aboutsummaryrefslogtreecommitdiff
path: root/arch/i386/kernel/nmi.c
blob: b11abacc5cfd3d869095c744f60556e79cfae238 (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
/*
 *  linux/arch/i386/nmi.c
 *
 *  NMI watchdog support on APIC systems
 *
 *  Started by Ingo Molnar <mingo@redhat.com>
 *
 *  Fixes:
 *  Mikael Pettersson	: AMD K7 support for local APIC NMI watchdog.
 *  Mikael Pettersson	: Power Management for local APIC NMI watchdog.
 *  Mikael Pettersson	: Pentium 4 support for local APIC NMI watchdog.
 *  Pavel Machek and
 *  Mikael Pettersson	: PM converted to driver model. Disable/enable API.
 */

#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/nmi.h>
#include <linux/sysdev.h>
#include <linux/sysctl.h>
#include <linux/percpu.h>
#include <linux/dmi.h>
#include <linux/kprobes.h>
#include <linux/cpumask.h>

#include <asm/smp.h>
#include <asm/nmi.h>
#include <asm/kdebug.h>
#include <asm/intel_arch_perfmon.h>

#include "mach_traps.h"

int unknown_nmi_panic;
int nmi_watchdog_enabled;

/* perfctr_nmi_owner tracks the ownership of the perfctr registers:
 * evtsel_nmi_owner tracks the ownership of the event selection
 * - different performance counters/ event selection may be reserved for
 *   different subsystems this reservation system just tries to coordinate
 *   things a little
 */
static DEFINE_PER_CPU(unsigned long, perfctr_nmi_owner);
static DEFINE_PER_CPU(unsigned long, evntsel_nmi_owner[3]);

static cpumask_t backtrace_mask = CPU_MASK_NONE;

/* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
 * offset from MSR_P4_BSU_ESCR0.  It will be the max for all platforms (for now)
 */
#define NMI_MAX_COUNTER_BITS 66

/* nmi_active:
 * >0: the lapic NMI watchdog is active, but can be disabled
 * <0: the lapic NMI watchdog has not been set up, and cannot
 *     be enabled
 *  0: the lapic NMI watchdog is disabled, but can be enabled
 */
atomic_t nmi_active = ATOMIC_INIT(0);		/* oprofile uses this */

unsigned int nmi_watchdog = NMI_DEFAULT;
static unsigned int nmi_hz = HZ;

struct nmi_watchdog_ctlblk {
	int enabled;
	u64 check_bit;
	unsigned int cccr_msr;
	unsigned int perfctr_msr;  /* the MSR to reset in NMI handler */
	unsigned int evntsel_msr;  /* the MSR to select the events to handle */
};
static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);

/* local prototypes */
static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu);

extern void show_registers(struct pt_regs *regs);
extern int unknown_nmi_panic;

/* converts an msr to an appropriate reservation bit */
static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
{
	/* returns the bit offset of the performance counter register */
	switch (boot_cpu_data.x86_vendor) {
	case X86_VENDOR_AMD:
		return (msr - MSR_K7_PERFCTR0);
	case X86_VENDOR_INTEL:
		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
			return (msr - MSR_ARCH_PERFMON_PERFCTR0);

		switch (boot_cpu_data.x86) {
		case 6:
			return (msr - MSR_P6_PERFCTR0);
		case 15:
			return (msr - MSR_P4_BPU_PERFCTR0);
		}
	}
	return 0;
}

/* converts an msr to an appropriate reservation bit */
static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
{
	/* returns the bit offset of the event selection register */
	switch (boot_cpu_data.x86_vendor) {
	case X86_VENDOR_AMD:
		return (msr - MSR_K7_EVNTSEL0);
	case X86_VENDOR_INTEL:
		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
			return (msr - MSR_ARCH_PERFMON_EVENTSEL0);

		switch (boot_cpu_data.x86) {
		case 6:
			return (msr - MSR_P6_EVNTSEL0);
		case 15:
			return (msr - MSR_P4_BSU_ESCR0);
		}
	}
	return 0;
}

