netdevice.h 114.2 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

28
#include <linux/pm_qos.h>
A
Al Viro 已提交
29
#include <linux/timer.h>
30
#include <linux/bug.h>
31
#include <linux/delay.h>
A
Arun Sharma 已提交
32
#include <linux/atomic.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

54
struct netpoll_info;
55
struct device;
56
struct phy_device;
57 58
/* 802.11 specific */
struct wireless_dev;
L
Linus Torvalds 已提交
59

60 61
void netdev_set_default_ethtool_ops(struct net_device *dev,
				    const struct ethtool_ops *ops);
62

63 64 65 66
/* Backlog congestion levels */
#define NET_RX_SUCCESS		0	/* keep 'em coming, baby */
#define NET_RX_DROP		1	/* packet dropped */

67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85
/*
 * 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
86 87 88 89
#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
90

91 92 93
/* 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. */
94
#define net_xmit_eval(e)	((e) == NET_XMIT_CN ? 0 : (e))
L
Linus Torvalds 已提交
95 96
#define net_xmit_errno(e)	((e) != NET_XMIT_CN ? -ENOBUFS : 0)

97
/* Driver transmit return codes */
98
#define NETDEV_TX_MASK		0xf0
99

100
enum netdev_tx {
101
	__NETDEV_TX_MIN	 = INT_MIN,	/* make sure enum is signed */
102 103 104
	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 */
105 106 107
};
typedef enum netdev_tx netdev_tx_t;

108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125
/*
 * 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
126 127 128 129
/*
 *	Compute the worst case header length according to the protocols
 *	used.
 */
G
Graf Yang 已提交
130

131
#if defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25)
132 133 134 135 136
# if defined(CONFIG_MAC80211_MESH)
#  define LL_MAX_HEADER 128
# else
#  define LL_MAX_HEADER 96
# endif
L
Linus Torvalds 已提交
137
#else
138
# define LL_MAX_HEADER 32
L
Linus Torvalds 已提交
139 140
#endif

141 142
#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
143 144 145 146 147 148
#define MAX_HEADER LL_MAX_HEADER
#else
#define MAX_HEADER (LL_MAX_HEADER + 48)
#endif

/*
149 150
 *	Old network device statistics. Fields are native words
 *	(unsigned long) so they can be read and written atomically.
L
Linus Torvalds 已提交
151
 */
G
Graf Yang 已提交
152

E
Eric Dumazet 已提交
153
struct net_device_stats {
154 155 156 157 158 159 160 161 162
	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
163 164
	unsigned long	collisions;
	unsigned long	rx_length_errors;
165 166 167 168 169
	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
170 171 172 173 174 175 176 177 178 179 180 181 182
	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>

183
#ifdef CONFIG_RPS
184 185
#include <linux/static_key.h>
extern struct static_key rps_needed;
186 187
#endif

L
Linus Torvalds 已提交
188 189 190 191
struct neighbour;
struct neigh_parms;
struct sk_buff;

192 193 194 195
struct netdev_hw_addr {
	struct list_head	list;
	unsigned char		addr[MAX_ADDR_LEN];
	unsigned char		type;
J
Jiri Pirko 已提交
196 197 198 199
#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
200 201
#define NETDEV_HW_ADDR_T_MULTICAST	5
	bool			global_use;
202
	int			sync_cnt;
203
	int			refcount;
204
	int			synced;
205 206 207
	struct rcu_head		rcu_head;
};

208 209 210 211 212
struct netdev_hw_addr_list {
	struct list_head	list;
	int			count;
};

213 214 215 216
#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)
217

218 219 220 221
#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)
222

223 224
#define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc)
#define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc)
225
#define netdev_for_each_mc_addr(ha, dev) \
226
	netdev_hw_addr_list_for_each(ha, &(dev)->mc)
227

E
Eric Dumazet 已提交
228
struct hh_cache {
229
	u16		hh_len;
230
	u16		__pad;
231
	seqlock_t	hh_lock;
L
Linus Torvalds 已提交
232 233 234 235

	/* cached hardware header; allow for machine alignment needs.        */
#define HH_DATA_MOD	16
#define HH_DATA_OFF(__len) \
J
Jiri Benc 已提交
236
	(HH_DATA_MOD - (((__len - 1) & (HH_DATA_MOD - 1)) + 1))
L
Linus Torvalds 已提交
237 238 239 240 241 242 243 244 245 246 247 248 249 250
#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) \
251
	((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
L
Linus Torvalds 已提交
252
#define LL_RESERVED_SPACE_EXTRA(dev,extra) \
253
	((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
L
Linus Torvalds 已提交
254

255 256 257
struct header_ops {
	int	(*create) (struct sk_buff *skb, struct net_device *dev,
			   unsigned short type, const void *daddr,
258
			   const void *saddr, unsigned int len);
259 260
	int	(*parse)(const struct sk_buff *skb, unsigned char *haddr);
	int	(*rebuild)(struct sk_buff *skb);
261
	int	(*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type);
262 263 264 265 266
	void	(*cache_update)(struct hh_cache *hh,
				const struct net_device *dev,
				const unsigned char *haddr);
};

L
Linus Torvalds 已提交
267 268 269 270 271
/* 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
272
enum netdev_state_t {
L
Linus Torvalds 已提交
273 274 275
	__LINK_STATE_START,
	__LINK_STATE_PRESENT,
	__LINK_STATE_NOCARRIER,
S
Stefan Rompf 已提交
276 277
	__LINK_STATE_LINKWATCH_PENDING,
	__LINK_STATE_DORMANT,
L
Linus Torvalds 已提交
278 279 280 281 282
};


/*
 * This structure holds at boot time configured netdevice settings. They
G
Graf Yang 已提交
283
 * are then used in the device probing.
L
Linus Torvalds 已提交
284 285 286 287 288 289 290
 */
struct netdev_boot_setup {
	char name[IFNAMSIZ];
	struct ifmap map;
};
#define NETDEV_BOOT_SETUP_MAX 8

291
int __init netdev_boot_setup(char *str);
L
Linus Torvalds 已提交
292

293 294 295 296 297 298 299 300 301 302 303 304 305 306
/*
 * 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;
307
	unsigned int		gro_count;
308 309 310 311 312
	int			(*poll)(struct napi_struct *, int);
#ifdef CONFIG_NETPOLL
	spinlock_t		poll_lock;
	int			poll_owner;
#endif
H
Herbert Xu 已提交
313
	struct net_device	*dev;
314
	struct sk_buff		*gro_list;
H
Herbert Xu 已提交
315
	struct sk_buff		*skb;
316
	struct list_head	dev_list;
E
Eliezer Tamir 已提交
317 318
	struct hlist_node	napi_hash_node;
	unsigned int		napi_id;
319 320
};

E
Eric Dumazet 已提交
321
enum {
322
	NAPI_STATE_SCHED,	/* Poll is scheduled */
D
David S. Miller 已提交
323
	NAPI_STATE_DISABLE,	/* Disable pending */
324
	NAPI_STATE_NPSVC,	/* Netpoll - don't dequeue from poll_list */
E
Eliezer Tamir 已提交
325
	NAPI_STATE_HASHED,	/* In NAPI hash */
326 327
};

328
enum gro_result {
329 330 331 332 333 334
	GRO_MERGED,
	GRO_MERGED_FREE,
	GRO_HELD,
	GRO_NORMAL,
	GRO_DROP,
};
335
typedef enum gro_result gro_result_t;
336

337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368
/*
 * 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
369
 * are registered on exact device (ptype->dev == skb->dev).
370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385
 *
 * 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);
386

387
void __napi_schedule(struct napi_struct *n);
388

389
static inline bool napi_disable_pending(struct napi_struct *n)
D
David S. Miller 已提交
390 391 392 393
{
	return test_bit(NAPI_STATE_DISABLE, &n->state);
}

394 395 396 397 398 399
/**
 *	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
400 401
 * insure only one NAPI poll instance runs.  We also make
 * sure there is no pending NAPI disable.
402
 */
403
static inline bool napi_schedule_prep(struct napi_struct *n)
404
{
D
David S. Miller 已提交
405 406
	return !napi_disable_pending(n) &&
		!test_and_set_bit(NAPI_STATE_SCHED, &n->state);
407 408 409 410 411 412 413 414 415 416 417 418 419 420 421
}

/**
 *	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);
}

422
/* Try to reschedule poll. Called by dev->poll() after napi_complete().  */
423
static inline bool napi_reschedule(struct napi_struct *napi)
424 425 426
{
	if (napi_schedule_prep(napi)) {
		__napi_schedule(napi);
427
		return true;
428
	}
429
	return false;
430 431
}

432 433 434 435 436 437
/**
 *	napi_complete - NAPI processing complete
 *	@n: napi context
 *
 * Mark NAPI processing as complete.
 */
438 439
void __napi_complete(struct napi_struct *n);
void napi_complete(struct napi_struct *n);
440

E
Eliezer Tamir 已提交
441 442 443 444 445 446 447
/**
 *	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()
 */
448
struct napi_struct *napi_by_id(unsigned int napi_id);
E
Eliezer Tamir 已提交
449 450 451 452 453 454 455

/**
 *	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
 */
456
void napi_hash_add(struct napi_struct *napi);
E
Eliezer Tamir 已提交
457 458 459 460 461 462 463 464

/**
 *	napi_hash_del - remove a NAPI from global table
 *	@napi: napi context
 *
 * Warning: caller must observe rcu grace period
 * before freeing memory containing @napi
 */
465
void napi_hash_del(struct napi_struct *napi);
E
Eliezer Tamir 已提交
466

467 468 469 470 471 472 473 474 475
/**
 *	napi_disable - prevent NAPI from scheduling
 *	@n: napi context
 *
 * Stop NAPI from being scheduled on this context.
 * Waits till any outstanding processing completes.
 */
static inline void napi_disable(struct napi_struct *n)
{
476
	might_sleep();
D
David S. Miller 已提交
477
	set_bit(NAPI_STATE_DISABLE, &n->state);
478
	while (test_and_set_bit(NAPI_STATE_SCHED, &n->state))
479
		msleep(1);
D
David S. Miller 已提交
480
	clear_bit(NAPI_STATE_DISABLE, &n->state);
481 482 483 484 485 486 487 488 489 490 491 492
}

/**
 *	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));
493
	smp_mb__before_atomic();
494 495 496
	clear_bit(NAPI_STATE_SCHED, &n->state);
}

