aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/oprofile/op_model_amd.c
blob: 9cbb710dc94b6ee8c6df0fec2004173ac667d882 (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
/*
 * @file op_model_amd.c
 * athlon / K7 / K8 / Family 10h model-specific MSR operations
 *
 * @remark Copyright 2002-2009 OProfile authors
 * @remark Read the file COPYING
 *
 * @author John Levon
 * @author Philippe Elie
 * @author Graydon Hoare
 * @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/oprofile.h>
#include <linux/device.h>
#include <linux/pci.h>
#include <linux/percpu.h>

#include <asm/ptrace.h>
#include <asm/msr.h>
#include <asm/nmi.h>
#include <asm/apic.h>
#include <asm/processor.h>
#include <asm/cpufeature.h>

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

#define NUM_COUNTERS		4
#define NUM_COUNTERS_F15H	6
#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
#define NUM_VIRT_COUNTERS	32
#else
#define NUM_VIRT_COUNTERS	0
#endif

#define OP_EVENT_MASK			0x0FFF
#define OP_CTR_OVERFLOW			(1ULL<<31)

#define MSR_AMD_EVENTSEL_RESERVED	((0xFFFFFCF0ULL<<32)|(1ULL<<21))

static int num_counters;
static unsigned long reset_value[OP_MAX_COUNTER];

#define IBS_FETCH_SIZE			6
#define IBS_OP_SIZE			12

static u32 ibs_caps;

struct ibs_config {
	unsigned long op_enabled;
	unsigned long fetch_enabled;
	unsigned long max_cnt_fetch;
	unsigned long max_cnt_op;
	unsigned long rand_en;
	unsigned long dispatched_ops;
	unsigned long branch_target;
};

struct ibs_state {
	u64		ibs_op_ctl;
	int		branch_target;
	unsigned long	sample_size;
};

static struct ibs_config ibs_config;
static struct ibs_state ibs_state;

/*
 * IBS cpuid feature detection
 */

#define IBS_CPUID_FEATURES		0x8000001b

/*
 * Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but
 * bit 0 is used to indicate the existence of IBS.
 */
#define IBS_CAPS_AVAIL			(1U<<0)
#define IBS_CAPS_FETCHSAM		(1U<<1)
#define IBS_CAPS_OPSAM			(1U<<2)
#define IBS_CAPS_RDWROPCNT		(1U<<3)
#define IBS_CAPS_OPCNT			(1U<<4)
#define IBS_CAPS_BRNTRGT		(1U<<5)
#define IBS_CAPS_OPCNTEXT		(1U<<6)

#define IBS_CAPS_DEFAULT		(IBS_CAPS_AVAIL		\
					 | IBS_CAPS_FETCHSAM	\
					 | IBS_CAPS_OPSAM)

/*
 * IBS APIC setup
 */
#define IBSCTL				0x1cc
#define IBSCTL_LVT_OFFSET_VALID		(1ULL<<8)
#define IBSCTL_LVT_OFFSET_MASK		0x0F

/*
 * IBS randomization macros
 */
#define IBS_RANDOM_BITS			12
#define IBS_RANDOM_MASK			((1ULL << IBS_RANDOM_BITS) - 1)
#define IBS_RANDOM_MAXCNT_OFFSET	(1ULL << (IBS_RANDOM_BITS - 5))

static u32 get_ibs_caps(void)
{
	u32 ibs_caps;
	unsigned int max_level;

	if (!boot_cpu_has(X86_FEATURE_IBS))
		return 0;

	/* check IBS cpuid feature flags */
	max_level = cpuid_eax(0x80000000);
	if (max_level < IBS_CPUID_FEATURES)
		return IBS_CAPS_DEFAULT;

	ibs_caps = cpuid_eax(IBS_CPUID_FEATURES);
	if (!(ibs_caps & IBS_CAPS_AVAIL))
		/* cpuid flags not valid */
		return IBS_CAPS_DEFAULT;

	return ibs_caps;
}

/*
 * 16-bit Linear Feedback Shift Register (LFSR)
 *
 *                       16   14   13    11
 * Feedback polynomial = X  + X  + X  +  X  + 1
 */
static unsigned int lfsr_random(void)
{
	static unsigned int lfsr_value = 0xF00D;
	unsigned int bit;

