summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/pmu.c
blob: 827886c12c16e6a9b297ec58c1a997485288dadb (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Kernel-based Virtual Machine -- Performance Monitoring Unit support
 *
 * Copyright 2015 Red Hat, Inc. and/or its affiliates.
 *
 * Authors:
 *   Avi Kivity   <avi@redhat.com>
 *   Gleb Natapov <gleb@redhat.com>
 *   Wei Huang    <wei@redhat.com>
 */

#include <linux/types.h>
#include <linux/kvm_host.h>
#include <linux/perf_event.h>
#include <asm/perf_event.h>
#include "x86.h"
#include "cpuid.h"
#include "lapic.h"
#include "pmu.h"

/* This is enough to filter the vast majority of currently defined events. */
#define KVM_PMU_EVENT_FILTER_MAX_EVENTS 300

/* NOTE:
 * - Each perf counter is defined as "struct kvm_pmc";
 * - There are two types of perf counters: general purpose (gp) and fixed.
 *   gp counters are stored in gp_counters[] and fixed counters are stored
 *   in fixed_counters[] respectively. Both of them are part of "struct
 *   kvm_pmu";
 * - pmu.c understands the difference between gp counters and fixed counters.
 *   However AMD doesn't support fixed-counters;
 * - There are three types of index to access perf counters (PMC):
 *     1. MSR (named msr): For example Intel has MSR_IA32_PERFCTRn and AMD
 *        has MSR_K7_PERFCTRn.
 *     2. MSR Index (named idx): This normally is used by RDPMC instruction.
 *        For instance AMD RDPMC instruction uses 0000_0003h in ECX to access
 *        C001_0007h (MSR_K7_PERCTR3). Intel has a similar mechanism, except
 *        that it also supports fixed counters. idx can be used to as index to
 *        gp and fixed counters.
 *     3. Global PMC Index (named pmc): pmc is an index specific to PMU
 *        code. Each pmc, stored in kvm_pmc.idx field, is unique across
 *        all perf counters (both gp and fixed). The mapping relationship
 *        between pmc and perf counters is as the following:
 *        * Intel: [0 .. INTEL_PMC_MAX_GENERIC-1] <=> gp counters
 *                 [INTEL_PMC_IDX_FIXED .. INTEL_PMC_IDX_FIXED + 2] <=> fixed
 *        * AMD:   [0 .. AMD64_NUM_COUNTERS-1] <=> gp counters
 */

static void kvm_pmi_trigger_fn(struct irq_work *irq_work)
{
	struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work);
	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);

	kvm_pmu_deliver_pmi(vcpu);
}

static void kvm_perf_overflow(struct perf_event *perf_event,
			      struct perf_sample_data *data,
			      struct pt_regs *regs)
{
	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
	struct kvm_pmu *pmu = pmc_to_pmu(pmc);

	if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
	}
}

static void kvm_perf_overflow_intr(struct perf_event *perf_event,
				   struct perf_sample_data *data,
				   struct pt_regs *regs)
{
	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
	struct kvm_pmu *pmu = pmc_to_pmu(pmc);

	if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);

		/*
		 * Inject PMI. If vcpu was in a guest mode during NMI PMI
		 * can be ejected on a guest mode re-entry. Otherwise we can't
		 * be sure that vcpu wasn't executing hlt instruction at the
		 * time of vmexit and is not going to re-enter guest mode until
		 * woken up. So we should wake it, but this is impossible from
		 * NMI context. Do it from irq work instead.
		 */
		if (!kvm_is_in_guest())
			irq_work_queue(&pmc_to_pmu(pmc)->irq_work);
		else
			kvm_make_request(KVM_REQ_PMI, pmc->vcpu);
	}
}

static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
				  unsigned config, bool exclude_user,
				  bool exclude_kernel, bool intr,
				  bool in_tx, bool in_tx_cp)
{
	struct perf_event *event;
	struct perf_event_attr attr = {
		.type = type,
		.size = sizeof(attr),
		.pinned = true,
		.exclude_idle = true,
		.exclude_host = 1,
		.exclude_user = exclude_user,
		.exclude_kernel = exclude_kernel,
		.config = config,
	};

