summaryrefslogtreecommitdiff
path: root/drivers/watchdog/watchdog_dev.c
blob: dbd2ad4c929481fa95fcbbb03a713c81704a5305 (plain)
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
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
// SPDX-License-Identifier: GPL-2.0+
/*
 *	watchdog_dev.c
 *
 *	(c) Copyright 2008-2011 Alan Cox <alan@lxorguk.ukuu.org.uk>,
 *						All Rights Reserved.
 *
 *	(c) Copyright 2008-2011 Wim Van Sebroeck <wim@iguana.be>.
 *
 *
 *	This source code is part of the generic code that can be used
 *	by all the watchdog timer drivers.
 *
 *	This part of the generic code takes care of the following
 *	misc device: /dev/watchdog.
 *
 *	Based on source code of the following authors:
 *	  Matt Domsch <Matt_Domsch@dell.com>,
 *	  Rob Radez <rob@osinvestor.com>,
 *	  Rusty Lynch <rusty@linux.co.intel.com>
 *	  Satyam Sharma <satyam@infradead.org>
 *	  Randy Dunlap <randy.dunlap@oracle.com>
 *
 *	Neither Alan Cox, CymruNet Ltd., Wim Van Sebroeck nor Iguana vzw.
 *	admit liability nor provide warranty for any of this software.
 *	This material is provided "AS-IS" and at no charge.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/cdev.h>		/* For character device */
#include <linux/errno.h>	/* For the -ENODEV/... values */
#include <linux/fs.h>		/* For file operations */
#include <linux/init.h>		/* For __init/__exit/... */
#include <linux/hrtimer.h>	/* For hrtimers */
#include <linux/kernel.h>	/* For printk/panic/... */
#include <linux/kref.h>		/* For data references */
#include <linux/kthread.h>	/* For kthread_work */
#include <linux/miscdevice.h>	/* For handling misc devices */
#include <linux/module.h>	/* For module stuff/... */
#include <linux/mutex.h>	/* For mutexes */
#include <linux/reboot.h>	/* For reboot notifier */
#include <linux/slab.h>		/* For memory functions */
#include <linux/types.h>	/* For standard types (like size_t) */
#include <linux/watchdog.h>	/* For watchdog specific items */
#include <linux/uaccess.h>	/* For copy_to_user/put_user/... */

#include <uapi/linux/sched/types.h>	/* For struct sched_param */

#include "watchdog_core.h"
#include "watchdog_pretimeout.h"

/*
 * struct watchdog_core_data - watchdog core internal data
 * @kref:	Reference count.
 * @cdev:	The watchdog's Character device.
 * @wdd:	Pointer to watchdog device.
 * @lock:	Lock for watchdog core.
 * @status:	Watchdog core internal status bits.
 */
struct watchdog_core_data {
	struct kref kref;
	struct cdev cdev;
	struct watchdog_device *wdd;
	struct mutex lock;
	ktime_t last_keepalive;
	ktime_t last_hw_keepalive;
	ktime_t open_deadline;
	struct hrtimer timer;
	struct kthread_work work;
	unsigned long status;		/* Internal status bits */
#define _WDOG_DEV_OPEN		0	/* Opened ? */
#define _WDOG_ALLOW_RELEASE	1	/* Did we receive the magic char ? */
#define _WDOG_KEEPALIVE		2	/* Did we receive a keepalive ? */
};

/* the dev_t structure to store the dynamically allocated watchdog devices */
static dev_t watchdog_devt;
/* Reference to watchdog device behind /dev/watchdog */
static struct watchdog_core_data *old_wd_data;

static struct kthread_worker *watchdog_kworker;

static bool handle_boot_enabled =
	IS_ENABLED(CONFIG_WATCHDOG_HANDLE_BOOT_ENABLED);

static unsigned open_timeout = CONFIG_WATCHDOG_OPEN_TIMEOUT;

static bool watchdog_past_open_deadline(struct watchdog_core_data *data)
{
	return ktime_after(ktime_get(), data->open_deadline);
}

static void watchdog_set_open_deadline(struct watchdog_core_data *data)
{
	data->open_deadline = open_timeout ?
		ktime_get() + ktime_set(open_timeout, 0) : KTIME_MAX;
}

static inline bool watchdog_need_worker(struct watchdog_device *wdd)
{
	/* All variables in milli-seconds */
	unsigned int hm = wdd->max_hw_heartbeat_ms;
	unsigned int t = wdd->timeout * 1000;

