summaryrefslogtreecommitdiff
path: root/arch/arm64/kernel/topology.c
blob: 7415c166281f80ad44062f4a9cf4bdbc3efb5a5d (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
/*
 * arch/arm64/kernel/topology.c
 *
 * Copyright (C) 2011,2013,2014 Linaro Limited.
 *
 * Based on the arm32 version written by Vincent Guittot in turn based on
 * arch/sh/kernel/topology.c
 *
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 */

#include <linux/acpi.h>
#include <linux/arch_topology.h>
#include <linux/cacheinfo.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/init.h>
#include <linux/percpu.h>
#include <linux/node.h>
#include <linux/nodemask.h>
#include <linux/of.h>
#include <linux/sched.h>
#include <linux/sched/topology.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/string.h>

#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/topology.h>

static int __init get_cpu_for_node(struct device_node *node)
{
	struct device_node *cpu_node;
	int cpu;

	cpu_node = of_parse_phandle(node, "cpu", 0);
	if (!cpu_node)
		return -1;

	cpu = of_cpu_node_to_id(cpu_node);
	if (cpu >= 0)
		topology_parse_cpu_capacity(cpu_node, cpu);
	else
		pr_crit("Unable to find CPU node for %pOF\n", cpu_node);

	of_node_put(cpu_node);
	return cpu;
}

static int __init parse_core(struct device_node *core, int package_id,
			     int core_id)
{
	char name[10];
	bool leaf = true;
	int i = 0;
	int cpu;
	struct device_node *t;

	do {
		snprintf(name, sizeof(name), "thread%d", i);
		t = of_get_child_by_name(core, name);
		if (t) {
			leaf = false;
			cpu = get_cpu_for_node(t);
			if (cpu >= 0) {
				cpu_topology[cpu].package_id = package_id;
				cpu_topology[cpu].core_id = core_id;
				cpu_topology[cpu].thread_id = i;
			} else {
				pr_err("%pOF: Can't get CPU for thread\n",
				       t);
				of_node_put(t);
				return -EINVAL;
			}
			of_node_put(t);
		}
		i++;
	} while (t);

	cpu = get_cpu_for_node(core);
	if (cpu >= 0) {
		if (!leaf) {
			pr_err("%pOF: Core has both threads and CPU\n",
			       core);
			return -EINVAL;
		}

		cpu_topology[cpu].package_id = package_id;
		cpu_topology[cpu].core_id = core_id;
	} else if (leaf) {
		pr_err("%pOF: Can't get CPU for leaf core\n", core);
		return -EINVAL;
	}

	return 0;
}

static int __init parse_cluster(struct device_node *cluster, int depth)
{
	char name[10];
	bool leaf = true;
	bool has_cores = false;
	struct device_node *c;
	static int package_id __initdata;
	int core_id = 0;
	int i, ret;

	/*
	 * First check for child clusters; we currently ignore any
	 * information about the nesting of clusters and present the
	 * scheduler with a flat list of them.
	 */
	i = 0;
	do {
		snprintf(name, sizeof(name), "cluster%d", i);
		c = of_get_child_by_name(cluster, name);
		if (c) {
			leaf = false;
			ret = parse_cluster(c, depth + 1);
			of_node_put(c);
			if (ret != 0)
				return ret;
		}
		i++;
	} while (c);

	/* Now check for cores */
	i = 0;
	do {
		snprintf(name, sizeof(name), "core%d", i);
		c = of_get_child_by_name(cluster, name);
		if (c) {
			has_cores = true;

			if (depth == 0) {
				pr_err("%pOF: cpu-map children should be clusters\n",
				       c);
				of_node_put(c);
				return -EINVAL;
			}

			if (leaf) {
				ret = parse_core(c, package_id, core_id++);
			} else {
				pr_err("%pOF: Non-leaf cluster with core %s\n",
				       cluster, name);
				ret = -EINVAL;
			}

			of_node_put(c);
			if (ret != 0)
				return ret;
		}
		i++;
	} while (c);

	if (leaf && !has_cores)
		pr_warn("%pOF: empty cluster\n", cluster);

	if (leaf)
		package_id++;

	return 0;
}

static int __init parse_dt_topology(void)
{
	struct device_node *cn, *map;
	int ret = 0;
	int cpu;

	cn = of_find_node_by_path("/cpus");
	if (!cn) {
		pr_err("No CPU information found in DT\n");
		return 0;
	}

	/*
	 * When topology is provided cpu-map is essentially a root
	 * cluster with restricted subnodes.
	 */
	map = of_get_child_by_name(cn, "cpu-map");
	if (!map)
		goto out;

	ret = parse_cluster(map, 0);
	if (ret != 0)
		goto out_map;

	topology_normalize_cpu_scale();

	/*
	 * Check that all cores are in the topology; the SMP code will
	 * only mark cores described in the DT as possible.
	 */
	for_each_possible_cpu(cpu)
		if (cpu_topology[cpu].package_id == -1)
			ret = -EINVAL;

out_map:
	of_node_put(map);
out:
	of_node_put(cn);
	return ret;
}

/*
 * cpu topology table
 */
struct cpu_topology cpu_topology[NR_CPUS];
EXPORT_SYMBOL_GPL(cpu_topology);

const struct cpumask *cpu_coregroup_mask(int cpu)
{
	const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu));