/* checks for a bit availability (hack for oprofile) */
int avail_to_resrv_perfctr_nmi_bit(unsigned int counter)
{
	BUG_ON(counter > NMI_MAX_COUNTER_BITS);

	return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner)));
}

/* checks the an msr for availability */
int avail_to_resrv_perfctr_nmi(unsigned int msr)
{
	unsigned int counter;

	counter = nmi_perfctr_msr_to_bit(msr);
	BUG_ON(counter > NMI_MAX_COUNTER_BITS);

	return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner)));
}

int reserve_perfctr_nmi(unsigned int msr)
{
	unsigned int counter;

	counter = nmi_perfctr_msr_to_bit(msr);
	BUG_ON(counter > NMI_MAX_COUNTER_BITS);

	if (!test_and_set_bit(counter, &__get_cpu_var(perfctr_nmi_owner)))
		return 1;
	return 0;
}

void release_perfctr_nmi(unsigned int msr)
{
	unsigned int counter;

	counter = nmi_perfctr_msr_to_bit(msr);
	BUG_ON(counter > NMI_MAX_COUNTER_BITS);

	clear_bit(counter, &__get_cpu_var(perfctr_nmi_owner));
}

int reserve_evntsel_nmi(unsigned int msr)
{
	unsigned int counter;

	counter = nmi_evntsel_msr_to_bit(msr);
	BUG_ON(counter > NMI_MAX_COUNTER_BITS);

	if (!test_and_set_bit(counter, &__get_cpu_var(evntsel_nmi_owner)[0]))
		return 1;
	return 0;
}

void release_evntsel_nmi(unsigned int msr)
{
	unsigned int counter;

	counter = nmi_evntsel_msr_to_bit(msr);
	BUG_ON(counter > NMI_MAX_COUNTER_BITS);

	clear_bit(counter, &__get_cpu_var(evntsel_nmi_owner)[0]);
}

static __cpuinit inline int nmi_known_cpu(void)
{
	switch (boot_cpu_data.x86_vendor) {
	case X86_VENDOR_AMD:
		return ((boot_cpu_data.x86 == 15) || (boot_cpu_data.x86 == 6));
	case X86_VENDOR_INTEL:
		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
			return 1;
		else
			return ((boot_cpu_data.x86 == 15) || (boot_cpu_data.x86 == 6));
	}
	return 0;
}

static int endflag __initdata = 0;

#ifdef CONFIG_SMP
/* The performance counters used by NMI_LOCAL_APIC don't trigger when
 * the CPU is idle. To make sure the NMI watchdog really ticks on all
 * CPUs during the test make them busy.
 */
static __init void nmi_cpu_busy(void *data)
{
	local_irq_enable_in_hardirq();
	/* Intentionally don't use cpu_relax here. This is
	   to make sure that the performance counter really ticks,
	   even if there is a simulator or similar that catches the
	   pause instruction. On a real HT machine this is fine because
	   all other CPUs are busy with "useless" delay loops and don't
	   care if they get somewhat less cycles. */
	while (endflag == 0)
		mb();
}
#endif

static unsigned int adjust_for_32bit_ctr(unsigned int hz)
{
	u64 counter_val;
	unsigned int retval = hz;

	/*
	 * On Intel CPUs with P6/ARCH_PERFMON only 32 bits in the counter
	 * are writable, with higher bits sign extending from bit 31.
	 * So, we can only program the counter with 31 bit values and
	 * 32nd bit should be 1, for 33.. to be 1.
	 * Find the appropriate nmi_hz
	 */
	counter_val = (u64)cpu_khz * 1000;
	do_div(counter_val, retval);
 	if (counter_val > 0x7fffffffULL) {
		u64 count = (u64)cpu_khz * 1000;
		do_div(count, 0x7fffffffUL);
		retval = count + 1;
	}
	return retval;
}

static int __init check_nmi_watchdog(void)
{
	unsigned int *prev_nmi_count;
	int cpu;

	/* Enable NMI watchdog for newer systems.
	   Probably safe on most older systems too, but let's be careful.
	   IBM ThinkPads use INT10 inside SMM and that allows early NMI inside SMM
	   which hangs the system. Disable watchdog for all thinkpads */
	if (nmi_watchdog == NMI_DEFAULT && dmi_get_year(DMI_BIOS_DATE) >= 2004 &&
		!dmi_name_in_vendors("ThinkPad"))
		nmi_watchdog = NMI_LOCAL_APIC;

	if ((nmi_watchdog == NMI_NONE) || (nmi_watchdog == NMI_DEFAULT))
		return 0;

	if (!atomic_read(&nmi_active))
		return 0;

	prev_nmi_count = kmalloc(NR_CPUS * sizeof(int), GFP_KERNEL);
	if (!prev_nmi_count)
		return -1;

	printk(KERN_INFO "Testing NMI watchdog ... ");

	if (nmi_watchdog == NMI_LOCAL_APIC)
		smp_call_function(nmi_cpu_busy, (void *)&endflag, 0, 0);