	/* Compute next bit to shift in */
	bit = ((lfsr_value >> 0) ^
	       (lfsr_value >> 2) ^
	       (lfsr_value >> 3) ^
	       (lfsr_value >> 5)) & 0x0001;

	/* Advance to next register value */
	lfsr_value = (lfsr_value >> 1) | (bit << 15);

	return lfsr_value;
}

/*
 * IBS software randomization
 *
 * The IBS periodic op counter is randomized in software. The lower 12
 * bits of the 20 bit counter are randomized. IbsOpCurCnt is
 * initialized with a 12 bit random value.
 */
static inline u64 op_amd_randomize_ibs_op(u64 val)
{
	unsigned int random = lfsr_random();

	if (!(ibs_caps & IBS_CAPS_RDWROPCNT))
		/*
		 * Work around if the hw can not write to IbsOpCurCnt
		 *
		 * Randomize the lower 8 bits of the 16 bit
		 * IbsOpMaxCnt [15:0] value in the range of -128 to
		 * +127 by adding/subtracting an offset to the
		 * maximum count (IbsOpMaxCnt).
		 *
		 * To avoid over or underflows and protect upper bits
		 * starting at bit 16, the initial value for
		 * IbsOpMaxCnt must fit in the range from 0x0081 to
		 * 0xff80.
		 */
		val += (s8)(random >> 4);
	else
		val |= (u64)(random & IBS_RANDOM_MASK) << 32;

	return val;
}

static inline void
op_amd_handle_ibs(struct pt_regs * const regs,
		  struct op_msrs const * const msrs)
{
	u64 val, ctl;
	struct op_entry entry;

	if (!ibs_caps)
		return;

	if (ibs_config.fetch_enabled) {
		rdmsrl(MSR_AMD64_IBSFETCHCTL, ctl);
		if (ctl & IBS_FETCH_VAL) {
			rdmsrl(MSR_AMD64_IBSFETCHLINAD, val);
			oprofile_write_reserve(&entry, regs, val,
					       IBS_FETCH_CODE, IBS_FETCH_SIZE);
			oprofile_add_data64(&entry, val);
			oprofile_add_data64(&entry, ctl);
			rdmsrl(MSR_AMD64_IBSFETCHPHYSAD, val);
			oprofile_add_data64(&entry, val);
			oprofile_write_commit(&entry);

			/* reenable the IRQ */
			ctl &= ~(IBS_FETCH_VAL | IBS_FETCH_CNT);
			ctl |= IBS_FETCH_ENABLE;
			wrmsrl(MSR_AMD64_IBSFETCHCTL, ctl);
		}
	}

	if (ibs_config.op_enabled) {
		rdmsrl(MSR_AMD64_IBSOPCTL, ctl);
		if (ctl & IBS_OP_VAL) {
			rdmsrl(MSR_AMD64_IBSOPRIP, val);
			oprofile_write_reserve(&entry, regs, val, IBS_OP_CODE,
					       ibs_state.sample_size);
			oprofile_add_data64(&entry, val);
			rdmsrl(MSR_AMD64_IBSOPDATA, val);
			oprofile_add_data64(&entry, val);
			rdmsrl(MSR_AMD64_IBSOPDATA2, val);
			oprofile_add_data64(&entry, val);
			rdmsrl(MSR_AMD64_IBSOPDATA3, val);
			oprofile_add_data64(&entry, val);
			rdmsrl(MSR_AMD64_IBSDCLINAD, val);
			oprofile_add_data64(&entry, val);
			rdmsrl(MSR_AMD64_IBSDCPHYSAD, val);
			oprofile_add_data64(&entry, val);
			if (ibs_state.branch_target) {
				rdmsrl(MSR_AMD64_IBSBRTARGET, val);
				oprofile_add_data(&entry, (unsigned long)val);
			}
			oprofile_write_commit(&entry);