497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514
#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
515
enum netdev_queue_state_t {
516 517
	__QUEUE_STATE_DRV_XOFF,
	__QUEUE_STATE_STACK_XOFF,
518
	__QUEUE_STATE_FROZEN,
519
};
520 521 522 523 524 525 526 527 528 529 530

#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)

531 532 533 534 535 536 537 538 539
/*
 * __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_*.
 */
540

541
struct netdev_queue {
542 543 544
/*
 * read mostly part
 */
545
	struct net_device	*dev;
546 547
	struct Qdisc		*qdisc;
	struct Qdisc		*qdisc_sleeping;
548
#ifdef CONFIG_SYSFS
T
Tom Herbert 已提交
549 550
	struct kobject		kobj;
#endif
551 552 553
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
	int			numa_node;
#endif
554 555 556 557 558
/*
 * write mostly part
 */
	spinlock_t		_xmit_lock ____cacheline_aligned_in_smp;
	int			xmit_lock_owner;
559 560 561 562
	/*
	 * please use this field instead of dev->trans_start
	 */
	unsigned long		trans_start;
563 564 565 566 567 568

	/*
	 * Number of TX timeouts for this queue
	 * (/sys/class/net/DEV/Q/trans_timeout)
	 */
	unsigned long		trans_timeout;
T
Tom Herbert 已提交
569 570 571 572 573 574

	unsigned long		state;

#ifdef CONFIG_BQL
	struct dql		dql;
#endif
575
} ____cacheline_aligned_in_smp;
576

577 578 579 580 581
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
582
	return NUMA_NO_NODE;
583 584 585 586 587 588 589 590 591 592
#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
593
#ifdef CONFIG_RPS
T
Tom Herbert 已提交
594 595 596 597 598 599 600 601 602
/*
 * 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];
};
603
#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16)))
T
Tom Herbert 已提交
604

T
Tom Herbert 已提交
605
/*
606 607 608
 * 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
609 610 611
 */
struct rps_dev_flow {
	u16 cpu;
612
	u16 filter;
T
Tom Herbert 已提交
613 614
	unsigned int last_qtail;
};
615
#define RPS_NO_FILTER 0xffff
T
Tom Herbert 已提交
616 617 618 619 620 621 622 623 624 625

/*
 * 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) + \
626
    ((_num) * sizeof(struct rps_dev_flow)))
T
Tom Herbert 已提交
627 628 629 630 631 632 633 634 635 636

/*
 * The rps_sock_flow_table contains mappings of flows to the last CPU
 * on which they were processed by the application (set in recvmsg).
 */
struct rps_sock_flow_table {
	unsigned int mask;
	u16 ents[0];
};
#define	RPS_SOCK_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_sock_flow_table) + \
637
    ((_num) * sizeof(u16)))
T
Tom Herbert 已提交
638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661

#define RPS_NO_CPU 0xffff

static inline void rps_record_sock_flow(struct rps_sock_flow_table *table,
					u32 hash)
{
	if (table && hash) {
		unsigned int cpu, index = hash & table->mask;

		/* We only give a hint, preemption can change cpu under us */
		cpu = raw_smp_processor_id();

		if (table->ents[index] != cpu)
			table->ents[index] = cpu;
	}
}

static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table,
				       u32 hash)
{
	if (table && hash)
		table->ents[hash & table->mask] = RPS_NO_CPU;
}

E
Eric Dumazet 已提交
662
extern struct rps_sock_flow_table __rcu *rps_sock_flow_table;
T
Tom Herbert 已提交
663

664
#ifdef CONFIG_RFS_ACCEL
665 666
bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
			 u16 filter_id);
667
#endif
668
#endif /* CONFIG_RPS */
669

T
Tom Herbert 已提交
670 671
/* This structure contains an instance of an RX queue. */
struct netdev_rx_queue {
672
#ifdef CONFIG_RPS
E
Eric Dumazet 已提交
673 674
	struct rps_map __rcu		*rps_map;
	struct rps_dev_flow_table __rcu	*rps_flow_table;
675
#endif
E
Eric Dumazet 已提交
676
	struct kobject			kobj;
T
Tom Herbert 已提交
677
	struct net_device		*dev;
T
Tom Herbert 已提交
678
} ____cacheline_aligned_in_smp;
679 680 681 682 683 684 685 686 687 688 689

/*
 * 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);
};
690

T
Tom Herbert 已提交
691 692 693 694 695 696 697 698 699 700 701
#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];
};
702
#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + ((_num) * sizeof(u16)))
T
Tom Herbert 已提交
703 704 705 706 707 708 709 710
#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
711
	struct xps_map __rcu *cpu_map[0];
T
Tom Herbert 已提交
712 713 714 715 716
};
#define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) +		\
    (nr_cpu_ids * sizeof(struct xps_map *)))
#endif /* CONFIG_XPS */

717 718 719 720 721 722 723 724
#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;
};

725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741
#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

742 743 744 745 746 747 748 749 750 751
#define MAX_PHYS_PORT_ID_LEN 32

/* This structure holds a unique identifier to identify the
 * physical port used by a netdevice.
 */
struct netdev_phys_port_id {
	unsigned char id[MAX_PHYS_PORT_ID_LEN];
	unsigned char id_len;
};

752 753 754
typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
				       struct sk_buff *skb);

755 756
/*
 * This structure defines the management hooks for network devices.
757 758
 * The following hooks can be defined; unless noted otherwise, they are
 * optional and can be filled with a null pointer.
759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777
 *
 * 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.
 *
778 779
 * netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb,
 *                               struct net_device *dev);
780
 *	Called when a packet needs to be transmitted.
781 782
 *	Must return NETDEV_TX_OK , NETDEV_TX_BUSY.
 *        (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
783 784
 *	Required can not be NULL.
 *
785
 * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
786
 *                         void *accel_priv, select_queue_fallback_t fallback);
787 788 789
 *	Called to decide which queue to when device supports multiple
 *	transmit queues.
 *
790 791 792 793 794 795
 * 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.
796 797
 *	If driver handles unicast address filtering, it should set
 *	IFF_UNICAST_FLT to its priv_flags.
798 799 800
 *
 * int (*ndo_set_mac_address)(struct net_device *dev, void *addr);
 *	This function  is called when the Media Access Control address
801
 *	needs to be changed. If this interface is not defined, the
802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821
 *	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.
 *
822
 * void (*ndo_tx_timeout)(struct net_device *dev);
823 824 825
 *	Callback uses when the transmitter has not made any progress
 *	for dev->watchdog ticks.
 *
826
 * struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev,
827
 *                      struct rtnl_link_stats64 *storage);
828
 * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
829
 *	Called when a user wants to get the network device usage
830
 *	statistics. Drivers must do one of the following:
831 832
 *	1. Define @ndo_get_stats64 to fill in a zero-initialised
 *	   rtnl_link_stats64 structure passed by the caller.
833
 *	2. Define @ndo_get_stats to update a net_device_stats structure
834 835 836 837 838
 *	   (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.
839
 *
840 841 842
 * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16t vid);
 *	If device support VLAN filtering this function is called when a
 *	VLAN id is registered.
843
 *
844
 * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid);
845 846
 *	If device support VLAN filtering this function is called when a
 *	VLAN id is unregistered.
847 848
 *
 * void (*ndo_poll_controller)(struct net_device *dev);
849 850 851 852
 *
 *	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);
853 854
 * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate,
 *			  int max_tx_rate);
855
 * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting);
856 857
 * int (*ndo_get_vf_config)(struct net_device *dev,
 *			    int vf, struct ifla_vf_info *ivf);
858
 * int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state);
859 860 861
 * 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);
862 863 864 865 866
 * 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.
867
 *
868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897
 *	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.
 *
898 899 900 901 902 903 904
 * 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.
 *
905 906 907 908 909 910
 * 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.
 *
911 912 913 914 915 916
 *	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.
917
 *
918
 *	Slave management functions (for bridge, bonding, etc).
919 920 921 922 923
 * 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.
924 925
 *
 *      Feature/offload setting functions.
926 927
 * netdev_features_t (*ndo_fix_features)(struct net_device *dev,
 *		netdev_features_t features);
928 929 930 931
 *	Adjusts the requested feature flags according to device-specific
 *	constraints, and returns the resulting flags. Must not modify
 *	the device state.
 *
932
 * int (*ndo_set_features)(struct net_device *dev, netdev_features_t features);
933 934 935 936
 *	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.
 *
937 938
 * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[],
 *		      struct net_device *dev,
939
 *		      const unsigned char *addr, u16 flags)
940
 *	Adds an FDB entry to dev for addr.
941 942
 * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[],
 *		      struct net_device *dev,
943
 *		      const unsigned char *addr)
944 945
 *	Deletes the FDB entry from dev coresponding to addr.
 * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb,
946 947
 *		       struct net_device *dev, struct net_device *filter_dev,
 *		       int idx)
948 949
 *	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
950 951 952
 *
 * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh)
 * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq,
953
 *			     struct net_device *dev, u32 filter_mask)
J
Jiri Pirko 已提交
954 955 956 957 958 959 960 961
 *
 * 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.
962 963 964 965 966 967
 *
 * int (*ndo_get_phys_port_id)(struct net_device *dev,
 *			       struct netdev_phys_port_id *ppid);
 *	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.
968 969
 *
 * void (*ndo_add_vxlan_port)(struct  net_device *dev,
J
Joseph Gasparakis 已提交
970
 *			      sa_family_t sa_family, __be16 port);
971 972 973 974 975 976
 *	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
977
 *			      sa_family_t sa_family, __be16 port);
978 979 980
 *	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.
981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999
 *
 * 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.
1000 1001 1002 1003 1004 1005
 */
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);
1006
	netdev_tx_t		(*ndo_start_xmit) (struct sk_buff *skb,
1007 1008
						   struct net_device *dev);
	u16			(*ndo_select_queue)(struct net_device *dev,
1009
						    struct sk_buff *skb,
1010 1011
						    void *accel_priv,
						    select_queue_fallback_t fallback);
1012 1013 1014 1015 1016 1017 1018 1019 1020 1021
	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);
1022 1023 1024 1025
	int			(*ndo_change_mtu)(struct net_device *dev,
						  int new_mtu);
	int			(*ndo_neigh_setup)(struct net_device *dev,
						   struct neigh_parms *);
1026 1027
	void			(*ndo_tx_timeout) (struct net_device *dev);

