aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/kernel/sysfs.c
blob: 68991c2d4a1b3a6fcb101728c2be0e9724dcf37d (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
#include <linux/sysdev.h>
#include <linux/cpu.h>
#include <linux/smp.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/nodemask.h>
#include <linux/cpumask.h>
#include <linux/notifier.h>

#include <asm/current.h>
#include <asm/processor.h>
#include <asm/cputable.h>
#include <asm/firmware.h>
#include <asm/hvcall.h>
#include <asm/prom.h>
#include <asm/paca.h>
#include <asm/lppaca.h>
#include <asm/machdep.h>
#include <asm/smp.h>

static DEFINE_PER_CPU(struct cpu, cpu_devices);

/* SMT stuff */

#ifdef CONFIG_PPC_MULTIPLATFORM
/* Time in microseconds we delay before sleeping in the idle loop */
DEFINE_PER_CPU(unsigned long, smt_snooze_delay) = { 100 };

static ssize_t store_smt_snooze_delay(struct sys_device *dev, const char *buf,
				      size_t count)
{
	struct cpu *cpu = container_of(dev, struct cpu, sysdev);
	ssize_t ret;
	unsigned long snooze;

	ret = sscanf(buf, "%lu", &snooze);
	if (ret != 1)
		return -EINVAL;

	per_cpu(smt_snooze_delay, cpu->sysdev.id) = snooze;

	return count;
}

static ssize_t show_smt_snooze_delay(struct sys_device *dev, char *buf)
{
	struct cpu *cpu = container_of(dev, struct cpu, sysdev);

	return sprintf(buf, "%lu\n", per_cpu(smt_snooze_delay, cpu->sysdev.id));
}

static SYSDEV_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay,
		   store_smt_snooze_delay);

/* Only parse OF options if the matching cmdline option was not specified */
static int smt_snooze_cmdline;

static int __init smt_setup(void)
{
	struct device_node *options;
	const unsigned int *val;
	unsigned int cpu;

	if (!cpu_has_feature(CPU_FTR_SMT))
		return -ENODEV;

	options = of_find_node_by_path("/options");
	if (!options)
		return -ENODEV;

	val = of_get_property(options, "ibm,smt-snooze-delay", NULL);
	if (!smt_snooze_cmdline && val) {
		for_each_possible_cpu(cpu)
			per_cpu(smt_snooze_delay, cpu) = *val;
	}

	of_node_put(options);
	return 0;
}
__initcall(smt_setup);

static int __init setup_smt_snooze_delay(char *str)
{
	unsigned int cpu;
	int snooze;

	if (!cpu_has_feature(CPU_FTR_SMT))
		return 1;

	smt_snooze_cmdline = 1;

	if (get_option(&str, &snooze)) {
		for_each_possible_cpu(cpu)
			per_cpu(smt_snooze_delay, cpu) = snooze;
	}

	return 1;
}
__setup("smt-snooze-delay=", setup_smt_snooze_delay);

#endif /* CONFIG_PPC_MULTIPLATFORM */

/*
 * Enabling PMCs will slow partition context switch times so we only do
 * it the first time we write to the PMCs.
 */

static DEFINE_PER_CPU(char, pmcs_enabled);

void ppc64_enable_pmcs(void)
{
	/* Only need to enable them once */
	if (__get_cpu_var(pmcs_enabled))
		return;

	__get_cpu_var(pmcs_enabled) = 1;

	if (ppc_md.enable_pmcs)
		ppc_md.enable_pmcs();
}
EXPORT_SYMBOL(ppc64_enable_pmcs);

/* XXX convert to rusty's on_one_cpu */
static unsigned long run_on_cpu(unsigned long cpu,
			        unsigned long (*func)(unsigned long),
				unsigned long arg)
{
	cpumask_t old_affinity = current->cpus_allowed;
	unsigned long ret;

