aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/platform/x86/hp-wmi.c
blob: 56086363becc21fba3dfcd1f8f31397881d5d76d (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
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
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
/*
 * HP WMI hotkeys
 *
 * Copyright (C) 2008 Red Hat <mjg@redhat.com>
 *
 * Portions based on wistron_btns.c:
 * Copyright (C) 2005 Miloslav Trmac <mitr@volny.cz>
 * Copyright (C) 2005 Bernhard Rosenkraenzer <bero@arklinux.org>
 * Copyright (C) 2005 Dmitry Torokhov <dtor@mail.ru>
 *
 *  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.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/types.h>
#include <linux/input.h>
#include <acpi/acpi_drivers.h>
#include <linux/platform_device.h>
#include <linux/acpi.h>
#include <linux/rfkill.h>
#include <linux/string.h>

MODULE_AUTHOR("Matthew Garrett <mjg59@srcf.ucam.org>");
MODULE_DESCRIPTION("HP laptop WMI hotkeys driver");
MODULE_LICENSE("GPL");

MODULE_ALIAS("wmi:95F24279-4D7B-4334-9387-ACCDC67EF61C");
MODULE_ALIAS("wmi:5FB7F034-2C63-45e9-BE91-3D44E2C707E4");

#define HPWMI_EVENT_GUID "95F24279-4D7B-4334-9387-ACCDC67EF61C"
#define HPWMI_BIOS_GUID "5FB7F034-2C63-45e9-BE91-3D44E2C707E4"

#define HPWMI_DISPLAY_QUERY 0x1
#define HPWMI_HDDTEMP_QUERY 0x2
#define HPWMI_ALS_QUERY 0x3
#define HPWMI_HARDWARE_QUERY 0x4
#define HPWMI_WIRELESS_QUERY 0x5
#define HPWMI_HOTKEY_QUERY 0xc

enum hp_wmi_radio {
	HPWMI_WIFI = 0,
	HPWMI_BLUETOOTH = 1,
	HPWMI_WWAN = 2,
};

static int __devinit hp_wmi_bios_setup(struct platform_device *device);
static int __exit hp_wmi_bios_remove(struct platform_device *device);
static int hp_wmi_resume_handler(struct device *device);

struct bios_args {
	u32 signature;
	u32 command;
	u32 commandtype;
	u32 datasize;
	u32 data;
};

struct bios_return {
	u32 sigpass;
	u32 return_code;
	u32 value;
};

struct key_entry {
	char type;		/* See KE_* below */
	u16 code;
	u16 keycode;
};

enum { KE_KEY, KE_END };

static struct key_entry hp_wmi_keymap[] = {
	{KE_KEY, 0x02, KEY_BRIGHTNESSUP},
	{KE_KEY, 0x03, KEY_BRIGHTNESSDOWN},
	{KE_KEY, 0x20e6, KEY_PROG1},
	{KE_KEY, 0x2142, KEY_MEDIA},
	{KE_KEY, 0x213b, KEY_INFO},
	{KE_KEY, 0x2169, KEY_DIRECTION},
	{KE_KEY, 0x231b, KEY_HELP},
	{KE_END, 0}
};

static struct input_dev *hp_wmi_input_dev;
static struct platform_device *hp_wmi_platform_dev;

static struct rfkill *wifi_rfkill;
static struct rfkill *bluetooth_rfkill;
static struct rfkill *wwan_rfkill;

static const struct dev_pm_ops hp_wmi_pm_ops = {
	.resume  = hp_wmi_resume_handler,
	.restore  = hp_wmi_resume_handler,
};

static struct platform_driver hp_wmi_driver = {
	.driver = {
		.name = "hp-wmi",
		.owner = THIS_MODULE,
		.pm = &hp_wmi_pm_ops,
	},
	.probe = hp_wmi_bios_setup,
	.remove = hp_wmi_bios_remove,
};

static int hp_wmi_perform_query(int query, int write, int value)
{
	struct bios_return bios_return;
	acpi_status status;
	union acpi_object *obj;
	struct bios_args args = {
		.signature = 0x55434553,
		.command = write ? 0x2 : 0x1,
		.commandtype = query,
		.datasize = write ? 0x4 : 0,
		.data = value,
	};
	struct acpi_buffer input = { sizeof(struct bios_args), &args };
	struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };

	status = wmi_evaluate_method(HPWMI_BIOS_GUID, 0, 0x3, &input, &output);

	obj = output.pointer;

	if (!obj)
		return -EINVAL;
	else if (obj->type != ACPI_TYPE_BUFFER) {
		kfree(obj);
		return -EINVAL;
	}

	bios_return = *((struct bios_return *)obj->buffer.pointer);
	kfree(obj);
	if (bios_return.return_code > 0)
		return bios_return.return_code * -1;
	else
		return bios_return.value;
}

static int hp_wmi_display_state(void)
{
	return hp_wmi_perform_query(HPWMI_DISPLAY_QUERY, 0, 0);
}

static int hp_wmi_hddtemp_state(void)
{
	return hp_wmi_perform_query(HPWMI_HDDTEMP_QUERY, 0, 0);
}

static int hp_wmi_als_state(void)
{
	return hp_wmi_perform_query(HPWMI_ALS_QUERY, 0, 0);
}

static int hp_wmi_dock_state(void)
{
	int ret = hp_wmi_perform_query(HPWMI_HARDWARE_QUERY, 0, 0);

	if (ret < 0)
		return ret;

	return ret & 0x1;
}

static int hp_wmi_tablet_state(void)
{
	int ret = hp_wmi_perform_query(HPWMI_HARDWARE_QUERY, 0, 0);

	if (ret < 0)
		return ret;

	return (ret & 0x4) ? 1 : 0;
}

static int hp_wmi_set_block(void *data, bool blocked)
{
	enum hp_wmi_radio r = (enum hp_wmi_radio) data;
	int query = BIT(r + 8) | ((!blocked) << r);

	return hp_wmi_perform_query(HPWMI_WIRELESS_QUERY, 1, query);
}

static const struct rfkill_ops hp_wmi_rfkill_ops = {
	.set_block = hp_wmi_set_block,
};

static bool hp_wmi_get_sw_state(enum hp_wmi_radio r)
{
	int wireless = hp_wmi_perform_query(HPWMI_WIRELESS_QUERY, 0, 0);
	int mask = 0x200 << (r * 8);

	if (wireless & mask)
		return false;
	else
		return true;
}

static bool hp_wmi_get_hw_state(enum hp_wmi_radio r)
{
	int wireless = hp_wmi_perform_query(HPWMI_WIRELESS_QUERY, 0, 0);
	int mask = 0x800 << (r * 8);

	if (wireless & mask)
		return false;
	else
		return true;
}

static ssize_t show_display(struct device *dev, struct device_attribute *attr,
			    char *buf)
{
	int value = hp_wmi_display_state();
	if (value < 0)
		return -EINVAL;
	return sprintf(buf, "%d\n", value);
}

static ssize_t show_hddtemp(struct device *dev, struct device_attribute *attr,
			    char *buf)
{
	int value = hp_wmi_hddtemp_state();
	if (value < 0)
		return -EINVAL;
	return sprintf(buf, "%d\n", value);
}

static ssize_t show_als(struct device *dev, struct device_attribute *attr,
			char *buf)
{
	int value = hp_wmi_als_state();
	if (value < 0)
		return -EINVAL;
	return sprintf(buf, "%d\n", value);
}

static ssize_t show_dock(struct device *dev, struct device_attribute *attr,
			 char *buf)
{
	int value = hp_wmi_dock_state();
	if (value < 0)
		return -EINVAL;
	return sprintf(buf, "%d\n", value);
}

static ssize_t show_tablet(struct device *dev, struct device_attribute *attr,
			 char *buf)
{
	int value = hp_wmi_tablet_state();
	if (value < 0)
		return -EINVAL;
	return sprintf(buf, "%d\n", value);
}

static ssize_t set_als(struct device *dev, struct device_attribute *attr,
		       const char *buf, size_t count)
{
	u32 tmp = simple_strtoul(buf, NULL, 10);
	hp_wmi_perform_query(HPWMI_ALS_QUERY, 1, tmp);
	return count;
}

static DEVICE_ATTR(display, S_IRUGO, show_display, NULL);
static DEVICE_ATTR(hddtemp, S_IRUGO, show_hddtemp, NULL);
static DEVICE_ATTR(als, S_IRUGO | S_IWUSR, show_als, set_als);
static DEVICE_ATTR(dock, S_IRUGO, show_dock, NULL);
static DEVICE_ATTR(tablet, S_IRUGO, show_tablet, NULL);

static struct key_entry *hp_wmi_get_entry_by_scancode(unsigned int code)
{
	struct key_entry *key;

	for (key = hp_wmi_keymap; key->type != KE_END; key++)
		if (code == key->code)
			return key;

	return NULL;
}

static struct key_entry *hp_wmi_get_entry_by_keycode(unsigned int keycode)
{
	struct key_entry *key;

	for (key = hp_wmi_keymap; key->type != KE_END; key++)
		if (key->type == KE_KEY && keycode == key->keycode)
			return key;

	return NULL;
}

static int hp_wmi_getkeycode(struct input_dev *dev,
			     unsigned int scancode, unsigned int *keycode)
{
	struct key_entry *key = hp_wmi_get_entry_by_scancode(scancode);

	if (key && key->type == KE_KEY) {
		*keycode = key->keycode;
		return 0;
	}

	return -EINVAL;
}

static int hp_wmi_setkeycode(struct input_dev *dev,
			     unsigned int scancode, unsigned int keycode)
{
	struct key_entry *key;
	unsigned int old_keycode;

	key = hp_wmi_get_entry_by_scancode(scancode);
	if (key && key->type == KE_KEY) {
		old_keycode = key->keycode;
		key->keycode = keycode;
		set_bit(keycode, dev->keybit);
		if (!hp_wmi_get_entry_by_keycode(old_keycode))
			clear_bit(old_keycode, dev->keybit);
		return 0;
	}

	return -EINVAL;
}

static void hp_wmi_notify(u32 value, void *context)
{
	struct acpi_buffer response = { ACPI_ALLOCATE_BUFFER, NULL };
	static struct key_entry *key;
	union acpi_object *obj;
	int eventcode;
	acpi_status status;

	status = wmi_get_event_data(value, &response);
	if (status != AE_OK) {
		printk(KERN_INFO "hp-wmi: bad event status 0x%x\n", status);
		return;
	}

	obj = (union acpi_object *)response.pointer;

	if (!obj || obj->type != ACPI_TYPE_BUFFER || obj->buffer.length != 8) {
		printk(KERN_INFO "HP WMI: Unknown response received\n");
		kfree(obj);
		return;
	}

	eventcode = *((u8 *) obj->buffer.pointer);
	kfree(obj);
	if (eventcode == 0x4)
		eventcode = hp_wmi_perform_query(HPWMI_HOTKEY_QUERY, 0,
						0);
	key = hp_wmi_get_entry_by_scancode(eventcode);
	if (key) {
		switch (key->type) {
		case KE_KEY:
			input_report_key(hp_wmi_input_dev,
					 key->keycode, 1);
			input_sync(hp_wmi_input_dev);
			input_report_key(hp_wmi_input_dev,
					 key->keycode, 0);
			input_sync(hp_wmi_input_dev);
			break;
		}
	} else if (eventcode == 0x1) {
		input_report_switch(hp_wmi_input_dev, SW_DOCK,
				    hp_wmi_dock_state());
		input_report_switch(hp_wmi_input_dev, SW_TABLET_MODE,
				    hp_wmi_tablet_state());
		input_sync(hp_wmi_input_dev);
	} else if (eventcode == 0x5) {
		if (wifi_rfkill)
			rfkill_set_states(wifi_rfkill,
					  hp_wmi_get_sw_state(HPWMI_WIFI),
					  hp_wmi_get_hw_state(HPWMI_WIFI));
		if (bluetooth_rfkill)
			rfkill_set_states(bluetooth_rfkill,
					  hp_wmi_get_sw_state(HPWMI_BLUETOOTH),
					  hp_wmi_get_hw_state(HPWMI_BLUETOOTH));
		if (wwan_rfkill)
			rfkill_set_states(wwan_rfkill,
					  hp_wmi_get_sw_state(HPWMI_WWAN),
					  hp_wmi_get_hw_state(HPWMI_WWAN));
	} else
		printk(KERN_INFO "HP WMI: Unknown key pressed - %x\n",
			eventcode);
}

static int __init hp_wmi_input_setup(void)
{
	struct key_entry *key;
	int err;

	hp_wmi_input_dev = input_allocate_device();

	hp_wmi_input_dev->name = "HP WMI hotkeys";
	hp_wmi_input_dev->phys = "wmi/input0";
	hp_wmi_input_dev->id.bustype = BUS_HOST;
	hp_wmi_input_dev->getkeycode = hp_wmi_getkeycode;
	hp_wmi_input_dev->setkeycode = hp_wmi_setkeycode;

	for (key = hp_wmi_keymap; key->type != KE_END; key++) {
		switch (key->type) {
		case KE_KEY:
			set_bit(EV_KEY, hp_wmi_input_dev->evbit);
			set_bit(key->keycode, hp_wmi_input_dev->keybit);
			break;
		}
	}

	set_bit(EV_SW, hp_wmi_input_dev->evbit);
	set_bit(SW_DOCK, hp_wmi_input_dev->swbit);
	set_bit(SW_TABLET_MODE, hp_wmi_input_dev->swbit);