1028 1029
	struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev,
						     struct rtnl_link_stats64 *storage);
1030 1031
	struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);

1032
	int			(*ndo_vlan_rx_add_vid)(struct net_device *dev,
1033
						       __be16 proto, u16 vid);
1034
	int			(*ndo_vlan_rx_kill_vid)(struct net_device *dev,
1035
						        __be16 proto, u16 vid);
1036 1037
#ifdef CONFIG_NET_POLL_CONTROLLER
	void                    (*ndo_poll_controller)(struct net_device *dev);
H
Herbert Xu 已提交
1038
	int			(*ndo_netpoll_setup)(struct net_device *dev,
1039
						     struct netpoll_info *info);
1040
	void			(*ndo_netpoll_cleanup)(struct net_device *dev);
E
Eliezer Tamir 已提交
1041
#endif
1042
#ifdef CONFIG_NET_RX_BUSY_POLL
1043
	int			(*ndo_busy_poll)(struct napi_struct *dev);
1044
#endif
1045 1046 1047 1048
	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);
1049 1050 1051
	int			(*ndo_set_vf_rate)(struct net_device *dev,
						   int vf, int min_tx_rate,
						   int max_tx_rate);
1052 1053
	int			(*ndo_set_vf_spoofchk)(struct net_device *dev,
						       int vf, bool setting);
1054 1055 1056
	int			(*ndo_get_vf_config)(struct net_device *dev,
						     int vf,
						     struct ifla_vf_info *ivf);
1057 1058
	int			(*ndo_set_vf_link_state)(struct net_device *dev,
							 int vf, int link_state);
1059 1060 1061 1062 1063
	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);
1064
	int			(*ndo_setup_tc)(struct net_device *dev, u8 tc);
1065
#if IS_ENABLED(CONFIG_FCOE)
1066 1067
	int			(*ndo_fcoe_enable)(struct net_device *dev);
	int			(*ndo_fcoe_disable)(struct net_device *dev);
1068 1069 1070 1071 1072 1073
	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);
1074 1075 1076 1077
	int			(*ndo_fcoe_ddp_target)(struct net_device *dev,
						       u16 xid,
						       struct scatterlist *sgl,
						       unsigned int sgc);
1078 1079
	int			(*ndo_fcoe_get_hbainfo)(struct net_device *dev,
							struct netdev_fcoe_hbainfo *hbainfo);
1080 1081
#endif

1082
#if IS_ENABLED(CONFIG_LIBFCOE)
1083 1084 1085 1086
#define NETDEV_FCOE_WWNN 0
#define NETDEV_FCOE_WWPN 1
	int			(*ndo_fcoe_get_wwn)(struct net_device *dev,
						    u64 *wwn, int type);
1087
#endif
1088

1089 1090 1091 1092 1093 1094
#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
1095 1096 1097 1098
	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);
1099 1100
	netdev_features_t	(*ndo_fix_features)(struct net_device *dev,
						    netdev_features_t features);
1101
	int			(*ndo_set_features)(struct net_device *dev,
1102
						    netdev_features_t features);
1103
	int			(*ndo_neigh_construct)(struct neighbour *n);
1104
	void			(*ndo_neigh_destroy)(struct neighbour *n);
1105 1106

	int			(*ndo_fdb_add)(struct ndmsg *ndm,
1107
					       struct nlattr *tb[],
1108
					       struct net_device *dev,
1109
					       const unsigned char *addr,
1110 1111
					       u16 flags);
	int			(*ndo_fdb_del)(struct ndmsg *ndm,
1112
					       struct nlattr *tb[],
1113
					       struct net_device *dev,
1114
					       const unsigned char *addr);
1115 1116 1117
	int			(*ndo_fdb_dump)(struct sk_buff *skb,
						struct netlink_callback *cb,
						struct net_device *dev,
1118
						struct net_device *filter_dev,
1119
						int idx);
J
John Fastabend 已提交
1120 1121 1122 1123 1124

	int			(*ndo_bridge_setlink)(struct net_device *dev,
						      struct nlmsghdr *nlh);
	int			(*ndo_bridge_getlink)(struct sk_buff *skb,
						      u32 pid, u32 seq,
1125 1126
						      struct net_device *dev,
						      u32 filter_mask);
1127 1128
	int			(*ndo_bridge_dellink)(struct net_device *dev,
						      struct nlmsghdr *nlh);
J
Jiri Pirko 已提交
1129 1130
	int			(*ndo_change_carrier)(struct net_device *dev,
						      bool new_carrier);
1131 1132
	int			(*ndo_get_phys_port_id)(struct net_device *dev,
							struct netdev_phys_port_id *ppid);
1133 1134
	void			(*ndo_add_vxlan_port)(struct  net_device *dev,
						      sa_family_t sa_family,
J
Joseph Gasparakis 已提交
1135
						      __be16 port);
1136 1137
	void			(*ndo_del_vxlan_port)(struct  net_device *dev,
						      sa_family_t sa_family,
J
Joseph Gasparakis 已提交
1138
						      __be16 port);
1139 1140 1141 1142 1143 1144 1145 1146 1147

	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);
1148
	int			(*ndo_get_lock_subclass)(struct net_device *dev);
1149 1150
};

1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233
/**
 * 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,
};

#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

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 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 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 1399 1400 1401 1402 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 1432 1433 1434
/**
 *	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
 *
 *	@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
 *	@iflink:	unique device identifier
 *
 *	@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
 *
 *	@carrier_changes:	Stats to monitor carrier on<->off transitions
 *
 *	@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
 *	@fwd_ops:	Management operations
 *	@header_ops:	Includes callbacks for creating,parsing,rebuilding,etc
 *			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:			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
 *	@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()
 *	@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
 *
 *	@_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
 *
 *	@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
 *
 *	@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
 *	@index_hlist:		Device index hash chain
 *	@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
 *
 *	@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
 *
 *	@group:		The group, that the device belongs to
 *	@pm_qos_req:	Power Management QoS object
L
Linus Torvalds 已提交
1435 1436 1437 1438 1439
 *
 *	FIXME: cleanup struct net_device such that network protocol info
 *	moves out.
 */

E
Eric Dumazet 已提交
1440
struct net_device {
L
Linus Torvalds 已提交
1441
	char			name[IFNAMSIZ];
1442
	struct hlist_node	name_hlist;
1443
	char 			*ifalias;
L
Linus Torvalds 已提交
1444 1445 1446 1447
	/*
	 *	I/O specific fields
	 *	FIXME: Merge these and struct ifmap into one
	 */
1448 1449 1450 1451
	unsigned long		mem_end;
	unsigned long		mem_start;
	unsigned long		base_addr;
	int			irq;
L
Linus Torvalds 已提交
1452 1453

	/*
1454 1455
	 *	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
1456 1457 1458 1459 1460
	 *	part of the usual set specified in Space.c.
	 */

	unsigned long		state;

1461
	struct list_head	dev_list;
1462
	struct list_head	napi_list;
1463
	struct list_head	unreg_list;
1464
	struct list_head	close_list;
1465 1466 1467 1468 1469 1470 1471 1472 1473 1474

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

	struct {
		struct list_head upper;
		struct list_head lower;
	} all_adj_list;
1475

1476 1477 1478 1479
	netdev_features_t	features;
	netdev_features_t	hw_features;
	netdev_features_t	wanted_features;
	netdev_features_t	vlan_features;
1480
	netdev_features_t	hw_enc_features;
S
Simon Horman 已提交
1481
	netdev_features_t	mpls_features;
1482

L
Linus Torvalds 已提交
1483 1484 1485
	int			ifindex;
	int			iflink;

R
Rusty Russell 已提交
1486
	struct net_device_stats	stats;
1487 1488 1489

	atomic_long_t		rx_dropped;
	atomic_long_t		tx_dropped;
L
Linus Torvalds 已提交
1490

1491 1492
	atomic_t		carrier_changes;

1493
#ifdef CONFIG_WIRELESS_EXT
L
Linus Torvalds 已提交
1494 1495
	const struct iw_handler_def *	wireless_handlers;
	struct iw_public_data *	wireless_data;
1496
#endif
1497
	const struct net_device_ops *netdev_ops;
1498
	const struct ethtool_ops *ethtool_ops;
1499
	const struct forwarding_accel_ops *fwd_ops;
L
Linus Torvalds 已提交
1500

1501 1502
	const struct header_ops *header_ops;

1503 1504 1505
	unsigned int		flags;
	unsigned int		priv_flags;

L
Linus Torvalds 已提交
1506
	unsigned short		gflags;
1507
	unsigned short		padded;
L
Linus Torvalds 已提交
1508

1509 1510
	unsigned char		operstate;
	unsigned char		link_mode;
S
Stefan Rompf 已提交
1511

1512 1513
	unsigned char		if_port;
	unsigned char		dma;
1514

1515 1516 1517
	unsigned int		mtu;
	unsigned short		type;
	unsigned short		hard_header_len;
L
Linus Torvalds 已提交
1518

1519 1520 1521
	unsigned short		needed_headroom;
	unsigned short		needed_tailroom;

L
Linus Torvalds 已提交
1522
	/* Interface address info. */
1523 1524 1525
	unsigned char		perm_addr[MAX_ADDR_LEN];
	unsigned char		addr_assign_type;
	unsigned char		addr_len;
1526
	unsigned short		neigh_priv_len;
1527 1528
	unsigned short          dev_id;
	unsigned short          dev_port;
J
Jiri Pirko 已提交
1529
	spinlock_t		addr_list_lock;
1530 1531 1532 1533
	struct netdev_hw_addr_list	uc;
	struct netdev_hw_addr_list	mc;
	struct netdev_hw_addr_list	dev_addrs;

1534 1535 1536 1537
#ifdef CONFIG_SYSFS
	struct kset		*queues_kset;
#endif

1538 1539
	unsigned char		name_assign_type;

1540
	bool			uc_promisc;
1541 1542
	unsigned int		promiscuity;
	unsigned int		allmulti;
L
Linus Torvalds 已提交
1543 1544 1545


	/* Protocol specific pointers */
1546

1547
#if IS_ENABLED(CONFIG_VLAN_8021Q)
1548
	struct vlan_info __rcu	*vlan_info;
1549
#endif
1550
#if IS_ENABLED(CONFIG_NET_DSA)
1551
	struct dsa_switch_tree	*dsa_ptr;
1552 1553
#endif
#if IS_ENABLED(CONFIG_TIPC)
1554
	struct tipc_bearer __rcu *tipc_ptr;
1555
#endif
1556 1557 1558 1559 1560 1561
	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;
L
Linus Torvalds 已提交
1562