	for_each_possible_cpu(cpu)
		prev_nmi_count[cpu] = per_cpu(irq_stat, cpu).__nmi_count;
	local_irq_enable();
	mdelay((10*1000)/nmi_hz); // wait 10 ticks

	for_each_possible_cpu(cpu) {
#ifdef CONFIG_SMP
		/* Check cpu_callin_map here because that is set
		   after the timer is started. */
		if (!cpu_isset(cpu, cpu_callin_map))
			continue;
#endif
		if (!per_cpu(nmi_watchdog_ctlblk, cpu).enabled)
			continue;
		if (nmi_count(cpu) - prev_nmi_count[cpu] <= 5) {
			printk("CPU#%d: NMI appears to be stuck (%d->%d)!\n",
				cpu,
				prev_nmi_count[cpu],
				nmi_count(cpu));
			per_cpu(nmi_watchdog_ctlblk, cpu).enabled = 0;
			atomic_dec(&nmi_active);
		}
	}
	if (!atomic_read(&nmi_active)) {
		kfree(prev_nmi_count);
		atomic_set(&nmi_active, -1);
		return -1;
	}
	endflag = 1;
	printk("OK.\n");

	/* now that we know it works we can reduce NMI frequency to
	   something more reasonable; makes a difference in some configs */
	if (nmi_watchdog == NMI_LOCAL_APIC) {
		struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);

		nmi_hz = 1;

		if (wd->perfctr_msr == MSR_P6_PERFCTR0 ||
		    wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
			nmi_hz = adjust_for_32bit_ctr(nmi_hz);
		}
	}

	kfree(prev_nmi_count);
	return 0;
}
/* This needs to happen later in boot so counters are working */
late_initcall(check_nmi_watchdog);

static int __init setup_nmi_watchdog(char *str)
{
	int nmi;

	get_option(&str, &nmi);

	if ((nmi >= NMI_INVALID) || (nmi < NMI_NONE))
		return 0;

	nmi_watchdog = nmi;
	return 1;
}

__setup("nmi_watchdog=", setup_nmi_watchdog);

static void disable_lapic_nmi_watchdog(void)
{
	BUG_ON(nmi_watchdog != NMI_LOCAL_APIC);

	if (atomic_read(&nmi_active) <= 0)
		return;

	on_each_cpu(stop_apic_nmi_watchdog, NULL, 0, 1);

	BUG_ON(atomic_read(&nmi_active) != 0);
}

static void enable_lapic_nmi_watchdog(void)
{
	BUG_ON(nmi_watchdog != NMI_LOCAL_APIC);

	/* are we already enabled */
	if (atomic_read(&nmi_active) != 0)
		return;

	/* are we lapic aware */
	if (nmi_known_cpu() <= 0)
		return;

	on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1);
	touch_nmi_watchdog();
}

void disable_timer_nmi_watchdog(void)
{
	BUG_ON(nmi_watchdog != NMI_IO_APIC);

	if (atomic_read(&nmi_active) <= 0)
		return;

	disable_irq(0);
	on_each_cpu(stop_apic_nmi_watchdog, NULL, 0, 1);

	BUG_ON(atomic_read(&nmi_active) != 0);
}

void enable_timer_nmi_watchdog(void)
{
	BUG_ON(nmi_watchdog != NMI_IO_APIC);

	if (atomic_read(&nmi_active) == 0) {
		touch_nmi_watchdog();
		on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1);
		enable_irq(0);
	}
}

static void __acpi_nmi_disable(void *__unused)
{
	apic_write_around(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
}

/*
 * Disable timer based NMIs on all CPUs:
 */
void acpi_nmi_disable(void)
{
	if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
		on_each_cpu(__acpi_nmi_disable, NULL, 0, 1);
}

static void __acpi_nmi_enable(void *__unused)
{
	apic_write_around(APIC_LVT0, APIC_DM_NMI);
}

/*
 * Enable timer based NMIs on all CPUs:
 */
void acpi_nmi_enable(void)
{
	if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
		on_each_cpu(__acpi_nmi_enable, NULL, 0, 1);
}

