aboutsummaryrefslogtreecommitdiffstats
path: root/arch/s390/kernel/topology.c
blob: 05151e06c38808e8fb7e70acf487aaae6c031e93 (plain) (blame)
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
/*
 *    Copyright IBM Corp. 2007, 2011
 *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
 */

#define KMSG_COMPONENT "cpu"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt

#include <linux/workqueue.h>
#include <linux/bootmem.h>
#include <linux/cpuset.h>
#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/cpu.h>
#include <linux/smp.h>
#include <linux/mm.h>

#define PTF_HORIZONTAL	(0UL)
#define PTF_VERTICAL	(1UL)
#define PTF_CHECK	(2UL)

struct mask_info {
	struct mask_info *next;
	unsigned char id;
	cpumask_t mask;
};

static int topology_enabled = 1;
static void topology_work_fn(struct work_struct *work);
static struct sysinfo_15_1_x *tl_info;
static void set_topology_timer(void);
static DECLARE_WORK(topology_work, topology_work_fn);
/* topology_lock protects the core linked list */
static DEFINE_SPINLOCK(topology_lock);

static struct mask_info core_info;
cpumask_t cpu_core_map[NR_CPUS];
unsigned char cpu_core_id[NR_CPUS];

static struct mask_info book_info;
cpumask_t cpu_book_map[NR_CPUS];
unsigned char cpu_book_id[NR_CPUS];

/* smp_cpu_state_mutex must be held when accessing this array */
int cpu_polarization[NR_CPUS];

static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
{
	cpumask_t mask;

	cpumask_clear(&mask);
	if (!topology_enabled || !MACHINE_HAS_TOPOLOGY) {
		cpumask_copy(&mask, cpumask_of(cpu));
		return mask;
	}
	while (info) {
		if (cpumask_test_cpu(cpu, &info->mask)) {
			mask = info->mask;
			break;
		}
		info = info->next;
	}
	if (cpumask_empty(&mask))
		cpumask_copy(&mask, cpumask_of(cpu));
	return mask;
}

static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu,
					  struct mask_info *book,
					  struct mask_info *core,
					  int one_core_per_cpu)
{
	unsigned int cpu;

	for (cpu = find_first_bit(&tl_cpu->mask[0], TOPOLOGY_CPU_BITS);
	     cpu < TOPOLOGY_CPU_BITS;
	     cpu = find_next_bit(&tl_cpu->mask[0], TOPOLOGY_CPU_BITS, cpu + 1))
	{
		unsigned int rcpu;
		int lcpu;

		rcpu = TOPOLOGY_CPU_BITS - 1 - cpu + tl_cpu->origin;
		lcpu = smp_find_processor_id(rcpu);
		if (lcpu >= 0) {
			cpumask_set_cpu(lcpu, &book->mask);
			cpu_book_id[lcpu] = book->id;
			cpumask_set_cpu(lcpu, &core->mask);
			if (one_core_per_cpu) {
				cpu_core_id[lcpu] = rcpu;
				core = core->next;
			} else {
				cpu_core_id[lcpu] = core->id;
			}
			cpu_set_polarization(lcpu, tl_cpu->pp);
		}
	}
	return core;
}

static void clear_masks(void)
{
	struct mask_info *info;

	info = &core_info;
	while (info) {
		cpumask_clear(&info->mask);
		info = info->next;
	}
	info = &book_info;
	while (info) {
		cpumask_clear(&info->mask);
		info = info->next;
	}
}

static union topology_entry *next_tle(union topology_entry *tle)
{
	if (!tle->nl)
		return (union topology_entry *)((struct topology_cpu *)tle + 1);
	return (union topology_entry *)((struct topology_container *)tle + 1);
}

static void __tl_to_cores_generic(struct sysinfo_15_1_x *info)
{
	struct mask_info *core = &core_info;
	struct mask_info *book = &book_info;
	union topology_entry *tle, *end;

	tle = info->tle;
	end = (union topology_entry *)((unsigned long)info + info->length);
	while (tle < end) {
		switch (tle->nl) {
		case 2:
			book = book->next;
			book->id = tle->container.id;
			break;
		case 1:
			core = core->next;
			core->id = tle->container.id;
			break;
		case 0:
			add_cpus_to_mask(&tle->cpu, book, core, 0);
			break;
		default:
			clear_masks();
			return;
		}
		tle = next_tle(tle);
	}
}