1563
/*
E
Eric Dumazet 已提交
1564
 * Cache lines mostly used on receive path (including eth_type_trans())
1565
 */
1566
	unsigned long		last_rx;
1567

1568
	/* Interface address info used in eth_type_trans() */
1569
	unsigned char		*dev_addr;
1570

T
Tom Herbert 已提交
1571

1572
#ifdef CONFIG_SYSFS
T
Tom Herbert 已提交
1573 1574 1575
	struct netdev_rx_queue	*_rx;

	unsigned int		num_rx_queues;
1576
	unsigned int		real_num_rx_queues;
1577

E
Eric Dumazet 已提交
1578
#endif
T
Tom Herbert 已提交
1579

1580 1581
	rx_handler_func_t __rcu	*rx_handler;
	void __rcu		*rx_handler_data;
1582

1583
	struct netdev_queue __rcu *ingress_queue;
1584
	unsigned char		broadcast[MAX_ADDR_LEN];
1585

E
Eric Dumazet 已提交
1586 1587 1588 1589

/*
 * Cache lines mostly used on transmit path
 */
1590 1591
	struct netdev_queue	*_tx ____cacheline_aligned_in_smp;
	unsigned int		num_tx_queues;
1592
	unsigned int		real_num_tx_queues;
1593
	struct Qdisc		*qdisc;
1594
	unsigned long		tx_queue_len;
1595
	spinlock_t		tx_global_lock;
E
Eric Dumazet 已提交
1596

T
Tom Herbert 已提交
1597
#ifdef CONFIG_XPS
E
Eric Dumazet 已提交
1598
	struct xps_dev_maps __rcu *xps_maps;
T
Tom Herbert 已提交
1599
#endif
1600 1601 1602
#ifdef CONFIG_RFS_ACCEL
	struct cpu_rmap		*rx_cpu_rmap;
#endif
T
Tom Herbert 已提交
1603

1604
	/* These may be needed for future network-power-down code. */
1605 1606 1607 1608 1609

	/*
	 * trans_start here is expensive for high speed devices on SMP,
	 * please use netdev_queue->trans_start instead.
	 */
1610
	unsigned long		trans_start;
1611

1612
	int			watchdog_timeo;
1613 1614
	struct timer_list	watchdog_timer;

E
Eric Dumazet 已提交
1615
	int __percpu		*pcpu_refcnt;
L
Linus Torvalds 已提交
1616 1617
	struct list_head	todo_list;

1618
	struct hlist_node	index_hlist;
1619
	struct list_head	link_watch_list;
1620

L
Linus Torvalds 已提交
1621
	enum { NETREG_UNINITIALIZED=0,
1622
	       NETREG_REGISTERED,	/* completed register_netdevice */
L
Linus Torvalds 已提交
1623 1624 1625
	       NETREG_UNREGISTERING,	/* called unregister_netdevice */
	       NETREG_UNREGISTERED,	/* completed unregister todo */
	       NETREG_RELEASED,		/* called free_netdev */
1626
	       NETREG_DUMMY,		/* dummy device for NAPI poll */
1627 1628
	} reg_state:8;

1629
	bool dismantle;
1630 1631 1632 1633 1634

	enum {
		RTNL_LINK_INITIALIZED,
		RTNL_LINK_INITIALIZING,
	} rtnl_link_state:16;
L
Linus Torvalds 已提交
1635

1636
	void (*destructor)(struct net_device *dev);
L
Linus Torvalds 已提交
1637 1638

#ifdef CONFIG_NETPOLL
1639
	struct netpoll_info __rcu	*npinfo;
L
Linus Torvalds 已提交
1640
#endif
1641

1642
#ifdef CONFIG_NET_NS
1643
	struct net		*nd_net;
1644
#endif
1645

D
David S. Miller 已提交
1646
	/* mid-layer private */
E
Eric Dumazet 已提交
1647
	union {
1648 1649
		void					*ml_priv;
		struct pcpu_lstats __percpu		*lstats;
1650
		struct pcpu_sw_netstats __percpu	*tstats;
1651 1652
		struct pcpu_dstats __percpu		*dstats;
		struct pcpu_vstats __percpu		*vstats;
E
Eric Dumazet 已提交
1653
	};
1654

E
Eric Dumazet 已提交
1655
	struct garp_port __rcu	*garp_port;
1656
	struct mrp_port __rcu	*mrp_port;
L
Linus Torvalds 已提交
1657

1658
	struct device	dev;
1659
	const struct attribute_group *sysfs_groups[4];
1660
	const struct attribute_group *sysfs_rx_queue_group;
P
Patrick McHardy 已提交
1661 1662

	const struct rtnl_link_ops *rtnl_link_ops;
1663

1664 1665 1666
	/* for setting kernel sock attribute on TCP connection setup */
#define GSO_MAX_SIZE		65536
	unsigned int		gso_max_size;
1667 1668
#define GSO_MAX_SEGS		65535
	u16			gso_max_segs;
1669

J
Jeff Kirsher 已提交
1670
#ifdef CONFIG_DCB
1671
	const struct dcbnl_rtnl_ops *dcbnl_ops;
1672
#endif
1673 1674 1675
	u8 num_tc;
	struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
	u8 prio_tc_map[TC_BITMASK + 1];
1676

1677
#if IS_ENABLED(CONFIG_FCOE)
1678
	unsigned int		fcoe_ddp_xid;
1679
#endif
1680
#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
1681
	struct netprio_map __rcu *priomap;
1682
#endif
1683
	struct phy_device *phydev;
1684
	struct lock_class_key *qdisc_tx_busylock;
1685
	int group;
1686
	struct pm_qos_request	pm_qos_req;
L
Linus Torvalds 已提交
1687
};
1688
#define to_net_dev(d) container_of(d, struct net_device, dev)
L
Linus Torvalds 已提交
1689 1690 1691

#define	NETDEV_ALIGN		32

1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742
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;
}

1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761
static inline
struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
					 unsigned int index)
{
	return &dev->_tx[index];
}

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

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

1762
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
1763 1764
				    struct sk_buff *skb,
				    void *accel_priv);
1765

1766 1767 1768 1769 1770 1771
/*
 * Net namespace inlines
 */
static inline
struct net *dev_net(const struct net_device *dev)
{
E
Eric Dumazet 已提交
1772
	return read_pnet(&dev->nd_net);
1773 1774 1775
}

static inline
1776
void dev_net_set(struct net_device *dev, struct net *net)
1777 1778
{
#ifdef CONFIG_NET_NS
1779 1780
	release_net(dev->nd_net);
	dev->nd_net = hold_net(net);
1781 1782 1783
#endif
}

1784
static inline bool netdev_uses_dsa(struct net_device *dev)
1785
{
1786
#ifdef CONFIG_NET_DSA
1787 1788
	if (dev->dsa_ptr != NULL)
		return dsa_uses_tagged_protocol(dev->dsa_ptr);
1789
#endif
1790
	return false;
1791 1792
}

1793 1794 1795 1796 1797 1798
/**
 *	netdev_priv - access network device private data
 *	@dev: network device
 *
 * Get network device private data
 */
1799
static inline void *netdev_priv(const struct net_device *dev)
L
Linus Torvalds 已提交
1800
{
1801
	return (char *)dev + ALIGN(sizeof(struct net_device), NETDEV_ALIGN);
L
Linus Torvalds 已提交
1802 1803 1804 1805 1806
}

/* Set the sysfs physical device reference for the network logical device
 * if set prior to registration will cause a symlink during initialization.
 */
1807
#define SET_NETDEV_DEV(net, pdev)	((net)->dev.parent = (pdev))
L
Linus Torvalds 已提交
1808

1809
/* Set the sysfs device type for the network logical device to allow
1810
 * fine-grained identification of different network device types. For
1811 1812 1813 1814
 * example Ethernet, Wirelss LAN, Bluetooth, WiMAX etc.
 */
#define SET_NETDEV_DEVTYPE(net, devtype)	((net)->dev.type = (devtype))

E
Eric Dumazet 已提交
1815 1816 1817 1818 1819
/* Default NAPI poll() weight
 * Device drivers are strongly advised to not use bigger value
 */
#define NAPI_POLL_WEIGHT 64

1820 1821 1822 1823 1824 1825 1826 1827 1828 1829
/**
 *	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.
 */
1830 1831
void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
		    int (*poll)(struct napi_struct *, int), int weight);
1832

1833 1834 1835 1836 1837 1838
/**
 *  netif_napi_del - remove a napi context
 *  @napi: napi context
 *
 *  netif_napi_del() removes a napi context from the network device napi list
 */
1839 1840 1841
void netif_napi_del(struct napi_struct *napi);

struct napi_gro_cb {
1842 1843 1844
	/* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */
	void *frag0;

1845 1846 1847
	/* Length of frag0. */
	unsigned int frag0_len;

1848 1849 1850
	/* This indicates where we are processing relative to skb->data. */
	int data_offset;

1851
	/* This is non-zero if the packet cannot be merged with the new skb. */
1852 1853 1854 1855
	u16	flush;

	/* Save the IP ID here and check when we get to the transport layer */
	u16	flush_id;
1856 1857

	/* Number of segments aggregated. */
1858 1859 1860 1861
	u16	count;

	/* This is non-zero if the packet may be of the same flow. */
	u8	same_flow;
H
Herbert Xu 已提交
1862 1863

	/* Free the skb? */
1864
	u8	free;
1865 1866
#define NAPI_GRO_FREE		  1
#define NAPI_GRO_FREE_STOLEN_HEAD 2
1867 1868 1869

	/* jiffies when first packet was created/queued */
	unsigned long age;
1870 1871

	/* Used in ipv6_gro_receive() */
1872 1873 1874
	u16	proto;

	/* Used in udp_gro_receive */
T
Tom Herbert 已提交
1875 1876 1877 1878 1879 1880 1881
	u8	udp_mark:1;

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

	/* Number encapsulation layers crossed */
	u8	encapsulation;
1882

1883 1884 1885
	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
	__wsum	csum;

1886 1887
	/* used in skb_gro_receive() slow path */
	struct sk_buff *last;
1888 1889 1890
};