	/* Find the smaller of NUMA, core or LLC siblings */
	if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) {
		/* not numa in package, lets use the package siblings */
		core_mask = &cpu_topology[cpu].core_sibling;
	}
	if (cpu_topology[cpu].llc_id != -1) {
		if (cpumask_subset(&cpu_topology[cpu].llc_siblings, core_mask))
			core_mask = &cpu_topology[cpu].llc_siblings;
	}

	return core_mask;
}

static void update_siblings_masks(unsigned int cpuid)
{
	struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
	int cpu;

	/* update core and thread sibling masks */
	for_each_possible_cpu(cpu) {
		cpu_topo = &cpu_topology[cpu];

		if (cpuid_topo->llc_id == cpu_topo->llc_id)
			cpumask_set_cpu(cpu, &cpuid_topo->llc_siblings);

		if (cpuid_topo->package_id != cpu_topo->package_id)
			continue;

		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
		if (cpu != cpuid)
			cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);

		if (cpuid_topo->core_id != cpu_topo->core_id)
			continue;

		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
		if (cpu != cpuid)
			cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
	}
}

void store_cpu_topology(unsigned int cpuid)
{
	struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
	u64 mpidr;

	if (cpuid_topo->package_id != -1)
		goto topology_populated;

	mpidr = read_cpuid_mpidr();

	/* Uniprocessor systems can rely on default topology values */
	if (mpidr & MPIDR_UP_BITMASK)
		return;

	/* Create cpu topology mapping based on MPIDR. */
	if (mpidr & MPIDR_MT_BITMASK) {
		/* Multiprocessor system : Multi-threads per core */
		cpuid_topo->thread_id  = MPIDR_AFFINITY_LEVEL(mpidr, 0);
		cpuid_topo->core_id    = MPIDR_AFFINITY_LEVEL(mpidr, 1);
		cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 2) |
					 MPIDR_AFFINITY_LEVEL(mpidr, 3) << 8;
	} else {
		/* Multiprocessor system : Single-thread per core */
		cpuid_topo->thread_id  = -1;
		cpuid_topo->core_id    = MPIDR_AFFINITY_LEVEL(mpidr, 0);
		cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 1) |
					 MPIDR_AFFINITY_LEVEL(mpidr, 2) << 8 |
					 MPIDR_AFFINITY_LEVEL(mpidr, 3) << 16;
	}

	pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n",
		 cpuid, cpuid_topo->package_id, cpuid_topo->core_id,
		 cpuid_topo->thread_id, mpidr);

topology_populated:
	update_siblings_masks(cpuid);
}

static void __init reset_cpu_topology(void)
{
	unsigned int cpu;

	for_each_possible_cpu(cpu) {
		struct cpu_topology *cpu_topo = &cpu_topology[cpu];

		cpu_topo->thread_id = -1;
		cpu_topo->core_id = 0;
		cpu_topo->package_id = -1;

		cpu_topo->llc_id = -1;
		cpumask_clear(&cpu_topo->llc_siblings);
		cpumask_set_cpu(cpu, &cpu_topo->llc_siblings);

		cpumask_clear(&cpu_topo->core_sibling);
		cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
		cpumask_clear(&cpu_topo->thread_sibling);
		cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
	}
}

#ifdef CONFIG_ACPI
/*
 * Propagate the topology information of the processor_topology_node tree to the
 * cpu_topology array.
 */
static int __init parse_acpi_topology(void)
{
	bool is_threaded;
	int cpu, topology_id;

	is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK;

	for_each_possible_cpu(cpu) {
		int i, cache_id;

		topology_id = find_acpi_cpu_topology(cpu, 0);
		if (topology_id < 0)
			return topology_id;

		if (is_threaded) {
			cpu_topology[cpu].thread_id = topology_id;
			topology_id = find_acpi_cpu_topology(cpu, 1);
			cpu_topology[cpu].core_id   = topology_id;
		} else {
			cpu_topology[cpu].thread_id  = -1;
			cpu_topology[cpu].core_id    = topology_id;
		}
		topology_id = find_acpi_cpu_topology_package(cpu);
		cpu_topology[cpu].package_id = topology_id;

		i = acpi_find_last_cache_level(cpu);

		if (i > 0) {
			/*
			 * this is the only part of cpu_topology that has
			 * a direct relationship with the cache topology
			 */
			cache_id = find_acpi_cpu_cache_topology(cpu, i);
			if (cache_id > 0)
				cpu_topology[cpu].llc_id = cache_id;
		}
	}

	return 0;
}

#else
static inline int __init parse_acpi_topology(void)
{
	return -EINVAL;
}
#endif

void __init init_cpu_topology(void)
{
	reset_cpu_topology();

	/*
	 * Discard anything that was parsed if we hit an error so we
	 * don't use partial information.
	 */
	if (!acpi_disabled && parse_acpi_topology())
		reset_cpu_topology();
	else if (of_have_populated_dt() && parse_dt_topology())
		reset_cpu_topology();
}