	/* should return -EINVAL to userspace */
	if (set_cpus_allowed(current, cpumask_of_cpu(cpu)))
		return 0;

	ret = func(arg);

	set_cpus_allowed(current, old_affinity);

	return ret;
}

#define SYSFS_PMCSETUP(NAME, ADDRESS) \
static unsigned long read_##NAME(unsigned long junk) \
{ \
	return mfspr(ADDRESS); \
} \
static unsigned long write_##NAME(unsigned long val) \
{ \
	ppc64_enable_pmcs(); \
	mtspr(ADDRESS, val); \
	return 0; \
} \
static ssize_t show_##NAME(struct sys_device *dev, char *buf) \
{ \
	struct cpu *cpu = container_of(dev, struct cpu, sysdev); \
	unsigned long val = run_on_cpu(cpu->sysdev.id, read_##NAME, 0); \
	return sprintf(buf, "%lx\n", val); \
} \
static ssize_t __attribute_used__ \
	store_##NAME(struct sys_device *dev, const char *buf, size_t count) \
{ \
	struct cpu *cpu = container_of(dev, struct cpu, sysdev); \
	unsigned long val; \
	int ret = sscanf(buf, "%lx", &val); \
	if (ret != 1) \
		return -EINVAL; \
	run_on_cpu(cpu->sysdev.id, write_##NAME, val); \
	return count; \
}


/* Let's define all possible registers, we'll only hook up the ones
 * that are implemented on the current processor
 */

SYSFS_PMCSETUP(mmcr0, SPRN_MMCR0);
SYSFS_PMCSETUP(mmcr1, SPRN_MMCR1);
SYSFS_PMCSETUP(mmcra, SPRN_MMCRA);
SYSFS_PMCSETUP(pmc1, SPRN_PMC1);
SYSFS_PMCSETUP(pmc2, SPRN_PMC2);
SYSFS_PMCSETUP(pmc3, SPRN_PMC3);
SYSFS_PMCSETUP(pmc4, SPRN_PMC4);
SYSFS_PMCSETUP(pmc5, SPRN_PMC5);
SYSFS_PMCSETUP(pmc6, SPRN_PMC6);
SYSFS_PMCSETUP(pmc7, SPRN_PMC7);
SYSFS_PMCSETUP(pmc8, SPRN_PMC8);
SYSFS_PMCSETUP(purr, SPRN_PURR);
SYSFS_PMCSETUP(spurr, SPRN_SPURR);
SYSFS_PMCSETUP(dscr, SPRN_DSCR);

SYSFS_PMCSETUP(pa6t_pmc0, SPRN_PA6T_PMC0);
SYSFS_PMCSETUP(pa6t_pmc1, SPRN_PA6T_PMC1);
SYSFS_PMCSETUP(pa6t_pmc2, SPRN_PA6T_PMC2);
SYSFS_PMCSETUP(pa6t_pmc3, SPRN_PA6T_PMC3);
SYSFS_PMCSETUP(pa6t_pmc4, SPRN_PA6T_PMC4);
SYSFS_PMCSETUP(pa6t_pmc5, SPRN_PA6T_PMC5);


static SYSDEV_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
static SYSDEV_ATTR(spurr, 0600, show_spurr, NULL);
static SYSDEV_ATTR(dscr, 0600, show_dscr, store_dscr);
static SYSDEV_ATTR(purr, 0600, show_purr, store_purr);

static struct sysdev_attribute ibm_common_attrs[] = {
	_SYSDEV_ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0),
	_SYSDEV_ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1),
};

static struct sysdev_attribute ibm_pmc_attrs[] = {
	_SYSDEV_ATTR(pmc1, 0600, show_pmc1, store_pmc1),
	_SYSDEV_ATTR(pmc2, 0600, show_pmc2, store_pmc2),
	_SYSDEV_ATTR(pmc3, 0600, show_pmc3, store_pmc3),
	_SYSDEV_ATTR(pmc4, 0600, show_pmc4, store_pmc4),
	_SYSDEV_ATTR(pmc5, 0600, show_pmc5, store_pmc5),
	_SYSDEV_ATTR(pmc6, 0600, show_pmc6, store_pmc6),
	_SYSDEV_ATTR(pmc7, 0600, show_pmc7, store_pmc7),
	_SYSDEV_ATTR(pmc8, 0600, show_pmc8, store_pmc8),
};

static struct sysdev_attribute pa6t_attrs[] = {
	_SYSDEV_ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0),
	_SYSDEV_ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1),
	_SYSDEV_ATTR(pmc0, 0600, show_pa6t_pmc0, store_pa6t_pmc0),
	_SYSDEV_ATTR(pmc1, 0600, show_pa6t_pmc1, store_pa6t_pmc1),
	_SYSDEV_ATTR(pmc2, 0600, show_pa6t_pmc2, store_pa6t_pmc2),
	_SYSDEV_ATTR(pmc3, 0600, show_pa6t_pmc3, store_pa6t_pmc3),
	_SYSDEV_ATTR(pmc4, 0600, show_pa6t_pmc4, store_pa6t_pmc4),
	_SYSDEV_ATTR(pmc5, 0600, show_pa6t_pmc5, store_pa6t_pmc5),
};