	/* Set initial hardware state */
	input_report_switch(hp_wmi_input_dev, SW_DOCK, hp_wmi_dock_state());
	input_report_switch(hp_wmi_input_dev, SW_TABLET_MODE,
			    hp_wmi_tablet_state());
	input_sync(hp_wmi_input_dev);

	err = input_register_device(hp_wmi_input_dev);

	if (err) {
		input_free_device(hp_wmi_input_dev);
		return err;
	}

	return 0;
}

static void cleanup_sysfs(struct platform_device *device)
{
	device_remove_file(&device->dev, &dev_attr_display);
	device_remove_file(&device->dev, &dev_attr_hddtemp);
	device_remove_file(&device->dev, &dev_attr_als);
	device_remove_file(&device->dev, &dev_attr_dock);
	device_remove_file(&device->dev, &dev_attr_tablet);
}

static int __devinit hp_wmi_bios_setup(struct platform_device *device)
{
	int err;
	int wireless = hp_wmi_perform_query(HPWMI_WIRELESS_QUERY, 0, 0);

	err = device_create_file(&device->dev, &dev_attr_display);
	if (err)
		goto add_sysfs_error;
	err = device_create_file(&device->dev, &dev_attr_hddtemp);
	if (err)
		goto add_sysfs_error;
	err = device_create_file(&device->dev, &dev_attr_als);
	if (err)
		goto add_sysfs_error;
	err = device_create_file(&device->dev, &dev_attr_dock);
	if (err)
		goto add_sysfs_error;
	err = device_create_file(&device->dev, &dev_attr_tablet);
	if (err)
		goto add_sysfs_error;

	if (wireless & 0x1) {
		wifi_rfkill = rfkill_alloc("hp-wifi", &device->dev,
					   RFKILL_TYPE_WLAN,
					   &hp_wmi_rfkill_ops,
					   (void *) HPWMI_WIFI);
		rfkill_init_sw_state(wifi_rfkill,
				     hp_wmi_get_sw_state(HPWMI_WIFI));
		rfkill_set_hw_state(wifi_rfkill,
				    hp_wmi_get_hw_state(HPWMI_WIFI));
		err = rfkill_register(wifi_rfkill);
		if (err)
			goto register_wifi_error;
	}

	if (wireless & 0x2) {
		bluetooth_rfkill = rfkill_alloc("hp-bluetooth", &device->dev,
						RFKILL_TYPE_BLUETOOTH,
						&hp_wmi_rfkill_ops,
						(void *) HPWMI_BLUETOOTH);
		rfkill_init_sw_state(bluetooth_rfkill,
				     hp_wmi_get_sw_state(HPWMI_BLUETOOTH));
		rfkill_set_hw_state(bluetooth_rfkill,
				    hp_wmi_get_hw_state(HPWMI_BLUETOOTH));
		err = rfkill_register(bluetooth_rfkill);
		if (err)
			goto register_bluetooth_error;
	}

	if (wireless & 0x4) {
		wwan_rfkill = rfkill_alloc("hp-wwan", &device->dev,
					   RFKILL_TYPE_WWAN,
					   &hp_wmi_rfkill_ops,
					   (void *) HPWMI_WWAN);
		rfkill_init_sw_state(wwan_rfkill,
				     hp_wmi_get_sw_state(HPWMI_WWAN));
		rfkill_set_hw_state(wwan_rfkill,
				    hp_wmi_get_hw_state(HPWMI_WWAN));
		err = rfkill_register(wwan_rfkill);
		if (err)
			goto register_wwan_err;
	}

	return 0;
register_wwan_err:
	rfkill_destroy(wwan_rfkill);
	if (bluetooth_rfkill)
		rfkill_unregister(bluetooth_rfkill);
register_bluetooth_error:
	rfkill_destroy(bluetooth_rfkill);
	if (wifi_rfkill)
		rfkill_unregister(wifi_rfkill);
register_wifi_error:
	rfkill_destroy(wifi_rfkill);
add_sysfs_error:
	cleanup_sysfs(device);
	return err;
}

static int __exit hp_wmi_bios_remove(struct platform_device *device)
{
	cleanup_sysfs(device);

	if (wifi_rfkill) {
		rfkill_unregister(wifi_rfkill);
		rfkill_destroy(wifi_rfkill);
	}
	if (bluetooth_rfkill) {
		rfkill_unregister(bluetooth_rfkill);
		rfkill_destroy(bluetooth_rfkill);
	}
	if (wwan_rfkill) {
		rfkill_unregister(wwan_rfkill);
		rfkill_destroy(wwan_rfkill);
	}

	return 0;
}

static int hp_wmi_resume_handler(struct device *device)
{
	/*
	 * Hardware state may have changed while suspended, so trigger
	 * input events for the current state. As this is a switch,
	 * the input layer will only actually pass it on if the state
	 * changed.
	 */
	if (hp_wmi_input_dev) {
		input_report_switch(hp_wmi_input_dev, SW_DOCK,
				    hp_wmi_dock_state());
		input_report_switch(hp_wmi_input_dev, SW_TABLET_MODE,
				    hp_wmi_tablet_state());
		input_sync(hp_wmi_input_dev);
	}

	if (wifi_rfkill)
		rfkill_set_states(wifi_rfkill,
				  hp_wmi_get_sw_state(HPWMI_WIFI),
				  hp_wmi_get_hw_state(HPWMI_WIFI));
	if (bluetooth_rfkill)
		rfkill_set_states(bluetooth_rfkill,
				  hp_wmi_get_sw_state(HPWMI_BLUETOOTH),
				  hp_wmi_get_hw_state(HPWMI_BLUETOOTH));
	if (wwan_rfkill)
		rfkill_set_states(wwan_rfkill,
				  hp_wmi_get_sw_state(HPWMI_WWAN),
				  hp_wmi_get_hw_state(HPWMI_WWAN));

	return 0;
}

static int __init hp_wmi_init(void)
{
	int err;

	if (wmi_has_guid(HPWMI_EVENT_GUID)) {
		err = wmi_install_notify_handler(HPWMI_EVENT_GUID,
						 hp_wmi_notify, NULL);
		if (ACPI_SUCCESS(err))
			hp_wmi_input_setup();
	}

	if (wmi_has_guid(HPWMI_BIOS_GUID)) {
		err = platform_driver_register(&hp_wmi_driver);
		if (err)
			return 0;
		hp_wmi_platform_dev = platform_device_alloc("hp-wmi", -1);
		if (!hp_wmi_platform_dev) {
			platform_driver_unregister(&hp_wmi_driver);
			return 0;
		}
		platform_device_add(hp_wmi_platform_dev);
	}

	return 0;
}

static void __exit hp_wmi_exit(void)
{
	if (wmi_has_guid(HPWMI_EVENT_GUID)) {
		wmi_remove_notify_handler(HPWMI_EVENT_GUID);
		input_unregister_device(hp_wmi_input_dev);
	}
	if (hp_wmi_platform_dev) {
		platform_device_del(hp_wmi_platform_dev);
		platform_driver_unregister(&hp_wmi_driver);
	}
}

module_init(hp_wmi_init);
module_exit(hp_wmi_exit);
id='n2392' href='#n2392'>2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 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 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 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 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 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 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 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 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 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 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545
/*
 * originally based on the dummy device.
 *
 * Copyright 1999, Thomas Davis, tadavis@lbl.gov.
 * Licensed under the GPL. Based on dummy.c, and eql.c devices.
 *
 * bonding.c: an Ethernet Bonding driver
 *
 * This is useful to talk to a Cisco EtherChannel compatible equipment:
 *	Cisco 5500
 *	Sun Trunking (Solaris)
 *	Alteon AceDirector Trunks
 *	Linux Bonding
 *	and probably many L2 switches ...
 *
 * How it works:
 *    ifconfig bond0 ipaddress netmask up
 *      will setup a network device, with an ip address.  No mac address
 *	will be assigned at this time.  The hw mac address will come from
 *	the first slave bonded to the channel.  All slaves will then use
 *	this hw mac address.
 *
 *    ifconfig bond0 down
 *         will release all slaves, marking them as down.
 *
 *    ifenslave bond0 eth0
 *	will attach eth0 to bond0 as a slave.  eth0 hw mac address will either
 *	a: be used as initial mac address
 *	b: if a hw mac address already is there, eth0's hw mac address
 *	   will then be set from bond0.
 *
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/interrupt.h>
#include <linux/ptrace.h>
#include <linux/ioport.h>
#include <linux/in.h>
#include <net/ip.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/timer.h>
#include <linux/socket.h>
#include <linux/ctype.h>
#include <linux/inet.h>
#include <linux/bitops.h>
#include <linux/io.h>
#include <asm/dma.h>
#include <linux/uaccess.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <linux/rtnetlink.h>
#include <linux/smp.h>
#include <linux/if_ether.h>
#include <net/arp.h>
#include <linux/mii.h>
#include <linux/ethtool.h>
#include <linux/if_vlan.h>
#include <linux/if_bonding.h>
#include <linux/jiffies.h>
#include <linux/preempt.h>
#include <net/route.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/pkt_sched.h>
#include <linux/rculist.h>
#include <net/flow_keys.h>
#include "bonding.h"
#include "bond_3ad.h"
#include "bond_alb.h"

/*---------------------------- Module parameters ----------------------------*/

/* monitor all links that often (in milliseconds). <=0 disables monitoring */

static int max_bonds	= BOND_DEFAULT_MAX_BONDS;
static int tx_queues	= BOND_DEFAULT_TX_QUEUES;
static int num_peer_notif = 1;
static int miimon;
static int updelay;
static int downdelay;
static int use_carrier	= 1;
static char *mode;
static char *primary;
static char *primary_reselect;
static char *lacp_rate;
static int min_links;
static char *ad_select;
static char *xmit_hash_policy;
static int arp_interval;
static char *arp_ip_target[BOND_MAX_ARP_TARGETS];
static char *arp_validate;
static char *arp_all_targets;
static char *fail_over_mac;
static int all_slaves_active;
static struct bond_params bonding_defaults;
static int resend_igmp = BOND_DEFAULT_RESEND_IGMP;
static int packets_per_slave = 1;
static int lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL;

module_param(max_bonds, int, 0);
MODULE_PARM_DESC(max_bonds, "Max number of bonded devices");
module_param(tx_queues, int, 0);
MODULE_PARM_DESC(tx_queues, "Max number of transmit queues (default = 16)");
module_param_named(num_grat_arp, num_peer_notif, int, 0644);
MODULE_PARM_DESC(num_grat_arp, "Number of peer notifications to send on "
			       "failover event (alias of num_unsol_na)");
module_param_named(num_unsol_na, num_peer_notif, int, 0644);
MODULE_PARM_DESC(num_unsol_na, "Number of peer notifications to send on "
			       "failover event (alias of num_grat_arp)");
module_param(miimon, int, 0);
MODULE_PARM_DESC(miimon, "Link check interval in milliseconds");
module_param(updelay, int, 0);
MODULE_PARM_DESC(updelay, "Delay before considering link up, in milliseconds");
module_param(downdelay, int, 0);
MODULE_PARM_DESC(downdelay, "Delay before considering link down, "
			    "in milliseconds");
module_param(use_carrier, int, 0);
MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; "
			      "0 for off, 1 for on (default)");
module_param(mode, charp, 0);
MODULE_PARM_DESC(mode, "Mode of operation; 0 for balance-rr, "
		       "1 for active-backup, 2 for balance-xor, "
		       "3 for broadcast, 4 for 802.3ad, 5 for balance-tlb, "
		       "6 for balance-alb");
module_param(primary, charp, 0);
MODULE_PARM_DESC(primary, "Primary network device to use");
module_param(primary_reselect, charp, 0);
MODULE_PARM_DESC(primary_reselect, "Reselect primary slave "
				   "once it comes up; "
				   "0 for always (default), "
				   "1 for only if speed of primary is "
				   "better, "
				   "2 for only on active slave "
				   "failure");
module_param(lacp_rate, charp, 0);
MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner; "
			    "0 for slow, 1 for fast");
module_param(ad_select, charp, 0);
MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic; "
			    "0 for stable (default), 1 for bandwidth, "
			    "2 for count");
module_param(min_links, int, 0);
MODULE_PARM_DESC(min_links, "Minimum number of available links before turning on carrier");

module_param(xmit_hash_policy, charp, 0);
MODULE_PARM_DESC(xmit_hash_policy, "balance-xor and 802.3ad hashing method; "
				   "0 for layer 2 (default), 1 for layer 3+4, "
				   "2 for layer 2+3, 3 for encap layer 2+3, "
				   "4 for encap layer 3+4");
module_param(arp_interval, int, 0);
MODULE_PARM_DESC(arp_interval, "arp interval in milliseconds");
module_param_array(arp_ip_target, charp, NULL, 0);
MODULE_PARM_DESC(arp_ip_target, "arp targets in n.n.n.n form");
module_param(arp_validate, charp, 0);
MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes; "
			       "0 for none (default), 1 for active, "
			       "2 for backup, 3 for all");
module_param(arp_all_targets, charp, 0);
MODULE_PARM_DESC(arp_all_targets, "fail on any/all arp targets timeout; 0 for any (default), 1 for all");
module_param(fail_over_mac, charp, 0);
MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to "
				"the same MAC; 0 for none (default), "
				"1 for active, 2 for follow");
module_param(all_slaves_active, int, 0);
MODULE_PARM_DESC(all_slaves_active, "Keep all frames received on an interface"
				     "by setting active flag for all slaves; "
				     "0 for never (default), 1 for always.");
module_param(resend_igmp, int, 0);
MODULE_PARM_DESC(resend_igmp, "Number of IGMP membership reports to send on "
			      "link failure");
module_param(packets_per_slave, int, 0);
MODULE_PARM_DESC(packets_per_slave, "Packets to send per slave in balance-rr "
				    "mode; 0 for a random slave, 1 packet per "
				    "slave (default), >1 packets per slave.");
module_param(lp_interval, uint, 0);
MODULE_PARM_DESC(lp_interval, "The number of seconds between instances where "
			      "the bonding driver sends learning packets to "
			      "each slaves peer switch. The default is 1.");

/*----------------------------- Global variables ----------------------------*/

#ifdef CONFIG_NET_POLL_CONTROLLER
atomic_t netpoll_block_tx = ATOMIC_INIT(0);
#endif

int bond_net_id __read_mostly;

static __be32 arp_target[BOND_MAX_ARP_TARGETS];
static int arp_ip_count;
static int bond_mode	= BOND_MODE_ROUNDROBIN;
static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
static int lacp_fast;

/*-------------------------- Forward declarations ---------------------------*/

static int bond_init(struct net_device *bond_dev);
static void bond_uninit(struct net_device *bond_dev);

/*---------------------------- General routines -----------------------------*/

const char *bond_mode_name(int mode)
{
	static const char *names[] = {
		[BOND_MODE_ROUNDROBIN] = "load balancing (round-robin)",
		[BOND_MODE_ACTIVEBACKUP] = "fault-tolerance (active-backup)",
		[BOND_MODE_XOR] = "load balancing (xor)",
		[BOND_MODE_BROADCAST] = "fault-tolerance (broadcast)",
		[BOND_MODE_8023AD] = "IEEE 802.3ad Dynamic link aggregation",
		[BOND_MODE_TLB] = "transmit load balancing",
		[BOND_MODE_ALB] = "adaptive load balancing",
	};

	if (mode < BOND_MODE_ROUNDROBIN || mode > BOND_MODE_ALB)
		return "unknown";

	return names[mode];
}

/*---------------------------------- VLAN -----------------------------------*/

/**
 * bond_dev_queue_xmit - Prepare skb for xmit.
 *
 * @bond: bond device that got this skb for tx.
 * @skb: hw accel VLAN tagged skb to transmit
 * @slave_dev: slave that is supposed to xmit this skbuff
 */
void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
			struct net_device *slave_dev)
{
	skb->dev = slave_dev;