	/*
	 * A worker to generate heartbeat requests is needed if all of the
	 * following conditions are true.
	 * - Userspace activated the watchdog.
	 * - The driver provided a value for the maximum hardware timeout, and
	 *   thus is aware that the framework supports generating heartbeat
	 *   requests.
	 * - Userspace requests a longer timeout than the hardware can handle.
	 *
	 * Alternatively, if userspace has not opened the watchdog
	 * device, we take care of feeding the watchdog if it is
	 * running.
	 */
	return (hm && watchdog_active(wdd) && t > hm) ||
		(t && !watchdog_active(wdd) && watchdog_hw_running(wdd));
}

static ktime_t watchdog_next_keepalive(struct watchdog_device *wdd)
{
	struct watchdog_core_data *wd_data = wdd->wd_data;
	unsigned int timeout_ms = wdd->timeout * 1000;
	ktime_t keepalive_interval;
	ktime_t last_heartbeat, latest_heartbeat;
	ktime_t virt_timeout;
	unsigned int hw_heartbeat_ms;

	if (watchdog_active(wdd))
		virt_timeout = ktime_add(wd_data->last_keepalive,
					 ms_to_ktime(timeout_ms));
	else
		virt_timeout = wd_data->open_deadline;

	hw_heartbeat_ms = min_not_zero(timeout_ms, wdd->max_hw_heartbeat_ms);
	keepalive_interval = ms_to_ktime(hw_heartbeat_ms / 2);

	/*
	 * To ensure that the watchdog times out wdd->timeout seconds
	 * after the most recent ping from userspace, the last
	 * worker ping has to come in hw_heartbeat_ms before this timeout.
	 */
	last_heartbeat = ktime_sub(virt_timeout, ms_to_ktime(hw_heartbeat_ms));
	latest_heartbeat = ktime_sub(last_heartbeat, ktime_get());
	if (ktime_before(latest_heartbeat, keepalive_interval))
		return latest_heartbeat;
	return keepalive_interval;
}

static inline void watchdog_update_worker(struct watchdog_device *wdd)
{
	struct watchdog_core_data *wd_data = wdd->wd_data;

	if (watchdog_need_worker(wdd)) {
		ktime_t t = watchdog_next_keepalive(wdd);

		if (t > 0)
			hrtimer_start(&wd_data->timer, t, HRTIMER_MODE_REL);
	} else {
		hrtimer_cancel(&wd_data->timer);
	}
}

static int __watchdog_ping(struct watchdog_device *wdd)
{
	struct watchdog_core_data *wd_data = wdd->wd_data;
	ktime_t earliest_keepalive, now;
	int err;

	earliest_keepalive = ktime_add(wd_data->last_hw_keepalive,
				       ms_to_ktime(wdd->min_hw_heartbeat_ms));
	now = ktime_get();

	if (ktime_after(earliest_keepalive, now)) {
		hrtimer_start(&wd_data->timer,
			      ktime_sub(earliest_keepalive, now),
			      HRTIMER_MODE_REL);
		return 0;
	}

	wd_data->last_hw_keepalive = now;

	if (wdd->ops->ping)
		err = wdd->ops->ping(wdd);  /* ping the watchdog */
	else
		err = wdd->ops->start(wdd); /* restart watchdog */

	watchdog_update_worker(wdd);

	return err;
}

/*
 *	watchdog_ping: ping the watchdog.
 *	@wdd: the watchdog device to ping
 *
 *	The caller must hold wd_data->lock.
 *
 *	If the watchdog has no own ping operation then it needs to be
 *	restarted via the start operation. This wrapper function does
 *	exactly that.
 *	We only ping when the watchdog device is running.
 */

static int watchdog_ping(struct watchdog_device *wdd)
{
	struct watchdog_core_data *wd_data = wdd->wd_data;

	if (!watchdog_active(wdd) && !watchdog_hw_running(wdd))
		return 0;

	set_bit(_WDOG_KEEPALIVE, &wd_data->status);

	wd_data->last_keepalive = ktime_get();
	return __watchdog_ping(wdd);
}

static bool watchdog_worker_should_ping(struct watchdog_core_data *wd_data)
{
	struct watchdog_device *wdd = wd_data->wdd;

	if (!wdd)
		return false;

	if (watchdog_active(wdd))
		return true;

	return watchdog_hw_running(wdd) && !watchdog_past_open_deadline(wd_data);
}

static void watchdog_ping_work(struct kthread_work *work)
{
	struct watchdog_core_data *wd_data;

	wd_data = container_of(work, struct watchdog_core_data, work);

	mutex_lock(&wd_data->lock);
	if (watchdog_worker_should_ping(wd_data))
		__watchdog_ping(wd_data->wdd);
	mutex_unlock(&wd_data->lock);
}

static enum hrtimer_restart watchdog_timer_expired(struct hrtimer *timer)
{
	struct watchdog_core_data *wd_data;

	wd_data = container_of(timer, struct watchdog_core_data, timer);

	kthread_queue_work(watchdog_kworker, &wd_data->work);
	return HRTIMER_NORESTART;
}

