aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/oprofile/nmi_int.c
blob: 1ba67dc8006ab700170afb6964954c33c5705591 (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
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
/**
 * @file nmi_int.c
 *
 * @remark Copyright 2002-2009 OProfile authors
 * @remark Read the file COPYING
 *
 * @author John Levon <levon@movementarian.org>
 * @author Robert Richter <robert.richter@amd.com>
 * @author Barry Kasindorf <barry.kasindorf@amd.com>
 * @author Jason Yeh <jason.yeh@amd.com>
 * @author Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
 */

#include <linux/init.h>
#include <linux/notifier.h>
#include <linux/smp.h>
#include <linux/oprofile.h>
#include <linux/sysdev.h>
#include <linux/slab.h>
#include <linux/moduleparam.h>
#include <linux/kdebug.h>
#include <linux/cpu.h>
#include <asm/nmi.h>
#include <asm/msr.h>
#include <asm/apic.h>

#include "op_counter.h"
#include "op_x86_model.h"

static struct op_x86_model_spec *model;
static DEFINE_PER_CPU(struct op_msrs, cpu_msrs);
static DEFINE_PER_CPU(unsigned long, saved_lvtpc);

/* must be protected with get_online_cpus()/put_online_cpus(): */
static int nmi_enabled;
static int ctr_running;

struct op_counter_config counter_config[OP_MAX_COUNTER];

/* common functions */

u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
		    struct op_counter_config *counter_config)
{
	u64 val = 0;
	u16 event = (u16)counter_config->event;

	val |= ARCH_PERFMON_EVENTSEL_INT;
	val |= counter_config->user ? ARCH_PERFMON_EVENTSEL_USR : 0;
	val |= counter_config->kernel ? ARCH_PERFMON_EVENTSEL_OS : 0;
	val |= (counter_config->unit_mask & 0xFF) << 8;
	event &= model->event_mask ? model->event_mask : 0xFF;
	val |= event & 0xFF;
	val |= (event & 0x0F00) << 24;

	return val;
}


static int profile_exceptions_notify(struct notifier_block *self,
				     unsigned long val, void *data)
{
	struct die_args *args = (struct die_args *)data;
	int ret = NOTIFY_DONE;

	switch (val) {
	case DIE_NMI:
	case DIE_NMI_IPI:
		if (ctr_running)
			model->check_ctrs(args->regs, &__get_cpu_var(cpu_msrs));
		else if (!nmi_enabled)
			break;
		else
			model->stop(&__get_cpu_var(cpu_msrs));
		ret = NOTIFY_STOP;
		break;
	default:
		break;
	}
	return ret;
}

static void nmi_cpu_save_registers(struct op_msrs *msrs)
{
	struct op_msr *counters = msrs->counters;
	struct op_msr *controls = msrs->controls;
	unsigned int i;

	for (i = 0; i < model->num_counters; ++i) {
		if (counters[i].addr)
			rdmsrl(counters[i].addr, counters[i].saved);
	}

	for (i = 0; i < model->num_controls; ++i) {
		if (controls[i].addr)
			rdmsrl(controls[i].addr, controls[i].saved);
	}
}

static void nmi_cpu_start(void *dummy)
{
	struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
	if (!msrs->controls)
		WARN_ON_ONCE(1);
	else
		model->start(msrs);
}

static int nmi_start(void)
{
	get_online_cpus();
	on_each_cpu(nmi_cpu_start, NULL, 1);
	ctr_running = 1;
	put_online_cpus();
	return 0;
}

static void nmi_cpu_stop(void *dummy)
{
	struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
	if (!msrs->controls)
		WARN_ON_ONCE(1);
	else
		model->stop(msrs);
}

static void nmi_stop(void)
{
	get_online_cpus();
	on_each_cpu(nmi_cpu_stop, NULL, 1);
	ctr_running = 0;
	put_online_cpus();
}