#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
1891

L
Linus Torvalds 已提交
1892
struct packet_type {
D
David S. Miller 已提交
1893 1894 1895 1896 1897 1898
	__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 *);
1899 1900
	bool			(*id_match)(struct packet_type *ptype,
					    struct sock *sk);
L
Linus Torvalds 已提交
1901 1902 1903 1904
	void			*af_packet_priv;
	struct list_head	list;
};

1905
struct offload_callbacks {
1906
	struct sk_buff		*(*gso_segment)(struct sk_buff *skb,
1907
						netdev_features_t features);
1908
	int			(*gso_send_check)(struct sk_buff *skb);
1909 1910
	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
					       struct sk_buff *skb);
1911
	int			(*gro_complete)(struct sk_buff *skb, int nhoff);
1912 1913 1914 1915 1916 1917
};

struct packet_offload {
	__be16			 type;	/* This is really htons(ether_type). */
	struct offload_callbacks callbacks;
	struct list_head	 list;
L
Linus Torvalds 已提交
1918 1919
};

1920 1921 1922 1923 1924
struct udp_offload {
	__be16			 port;
	struct offload_callbacks callbacks;
};

1925 1926 1927 1928 1929 1930 1931
struct dsa_device_ops {
	netdev_tx_t (*xmit)(struct sk_buff *skb, struct net_device *dev);
	int (*rcv)(struct sk_buff *skb, struct net_device *dev,
		   struct packet_type *pt, struct net_device *orig_dev);
};


1932 1933 1934 1935 1936 1937 1938 1939 1940
/* 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;
};

1941 1942
#define netdev_alloc_pcpu_stats(type)				\
({								\
1943
	typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \
1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954
	if (pcpu_stats)	{					\
		int i;						\
		for_each_possible_cpu(i) {			\
			typeof(type) *stat;			\
			stat = per_cpu_ptr(pcpu_stats, i);	\
			u64_stats_init(&stat->syncp);		\
		}						\
	}							\
	pcpu_stats;						\
})

L
Linus Torvalds 已提交
1955 1956
#include <linux/notifier.h>

1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969
/* 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
1970
#define NETDEV_CHANGEMTU	0x0007 /* notify after mtu change happened */
1971 1972 1973 1974 1975 1976 1977 1978 1979
#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
1980
#define NETDEV_UNREGISTER_FINAL 0x0011
1981 1982 1983
#define NETDEV_RELEASE		0x0012
#define NETDEV_NOTIFY_PEERS	0x0013
#define NETDEV_JOIN		0x0014
1984
#define NETDEV_CHANGEUPPER	0x0015
1985
#define NETDEV_RESEND_IGMP	0x0016
1986
#define NETDEV_PRECHANGEMTU	0x0017 /* notify before mtu change happened */
1987
#define NETDEV_CHANGEINFODATA	0x0018
1988

1989 1990
int register_netdevice_notifier(struct notifier_block *nb);
int unregister_netdevice_notifier(struct notifier_block *nb);
1991 1992 1993 1994 1995

struct netdev_notifier_info {
	struct net_device *dev;
};

1996 1997 1998 1999 2000
struct netdev_notifier_change_info {
	struct netdev_notifier_info info; /* must be first */
	unsigned int flags_changed;
};

2001 2002 2003 2004 2005 2006
static inline void netdev_notifier_info_init(struct netdev_notifier_info *info,
					     struct net_device *dev)
{
	info->dev = dev;
}

2007 2008 2009 2010 2011 2012
static inline struct net_device *
netdev_notifier_info_to_dev(const struct netdev_notifier_info *info)
{
	return info->dev;
}

2013
int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
2014 2015


L
Linus Torvalds 已提交
2016 2017
extern rwlock_t				dev_base_lock;		/* Device list lock */

2018 2019
#define for_each_netdev(net, d)		\
		list_for_each_entry(d, &(net)->dev_base_head, dev_list)
2020 2021
#define for_each_netdev_reverse(net, d)	\
		list_for_each_entry_reverse(d, &(net)->dev_base_head, dev_list)
2022 2023
#define for_each_netdev_rcu(net, d)		\
		list_for_each_entry_rcu(d, &(net)->dev_base_head, dev_list)
2024 2025 2026 2027
#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)
2028 2029
#define for_each_netdev_continue_rcu(net, d)		\
	list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list)
2030 2031 2032
#define for_each_netdev_in_bond_rcu(bond, slave)	\
		for_each_netdev_rcu(&init_net, slave)	\
			if (netdev_master_upper_dev_get_rcu(slave) == bond)
2033
#define net_device_entry(lh)	list_entry(lh, struct net_device, dev_list)
2034

2035 2036 2037 2038 2039
static inline struct net_device *next_net_device(struct net_device *dev)
{
	struct list_head *lh;
	struct net *net;

2040
	net = dev_net(dev);
2041 2042 2043 2044
	lh = dev->dev_list.next;
	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
}

2045 2046 2047 2048 2049 2050
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
2051
	lh = rcu_dereference(list_next_rcu(&dev->dev_list));
2052 2053 2054
	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
}

2055 2056 2057 2058 2059
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);
}
2060

E
Eric Dumazet 已提交
2061 2062 2063 2064 2065 2066 2067
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);
}

2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090
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);

struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short flags,
					unsigned short mask);
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);
void dev_disable_lro(struct net_device *dev);
int dev_loopback_xmit(struct sk_buff *newskb);
int dev_queue_xmit(struct sk_buff *skb);
2091
int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv);
2092 2093 2094
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);
2095 2096 2097 2098 2099
static inline void unregister_netdevice(struct net_device *dev)
{
	unregister_netdevice_queue(dev, NULL);
}

2100 2101
int netdev_refcnt_read(const struct net_device *dev);
void free_netdev(struct net_device *dev);
2102
void netdev_freemem(struct net_device *dev);
2103 2104
void synchronize_net(void);
int init_dummy_netdev(struct net_device *dev);
2105

2106 2107 2108 2109 2110 2111
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);
2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127

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;
}

2128 2129
static inline void *skb_gro_header_fast(struct sk_buff *skb,
					unsigned int offset)
2130
{
2131 2132
	return NAPI_GRO_CB(skb)->frag0 + offset;
}
2133

2134 2135 2136 2137
static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen)
{
	return NAPI_GRO_CB(skb)->frag0_len < hlen;
}
2138

2139 2140 2141
static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen,
					unsigned int offset)
{
2142 2143 2144
	if (!pskb_may_pull(skb, hlen))
		return NULL;

2145 2146
	NAPI_GRO_CB(skb)->frag0 = NULL;
	NAPI_GRO_CB(skb)->frag0_len = 0;
2147
	return skb->data + offset;
2148
}
L
Linus Torvalds 已提交
2149

H
Herbert Xu 已提交
2150 2151
static inline void *skb_gro_network_header(struct sk_buff *skb)
{
2152 2153
	return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) +
	       skb_network_offset(skb);
H
Herbert Xu 已提交
2154 2155
}

2156 2157 2158
static inline void skb_gro_postpull_rcsum(struct sk_buff *skb,
					const void *start, unsigned int len)
{
T
Tom Herbert 已提交
2159
	if (NAPI_GRO_CB(skb)->csum_valid)
2160 2161 2162 2163
		NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum,
						  csum_partial(start, len, 0));
}

T
Tom Herbert 已提交
2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229
/* 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);

static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb,
						      bool zero_okay,
						      __sum16 check)
{
	return (skb->ip_summed != CHECKSUM_PARTIAL &&
		(skb->ip_summed != CHECKSUM_UNNECESSARY ||
		 (NAPI_GRO_CB(skb)->encapsulation > skb->encapsulation)) &&
		(!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);
}

/* Update skb for CHECKSUM_UNNECESSARY when we verified a top level
 * checksum or an encapsulated one during GRO. This saves work
 * if we fallback to normal path with the packet.
 */
static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb)
{
	if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
		if (NAPI_GRO_CB(skb)->encapsulation)
			skb->encapsulation = 1;
	} else if (skb->ip_summed != CHECKSUM_PARTIAL) {
		skb->ip_summed = CHECKSUM_UNNECESSARY;
		skb->encapsulation = 0;
	}
}

#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));		\
	if (!__ret)							\
		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)

2230 2231
static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
				  unsigned short type,
2232
				  const void *daddr, const void *saddr,
2233
				  unsigned int len)
2234
{
2235
	if (!dev->header_ops || !dev->header_ops->create)
2236
		return 0;
2237 2238

	return dev->header_ops->create(skb, dev, type, daddr, saddr, len);
2239 2240
}

S
Stephen Hemminger 已提交
2241 2242 2243 2244 2245
static inline int dev_parse_header(const struct sk_buff *skb,
				   unsigned char *haddr)
{
	const struct net_device *dev = skb->dev;

2246
	if (!dev->header_ops || !dev->header_ops->parse)
S
Stephen Hemminger 已提交
2247
		return 0;
2248
	return dev->header_ops->parse(skb, haddr);
S
Stephen Hemminger 已提交
2249 2250
}

2251 2252 2253 2254 2255 2256 2257 2258 2259
static inline int dev_rebuild_header(struct sk_buff *skb)
{
	const struct net_device *dev = skb->dev;

	if (!dev->header_ops || !dev->header_ops->rebuild)
		return 0;
	return dev->header_ops->rebuild(skb);
}

L
Linus Torvalds 已提交
2260
typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
2261
int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
L
Linus Torvalds 已提交
2262 2263 2264 2265 2266
static inline int unregister_gifconf(unsigned int family)
{
	return register_gifconf(family, NULL);
}

2267
#ifdef CONFIG_NET_FLOW_LIMIT
2268
#define FLOW_LIMIT_HISTORY	(1 << 7)  /* must be ^2 and !overflow buckets */
2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279
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
2280
/*
E
Eric Dumazet 已提交
2281
 * Incoming packets are placed on per-cpu queues
L
Linus Torvalds 已提交
2282
 */
E
Eric Dumazet 已提交
2283
struct softnet_data {
2284
	struct Qdisc		*output_queue;
2285
	struct Qdisc		**output_queue_tailp;
L
Linus Torvalds 已提交
2286 2287
	struct list_head	poll_list;
	struct sk_buff		*completion_queue;
2288
	struct sk_buff_head	process_queue;
L
Linus Torvalds 已提交
2289

C
Changli Gao 已提交
2290
	/* stats */
2291 2292 2293 2294
	unsigned int		processed;
	unsigned int		time_squeeze;
	unsigned int		cpu_collision;
	unsigned int		received_rps;
C
Changli Gao 已提交
2295

