E
Eric Dumazet 已提交
3477
extern int		netdev_tstamp_prequeue;
L
Linus Torvalds 已提交
3478
extern int		weight_p;
3479
extern int		bpf_jit_enable;
J
Jiri Pirko 已提交
3480

3481
bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev);
3482 3483
struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
						     struct list_head **iter);
3484 3485
struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
						     struct list_head **iter);
3486

3487 3488 3489 3490 3491 3492 3493
/* iterate through upper list, must be called under RCU read lock */
#define netdev_for_each_upper_dev_rcu(dev, updev, iter) \
	for (iter = &(dev)->adj_list.upper, \
	     updev = netdev_upper_get_next_dev_rcu(dev, &(iter)); \
	     updev; \
	     updev = netdev_upper_get_next_dev_rcu(dev, &(iter)))

3494
/* iterate through upper list, must be called under RCU read lock */
3495 3496 3497 3498 3499
#define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \
	for (iter = &(dev)->all_adj_list.upper, \
	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)); \
	     updev; \
	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)))
3500

3501 3502 3503 3504
void *netdev_lower_get_next_private(struct net_device *dev,
				    struct list_head **iter);
void *netdev_lower_get_next_private_rcu(struct net_device *dev,
					struct list_head **iter);
3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517

#define netdev_for_each_lower_private(dev, priv, iter) \
	for (iter = (dev)->adj_list.lower.next, \
	     priv = netdev_lower_get_next_private(dev, &(iter)); \
	     priv; \
	     priv = netdev_lower_get_next_private(dev, &(iter)))

#define netdev_for_each_lower_private_rcu(dev, priv, iter) \
	for (iter = &(dev)->adj_list.lower, \
	     priv = netdev_lower_get_next_private_rcu(dev, &(iter)); \
	     priv; \
	     priv = netdev_lower_get_next_private_rcu(dev, &(iter)))

3518 3519 3520 3521 3522 3523 3524 3525
void *netdev_lower_get_next(struct net_device *dev,
				struct list_head **iter);
#define netdev_for_each_lower_dev(dev, ldev, iter) \
	for (iter = &(dev)->adj_list.lower, \
	     ldev = netdev_lower_get_next(dev, &(iter)); \
	     ldev; \
	     ldev = netdev_lower_get_next(dev, &(iter)))

3526
void *netdev_adjacent_get_private(struct list_head *adj_list);
3527
void *netdev_lower_get_first_private_rcu(struct net_device *dev);
3528 3529 3530 3531
struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev);
int netdev_master_upper_dev_link(struct net_device *dev,
J
Jiri Pirko 已提交
3532
				 struct net_device *upper_dev);
3533 3534 3535 3536 3537
int netdev_master_upper_dev_link_private(struct net_device *dev,
					 struct net_device *upper_dev,
					 void *private);
void netdev_upper_dev_unlink(struct net_device *dev,
			     struct net_device *upper_dev);
3538
void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
3539 3540
void *netdev_lower_dev_get_private(struct net_device *dev,
				   struct net_device *lower_dev);
3541 3542 3543 3544 3545 3546

/* RSS keys are 40 or 52 bytes long */
#define NETDEV_RSS_KEY_LEN 52
extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN];
void netdev_rss_key_fill(void *buffer, size_t len);

3547 3548
int dev_get_nest_level(struct net_device *dev,
		       bool (*type_check)(struct net_device *dev));
3549 3550 3551 3552 3553
int skb_checksum_help(struct sk_buff *skb);
struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
				  netdev_features_t features, bool tx_path);
struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
				    netdev_features_t features);
3554

3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567
struct netdev_bonding_info {
	ifslave	slave;
	ifbond	master;
};

struct netdev_notifier_bonding_info {
	struct netdev_notifier_info info; /* must be first */
	struct netdev_bonding_info  bonding_info;
};

void netdev_bonding_info_change(struct net_device *dev,
				struct netdev_bonding_info *bonding_info);

3568 3569 3570 3571 3572
static inline
struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features)
{
	return __skb_gso_segment(skb, features, true);
}
3573
__be16 skb_network_protocol(struct sk_buff *skb, int *depth);
3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585

static inline bool can_checksum_protocol(netdev_features_t features,
					 __be16 protocol)
{
	return ((features & NETIF_F_GEN_CSUM) ||
		((features & NETIF_F_V4_CSUM) &&
		 protocol == htons(ETH_P_IP)) ||
		((features & NETIF_F_V6_CSUM) &&
		 protocol == htons(ETH_P_IPV6)) ||
		((features & NETIF_F_FCOE_CRC) &&
		 protocol == htons(ETH_P_FCOE)));
}
3586