			/* reenable the IRQ */
			ctl = op_amd_randomize_ibs_op(ibs_state.ibs_op_ctl);
			wrmsrl(MSR_AMD64_IBSOPCTL, ctl);
		}
	}
}

static inline void op_amd_start_ibs(void)
{
	u64 val;

	if (!ibs_caps)
		return;

	memset(&ibs_state, 0, sizeof(ibs_state));

	/*
	 * Note: Since the max count settings may out of range we
	 * write back the actual used values so that userland can read
	 * it.
	 */

	if (ibs_config.fetch_enabled) {
		val = ibs_config.max_cnt_fetch >> 4;
		val = min(val, IBS_FETCH_MAX_CNT);
		ibs_config.max_cnt_fetch = val << 4;
		val |= ibs_config.rand_en ? IBS_FETCH_RAND_EN : 0;
		val |= IBS_FETCH_ENABLE;
		wrmsrl(MSR_AMD64_IBSFETCHCTL, val);
	}

	if (ibs_config.op_enabled) {
		val = ibs_config.max_cnt_op >> 4;
		if (!(ibs_caps & IBS_CAPS_RDWROPCNT)) {
			/*
			 * IbsOpCurCnt not supported.  See
			 * op_amd_randomize_ibs_op() for details.
			 */
			val = clamp(val, 0x0081ULL, 0xFF80ULL);
			ibs_config.max_cnt_op = val << 4;
		} else {
			/*
			 * The start value is randomized with a
			 * positive offset, we need to compensate it
			 * with the half of the randomized range. Also
			 * avoid underflows.
			 */
			val += IBS_RANDOM_MAXCNT_OFFSET;
			if (ibs_caps & IBS_CAPS_OPCNTEXT)
				val = min(val, IBS_OP_MAX_CNT_EXT);
			else
				val = min(val, IBS_OP_MAX_CNT);
			ibs_config.max_cnt_op =
				(val - IBS_RANDOM_MAXCNT_OFFSET) << 4;
		}
		val = ((val & ~IBS_OP_MAX_CNT) << 4) | (val & IBS_OP_MAX_CNT);
		val |= ibs_config.dispatched_ops ? IBS_OP_CNT_CTL : 0;
		val |= IBS_OP_ENABLE;
		ibs_state.ibs_op_ctl = val;
		ibs_state.sample_size = IBS_OP_SIZE;
		if (ibs_config.branch_target) {
			ibs_state.branch_target = 1;
			ibs_state.sample_size++;
		}
		val = op_amd_randomize_ibs_op(ibs_state.ibs_op_ctl);
		wrmsrl(MSR_AMD64_IBSOPCTL, val);
	}
}

static void op_amd_stop_ibs(void)
{
	if (!ibs_caps)
		return;

	if (ibs_config.fetch_enabled)
		/* clear max count and enable */
		wrmsrl(MSR_AMD64_IBSFETCHCTL, 0);

	if (ibs_config.op_enabled)
		/* clear max count and enable */
		wrmsrl(MSR_AMD64_IBSOPCTL, 0);
}

static inline int get_eilvt(int offset)
{
	return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1);
}

static inline int put_eilvt(int offset)
{
	return !setup_APIC_eilvt(offset, 0, 0, 1);
}

static inline int ibs_eilvt_valid(void)
{
	int offset;
	u64 val;
	int valid = 0;

	preempt_disable();

	rdmsrl(MSR_AMD64_IBSCTL, val);
	offset = val & IBSCTL_LVT_OFFSET_MASK;

	if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
		pr_err(FW_BUG "cpu %d, invalid IBS interrupt offset %d (MSR%08X=0x%016llx)\n",
		       smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
		goto out;
	}