static void register_cpu_online(unsigned int cpu)
{
	struct cpu *c = &per_cpu(cpu_devices, cpu);
	struct sys_device *s = &c->sysdev;
	struct sysdev_attribute *attrs, *pmc_attrs;
	int i, nattrs;

	if (!firmware_has_feature(FW_FEATURE_ISERIES) &&
			cpu_has_feature(CPU_FTR_SMT))
		sysdev_create_file(s, &attr_smt_snooze_delay);

	/* PMC stuff */
	switch (cur_cpu_spec->pmc_type) {
	case PPC_PMC_IBM:
		attrs = ibm_common_attrs;
		nattrs = sizeof(ibm_common_attrs) / sizeof(struct sysdev_attribute);
		pmc_attrs = ibm_pmc_attrs;
		break;
	case PPC_PMC_PA6T:
		/* PA Semi starts counting at PMC0 */
		attrs = pa6t_attrs;
		nattrs = sizeof(pa6t_attrs) / sizeof(struct sysdev_attribute);
		pmc_attrs = NULL;
		break;
	default:
		attrs = NULL;
		nattrs = 0;
		pmc_attrs = NULL;
	}

	for (i = 0; i < nattrs; i++)
		sysdev_create_file(s, &attrs[i]);

	if (pmc_attrs)
		for (i = 0; i < cur_cpu_spec->num_pmcs; i++)
			sysdev_create_file(s, &pmc_attrs[i]);

	if (cpu_has_feature(CPU_FTR_MMCRA))
		sysdev_create_file(s, &attr_mmcra);

	if (cpu_has_feature(CPU_FTR_PURR))
		sysdev_create_file(s, &attr_purr);

	if (cpu_has_feature(CPU_FTR_SPURR))
		sysdev_create_file(s, &attr_spurr);

	if (cpu_has_feature(CPU_FTR_DSCR))
		sysdev_create_file(s, &attr_dscr);
}

#ifdef CONFIG_HOTPLUG_CPU
static void unregister_cpu_online(unsigned int cpu)
{
	struct cpu *c = &per_cpu(cpu_devices, cpu);
	struct sys_device *s = &c->sysdev;
	struct sysdev_attribute *attrs, *pmc_attrs;
	int i, nattrs;

	BUG_ON(!c->hotpluggable);

	if (!firmware_has_feature(FW_FEATURE_ISERIES) &&
			cpu_has_feature(CPU_FTR_SMT))
		sysdev_remove_file(s, &attr_smt_snooze_delay);

	/* PMC stuff */
	switch (cur_cpu_spec->pmc_type) {
	case PPC_PMC_IBM:
		attrs = ibm_common_attrs;
		nattrs = sizeof(ibm_common_attrs) / sizeof(struct sysdev_attribute);
		pmc_attrs = ibm_pmc_attrs;
		break;
	case PPC_PMC_PA6T:
		/* PA Semi starts counting at PMC0 */
		attrs = pa6t_attrs;
		nattrs = sizeof(pa6t_attrs) / sizeof(struct sysdev_attribute);
		pmc_attrs = NULL;
		break;
	default:
		attrs = NULL;
		nattrs = 0;
		pmc_attrs = NULL;
	}

	for (i = 0; i < nattrs; i++)
		sysdev_remove_file(s, &attrs[i]);

	if (pmc_attrs)
		for (i = 0; i < cur_cpu_spec->num_pmcs; i++)
			sysdev_remove_file(s, &pmc_attrs[i]);

	if (cpu_has_feature(CPU_FTR_MMCRA))
		sysdev_remove_file(s, &attr_mmcra);

	if (cpu_has_feature(CPU_FTR_PURR))
		sysdev_remove_file(s, &attr_purr);

	if (cpu_has_feature(CPU_FTR_SPURR))
		sysdev_remove_file(s, &attr_spurr);

	if (cpu_has_feature(CPU_FTR_DSCR))
		sysdev_remove_file(s, &attr_dscr);
}
#endif /* CONFIG_HOTPLUG_CPU */

static int __cpuinit sysfs_cpu_notify(struct notifier_block *self,
				      unsigned long action, void *hcpu)
{
	unsigned int cpu = (unsigned int)(long)hcpu;