/*
 *	watchdog_start: wrapper to start the watchdog.
 *	@wdd: the watchdog device to start
 *
 *	The caller must hold wd_data->lock.
 *
 *	Start the watchdog if it is not active and mark it active.
 *	This function returns zero on success or a negative errno code for
 *	failure.
 */

static int watchdog_start(struct watchdog_device *wdd)
{
	struct watchdog_core_data *wd_data = wdd->wd_data;
	ktime_t started_at;
	int err;

	if (watchdog_active(wdd))
		return 0;

	set_bit(_WDOG_KEEPALIVE, &wd_data->status);

	started_at = ktime_get();
	if (watchdog_hw_running(wdd) && wdd->ops->ping)
		err = wdd->ops->ping(wdd);
	else
		err = wdd->ops->start(wdd);
	if (err == 0) {
		set_bit(WDOG_ACTIVE, &wdd->status);
		wd_data->last_keepalive = started_at;
		watchdog_update_worker(wdd);
	}

	return err;
}

/*
 *	watchdog_stop: wrapper to stop the watchdog.
 *	@wdd: the watchdog device to stop
 *
 *	The caller must hold wd_data->lock.
 *
 *	Stop the watchdog if it is still active and unmark it active.
 *	This function returns zero on success or a negative errno code for
 *	failure.
 *	If the 'nowayout' feature was set, the watchdog cannot be stopped.
 */

static int watchdog_stop(struct watchdog_device *wdd)
{
	int err = 0;

	if (!watchdog_active(wdd))
		return 0;

	if (test_bit(WDOG_NO_WAY_OUT, &wdd->status)) {
		pr_info("watchdog%d: nowayout prevents watchdog being stopped!\n",
			wdd->id);
		return -EBUSY;
	}

	if (wdd->ops->stop) {
		clear_bit(WDOG_HW_RUNNING, &wdd->status);
		err = wdd->ops->stop(wdd);
	} else {
		set_bit(WDOG_HW_RUNNING, &wdd->status);
	}

	if (err == 0) {
		clear_bit(WDOG_ACTIVE, &wdd->status);
		watchdog_update_worker(wdd);
	}

	return err;
}

/*
 *	watchdog_get_status: wrapper to get the watchdog status
 *	@wdd: the watchdog device to get the status from
 *
 *	The caller must hold wd_data->lock.
 *
 *	Get the watchdog's status flags.
 */

static unsigned int watchdog_get_status(struct watchdog_device *wdd)
{
	struct watchdog_core_data *wd_data = wdd->wd_data;
	unsigned int status;

	if (wdd->ops->status)
		status = wdd->ops->status(wdd);
	else
		status = wdd->bootstatus & (WDIOF_CARDRESET |
					    WDIOF_OVERHEAT |
					    WDIOF_FANFAULT |
					    WDIOF_EXTERN1 |
					    WDIOF_EXTERN2 |
					    WDIOF_POWERUNDER |
					    WDIOF_POWEROVER);

	if (test_bit(_WDOG_ALLOW_RELEASE, &wd_data->status))
		status |= WDIOF_MAGICCLOSE;

	if (test_and_clear_bit(_WDOG_KEEPALIVE, &wd_data->status))
		status |= WDIOF_KEEPALIVEPING;

	return status;
}

/*
 *	watchdog_set_timeout: set the watchdog timer timeout
 *	@wdd: the watchdog device to set the timeout for
 *	@timeout: timeout to set in seconds
 *
 *	The caller must hold wd_data->lock.
 */

static int watchdog_set_timeout(struct watchdog_device *wdd,
							unsigned int timeout)
{
	int err = 0;

	if (!(wdd->info->options & WDIOF_SETTIMEOUT))
		return -EOPNOTSUPP;

	if (watchdog_timeout_invalid(wdd, timeout))
		return -EINVAL;

	if (wdd->ops->set_timeout) {
		err = wdd->ops->set_timeout(wdd, timeout);
	} else {
		wdd->timeout = timeout;
		/* Disable pretimeout if it doesn't fit the new timeout */
		if (wdd->pretimeout >= wdd->timeout)
			wdd->pretimeout = 0;
	}

	watchdog_update_worker(wdd);

	return err;
}

/*
 *	watchdog_set_pretimeout: set the watchdog timer pretimeout
 *	@wdd: the watchdog device to set the timeout for
 *	@timeout: pretimeout to set in seconds
 */

static int watchdog_set_pretimeout(struct watchdog_device *wdd,
				   unsigned int timeout)
{
	int err = 0;

	if (!(wdd->info->options & WDIOF_PRETIMEOUT))
		return -EOPNOTSUPP;

	if (watchdog_pretimeout_invalid(wdd, timeout))
		return -EINVAL;

	if (wdd->ops->set_pretimeout)
		err = wdd->ops->set_pretimeout(wdd, timeout);
	else
		wdd->pretimeout = timeout;

	return err;
}

/*
 *	watchdog_get_timeleft: wrapper to get the time left before a reboot
 *	@wdd: the watchdog device to get the remaining time from
 *	@timeleft: the time that's left
 *
 *	The caller must hold wd_data->lock.
 *
 *	Get the time before a watchdog will reboot (if not pinged).
 */

static int watchdog_get_timeleft(struct watchdog_device *wdd,
							unsigned int *timeleft)
{
	*timeleft = 0;

	if (!wdd->ops->get_timeleft)
		return -EOPNOTSUPP;