3587
#ifdef CONFIG_BUG
3588
void netdev_rx_csum_fault(struct net_device *dev);
3589 3590 3591 3592 3593
#else
static inline void netdev_rx_csum_fault(struct net_device *dev)
{
}
#endif
L
Linus Torvalds 已提交
3594
/* rx skb timestamps */
3595 3596
void net_enable_timestamp(void);
void net_disable_timestamp(void);
L
Linus Torvalds 已提交
3597

3598
#ifdef CONFIG_PROC_FS
3599
int __init dev_proc_init(void);
3600 3601
#else
#define dev_proc_init() 0
3602 3603
#endif

D
David S. Miller 已提交
3604
static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
3605 3606
					      struct sk_buff *skb, struct net_device *dev,
					      bool more)
D
David S. Miller 已提交
3607
{
3608
	skb->xmit_more = more ? 1 : 0;
3609
	return ops->ndo_start_xmit(skb, dev);
D
David S. Miller 已提交
3610 3611
}

3612
static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev,
3613
					    struct netdev_queue *txq, bool more)
D
David S. Miller 已提交
3614 3615
{
	const struct net_device_ops *ops = dev->netdev_ops;
3616
	int rc;
D
David S. Miller 已提交
3617

3618
	rc = __netdev_start_xmit(ops, skb, dev, more);
3619 3620 3621 3622
	if (rc == NETDEV_TX_OK)
		txq_trans_update(txq);

	return rc;
D
David S. Miller 已提交
3623 3624
}

3625 3626 3627 3628
int netdev_class_create_file_ns(struct class_attribute *class_attr,
				const void *ns);
void netdev_class_remove_file_ns(struct class_attribute *class_attr,
				 const void *ns);
3629 3630 3631 3632 3633 3634 3635 3636 3637 3638

static inline int netdev_class_create_file(struct class_attribute *class_attr)
{
	return netdev_class_create_file_ns(class_attr, NULL);
}

static inline void netdev_class_remove_file(struct class_attribute *class_attr)
{
	netdev_class_remove_file_ns(class_attr, NULL);
}
3639

3640 3641
extern struct kobj_ns_type_operations net_ns_type_operations;

3642
const char *netdev_drivername(const struct net_device *dev);
3643

3644
void linkwatch_run_queue(void);
3645

3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659
static inline netdev_features_t netdev_intersect_features(netdev_features_t f1,
							  netdev_features_t f2)
{
	if (f1 & NETIF_F_GEN_CSUM)
		f1 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM);
	if (f2 & NETIF_F_GEN_CSUM)
		f2 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM);
	f1 &= f2;
	if (f1 & NETIF_F_GEN_CSUM)
		f1 &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM);

	return f1;
}

3660 3661
static inline netdev_features_t netdev_get_wanted_features(
	struct net_device *dev)
3662 3663 3664
{
	return (dev->features & ~dev->hw_features) | dev->wanted_features;
}
3665 3666
netdev_features_t netdev_increment_features(netdev_features_t all,
	netdev_features_t one, netdev_features_t mask);
3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677

/* Allow TSO being used on stacked device :
 * Performing the GSO segmentation before last device
 * is a performance improvement.
 */
static inline netdev_features_t netdev_add_tso_features(netdev_features_t features,
							netdev_features_t mask)
{
	return netdev_increment_features(features, NETIF_F_ALL_TSO, mask);
}

3678
int __netdev_update_features(struct net_device *dev);
3679
void netdev_update_features(struct net_device *dev);
3680
void netdev_change_features(struct net_device *dev);
3681

3682 3683 3684
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
					struct net_device *dev);

3685 3686 3687
netdev_features_t passthru_features_check(struct sk_buff *skb,
					  struct net_device *dev,
					  netdev_features_t features);
3688
netdev_features_t netif_skb_features(struct sk_buff *skb);
3689

3690
static inline bool net_gso_ok(netdev_features_t features, int gso_type)
3691
{
3692
	netdev_features_t feature = gso_type << NETIF_F_GSO_SHIFT;
3693 3694 3695 3696 3697 3698 3699 3700

	/* check flags correspondence */
	BUILD_BUG_ON(SKB_GSO_TCPV4   != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT));
	BUILD_BUG_ON(SKB_GSO_UDP     != (NETIF_F_UFO >> NETIF_F_GSO_SHIFT));
	BUILD_BUG_ON(SKB_GSO_DODGY   != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT));
	BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT));
	BUILD_BUG_ON(SKB_GSO_TCPV6   != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT));
	BUILD_BUG_ON(SKB_GSO_FCOE    != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
3701 3702 3703 3704 3705 3706
	BUILD_BUG_ON(SKB_GSO_GRE     != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT));
	BUILD_BUG_ON(SKB_GSO_GRE_CSUM != (NETIF_F_GSO_GRE_CSUM >> NETIF_F_GSO_SHIFT));
	BUILD_BUG_ON(SKB_GSO_IPIP    != (NETIF_F_GSO_IPIP >> NETIF_F_GSO_SHIFT));
	BUILD_BUG_ON(SKB_GSO_SIT     != (NETIF_F_GSO_SIT >> NETIF_F_GSO_SHIFT));
	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT));
	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT));
3707
	BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT));
3708