	attr.sample_period = get_sample_period(pmc, pmc->counter);

	if (in_tx)
		attr.config |= HSW_IN_TX;
	if (in_tx_cp) {
		/*
		 * HSW_IN_TX_CHECKPOINTED is not supported with nonzero
		 * period. Just clear the sample period so at least
		 * allocating the counter doesn't fail.
		 */
		attr.sample_period = 0;
		attr.config |= HSW_IN_TX_CHECKPOINTED;
	}

	event = perf_event_create_kernel_counter(&attr, -1, current,
						 intr ? kvm_perf_overflow_intr :
						 kvm_perf_overflow, pmc);
	if (IS_ERR(event)) {
		pr_debug_ratelimited("kvm_pmu: event creation failed %ld for pmc->idx = %d\n",
			    PTR_ERR(event), pmc->idx);
		return;
	}

	pmc->perf_event = event;
	pmc_to_pmu(pmc)->event_count++;
	clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
}

static void pmc_pause_counter(struct kvm_pmc *pmc)
{
	u64 counter = pmc->counter;

	if (!pmc->perf_event)
		return;

	/* update counter, reset event value to avoid redundant accumulation */
	counter += perf_event_pause(pmc->perf_event, true);
	pmc->counter = counter & pmc_bitmask(pmc);
}

static bool pmc_resume_counter(struct kvm_pmc *pmc)
{
	if (!pmc->perf_event)
		return false;

	/* recalibrate sample period and check if it's accepted by perf core */
	if (perf_event_period(pmc->perf_event,
			      get_sample_period(pmc, pmc->counter)))
		return false;

	/* reuse perf_event to serve as pmc_reprogram_counter() does*/
	perf_event_enable(pmc->perf_event);

	clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
	return true;
}

void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
{
	unsigned config, type = PERF_TYPE_RAW;
	u8 event_select, unit_mask;
	struct kvm *kvm = pmc->vcpu->kvm;
	struct kvm_pmu_event_filter *filter;
	int i;
	bool allow_event = true;

	if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
		printk_once("kvm pmu: pin control bit is ignored\n");

	pmc->eventsel = eventsel;

	pmc_pause_counter(pmc);

	if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc))
		return;

	filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu);
	if (filter) {
		for (i = 0; i < filter->nevents; i++)
			if (filter->events[i] ==
			    (eventsel & AMD64_RAW_EVENT_MASK_NB))
				break;
		if (filter->action == KVM_PMU_EVENT_ALLOW &&
		    i == filter->nevents)
			allow_event = false;
		if (filter->action == KVM_PMU_EVENT_DENY &&
		    i < filter->nevents)
			allow_event = false;
	}
	if (!allow_event)
		return;

	event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
	unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;

	if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
			  ARCH_PERFMON_EVENTSEL_INV |
			  ARCH_PERFMON_EVENTSEL_CMASK |
			  HSW_IN_TX |
			  HSW_IN_TX_CHECKPOINTED))) {
		config = kvm_x86_ops.pmu_ops->find_arch_event(pmc_to_pmu(pmc),
						      event_select,
						      unit_mask);
		if (config != PERF_COUNT_HW_MAX)
			type = PERF_TYPE_HARDWARE;
	}

	if (type == PERF_TYPE_RAW)
		config = eventsel & X86_RAW_EVENT_MASK;

	if (pmc->current_config == eventsel && pmc_resume_counter(pmc))
		return;

	pmc_release_perf_event(pmc);

	pmc->current_config = eventsel;
	pmc_reprogram_counter(pmc, type, config,
			      !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
			      !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
			      eventsel & ARCH_PERFMON_EVENTSEL_INT,
			      (eventsel & HSW_IN_TX),
			      (eventsel & HSW_IN_TX_CHECKPOINTED));
}
EXPORT_SYMBOL_GPL(reprogram_gp_counter);

void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
{
	unsigned en_field = ctrl & 0x3;
	bool pmi = ctrl & 0x8;
	struct kvm_pmu_event_filter *filter;
	struct kvm *kvm = pmc->vcpu->kvm;

	pmc_pause_counter(pmc);