static void __tl_to_cores_z10(struct sysinfo_15_1_x *info)
{
	struct mask_info *core = &core_info;
	struct mask_info *book = &book_info;
	union topology_entry *tle, *end;

	tle = info->tle;
	end = (union topology_entry *)((unsigned long)info + info->length);
	while (tle < end) {
		switch (tle->nl) {
		case 1:
			book = book->next;
			book->id = tle->container.id;
			break;
		case 0:
			core = add_cpus_to_mask(&tle->cpu, book, core, 1);
			break;
		default:
			clear_masks();
			return;
		}
		tle = next_tle(tle);
	}
}

static void tl_to_cores(struct sysinfo_15_1_x *info)
{
	struct cpuid cpu_id;

	get_cpu_id(&cpu_id);
	spin_lock_irq(&topology_lock);
	clear_masks();
	switch (cpu_id.machine) {
	case 0x2097:
	case 0x2098:
		__tl_to_cores_z10(info);
		break;
	default:
		__tl_to_cores_generic(info);
	}
	spin_unlock_irq(&topology_lock);
}

static void topology_update_polarization_simple(void)
{
	int cpu;

	mutex_lock(&smp_cpu_state_mutex);
	for_each_possible_cpu(cpu)
		cpu_set_polarization(cpu, POLARIZATION_HRZ);
	mutex_unlock(&smp_cpu_state_mutex);
}

static int ptf(unsigned long fc)
{
	int rc;

	asm volatile(
		"	.insn	rre,0xb9a20000,%1,%1\n"
		"	ipm	%0\n"
		"	srl	%0,28\n"
		: "=d" (rc)
		: "d" (fc)  : "cc");
	return rc;
}

int topology_set_cpu_management(int fc)
{
	int cpu, rc;

	if (!MACHINE_HAS_TOPOLOGY)
		return -EOPNOTSUPP;
	if (fc)
		rc = ptf(PTF_VERTICAL);
	else
		rc = ptf(PTF_HORIZONTAL);
	if (rc)
		return -EBUSY;
	for_each_possible_cpu(cpu)
		cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
	return rc;
}

static void update_cpu_core_map(void)
{
	unsigned long flags;
	int cpu;

	spin_lock_irqsave(&topology_lock, flags);
	for_each_possible_cpu(cpu) {
		cpu_core_map[cpu] = cpu_group_map(&core_info, cpu);
		cpu_book_map[cpu] = cpu_group_map(&book_info, cpu);
	}
	spin_unlock_irqrestore(&topology_lock, flags);
}

void store_topology(struct sysinfo_15_1_x *info)
{
	int rc;

	rc = stsi(info, 15, 1, 3);
	if (rc != -ENOSYS)
		return;
	stsi(info, 15, 1, 2);
}

int arch_update_cpu_topology(void)
{
	struct sysinfo_15_1_x *info = tl_info;
	struct device *dev;
	int cpu;

	if (!MACHINE_HAS_TOPOLOGY) {
		update_cpu_core_map();
		topology_update_polarization_simple();
		return 0;
	}
	store_topology(info);
	tl_to_cores(info);
	update_cpu_core_map();
	for_each_online_cpu(cpu) {
		dev = get_cpu_device(cpu);
		kobject_uevent(&dev->kobj, KOBJ_CHANGE);
	}
	return 1;
}

static void topology_work_fn(struct work_struct *work)
{
	rebuild_sched_domains();
}

void topology_schedule_update(void)
{
	schedule_work(&topology_work);
}

static void topology_timer_fn(unsigned long ignored)
{
	if (ptf(PTF_CHECK))
		topology_schedule_update();
	set_topology_timer();
}

static struct timer_list topology_timer =
	TIMER_DEFERRED_INITIALIZER(topology_timer_fn, 0, 0);

static atomic_t topology_poll = ATOMIC_INIT(0);

static void set_topology_timer(void)
{
	if (atomic_add_unless(&topology_poll, -1, 0))
		mod_timer(&topology_timer, jiffies + HZ / 10);
	else
		mod_timer(&topology_timer, jiffies + HZ * 60);
}

void topology_expect_change(void)
{
	if (!MACHINE_HAS_TOPOLOGY)
		return;
	/* This is racy, but it doesn't matter since it is just a heuristic.
	 * Worst case is that we poll in a higher frequency for a bit longer.
	 */
	if (atomic_read(&topology_poll) > 60)
		return;
	atomic_add(60, &topology_poll);
	set_topology_timer();
}