3709
	return (features & feature) == feature;
3710 3711
}

3712
static inline bool skb_gso_ok(struct sk_buff *skb, netdev_features_t features)
3713
{
H
Herbert Xu 已提交
3714
	return net_gso_ok(features, skb_shinfo(skb)->gso_type) &&
3715
	       (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST));
3716 3717
}

3718
static inline bool netif_needs_gso(struct sk_buff *skb,
3719
				   netdev_features_t features)
3720
{
3721
	return skb_is_gso(skb) && (!skb_gso_ok(skb, features) ||
3722 3723
		unlikely((skb->ip_summed != CHECKSUM_PARTIAL) &&
			 (skb->ip_summed != CHECKSUM_UNNECESSARY)));
3724 3725
}

3726 3727 3728 3729 3730 3731
static inline void netif_set_gso_max_size(struct net_device *dev,
					  unsigned int size)
{
	dev->gso_max_size = size;
}

3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744
static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol,
					int pulled_hlen, u16 mac_offset,
					int mac_len)
{
	skb->protocol = protocol;
	skb->encapsulation = 1;
	skb_push(skb, pulled_hlen);
	skb_reset_transport_header(skb);
	skb->mac_header = mac_offset;
	skb->network_header = skb->mac_header + mac_len;
	skb->mac_len = mac_len;
}

3745 3746 3747 3748 3749
static inline bool netif_is_macvlan(struct net_device *dev)
{
	return dev->priv_flags & IFF_MACVLAN;
}

3750 3751 3752 3753 3754
static inline bool netif_is_macvlan_port(struct net_device *dev)
{
	return dev->priv_flags & IFF_MACVLAN_PORT;
}

3755 3756 3757 3758 3759 3760 3761 3762 3763 3764
static inline bool netif_is_ipvlan(struct net_device *dev)
{
	return dev->priv_flags & IFF_IPVLAN_SLAVE;
}

static inline bool netif_is_ipvlan_port(struct net_device *dev)
{
	return dev->priv_flags & IFF_IPVLAN_MASTER;
}

3765 3766 3767 3768 3769
static inline bool netif_is_bond_master(struct net_device *dev)
{
	return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING;
}

3770
static inline bool netif_is_bond_slave(struct net_device *dev)
J
Jiri Pirko 已提交
3771 3772 3773 3774
{
	return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING;
}

3775 3776 3777 3778 3779
static inline bool netif_supports_nofcs(struct net_device *dev)
{
	return dev->priv_flags & IFF_SUPP_NOFCS;
}

3780 3781 3782 3783 3784 3785
/* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */
static inline void netif_keep_dst(struct net_device *dev)
{
	dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM);
}

3786
extern struct pernet_operations __net_initdata loopback_net_ops;
3787

3788 3789 3790 3791 3792 3793
/* Logging, debugging and troubleshooting/diagnostic helpers. */

/* netdev_printk helpers, similar to dev_printk */

static inline const char *netdev_name(const struct net_device *dev)
{
3794 3795
	if (!dev->name[0] || strchr(dev->name, '%'))
		return "(unnamed net_device)";
3796 3797 3798
	return dev->name;
}

3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813
static inline const char *netdev_reg_state(const struct net_device *dev)
{
	switch (dev->reg_state) {
	case NETREG_UNINITIALIZED: return " (uninitialized)";
	case NETREG_REGISTERED: return "";
	case NETREG_UNREGISTERING: return " (unregistering)";
	case NETREG_UNREGISTERED: return " (unregistered)";
	case NETREG_RELEASED: return " (released)";
	case NETREG_DUMMY: return " (dummy)";
	}

	WARN_ONCE(1, "%s: unknown reg_state %d\n", dev->name, dev->reg_state);
	return " (unknown)";
}

3814
__printf(3, 4)
3815 3816
void netdev_printk(const char *level, const struct net_device *dev,
		   const char *format, ...);
3817
__printf(2, 3)
3818
void netdev_emerg(const struct net_device *dev, const char *format, ...);
3819
__printf(2, 3)
3820
void netdev_alert(const struct net_device *dev, const char *format, ...);
3821
__printf(2, 3)
3822
void netdev_crit(const struct net_device *dev, const char *format, ...);
3823
__printf(2, 3)
3824
void netdev_err(const struct net_device *dev, const char *format, ...);
3825
__printf(2, 3)
3826
void netdev_warn(const struct net_device *dev, const char *format, ...);
3827
__printf(2, 3)
3828
void netdev_notice(const struct net_device *dev, const char *format, ...);
3829
__printf(2, 3)
3830
void netdev_info(const struct net_device *dev, const char *format, ...);
3831

