summaryrefslogtreecommitdiffstats
path: root/arch/x86/oprofile/op_model_ppro.c
blob: f8e268e8e992e7b0b8a9912e47eb20e3d64e28ef (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
/*
 * @file op_model_ppro.h
 * Family 6 perfmon and architectural perfmon MSR operations
 *
 * @remark Copyright 2002 OProfile authors
 * @remark Copyright 2008 Intel Corporation
 * @remark Read the file COPYING
 *
 * @author John Levon
 * @author Philippe Elie
 * @author Graydon Hoare
 * @author Andi Kleen
 * @author Robert Richter <robert.richter@amd.com>
 */

#include <linux/oprofile.h>
#include <linux/slab.h>
#include <asm/ptrace.h>
#include <asm/msr.h>
#include <asm/apic.h>
#include <asm/nmi.h>

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

static int num_counters = 2;
static int counter_width = 32;

#define MSR_PPRO_EVENTSEL_RESERVED	((0xFFFFFFFFULL<<32)|(1ULL<<21))

static u64 *reset_value;

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

	for (i = 0; i < num_counters; i++) {
		if (!reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i))
			continue;
		if (!reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i)) {
			release_perfctr_nmi(MSR_P6_PERFCTR0 + i);
			continue;
		}
		/* both registers must be reserved */
		msrs->counters[i].addr = MSR_P6_PERFCTR0 + i;
		msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i;
	}
}


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

	if (!reset_value) {
		reset_value = kzalloc(sizeof(reset_value[0]) * num_counters,
					GFP_ATOMIC);
		if (!reset_value)
			return;
	}

	if (cpu_has_arch_perfmon) {
		union cpuid10_eax eax;
		eax.full = cpuid_eax(0xa);

		/*
		 * For Core2 (family 6, model 15), don't reset the
		 * counter width:
		 */
		if (!(eax.split.version_id == 0 &&
			current_cpu_data.x86 == 6 &&
				current_cpu_data.x86_model == 15)) {

			if (counter_width < eax.split.bit_width)
				counter_width = eax.split.bit_width;
		}
	}

	/* clear all counters */
	for (i = 0; i < num_counters; ++i) {
		if (unlikely(!msrs->controls[i].addr)) {
			if (counter_config[i].enabled && !smp_processor_id())
				/*
				 * counter is reserved, this is on all
				 * cpus, so report only for cpu #0
				 */
				op_x86_warn_reserved(i);
			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) {
		if (counter_config[i].enabled && msrs->counters[i].addr) {
			reset_value[i] = counter_config[i].count;
			wrmsrl(msrs->counters[i].addr, -reset_value[i]);
			rdmsrl(msrs->controls[i].addr, val);
			val &= model->reserved;
			val |= op_x86_get_ctrl(model, &counter_config[i]);
			wrmsrl(msrs->controls[i].addr, val);
		} else {
			reset_value[i] = 0;
		}
	}
}


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

	/*
	 * This can happen if perf counters are in use when
	 * we steal the die notifier NMI.
	 */
	if (unlikely(!reset_value))
		goto out;

	for (i = 0; i < num_counters; ++i) {
		if (!reset_value[i])
			continue;
		rdmsrl(msrs->counters[i].addr, val);
		if (val & (1ULL << (counter_width - 1)))
			continue;
		oprofile_add_sample(regs, i);
		wrmsrl(msrs->counters[i].addr, -reset_value[i]);
	}

out:
	/* Only P6 based Pentium M need to re-unmask the apic vector but it
	 * doesn't hurt other P6 variant */
	apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED);

	/* We can't work out if we really handled an interrupt. We
	 * might have caught a *second* counter just after overflowing
	 * the interrupt for this counter then arrives
	 * and we don't find a counter that's overflowed, so we
	 * would return 0 and get dazed + confused. Instead we always
	 * assume we found an overflow. This sucks.
	 */
	return 1;
}


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

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


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

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

static void ppro_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_P6_PERFCTR0 + i);
		release_evntsel_nmi(MSR_P6_EVNTSEL0 + i);
	}
	if (reset_value) {
		kfree(reset_value);
		reset_value = NULL;
	}
}


struct op_x86_model_spec op_ppro_spec = {
	.num_counters		= 2,
	.num_controls		= 2,
	.reserved		= MSR_PPRO_EVENTSEL_RESERVED,
	.fill_in_addresses	= &ppro_fill_in_addresses,
	.setup_ctrs		= &ppro_setup_ctrs,
	.check_ctrs		= &ppro_check_ctrs,
	.start			= &ppro_start,
	.stop			= &ppro_stop,
	.shutdown		= &ppro_shutdown
};

/*
 * Architectural performance monitoring.
 *
 * Newer Intel CPUs (Core1+) have support for architectural
 * events described in CPUID 0xA. See the IA32 SDM Vol3b.18 for details.
 * The advantage of this is that it can be done without knowing about
 * the specific CPU.
 */

static void arch_perfmon_setup_counters(void)
{
	union cpuid10_eax eax;

	eax.full = cpuid_eax(0xa);

	/* Workaround for BIOS bugs in 6/15. Taken from perfmon2 */
	if (eax.split.version_id == 0 && current_cpu_data.x86 == 6 &&
		current_cpu_data.x86_model == 15) {
		eax.split.version_id = 2;
		eax.split.num_events = 2;
		eax.split.bit_width = 40;
	}

	num_counters = eax.split.num_events;

	op_arch_perfmon_spec.num_counters = num_counters;
	op_arch_perfmon_spec.num_controls = num_counters;
}

static int arch_perfmon_init(struct oprofile_operations *ignore)
{
	arch_perfmon_setup_counters();
	return 0;
}

struct op_x86_model_spec op_arch_perfmon_spec = {
	.reserved		= MSR_PPRO_EVENTSEL_RESERVED,
	.init			= &arch_perfmon_init,
	/* num_counters/num_controls filled in at runtime */
	.fill_in_addresses	= &ppro_fill_in_addresses,
	/* user space does the cpuid check for available events */
	.setup_ctrs		= &ppro_setup_ctrs,
	.check_ctrs		= &ppro_check_ctrs,
	.start			= &ppro_start,
	.stop			= &ppro_stop,
	.shutdown		= &ppro_shutdown
};