Home Home > GIT Browse > stable-xen
summaryrefslogtreecommitdiff
blob: 1098bd62032710af835d27cafb93518700d58cd6 (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
/*
 * CPU subsystem support
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/cpu.h>
#include <linux/topology.h>
#include <linux/device.h>
#include <linux/node.h>
#include <linux/gfp.h>
#include <linux/slab.h>
#include <linux/percpu.h>
#include <linux/acpi.h>
#include <linux/of.h>
#include <linux/cpufeature.h>
#include <linux/tick.h>
#include <linux/pm_qos.h>

#include "base.h"

static DEFINE_PER_CPU(struct device *, cpu_sys_devices);

static int cpu_subsys_match(struct device *dev, struct device_driver *drv)
{
	/* ACPI style match is the only one that may succeed. */
	if (acpi_driver_match_device(dev, drv))
		return 1;

	return 0;
}

#ifdef CONFIG_HOTPLUG_CPU
static void change_cpu_under_node(struct cpu *cpu,
			unsigned int from_nid, unsigned int to_nid)
{
	int cpuid = cpu->dev.id;
	unregister_cpu_under_node(cpuid, from_nid);
	register_cpu_under_node(cpuid, to_nid);
	cpu->node_id = to_nid;
}

static int cpu_subsys_online(struct device *dev)
{
	struct cpu *cpu = container_of(dev, struct cpu, dev);
	int cpuid = dev->id;
	int from_nid, to_nid;
	int ret;

	from_nid = cpu_to_node(cpuid);
	if (from_nid == NUMA_NO_NODE)
		return -ENODEV;

	ret = cpu_up(cpuid);
	/*
	 * When hot adding memory to memoryless node and enabling a cpu
	 * on the node, node number of the cpu may internally change.
	 */
	to_nid = cpu_to_node(cpuid);
	if (from_nid != to_nid)
		change_cpu_under_node(cpu, from_nid, to_nid);

	return ret;
}

static int cpu_subsys_offline(struct device *dev)
{
	return cpu_down(dev->id);
}

void unregister_cpu(struct cpu *cpu)
{
	int logical_cpu = cpu->dev.id;

	unregister_cpu_under_node(logical_cpu, cpu_to_node(logical_cpu));

	device_unregister(&cpu->dev);
	per_cpu(cpu_sys_devices, logical_cpu) = NULL;
	return;
}

#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
static ssize_t cpu_probe_store(struct device *dev,
			       struct device_attribute *attr,
			       const char *buf,
			       size_t count)
{
	ssize_t cnt;
	int ret;

	ret = lock_device_hotplug_sysfs();
	if (ret)
		return ret;

	cnt = arch_cpu_probe(buf, count);

	unlock_device_hotplug();
	return cnt;
}

static ssize_t cpu_release_store(struct device *dev,
				 struct device_attribute *attr,
				 const char *buf,
				 size_t count)
{
	ssize_t cnt;
	int ret;

	ret = lock_device_hotplug_sysfs();
	if (ret)
		return ret;

	cnt = arch_cpu_release(buf, count);

	unlock_device_hotplug();
	return cnt;
}

static DEVICE_ATTR(probe, S_IWUSR, NULL, cpu_probe_store);
static DEVICE_ATTR(release, S_IWUSR, NULL, cpu_release_store);
#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
#endif /* CONFIG_HOTPLUG_CPU */

struct bus_type cpu_subsys = {
	.name = "cpu",
	.dev_name = "cpu",
	.match = cpu_subsys_match,
#ifdef CONFIG_HOTPLUG_CPU
	.online = cpu_subsys_online,
	.offline = cpu_subsys_offline,
#endif
};
EXPORT_SYMBOL_GPL(cpu_subsys);