	*timeleft = wdd->ops->get_timeleft(wdd);

	return 0;
}

#ifdef CONFIG_WATCHDOG_SYSFS
static ssize_t nowayout_show(struct device *dev, struct device_attribute *attr,
				char *buf)
{
	struct watchdog_device *wdd = dev_get_drvdata(dev);

	return sprintf(buf, "%d\n", !!test_bit(WDOG_NO_WAY_OUT, &wdd->status));
}
static DEVICE_ATTR_RO(nowayout);

static ssize_t status_show(struct device *dev, struct device_attribute *attr,
				char *buf)
{
	struct watchdog_device *wdd = dev_get_drvdata(dev);
	struct watchdog_core_data *wd_data = wdd->wd_data;
	unsigned int status;

	mutex_lock(&wd_data->lock);
	status = watchdog_get_status(wdd);
	mutex_unlock(&wd_data->lock);

	return sprintf(buf, "0x%x\n", status);
}
static DEVICE_ATTR_RO(status);

static ssize_t bootstatus_show(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	struct watchdog_device *wdd = dev_get_drvdata(dev);

	return sprintf(buf, "%u\n", wdd->bootstatus);
}
static DEVICE_ATTR_RO(bootstatus);

static ssize_t timeleft_show(struct device *dev, struct device_attribute *attr,
				char *buf)
{
	struct watchdog_device *wdd = dev_get_drvdata(dev);
	struct watchdog_core_data *wd_data = wdd->wd_data;
	ssize_t status;
	unsigned int val;

	mutex_lock(&wd_data->lock);
	status = watchdog_get_timeleft(wdd, &val);
	mutex_unlock(&wd_data->lock);
	if (!status)
		status = sprintf(buf, "%u\n", val);

	return status;
}
static DEVICE_ATTR_RO(timeleft);

static ssize_t timeout_show(struct device *dev, struct device_attribute *attr,
				char *buf)
{
	struct watchdog_device *wdd = dev_get_drvdata(dev);

	return sprintf(buf, "%u\n", wdd->timeout);
}
static DEVICE_ATTR_RO(timeout);

static ssize_t pretimeout_show(struct device *dev,
			       struct device_attribute *attr, char *buf)
{
	struct watchdog_device *wdd = dev_get_drvdata(dev);

	return sprintf(buf, "%u\n", wdd->pretimeout);
}
static DEVICE_ATTR_RO(pretimeout);

static ssize_t identity_show(struct device *dev, struct device_attribute *attr,
				char *buf)
{
	struct watchdog_device *wdd = dev_get_drvdata(dev);

	return sprintf(buf, "%s\n", wdd->info->identity);
}
static DEVICE_ATTR_RO(identity);

static ssize_t state_show(struct device *dev, struct device_attribute *attr,
				char *buf)
{
	struct watchdog_device *wdd = dev_get_drvdata(dev);

	if (watchdog_active(wdd))
		return sprintf(buf, "active\n");

	return sprintf(buf, "inactive\n");
}
static DEVICE_ATTR_RO(state);

static ssize_t pretimeout_available_governors_show(struct device *dev,
				   struct device_attribute *attr, char *buf)
{
	return watchdog_pretimeout_available_governors_get(buf);
}
static DEVICE_ATTR_RO(pretimeout_available_governors);

static ssize_t pretimeout_governor_show(struct device *dev,
					struct device_attribute *attr,
					char *buf)
{
	struct watchdog_device *wdd = dev_get_drvdata(dev);

	return watchdog_pretimeout_governor_get(wdd, buf);
}

static ssize_t pretimeout_governor_store(struct device *dev,
					 struct device_attribute *attr,
					 const char *buf, size_t count)
{
	struct watchdog_device *wdd = dev_get_drvdata(dev);
	int ret = watchdog_pretimeout_governor_set(wdd, buf);

	if (!ret)
		ret = count;

	return ret;
}
static DEVICE_ATTR_RW(pretimeout_governor);

static umode_t wdt_is_visible(struct kobject *kobj, struct attribute *attr,
				int n)
{
	struct device *dev = container_of(kobj, struct device, kobj);
	struct watchdog_device *wdd = dev_get_drvdata(dev);
	umode_t mode = attr->mode;

	if (attr == &dev_attr_timeleft.attr && !wdd->ops->get_timeleft)
		mode = 0;
	else if (attr == &dev_attr_pretimeout.attr &&
		 !(wdd->info->options & WDIOF_PRETIMEOUT))
		mode = 0;
	else if ((attr == &dev_attr_pretimeout_governor.attr ||
		  attr == &dev_attr_pretimeout_available_governors.attr) &&
		 (!(wdd->info->options & WDIOF_PRETIMEOUT) ||
		  !IS_ENABLED(CONFIG_WATCHDOG_PRETIMEOUT_GOV)))
		mode = 0;