	BUILD_BUG_ON(sizeof(skb->queue_mapping) !=
		     sizeof(qdisc_skb_cb(skb)->slave_dev_queue_mapping));
	skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping;

	if (unlikely(netpoll_tx_running(bond->dev)))
		bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb);
	else
		dev_queue_xmit(skb);
}

/*
 * In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid,
 * We don't protect the slave list iteration with a lock because:
 * a. This operation is performed in IOCTL context,
 * b. The operation is protected by the RTNL semaphore in the 8021q code,
 * c. Holding a lock with BH disabled while directly calling a base driver
 *    entry point is generally a BAD idea.
 *
 * The design of synchronization/protection for this operation in the 8021q
 * module is good for one or more VLAN devices over a single physical device
 * and cannot be extended for a teaming solution like bonding, so there is a
 * potential race condition here where a net device from the vlan group might
 * be referenced (either by a base driver or the 8021q code) while it is being
 * removed from the system. However, it turns out we're not making matters
 * worse, and if it works for regular VLAN usage it will work here too.
*/

/**
 * bond_vlan_rx_add_vid - Propagates adding an id to slaves
 * @bond_dev: bonding net device that got called
 * @vid: vlan id being added
 */
static int bond_vlan_rx_add_vid(struct net_device *bond_dev,
				__be16 proto, u16 vid)
{
	struct bonding *bond = netdev_priv(bond_dev);
	struct slave *slave, *rollback_slave;
	struct list_head *iter;
	int res;

	bond_for_each_slave(bond, slave, iter) {
		res = vlan_vid_add(slave->dev, proto, vid);
		if (res)
			goto unwind;
	}

	return 0;

unwind:
	/* unwind to the slave that failed */
	bond_for_each_slave(bond, rollback_slave, iter) {
		if (rollback_slave == slave)
			break;

		vlan_vid_del(rollback_slave->dev, proto, vid);
	}

	return res;
}

/**
 * bond_vlan_rx_kill_vid - Propagates deleting an id to slaves
 * @bond_dev: bonding net device that got called
 * @vid: vlan id being removed
 */
static int bond_vlan_rx_kill_vid(struct net_device *bond_dev,
				 __be16 proto, u16 vid)
{
	struct bonding *bond = netdev_priv(bond_dev);
	struct list_head *iter;
	struct slave *slave;

	bond_for_each_slave(bond, slave, iter)
		vlan_vid_del(slave->dev, proto, vid);

	if (bond_is_lb(bond))
		bond_alb_clear_vlan(bond, vid);

	return 0;
}

/*------------------------------- Link status -------------------------------*/

/*
 * Set the carrier state for the master according to the state of its
 * slaves.  If any slaves are up, the master is up.  In 802.3ad mode,
 * do special 802.3ad magic.
 *
 * Returns zero if carrier state does not change, nonzero if it does.
 */
static int bond_set_carrier(struct bonding *bond)
{
	struct list_head *iter;
	struct slave *slave;

	if (!bond_has_slaves(bond))
		goto down;

	if (bond->params.mode == BOND_MODE_8023AD)
		return bond_3ad_set_carrier(bond);

	bond_for_each_slave(bond, slave, iter) {
		if (slave->link == BOND_LINK_UP) {
			if (!netif_carrier_ok(bond->dev)) {
				netif_carrier_on(bond->dev);
				return 1;
			}
			return 0;
		}
	}

down:
	if (netif_carrier_ok(bond->dev)) {
		netif_carrier_off(bond->dev);
		return 1;
	}
	return 0;
}

/*
 * Get link speed and duplex from the slave's base driver
 * using ethtool. If for some reason the call fails or the
 * values are invalid, set speed and duplex to -1,
 * and return.
 */
static void bond_update_speed_duplex(struct slave *slave)
{
	struct net_device *slave_dev = slave->dev;
	struct ethtool_cmd ecmd;
	u32 slave_speed;
	int res;

	slave->speed = SPEED_UNKNOWN;
	slave->duplex = DUPLEX_UNKNOWN;

	res = __ethtool_get_settings(slave_dev, &ecmd);
	if (res < 0)
		return;

	slave_speed = ethtool_cmd_speed(&ecmd);
	if (slave_speed == 0 || slave_speed == ((__u32) -1))
		return;

	switch (ecmd.duplex) {
	case DUPLEX_FULL:
	case DUPLEX_HALF:
		break;
	default:
		return;
	}

	slave->speed = slave_speed;
	slave->duplex = ecmd.duplex;

	return;
}

const char *bond_slave_link_status(s8 link)
{
	switch (link) {
	case BOND_LINK_UP:
		return "up";
	case BOND_LINK_FAIL:
		return "going down";
	case BOND_LINK_DOWN:
		return "down";
	case BOND_LINK_BACK:
		return "going back";
	default:
		return "unknown";
	}
}

/*
 * if <dev> supports MII link status reporting, check its link status.
 *
 * We either do MII/ETHTOOL ioctls, or check netif_carrier_ok(),
 * depending upon the setting of the use_carrier parameter.
 *
 * Return either BMSR_LSTATUS, meaning that the link is up (or we
 * can't tell and just pretend it is), or 0, meaning that the link is
 * down.
 *
 * If reporting is non-zero, instead of faking link up, return -1 if
 * both ETHTOOL and MII ioctls fail (meaning the device does not
 * support them).  If use_carrier is set, return whatever it says.
 * It'd be nice if there was a good way to tell if a driver supports
 * netif_carrier, but there really isn't.
 */
static int bond_check_dev_link(struct bonding *bond,
			       struct net_device *slave_dev, int reporting)
{
	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
	int (*ioctl)(struct net_device *, struct ifreq *, int);
	struct ifreq ifr;
	struct mii_ioctl_data *mii;

	if (!reporting && !netif_running(slave_dev))
		return 0;

	if (bond->params.use_carrier)
		return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0;

	/* Try to get link status using Ethtool first. */
	if (slave_dev->ethtool_ops->get_link)
		return slave_dev->ethtool_ops->get_link(slave_dev) ?
			BMSR_LSTATUS : 0;

	/* Ethtool can't be used, fallback to MII ioctls. */
	ioctl = slave_ops->ndo_do_ioctl;
	if (ioctl) {
		/* TODO: set pointer to correct ioctl on a per team member */
		/*       bases to make this more efficient. that is, once  */
		/*       we determine the correct ioctl, we will always    */
		/*       call it and not the others for that team          */
		/*       member.                                           */

		/*
		 * We cannot assume that SIOCGMIIPHY will also read a
		 * register; not all network drivers (e.g., e100)
		 * support that.
		 */

		/* Yes, the mii is overlaid on the ifreq.ifr_ifru */
		strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ);
		mii = if_mii(&ifr);
		if (IOCTL(slave_dev, &ifr, SIOCGMIIPHY) == 0) {
			mii->reg_num = MII_BMSR;
			if (IOCTL(slave_dev, &ifr, SIOCGMIIREG) == 0)
				return mii->val_out & BMSR_LSTATUS;
		}
	}

	/*
	 * If reporting, report that either there's no dev->do_ioctl,
	 * or both SIOCGMIIREG and get_link failed (meaning that we
	 * cannot report link status).  If not reporting, pretend
	 * we're ok.
	 */
	return reporting ? -1 : BMSR_LSTATUS;
}

/*----------------------------- Multicast list ------------------------------*/

/*
 * Push the promiscuity flag down to appropriate slaves
 */
static int bond_set_promiscuity(struct bonding *bond, int inc)
{
	struct list_head *iter;
	int err = 0;

	if (USES_PRIMARY(bond->params.mode)) {
		/* write lock already acquired */
		if (bond->curr_active_slave) {
			err = dev_set_promiscuity(bond->curr_active_slave->dev,
						  inc);
		}
	} else {
		struct slave *slave;

		bond_for_each_slave(bond, slave, iter) {
			err = dev_set_promiscuity(slave->dev, inc);
			if (err)
				return err;
		}
	}
	return err;
}

/*
 * Push the allmulti flag down to all slaves
 */
static int bond_set_allmulti(struct bonding *bond, int inc)
{
	struct list_head *iter;
	int err = 0;

	if (USES_PRIMARY(bond->params.mode)) {
		/* write lock already acquired */
		if (bond->curr_active_slave) {
			err = dev_set_allmulti(bond->curr_active_slave->dev,
					       inc);
		}
	} else {
		struct slave *slave;

		bond_for_each_slave(bond, slave, iter) {
			err = dev_set_allmulti(slave->dev, inc);
			if (err)
				return err;
		}
	}
	return err;
}

/*
 * Retrieve the list of registered multicast addresses for the bonding
 * device and retransmit an IGMP JOIN request to the current active
 * slave.
 */
static void bond_resend_igmp_join_requests_delayed(struct work_struct *work)
{
	struct bonding *bond = container_of(work, struct bonding,
					    mcast_work.work);

	if (!rtnl_trylock()) {
		queue_delayed_work(bond->wq, &bond->mcast_work, 1);
		return;
	}
	call_netdevice_notifiers(NETDEV_RESEND_IGMP, bond->dev);

	if (bond->igmp_retrans > 1) {
		bond->igmp_retrans--;
		queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5);
	}
	rtnl_unlock();
}

/* Flush bond's hardware addresses from slave
 */
static void bond_hw_addr_flush(struct net_device *bond_dev,
			       struct net_device *slave_dev)
{
	struct bonding *bond = netdev_priv(bond_dev);

	dev_uc_unsync(slave_dev, bond_dev);
	dev_mc_unsync(slave_dev, bond_dev);

	if (bond->params.mode == BOND_MODE_8023AD) {
		/* del lacpdu mc addr from mc list */
		u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;

		dev_mc_del(slave_dev, lacpdu_multicast);
	}
}

/*--------------------------- Active slave change ---------------------------*/

/* Update the hardware address list and promisc/allmulti for the new and
 * old active slaves (if any).  Modes that are !USES_PRIMARY keep all
 * slaves up date at all times; only the USES_PRIMARY modes need to call
 * this function to swap these settings during a failover.
 */
static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
			      struct slave *old_active)
{
	ASSERT_RTNL();

	if (old_active) {
		if (bond->dev->flags & IFF_PROMISC)
			dev_set_promiscuity(old_active->dev, -1);

		if (bond->dev->flags & IFF_ALLMULTI)
			dev_set_allmulti(old_active->dev, -1);

		bond_hw_addr_flush(bond->dev, old_active->dev);
	}

	if (new_active) {
		/* FIXME: Signal errors upstream. */
		if (bond->dev->flags & IFF_PROMISC)
			dev_set_promiscuity(new_active->dev, 1);

		if (bond->dev->flags & IFF_ALLMULTI)
			dev_set_allmulti(new_active->dev, 1);

		netif_addr_lock_bh(bond->dev);
		dev_uc_sync(new_active->dev, bond->dev);
		dev_mc_sync(new_active->dev, bond->dev);
		netif_addr_unlock_bh(bond->dev);
	}
}

/**
 * bond_set_dev_addr - clone slave's address to bond
 * @bond_dev: bond net device
 * @slave_dev: slave net device
 *
 * Should be called with RTNL held.
 */
static void bond_set_dev_addr(struct net_device *bond_dev,
			      struct net_device *slave_dev)
{
	pr_debug("bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n",
		 bond_dev, slave_dev, slave_dev->addr_len);
	memcpy(bond_dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len);
	bond_dev->addr_assign_type = NET_ADDR_STOLEN;
	call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev);
}

/*
 * bond_do_fail_over_mac
 *
 * Perform special MAC address swapping for fail_over_mac settings
 *
 * Called with RTNL, curr_slave_lock for write_bh.
 */
static void bond_do_fail_over_mac(struct bonding *bond,
				  struct slave *new_active,
				  struct slave *old_active)
	__releases(&bond->curr_slave_lock)
	__acquires(&bond->curr_slave_lock)
{
	u8 tmp_mac[ETH_ALEN];
	struct sockaddr saddr;
	int rv;

	switch (bond->params.fail_over_mac) {
	case BOND_FOM_ACTIVE:
		if (new_active) {
			write_unlock_bh(&bond->curr_slave_lock);
			bond_set_dev_addr(bond->dev, new_active->dev);
			write_lock_bh(&bond->curr_slave_lock);
		}
		break;
	case BOND_FOM_FOLLOW:
		/*
		 * if new_active && old_active, swap them
		 * if just old_active, do nothing (going to no active slave)
		 * if just new_active, set new_active to bond's MAC
		 */
		if (!new_active)
			return;

		write_unlock_bh(&bond->curr_slave_lock);

		if (old_active) {
			memcpy(tmp_mac, new_active->dev->dev_addr, ETH_ALEN);
			memcpy(saddr.sa_data, old_active->dev->dev_addr,
			       ETH_ALEN);
			saddr.sa_family = new_active->dev->type;
		} else {
			memcpy(saddr.sa_data, bond->dev->dev_addr, ETH_ALEN);
			saddr.sa_family = bond->dev->type;
		}

		rv = dev_set_mac_address(new_active->dev, &saddr);
		if (rv) {
			pr_err("%s: Error %d setting MAC of slave %s\n",
			       bond->dev->name, -rv, new_active->dev->name);
			goto out;
		}

		if (!old_active)
			goto out;

		memcpy(saddr.sa_data, tmp_mac, ETH_ALEN);
		saddr.sa_family = old_active->dev->type;

		rv = dev_set_mac_address(old_active->dev, &saddr);
		if (rv)
			pr_err("%s: Error %d setting MAC of slave %s\n",
			       bond->dev->name, -rv, new_active->dev->name);
out:
		write_lock_bh(&bond->curr_slave_lock);
		break;
	default:
		pr_err("%s: bond_do_fail_over_mac impossible: bad policy %d\n",
		       bond->dev->name, bond->params.fail_over_mac);
		break;
	}

}

static bool bond_should_change_active(struct bonding *bond)
{
	struct slave *prim = bond->primary_slave;
	struct slave *curr = bond->curr_active_slave;

	if (!prim || !curr || curr->link != BOND_LINK_UP)
		return true;
	if (bond->force_primary) {
		bond->force_primary = false;
		return true;
	}
	if (bond->params.primary_reselect == BOND_PRI_RESELECT_BETTER &&
	    (prim->speed < curr->speed ||
	     (prim->speed == curr->speed && prim->duplex <= curr->duplex)))
		return false;
	if (bond->params.primary_reselect == BOND_PRI_RESELECT_FAILURE)
		return false;
	return true;
}