#if defined(CONFIG_KEXEC) && !defined(CONFIG_XEN)
#include <linux/kexec.h>

static ssize_t show_crash_notes(struct device *dev, struct device_attribute *attr,
				char *buf)
{
	struct cpu *cpu = container_of(dev, struct cpu, dev);
	ssize_t rc;
	unsigned long long addr;
	int cpunum;

	cpunum = cpu->dev.id;

	/*
	 * Might be reading other cpu's data based on which cpu read thread
	 * has been scheduled. But cpu data (memory) is allocated once during
	 * boot up and this data does not change there after. Hence this
	 * operation should be safe. No locking required.
	 */
	addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpunum));
	rc = sprintf(buf, "%Lx\n", addr);
	return rc;
}
static DEVICE_ATTR(crash_notes, 0400, show_crash_notes, NULL);

static ssize_t show_crash_notes_size(struct device *dev,
				     struct device_attribute *attr,
				     char *buf)
{
	ssize_t rc;

	rc = sprintf(buf, "%zu\n", sizeof(note_buf_t));
	return rc;
}
static DEVICE_ATTR(crash_notes_size, 0400, show_crash_notes_size, NULL);

static struct attribute *crash_note_cpu_attrs[] = {
	&dev_attr_crash_notes.attr,
	&dev_attr_crash_notes_size.attr,
	NULL
};

static struct attribute_group crash_note_cpu_attr_group = {
	.attrs = crash_note_cpu_attrs,
};
#endif

static const struct attribute_group *common_cpu_attr_groups[] = {
#if defined(CONFIG_KEXEC) && !defined(CONFIG_XEN)
	&crash_note_cpu_attr_group,
#endif
	NULL
};

static const struct attribute_group *hotplugable_cpu_attr_groups[] = {
#if defined(CONFIG_KEXEC) && !defined(CONFIG_XEN)
	&crash_note_cpu_attr_group,
#endif
	NULL
};

/*
 * Print cpu online, possible, present, and system maps
 */

struct cpu_attr {
	struct device_attribute attr;
	const struct cpumask *const map;
};

static ssize_t show_cpus_attr(struct device *dev,
			      struct device_attribute *attr,
			      char *buf)
{
	struct cpu_attr *ca = container_of(attr, struct cpu_attr, attr);

	return cpumap_print_to_pagebuf(true, buf, ca->map);
}

#define _CPU_ATTR(name, map) \
	{ __ATTR(name, 0444, show_cpus_attr, NULL), map }

/* Keep in sync with cpu_subsys_attrs */
static struct cpu_attr cpu_attrs[] = {
	_CPU_ATTR(online, &__cpu_online_mask),
	_CPU_ATTR(possible, &__cpu_possible_mask),
	_CPU_ATTR(present, &__cpu_present_mask),
};

/*
 * Print values for NR_CPUS and offlined cpus
 */
static ssize_t print_cpus_kernel_max(struct device *dev,
				     struct device_attribute *attr, char *buf)
{
	int n = snprintf(buf, PAGE_SIZE-2, "%d\n", NR_CPUS - 1);
	return n;
}
static DEVICE_ATTR(kernel_max, 0444, print_cpus_kernel_max, NULL);

/* arch-optional setting to enable display of offline cpus >= nr_cpu_ids */
unsigned int total_cpus;

static ssize_t print_cpus_offline(struct device *dev,
				  struct device_attribute *attr, char *buf)
{
	int n = 0, len = PAGE_SIZE-2;
	cpumask_var_t offline;

	/* display offline cpus < nr_cpu_ids */
	if (!alloc_cpumask_var(&offline, GFP_KERNEL))
		return -ENOMEM;
	cpumask_andnot(offline, cpu_possible_mask, cpu_online_mask);
	n = scnprintf(buf, len, "%*pbl", cpumask_pr_args(offline));
	free_cpumask_var(offline);