	return mode;
}
static struct attribute *wdt_attrs[] = {
	&dev_attr_state.attr,
	&dev_attr_identity.attr,
	&dev_attr_timeout.attr,
	&dev_attr_pretimeout.attr,
	&dev_attr_timeleft.attr,
	&dev_attr_bootstatus.attr,
	&dev_attr_status.attr,
	&dev_attr_nowayout.attr,
	&dev_attr_pretimeout_governor.attr,
	&dev_attr_pretimeout_available_governors.attr,
	NULL,
};

static const struct attribute_group wdt_group = {
	.attrs = wdt_attrs,
	.is_visible = wdt_is_visible,
};
__ATTRIBUTE_GROUPS(wdt);
#else
#define wdt_groups	NULL
#endif

/*
 *	watchdog_ioctl_op: call the watchdog drivers ioctl op if defined
 *	@wdd: the watchdog device to do the ioctl on
 *	@cmd: watchdog command
 *	@arg: argument pointer
 *
 *	The caller must hold wd_data->lock.
 */

static int watchdog_ioctl_op(struct watchdog_device *wdd, unsigned int cmd,
							unsigned long arg)
{
	if (!wdd->ops->ioctl)
		return -ENOIOCTLCMD;

	return wdd->ops->ioctl(wdd, cmd, arg);
}

/*
 *	watchdog_write: writes to the watchdog.
 *	@file: file from VFS
 *	@data: user address of data
 *	@len: length of data
 *	@ppos: pointer to the file offset
 *
 *	A write to a watchdog device is defined as a keepalive ping.
 *	Writing the magic 'V' sequence allows the next close to turn
 *	off the watchdog (if 'nowayout' is not set).
 */

static ssize_t watchdog_write(struct file *file, const char __user *data,
						size_t len, loff_t *ppos)
{
	struct watchdog_core_data *wd_data = file->private_data;
	struct watchdog_device *wdd;
	int err;
	size_t i;
	char c;

	if (len == 0)
		return 0;

	/*
	 * Note: just in case someone wrote the magic character
	 * five months ago...
	 */
	clear_bit(_WDOG_ALLOW_RELEASE, &wd_data->status);

	/* scan to see whether or not we got the magic character */
	for (i = 0; i != len; i++) {
		if (get_user(c, data + i))
			return -EFAULT;
		if (c == 'V')
			set_bit(_WDOG_ALLOW_RELEASE, &wd_data->status);
	}

	/* someone wrote to us, so we send the watchdog a keepalive ping */

	err = -ENODEV;
	mutex_lock(&wd_data->lock);
	wdd = wd_data->wdd;
	if (wdd)
		err = watchdog_ping(wdd);
	mutex_unlock(&wd_data->lock);

	if (err < 0)
		return err;

	return len;
}

/*
 *	watchdog_ioctl: handle the different ioctl's for the watchdog device.
 *	@file: file handle to the device
 *	@cmd: watchdog command
 *	@arg: argument pointer
 *
 *	The watchdog API defines a common set of functions for all watchdogs
 *	according to their available features.
 */

static long watchdog_ioctl(struct file *file, unsigned int cmd,
							unsigned long arg)
{
	struct watchdog_core_data *wd_data = file->private_data;
	void __user *argp = (void __user *)arg;
	struct watchdog_device *wdd;
	int __user *p = argp;
	unsigned int val;
	int err;

	mutex_lock(&wd_data->lock);

	wdd = wd_data->wdd;
	if (!wdd) {
		err = -ENODEV;
		goto out_ioctl;
	}

	err = watchdog_ioctl_op(wdd, cmd, arg);
	if (err != -ENOIOCTLCMD)
		goto out_ioctl;