	if (!get_eilvt(offset)) {
		pr_err(FW_BUG "cpu %d, IBS interrupt offset %d not available (MSR%08X=0x%016llx)\n",
		       smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
		goto out;
	}

	valid = 1;
out:
	preempt_enable();

	return valid;
}

static inline int get_ibs_offset(void)
{
	u64 val;

	rdmsrl(MSR_AMD64_IBSCTL, val);
	if (!(val & IBSCTL_LVT_OFFSET_VALID))
		return -EINVAL;

	return val & IBSCTL_LVT_OFFSET_MASK;
}

static void setup_APIC_ibs(void)
{
	int offset;

	offset = get_ibs_offset();
	if (offset < 0)
		goto failed;

	if (!setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 0))
		return;
failed:
	pr_warn("oprofile: IBS APIC setup failed on cpu #%d\n",
		smp_processor_id());
}

static void clear_APIC_ibs(void)
{
	int offset;

	offset = get_ibs_offset();
	if (offset >= 0)
		setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
}

#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX

static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
			       struct op_msrs const * const msrs)
{
	u64 val;
	int i;

	/* enable active counters */
	for (i = 0; i < num_counters; ++i) {
		int virt = op_x86_phys_to_virt(i);
		if (!reset_value[virt])
			continue;
		rdmsrl(msrs->controls[i].addr, val);
		val &= model->reserved;
		val |= op_x86_get_ctrl(model, &counter_config[virt]);
		wrmsrl(msrs->controls[i].addr, val);
	}
}

#endif

/* functions for op_amd_spec */

static void op_amd_shutdown(struct op_msrs const * const msrs)
{
	int i;

	for (i = 0; i < num_counters; ++i) {
		if (!msrs->counters[i].addr)
			continue;
		release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
		release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
	}
}

static int op_amd_fill_in_addresses(struct op_msrs * const msrs)
{
	int i;

	for (i = 0; i < num_counters; i++) {
		if (!reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i))
			goto fail;
		if (!reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) {
			release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
			goto fail;
		}
		/* both registers must be reserved */
		if (num_counters == NUM_COUNTERS_F15H) {
			msrs->counters[i].addr = MSR_F15H_PERF_CTR + (i << 1);
			msrs->controls[i].addr = MSR_F15H_PERF_CTL + (i << 1);
		} else {
			msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i;
			msrs->counters[i].addr = MSR_K7_PERFCTR0 + i;
		}
		continue;
	fail:
		if (!counter_config[i].enabled)
			continue;
		op_x86_warn_reserved(i);
		op_amd_shutdown(msrs);
		return -EBUSY;
	}

	return 0;
}

static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
			      struct op_msrs const * const msrs)
{
	u64 val;
	int i;

	/* setup reset_value */
	for (i = 0; i < OP_MAX_COUNTER; ++i) {
		if (counter_config[i].enabled
		    && msrs->counters[op_x86_virt_to_phys(i)].addr)
			reset_value[i] = counter_config[i].count;
		else
			reset_value[i] = 0;
	}

	/* clear all counters */
	for (i = 0; i < num_counters; ++i) {
		if (!msrs->controls[i].addr)
			continue;
		rdmsrl(msrs->controls[i].addr, val);
		if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
			op_x86_warn_in_use(i);
		val &= model->reserved;
		wrmsrl(msrs->controls[i].addr, val);
		/*
		 * avoid a false detection of ctr overflows in NMI
		 * handler
		 */
		wrmsrl(msrs->counters[i].addr, -1LL);
	}

	/* enable active counters */
	for (i = 0; i < num_counters; ++i) {
		int virt = op_x86_phys_to_virt(i);
		if (!reset_value[virt])
			continue;

		/* setup counter registers */
		wrmsrl(msrs->counters[i].addr, -(u64)reset_value[virt]);