/**
 * find_best_interface - select the best available slave to be the active one
 * @bond: our bonding struct
 */
static struct slave *bond_find_best_slave(struct bonding *bond)
{
	struct slave *slave, *bestslave = NULL;
	struct list_head *iter;
	int mintime = bond->params.updelay;

	if (bond->primary_slave && bond->primary_slave->link == BOND_LINK_UP &&
	    bond_should_change_active(bond))
		return bond->primary_slave;

	bond_for_each_slave(bond, slave, iter) {
		if (slave->link == BOND_LINK_UP)
			return slave;
		if (slave->link == BOND_LINK_BACK && IS_UP(slave->dev) &&
		    slave->delay < mintime) {
			mintime = slave->delay;
			bestslave = slave;
		}
	}

	return bestslave;
}

static bool bond_should_notify_peers(struct bonding *bond)
{
	struct slave *slave;

	rcu_read_lock();
	slave = rcu_dereference(bond->curr_active_slave);
	rcu_read_unlock();

	pr_debug("bond_should_notify_peers: bond %s slave %s\n",
		 bond->dev->name, slave ? slave->dev->name : "NULL");

	if (!slave || !bond->send_peer_notif ||
	    test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
		return false;

	return true;
}

/**
 * change_active_interface - change the active slave into the specified one
 * @bond: our bonding struct
 * @new: the new slave to make the active one
 *
 * Set the new slave to the bond's settings and unset them on the old
 * curr_active_slave.
 * Setting include flags, mc-list, promiscuity, allmulti, etc.
 *
 * If @new's link state is %BOND_LINK_BACK we'll set it to %BOND_LINK_UP,
 * because it is apparently the best available slave we have, even though its
 * updelay hasn't timed out yet.
 *
 * If new_active is not NULL, caller must hold curr_slave_lock for write_bh.
 */
void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
{
	struct slave *old_active = bond->curr_active_slave;

	if (old_active == new_active)
		return;

	if (new_active) {
		new_active->jiffies = jiffies;

		if (new_active->link == BOND_LINK_BACK) {
			if (USES_PRIMARY(bond->params.mode)) {
				pr_info("%s: making interface %s the new active one %d ms earlier.\n",
					bond->dev->name, new_active->dev->name,
					(bond->params.updelay - new_active->delay) * bond->params.miimon);
			}

			new_active->delay = 0;
			new_active->link = BOND_LINK_UP;

			if (bond->params.mode == BOND_MODE_8023AD)
				bond_3ad_handle_link_change(new_active, BOND_LINK_UP);

			if (bond_is_lb(bond))
				bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP);
		} else {
			if (USES_PRIMARY(bond->params.mode)) {
				pr_info("%s: making interface %s the new active one.\n",
					bond->dev->name, new_active->dev->name);
			}
		}
	}

	if (USES_PRIMARY(bond->params.mode))
		bond_hw_addr_swap(bond, new_active, old_active);

	if (bond_is_lb(bond)) {
		bond_alb_handle_active_change(bond, new_active);
		if (old_active)
			bond_set_slave_inactive_flags(old_active);
		if (new_active)
			bond_set_slave_active_flags(new_active);
	} else {
		rcu_assign_pointer(bond->curr_active_slave, new_active);
	}

	if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
		if (old_active)
			bond_set_slave_inactive_flags(old_active);

		if (new_active) {
			bool should_notify_peers = false;

			bond_set_slave_active_flags(new_active);

			if (bond->params.fail_over_mac)
				bond_do_fail_over_mac(bond, new_active,
						      old_active);

			if (netif_running(bond->dev)) {
				bond->send_peer_notif =
					bond->params.num_peer_notif;
				should_notify_peers =
					bond_should_notify_peers(bond);
			}

			write_unlock_bh(&bond->curr_slave_lock);

			call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev);
			if (should_notify_peers)
				call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
							 bond->dev);

			write_lock_bh(&bond->curr_slave_lock);
		}
	}

	/* resend IGMP joins since active slave has changed or
	 * all were sent on curr_active_slave.
	 * resend only if bond is brought up with the affected
	 * bonding modes and the retransmission is enabled */
	if (netif_running(bond->dev) && (bond->params.resend_igmp > 0) &&
	    ((USES_PRIMARY(bond->params.mode) && new_active) ||
	     bond->params.mode == BOND_MODE_ROUNDROBIN)) {
		bond->igmp_retrans = bond->params.resend_igmp;
		queue_delayed_work(bond->wq, &bond->mcast_work, 1);
	}
}

/**
 * bond_select_active_slave - select a new active slave, if needed
 * @bond: our bonding struct
 *
 * This functions should be called when one of the following occurs:
 * - The old curr_active_slave has been released or lost its link.
 * - The primary_slave has got its link back.
 * - A slave has got its link back and there's no old curr_active_slave.
 *
 * Caller must hold curr_slave_lock for write_bh.
 */
void bond_select_active_slave(struct bonding *bond)
{
	struct slave *best_slave;
	int rv;

	best_slave = bond_find_best_slave(bond);
	if (best_slave != bond->curr_active_slave) {
		bond_change_active_slave(bond, best_slave);
		rv = bond_set_carrier(bond);
		if (!rv)
			return;

		if (netif_carrier_ok(bond->dev)) {
			pr_info("%s: first active interface up!\n",
				bond->dev->name);
		} else {
			pr_info("%s: now running without any active interface !\n",
				bond->dev->name);
		}
	}
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static inline int slave_enable_netpoll(struct slave *slave)
{
	struct netpoll *np;
	int err = 0;

	np = kzalloc(sizeof(*np), GFP_ATOMIC);
	err = -ENOMEM;
	if (!np)
		goto out;

	err = __netpoll_setup(np, slave->dev, GFP_ATOMIC);
	if (err) {
		kfree(np);
		goto out;
	}
	slave->np = np;
out:
	return err;
}
static inline void slave_disable_netpoll(struct slave *slave)
{
	struct netpoll *np = slave->np;

	if (!np)
		return;

	slave->np = NULL;
	__netpoll_free_async(np);
}
static inline bool slave_dev_support_netpoll(struct net_device *slave_dev)
{
	if (slave_dev->priv_flags & IFF_DISABLE_NETPOLL)
		return false;
	if (!slave_dev->netdev_ops->ndo_poll_controller)
		return false;
	return true;
}

static void bond_poll_controller(struct net_device *bond_dev)
{
}

static void bond_netpoll_cleanup(struct net_device *bond_dev)
{
	struct bonding *bond = netdev_priv(bond_dev);
	struct list_head *iter;
	struct slave *slave;

	bond_for_each_slave(bond, slave, iter)
		if (IS_UP(slave->dev))
			slave_disable_netpoll(slave);
}

static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, gfp_t gfp)
{
	struct bonding *bond = netdev_priv(dev);
	struct list_head *iter;
	struct slave *slave;
	int err = 0;

	bond_for_each_slave(bond, slave, iter) {
		err = slave_enable_netpoll(slave);
		if (err) {
			bond_netpoll_cleanup(dev);
			break;
		}
	}
	return err;
}
#else
static inline int slave_enable_netpoll(struct slave *slave)
{
	return 0;
}
static inline void slave_disable_netpoll(struct slave *slave)
{
}
static void bond_netpoll_cleanup(struct net_device *bond_dev)
{
}
#endif

/*---------------------------------- IOCTL ----------------------------------*/

static netdev_features_t bond_fix_features(struct net_device *dev,
					   netdev_features_t features)
{
	struct bonding *bond = netdev_priv(dev);
	struct list_head *iter;
	netdev_features_t mask;
	struct slave *slave;

	if (!bond_has_slaves(bond)) {
		/* Disable adding VLANs to empty bond. But why? --mq */
		features |= NETIF_F_VLAN_CHALLENGED;
		return features;
	}

	mask = features;
	features &= ~NETIF_F_ONE_FOR_ALL;
	features |= NETIF_F_ALL_FOR_ALL;

	bond_for_each_slave(bond, slave, iter) {
		features = netdev_increment_features(features,
						     slave->dev->features,
						     mask);
	}
	features = netdev_add_tso_features(features, mask);

	return features;
}

#define BOND_VLAN_FEATURES	(NETIF_F_ALL_CSUM | NETIF_F_SG | \
				 NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
				 NETIF_F_HIGHDMA | NETIF_F_LRO)

static void bond_compute_features(struct bonding *bond)
{
	unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE;
	netdev_features_t vlan_features = BOND_VLAN_FEATURES;
	struct net_device *bond_dev = bond->dev;
	struct list_head *iter;
	struct slave *slave;
	unsigned short max_hard_header_len = ETH_HLEN;
	unsigned int gso_max_size = GSO_MAX_SIZE;
	u16 gso_max_segs = GSO_MAX_SEGS;

	if (!bond_has_slaves(bond))
		goto done;

	bond_for_each_slave(bond, slave, iter) {
		vlan_features = netdev_increment_features(vlan_features,
			slave->dev->vlan_features, BOND_VLAN_FEATURES);

		dst_release_flag &= slave->dev->priv_flags;
		if (slave->dev->hard_header_len > max_hard_header_len)
			max_hard_header_len = slave->dev->hard_header_len;

		gso_max_size = min(gso_max_size, slave->dev->gso_max_size);
		gso_max_segs = min(gso_max_segs, slave->dev->gso_max_segs);
	}

done:
	bond_dev->vlan_features = vlan_features;
	bond_dev->hard_header_len = max_hard_header_len;
	bond_dev->gso_max_segs = gso_max_segs;
	netif_set_gso_max_size(bond_dev, gso_max_size);

	flags = bond_dev->priv_flags & ~IFF_XMIT_DST_RELEASE;
	bond_dev->priv_flags = flags | dst_release_flag;

	netdev_change_features(bond_dev);
}

static void bond_setup_by_slave(struct net_device *bond_dev,
				struct net_device *slave_dev)
{
	bond_dev->header_ops	    = slave_dev->header_ops;

	bond_dev->type		    = slave_dev->type;
	bond_dev->hard_header_len   = slave_dev->hard_header_len;
	bond_dev->addr_len	    = slave_dev->addr_len;

	memcpy(bond_dev->broadcast, slave_dev->broadcast,
		slave_dev->addr_len);
}

/* On bonding slaves other than the currently active slave, suppress
 * duplicates except for alb non-mcast/bcast.
 */
static bool bond_should_deliver_exact_match(struct sk_buff *skb,
					    struct slave *slave,
					    struct bonding *bond)
{
	if (bond_is_slave_inactive(slave)) {
		if (bond->params.mode == BOND_MODE_ALB &&
		    skb->pkt_type != PACKET_BROADCAST &&
		    skb->pkt_type != PACKET_MULTICAST)
			return false;
		return true;
	}
	return false;
}

static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
{
	struct sk_buff *skb = *pskb;
	struct slave *slave;
	struct bonding *bond;
	int (*recv_probe)(const struct sk_buff *, struct bonding *,
			  struct slave *);
	int ret = RX_HANDLER_ANOTHER;

	skb = skb_share_check(skb, GFP_ATOMIC);
	if (unlikely(!skb))
		return RX_HANDLER_CONSUMED;

	*pskb = skb;

	slave = bond_slave_get_rcu(skb->dev);
	bond = slave->bond;

	if (bond->params.arp_interval)
		slave->dev->last_rx = jiffies;

	recv_probe = ACCESS_ONCE(bond->recv_probe);
	if (recv_probe) {
		ret = recv_probe(skb, bond, slave);
		if (ret == RX_HANDLER_CONSUMED) {
			consume_skb(skb);
			return ret;
		}
	}

	if (bond_should_deliver_exact_match(skb, slave, bond)) {
		return RX_HANDLER_EXACT;
	}

	skb->dev = bond->dev;

	if (bond->params.mode == BOND_MODE_ALB &&
	    bond->dev->priv_flags & IFF_BRIDGE_PORT &&
	    skb->pkt_type == PACKET_HOST) {

		if (unlikely(skb_cow_head(skb,
					  skb->data - skb_mac_header(skb)))) {
			kfree_skb(skb);
			return RX_HANDLER_CONSUMED;
		}
		memcpy(eth_hdr(skb)->h_dest, bond->dev->dev_addr, ETH_ALEN);
	}

	return ret;
}

static int bond_master_upper_dev_link(struct net_device *bond_dev,
				      struct net_device *slave_dev,
				      struct slave *slave)
{
	int err;

	err = netdev_master_upper_dev_link_private(slave_dev, bond_dev, slave);
	if (err)
		return err;
	slave_dev->flags |= IFF_SLAVE;
	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL);
	return 0;
}

static void bond_upper_dev_unlink(struct net_device *bond_dev,
				  struct net_device *slave_dev)
{
	netdev_upper_dev_unlink(slave_dev, bond_dev);
	slave_dev->flags &= ~IFF_SLAVE;
	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL);
}

/* enslave device <slave> to bond device <master> */
int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
{
	struct bonding *bond = netdev_priv(bond_dev);
	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
	struct slave *new_slave = NULL, *prev_slave;
	struct sockaddr addr;
	int link_reporting;
	int res = 0, i;

	if (!bond->params.use_carrier &&
	    slave_dev->ethtool_ops->get_link == NULL &&
	    slave_ops->ndo_do_ioctl == NULL) {
		pr_warning("%s: Warning: no link monitoring support for %s\n",
			   bond_dev->name, slave_dev->name);
	}

	/* already enslaved */
	if (slave_dev->flags & IFF_SLAVE) {
		pr_debug("Error, Device was already enslaved\n");
		return -EBUSY;
	}

	/* vlan challenged mutual exclusion */
	/* no need to lock since we're protected by rtnl_lock */
	if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) {
		pr_debug("%s: NETIF_F_VLAN_CHALLENGED\n", slave_dev->name);
		if (vlan_uses_dev(bond_dev)) {
			pr_err("%s: Error: cannot enslave VLAN challenged slave %s on VLAN enabled bond %s\n",
			       bond_dev->name, slave_dev->name, bond_dev->name);
			return -EPERM;
		} else {
			pr_warning("%s: Warning: enslaved VLAN challenged slave %s. Adding VLANs will be blocked as long as %s is part of bond %s\n",
				   bond_dev->name, slave_dev->name,
				   slave_dev->name, bond_dev->name);
		}
	} else {
		pr_debug("%s: ! NETIF_F_VLAN_CHALLENGED\n", slave_dev->name);
	}

	/*
	 * Old ifenslave binaries are no longer supported.  These can
	 * be identified with moderate accuracy by the state of the slave:
	 * the current ifenslave will set the interface down prior to
	 * enslaving it; the old ifenslave will not.
	 */
	if ((slave_dev->flags & IFF_UP)) {
		pr_err("%s is up. This may be due to an out of date ifenslave.\n",
		       slave_dev->name);
		res = -EPERM;
		goto err_undo_flags;
	}