#ifdef CONFIG_PM

static int nmi_pm_active; /* nmi_active before suspend */

static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
{
	/* only CPU0 goes here, other CPUs should be offline */
	nmi_pm_active = atomic_read(&nmi_active);
	stop_apic_nmi_watchdog(NULL);
	BUG_ON(atomic_read(&nmi_active) != 0);
	return 0;
}

static int lapic_nmi_resume(struct sys_device *dev)
{
	/* only CPU0 goes here, other CPUs should be offline */
	if (nmi_pm_active > 0) {
		setup_apic_nmi_watchdog(NULL);
		touch_nmi_watchdog();
	}
	return 0;
}


static struct sysdev_class nmi_sysclass = {
	set_kset_name("lapic_nmi"),
	.resume		= lapic_nmi_resume,
	.suspend	= lapic_nmi_suspend,
};

static struct sys_device device_lapic_nmi = {
	.id	= 0,
	.cls	= &nmi_sysclass,
};

static int __init init_lapic_nmi_sysfs(void)
{
	int error;

	/* should really be a BUG_ON but b/c this is an
	 * init call, it just doesn't work.  -dcz
	 */
	if (nmi_watchdog != NMI_LOCAL_APIC)
		return 0;

	if ( atomic_read(&nmi_active) < 0 )
		return 0;

	error = sysdev_class_register(&nmi_sysclass);
	if (!error)
		error = sysdev_register(&device_lapic_nmi);
	return error;
}
/* must come after the local APIC's device_initcall() */
late_initcall(init_lapic_nmi_sysfs);

#endif	/* CONFIG_PM */

/*
 * Activate the NMI watchdog via the local APIC.
 * Original code written by Keith Owens.
 */

static void write_watchdog_counter(unsigned int perfctr_msr, const char *descr)
{
	u64 count = (u64)cpu_khz * 1000;

	do_div(count, nmi_hz);
	if(descr)
		Dprintk("setting %s to -0x%08Lx\n", descr, count);
	wrmsrl(perfctr_msr, 0 - count);
}

static void write_watchdog_counter32(unsigned int perfctr_msr,
		const char *descr)
{
	u64 count = (u64)cpu_khz * 1000;

	do_div(count, nmi_hz);
	if(descr)
		Dprintk("setting %s to -0x%08Lx\n", descr, count);
	wrmsr(perfctr_msr, (u32)(-count), 0);
}

/* Note that these events don't tick when the CPU idles. This means
   the frequency varies with CPU load. */

#define K7_EVNTSEL_ENABLE	(1 << 22)
#define K7_EVNTSEL_INT		(1 << 20)
#define K7_EVNTSEL_OS		(1 << 17)
#define K7_EVNTSEL_USR		(1 << 16)
#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING	0x76
#define K7_NMI_EVENT		K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING

static int setup_k7_watchdog(void)
{
	unsigned int perfctr_msr, evntsel_msr;
	unsigned int evntsel;
	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);

	perfctr_msr = MSR_K7_PERFCTR0;
	evntsel_msr = MSR_K7_EVNTSEL0;
	if (!reserve_perfctr_nmi(perfctr_msr))
		goto fail;

	if (!reserve_evntsel_nmi(evntsel_msr))
		goto fail1;

	wrmsrl(perfctr_msr, 0UL);

	evntsel = K7_EVNTSEL_INT
		| K7_EVNTSEL_OS
		| K7_EVNTSEL_USR
		| K7_NMI_EVENT;

	/* setup the timer */
	wrmsr(evntsel_msr, evntsel, 0);
	write_watchdog_counter(perfctr_msr, "K7_PERFCTR0");
	apic_write(APIC_LVTPC, APIC_DM_NMI);
	evntsel |= K7_EVNTSEL_ENABLE;
	wrmsr(evntsel_msr, evntsel, 0);

	wd->perfctr_msr = perfctr_msr;
	wd->evntsel_msr = evntsel_msr;
	wd->cccr_msr = 0;  //unused
	wd->check_bit = 1ULL<<63;
	return 1;
fail1:
	release_perfctr_nmi(perfctr_msr);
fail:
	return 0;
}

static void stop_k7_watchdog(void)
{
	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);

	wrmsr(wd->evntsel_msr, 0, 0);

	release_evntsel_nmi(wd->evntsel_msr);
	release_perfctr_nmi(wd->perfctr_msr);
}

#define P6_EVNTSEL0_ENABLE	(1 << 22)
#define P6_EVNTSEL_INT		(1 << 20)
#define P6_EVNTSEL_OS		(1 << 17)
#define P6_EVNTSEL_USR		(1 << 16)
#define P6_EVENT_CPU_CLOCKS_NOT_HALTED	0x79
#define P6_NMI_EVENT		P6_EVENT_CPU_CLOCKS_NOT_HALTED

static int setup_p6_watchdog(void)
{
	unsigned int perfctr_msr, evntsel_msr;
	unsigned int evntsel;
	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);

	perfctr_msr = MSR_P6_PERFCTR0;
	evntsel_msr = MSR_P6_EVNTSEL0;
	if (!reserve_perfctr_nmi(perfctr_msr))
		goto fail;

	if (!reserve_evntsel_nmi(evntsel_msr))
		goto fail1;

	wrmsrl(perfctr_msr, 0UL);

	evntsel = P6_EVNTSEL_INT
		| P6_EVNTSEL_OS
		| P6_EVNTSEL_USR
		| P6_NMI_EVENT;