	if (!en_field || !pmc_is_enabled(pmc))
		return;

	filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu);
	if (filter) {
		if (filter->action == KVM_PMU_EVENT_DENY &&
		    test_bit(idx, (ulong *)&filter->fixed_counter_bitmap))
			return;
		if (filter->action == KVM_PMU_EVENT_ALLOW &&
		    !test_bit(idx, (ulong *)&filter->fixed_counter_bitmap))
			return;
	}

	if (pmc->current_config == (u64)ctrl && pmc_resume_counter(pmc))
		return;

	pmc_release_perf_event(pmc);

	pmc->current_config = (u64)ctrl;
	pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE,
			      kvm_x86_ops.pmu_ops->find_fixed_event(idx),
			      !(en_field & 0x2), /* exclude user */
			      !(en_field & 0x1), /* exclude kernel */
			      pmi, false, false);
}
EXPORT_SYMBOL_GPL(reprogram_fixed_counter);

void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx)
{
	struct kvm_pmc *pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, pmc_idx);

	if (!pmc)
		return;

	if (pmc_is_gp(pmc))
		reprogram_gp_counter(pmc, pmc->eventsel);
	else {
		int idx = pmc_idx - INTEL_PMC_IDX_FIXED;
		u8 ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, idx);

		reprogram_fixed_counter(pmc, ctrl, idx);
	}
}
EXPORT_SYMBOL_GPL(reprogram_counter);

void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
{
	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
	int bit;

	for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) {
		struct kvm_pmc *pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, bit);

		if (unlikely(!pmc || !pmc->perf_event)) {
			clear_bit(bit, pmu->reprogram_pmi);
			continue;
		}

		reprogram_counter(pmu, bit);
	}

	/*
	 * Unused perf_events are only released if the corresponding MSRs
	 * weren't accessed during the last vCPU time slice. kvm_arch_sched_in
	 * triggers KVM_REQ_PMU if cleanup is needed.
	 */
	if (unlikely(pmu->need_cleanup))
		kvm_pmu_cleanup(vcpu);
}

/* check if idx is a valid index to access PMU */
int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
{
	return kvm_x86_ops.pmu_ops->is_valid_rdpmc_ecx(vcpu, idx);
}

bool is_vmware_backdoor_pmc(u32 pmc_idx)
{
	switch (pmc_idx) {
	case VMWARE_BACKDOOR_PMC_HOST_TSC:
	case VMWARE_BACKDOOR_PMC_REAL_TIME:
	case VMWARE_BACKDOOR_PMC_APPARENT_TIME:
		return true;
	}
	return false;
}

static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
{
	u64 ctr_val;

	switch (idx) {
	case VMWARE_BACKDOOR_PMC_HOST_TSC:
		ctr_val = rdtsc();
		break;
	case VMWARE_BACKDOOR_PMC_REAL_TIME:
		ctr_val = ktime_get_boottime_ns();
		break;
	case VMWARE_BACKDOOR_PMC_APPARENT_TIME:
		ctr_val = ktime_get_boottime_ns() +
			vcpu->kvm->arch.kvmclock_offset;
		break;
	default:
		return 1;
	}

	*data = ctr_val;
	return 0;
}

int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
{
	bool fast_mode = idx & (1u << 31);
	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
	struct kvm_pmc *pmc;
	u64 mask = fast_mode ? ~0u : ~0ull;

	if (!pmu->version)
		return 1;

	if (is_vmware_backdoor_pmc(idx))
		return kvm_pmu_rdpmc_vmware(vcpu, idx, data);

	pmc = kvm_x86_ops.pmu_ops->rdpmc_ecx_to_pmc(vcpu, idx, &mask);
	if (!pmc)
		return 1;

	if (!(kvm_read_cr4(vcpu) & X86_CR4_PCE) &&
	    (static_call(kvm_x86_get_cpl)(vcpu) != 0) &&
	    (kvm_read_cr0(vcpu) & X86_CR0_PE))
		return 1;