	/* set bonding device ether type by slave - bonding netdevices are
	 * created with ether_setup, so when the slave type is not ARPHRD_ETHER
	 * there is a need to override some of the type dependent attribs/funcs.
	 *
	 * bond ether type mutual exclusion - don't allow slaves of dissimilar
	 * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond
	 */
	if (!bond_has_slaves(bond)) {
		if (bond_dev->type != slave_dev->type) {
			pr_debug("%s: change device type from %d to %d\n",
				 bond_dev->name,
				 bond_dev->type, slave_dev->type);

			res = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE,
						       bond_dev);
			res = notifier_to_errno(res);
			if (res) {
				pr_err("%s: refused to change device type\n",
				       bond_dev->name);
				res = -EBUSY;
				goto err_undo_flags;
			}

			/* Flush unicast and multicast addresses */
			dev_uc_flush(bond_dev);
			dev_mc_flush(bond_dev);

			if (slave_dev->type != ARPHRD_ETHER)
				bond_setup_by_slave(bond_dev, slave_dev);
			else {
				ether_setup(bond_dev);
				bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING;
			}

			call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE,
						 bond_dev);
		}
	} else if (bond_dev->type != slave_dev->type) {
		pr_err("%s ether type (%d) is different from other slaves (%d), can not enslave it.\n",
		       slave_dev->name,
		       slave_dev->type, bond_dev->type);
		res = -EINVAL;
		goto err_undo_flags;
	}

	if (slave_ops->ndo_set_mac_address == NULL) {
		if (!bond_has_slaves(bond)) {
			pr_warn("%s: Warning: The first slave device specified does not support setting the MAC address.\n",
				bond_dev->name);
			if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
				bond->params.fail_over_mac = BOND_FOM_ACTIVE;
				pr_warn("%s: Setting fail_over_mac to active for active-backup mode.\n",
					bond_dev->name);
			}
		} else if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) {
			pr_err("%s: Error: The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active.\n",
			       bond_dev->name);
			res = -EOPNOTSUPP;
			goto err_undo_flags;
		}
	}

	call_netdevice_notifiers(NETDEV_JOIN, slave_dev);

	/* If this is the first slave, then we need to set the master's hardware
	 * address to be the same as the slave's. */
	if (!bond_has_slaves(bond) &&
	    bond->dev->addr_assign_type == NET_ADDR_RANDOM)
		bond_set_dev_addr(bond->dev, slave_dev);

	new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL);
	if (!new_slave) {
		res = -ENOMEM;
		goto err_undo_flags;
	}
	/*
	 * Set the new_slave's queue_id to be zero.  Queue ID mapping
	 * is set via sysfs or module option if desired.
	 */
	new_slave->queue_id = 0;

	/* Save slave's original mtu and then set it to match the bond */
	new_slave->original_mtu = slave_dev->mtu;
	res = dev_set_mtu(slave_dev, bond->dev->mtu);
	if (res) {
		pr_debug("Error %d calling dev_set_mtu\n", res);
		goto err_free;
	}

	/*
	 * Save slave's original ("permanent") mac address for modes
	 * that need it, and for restoring it upon release, and then
	 * set it to the master's address
	 */
	memcpy(new_slave->perm_hwaddr, slave_dev->dev_addr, ETH_ALEN);

	if (!bond->params.fail_over_mac ||
	    bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
		/*
		 * Set slave to master's mac address.  The application already
		 * set the master's mac address to that of the first slave
		 */
		memcpy(addr.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
		addr.sa_family = slave_dev->type;
		res = dev_set_mac_address(slave_dev, &addr);
		if (res) {
			pr_debug("Error %d calling set_mac_address\n", res);
			goto err_restore_mtu;
		}
	}

	/* open the slave since the application closed it */
	res = dev_open(slave_dev);
	if (res) {
		pr_debug("Opening slave %s failed\n", slave_dev->name);
		goto err_restore_mac;
	}

	new_slave->bond = bond;
	new_slave->dev = slave_dev;
	slave_dev->priv_flags |= IFF_BONDING;

	if (bond_is_lb(bond)) {
		/* bond_alb_init_slave() must be called before all other stages since
		 * it might fail and we do not want to have to undo everything
		 */
		res = bond_alb_init_slave(bond, new_slave);
		if (res)
			goto err_close;
	}

	/* If the mode USES_PRIMARY, then the following is handled by
	 * bond_change_active_slave().
	 */
	if (!USES_PRIMARY(bond->params.mode)) {
		/* set promiscuity level to new slave */
		if (bond_dev->flags & IFF_PROMISC) {
			res = dev_set_promiscuity(slave_dev, 1);
			if (res)
				goto err_close;
		}

		/* set allmulti level to new slave */
		if (bond_dev->flags & IFF_ALLMULTI) {
			res = dev_set_allmulti(slave_dev, 1);
			if (res)
				goto err_close;
		}

		netif_addr_lock_bh(bond_dev);

		dev_mc_sync_multiple(slave_dev, bond_dev);
		dev_uc_sync_multiple(slave_dev, bond_dev);

		netif_addr_unlock_bh(bond_dev);
	}

	if (bond->params.mode == BOND_MODE_8023AD) {
		/* add lacpdu mc addr to mc list */
		u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;

		dev_mc_add(slave_dev, lacpdu_multicast);
	}

	res = vlan_vids_add_by_dev(slave_dev, bond_dev);
	if (res) {
		pr_err("%s: Error: Couldn't add bond vlan ids to %s\n",
		       bond_dev->name, slave_dev->name);
		goto err_close;
	}

	prev_slave = bond_last_slave(bond);

	new_slave->delay = 0;
	new_slave->link_failure_count = 0;

	bond_update_speed_duplex(new_slave);

	new_slave->last_arp_rx = jiffies -
		(msecs_to_jiffies(bond->params.arp_interval) + 1);
	for (i = 0; i < BOND_MAX_ARP_TARGETS; i++)
		new_slave->target_last_arp_rx[i] = new_slave->last_arp_rx;

	if (bond->params.miimon && !bond->params.use_carrier) {
		link_reporting = bond_check_dev_link(bond, slave_dev, 1);

		if ((link_reporting == -1) && !bond->params.arp_interval) {
			/*
			 * miimon is set but a bonded network driver
			 * does not support ETHTOOL/MII and
			 * arp_interval is not set.  Note: if
			 * use_carrier is enabled, we will never go
			 * here (because netif_carrier is always
			 * supported); thus, we don't need to change
			 * the messages for netif_carrier.
			 */
			pr_warning("%s: Warning: MII and ETHTOOL support not available for interface %s, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details.\n",
			       bond_dev->name, slave_dev->name);
		} else if (link_reporting == -1) {
			/* unable get link status using mii/ethtool */
			pr_warning("%s: Warning: can't get link status from interface %s; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface.\n",
				   bond_dev->name, slave_dev->name);
		}
	}

	/* check for initial state */
	if (bond->params.miimon) {
		if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) {
			if (bond->params.updelay) {
				new_slave->link = BOND_LINK_BACK;
				new_slave->delay = bond->params.updelay;
			} else {
				new_slave->link = BOND_LINK_UP;
			}
		} else {
			new_slave->link = BOND_LINK_DOWN;
		}
	} else if (bond->params.arp_interval) {
		new_slave->link = (netif_carrier_ok(slave_dev) ?
			BOND_LINK_UP : BOND_LINK_DOWN);
	} else {
		new_slave->link = BOND_LINK_UP;
	}

	if (new_slave->link != BOND_LINK_DOWN)
		new_slave->jiffies = jiffies;
	pr_debug("Initial state of slave_dev is BOND_LINK_%s\n",
		new_slave->link == BOND_LINK_DOWN ? "DOWN" :
			(new_slave->link == BOND_LINK_UP ? "UP" : "BACK"));

	if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) {
		/* if there is a primary slave, remember it */
		if (strcmp(bond->params.primary, new_slave->dev->name) == 0) {
			bond->primary_slave = new_slave;
			bond->force_primary = true;
		}
	}

	switch (bond->params.mode) {
	case BOND_MODE_ACTIVEBACKUP:
		bond_set_slave_inactive_flags(new_slave);
		break;
	case BOND_MODE_8023AD:
		/* in 802.3ad mode, the internal mechanism
		 * will activate the slaves in the selected
		 * aggregator
		 */
		bond_set_slave_inactive_flags(new_slave);
		/* if this is the first slave */
		if (!prev_slave) {
			SLAVE_AD_INFO(new_slave).id = 1;
			/* Initialize AD with the number of times that the AD timer is called in 1 second
			 * can be called only after the mac address of the bond is set
			 */
			bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL);
		} else {
			SLAVE_AD_INFO(new_slave).id =
				SLAVE_AD_INFO(prev_slave).id + 1;
		}

		bond_3ad_bind_slave(new_slave);
		break;
	case BOND_MODE_TLB:
	case BOND_MODE_ALB:
		bond_set_active_slave(new_slave);
		bond_set_slave_inactive_flags(new_slave);
		break;
	default:
		pr_debug("This slave is always active in trunk mode\n");

		/* always active in trunk mode */
		bond_set_active_slave(new_slave);

		/* In trunking mode there is little meaning to curr_active_slave
		 * anyway (it holds no special properties of the bond device),
		 * so we can change it without calling change_active_interface()
		 */
		if (!bond->curr_active_slave && new_slave->link == BOND_LINK_UP)
			rcu_assign_pointer(bond->curr_active_slave, new_slave);

		break;
	} /* switch(bond_mode) */

#ifdef CONFIG_NET_POLL_CONTROLLER
	slave_dev->npinfo = bond->dev->npinfo;
	if (slave_dev->npinfo) {
		if (slave_enable_netpoll(new_slave)) {
			pr_info("Error, %s: master_dev is using netpoll, "
				 "but new slave device does not support netpoll.\n",
				 bond_dev->name);
			res = -EBUSY;
			goto err_detach;
		}
	}
#endif

	res = netdev_rx_handler_register(slave_dev, bond_handle_frame,
					 new_slave);
	if (res) {
		pr_debug("Error %d calling netdev_rx_handler_register\n", res);
		goto err_detach;
	}

	res = bond_master_upper_dev_link(bond_dev, slave_dev, new_slave);
	if (res) {
		pr_debug("Error %d calling bond_master_upper_dev_link\n", res);
		goto err_unregister;
	}

	res = bond_sysfs_slave_add(new_slave);
	if (res) {
		pr_debug("Error %d calling bond_sysfs_slave_add\n", res);
		goto err_upper_unlink;
	}

	bond->slave_cnt++;
	bond_compute_features(bond);
	bond_set_carrier(bond);

	if (USES_PRIMARY(bond->params.mode)) {
		write_lock_bh(&bond->curr_slave_lock);
		bond_select_active_slave(bond);
		write_unlock_bh(&bond->curr_slave_lock);
	}

	pr_info("%s: enslaving %s as a%s interface with a%s link.\n",
		bond_dev->name, slave_dev->name,
		bond_is_active_slave(new_slave) ? "n active" : " backup",
		new_slave->link != BOND_LINK_DOWN ? "n up" : " down");

	/* enslave is successful */
	return 0;

/* Undo stages on error */
err_upper_unlink:
	bond_upper_dev_unlink(bond_dev, slave_dev);

err_unregister:
	netdev_rx_handler_unregister(slave_dev);

err_detach:
	if (!USES_PRIMARY(bond->params.mode))
		bond_hw_addr_flush(bond_dev, slave_dev);

	vlan_vids_del_by_dev(slave_dev, bond_dev);
	if (bond->primary_slave == new_slave)
		bond->primary_slave = NULL;
	if (bond->curr_active_slave == new_slave) {
		write_lock_bh(&bond->curr_slave_lock);
		bond_change_active_slave(bond, NULL);
		bond_select_active_slave(bond);
		write_unlock_bh(&bond->curr_slave_lock);
	}
	slave_disable_netpoll(new_slave);

err_close:
	slave_dev->priv_flags &= ~IFF_BONDING;
	dev_close(slave_dev);

err_restore_mac:
	if (!bond->params.fail_over_mac ||
	    bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
		/* XXX TODO - fom follow mode needs to change master's
		 * MAC if this slave's MAC is in use by the bond, or at
		 * least print a warning.
		 */
		memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN);
		addr.sa_family = slave_dev->type;
		dev_set_mac_address(slave_dev, &addr);
	}

err_restore_mtu:
	dev_set_mtu(slave_dev, new_slave->original_mtu);

err_free:
	kfree(new_slave);

err_undo_flags:
	/* Enslave of first slave has failed and we need to fix master's mac */
	if (!bond_has_slaves(bond) &&
	    ether_addr_equal_64bits(bond_dev->dev_addr, slave_dev->dev_addr))
		eth_hw_addr_random(bond_dev);

	return res;
}

/*
 * Try to release the slave device <slave> from the bond device <master>
 * It is legal to access curr_active_slave without a lock because all the function
 * is write-locked. If "all" is true it means that the function is being called
 * while destroying a bond interface and all slaves are being released.
 *
 * The rules for slave state should be:
 *   for Active/Backup:
 *     Active stays on all backups go down
 *   for Bonded connections:
 *     The first up interface should be left on and all others downed.
 */
static int __bond_release_one(struct net_device *bond_dev,
			      struct net_device *slave_dev,
			      bool all)
{
	struct bonding *bond = netdev_priv(bond_dev);
	struct slave *slave, *oldcurrent;
	struct sockaddr addr;
	int old_flags = bond_dev->flags;
	netdev_features_t old_features = bond_dev->features;

	/* slave is not a slave or master is not master of this slave */
	if (!(slave_dev->flags & IFF_SLAVE) ||
	    !netdev_has_upper_dev(slave_dev, bond_dev)) {
		pr_err("%s: Error: cannot release %s.\n",
		       bond_dev->name, slave_dev->name);
		return -EINVAL;
	}

	block_netpoll_tx();

	slave = bond_get_slave_by_dev(bond, slave_dev);
	if (!slave) {
		/* not a slave of this bond */
		pr_info("%s: %s not enslaved\n",
			bond_dev->name, slave_dev->name);
		unblock_netpoll_tx();
		return -EINVAL;
	}

	/* release the slave from its bond */
	bond->slave_cnt--;

	bond_sysfs_slave_del(slave);

	bond_upper_dev_unlink(bond_dev, slave_dev);
	/* unregister rx_handler early so bond_handle_frame wouldn't be called
	 * for this slave anymore.
	 */
	netdev_rx_handler_unregister(slave_dev);
	write_lock_bh(&bond->lock);