	/* setup the timer */
	wrmsr(evntsel_msr, evntsel, 0);
	nmi_hz = adjust_for_32bit_ctr(nmi_hz);
	write_watchdog_counter32(perfctr_msr, "P6_PERFCTR0");
	apic_write(APIC_LVTPC, APIC_DM_NMI);
	evntsel |= P6_EVNTSEL0_ENABLE;
	wrmsr(evntsel_msr, evntsel, 0);

	wd->perfctr_msr = perfctr_msr;
	wd->evntsel_msr = evntsel_msr;
	wd->cccr_msr = 0;  //unused
	wd->check_bit = 1ULL<<39;
	return 1;
fail1:
	release_perfctr_nmi(perfctr_msr);
fail:
	return 0;
}

static void stop_p6_watchdog(void)
{
	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);

	wrmsr(wd->evntsel_msr, 0, 0);

	release_evntsel_nmi(wd->evntsel_msr);
	release_perfctr_nmi(wd->perfctr_msr);
}

/* Note that these events don't tick when the CPU idles. This means
   the frequency varies with CPU load. */

#define MSR_P4_MISC_ENABLE_PERF_AVAIL	(1<<7)
#define P4_ESCR_EVENT_SELECT(N)	((N)<<25)
#define P4_ESCR_OS		(1<<3)
#define P4_ESCR_USR		(1<<2)
#define P4_CCCR_OVF_PMI0	(1<<26)
#define P4_CCCR_OVF_PMI1	(1<<27)
#define P4_CCCR_THRESHOLD(N)	((N)<<20)
#define P4_CCCR_COMPLEMENT	(1<<19)
#define P4_CCCR_COMPARE		(1<<18)
#define P4_CCCR_REQUIRED	(3<<16)
#define P4_CCCR_ESCR_SELECT(N)	((N)<<13)
#define P4_CCCR_ENABLE		(1<<12)
#define P4_CCCR_OVF 		(1<<31)
/* Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter
   CRU_ESCR0 (with any non-null event selector) through a complemented
   max threshold. [IA32-Vol3, Section 14.9.9] */

static int setup_p4_watchdog(void)
{
	unsigned int perfctr_msr, evntsel_msr, cccr_msr;
	unsigned int evntsel, cccr_val;
	unsigned int misc_enable, dummy;
	unsigned int ht_num;
	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);

	rdmsr(MSR_IA32_MISC_ENABLE, misc_enable, dummy);
	if (!(misc_enable & MSR_P4_MISC_ENABLE_PERF_AVAIL))
		return 0;

#ifdef CONFIG_SMP
	/* detect which hyperthread we are on */
	if (smp_num_siblings == 2) {
		unsigned int ebx, apicid;

        	ebx = cpuid_ebx(1);
	        apicid = (ebx >> 24) & 0xff;
        	ht_num = apicid & 1;
	} else
#endif
		ht_num = 0;

	/* performance counters are shared resources
	 * assign each hyperthread its own set
	 * (re-use the ESCR0 register, seems safe
	 * and keeps the cccr_val the same)
	 */
	if (!ht_num) {
		/* logical cpu 0 */
		perfctr_msr = MSR_P4_IQ_PERFCTR0;
		evntsel_msr = MSR_P4_CRU_ESCR0;
		cccr_msr = MSR_P4_IQ_CCCR0;
		cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4);
	} else {
		/* logical cpu 1 */
		perfctr_msr = MSR_P4_IQ_PERFCTR1;
		evntsel_msr = MSR_P4_CRU_ESCR0;
		cccr_msr = MSR_P4_IQ_CCCR1;
		cccr_val = P4_CCCR_OVF_PMI1 | P4_CCCR_ESCR_SELECT(4);
	}

	if (!reserve_perfctr_nmi(perfctr_msr))
		goto fail;

	if (!reserve_evntsel_nmi(evntsel_msr))
		goto fail1;

	evntsel = P4_ESCR_EVENT_SELECT(0x3F)
	 	| P4_ESCR_OS
		| P4_ESCR_USR;