	switch (action) {
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		register_cpu_online(cpu);
		break;
#ifdef CONFIG_HOTPLUG_CPU
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		unregister_cpu_online(cpu);
		break;
#endif
	}
	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata sysfs_cpu_nb = {
	.notifier_call	= sysfs_cpu_notify,
};

static DEFINE_MUTEX(cpu_mutex);

int cpu_add_sysdev_attr(struct sysdev_attribute *attr)
{
	int cpu;

	mutex_lock(&cpu_mutex);

	for_each_possible_cpu(cpu) {
		sysdev_create_file(get_cpu_sysdev(cpu), attr);
	}

	mutex_unlock(&cpu_mutex);
	return 0;
}
EXPORT_SYMBOL_GPL(cpu_add_sysdev_attr);

int cpu_add_sysdev_attr_group(struct attribute_group *attrs)
{
	int cpu;
	struct sys_device *sysdev;

	mutex_lock(&cpu_mutex);

	for_each_possible_cpu(cpu) {
		sysdev = get_cpu_sysdev(cpu);
		sysfs_create_group(&sysdev->kobj, attrs);
	}

	mutex_unlock(&cpu_mutex);
	return 0;
}
EXPORT_SYMBOL_GPL(cpu_add_sysdev_attr_group);


void cpu_remove_sysdev_attr(struct sysdev_attribute *attr)
{
	int cpu;

	mutex_lock(&cpu_mutex);

	for_each_possible_cpu(cpu) {
		sysdev_remove_file(get_cpu_sysdev(cpu), attr);
	}

	mutex_unlock(&cpu_mutex);
}
EXPORT_SYMBOL_GPL(cpu_remove_sysdev_attr);

void cpu_remove_sysdev_attr_group(struct attribute_group *attrs)
{
	int cpu;
	struct sys_device *sysdev;

	mutex_lock(&cpu_mutex);

	for_each_possible_cpu(cpu) {
		sysdev = get_cpu_sysdev(cpu);
		sysfs_remove_group(&sysdev->kobj, attrs);
	}

	mutex_unlock(&cpu_mutex);
}
EXPORT_SYMBOL_GPL(cpu_remove_sysdev_attr_group);


/* NUMA stuff */

#ifdef CONFIG_NUMA
static void register_nodes(void)
{
	int i;

	for (i = 0; i < MAX_NUMNODES; i++)
		register_one_node(i);
}

int sysfs_add_device_to_node(struct sys_device *dev, int nid)
{
	struct node *node = &node_devices[nid];
	return sysfs_create_link(&node->sysdev.kobj, &dev->kobj,
			kobject_name(&dev->kobj));
}

void sysfs_remove_device_from_node(struct sys_device *dev, int nid)
{
	struct node *node = &node_devices[nid];
	sysfs_remove_link(&node->sysdev.kobj, kobject_name(&dev->kobj));
}

#else
static void register_nodes(void)
{
	return;
}

#endif

EXPORT_SYMBOL_GPL(sysfs_add_device_to_node);
EXPORT_SYMBOL_GPL(sysfs_remove_device_from_node);

/* Only valid if CPU is present. */
static ssize_t show_physical_id(struct sys_device *dev, char *buf)
{
	struct cpu *cpu = container_of(dev, struct cpu, sysdev);

	return sprintf(buf, "%d\n", get_hard_smp_processor_id(cpu->sysdev.id));
}
static SYSDEV_ATTR(physical_id, 0444, show_physical_id, NULL);

static int __init topology_init(void)
{
	int cpu;

	register_nodes();
	register_cpu_notifier(&sysfs_cpu_nb);

	for_each_possible_cpu(cpu) {
		struct cpu *c = &per_cpu(cpu_devices, cpu);

		/*
		 * For now, we just see if the system supports making
		 * the RTAS calls for CPU hotplug.  But, there may be a
		 * more comprehensive way to do this for an individual
		 * CPU.  For instance, the boot cpu might never be valid
		 * for hotplugging.
		 */
		if (ppc_md.cpu_die)
			c->hotpluggable = 1;

		if (cpu_online(cpu) || c->hotpluggable) {
			register_cpu(c, cpu);

			sysdev_create_file(&c->sysdev, &attr_physical_id);
		}

		if (cpu_online(cpu))
			register_cpu_online(cpu);
	}

	return 0;
}
subsys_initcall(topology_init);