	switch (cmd) {
	case WDIOC_GETSUPPORT:
		err = copy_to_user(argp, wdd->info,
			sizeof(struct watchdog_info)) ? -EFAULT : 0;
		break;
	case WDIOC_GETSTATUS:
		val = watchdog_get_status(wdd);
		err = put_user(val, p);
		break;
	case WDIOC_GETBOOTSTATUS:
		err = put_user(wdd->bootstatus, p);
		break;
	case WDIOC_SETOPTIONS:
		if (get_user(val, p)) {
			err = -EFAULT;
			break;
		}
		if (val & WDIOS_DISABLECARD) {
			err = watchdog_stop(wdd);
			if (err < 0)
				break;
		}
		if (val & WDIOS_ENABLECARD)
			err = watchdog_start(wdd);
		break;
	case WDIOC_KEEPALIVE:
		if (!(wdd->info->options & WDIOF_KEEPALIVEPING)) {
			err = -EOPNOTSUPP;
			break;
		}
		err = watchdog_ping(wdd);
		break;
	case WDIOC_SETTIMEOUT:
		if (get_user(val, p)) {
			err = -EFAULT;
			break;
		}
		err = watchdog_set_timeout(wdd, val);
		if (err < 0)
			break;
		/* If the watchdog is active then we send a keepalive ping
		 * to make sure that the watchdog keep's running (and if
		 * possible that it takes the new timeout) */
		err = watchdog_ping(wdd);
		if (err < 0)
			break;
		/* fall through */
	case WDIOC_GETTIMEOUT:
		/* timeout == 0 means that we don't know the timeout */
		if (wdd->timeout == 0) {
			err = -EOPNOTSUPP;
			break;
		}
		err = put_user(wdd->timeout, p);
		break;
	case WDIOC_GETTIMELEFT:
		err = watchdog_get_timeleft(wdd, &val);
		if (err < 0)
			break;
		err = put_user(val, p);
		break;
	case WDIOC_SETPRETIMEOUT:
		if (get_user(val, p)) {
			err = -EFAULT;
			break;
		}
		err = watchdog_set_pretimeout(wdd, val);
		break;
	case WDIOC_GETPRETIMEOUT:
		err = put_user(wdd->pretimeout, p);
		break;
	default:
		err = -ENOTTY;
		break;
	}

out_ioctl:
	mutex_unlock(&wd_data->lock);
	return err;
}

/*
 *	watchdog_open: open the /dev/watchdog* devices.
 *	@inode: inode of device
 *	@file: file handle to device
 *
 *	When the /dev/watchdog* device gets opened, we start the watchdog.
 *	Watch out: the /dev/watchdog device is single open, so we make sure
 *	it can only be opened once.
 */

static int watchdog_open(struct inode *inode, struct file *file)
{
	struct watchdog_core_data *wd_data;
	struct watchdog_device *wdd;
	bool hw_running;
	int err;

	/* Get the corresponding watchdog device */
	if (imajor(inode) == MISC_MAJOR)
		wd_data = old_wd_data;
	else
		wd_data = container_of(inode->i_cdev, struct watchdog_core_data,
				       cdev);

	/* the watchdog is single open! */
	if (test_and_set_bit(_WDOG_DEV_OPEN, &wd_data->status))
		return -EBUSY;

	wdd = wd_data->wdd;

	/*
	 * If the /dev/watchdog device is open, we don't want the module
	 * to be unloaded.
	 */
	hw_running = watchdog_hw_running(wdd);
	if (!hw_running && !try_module_get(wdd->ops->owner)) {
		err = -EBUSY;
		goto out_clear;
	}

	err = watchdog_start(wdd);
	if (err < 0)
		goto out_mod;

	file->private_data = wd_data;

	if (!hw_running)
		kref_get(&wd_data->kref);

	/*
	 * open_timeout only applies for the first open from
	 * userspace. Set open_deadline to infinity so that the kernel
	 * will take care of an always-running hardware watchdog in
	 * case the device gets magic-closed or WDIOS_DISABLECARD is
	 * applied.
	 */
	wd_data->open_deadline = KTIME_MAX;

	/* dev/watchdog is a virtual (and thus non-seekable) filesystem */
	return stream_open(inode, file);

out_mod:
	module_put(wd_data->wdd->ops->owner);
out_clear:
	clear_bit(_WDOG_DEV_OPEN, &wd_data->status);
	return err;
}

static void watchdog_core_data_release(struct kref *kref)
{
	struct watchdog_core_data *wd_data;

	wd_data = container_of(kref, struct watchdog_core_data, kref);

	kfree(wd_data);
}

/*
 *	watchdog_release: release the watchdog device.
 *	@inode: inode of device
 *	@file: file handle to device
 *
 *	This is the code for when /dev/watchdog gets closed. We will only
 *	stop the watchdog when we have received the magic char (and nowayout
 *	was not set), else the watchdog will keep running.
 */

static int watchdog_release(struct inode *inode, struct file *file)
{
	struct watchdog_core_data *wd_data = file->private_data;
	struct watchdog_device *wdd;
	int err = -EBUSY;
	bool running;

	mutex_lock(&wd_data->lock);

	wdd = wd_data->wdd;
	if (!wdd)
		goto done;

	/*
	 * We only stop the watchdog if we received the magic character
	 * or if WDIOF_MAGICCLOSE is not set. If nowayout was set then
	 * watchdog_stop will fail.
	 */
	if (!test_bit(WDOG_ACTIVE, &wdd->status))
		err = 0;
	else if (test_and_clear_bit(_WDOG_ALLOW_RELEASE, &wd_data->status) ||
		 !(wdd->info->options & WDIOF_MAGICCLOSE))
		err = watchdog_stop(wdd);

	/* If the watchdog was not stopped, send a keepalive ping */
	if (err < 0) {
		pr_crit("watchdog%d: watchdog did not stop!\n", wdd->id);
		watchdog_ping(wdd);
	}

	watchdog_update_worker(wdd);