3832 3833 3834
#define MODULE_ALIAS_NETDEV(device) \
	MODULE_ALIAS("netdev-" device)

3835
#if defined(CONFIG_DYNAMIC_DEBUG)
3836 3837
#define netdev_dbg(__dev, format, args...)			\
do {								\
3838
	dynamic_netdev_dbg(__dev, format, ##args);		\
3839
} while (0)
3840 3841 3842
#elif defined(DEBUG)
#define netdev_dbg(__dev, format, args...)			\
	netdev_printk(KERN_DEBUG, __dev, format, ##args)
3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868
#else
#define netdev_dbg(__dev, format, args...)			\
({								\
	if (0)							\
		netdev_printk(KERN_DEBUG, __dev, format, ##args); \
})
#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...)			\
3869 3870
	WARN(1, "netdevice: %s%s\n" format, netdev_name(dev),	\
	     netdev_reg_state(dev), ##args)
3871

3872 3873 3874 3875 3876 3877 3878 3879
/* netif printk helpers, similar to netdev_printk */

#define netif_printk(priv, type, level, dev, fmt, args...)	\
do {					  			\
	if (netif_msg_##type(priv))				\
		netdev_printk(level, (dev), fmt, ##args);	\
} while (0)

3880 3881 3882 3883 3884 3885
#define netif_level(level, priv, type, dev, fmt, args...)	\
do {								\
	if (netif_msg_##type(priv))				\
		netdev_##level(dev, fmt, ##args);		\
} while (0)

3886
#define netif_emerg(priv, type, dev, fmt, args...)		\
3887
	netif_level(emerg, priv, type, dev, fmt, ##args)
3888
#define netif_alert(priv, type, dev, fmt, args...)		\
3889
	netif_level(alert, priv, type, dev, fmt, ##args)
3890
#define netif_crit(priv, type, dev, fmt, args...)		\
3891
	netif_level(crit, priv, type, dev, fmt, ##args)
3892
#define netif_err(priv, type, dev, fmt, args...)		\
3893
	netif_level(err, priv, type, dev, fmt, ##args)
3894
#define netif_warn(priv, type, dev, fmt, args...)		\
3895
	netif_level(warn, priv, type, dev, fmt, ##args)
3896
#define netif_notice(priv, type, dev, fmt, args...)		\
3897
	netif_level(notice, priv, type, dev, fmt, ##args)
3898
#define netif_info(priv, type, dev, fmt, args...)		\
3899
	netif_level(info, priv, type, dev, fmt, ##args)
3900

3901
#if defined(CONFIG_DYNAMIC_DEBUG)
3902 3903 3904
#define netif_dbg(priv, type, netdev, format, args...)		\
do {								\
	if (netif_msg_##type(priv))				\
3905
		dynamic_netdev_dbg(netdev, format, ##args);	\
3906
} while (0)
3907 3908 3909
#elif defined(DEBUG)
#define netif_dbg(priv, type, dev, format, args...)		\
	netif_printk(priv, type, KERN_DEBUG, dev, format, ##args)
3910 3911 3912 3913 3914 3915 3916 3917 3918 3919
#else
#define netif_dbg(priv, type, dev, format, args...)			\
({									\
	if (0)								\
		netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
	0;								\
})
#endif

#if defined(VERBOSE_DEBUG)
3920
#define netif_vdbg	netif_dbg
3921 3922 3923 3924
#else
#define netif_vdbg(priv, type, dev, format, args...)		\
({								\
	if (0)							\
3925
		netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
3926 3927 3928
	0;							\
})
#endif
3929

3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959
/*
 *	The list of packet types we will receive (as opposed to discard)
 *	and the routines to invoke.
 *
 *	Why 16. Because with 16 the only overlap we get on a hash of the
 *	low nibble of the protocol value is RARP/SNAP/X.25.
 *
 *      NOTE:  That is no longer true with the addition of VLAN tags.  Not
 *             sure which should go first, but I bet it won't make much
 *             difference if we are running VLANs.  The good news is that
 *             this protocol won't be in the list unless compiled in, so
 *             the average user (w/out VLANs) will not be adversely affected.
 *             --BLG
 *
 *		0800	IP
 *		8100    802.1Q VLAN
 *		0001	802.3
 *		0002	AX.25
 *		0004	802.2
 *		8035	RARP
 *		0005	SNAP
 *		0805	X.25
 *		0806	ARP
 *		8137	IPX
 *		0009	Localtalk
 *		86DD	IPv6
 */
#define PTYPE_HASH_SIZE	(16)
#define PTYPE_HASH_MASK	(PTYPE_HASH_SIZE - 1)

3960
#endif	/* _LINUX_NETDEVICE_H */