	/* Inform AD package of unbinding of slave. */
	if (bond->params.mode == BOND_MODE_8023AD)
		bond_3ad_unbind_slave(slave);

	write_unlock_bh(&bond->lock);

	pr_info("%s: releasing %s interface %s\n",
		bond_dev->name,
		bond_is_active_slave(slave) ? "active" : "backup",
		slave_dev->name);

	oldcurrent = bond->curr_active_slave;

	bond->current_arp_slave = NULL;

	if (!all && (!bond->params.fail_over_mac ||
		     bond->params.mode != BOND_MODE_ACTIVEBACKUP)) {
		if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) &&
		    bond_has_slaves(bond))
			pr_warn("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n",
				   bond_dev->name, slave_dev->name,
				   slave->perm_hwaddr,
				   bond_dev->name, slave_dev->name);
	}

	if (bond->primary_slave == slave)
		bond->primary_slave = NULL;

	if (oldcurrent == slave) {
		write_lock_bh(&bond->curr_slave_lock);
		bond_change_active_slave(bond, NULL);
		write_unlock_bh(&bond->curr_slave_lock);
	}

	if (bond_is_lb(bond)) {
		/* Must be called only after the slave has been
		 * detached from the list and the curr_active_slave
		 * has been cleared (if our_slave == old_current),
		 * but before a new active slave is selected.
		 */
		bond_alb_deinit_slave(bond, slave);
	}

	if (all) {
		RCU_INIT_POINTER(bond->curr_active_slave, NULL);
	} else if (oldcurrent == slave) {
		/*
		 * Note that we hold RTNL over this sequence, so there
		 * is no concern that another slave add/remove event
		 * will interfere.
		 */
		write_lock_bh(&bond->curr_slave_lock);

		bond_select_active_slave(bond);

		write_unlock_bh(&bond->curr_slave_lock);
	}

	if (!bond_has_slaves(bond)) {
		bond_set_carrier(bond);
		eth_hw_addr_random(bond_dev);

		if (vlan_uses_dev(bond_dev)) {
			pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n",
				   bond_dev->name, bond_dev->name);
			pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n",
				   bond_dev->name);
		}
	}

	unblock_netpoll_tx();
	synchronize_rcu();

	if (!bond_has_slaves(bond)) {
		call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev);
		call_netdevice_notifiers(NETDEV_RELEASE, bond->dev);
	}

	bond_compute_features(bond);
	if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) &&
	    (old_features & NETIF_F_VLAN_CHALLENGED))
		pr_info("%s: last VLAN challenged slave %s left bond %s. VLAN blocking is removed\n",
			bond_dev->name, slave_dev->name, bond_dev->name);

	/* must do this from outside any spinlocks */
	vlan_vids_del_by_dev(slave_dev, bond_dev);

	/* If the mode USES_PRIMARY, then this cases was handled above by
	 * bond_change_active_slave(..., NULL)
	 */
	if (!USES_PRIMARY(bond->params.mode)) {
		/* unset promiscuity level from slave
		 * NOTE: The NETDEV_CHANGEADDR call above may change the value
		 * of the IFF_PROMISC flag in the bond_dev, but we need the
		 * value of that flag before that change, as that was the value
		 * when this slave was attached, so we cache at the start of the
		 * function and use it here. Same goes for ALLMULTI below
		 */
		if (old_flags & IFF_PROMISC)
			dev_set_promiscuity(slave_dev, -1);

		/* unset allmulti level from slave */
		if (old_flags & IFF_ALLMULTI)
			dev_set_allmulti(slave_dev, -1);

		bond_hw_addr_flush(bond_dev, slave_dev);
	}

	slave_disable_netpoll(slave);

	/* close slave before restoring its mac address */
	dev_close(slave_dev);

	if (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
	    bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
		/* restore original ("permanent") mac address */
		memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
		addr.sa_family = slave_dev->type;
		dev_set_mac_address(slave_dev, &addr);
	}

	dev_set_mtu(slave_dev, slave->original_mtu);

	slave_dev->priv_flags &= ~IFF_BONDING;

	kfree(slave);

	return 0;  /* deletion OK */
}

/* A wrapper used because of ndo_del_link */
int bond_release(struct net_device *bond_dev, struct net_device *slave_dev)
{
	return __bond_release_one(bond_dev, slave_dev, false);
}

/*
* First release a slave and then destroy the bond if no more slaves are left.
* Must be under rtnl_lock when this function is called.
*/
static int  bond_release_and_destroy(struct net_device *bond_dev,
				     struct net_device *slave_dev)
{
	struct bonding *bond = netdev_priv(bond_dev);
	int ret;

	ret = bond_release(bond_dev, slave_dev);
	if (ret == 0 && !bond_has_slaves(bond)) {
		bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
		pr_info("%s: destroying bond %s.\n",
			bond_dev->name, bond_dev->name);
		unregister_netdevice(bond_dev);
	}
	return ret;
}

static int bond_info_query(struct net_device *bond_dev, struct ifbond *info)
{
	struct bonding *bond = netdev_priv(bond_dev);

	info->bond_mode = bond->params.mode;
	info->miimon = bond->params.miimon;

	read_lock(&bond->lock);
	info->num_slaves = bond->slave_cnt;
	read_unlock(&bond->lock);

	return 0;
}

static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info)
{
	struct bonding *bond = netdev_priv(bond_dev);
	struct list_head *iter;
	int i = 0, res = -ENODEV;
	struct slave *slave;

	read_lock(&bond->lock);
	bond_for_each_slave(bond, slave, iter) {
		if (i++ == (int)info->slave_id) {
			res = 0;
			strcpy(info->slave_name, slave->dev->name);
			info->link = slave->link;
			info->state = bond_slave_state(slave);
			info->link_failure_count = slave->link_failure_count;
			break;
		}
	}
	read_unlock(&bond->lock);

	return res;
}

/*-------------------------------- Monitoring -------------------------------*/


static int bond_miimon_inspect(struct bonding *bond)
{
	int link_state, commit = 0;
	struct list_head *iter;
	struct slave *slave;
	bool ignore_updelay;

	ignore_updelay = !bond->curr_active_slave ? true : false;

	bond_for_each_slave_rcu(bond, slave, iter) {
		slave->new_link = BOND_LINK_NOCHANGE;

		link_state = bond_check_dev_link(bond, slave->dev, 0);

		switch (slave->link) {
		case BOND_LINK_UP:
			if (link_state)
				continue;

			slave->link = BOND_LINK_FAIL;
			slave->delay = bond->params.downdelay;
			if (slave->delay) {
				pr_info("%s: link status down for %sinterface %s, disabling it in %d ms.\n",
					bond->dev->name,
					(bond->params.mode ==
					 BOND_MODE_ACTIVEBACKUP) ?
					(bond_is_active_slave(slave) ?
					 "active " : "backup ") : "",
					slave->dev->name,
					bond->params.downdelay * bond->params.miimon);
			}
			/*FALLTHRU*/
		case BOND_LINK_FAIL:
			if (link_state) {
				/*
				 * recovered before downdelay expired
				 */
				slave->link = BOND_LINK_UP;
				slave->jiffies = jiffies;
				pr_info("%s: link status up again after %d ms for interface %s.\n",
					bond->dev->name,
					(bond->params.downdelay - slave->delay) *
					bond->params.miimon,
					slave->dev->name);
				continue;
			}

			if (slave->delay <= 0) {
				slave->new_link = BOND_LINK_DOWN;
				commit++;
				continue;
			}

			slave->delay--;
			break;

		case BOND_LINK_DOWN:
			if (!link_state)
				continue;

			slave->link = BOND_LINK_BACK;
			slave->delay = bond->params.updelay;

			if (slave->delay) {
				pr_info("%s: link status up for interface %s, enabling it in %d ms.\n",
					bond->dev->name, slave->dev->name,
					ignore_updelay ? 0 :
					bond->params.updelay *
					bond->params.miimon);
			}
			/*FALLTHRU*/
		case BOND_LINK_BACK:
			if (!link_state) {
				slave->link = BOND_LINK_DOWN;
				pr_info("%s: link status down again after %d ms for interface %s.\n",
					bond->dev->name,
					(bond->params.updelay - slave->delay) *
					bond->params.miimon,
					slave->dev->name);

				continue;
			}

			if (ignore_updelay)
				slave->delay = 0;

			if (slave->delay <= 0) {
				slave->new_link = BOND_LINK_UP;
				commit++;
				ignore_updelay = false;
				continue;
			}

			slave->delay--;
			break;
		}
	}

	return commit;
}

static void bond_miimon_commit(struct bonding *bond)
{
	struct list_head *iter;
	struct slave *slave;

	bond_for_each_slave(bond, slave, iter) {
		switch (slave->new_link) {
		case BOND_LINK_NOCHANGE:
			continue;

		case BOND_LINK_UP:
			slave->link = BOND_LINK_UP;
			slave->jiffies = jiffies;

			if (bond->params.mode == BOND_MODE_8023AD) {
				/* prevent it from being the active one */
				bond_set_backup_slave(slave);
			} else if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
				/* make it immediately active */
				bond_set_active_slave(slave);
			} else if (slave != bond->primary_slave) {
				/* prevent it from being the active one */
				bond_set_backup_slave(slave);
			}

			pr_info("%s: link status definitely up for interface %s, %u Mbps %s duplex.\n",
				bond->dev->name, slave->dev->name,
				slave->speed == SPEED_UNKNOWN ? 0 : slave->speed,
				slave->duplex ? "full" : "half");

			/* notify ad that the link status has changed */
			if (bond->params.mode == BOND_MODE_8023AD)
				bond_3ad_handle_link_change(slave, BOND_LINK_UP);

			if (bond_is_lb(bond))
				bond_alb_handle_link_change(bond, slave,
							    BOND_LINK_UP);

			if (!bond->curr_active_slave ||
			    (slave == bond->primary_slave))
				goto do_failover;

			continue;

		case BOND_LINK_DOWN:
			if (slave->link_failure_count < UINT_MAX)
				slave->link_failure_count++;

			slave->link = BOND_LINK_DOWN;

			if (bond->params.mode == BOND_MODE_ACTIVEBACKUP ||
			    bond->params.mode == BOND_MODE_8023AD)
				bond_set_slave_inactive_flags(slave);

			pr_info("%s: link status definitely down for interface %s, disabling it\n",
				bond->dev->name, slave->dev->name);

			if (bond->params.mode == BOND_MODE_8023AD)
				bond_3ad_handle_link_change(slave,
							    BOND_LINK_DOWN);

			if (bond_is_lb(bond))
				bond_alb_handle_link_change(bond, slave,
							    BOND_LINK_DOWN);

			if (slave == bond->curr_active_slave)
				goto do_failover;

			continue;

		default:
			pr_err("%s: invalid new link %d on slave %s\n",
			       bond->dev->name, slave->new_link,
			       slave->dev->name);
			slave->new_link = BOND_LINK_NOCHANGE;

			continue;
		}

do_failover:
		ASSERT_RTNL();
		block_netpoll_tx();
		write_lock_bh(&bond->curr_slave_lock);
		bond_select_active_slave(bond);
		write_unlock_bh(&bond->curr_slave_lock);
		unblock_netpoll_tx();
	}

	bond_set_carrier(bond);
}

/*
 * bond_mii_monitor
 *
 * Really a wrapper that splits the mii monitor into two phases: an
 * inspection, then (if inspection indicates something needs to be done)
 * an acquisition of appropriate locks followed by a commit phase to
 * implement whatever link state changes are indicated.
 */
static void bond_mii_monitor(struct work_struct *work)
{
	struct bonding *bond = container_of(work, struct bonding,
					    mii_work.work);
	bool should_notify_peers = false;
	unsigned long delay;

	delay = msecs_to_jiffies(bond->params.miimon);

	if (!bond_has_slaves(bond))
		goto re_arm;

	rcu_read_lock();

	should_notify_peers = bond_should_notify_peers(bond);

	if (bond_miimon_inspect(bond)) {
		rcu_read_unlock();

		/* Race avoidance with bond_close cancel of workqueue */
		if (!rtnl_trylock()) {
			delay = 1;
			should_notify_peers = false;
			goto re_arm;
		}

		bond_miimon_commit(bond);

		rtnl_unlock();	/* might sleep, hold no other locks */
	} else
		rcu_read_unlock();

re_arm:
	if (bond->params.miimon)
		queue_delayed_work(bond->wq, &bond->mii_work, delay);

	if (should_notify_peers) {
		if (!rtnl_trylock())
			return;
		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
		rtnl_unlock();
	}
}

static bool bond_has_this_ip(struct bonding *bond, __be32 ip)
{
	struct net_device *upper;
	struct list_head *iter;
	bool ret = false;

	if (ip == bond_confirm_addr(bond->dev, 0, ip))
		return true;

	rcu_read_lock();
	netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
		if (ip == bond_confirm_addr(upper, 0, ip)) {
			ret = true;
			break;
		}
	}
	rcu_read_unlock();

	return ret;
}

/*
 * We go to the (large) trouble of VLAN tagging ARP frames because
 * switches in VLAN mode (especially if ports are configured as
 * "native" to a VLAN) might not pass non-tagged frames.
 */
static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_ip, __be32 src_ip, unsigned short vlan_id)
{
	struct sk_buff *skb;

	pr_debug("arp %d on slave %s: dst %pI4 src %pI4 vid %d\n", arp_op,
		 slave_dev->name, &dest_ip, &src_ip, vlan_id);

	skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip,
			 NULL, slave_dev->dev_addr, NULL);

	if (!skb) {
		pr_err("ARP packet allocation failed\n");
		return;
	}
	if (vlan_id) {
		skb = vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_id);
		if (!skb) {
			pr_err("failed to insert VLAN tag\n");
			return;
		}
	}
	arp_xmit(skb);
}


static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
{
	struct net_device *upper, *vlan_upper;
	struct list_head *iter, *vlan_iter;
	struct rtable *rt;
	__be32 *targets = bond->params.arp_targets, addr;
	int i, vlan_id;

	for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) {
		pr_debug("basa: target %pI4\n", &targets[i]);

		/* Find out through which dev should the packet go */
		rt = ip_route_output(dev_net(bond->dev), targets[i], 0,
				     RTO_ONLINK, 0);
		if (IS_ERR(rt)) {
			pr_debug("%s: no route to arp_ip_target %pI4\n",
				 bond->dev->name, &targets[i]);
			continue;
		}

		vlan_id = 0;

		/* bond device itself */
		if (rt->dst.dev == bond->dev)
			goto found;

		rcu_read_lock();
		/* first we search only for vlan devices. for every vlan
		 * found we verify its upper dev list, searching for the
		 * rt->dst.dev. If found we save the tag of the vlan and
		 * proceed to send the packet.
		 *
		 * TODO: QinQ?
		 */
		netdev_for_each_all_upper_dev_rcu(bond->dev, vlan_upper,
						  vlan_iter) {
			if (!is_vlan_dev(vlan_upper))
				continue;
			netdev_for_each_all_upper_dev_rcu(vlan_upper, upper,
							  iter) {
				if (upper == rt->dst.dev) {
					vlan_id = vlan_dev_vlan_id(vlan_upper);
					rcu_read_unlock();
					goto found;
				}
			}
		}