2296
#ifdef CONFIG_RPS
E
Eric Dumazet 已提交
2297 2298 2299
	struct softnet_data	*rps_ipi_list;

	/* Elements below can be accessed between CPUs for RPS */
T
Tom Herbert 已提交
2300
	struct call_single_data	csd ____cacheline_aligned_in_smp;
E
Eric Dumazet 已提交
2301 2302
	struct softnet_data	*rps_ipi_next;
	unsigned int		cpu;
T
Tom Herbert 已提交
2303
	unsigned int		input_queue_head;
2304
	unsigned int		input_queue_tail;
2305
#endif
2306
	unsigned int		dropped;
T
Tom Herbert 已提交
2307
	struct sk_buff_head	input_pkt_queue;
2308
	struct napi_struct	backlog;
2309 2310

#ifdef CONFIG_NET_FLOW_LIMIT
2311
	struct sd_flow_limit __rcu *flow_limit;
2312
#endif
L
Linus Torvalds 已提交
2313 2314
};

2315
static inline void input_queue_head_incr(struct softnet_data *sd)
T
Tom Herbert 已提交
2316 2317
{
#ifdef CONFIG_RPS
2318 2319 2320 2321 2322 2323 2324 2325 2326
	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
2327 2328 2329
#endif
}

T
Tom Herbert 已提交
2330
DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
L
Linus Torvalds 已提交
2331

2332
void __netif_schedule(struct Qdisc *q);
L
Linus Torvalds 已提交
2333

2334
static inline void netif_schedule_queue(struct netdev_queue *txq)
L
Linus Torvalds 已提交
2335
{
2336
	if (!(txq->state & QUEUE_STATE_ANY_XOFF))
2337
		__netif_schedule(txq->qdisc);
2338 2339
}

2340 2341 2342 2343 2344 2345 2346 2347
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));
}

2348 2349
static inline void netif_tx_start_queue(struct netdev_queue *dev_queue)
{
2350
	clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
2351 2352
}

2353 2354 2355 2356 2357 2358
/**
 *	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
2359 2360
static inline void netif_start_queue(struct net_device *dev)
{
2361
	netif_tx_start_queue(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
2362 2363
}

2364 2365 2366 2367 2368 2369 2370 2371 2372 2373
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);
	}
}

2374
static inline void netif_tx_wake_queue(struct netdev_queue *dev_queue)
L
Linus Torvalds 已提交
2375
{
2376
	if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state))
2377
		__netif_schedule(dev_queue->qdisc);
2378 2379
}

2380 2381 2382 2383 2384 2385 2386
/**
 *	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.
 */
2387 2388
static inline void netif_wake_queue(struct net_device *dev)
{
2389
	netif_tx_wake_queue(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
2390 2391
}

2392 2393 2394 2395 2396 2397 2398 2399 2400 2401
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);
	}
}

2402 2403
static inline void netif_tx_stop_queue(struct netdev_queue *dev_queue)
{
2404
	if (WARN_ON(!dev_queue)) {
2405
		pr_info("netif_stop_queue() cannot be called before register_netdev()\n");
2406 2407
		return;
	}
2408
	set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
2409 2410
}

2411 2412 2413 2414 2415 2416 2417
/**
 *	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
2418 2419
static inline void netif_stop_queue(struct net_device *dev)
{
2420
	netif_tx_stop_queue(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
2421 2422
}

2423 2424 2425 2426 2427 2428 2429 2430 2431 2432
static inline void netif_tx_stop_all_queues(struct net_device *dev)
{
	unsigned int i;

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

2433
static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue)
2434
{
2435
	return test_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
2436 2437
}

2438 2439 2440 2441 2442 2443
/**
 *	netif_queue_stopped - test if transmit queue is flowblocked
 *	@dev: network device
 *
 *	Test if transmit queue on device is currently unable to send.
 */
2444
static inline bool netif_queue_stopped(const struct net_device *dev)
L
Linus Torvalds 已提交
2445
{
2446
	return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0));
L
Linus Torvalds 已提交
2447 2448
}

2449
static inline bool netif_xmit_stopped(const struct netdev_queue *dev_queue)
2450
{
2451 2452 2453
	return dev_queue->state & QUEUE_STATE_ANY_XOFF;
}

2454 2455
static inline bool
netif_xmit_frozen_or_stopped(const struct netdev_queue *dev_queue)
2456 2457 2458 2459
{
	return dev_queue->state & QUEUE_STATE_ANY_XOFF_OR_FROZEN;
}

2460 2461 2462 2463 2464 2465
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;
}

2466 2467 2468
static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
					unsigned int bytes)
{
T
Tom Herbert 已提交
2469 2470
#ifdef CONFIG_BQL
	dql_queued(&dev_queue->dql, bytes);
2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486

	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
2487
#endif
2488 2489
}

2490 2491 2492 2493 2494 2495 2496 2497 2498
/**
 * 	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
 */
2499 2500 2501 2502 2503 2504
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,
2505
					     unsigned int pkts, unsigned int bytes)
2506
{
T
Tom Herbert 已提交
2507
#ifdef CONFIG_BQL
2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524
	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
2525
#endif
2526 2527
}

2528 2529 2530 2531 2532 2533 2534 2535 2536 2537
/**
 * 	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()
 */
2538
static inline void netdev_completed_queue(struct net_device *dev,
2539
					  unsigned int pkts, unsigned int bytes)
2540 2541 2542 2543 2544 2545
{
	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
2546
#ifdef CONFIG_BQL
2547
	clear_bit(__QUEUE_STATE_STACK_XOFF, &q->state);
T
Tom Herbert 已提交
2548 2549
	dql_reset(&q->dql);
#endif
2550 2551
}

2552 2553 2554 2555 2556 2557 2558
/**
 * 	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
 */
2559 2560 2561
static inline void netdev_reset_queue(struct net_device *dev_queue)
{
	netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0));
2562 2563
}

2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583
/**
 * 	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;
}

2584 2585 2586 2587 2588 2589
/**
 *	netif_running - test if up
 *	@dev: network device
 *
 *	Test if the device has been brought up.
 */
2590
static inline bool netif_running(const struct net_device *dev)
L
Linus Torvalds 已提交
2591 2592 2593 2594
{
	return test_bit(__LINK_STATE_START, &dev->state);
}

2595 2596 2597 2598 2599 2600
/*
 * 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.
 */
2601 2602 2603 2604 2605 2606 2607 2608

/**
 *	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.
 */
2609 2610
static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index)
{
2611
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
2612 2613

	netif_tx_start_queue(txq);
2614 2615
}

2616 2617 2618 2619 2620 2621 2622
/**
 *	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.
 */
2623 2624
static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index)
{
2625
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
2626
	netif_tx_stop_queue(txq);
2627 2628
}

2629 2630 2631 2632 2633 2634 2635
/**
 *	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.
 */
2636 2637
static inline bool __netif_subqueue_stopped(const struct net_device *dev,
					    u16 queue_index)
2638
{
2639
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
2640 2641

	return netif_tx_queue_stopped(txq);
2642 2643
}

2644 2645
static inline bool netif_subqueue_stopped(const struct net_device *dev,
					  struct sk_buff *skb)
2646 2647 2648
{
	return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb));
}
2649 2650 2651 2652 2653 2654 2655 2656

/**
 *	netif_wake_subqueue - allow sending packets on subqueue
 *	@dev: network device
 *	@queue_index: sub queue index
 *
 * Resume individual transmit queue of a device with multiple transmit queues.
 */
2657 2658
static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
{
2659
	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
2660
	if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state))
2661
		__netif_schedule(txq->qdisc);
2662 2663
}

2664
#ifdef CONFIG_XPS
2665
int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
2666
			u16 index);
2667 2668
#else
static inline int netif_set_xps_queue(struct net_device *dev,
2669
				      const struct cpumask *mask,
2670 2671 2672 2673 2674 2675
				      u16 index)
{
	return 0;
}
#endif

2676 2677 2678 2679 2680
/*
 * 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,
2681
			      struct sk_buff *skb)
2682 2683 2684 2685
{
	return __skb_tx_hash(dev, skb, dev->real_num_tx_queues);
}

2686 2687 2688 2689 2690 2691
/**
 *	netif_is_multiqueue - test if device has multiple transmit queues
 *	@dev: network device
 *
 * Check if device has multiple transmit queues
 */
2692
static inline bool netif_is_multiqueue(const struct net_device *dev)
2693
{
E
Eric Dumazet 已提交
2694
	return dev->num_tx_queues > 1;
2695
}
L
Linus Torvalds 已提交
2696

2697
int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq);
2698

2699
#ifdef CONFIG_SYSFS
2700
int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq);
2701 2702 2703 2704 2705 2706 2707 2708
#else
static inline int netif_set_real_num_rx_queues(struct net_device *dev,
						unsigned int rxq)
{
	return 0;
}
#endif

2709 2710 2711
static inline int netif_copy_real_num_queues(struct net_device *to_dev,
					     const struct net_device *from_dev)
{
2712 2713 2714 2715 2716 2717
	int err;

	err = netif_set_real_num_tx_queues(to_dev,
					   from_dev->real_num_tx_queues);
	if (err)
		return err;
2718
#ifdef CONFIG_SYSFS
2719 2720 2721 2722 2723 2724 2725
	return netif_set_real_num_rx_queues(to_dev,
					    from_dev->real_num_rx_queues);
#else
	return 0;
#endif
}

2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737
#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

2738
#define DEFAULT_MAX_NUM_RSS_QUEUES	(8)
2739
int netif_get_num_default_rss_queues(void);
2740

2741 2742 2743 2744 2745 2746 2747
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
2748

2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766
/*
 * 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
2767
 */
2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786
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
2787

2788 2789 2790 2791 2792 2793 2794
int netif_rx(struct sk_buff *skb);
int netif_rx_ni(struct sk_buff *skb);
int netif_receive_skb(struct sk_buff *skb);
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);
2795 2796
struct packet_offload *gro_find_receive_by_type(__be16 type);
struct packet_offload *gro_find_complete_by_type(__be16 type);
2797 2798 2799 2800 2801 2802 2803

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

2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814
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);
2815 2816
void __dev_notify_flags(struct net_device *, unsigned int old_flags,
			unsigned int gchanges);
2817 2818 2819 2820 2821 2822 2823 2824 2825 2826
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,
			 struct netdev_phys_port_id *ppid);
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
2827
			struct netdev_queue *txq);
H
Herbert Xu 已提交
2828
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
2829
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
2830
bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb);
L
Linus Torvalds 已提交
2831