	/* display offline cpus >= nr_cpu_ids */
	if (total_cpus && nr_cpu_ids < total_cpus) {
		if (n && n < len)
			buf[n++] = ',';

		if (nr_cpu_ids == total_cpus-1)
			n += snprintf(&buf[n], len - n, "%d", nr_cpu_ids);
		else
			n += snprintf(&buf[n], len - n, "%d-%d",
						      nr_cpu_ids, total_cpus-1);
	}

	n += snprintf(&buf[n], len - n, "\n");
	return n;
}
static DEVICE_ATTR(offline, 0444, print_cpus_offline, NULL);

static ssize_t print_cpus_isolated(struct device *dev,
				  struct device_attribute *attr, char *buf)
{
	int n = 0, len = PAGE_SIZE-2;

	n = scnprintf(buf, len, "%*pbl\n", cpumask_pr_args(cpu_isolated_map));

	return n;
}
static DEVICE_ATTR(isolated, 0444, print_cpus_isolated, NULL);

#ifdef CONFIG_NO_HZ_FULL
static ssize_t print_cpus_nohz_full(struct device *dev,
				  struct device_attribute *attr, char *buf)
{
	int n = 0, len = PAGE_SIZE-2;

	n = scnprintf(buf, len, "%*pbl\n", cpumask_pr_args(tick_nohz_full_mask));

	return n;
}
static DEVICE_ATTR(nohz_full, 0444, print_cpus_nohz_full, NULL);
#endif

static void cpu_device_release(struct device *dev)
{
	/*
	 * This is an empty function to prevent the driver core from spitting a
	 * warning at us.  Yes, I know this is directly opposite of what the
	 * documentation for the driver core and kobjects say, and the author
	 * of this code has already been publically ridiculed for doing
	 * something as foolish as this.  However, at this point in time, it is
	 * the only way to handle the issue of statically allocated cpu
	 * devices.  The different architectures will have their cpu device
	 * code reworked to properly handle this in the near future, so this
	 * function will then be changed to correctly free up the memory held
	 * by the cpu device.
	 *
	 * Never copy this way of doing things, or you too will be made fun of
	 * on the linux-kernel list, you have been warned.
	 */
}

#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
static ssize_t print_cpu_modalias(struct device *dev,
				  struct device_attribute *attr,
				  char *buf)
{
	ssize_t n;
	u32 i;

	n = sprintf(buf, "cpu:type:" CPU_FEATURE_TYPEFMT ":feature:",
		    CPU_FEATURE_TYPEVAL);

	for (i = 0; i < MAX_CPU_FEATURES; i++)
		if (cpu_have_feature(i)) {
			if (PAGE_SIZE < n + sizeof(",XXXX\n")) {
				WARN(1, "CPU features overflow page\n");
				break;
			}
			n += sprintf(&buf[n], ",%04X", i);
		}
	buf[n++] = '\n';
	return n;
}

static int cpu_uevent(struct device *dev, struct kobj_uevent_env *env)
{
	char *buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
	if (buf) {
		print_cpu_modalias(NULL, NULL, buf);
		add_uevent_var(env, "MODALIAS=%s", buf);
		kfree(buf);
	}
	return 0;
}
#endif

/*
 * register_cpu - Setup a sysfs device for a CPU.
 * @cpu - cpu->hotpluggable field set to 1 will generate a control file in
 *	  sysfs for this CPU.
 * @num - CPU number to use when creating the device.
 *
 * Initialize and register the CPU device.
 */
int register_cpu(struct cpu *cpu, int num)
{
	int error;

	cpu->node_id = cpu_to_node(num);
	memset(&cpu->dev, 0x00, sizeof(struct device));
	cpu->dev.id = num;
	cpu->dev.bus = &cpu_subsys;
	cpu->dev.release = cpu_device_release;
	cpu->dev.offline_disabled = !cpu->hotpluggable;
	cpu->dev.offline = !cpu_online(num);
	cpu->dev.of_node = of_get_cpu_node(num, NULL);
#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
	cpu->dev.bus->uevent = cpu_uevent;
#endif
	cpu->dev.groups = common_cpu_attr_groups;
	if (cpu->hotpluggable)
		cpu->dev.groups = hotplugable_cpu_attr_groups;
	error = device_register(&cpu->dev);
	if (error)
		return error;