		/* if the device we're looking for is not on top of any of
		 * our upper vlans, then just search for any dev that
		 * matches, and in case it's a vlan - save the id
		 */
		netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
			if (upper == rt->dst.dev) {
				/* if it's a vlan - get its VID */
				if (is_vlan_dev(upper))
					vlan_id = vlan_dev_vlan_id(upper);

				rcu_read_unlock();
				goto found;
			}
		}
		rcu_read_unlock();

		/* Not our device - skip */
		pr_debug("%s: no path to arp_ip_target %pI4 via rt.dev %s\n",
			 bond->dev->name, &targets[i],
			 rt->dst.dev ? rt->dst.dev->name : "NULL");

		ip_rt_put(rt);
		continue;

found:
		addr = bond_confirm_addr(rt->dst.dev, targets[i], 0);
		ip_rt_put(rt);
		bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
			      addr, vlan_id);
	}
}

static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip)
{
	int i;

	if (!sip || !bond_has_this_ip(bond, tip)) {
		pr_debug("bva: sip %pI4 tip %pI4 not found\n", &sip, &tip);
		return;
	}

	i = bond_get_targets_ip(bond->params.arp_targets, sip);
	if (i == -1) {
		pr_debug("bva: sip %pI4 not found in targets\n", &sip);
		return;
	}
	slave->last_arp_rx = jiffies;
	slave->target_last_arp_rx[i] = jiffies;
}

int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
		 struct slave *slave)
{
	struct arphdr *arp = (struct arphdr *)skb->data;
	unsigned char *arp_ptr;
	__be32 sip, tip;
	int alen;

	if (skb->protocol != __cpu_to_be16(ETH_P_ARP))
		return RX_HANDLER_ANOTHER;

	read_lock(&bond->lock);

	if (!slave_do_arp_validate(bond, slave))
		goto out_unlock;

	alen = arp_hdr_len(bond->dev);

	pr_debug("bond_arp_rcv: bond %s skb->dev %s\n",
		 bond->dev->name, skb->dev->name);

	if (alen > skb_headlen(skb)) {
		arp = kmalloc(alen, GFP_ATOMIC);
		if (!arp)
			goto out_unlock;
		if (skb_copy_bits(skb, 0, arp, alen) < 0)
			goto out_unlock;
	}

	if (arp->ar_hln != bond->dev->addr_len ||
	    skb->pkt_type == PACKET_OTHERHOST ||
	    skb->pkt_type == PACKET_LOOPBACK ||
	    arp->ar_hrd != htons(ARPHRD_ETHER) ||
	    arp->ar_pro != htons(ETH_P_IP) ||
	    arp->ar_pln != 4)
		goto out_unlock;

	arp_ptr = (unsigned char *)(arp + 1);
	arp_ptr += bond->dev->addr_len;
	memcpy(&sip, arp_ptr, 4);
	arp_ptr += 4 + bond->dev->addr_len;
	memcpy(&tip, arp_ptr, 4);

	pr_debug("bond_arp_rcv: %s %s/%d av %d sv %d sip %pI4 tip %pI4\n",
		 bond->dev->name, slave->dev->name, bond_slave_state(slave),
		 bond->params.arp_validate, slave_do_arp_validate(bond, slave),
		 &sip, &tip);

	/*
	 * Backup slaves won't see the ARP reply, but do come through
	 * here for each ARP probe (so we swap the sip/tip to validate
	 * the probe).  In a "redundant switch, common router" type of
	 * configuration, the ARP probe will (hopefully) travel from
	 * the active, through one switch, the router, then the other
	 * switch before reaching the backup.
	 *
	 * We 'trust' the arp requests if there is an active slave and
	 * it received valid arp reply(s) after it became active. This
	 * is done to avoid endless looping when we can't reach the
	 * arp_ip_target and fool ourselves with our own arp requests.
	 */
	if (bond_is_active_slave(slave))
		bond_validate_arp(bond, slave, sip, tip);
	else if (bond->curr_active_slave &&
		 time_after(slave_last_rx(bond, bond->curr_active_slave),
			    bond->curr_active_slave->jiffies))
		bond_validate_arp(bond, slave, tip, sip);

out_unlock:
	read_unlock(&bond->lock);
	if (arp != (struct arphdr *)skb->data)
		kfree(arp);
	return RX_HANDLER_ANOTHER;
}

/* function to verify if we're in the arp_interval timeslice, returns true if
 * (last_act - arp_interval) <= jiffies <= (last_act + mod * arp_interval +
 * arp_interval/2) . the arp_interval/2 is needed for really fast networks.
 */
static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
				  int mod)
{
	int delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);

	return time_in_range(jiffies,
			     last_act - delta_in_ticks,
			     last_act + mod * delta_in_ticks + delta_in_ticks/2);
}

/*
 * this function is called regularly to monitor each slave's link
 * ensuring that traffic is being sent and received when arp monitoring
 * is used in load-balancing mode. if the adapter has been dormant, then an
 * arp is transmitted to generate traffic. see activebackup_arp_monitor for
 * arp monitoring in active backup mode.
 */
static void bond_loadbalance_arp_mon(struct work_struct *work)
{
	struct bonding *bond = container_of(work, struct bonding,
					    arp_work.work);
	struct slave *slave, *oldcurrent;
	struct list_head *iter;
	int do_failover = 0, slave_state_changed = 0;

	if (!bond_has_slaves(bond))
		goto re_arm;

	rcu_read_lock();

	oldcurrent = ACCESS_ONCE(bond->curr_active_slave);
	/* see if any of the previous devices are up now (i.e. they have
	 * xmt and rcv traffic). the curr_active_slave does not come into
	 * the picture unless it is null. also, slave->jiffies is not needed
	 * here because we send an arp on each slave and give a slave as
	 * long as it needs to get the tx/rx within the delta.
	 * TODO: what about up/down delay in arp mode? it wasn't here before
	 *       so it can wait
	 */
	bond_for_each_slave_rcu(bond, slave, iter) {
		unsigned long trans_start = dev_trans_start(slave->dev);

		if (slave->link != BOND_LINK_UP) {
			if (bond_time_in_interval(bond, trans_start, 1) &&
			    bond_time_in_interval(bond, slave->dev->last_rx, 1)) {

				slave->link  = BOND_LINK_UP;
				slave_state_changed = 1;

				/* primary_slave has no meaning in round-robin
				 * mode. the window of a slave being up and
				 * curr_active_slave being null after enslaving
				 * is closed.
				 */
				if (!oldcurrent) {
					pr_info("%s: link status definitely up for interface %s, ",
						bond->dev->name,
						slave->dev->name);
					do_failover = 1;
				} else {
					pr_info("%s: interface %s is now up\n",
						bond->dev->name,
						slave->dev->name);
				}
			}
		} else {
			/* slave->link == BOND_LINK_UP */

			/* not all switches will respond to an arp request
			 * when the source ip is 0, so don't take the link down
			 * if we don't know our ip yet
			 */
			if (!bond_time_in_interval(bond, trans_start, 2) ||
			    !bond_time_in_interval(bond, slave->dev->last_rx, 2)) {

				slave->link  = BOND_LINK_DOWN;
				slave_state_changed = 1;

				if (slave->link_failure_count < UINT_MAX)
					slave->link_failure_count++;

				pr_info("%s: interface %s is now down.\n",
					bond->dev->name,
					slave->dev->name);

				if (slave == oldcurrent)
					do_failover = 1;
			}
		}

		/* note: if switch is in round-robin mode, all links
		 * must tx arp to ensure all links rx an arp - otherwise
		 * links may oscillate or not come up at all; if switch is
		 * in something like xor mode, there is nothing we can
		 * do - all replies will be rx'ed on same link causing slaves
		 * to be unstable during low/no traffic periods
		 */
		if (IS_UP(slave->dev))
			bond_arp_send_all(bond, slave);
	}

	rcu_read_unlock();

	if (do_failover || slave_state_changed) {
		if (!rtnl_trylock())
			goto re_arm;

		if (slave_state_changed) {
			bond_slave_state_change(bond);
		} else if (do_failover) {
			/* the bond_select_active_slave must hold RTNL
			 * and curr_slave_lock for write.
			 */
			block_netpoll_tx();
			write_lock_bh(&bond->curr_slave_lock);

			bond_select_active_slave(bond);

			write_unlock_bh(&bond->curr_slave_lock);
			unblock_netpoll_tx();
		}
		rtnl_unlock();
	}

re_arm:
	if (bond->params.arp_interval)
		queue_delayed_work(bond->wq, &bond->arp_work,
				   msecs_to_jiffies(bond->params.arp_interval));
}

/*
 * Called to inspect slaves for active-backup mode ARP monitor link state
 * changes.  Sets new_link in slaves to specify what action should take
 * place for the slave.  Returns 0 if no changes are found, >0 if changes
 * to link states must be committed.
 *
 * Called with rcu_read_lock hold.
 */
static int bond_ab_arp_inspect(struct bonding *bond)
{
	unsigned long trans_start, last_rx;
	struct list_head *iter;
	struct slave *slave;
	int commit = 0;

	bond_for_each_slave_rcu(bond, slave, iter) {
		slave->new_link = BOND_LINK_NOCHANGE;
		last_rx = slave_last_rx(bond, slave);

		if (slave->link != BOND_LINK_UP) {
			if (bond_time_in_interval(bond, last_rx, 1)) {
				slave->new_link = BOND_LINK_UP;
				commit++;
			}
			continue;
		}

		/*
		 * Give slaves 2*delta after being enslaved or made
		 * active.  This avoids bouncing, as the last receive
		 * times need a full ARP monitor cycle to be updated.
		 */
		if (bond_time_in_interval(bond, slave->jiffies, 2))
			continue;

		/*
		 * Backup slave is down if:
		 * - No current_arp_slave AND
		 * - more than 3*delta since last receive AND
		 * - the bond has an IP address
		 *
		 * Note: a non-null current_arp_slave indicates
		 * the curr_active_slave went down and we are
		 * searching for a new one; under this condition
		 * we only take the curr_active_slave down - this
		 * gives each slave a chance to tx/rx traffic
		 * before being taken out
		 */
		if (!bond_is_active_slave(slave) &&
		    !bond->current_arp_slave &&
		    !bond_time_in_interval(bond, last_rx, 3)) {
			slave->new_link = BOND_LINK_DOWN;
			commit++;
		}

		/*
		 * Active slave is down if:
		 * - more than 2*delta since transmitting OR
		 * - (more than 2*delta since receive AND
		 *    the bond has an IP address)
		 */
		trans_start = dev_trans_start(slave->dev);
		if (bond_is_active_slave(slave) &&
		    (!bond_time_in_interval(bond, trans_start, 2) ||
		     !bond_time_in_interval(bond, last_rx, 2))) {
			slave->new_link = BOND_LINK_DOWN;
			commit++;
		}
	}

	return commit;
}

/*
 * Called to commit link state changes noted by inspection step of
 * active-backup mode ARP monitor.
 *
 * Called with RTNL hold.
 */
static void bond_ab_arp_commit(struct bonding *bond)
{
	unsigned long trans_start;
	struct list_head *iter;
	struct slave *slave;

	bond_for_each_slave(bond, slave, iter) {
		switch (slave->new_link) {
		case BOND_LINK_NOCHANGE:
			continue;

		case BOND_LINK_UP:
			trans_start = dev_trans_start(slave->dev);
			if (bond->curr_active_slave != slave ||
			    (!bond->curr_active_slave &&
			     bond_time_in_interval(bond, trans_start, 1))) {
				slave->link = BOND_LINK_UP;
				if (bond->current_arp_slave) {
					bond_set_slave_inactive_flags(
						bond->current_arp_slave);
					bond->current_arp_slave = NULL;
				}

				pr_info("%s: link status definitely up for interface %s.\n",
					bond->dev->name, slave->dev->name);

				if (!bond->curr_active_slave ||
				    (slave == bond->primary_slave))
					goto do_failover;

			}

			continue;

		case BOND_LINK_DOWN:
			if (slave->link_failure_count < UINT_MAX)
				slave->link_failure_count++;

			slave->link = BOND_LINK_DOWN;
			bond_set_slave_inactive_flags(slave);

			pr_info("%s: link status definitely down for interface %s, disabling it\n",
				bond->dev->name, slave->dev->name);

			if (slave == bond->curr_active_slave) {
				bond->current_arp_slave = NULL;
				goto do_failover;
			}

			continue;

		default:
			pr_err("%s: impossible: new_link %d on slave %s\n",
			       bond->dev->name, slave->new_link,
			       slave->dev->name);
			continue;
		}

do_failover:
		ASSERT_RTNL();
		block_netpoll_tx();
		write_lock_bh(&bond->curr_slave_lock);
		bond_select_active_slave(bond);
		write_unlock_bh(&bond->curr_slave_lock);
		unblock_netpoll_tx();
	}

	bond_set_carrier(bond);
}

/*
 * Send ARP probes for active-backup mode ARP monitor.
 */
static bool bond_ab_arp_probe(struct bonding *bond)
{
	struct slave *slave, *before = NULL, *new_slave = NULL,
		     *curr_arp_slave, *curr_active_slave;
	struct list_head *iter;
	bool found = false;

	rcu_read_lock();
	curr_arp_slave = rcu_dereference(bond->current_arp_slave);
	curr_active_slave = rcu_dereference(bond->curr_active_slave);

	if (curr_arp_slave && curr_active_slave)
		pr_info("PROBE: c_arp %s && cas %s BAD\n",
			curr_arp_slave->dev->name,
			curr_active_slave->dev->name);

	if (curr_active_slave) {
		bond_arp_send_all(bond, curr_active_slave);
		rcu_read_unlock();
		return true;
	}
	rcu_read_unlock();