#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX

static DEFINE_PER_CPU(int, switch_index);

static inline int has_mux(void)
{
	return !!model->switch_ctrl;
}

inline int op_x86_phys_to_virt(int phys)
{
	return __get_cpu_var(switch_index) + phys;
}

inline int op_x86_virt_to_phys(int virt)
{
	return virt % model->num_counters;
}

static void nmi_shutdown_mux(void)
{
	int i;

	if (!has_mux())
		return;

	for_each_possible_cpu(i) {
		kfree(per_cpu(cpu_msrs, i).multiplex);
		per_cpu(cpu_msrs, i).multiplex = NULL;
		per_cpu(switch_index, i) = 0;
	}
}

static int nmi_setup_mux(void)
{
	size_t multiplex_size =
		sizeof(struct op_msr) * model->num_virt_counters;
	int i;

	if (!has_mux())
		return 1;

	for_each_possible_cpu(i) {
		per_cpu(cpu_msrs, i).multiplex =
			kzalloc(multiplex_size, GFP_KERNEL);
		if (!per_cpu(cpu_msrs, i).multiplex)
			return 0;
	}

	return 1;
}

static void nmi_cpu_setup_mux(int cpu, struct op_msrs const * const msrs)
{
	int i;
	struct op_msr *multiplex = msrs->multiplex;

	if (!has_mux())
		return;

	for (i = 0; i < model->num_virt_counters; ++i) {
		if (counter_config[i].enabled) {
			multiplex[i].saved = -(u64)counter_config[i].count;
		} else {
			multiplex[i].saved = 0;
		}
	}

	per_cpu(switch_index, cpu) = 0;
}

static void nmi_cpu_save_mpx_registers(struct op_msrs *msrs)
{
	struct op_msr *counters = msrs->counters;
	struct op_msr *multiplex = msrs->multiplex;
	int i;

	for (i = 0; i < model->num_counters; ++i) {
		int virt = op_x86_phys_to_virt(i);
		if (counters[i].addr)
			rdmsrl(counters[i].addr, multiplex[virt].saved);
	}
}

static void nmi_cpu_restore_mpx_registers(struct op_msrs *msrs)
{
	struct op_msr *counters = msrs->counters;
	struct op_msr *multiplex = msrs->multiplex;
	int i;

	for (i = 0; i < model->num_counters; ++i) {
		int virt = op_x86_phys_to_virt(i);
		if (counters[i].addr)
			wrmsrl(counters[i].addr, multiplex[virt].saved);
	}
}

static void nmi_cpu_switch(void *dummy)
{
	int cpu = smp_processor_id();
	int si = per_cpu(switch_index, cpu);
	struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu);

	nmi_cpu_stop(NULL);
	nmi_cpu_save_mpx_registers(msrs);

	/* move to next set */
	si += model->num_counters;
	if ((si >= model->num_virt_counters) || (counter_config[si].count == 0))
		per_cpu(switch_index, cpu) = 0;
	else
		per_cpu(switch_index, cpu) = si;

	model->switch_ctrl(model, msrs);
	nmi_cpu_restore_mpx_registers(msrs);

	nmi_cpu_start(NULL);
}


/*
 * Quick check to see if multiplexing is necessary.
 * The check should be sufficient since counters are used
 * in ordre.
 */
static int nmi_multiplex_on(void)
{
	return counter_config[model->num_counters].count ? 0 : -EINVAL;
}

static int nmi_switch_event(void)
{
	if (!has_mux())
		return -ENOSYS;		/* not implemented */
	if (nmi_multiplex_on() < 0)
		return -EINVAL;		/* not necessary */

	get_online_cpus();
	if (ctr_running)
		on_each_cpu(nmi_cpu_switch, NULL, 1);
	put_online_cpus();

	return 0;
}

static inline void mux_init(struct oprofile_operations *ops)
{
	if (has_mux())
		ops->switch_events = nmi_switch_event;
}

static void mux_clone(int cpu)
{
	if (!has_mux())
		return;

	memcpy(per_cpu(cpu_msrs, cpu).multiplex,
	       per_cpu(cpu_msrs, 0).multiplex,
	       sizeof(struct op_msr) * model->num_virt_counters);
}

#else

inline int op_x86_phys_to_virt(int phys) { return phys; }
inline int op_x86_virt_to_phys(int virt) { return virt; }
static inline void nmi_shutdown_mux(void) { }
static inline int nmi_setup_mux(void) { return 1; }
static inline void
nmi_cpu_setup_mux(int cpu, struct op_msrs const * const msrs) { }
static inline void mux_init(struct oprofile_operations *ops) { }
static void mux_clone(int cpu) { }