	per_cpu(cpu_sys_devices, num) = &cpu->dev;
	register_cpu_under_node(num, cpu_to_node(num));
	dev_pm_qos_expose_latency_limit(&cpu->dev, 0);

	return 0;
}

struct device *get_cpu_device(unsigned cpu)
{
	if (cpu < nr_cpu_ids && cpu_possible(cpu))
		return per_cpu(cpu_sys_devices, cpu);
	else
		return NULL;
}
EXPORT_SYMBOL_GPL(get_cpu_device);

static void device_create_release(struct device *dev)
{
	kfree(dev);
}

static struct device *
__cpu_device_create(struct device *parent, void *drvdata,
		    const struct attribute_group **groups,
		    const char *fmt, va_list args)
{
	struct device *dev = NULL;
	int retval = -ENODEV;

	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
	if (!dev) {
		retval = -ENOMEM;
		goto error;
	}

	device_initialize(dev);
	dev->parent = parent;
	dev->groups = groups;
	dev->release = device_create_release;
	dev_set_drvdata(dev, drvdata);

	retval = kobject_set_name_vargs(&dev->kobj, fmt, args);
	if (retval)
		goto error;

	retval = device_add(dev);
	if (retval)
		goto error;

	return dev;

error:
	put_device(dev);
	return ERR_PTR(retval);
}

struct device *cpu_device_create(struct device *parent, void *drvdata,
				 const struct attribute_group **groups,
				 const char *fmt, ...)
{
	va_list vargs;
	struct device *dev;

	va_start(vargs, fmt);
	dev = __cpu_device_create(parent, drvdata, groups, fmt, vargs);
	va_end(vargs);
	return dev;
}
EXPORT_SYMBOL_GPL(cpu_device_create);

#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
static DEVICE_ATTR(modalias, 0444, print_cpu_modalias, NULL);
#endif

static struct attribute *cpu_root_attrs[] = {
#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
	&dev_attr_probe.attr,
	&dev_attr_release.attr,
#endif
	&cpu_attrs[0].attr.attr,
	&cpu_attrs[1].attr.attr,
	&cpu_attrs[2].attr.attr,
	&dev_attr_kernel_max.attr,
	&dev_attr_offline.attr,
	&dev_attr_isolated.attr,
#ifdef CONFIG_NO_HZ_FULL
	&dev_attr_nohz_full.attr,
#endif
#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
	&dev_attr_modalias.attr,
#endif
	NULL
};

static struct attribute_group cpu_root_attr_group = {
	.attrs = cpu_root_attrs,
};

static const struct attribute_group *cpu_root_attr_groups[] = {
	&cpu_root_attr_group,
	NULL,
};

bool cpu_is_hotpluggable(unsigned cpu)
{
	struct device *dev = get_cpu_device(cpu);
	return dev && container_of(dev, struct cpu, dev)->hotpluggable;
}
EXPORT_SYMBOL_GPL(cpu_is_hotpluggable);

#ifdef CONFIG_GENERIC_CPU_DEVICES
static DEFINE_PER_CPU(struct cpu, cpu_devices);
#endif

static void __init cpu_dev_register_generic(void)
{
#ifdef CONFIG_GENERIC_CPU_DEVICES
	int i;

	for_each_possible_cpu(i) {
		if (register_cpu(&per_cpu(cpu_devices, i), i))
			panic("Failed to register CPU device");
	}
#endif
}

void __init cpu_dev_init(void)
{
	if (subsys_system_register(&cpu_subsys, cpu_root_attr_groups))
		panic("Failed to register CPU subsystem");

	cpu_dev_register_generic();
}