	cccr_val |= P4_CCCR_THRESHOLD(15)
		 | P4_CCCR_COMPLEMENT
		 | P4_CCCR_COMPARE
		 | P4_CCCR_REQUIRED;

	wrmsr(evntsel_msr, evntsel, 0);
	wrmsr(cccr_msr, cccr_val, 0);
	write_watchdog_counter(perfctr_msr, "P4_IQ_COUNTER0");
	apic_write(APIC_LVTPC, APIC_DM_NMI);
	cccr_val |= P4_CCCR_ENABLE;
	wrmsr(cccr_msr, cccr_val, 0);
	wd->perfctr_msr = perfctr_msr;
	wd->evntsel_msr = evntsel_msr;
	wd->cccr_msr = cccr_msr;
	wd->check_bit = 1ULL<<39;
	return 1;
fail1:
	release_perfctr_nmi(perfctr_msr);
fail:
	return 0;
}

static void stop_p4_watchdog(void)
{
	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);

	wrmsr(wd->cccr_msr, 0, 0);
	wrmsr(wd->evntsel_msr, 0, 0);

	release_evntsel_nmi(wd->evntsel_msr);
	release_perfctr_nmi(wd->perfctr_msr);
}

#define ARCH_PERFMON_NMI_EVENT_SEL	ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
#define ARCH_PERFMON_NMI_EVENT_UMASK	ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK

static int setup_intel_arch_watchdog(void)
{
	unsigned int ebx;
	union cpuid10_eax eax;
	unsigned int unused;
	unsigned int perfctr_msr, evntsel_msr;
	unsigned int evntsel;
	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);

	/*
	 * Check whether the Architectural PerfMon supports
	 * Unhalted Core Cycles Event or not.
	 * NOTE: Corresponding bit = 0 in ebx indicates event present.
	 */
	cpuid(10, &(eax.full), &ebx, &unused, &unused);
	if ((eax.split.mask_length < (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) ||
	    (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
		goto fail;

	perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0;
	evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL0;

	if (!reserve_perfctr_nmi(perfctr_msr))
		goto fail;

	if (!reserve_evntsel_nmi(evntsel_msr))
		goto fail1;

	wrmsrl(perfctr_msr, 0UL);

	evntsel = ARCH_PERFMON_EVENTSEL_INT
		| ARCH_PERFMON_EVENTSEL_OS
		| ARCH_PERFMON_EVENTSEL_USR
		| ARCH_PERFMON_NMI_EVENT_SEL
		| ARCH_PERFMON_NMI_EVENT_UMASK;

	/* setup the timer */
	wrmsr(evntsel_msr, evntsel, 0);
	nmi_hz = adjust_for_32bit_ctr(nmi_hz);
	write_watchdog_counter32(perfctr_msr, "INTEL_ARCH_PERFCTR0");
	apic_write(APIC_LVTPC, APIC_DM_NMI);
	evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
	wrmsr(evntsel_msr, evntsel, 0);

	wd->perfctr_msr = perfctr_msr;
	wd->evntsel_msr = evntsel_msr;
	wd->cccr_msr = 0;  //unused
	wd->check_bit = 1ULL << (eax.split.bit_width - 1);
	return 1;
fail1:
	release_perfctr_nmi(perfctr_msr);
fail:
	return 0;
}

static void stop_intel_arch_watchdog(void)
{
	unsigned int ebx;
	union cpuid10_eax eax;
	unsigned int unused;
	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);

	/*
	 * Check whether the Architectural PerfMon supports
	 * Unhalted Core Cycles Event or not.
	 * NOTE: Corresponding bit = 0 in ebx indicates event present.
	 */
	cpuid(10, &(eax.full), &ebx, &unused, &unused);
	if ((eax.split.mask_length < (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) ||
	    (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
		return;

	wrmsr(wd->evntsel_msr, 0, 0);
	release_evntsel_nmi(wd->evntsel_msr);
	release_perfctr_nmi(wd->perfctr_msr);
}

void setup_apic_nmi_watchdog (void *unused)
{
	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);

	/* only support LOCAL and IO APICs for now */
	if ((nmi_watchdog != NMI_LOCAL_APIC) &&
	    (nmi_watchdog != NMI_IO_APIC))
	    	return;

	if (wd->enabled == 1)
		return;