	*data = pmc_read_counter(pmc) & mask;
	return 0;
}

void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
{
	if (lapic_in_kernel(vcpu)) {
		if (kvm_x86_ops.pmu_ops->deliver_pmi)
			kvm_x86_ops.pmu_ops->deliver_pmi(vcpu);
		kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC);
	}
}

bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
{
	return kvm_x86_ops.pmu_ops->msr_idx_to_pmc(vcpu, msr) ||
		kvm_x86_ops.pmu_ops->is_valid_msr(vcpu, msr);
}

static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr)
{
	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
	struct kvm_pmc *pmc = kvm_x86_ops.pmu_ops->msr_idx_to_pmc(vcpu, msr);

	if (pmc)
		__set_bit(pmc->idx, pmu->pmc_in_use);
}

int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
	return kvm_x86_ops.pmu_ops->get_msr(vcpu, msr_info);
}

int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
	kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index);
	return kvm_x86_ops.pmu_ops->set_msr(vcpu, msr_info);
}

/* refresh PMU settings. This function generally is called when underlying
 * settings are changed (such as changes of PMU CPUID by guest VMs), which
 * should rarely happen.
 */
void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
{
	kvm_x86_ops.pmu_ops->refresh(vcpu);
}

void kvm_pmu_reset(struct kvm_vcpu *vcpu)
{
	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);

	irq_work_sync(&pmu->irq_work);
	kvm_x86_ops.pmu_ops->reset(vcpu);
}

void kvm_pmu_init(struct kvm_vcpu *vcpu)
{
	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);

	memset(pmu, 0, sizeof(*pmu));
	kvm_x86_ops.pmu_ops->init(vcpu);
	init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn);
	pmu->event_count = 0;
	pmu->need_cleanup = false;
	kvm_pmu_refresh(vcpu);
}

static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc)
{
	struct kvm_pmu *pmu = pmc_to_pmu(pmc);

	if (pmc_is_fixed(pmc))
		return fixed_ctrl_field(pmu->fixed_ctr_ctrl,
			pmc->idx - INTEL_PMC_IDX_FIXED) & 0x3;

	return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE;
}

/* Release perf_events for vPMCs that have been unused for a full time slice.  */
void kvm_pmu_cleanup(struct kvm_vcpu *vcpu)
{
	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
	struct kvm_pmc *pmc = NULL;
	DECLARE_BITMAP(bitmask, X86_PMC_IDX_MAX);
	int i;

	pmu->need_cleanup = false;

	bitmap_andnot(bitmask, pmu->all_valid_pmc_idx,
		      pmu->pmc_in_use, X86_PMC_IDX_MAX);

	for_each_set_bit(i, bitmask, X86_PMC_IDX_MAX) {
		pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, i);

		if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc))
			pmc_stop_counter(pmc);
	}

	if (kvm_x86_ops.pmu_ops->cleanup)
		kvm_x86_ops.pmu_ops->cleanup(vcpu);

	bitmap_zero(pmu->pmc_in_use, X86_PMC_IDX_MAX);
}

void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
{
	kvm_pmu_reset(vcpu);
}

int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
{
	struct kvm_pmu_event_filter tmp, *filter;
	size_t size;
	int r;

	if (copy_from_user(&tmp, argp, sizeof(tmp)))
		return -EFAULT;

	if (tmp.action != KVM_PMU_EVENT_ALLOW &&
	    tmp.action != KVM_PMU_EVENT_DENY)
		return -EINVAL;

	if (tmp.flags != 0)
		return -EINVAL;

	if (tmp.nevents > KVM_PMU_EVENT_FILTER_MAX_EVENTS)
		return -E2BIG;

	size = struct_size(filter, events, tmp.nevents);
	filter = kmalloc(size, GFP_KERNEL_ACCOUNT);
	if (!filter)
		return -ENOMEM;

	r = -EFAULT;
	if (copy_from_user(filter, argp, size))
		goto cleanup;

	/* Ensure nevents can't be changed between the user copies. */
	*filter = tmp;

	mutex_lock(&kvm->lock);
	filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter,
				     mutex_is_locked(&kvm->lock));
	mutex_unlock(&kvm->lock);

	synchronize_srcu_expedited(&kvm->srcu);
	r = 0;
cleanup:
	kfree(filter);
	return r;
}