static int __init early_parse_topology(char *p)
{
	if (strncmp(p, "off", 3))
		return 0;
	topology_enabled = 0;
	return 0;
}
early_param("topology", early_parse_topology);

static void __init alloc_masks(struct sysinfo_15_1_x *info,
			       struct mask_info *mask, int offset)
{
	int i, nr_masks;

	nr_masks = info->mag[TOPOLOGY_NR_MAG - offset];
	for (i = 0; i < info->mnest - offset; i++)
		nr_masks *= info->mag[TOPOLOGY_NR_MAG - offset - 1 - i];
	nr_masks = max(nr_masks, 1);
	for (i = 0; i < nr_masks; i++) {
		mask->next = alloc_bootmem(sizeof(struct mask_info));
		mask = mask->next;
	}
}

void __init s390_init_cpu_topology(void)
{
	struct sysinfo_15_1_x *info;
	int i;

	if (!MACHINE_HAS_TOPOLOGY)
		return;
	tl_info = alloc_bootmem_pages(PAGE_SIZE);
	info = tl_info;
	store_topology(info);
	pr_info("The CPU configuration topology of the machine is:");
	for (i = 0; i < TOPOLOGY_NR_MAG; i++)
		printk(KERN_CONT " %d", info->mag[i]);
	printk(KERN_CONT " / %d\n", info->mnest);
	alloc_masks(info, &core_info, 1);
	alloc_masks(info, &book_info, 2);
}

static int cpu_management;

static ssize_t dispatching_show(struct device *dev,
				struct device_attribute *attr,
				char *buf)
{
	ssize_t count;

	mutex_lock(&smp_cpu_state_mutex);
	count = sprintf(buf, "%d\n", cpu_management);
	mutex_unlock(&smp_cpu_state_mutex);
	return count;
}

static ssize_t dispatching_store(struct device *dev,
				 struct device_attribute *attr,
				 const char *buf,
				 size_t count)
{
	int val, rc;
	char delim;

	if (sscanf(buf, "%d %c", &val, &delim) != 1)
		return -EINVAL;
	if (val != 0 && val != 1)
		return -EINVAL;
	rc = 0;
	get_online_cpus();
	mutex_lock(&smp_cpu_state_mutex);
	if (cpu_management == val)
		goto out;
	rc = topology_set_cpu_management(val);
	if (rc)
		goto out;
	cpu_management = val;
	topology_expect_change();
out:
	mutex_unlock(&smp_cpu_state_mutex);
	put_online_cpus();
	return rc ? rc : count;
}
static DEVICE_ATTR(dispatching, 0644, dispatching_show,
			 dispatching_store);

static ssize_t cpu_polarization_show(struct device *dev,
				     struct device_attribute *attr, char *buf)
{
	int cpu = dev->id;
	ssize_t count;

	mutex_lock(&smp_cpu_state_mutex);
	switch (cpu_read_polarization(cpu)) {
	case POLARIZATION_HRZ:
		count = sprintf(buf, "horizontal\n");
		break;
	case POLARIZATION_VL:
		count = sprintf(buf, "vertical:low\n");
		break;
	case POLARIZATION_VM:
		count = sprintf(buf, "vertical:medium\n");
		break;
	case POLARIZATION_VH:
		count = sprintf(buf, "vertical:high\n");
		break;
	default:
		count = sprintf(buf, "unknown\n");
		break;
	}
	mutex_unlock(&smp_cpu_state_mutex);
	return count;
}
static DEVICE_ATTR(polarization, 0444, cpu_polarization_show, NULL);

static struct attribute *topology_cpu_attrs[] = {
	&dev_attr_polarization.attr,
	NULL,
};

static struct attribute_group topology_cpu_attr_group = {
	.attrs = topology_cpu_attrs,
};

int topology_cpu_init(struct cpu *cpu)
{
	return sysfs_create_group(&cpu->dev.kobj, &topology_cpu_attr_group);
}

static int __init topology_init(void)
{
	if (!MACHINE_HAS_TOPOLOGY) {
		topology_update_polarization_simple();
		goto out;
	}
	set_topology_timer();
out:
	update_cpu_core_map();
	return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching);
}
device_initcall(topology_init);