	/* cheap hack to support suspend/resume */
	/* if cpu0 is not active neither should the other cpus */
	if ((smp_processor_id() != 0) && (atomic_read(&nmi_active) <= 0))
		return;

	if (nmi_watchdog == NMI_LOCAL_APIC) {
		switch (boot_cpu_data.x86_vendor) {
		case X86_VENDOR_AMD:
			if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15)
				return;
			if (!setup_k7_watchdog())
				return;
			break;
		case X86_VENDOR_INTEL:
			if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
				if (!setup_intel_arch_watchdog())
					return;
				break;
			}
			switch (boot_cpu_data.x86) {
			case 6:
				if (boot_cpu_data.x86_model > 0xd)
					return;

				if (!setup_p6_watchdog())
					return;
				break;
			case 15:
				if (boot_cpu_data.x86_model > 0x4)
					return;

				if (!setup_p4_watchdog())
					return;
				break;
			default:
				return;
			}
			break;
		default:
			return;
		}
	}
	wd->enabled = 1;
	atomic_inc(&nmi_active);
}

void stop_apic_nmi_watchdog(void *unused)
{
	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);

	/* only support LOCAL and IO APICs for now */
	if ((nmi_watchdog != NMI_LOCAL_APIC) &&
	    (nmi_watchdog != NMI_IO_APIC))
	    	return;

	if (wd->enabled == 0)
		return;

	if (nmi_watchdog == NMI_LOCAL_APIC) {
		switch (boot_cpu_data.x86_vendor) {
		case X86_VENDOR_AMD:
			stop_k7_watchdog();
			break;
		case X86_VENDOR_INTEL:
			if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
				stop_intel_arch_watchdog();
				break;
			}
			switch (boot_cpu_data.x86) {
			case 6:
				if (boot_cpu_data.x86_model > 0xd)
					break;
				stop_p6_watchdog();
				break;
			case 15:
				if (boot_cpu_data.x86_model > 0x4)
					break;
				stop_p4_watchdog();
				break;
			}
			break;
		default:
			return;
		}
	}
	wd->enabled = 0;
	atomic_dec(&nmi_active);
}

/*
 * the best way to detect whether a CPU has a 'hard lockup' problem
 * is to check it's local APIC timer IRQ counts. If they are not
 * changing then that CPU has some problem.
 *
 * as these watchdog NMI IRQs are generated on every CPU, we only
 * have to check the current processor.
 *
 * since NMIs don't listen to _any_ locks, we have to be extremely
 * careful not to rely on unsafe variables. The printk might lock
 * up though, so we have to break up any console locks first ...
 * [when there will be more tty-related locks, break them up
 *  here too!]
 */

static unsigned int
	last_irq_sums [NR_CPUS],
	alert_counter [NR_CPUS];

void touch_nmi_watchdog (void)
{
	if (nmi_watchdog > 0) {
		unsigned cpu;

		/*
		 * Just reset the alert counters, (other CPUs might be
		 * spinning on locks we hold):
		 */
		for_each_present_cpu (cpu)
			alert_counter[cpu] = 0;
	}

	/*
	 * Tickle the softlockup detector too:
	 */
	touch_softlockup_watchdog();
}
EXPORT_SYMBOL(touch_nmi_watchdog);

extern void die_nmi(struct pt_regs *, const char *msg);

__kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
{

	/*
	 * Since current_thread_info()-> is always on the stack, and we
	 * always switch the stack NMI-atomically, it's safe to use
	 * smp_processor_id().
	 */
	unsigned int sum;
	int touched = 0;
	int cpu = smp_processor_id();
	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
	u64 dummy;
	int rc=0;

	/* check for other users first */
	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
			== NOTIFY_STOP) {
		rc = 1;
		touched = 1;
	}

	if (cpu_isset(cpu, backtrace_mask)) {
		static DEFINE_SPINLOCK(lock);	/* Serialise the printks */

		spin_lock(&lock);
		printk("NMI backtrace for cpu %d\n", cpu);
		dump_stack();
		spin_unlock(&lock);
		cpu_clear(cpu, backtrace_mask);
	}

	sum = per_cpu(irq_stat, cpu).apic_timer_irqs;

	/* if the apic timer isn't firing, this cpu isn't doing much */
	if (!touched && last_irq_sums[cpu] == sum) {
		/*
		 * Ayiee, looks like this CPU is stuck ...
		 * wait a few IRQs (5 seconds) before doing the oops ...
		 */
		alert_counter[cpu]++;
		if (alert_counter[cpu] == 5*nmi_hz)
			/*
			 * die_nmi will return ONLY if NOTIFY_STOP happens..
			 */
			die_nmi(regs, "BUG: NMI Watchdog detected LOCKUP");
	} else {
		last_irq_sums[cpu] = sum;
		alert_counter[cpu] = 0;
	}
	/* see if the nmi watchdog went off */
	if (wd->enabled) {
		if (nmi_watchdog == NMI_LOCAL_APIC) {
			rdmsrl(wd->perfctr_msr, dummy);
			if (dummy & wd->check_bit){
				/* this wasn't a watchdog timer interrupt */
				goto done;
			}