#endif

static void free_msrs(void)
{
	int i;
	for_each_possible_cpu(i) {
		kfree(per_cpu(cpu_msrs, i).counters);
		per_cpu(cpu_msrs, i).counters = NULL;
		kfree(per_cpu(cpu_msrs, i).controls);
		per_cpu(cpu_msrs, i).controls = NULL;
	}
	nmi_shutdown_mux();
}

static int allocate_msrs(void)
{
	size_t controls_size = sizeof(struct op_msr) * model->num_controls;
	size_t counters_size = sizeof(struct op_msr) * model->num_counters;

	int i;
	for_each_possible_cpu(i) {
		per_cpu(cpu_msrs, i).counters = kzalloc(counters_size,
							GFP_KERNEL);
		if (!per_cpu(cpu_msrs, i).counters)
			goto fail;
		per_cpu(cpu_msrs, i).controls = kzalloc(controls_size,
							GFP_KERNEL);
		if (!per_cpu(cpu_msrs, i).controls)
			goto fail;
	}

	if (!nmi_setup_mux())
		goto fail;

	return 1;

fail:
	free_msrs();
	return 0;
}

static void nmi_cpu_setup(void *dummy)
{
	int cpu = smp_processor_id();
	struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu);
	nmi_cpu_save_registers(msrs);
	spin_lock(&oprofilefs_lock);
	model->setup_ctrs(model, msrs);
	nmi_cpu_setup_mux(cpu, msrs);
	spin_unlock(&oprofilefs_lock);
	per_cpu(saved_lvtpc, cpu) = apic_read(APIC_LVTPC);
	apic_write(APIC_LVTPC, APIC_DM_NMI);
}

static struct notifier_block profile_exceptions_nb = {
	.notifier_call = profile_exceptions_notify,
	.next = NULL,
	.priority = 2
};

static void nmi_cpu_restore_registers(struct op_msrs *msrs)
{
	struct op_msr *counters = msrs->counters;
	struct op_msr *controls = msrs->controls;
	unsigned int i;

	for (i = 0; i < model->num_controls; ++i) {
		if (controls[i].addr)
			wrmsrl(controls[i].addr, controls[i].saved);
	}

	for (i = 0; i < model->num_counters; ++i) {
		if (counters[i].addr)
			wrmsrl(counters[i].addr, counters[i].saved);
	}
}

static void nmi_cpu_shutdown(void *dummy)
{
	unsigned int v;
	int cpu = smp_processor_id();
	struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu);

	/* restoring APIC_LVTPC can trigger an apic error because the delivery
	 * mode and vector nr combination can be illegal. That's by design: on
	 * power on apic lvt contain a zero vector nr which are legal only for
	 * NMI delivery mode. So inhibit apic err before restoring lvtpc
	 */
	v = apic_read(APIC_LVTERR);
	apic_write(APIC_LVTERR, v | APIC_LVT_MASKED);
	apic_write(APIC_LVTPC, per_cpu(saved_lvtpc, cpu));
	apic_write(APIC_LVTERR, v);
	nmi_cpu_restore_registers(msrs);
	if (model->cpu_down)
		model->cpu_down();
}

static void nmi_cpu_up(void *dummy)
{
	if (nmi_enabled)
		nmi_cpu_setup(dummy);
	if (ctr_running)
		nmi_cpu_start(dummy);
}

static void nmi_cpu_down(void *dummy)
{
	if (ctr_running)
		nmi_cpu_stop(dummy);
	if (nmi_enabled)
		nmi_cpu_shutdown(dummy);
}

static int nmi_create_files(struct super_block *sb, struct dentry *root)
{
	unsigned int i;

	for (i = 0; i < model->num_virt_counters; ++i) {
		struct dentry *dir;
		char buf[4];

		/* quick little hack to _not_ expose a counter if it is not
		 * available for use.  This should protect userspace app.
		 * NOTE:  assumes 1:1 mapping here (that counters are organized
		 *        sequentially in their struct assignment).
		 */
		if (!avail_to_resrv_perfctr_nmi_bit(op_x86_virt_to_phys(i)))
			continue;

		snprintf(buf,  sizeof(buf), "%d", i);
		dir = oprofilefs_mkdir(sb, root, buf);
		oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled);
		oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event);
		oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count);
		oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
		oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
		oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
	}

	return 0;
}

static int oprofile_cpu_notifier(struct notifier_block *b, unsigned long action,
				 void *data)
{
	int cpu = (unsigned long)data;
	switch (action) {
	case CPU_DOWN_FAILED:
	case CPU_ONLINE:
		smp_call_function_single(cpu, nmi_cpu_up, NULL, 0);
		break;
	case CPU_DOWN_PREPARE:
		smp_call_function_single(cpu, nmi_cpu_down, NULL, 1);
		break;
	}
	return NOTIFY_DONE;
}

static struct notifier_block oprofile_cpu_nb = {
	.notifier_call = oprofile_cpu_notifier
};

static int nmi_setup(void)
{
	int err = 0;
	int cpu;

	if (!allocate_msrs())
		return -ENOMEM;