2832
extern int		netdev_budget;
L
Linus Torvalds 已提交
2833 2834

/* Called by rtnetlink.c:rtnl_unlock() */
2835
void netdev_run_todo(void);
L
Linus Torvalds 已提交
2836

2837 2838 2839 2840
/**
 *	dev_put - release reference to device
 *	@dev: network device
 *
2841
 * Release reference to device to allow it to be freed.
2842
 */
L
Linus Torvalds 已提交
2843 2844
static inline void dev_put(struct net_device *dev)
{
2845
	this_cpu_dec(*dev->pcpu_refcnt);
L
Linus Torvalds 已提交
2846 2847
}

2848 2849 2850 2851
/**
 *	dev_hold - get reference to device
 *	@dev: network device
 *
2852
 * Hold reference to device to keep it from being freed.
2853
 */
2854 2855
static inline void dev_hold(struct net_device *dev)
{
2856
	this_cpu_inc(*dev->pcpu_refcnt);
2857
}
L
Linus Torvalds 已提交
2858 2859 2860 2861

/* 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
2862 2863 2864 2865
 *
 * 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
2866 2867
 */

2868 2869 2870
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
2871

2872 2873 2874 2875 2876 2877
/**
 *	netif_carrier_ok - test if carrier present
 *	@dev: network device
 *
 * Check if carrier is present on device
 */
2878
static inline bool netif_carrier_ok(const struct net_device *dev)
L
Linus Torvalds 已提交
2879 2880 2881 2882
{
	return !test_bit(__LINK_STATE_NOCARRIER, &dev->state);
}

2883
unsigned long dev_trans_start(struct net_device *dev);
2884

2885
void __netdev_watchdog_up(struct net_device *dev);
L
Linus Torvalds 已提交
2886

2887
void netif_carrier_on(struct net_device *dev);
L
Linus Torvalds 已提交
2888

2889
void netif_carrier_off(struct net_device *dev);
L
Linus Torvalds 已提交
2890

2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903
/**
 *	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
2904 2905 2906 2907 2908 2909
static inline void netif_dormant_on(struct net_device *dev)
{
	if (!test_and_set_bit(__LINK_STATE_DORMANT, &dev->state))
		linkwatch_fire_event(dev);
}

2910 2911 2912 2913 2914 2915
/**
 *	netif_dormant_off - set device as not dormant.
 *	@dev: network device
 *
 * Device is not in dormant state.
 */
S
Stefan Rompf 已提交
2916 2917 2918 2919 2920 2921
static inline void netif_dormant_off(struct net_device *dev)
{
	if (test_and_clear_bit(__LINK_STATE_DORMANT, &dev->state))
		linkwatch_fire_event(dev);
}

2922 2923 2924 2925 2926 2927
/**
 *	netif_dormant - test if carrier present
 *	@dev: network device
 *
 * Check if carrier is present on device
 */
2928
static inline bool netif_dormant(const struct net_device *dev)
S
Stefan Rompf 已提交
2929 2930 2931 2932 2933
{
	return test_bit(__LINK_STATE_DORMANT, &dev->state);
}


2934 2935 2936 2937 2938 2939
/**
 *	netif_oper_up - test if device is operational
 *	@dev: network device
 *
 * Check if carrier is operational
 */
2940
static inline bool netif_oper_up(const struct net_device *dev)
E
Eric Dumazet 已提交
2941
{
S
Stefan Rompf 已提交
2942 2943 2944 2945
	return (dev->operstate == IF_OPER_UP ||
		dev->operstate == IF_OPER_UNKNOWN /* backward compat */);
}

2946 2947 2948 2949 2950 2951
/**
 *	netif_device_present - is device available or removed
 *	@dev: network device
 *
 * Check if device has not been removed from system.
 */
2952
static inline bool netif_device_present(struct net_device *dev)
L
Linus Torvalds 已提交
2953 2954 2955 2956
{
	return test_bit(__LINK_STATE_PRESENT, &dev->state);
}

2957
void netif_device_detach(struct net_device *dev);
L
Linus Torvalds 已提交
2958

2959
void netif_device_attach(struct net_device *dev);
L
Linus Torvalds 已提交
2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009

/*
 * 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;
}

3010
static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
H
Herbert Xu 已提交
3011
{
3012 3013
	spin_lock(&txq->_xmit_lock);
	txq->xmit_lock_owner = cpu;
3014 3015
}

3016 3017 3018 3019 3020 3021
static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
{
	spin_lock_bh(&txq->_xmit_lock);
	txq->xmit_lock_owner = smp_processor_id();
}

3022
static inline bool __netif_tx_trylock(struct netdev_queue *txq)
3023
{
3024
	bool ok = spin_trylock(&txq->_xmit_lock);
3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041
	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
3042 3043 3044 3045 3046 3047
static inline void txq_trans_update(struct netdev_queue *txq)
{
	if (txq->xmit_lock_owner != -1)
		txq->trans_start = jiffies;
}

3048 3049 3050 3051 3052 3053
/**
 *	netif_tx_lock - grab network device transmit lock
 *	@dev: network device
 *
 * Get network device transmit lock
 */
3054 3055
static inline void netif_tx_lock(struct net_device *dev)
{
3056
	unsigned int i;
3057
	int cpu;
3058

3059 3060
	spin_lock(&dev->tx_global_lock);
	cpu = smp_processor_id();
3061 3062
	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
3063 3064 3065 3066 3067 3068 3069

		/* 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.
		 */
3070
		__netif_tx_lock(txq, cpu);
3071 3072
		set_bit(__QUEUE_STATE_FROZEN, &txq->state);
		__netif_tx_unlock(txq);
3073
	}
H
Herbert Xu 已提交
3074 3075 3076 3077
}

static inline void netif_tx_lock_bh(struct net_device *dev)
{
3078 3079
	local_bh_disable();
	netif_tx_lock(dev);
H
Herbert Xu 已提交
3080 3081 3082 3083
}

static inline void netif_tx_unlock(struct net_device *dev)
{
3084 3085 3086 3087
	unsigned int i;

	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
3088

3089 3090 3091 3092 3093
		/* 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);
3094
		netif_schedule_queue(txq);
3095 3096
	}
	spin_unlock(&dev->tx_global_lock);
H
Herbert Xu 已提交
3097 3098 3099 3100
}

static inline void netif_tx_unlock_bh(struct net_device *dev)
{
3101 3102
	netif_tx_unlock(dev);
	local_bh_enable();
H
Herbert Xu 已提交
3103 3104
}

3105
#define HARD_TX_LOCK(dev, txq, cpu) {			\
3106
	if ((dev->features & NETIF_F_LLTX) == 0) {	\
3107
		__netif_tx_lock(txq, cpu);		\
3108 3109 3110
	}						\
}

3111 3112 3113 3114 3115
#define HARD_TX_TRYLOCK(dev, txq)			\
	(((dev->features & NETIF_F_LLTX) == 0) ?	\
		__netif_tx_trylock(txq) :		\
		true )

3116
#define HARD_TX_UNLOCK(dev, txq) {			\
3117
	if ((dev->features & NETIF_F_LLTX) == 0) {	\
3118
		__netif_tx_unlock(txq);			\
3119 3120 3121
	}						\
}

L
Linus Torvalds 已提交
3122 3123
static inline void netif_tx_disable(struct net_device *dev)
{
3124
	unsigned int i;
3125
	int cpu;
3126

3127 3128
	local_bh_disable();
	cpu = smp_processor_id();
3129 3130
	for (i = 0; i < dev->num_tx_queues; i++) {
		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
3131 3132

		__netif_tx_lock(txq, cpu);
3133
		netif_tx_stop_queue(txq);
3134
		__netif_tx_unlock(txq);
3135
	}
3136
	local_bh_enable();
L
Linus Torvalds 已提交
3137 3138
}

3139 3140 3141 3142 3143
static inline void netif_addr_lock(struct net_device *dev)
{
	spin_lock(&dev->addr_list_lock);
}

3144 3145
static inline void netif_addr_lock_nested(struct net_device *dev)
{
3146 3147 3148 3149 3150 3151
	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);
3152 3153
}

3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168
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);
}

3169
/*
3170
 * dev_addrs walker. Should be used only for read access. Call with
3171 3172 3173
 * rcu_read_lock held.
 */
#define for_each_dev_addr(dev, ha) \
3174
		list_for_each_entry_rcu(ha, &dev->dev_addrs.list, list)
3175

L
Linus Torvalds 已提交
3176 3177
/* These functions live elsewhere (drivers/net/net_init.c, but related) */

3178
void ether_setup(struct net_device *dev);
L
Linus Torvalds 已提交
3179 3180

/* Support for loadable net-drivers */
3181
struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
3182
				    unsigned char name_assign_type,
3183 3184
				    void (*setup)(struct net_device *),
				    unsigned int txqs, unsigned int rxqs);
3185 3186
#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
3187

3188 3189 3190
#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
3191

3192 3193
int register_netdev(struct net_device *dev);
void unregister_netdev(struct net_device *dev);
3194

3195
/* General hardware address lists handling functions */
3196 3197 3198 3199
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);
3200 3201 3202 3203 3204 3205 3206 3207 3208
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 *));
3209
void __hw_addr_init(struct netdev_hw_addr_list *list);
3210

3211
/* Functions used for device addresses handling */
3212 3213 3214 3215 3216 3217
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);
3218 3219

/* Functions used for unicast addresses handling */
3220 3221 3222 3223 3224 3225 3226 3227
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);
3228

3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260
/**
 *  __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);
}

/**
 *  __dev_uc_unsync - Remove synchonized addresses from device
 *  @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);
}

3261
/* Functions used for multicast addresses handling */
3262 3263 3264 3265 3266 3267 3268 3269 3270 3271
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);
3272

3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304
/**
 *  __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);
}

/**
 *  __dev_mc_unsync - Remove synchonized addresses from device
 *  @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);
}

3305
/* Functions used for secondary unicast and multicast support */
3306 3307 3308 3309 3310 3311 3312
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
3313
/* Load a device via the kmod */
3314 3315 3316 3317 3318
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);
3319