			/* only Intel P4 uses the cccr msr */
	 		if (wd->cccr_msr != 0) {
	 			/*
	 			 * P4 quirks:
	 			 * - An overflown perfctr will assert its interrupt
	 			 *   until the OVF flag in its CCCR is cleared.
	 			 * - LVTPC is masked on interrupt and must be
	 			 *   unmasked by the LVTPC handler.
	 			 */
				rdmsrl(wd->cccr_msr, dummy);
				dummy &= ~P4_CCCR_OVF;
	 			wrmsrl(wd->cccr_msr, dummy);
	 			apic_write(APIC_LVTPC, APIC_DM_NMI);
				/* start the cycle over again */
				write_watchdog_counter(wd->perfctr_msr, NULL);
	 		}
			else if (wd->perfctr_msr == MSR_P6_PERFCTR0 ||
				 wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
				/* P6 based Pentium M need to re-unmask
				 * the apic vector but it doesn't hurt
				 * other P6 variant.
				 * ArchPerfom/Core Duo also needs this */
				apic_write(APIC_LVTPC, APIC_DM_NMI);
				/* P6/ARCH_PERFMON has 32 bit counter write */
				write_watchdog_counter32(wd->perfctr_msr, NULL);
			} else {
				/* start the cycle over again */
				write_watchdog_counter(wd->perfctr_msr, NULL);
			}
			rc = 1;
		} else if (nmi_watchdog == NMI_IO_APIC) {
			/* don't know how to accurately check for this.
			 * just assume it was a watchdog timer interrupt
			 * This matches the old behaviour.
			 */
			rc = 1;
		}
	}
done:
	return rc;
}

int do_nmi_callback(struct pt_regs * regs, int cpu)
{
#ifdef CONFIG_SYSCTL
	if (unknown_nmi_panic)
		return unknown_nmi_panic_callback(regs, cpu);
#endif
	return 0;
}

#ifdef CONFIG_SYSCTL

static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
{
	unsigned char reason = get_nmi_reason();
	char buf[64];

	sprintf(buf, "NMI received for unknown reason %02x\n", reason);
	die_nmi(regs, buf);
	return 0;
}

/*
 * proc handler for /proc/sys/kernel/nmi
 */
int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
			void __user *buffer, size_t *length, loff_t *ppos)
{
	int old_state;

	nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0;
	old_state = nmi_watchdog_enabled;
	proc_dointvec(table, write, file, buffer, length, ppos);
	if (!!old_state == !!nmi_watchdog_enabled)
		return 0;

	if (atomic_read(&nmi_active) < 0) {
		printk( KERN_WARNING "NMI watchdog is permanently disabled\n");
		return -EIO;
	}

	if (nmi_watchdog == NMI_DEFAULT) {
		if (nmi_known_cpu() > 0)
			nmi_watchdog = NMI_LOCAL_APIC;
		else
			nmi_watchdog = NMI_IO_APIC;
	}

	if (nmi_watchdog == NMI_LOCAL_APIC) {
		if (nmi_watchdog_enabled)
			enable_lapic_nmi_watchdog();
		else
			disable_lapic_nmi_watchdog();
	} else {
		printk( KERN_WARNING
			"NMI watchdog doesn't know what hardware to touch\n");
		return -EIO;
	}
	return 0;
}

#endif

void __trigger_all_cpu_backtrace(void)
{
	int i;

	backtrace_mask = cpu_online_map;
	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
	for (i = 0; i < 10 * 1000; i++) {
		if (cpus_empty(backtrace_mask))
			break;
		mdelay(1);
	}
}

EXPORT_SYMBOL(nmi_active);
EXPORT_SYMBOL(nmi_watchdog);
EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi);
EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit);
EXPORT_SYMBOL(reserve_perfctr_nmi);
EXPORT_SYMBOL(release_perfctr_nmi);
EXPORT_SYMBOL(reserve_evntsel_nmi);
EXPORT_SYMBOL(release_evntsel_nmi);
EXPORT_SYMBOL(disable_timer_nmi_watchdog);
EXPORT_SYMBOL(enable_timer_nmi_watchdog);