	/* We need to serialize save and setup for HT because the subset
	 * of msrs are distinct for save and setup operations
	 */

	/* Assume saved/restored counters are the same on all CPUs */
	err = model->fill_in_addresses(&per_cpu(cpu_msrs, 0));
	if (err)
		goto fail;

	for_each_possible_cpu(cpu) {
		if (!cpu)
			continue;

		memcpy(per_cpu(cpu_msrs, cpu).counters,
		       per_cpu(cpu_msrs, 0).counters,
		       sizeof(struct op_msr) * model->num_counters);

		memcpy(per_cpu(cpu_msrs, cpu).controls,
		       per_cpu(cpu_msrs, 0).controls,
		       sizeof(struct op_msr) * model->num_controls);

		mux_clone(cpu);
	}

	nmi_enabled = 0;
	ctr_running = 0;
	barrier();
	err = register_die_notifier(&profile_exceptions_nb);
	if (err)
		goto fail;

	get_online_cpus();
	register_cpu_notifier(&oprofile_cpu_nb);
	on_each_cpu(nmi_cpu_setup, NULL, 1);
	nmi_enabled = 1;
	put_online_cpus();

	return 0;
fail:
	free_msrs();
	return err;
}

static void nmi_shutdown(void)
{
	struct op_msrs *msrs;

	get_online_cpus();
	unregister_cpu_notifier(&oprofile_cpu_nb);
	on_each_cpu(nmi_cpu_shutdown, NULL, 1);
	nmi_enabled = 0;
	ctr_running = 0;
	put_online_cpus();
	barrier();
	unregister_die_notifier(&profile_exceptions_nb);
	msrs = &get_cpu_var(cpu_msrs);
	model->shutdown(msrs);
	free_msrs();
	put_cpu_var(cpu_msrs);
}

#ifdef CONFIG_PM

static int nmi_suspend(struct sys_device *dev, pm_message_t state)
{
	/* Only one CPU left, just stop that one */
	if (nmi_enabled == 1)
		nmi_cpu_stop(NULL);
	return 0;
}

static int nmi_resume(struct sys_device *dev)
{
	if (nmi_enabled == 1)
		nmi_cpu_start(NULL);
	return 0;
}

static struct sysdev_class oprofile_sysclass = {
	.name		= "oprofile",
	.resume		= nmi_resume,
	.suspend	= nmi_suspend,
};

static struct sys_device device_oprofile = {
	.id	= 0,
	.cls	= &oprofile_sysclass,
};

static int __init init_sysfs(void)
{
	int error;

	error = sysdev_class_register(&oprofile_sysclass);
	if (!error)
		error = sysdev_register(&device_oprofile);
	return error;
}

static void exit_sysfs(void)
{
	sysdev_unregister(&device_oprofile);
	sysdev_class_unregister(&oprofile_sysclass);
}

#else
#define init_sysfs() do { } while (0)
#define exit_sysfs() do { } while (0)
#endif /* CONFIG_PM */

static int __init p4_init(char **cpu_type)
{
	__u8 cpu_model = boot_cpu_data.x86_model;

	if (cpu_model > 6 || cpu_model == 5)
		return 0;