	/* make sure that /dev/watchdog can be re-opened */
	clear_bit(_WDOG_DEV_OPEN, &wd_data->status);

done:
	running = wdd && watchdog_hw_running(wdd);
	mutex_unlock(&wd_data->lock);
	/*
	 * Allow the owner module to be unloaded again unless the watchdog
	 * is still running. If the watchdog is still running, it can not
	 * be stopped, and its driver must not be unloaded.
	 */
	if (!running) {
		module_put(wd_data->cdev.owner);
		kref_put(&wd_data->kref, watchdog_core_data_release);
	}
	return 0;
}

static const struct file_operations watchdog_fops = {
	.owner		= THIS_MODULE,
	.write		= watchdog_write,
	.unlocked_ioctl	= watchdog_ioctl,
	.open		= watchdog_open,
	.release	= watchdog_release,
};

static struct miscdevice watchdog_miscdev = {
	.minor		= WATCHDOG_MINOR,
	.name		= "watchdog",
	.fops		= &watchdog_fops,
};

/*
 *	watchdog_cdev_register: register watchdog character device
 *	@wdd: watchdog device
 *	@devno: character device number
 *
 *	Register a watchdog character device including handling the legacy
 *	/dev/watchdog node. /dev/watchdog is actually a miscdevice and
 *	thus we set it up like that.
 */

static int watchdog_cdev_register(struct watchdog_device *wdd, dev_t devno)
{
	struct watchdog_core_data *wd_data;
	int err;

	wd_data = kzalloc(sizeof(struct watchdog_core_data), GFP_KERNEL);
	if (!wd_data)
		return -ENOMEM;
	kref_init(&wd_data->kref);
	mutex_init(&wd_data->lock);

	wd_data->wdd = wdd;
	wdd->wd_data = wd_data;

	if (IS_ERR_OR_NULL(watchdog_kworker))
		return -ENODEV;

	kthread_init_work(&wd_data->work, watchdog_ping_work);
	hrtimer_init(&wd_data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
	wd_data->timer.function = watchdog_timer_expired;

	if (wdd->id == 0) {
		old_wd_data = wd_data;
		watchdog_miscdev.parent = wdd->parent;
		err = misc_register(&watchdog_miscdev);
		if (err != 0) {
			pr_err("%s: cannot register miscdev on minor=%d (err=%d).\n",
				wdd->info->identity, WATCHDOG_MINOR, err);
			if (err == -EBUSY)
				pr_err("%s: a legacy watchdog module is probably present.\n",
					wdd->info->identity);
			old_wd_data = NULL;
			kfree(wd_data);
			return err;
		}
	}

	/* Fill in the data structures */
	cdev_init(&wd_data->cdev, &watchdog_fops);
	wd_data->cdev.owner = wdd->ops->owner;

	/* Add the device */
	err = cdev_add(&wd_data->cdev, devno, 1);
	if (err) {
		pr_err("watchdog%d unable to add device %d:%d\n",
			wdd->id,  MAJOR(watchdog_devt), wdd->id);
		if (wdd->id == 0) {
			misc_deregister(&watchdog_miscdev);
			old_wd_data = NULL;
			kref_put(&wd_data->kref, watchdog_core_data_release);
		}
		return err;
	}

	/* Record time of most recent heartbeat as 'just before now'. */
	wd_data->last_hw_keepalive = ktime_sub(ktime_get(), 1);
	watchdog_set_open_deadline(wd_data);

	/*
	 * If the watchdog is running, prevent its driver from being unloaded,
	 * and schedule an immediate ping.
	 */
	if (watchdog_hw_running(wdd)) {
		__module_get(wdd->ops->owner);
		kref_get(&wd_data->kref);
		if (handle_boot_enabled)
			hrtimer_start(&wd_data->timer, 0, HRTIMER_MODE_REL);
		else
			pr_info("watchdog%d running and kernel based pre-userspace handler disabled\n",
				wdd->id);
	}

	return 0;
}

/*
 *	watchdog_cdev_unregister: unregister watchdog character device
 *	@watchdog: watchdog device
 *
 *	Unregister watchdog character device and if needed the legacy
 *	/dev/watchdog device.
 */

static void watchdog_cdev_unregister(struct watchdog_device *wdd)
{
	struct watchdog_core_data *wd_data = wdd->wd_data;

	cdev_del(&wd_data->cdev);
	if (wdd->id == 0) {
		misc_deregister(&watchdog_miscdev);
		old_wd_data = NULL;
	}

	if (watchdog_active(wdd) &&
	    test_bit(WDOG_STOP_ON_UNREGISTER, &wdd->status)) {
		watchdog_stop(wdd);
	}

	mutex_lock(&wd_data->lock);
	wd_data->wdd = NULL;
	wdd->wd_data = NULL;
	mutex_unlock(&wd_data->lock);