L
Linus Torvalds 已提交
3320
extern int		netdev_max_backlog;
E
Eric Dumazet 已提交
3321
extern int		netdev_tstamp_prequeue;
L
Linus Torvalds 已提交
3322
extern int		weight_p;
3323
extern int		bpf_jit_enable;
J
Jiri Pirko 已提交
3324

3325
bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev);
3326 3327
struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
						     struct list_head **iter);
3328 3329
struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
						     struct list_head **iter);
3330

3331 3332 3333 3334 3335 3336 3337
/* 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)))

3338
/* iterate through upper list, must be called under RCU read lock */
3339 3340 3341 3342 3343
#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)))
3344

3345 3346 3347 3348
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);
3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361

#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)))

3362 3363 3364 3365 3366 3367 3368 3369
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)))

3370
void *netdev_adjacent_get_private(struct list_head *adj_list);
3371
void *netdev_lower_get_first_private_rcu(struct net_device *dev);
3372 3373 3374 3375
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
3376
				 struct net_device *upper_dev);
3377 3378 3379 3380 3381
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);
3382
void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
3383 3384
void *netdev_lower_dev_get_private(struct net_device *dev,
				   struct net_device *lower_dev);
3385 3386
int dev_get_nest_level(struct net_device *dev,
		       bool (*type_check)(struct net_device *dev));
3387 3388 3389 3390 3391
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);
3392 3393 3394 3395 3396 3397

static inline
struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features)
{
	return __skb_gso_segment(skb, features, true);
}
3398
__be16 skb_network_protocol(struct sk_buff *skb, int *depth);
3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410

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)));
}
3411

3412
#ifdef CONFIG_BUG
3413
void netdev_rx_csum_fault(struct net_device *dev);
3414 3415 3416 3417 3418
#else
static inline void netdev_rx_csum_fault(struct net_device *dev)
{
}
#endif
L
Linus Torvalds 已提交
3419
/* rx skb timestamps */
3420 3421
void net_enable_timestamp(void);
void net_disable_timestamp(void);
L
Linus Torvalds 已提交
3422

3423
#ifdef CONFIG_PROC_FS
3424
int __init dev_proc_init(void);
3425 3426
#else
#define dev_proc_init() 0
3427 3428
#endif

D
David S. Miller 已提交
3429 3430 3431
static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
					      struct sk_buff *skb, struct net_device *dev)
{
3432 3433
	skb->xmit_more = 0;
	return ops->ndo_start_xmit(skb, dev);
D
David S. Miller 已提交
3434 3435 3436 3437 3438 3439 3440 3441 3442
}

static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	const struct net_device_ops *ops = dev->netdev_ops;

	return __netdev_start_xmit(ops, skb, dev);
}

3443 3444 3445 3446
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);
3447 3448 3449 3450 3451 3452 3453 3454 3455 3456

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);
}
3457

3458 3459
extern struct kobj_ns_type_operations net_ns_type_operations;

3460
const char *netdev_drivername(const struct net_device *dev);
3461

3462
void linkwatch_run_queue(void);
3463

3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477
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;
}

3478 3479
static inline netdev_features_t netdev_get_wanted_features(
	struct net_device *dev)
3480 3481 3482
{
	return (dev->features & ~dev->hw_features) | dev->wanted_features;
}
3483 3484
netdev_features_t netdev_increment_features(netdev_features_t all,
	netdev_features_t one, netdev_features_t mask);
3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495

/* 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);
}

3496
int __netdev_update_features(struct net_device *dev);
3497
void netdev_update_features(struct net_device *dev);
3498
void netdev_change_features(struct net_device *dev);
3499

3500 3501 3502
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
					struct net_device *dev);

3503
netdev_features_t netif_skb_features(struct sk_buff *skb);
3504

3505
static inline bool net_gso_ok(netdev_features_t features, int gso_type)
3506
{
3507
	netdev_features_t feature = gso_type << NETIF_F_GSO_SHIFT;
3508 3509 3510 3511 3512 3513 3514 3515

	/* 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));
3516 3517 3518 3519 3520 3521 3522
	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));
	BUILD_BUG_ON(SKB_GSO_MPLS    != (NETIF_F_GSO_MPLS >> NETIF_F_GSO_SHIFT));
3523

3524
	return (features & feature) == feature;
3525 3526
}

3527
static inline bool skb_gso_ok(struct sk_buff *skb, netdev_features_t features)
3528
{
H
Herbert Xu 已提交
3529
	return net_gso_ok(features, skb_shinfo(skb)->gso_type) &&
3530
	       (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST));
3531 3532
}

3533 3534
static inline bool netif_needs_gso(struct sk_buff *skb,
				   netdev_features_t features)
3535
{
3536
	return skb_is_gso(skb) && (!skb_gso_ok(skb, features) ||
3537 3538
		unlikely((skb->ip_summed != CHECKSUM_PARTIAL) &&
			 (skb->ip_summed != CHECKSUM_UNNECESSARY)));
3539 3540
}

3541 3542 3543 3544 3545 3546
static inline void netif_set_gso_max_size(struct net_device *dev,
					  unsigned int size)
{
	dev->gso_max_size = size;
}

3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559
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;
}

3560 3561 3562 3563 3564
static inline bool netif_is_macvlan(struct net_device *dev)
{
	return dev->priv_flags & IFF_MACVLAN;
}

3565 3566 3567 3568 3569
static inline bool netif_is_bond_master(struct net_device *dev)
{
	return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING;
}

3570
static inline bool netif_is_bond_slave(struct net_device *dev)
J
Jiri Pirko 已提交
3571 3572 3573 3574
{
	return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING;
}

3575 3576 3577 3578 3579
static inline bool netif_supports_nofcs(struct net_device *dev)
{
	return dev->priv_flags & IFF_SUPP_NOFCS;
}

3580
extern struct pernet_operations __net_initdata loopback_net_ops;
3581

3582 3583 3584 3585 3586 3587
/* Logging, debugging and troubleshooting/diagnostic helpers. */

/* netdev_printk helpers, similar to dev_printk */

static inline const char *netdev_name(const struct net_device *dev)
{
3588 3589
	if (!dev->name[0] || strchr(dev->name, '%'))
		return "(unnamed net_device)";
3590 3591 3592
	return dev->name;
}

3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607
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)";
}

3608
__printf(3, 4)
3609 3610
int netdev_printk(const char *level, const struct net_device *dev,
		  const char *format, ...);
3611
__printf(2, 3)
3612
int netdev_emerg(const struct net_device *dev, const char *format, ...);
3613
__printf(2, 3)
3614
int netdev_alert(const struct net_device *dev, const char *format, ...);
3615
__printf(2, 3)
3616
int netdev_crit(const struct net_device *dev, const char *format, ...);
3617
__printf(2, 3)
3618
int netdev_err(const struct net_device *dev, const char *format, ...);
3619
__printf(2, 3)
3620
int netdev_warn(const struct net_device *dev, const char *format, ...);
3621
__printf(2, 3)
3622
int netdev_notice(const struct net_device *dev, const char *format, ...);
3623
__printf(2, 3)
3624
int netdev_info(const struct net_device *dev, const char *format, ...);
3625

3626 3627 3628
#define MODULE_ALIAS_NETDEV(device) \
	MODULE_ALIAS("netdev-" device)

3629
#if defined(CONFIG_DYNAMIC_DEBUG)
3630 3631
#define netdev_dbg(__dev, format, args...)			\
do {								\
3632
	dynamic_netdev_dbg(__dev, format, ##args);		\
3633
} while (0)
3634 3635 3636
#elif defined(DEBUG)
#define netdev_dbg(__dev, format, args...)			\
	netdev_printk(KERN_DEBUG, __dev, format, ##args)
3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663
#else
#define netdev_dbg(__dev, format, args...)			\
({								\
	if (0)							\
		netdev_printk(KERN_DEBUG, __dev, format, ##args); \
	0;							\
})
#endif

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

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

/*
 * netdev_WARN() acts like dev_printk(), but with the key difference
 * of using a WARN/WARN_ON to get the message out, including the
 * file/line information and a backtrace.
 */
#define netdev_WARN(dev, format, args...)			\
3664 3665
	WARN(1, "netdevice: %s%s\n" format, netdev_name(dev),	\
	     netdev_reg_state(dev), ##args)
3666

3667 3668 3669 3670 3671 3672 3673 3674
/* 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)

3675 3676 3677 3678 3679 3680
#define netif_level(level, priv, type, dev, fmt, args...)	\
do {								\
	if (netif_msg_##type(priv))				\
		netdev_##level(dev, fmt, ##args);		\
} while (0)

3681
#define netif_emerg(priv, type, dev, fmt, args...)		\
3682
	netif_level(emerg, priv, type, dev, fmt, ##args)
3683
#define netif_alert(priv, type, dev, fmt, args...)		\
3684
	netif_level(alert, priv, type, dev, fmt, ##args)
3685
#define netif_crit(priv, type, dev, fmt, args...)		\
3686
	netif_level(crit, priv, type, dev, fmt, ##args)
3687
#define netif_err(priv, type, dev, fmt, args...)		\
3688
	netif_level(err, priv, type, dev, fmt, ##args)
3689
#define netif_warn(priv, type, dev, fmt, args...)		\
3690
	netif_level(warn, priv, type, dev, fmt, ##args)
3691
#define netif_notice(priv, type, dev, fmt, args...)		\
3692
	netif_level(notice, priv, type, dev, fmt, ##args)
3693
#define netif_info(priv, type, dev, fmt, args...)		\
3694
	netif_level(info, priv, type, dev, fmt, ##args)
3695

3696
#if defined(CONFIG_DYNAMIC_DEBUG)
3697 3698 3699
#define netif_dbg(priv, type, netdev, format, args...)		\
do {								\
	if (netif_msg_##type(priv))				\
3700
		dynamic_netdev_dbg(netdev, format, ##args);	\
3701
} while (0)
3702 3703 3704
#elif defined(DEBUG)
#define netif_dbg(priv, type, dev, format, args...)		\
	netif_printk(priv, type, KERN_DEBUG, dev, format, ##args)
3705 3706 3707 3708 3709 3710 3711 3712 3713 3714
#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)
3715
#define netif_vdbg	netif_dbg
3716 3717 3718 3719
#else
#define netif_vdbg(priv, type, dev, format, args...)		\
({								\
	if (0)							\
3720
		netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
3721 3722 3723
	0;							\
})
#endif
3724

3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754
/*
 *	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)

3755
#endif	/* _LINUX_NETDEVICE_H */