#ifndef CONFIG_SMP
	*cpu_type = "i386/p4";
	model = &op_p4_spec;
	return 1;
#else
	switch (smp_num_siblings) {
	case 1:
		*cpu_type = "i386/p4";
		model = &op_p4_spec;
		return 1;

	case 2:
		*cpu_type = "i386/p4-ht";
		model = &op_p4_ht2_spec;
		return 1;
	}
#endif

	printk(KERN_INFO "oprofile: P4 HyperThreading detected with > 2 threads\n");
	printk(KERN_INFO "oprofile: Reverting to timer mode.\n");
	return 0;
}

static int force_arch_perfmon;
static int force_cpu_type(const char *str, struct kernel_param *kp)
{
	if (!strcmp(str, "arch_perfmon")) {
		force_arch_perfmon = 1;
		printk(KERN_INFO "oprofile: forcing architectural perfmon\n");
	}

	return 0;
}
module_param_call(cpu_type, force_cpu_type, NULL, NULL, 0);

static int __init ppro_init(char **cpu_type)
{
	__u8 cpu_model = boot_cpu_data.x86_model;
	struct op_x86_model_spec *spec = &op_ppro_spec;	/* default */

	if (force_arch_perfmon && cpu_has_arch_perfmon)
		return 0;

	/*
	 * Documentation on identifying Intel processors by CPU family
	 * and model can be found in the Intel Software Developer's
	 * Manuals (SDM):
	 *
	 *  http://www.intel.com/products/processor/manuals/
	 *
	 * As of May 2010 the documentation for this was in the:
	 * "Intel 64 and IA-32 Architectures Software Developer's
	 * Manual Volume 3B: System Programming Guide", "Table B-1
	 * CPUID Signature Values of DisplayFamily_DisplayModel".
	 */
	switch (cpu_model) {
	case 0 ... 2:
		*cpu_type = "i386/ppro";
		break;
	case 3 ... 5:
		*cpu_type = "i386/pii";
		break;
	case 6 ... 8:
	case 10 ... 11:
		*cpu_type = "i386/piii";
		break;
	case 9:
	case 13:
		*cpu_type = "i386/p6_mobile";
		break;
	case 14:
		*cpu_type = "i386/core";
		break;
	case 15: case 23:
		*cpu_type = "i386/core_2";
		break;
	case 0x1a:
	case 0x2e:
		spec = &op_arch_perfmon_spec;
		*cpu_type = "i386/core_i7";
		break;
	case 0x1c:
		*cpu_type = "i386/atom";
		break;
	default:
		/* Unknown */
		return 0;
	}

	model = spec;
	return 1;
}

/* in order to get sysfs right */
static int using_nmi;

int __init op_nmi_init(struct oprofile_operations *ops)
{
	__u8 vendor = boot_cpu_data.x86_vendor;
	__u8 family = boot_cpu_data.x86;
	char *cpu_type = NULL;
	int ret = 0;

	if (!cpu_has_apic)
		return -ENODEV;

	switch (vendor) {
	case X86_VENDOR_AMD:
		/* Needs to be at least an Athlon (or hammer in 32bit mode) */

		switch (family) {
		case 6:
			cpu_type = "i386/athlon";
			break;
		case 0xf:
			/*
			 * Actually it could be i386/hammer too, but
			 * give user space an consistent name.
			 */
			cpu_type = "x86-64/hammer";
			break;
		case 0x10:
			cpu_type = "x86-64/family10";
			break;
		case 0x11:
			cpu_type = "x86-64/family11h";
			break;
		default:
			return -ENODEV;
		}
		model = &op_amd_spec;
		break;

	case X86_VENDOR_INTEL:
		switch (family) {
			/* Pentium IV */
		case 0xf:
			p4_init(&cpu_type);
			break;

			/* A P6-class processor */
		case 6:
			ppro_init(&cpu_type);
			break;

		default:
			break;
		}

		if (cpu_type)
			break;

		if (!cpu_has_arch_perfmon)
			return -ENODEV;

		/* use arch perfmon as fallback */
		cpu_type = "i386/arch_perfmon";
		model = &op_arch_perfmon_spec;
		break;

	default:
		return -ENODEV;
	}

	/* default values, can be overwritten by model */
	ops->create_files	= nmi_create_files;
	ops->setup		= nmi_setup;
	ops->shutdown		= nmi_shutdown;
	ops->start		= nmi_start;
	ops->stop		= nmi_stop;
	ops->cpu_type		= cpu_type;

	if (model->init)
		ret = model->init(ops);
	if (ret)
		return ret;

	if (!model->num_virt_counters)
		model->num_virt_counters = model->num_counters;

	mux_init(ops);

	init_sysfs();
	using_nmi = 1;
	printk(KERN_INFO "oprofile: using NMI interrupt.\n");
	return 0;
}

void op_nmi_exit(void)
{
	if (using_nmi)
		exit_sysfs();
}