	hrtimer_cancel(&wd_data->timer);
	kthread_cancel_work_sync(&wd_data->work);

	kref_put(&wd_data->kref, watchdog_core_data_release);
}

static struct class watchdog_class = {
	.name =		"watchdog",
	.owner =	THIS_MODULE,
	.dev_groups =	wdt_groups,
};

static int watchdog_reboot_notifier(struct notifier_block *nb,
				    unsigned long code, void *data)
{
	struct watchdog_device *wdd;

	wdd = container_of(nb, struct watchdog_device, reboot_nb);
	if (code == SYS_DOWN || code == SYS_HALT) {
		if (watchdog_active(wdd)) {
			int ret;

			ret = wdd->ops->stop(wdd);
			if (ret)
				return NOTIFY_BAD;
		}
	}

	return NOTIFY_DONE;
}

/*
 *	watchdog_dev_register: register a watchdog device
 *	@wdd: watchdog device
 *
 *	Register a watchdog device including handling the legacy
 *	/dev/watchdog node. /dev/watchdog is actually a miscdevice and
 *	thus we set it up like that.
 */

int watchdog_dev_register(struct watchdog_device *wdd)
{
	struct device *dev;
	dev_t devno;
	int ret;

	devno = MKDEV(MAJOR(watchdog_devt), wdd->id);

	ret = watchdog_cdev_register(wdd, devno);
	if (ret)
		return ret;

	dev = device_create_with_groups(&watchdog_class, wdd->parent,
					devno, wdd, wdd->groups,
					"watchdog%d", wdd->id);
	if (IS_ERR(dev)) {
		watchdog_cdev_unregister(wdd);
		return PTR_ERR(dev);
	}

	ret = watchdog_register_pretimeout(wdd);
	if (ret) {
		device_destroy(&watchdog_class, devno);
		watchdog_cdev_unregister(wdd);
		return ret;
	}

	if (test_bit(WDOG_STOP_ON_REBOOT, &wdd->status)) {
		wdd->reboot_nb.notifier_call = watchdog_reboot_notifier;

		ret = devm_register_reboot_notifier(dev, &wdd->reboot_nb);
		if (ret) {
			pr_err("watchdog%d: Cannot register reboot notifier (%d)\n",
			       wdd->id, ret);
			watchdog_dev_unregister(wdd);
		}
	}

	return ret;
}

/*
 *	watchdog_dev_unregister: unregister a watchdog device
 *	@watchdog: watchdog device
 *
 *	Unregister watchdog device and if needed the legacy
 *	/dev/watchdog device.
 */

void watchdog_dev_unregister(struct watchdog_device *wdd)
{
	watchdog_unregister_pretimeout(wdd);
	device_destroy(&watchdog_class, wdd->wd_data->cdev.dev);
	watchdog_cdev_unregister(wdd);
}

/*
 *	watchdog_dev_init: init dev part of watchdog core
 *
 *	Allocate a range of chardev nodes to use for watchdog devices
 */

int __init watchdog_dev_init(void)
{
	int err;
	struct sched_param param = {.sched_priority = MAX_RT_PRIO - 1,};

	watchdog_kworker = kthread_create_worker(0, "watchdogd");
	if (IS_ERR(watchdog_kworker)) {
		pr_err("Failed to create watchdog kworker\n");
		return PTR_ERR(watchdog_kworker);
	}
	sched_setscheduler(watchdog_kworker->task, SCHED_FIFO, &param);

	err = class_register(&watchdog_class);
	if (err < 0) {
		pr_err("couldn't register class\n");
		goto err_register;
	}

	err = alloc_chrdev_region(&watchdog_devt, 0, MAX_DOGS, "watchdog");
	if (err < 0) {
		pr_err("watchdog: unable to allocate char dev region\n");
		goto err_alloc;
	}

	return 0;

err_alloc:
	class_unregister(&watchdog_class);
err_register:
	kthread_destroy_worker(watchdog_kworker);
	return err;
}

/*
 *	watchdog_dev_exit: exit dev part of watchdog core
 *
 *	Release the range of chardev nodes used for watchdog devices
 */

void __exit watchdog_dev_exit(void)
{
	unregister_chrdev_region(watchdog_devt, MAX_DOGS);
	class_unregister(&watchdog_class);
	kthread_destroy_worker(watchdog_kworker);
}

module_param(handle_boot_enabled, bool, 0444);
MODULE_PARM_DESC(handle_boot_enabled,
	"Watchdog core auto-updates boot enabled watchdogs before userspace takes over (default="
	__MODULE_STRING(IS_ENABLED(CONFIG_WATCHDOG_HANDLE_BOOT_ENABLED)) ")");

module_param(open_timeout, uint, 0644);
MODULE_PARM_DESC(open_timeout,
	"Maximum time (in seconds, 0 means infinity) for userspace to take over a running watchdog (default="
	__MODULE_STRING(CONFIG_WATCHDOG_OPEN_TIMEOUT) ")");