		/* setup control registers */
		rdmsrl(msrs->controls[i].addr, val);
		val &= model->reserved;
		val |= op_x86_get_ctrl(model, &counter_config[virt]);
		wrmsrl(msrs->controls[i].addr, val);
	}

	if (ibs_caps)
		setup_APIC_ibs();
}

static void op_amd_cpu_shutdown(void)
{
	if (ibs_caps)
		clear_APIC_ibs();
}

static int op_amd_check_ctrs(struct pt_regs * const regs,
			     struct op_msrs const * const msrs)
{
	u64 val;
	int i;

	for (i = 0; i < num_counters; ++i) {
		int virt = op_x86_phys_to_virt(i);
		if (!reset_value[virt])
			continue;
		rdmsrl(msrs->counters[i].addr, val);
		/* bit is clear if overflowed: */
		if (val & OP_CTR_OVERFLOW)
			continue;
		oprofile_add_sample(regs, virt);
		wrmsrl(msrs->counters[i].addr, -(u64)reset_value[virt]);
	}

	op_amd_handle_ibs(regs, msrs);

	/* See op_model_ppro.c */
	return 1;
}

static void op_amd_start(struct op_msrs const * const msrs)
{
	u64 val;
	int i;

	for (i = 0; i < num_counters; ++i) {
		if (!reset_value[op_x86_phys_to_virt(i)])
			continue;
		rdmsrl(msrs->controls[i].addr, val);
		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
		wrmsrl(msrs->controls[i].addr, val);
	}

	op_amd_start_ibs();
}

static void op_amd_stop(struct op_msrs const * const msrs)
{
	u64 val;
	int i;

	/*
	 * Subtle: stop on all counters to avoid race with setting our
	 * pm callback
	 */
	for (i = 0; i < num_counters; ++i) {
		if (!reset_value[op_x86_phys_to_virt(i)])
			continue;
		rdmsrl(msrs->controls[i].addr, val);
		val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
		wrmsrl(msrs->controls[i].addr, val);
	}

	op_amd_stop_ibs();
}

static int setup_ibs_ctl(int ibs_eilvt_off)
{
	struct pci_dev *cpu_cfg;
	int nodes;
	u32 value = 0;

	nodes = 0;
	cpu_cfg = NULL;
	do {
		cpu_cfg = pci_get_device(PCI_VENDOR_ID_AMD,
					 PCI_DEVICE_ID_AMD_10H_NB_MISC,
					 cpu_cfg);
		if (!cpu_cfg)
			break;
		++nodes;
		pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off
				       | IBSCTL_LVT_OFFSET_VALID);
		pci_read_config_dword(cpu_cfg, IBSCTL, &value);
		if (value != (ibs_eilvt_off | IBSCTL_LVT_OFFSET_VALID)) {
			pci_dev_put(cpu_cfg);
			printk(KERN_DEBUG "Failed to setup IBS LVT offset, "
			       "IBSCTL = 0x%08x\n", value);
			return -EINVAL;
		}
	} while (1);

	if (!nodes) {
		printk(KERN_DEBUG "No CPU node configured for IBS\n");
		return -ENODEV;
	}

	return 0;
}

/*
 * This runs only on the current cpu. We try to find an LVT offset and
 * setup the local APIC. For this we must disable preemption. On
 * success we initialize all nodes with this offset. This updates then
 * the offset in the IBS_CTL per-node msr. The per-core APIC setup of
 * the IBS interrupt vector is called from op_amd_setup_ctrs()/op_-
 * amd_cpu_shutdown() using the new offset.
 */
static int force_ibs_eilvt_setup(void)
{
	int offset;
	int ret;

	preempt_disable();
	/* find the next free available EILVT entry, skip offset 0 */
	for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) {
		if (get_eilvt(offset))
			break;
	}
	preempt_enable();

	if (offset == APIC_EILVT_NR_MAX) {
		printk(KERN_DEBUG "No EILVT entry available\n");
		return -EBUSY;
	}

	ret = setup_ibs_ctl(offset);
	if (ret)
		goto out;

	if (!ibs_eilvt_valid()) {
		ret = -EFAULT;
		goto out;
	}

	pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset);
	pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");

	return 0;
out:
	preempt_disable();
	put_eilvt(offset);
	preempt_enable();
	return ret;
}