	/* if we don't have a curr_active_slave, search for the next available
	 * backup slave from the current_arp_slave and make it the candidate
	 * for becoming the curr_active_slave
	 */

	if (!rtnl_trylock())
		return false;
	/* curr_arp_slave might have gone away */
	curr_arp_slave = ACCESS_ONCE(bond->current_arp_slave);

	if (!curr_arp_slave) {
		curr_arp_slave = bond_first_slave(bond);
		if (!curr_arp_slave) {
			rtnl_unlock();
			return true;
		}
	}

	bond_set_slave_inactive_flags(curr_arp_slave);

	bond_for_each_slave(bond, slave, iter) {
		if (!found && !before && IS_UP(slave->dev))
			before = slave;

		if (found && !new_slave && IS_UP(slave->dev))
			new_slave = slave;
		/* if the link state is up at this point, we
		 * mark it down - this can happen if we have
		 * simultaneous link failures and
		 * reselect_active_interface doesn't make this
		 * one the current slave so it is still marked
		 * up when it is actually down
		 */
		if (!IS_UP(slave->dev) && slave->link == BOND_LINK_UP) {
			slave->link = BOND_LINK_DOWN;
			if (slave->link_failure_count < UINT_MAX)
				slave->link_failure_count++;

			bond_set_slave_inactive_flags(slave);

			pr_info("%s: backup interface %s is now down.\n",
				bond->dev->name, slave->dev->name);
		}
		if (slave == curr_arp_slave)
			found = true;
	}

	if (!new_slave && before)
		new_slave = before;

	if (!new_slave) {
		rtnl_unlock();
		return true;
	}

	new_slave->link = BOND_LINK_BACK;
	bond_set_slave_active_flags(new_slave);
	bond_arp_send_all(bond, new_slave);
	new_slave->jiffies = jiffies;
	rcu_assign_pointer(bond->current_arp_slave, new_slave);
	rtnl_unlock();

	return true;
}

static void bond_activebackup_arp_mon(struct work_struct *work)
{
	struct bonding *bond = container_of(work, struct bonding,
					    arp_work.work);
	bool should_notify_peers = false, should_commit = false;
	int delta_in_ticks;

	delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);

	if (!bond_has_slaves(bond))
		goto re_arm;

	rcu_read_lock();
	should_notify_peers = bond_should_notify_peers(bond);
	should_commit = bond_ab_arp_inspect(bond);
	rcu_read_unlock();

	if (should_commit) {
		/* Race avoidance with bond_close flush of workqueue */
		if (!rtnl_trylock()) {
			delta_in_ticks = 1;
			should_notify_peers = false;
			goto re_arm;
		}

		bond_ab_arp_commit(bond);
		rtnl_unlock();
	}

	if (!bond_ab_arp_probe(bond)) {
		/* rtnl locking failed, re-arm */
		delta_in_ticks = 1;
		should_notify_peers = false;
	}

re_arm:
	if (bond->params.arp_interval)
		queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);

	if (should_notify_peers) {
		if (!rtnl_trylock())
			return;
		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
		rtnl_unlock();
	}
}

/*-------------------------- netdev event handling --------------------------*/

/*
 * Change device name
 */
static int bond_event_changename(struct bonding *bond)
{
	bond_remove_proc_entry(bond);
	bond_create_proc_entry(bond);

	bond_debug_reregister(bond);

	return NOTIFY_DONE;
}

static int bond_master_netdev_event(unsigned long event,
				    struct net_device *bond_dev)
{
	struct bonding *event_bond = netdev_priv(bond_dev);

	switch (event) {
	case NETDEV_CHANGENAME:
		return bond_event_changename(event_bond);
	case NETDEV_UNREGISTER:
		bond_remove_proc_entry(event_bond);
		break;
	case NETDEV_REGISTER:
		bond_create_proc_entry(event_bond);
		break;
	case NETDEV_NOTIFY_PEERS:
		if (event_bond->send_peer_notif)
			event_bond->send_peer_notif--;
		break;
	default:
		break;
	}

	return NOTIFY_DONE;
}

static int bond_slave_netdev_event(unsigned long event,
				   struct net_device *slave_dev)
{
	struct slave *slave = bond_slave_get_rtnl(slave_dev);
	struct bonding *bond;
	struct net_device *bond_dev;
	u32 old_speed;
	u8 old_duplex;

	/* A netdev event can be generated while enslaving a device
	 * before netdev_rx_handler_register is called in which case
	 * slave will be NULL
	 */
	if (!slave)
		return NOTIFY_DONE;
	bond_dev = slave->bond->dev;
	bond = slave->bond;

	switch (event) {
	case NETDEV_UNREGISTER:
		if (bond_dev->type != ARPHRD_ETHER)
			bond_release_and_destroy(bond_dev, slave_dev);
		else
			bond_release(bond_dev, slave_dev);
		break;
	case NETDEV_UP:
	case NETDEV_CHANGE:
		old_speed = slave->speed;
		old_duplex = slave->duplex;

		bond_update_speed_duplex(slave);

		if (bond->params.mode == BOND_MODE_8023AD) {
			if (old_speed != slave->speed)
				bond_3ad_adapter_speed_changed(slave);
			if (old_duplex != slave->duplex)
				bond_3ad_adapter_duplex_changed(slave);
		}
		break;
	case NETDEV_DOWN:
		/*
		 * ... Or is it this?
		 */
		break;
	case NETDEV_CHANGEMTU:
		/*
		 * TODO: Should slaves be allowed to
		 * independently alter their MTU?  For
		 * an active-backup bond, slaves need
		 * not be the same type of device, so
		 * MTUs may vary.  For other modes,
		 * slaves arguably should have the
		 * same MTUs. To do this, we'd need to
		 * take over the slave's change_mtu
		 * function for the duration of their
		 * servitude.
		 */
		break;
	case NETDEV_CHANGENAME:
		/* we don't care if we don't have primary set */
		if (!USES_PRIMARY(bond->params.mode) ||
		    !bond->params.primary[0])
			break;

		if (slave == bond->primary_slave) {
			/* slave's name changed - he's no longer primary */
			bond->primary_slave = NULL;
		} else if (!strcmp(slave_dev->name, bond->params.primary)) {
			/* we have a new primary slave */
			bond->primary_slave = slave;
		} else { /* we didn't change primary - exit */
			break;
		}

		pr_info("%s: Primary slave changed to %s, reselecting active slave.\n",
			bond->dev->name, bond->primary_slave ? slave_dev->name :
							       "none");
		write_lock_bh(&bond->curr_slave_lock);
		bond_select_active_slave(bond);
		write_unlock_bh(&bond->curr_slave_lock);
		break;
	case NETDEV_FEAT_CHANGE:
		bond_compute_features(bond);
		break;
	case NETDEV_RESEND_IGMP:
		/* Propagate to master device */
		call_netdevice_notifiers(event, slave->bond->dev);
		break;
	default:
		break;
	}

	return NOTIFY_DONE;
}

/*
 * bond_netdev_event: handle netdev notifier chain events.
 *
 * This function receives events for the netdev chain.  The caller (an
 * ioctl handler calling blocking_notifier_call_chain) holds the necessary
 * locks for us to safely manipulate the slave devices (RTNL lock,
 * dev_probe_lock).
 */
static int bond_netdev_event(struct notifier_block *this,
			     unsigned long event, void *ptr)
{
	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);

	pr_debug("event_dev: %s, event: %lx\n",
		 event_dev ? event_dev->name : "None",
		 event);

	if (!(event_dev->priv_flags & IFF_BONDING))
		return NOTIFY_DONE;

	if (event_dev->flags & IFF_MASTER) {
		pr_debug("IFF_MASTER\n");
		return bond_master_netdev_event(event, event_dev);
	}

	if (event_dev->flags & IFF_SLAVE) {
		pr_debug("IFF_SLAVE\n");
		return bond_slave_netdev_event(event, event_dev);
	}

	return NOTIFY_DONE;
}

static struct notifier_block bond_netdev_notifier = {
	.notifier_call = bond_netdev_event,
};

/*---------------------------- Hashing Policies -----------------------------*/

/* L2 hash helper */
static inline u32 bond_eth_hash(struct sk_buff *skb)
{
	struct ethhdr *data = (struct ethhdr *)skb->data;

	if (skb_headlen(skb) >= offsetof(struct ethhdr, h_proto))
		return data->h_dest[5] ^ data->h_source[5];

	return 0;
}

/* Extract the appropriate headers based on bond's xmit policy */
static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
			      struct flow_keys *fk)
{
	const struct ipv6hdr *iph6;
	const struct iphdr *iph;
	int noff, proto = -1;

	if (bond->params.xmit_policy > BOND_XMIT_POLICY_LAYER23)
		return skb_flow_dissect(skb, fk);

	fk->ports = 0;
	noff = skb_network_offset(skb);
	if (skb->protocol == htons(ETH_P_IP)) {
		if (!pskb_may_pull(skb, noff + sizeof(*iph)))
			return false;
		iph = ip_hdr(skb);
		fk->src = iph->saddr;
		fk->dst = iph->daddr;
		noff += iph->ihl << 2;
		if (!ip_is_fragment(iph))
			proto = iph->protocol;
	} else if (skb->protocol == htons(ETH_P_IPV6)) {
		if (!pskb_may_pull(skb, noff + sizeof(*iph6)))
			return false;
		iph6 = ipv6_hdr(skb);
		fk->src = (__force __be32)ipv6_addr_hash(&iph6->saddr);
		fk->dst = (__force __be32)ipv6_addr_hash(&iph6->daddr);
		noff += sizeof(*iph6);
		proto = iph6->nexthdr;
	} else {
		return false;
	}
	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34 && proto >= 0)
		fk->ports = skb_flow_get_ports(skb, noff, proto);

	return true;
}

/**
 * bond_xmit_hash - generate a hash value based on the xmit policy
 * @bond: bonding device
 * @skb: buffer to use for headers
 * @count: modulo value
 *
 * This function will extract the necessary headers from the skb buffer and use
 * them to generate a hash based on the xmit_policy set in the bonding device
 * which will be reduced modulo count before returning.
 */
int bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, int count)
{
	struct flow_keys flow;
	u32 hash;

	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 ||
	    !bond_flow_dissect(bond, skb, &flow))
		return bond_eth_hash(skb) % count;

	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 ||
	    bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23)
		hash = bond_eth_hash(skb);
	else
		hash = (__force u32)flow.ports;
	hash ^= (__force u32)flow.dst ^ (__force u32)flow.src;
	hash ^= (hash >> 16);
	hash ^= (hash >> 8);

	return hash % count;
}

/*-------------------------- Device entry points ----------------------------*/

static void bond_work_init_all(struct bonding *bond)
{
	INIT_DELAYED_WORK(&bond->mcast_work,
			  bond_resend_igmp_join_requests_delayed);
	INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor);
	INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor);
	if (bond->params.mode == BOND_MODE_ACTIVEBACKUP)
		INIT_DELAYED_WORK(&bond->arp_work, bond_activebackup_arp_mon);
	else
		INIT_DELAYED_WORK(&bond->arp_work, bond_loadbalance_arp_mon);
	INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler);
}

static void bond_work_cancel_all(struct bonding *bond)
{
	cancel_delayed_work_sync(&bond->mii_work);
	cancel_delayed_work_sync(&bond->arp_work);
	cancel_delayed_work_sync(&bond->alb_work);
	cancel_delayed_work_sync(&bond->ad_work);
	cancel_delayed_work_sync(&bond->mcast_work);
}

static int bond_open(struct net_device *bond_dev)
{
	struct bonding *bond = netdev_priv(bond_dev);
	struct list_head *iter;
	struct slave *slave;

	/* reset slave->backup and slave->inactive */
	read_lock(&bond->lock);
	if (bond_has_slaves(bond)) {
		read_lock(&bond->curr_slave_lock);
		bond_for_each_slave(bond, slave, iter) {
			if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP)
				&& (slave != bond->curr_active_slave)) {
				bond_set_slave_inactive_flags(slave);
			} else {
				bond_set_slave_active_flags(slave);
			}
		}
		read_unlock(&bond->curr_slave_lock);
	}
	read_unlock(&bond->lock);

	bond_work_init_all(bond);

	if (bond_is_lb(bond)) {
		/* bond_alb_initialize must be called before the timer
		 * is started.
		 */
		if (bond_alb_initialize(bond, (bond->params.mode == BOND_MODE_ALB)))
			return -ENOMEM;
		queue_delayed_work(bond->wq, &bond->alb_work, 0);
	}

	if (bond->params.miimon)  /* link check interval, in milliseconds. */
		queue_delayed_work(bond->wq, &bond->mii_work, 0);

	if (bond->params.arp_interval) {  /* arp interval, in milliseconds. */
		queue_delayed_work(bond->wq, &bond->arp_work, 0);
		if (bond->params.arp_validate)
			bond->recv_probe = bond_arp_rcv;
	}

	if (bond->params.mode == BOND_MODE_8023AD) {
		queue_delayed_work(bond->wq, &bond->ad_work, 0);
		/* register to receive LACPDUs */
		bond->recv_probe = bond_3ad_lacpdu_recv;
		bond_3ad_initiate_agg_selection(bond, 1);
	}

	return 0;
}

static int bond_close(struct net_device *bond_dev)
{
	struct bonding *bond = netdev_priv(bond_dev);

	bond_work_cancel_all(bond);
	bond->send_peer_notif = 0;
	if (bond_is_lb(bond))
		bond_alb_deinitialize(bond);
	bond->recv_probe = NULL;

	return 0;
}

static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
						struct rtnl_link_stats64 *stats)
{
	struct bonding *bond = netdev_priv(bond_dev);
	struct rtnl_link_stats64 temp;
	struct list_head *iter;
	struct slave *slave;

	memset(stats, 0, sizeof(*stats));

	read_lock_bh(&bond->lock);
	bond_for_each_slave(bond, slave, iter) {
		const struct rtnl_link_stats64 *sstats =
			dev_get_stats(slave->dev, &temp);

		stats->rx_packets += sstats->rx_packets;
		stats->rx_bytes += sstats->rx_bytes;
		stats->rx_errors += sstats->rx_errors;
		stats->rx_dropped += sstats->rx_dropped;

		stats->tx_packets += sstats->tx_packets;
		stats->tx_bytes += sstats->tx_bytes;
		stats->tx_errors += sstats->tx_errors;
		stats->tx_dropped += sstats->tx_dropped;

		stats->multicast += sstats->multicast;
		stats->collisions += sstats->collisions;

		stats->rx_length_errors += sstats->rx_length_errors;
		stats->rx_over_errors += sstats->rx_over_errors;
		stats->rx_crc_errors += sstats->rx_crc_errors;
		stats->rx_frame_errors += sstats->rx_frame_errors;
		stats->rx_fifo_errors += sstats->rx_fifo_errors;
		stats->rx_missed_errors += sstats->rx_missed_errors;

		stats->tx_aborted_errors += sstats->tx_aborted_errors;
		stats->tx_carrier_errors += sstats->tx_carrier_errors;
		stats->tx_fifo_errors += sstats->tx_fifo_errors;
		stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors;
		stats->tx_window_errors += sstats->tx_window_errors;
	}
	read_unlock_bh(&bond->lock);

	return stats;
}

static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
{
	struct bonding *bond = netdev_priv(bond_dev);
	struct net_device *slave_dev = NULL;
	struct ifbond k_binfo;
	struct ifbond __user *u_binfo = NULL;
	struct ifslave k_sinfo;
	struct ifslave __user *u_sinfo = NULL;
	struct mii_ioctl_data *mii = NULL;