/*
 * check and reserve APIC extended interrupt LVT offset for IBS if
 * available
 */

static void init_ibs(void)
{
	ibs_caps = get_ibs_caps();

	if (!ibs_caps)
		return;

	if (ibs_eilvt_valid())
		goto out;

	if (!force_ibs_eilvt_setup())
		goto out;

	/* Failed to setup ibs */
	ibs_caps = 0;
	return;

out:
	printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
}

static int (*create_arch_files)(struct super_block *sb, struct dentry *root);

static int setup_ibs_files(struct super_block *sb, struct dentry *root)
{
	struct dentry *dir;
	int ret = 0;

	/* architecture specific files */
	if (create_arch_files)
		ret = create_arch_files(sb, root);

	if (ret)
		return ret;

	if (!ibs_caps)
		return ret;

	/* model specific files */

	/* setup some reasonable defaults */
	memset(&ibs_config, 0, sizeof(ibs_config));
	ibs_config.max_cnt_fetch = 250000;
	ibs_config.max_cnt_op = 250000;

	if (ibs_caps & IBS_CAPS_FETCHSAM) {
		dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
		oprofilefs_create_ulong(sb, dir, "enable",
					&ibs_config.fetch_enabled);
		oprofilefs_create_ulong(sb, dir, "max_count",
					&ibs_config.max_cnt_fetch);
		oprofilefs_create_ulong(sb, dir, "rand_enable",
					&ibs_config.rand_en);
	}

	if (ibs_caps & IBS_CAPS_OPSAM) {
		dir = oprofilefs_mkdir(sb, root, "ibs_op");
		oprofilefs_create_ulong(sb, dir, "enable",
					&ibs_config.op_enabled);
		oprofilefs_create_ulong(sb, dir, "max_count",
					&ibs_config.max_cnt_op);
		if (ibs_caps & IBS_CAPS_OPCNT)
			oprofilefs_create_ulong(sb, dir, "dispatched_ops",
						&ibs_config.dispatched_ops);
		if (ibs_caps & IBS_CAPS_BRNTRGT)
			oprofilefs_create_ulong(sb, dir, "branch_target",
						&ibs_config.branch_target);
	}

	return 0;
}

struct op_x86_model_spec op_amd_spec;

static int op_amd_init(struct oprofile_operations *ops)
{
	init_ibs();
	create_arch_files = ops->create_files;
	ops->create_files = setup_ibs_files;

	if (boot_cpu_data.x86 == 0x15) {
		num_counters = NUM_COUNTERS_F15H;
	} else {
		num_counters = NUM_COUNTERS;
	}

	op_amd_spec.num_counters = num_counters;
	op_amd_spec.num_controls = num_counters;
	op_amd_spec.num_virt_counters = max(num_counters, NUM_VIRT_COUNTERS);

	return 0;
}

struct op_x86_model_spec op_amd_spec = {
	/* num_counters/num_controls filled in at runtime */
	.reserved		= MSR_AMD_EVENTSEL_RESERVED,
	.event_mask		= OP_EVENT_MASK,
	.init			= op_amd_init,
	.fill_in_addresses	= &op_amd_fill_in_addresses,
	.setup_ctrs		= &op_amd_setup_ctrs,
	.cpu_down		= &op_amd_cpu_shutdown,
	.check_ctrs		= &op_amd_check_ctrs,
	.start			= &op_amd_start,
	.stop			= &op_amd_stop,
	.shutdown		= &op_amd_shutdown,
#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
	.switch_ctrl		= &op_mux_switch_ctrl,
#endif
};