summaryrefslogtreecommitdiffstats
path: root/arch/ia64/kernel/domain.c
blob: fe532c970438973393cb4e1dc40f502e15aef858 (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
/*
 * arch/ia64/kernel/domain.c
 * Architecture specific sched-domains builder.
 *
 * Copyright (C) 2004 Jesse Barnes
 * Copyright (C) 2004 Silicon Graphics, Inc.
 */

#include <linux/sched.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/cpumask.h>
#include <linux/init.h>
#include <linux/topology.h>
#include <linux/nodemask.h>

#define SD_NODES_PER_DOMAIN 6

#ifdef CONFIG_NUMA
/**
 * find_next_best_node - find the next node to include in a sched_domain
 * @node: node whose sched_domain we're building
 * @used_nodes: nodes already in the sched_domain
 *
 * Find the next node to include in a given scheduling domain.  Simply
 * finds the closest node not already in the @used_nodes map.
 *
 * Should use nodemask_t.
 */
static int __devinit find_next_best_node(int node, unsigned long *used_nodes)
{
	int i, n, val, min_val, best_node = 0;

	min_val = INT_MAX;

	for (i = 0; i < MAX_NUMNODES; i++) {
		/* Start at @node */
		n = (node + i) % MAX_NUMNODES;

		if (!nr_cpus_node(n))
			continue;

		/* Skip already used nodes */
		if (test_bit(n, used_nodes))
			continue;

		/* Simple min distance search */
		val = node_distance(node, n);

		if (val < min_val) {
			min_val = val;
			best_node = n;
		}
	}

	set_bit(best_node, used_nodes);
	return best_node;
}

/**
 * sched_domain_node_span - get a cpumask for a node's sched_domain
 * @node: node whose cpumask we're constructing
 * @size: number of nodes to include in this span
 *
 * Given a node, construct a good cpumask for its sched_domain to span.  It
 * should be one that prevents unnecessary balancing, but also spreads tasks
 * out optimally.
 */
static cpumask_t __devinit sched_domain_node_span(int node)
{
	int i;
	cpumask_t span, nodemask;
	DECLARE_BITMAP(used_nodes, MAX_NUMNODES);

	cpus_clear(span);
	bitmap_zero(used_nodes, MAX_NUMNODES);

	nodemask = node_to_cpumask(node);
	cpus_or(span, span, nodemask);
	set_bit(node, used_nodes);

	for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
		int next_node = find_next_best_node(node, used_nodes);
		nodemask = node_to_cpumask(next_node);
		cpus_or(span, span, nodemask);
	}

	return span;
}
#endif

/*
 * At the moment, CONFIG_SCHED_SMT is never defined, but leave it in so we
 * can switch it on easily if needed.
 */
#ifdef CONFIG_SCHED_SMT
static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
static struct sched_group sched_group_cpus[NR_CPUS];
static int __devinit cpu_to_cpu_group(int cpu)
{
	return cpu;
}
#endif

static DEFINE_PER_CPU(struct sched_domain, phys_domains);
static struct sched_group sched_group_phys[NR_CPUS];
static int __devinit cpu_to_phys_group(int cpu)
{
#ifdef CONFIG_SCHED_SMT
	return first_cpu(cpu_sibling_map[cpu]);
#else
	return cpu;
#endif
}

#ifdef CONFIG_NUMA
/*
 * The init_sched_build_groups can't handle what we want to do with node
 * groups, so roll our own. Now each node has its own list of groups which
 * gets dynamically allocated.
 */
static DEFINE_PER_CPU(struct sched_domain, node_domains);
static struct sched_group *sched_group_nodes[MAX_NUMNODES];

static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
static struct sched_group sched_group_allnodes[MAX_NUMNODES];

static int __devinit cpu_to_allnodes_group(int cpu)
{
	return cpu_to_node(cpu);
}
#endif

/*
 * Set up scheduler domains and groups.  Callers must hold the hotplug lock.
 */
void __devinit arch_init_sched_domains(void)
{
	int i;
	cpumask_t cpu_default_map;

	/*
	 * Setup mask for cpus without special case scheduling requirements.
	 * For now this just excludes isolated cpus, but could be used to
	 * exclude other special cases in the future.
	 */
	cpus_complement(cpu_default_map, cpu_isolated_map);
	cpus_and(cpu_default_map, cpu_default_map, cpu_online_map);

	/*
	 * Set up domains. Isolated domains just stay on the dummy domain.
	 */
	for_each_cpu_mask(i, cpu_default_map) {
		int group;
		struct sched_domain *sd = NULL, *p;
		cpumask_t nodemask = node_to_cpumask(cpu_to_node(i));

		cpus_and(nodemask, nodemask, cpu_default_map);

#ifdef CONFIG_NUMA
		if (num_online_cpus()
				> SD_NODES_PER_DOMAIN*cpus_weight(nodemask)) {
			sd = &per_cpu(allnodes_domains, i);
			*sd = SD_ALLNODES_INIT;
			sd->span = cpu_default_map;
			group = cpu_to_allnodes_group(i);
			sd->groups = &sched_group_allnodes[group];
			p = sd;
		} else
			p = NULL;

		sd = &per_cpu(node_domains, i);
		*sd = SD_NODE_INIT;
		sd->span = sched_domain_node_span(cpu_to_node(i));
		sd->parent = p;
		cpus_and(sd->span, sd->span, cpu_default_map);
#endif

		p = sd;
		sd = &per_cpu(phys_domains, i);
		group = cpu_to_phys_group(i);
		*sd = SD_CPU_INIT;
		sd->span = nodemask;
		sd->parent = p;
		sd->groups = &sched_group_phys[group];

#ifdef CONFIG_SCHED_SMT
		p = sd;
		sd = &per_cpu(cpu_domains, i);
		group = cpu_to_cpu_group(i);
		*sd = SD_SIBLING_INIT;
		sd->span = cpu_sibling_map[i];
		cpus_and(sd->span, sd->span, cpu_default_map);
		sd->parent = p;
		sd->groups = &sched_group_cpus[group];
#endif
	}

#ifdef CONFIG_SCHED_SMT
	/* Set up CPU (sibling) groups */
	for_each_cpu_mask(i, cpu_default_map) {
		cpumask_t this_sibling_map = cpu_sibling_map[i];
		cpus_and(this_sibling_map, this_sibling_map, cpu_default_map);
		if (i != first_cpu(this_sibling_map))
			continue;

		init_sched_build_groups(sched_group_cpus, this_sibling_map,
						&cpu_to_cpu_group);
	}
#endif

	/* Set up physical groups */
	for (i = 0; i < MAX_NUMNODES; i++) {
		cpumask_t nodemask = node_to_cpumask(i);

		cpus_and(nodemask, nodemask, cpu_default_map);
		if (cpus_empty(nodemask))
			continue;

		init_sched_build_groups(sched_group_phys, nodemask,
						&cpu_to_phys_group);
	}

#ifdef CONFIG_NUMA
	init_sched_build_groups(sched_group_allnodes, cpu_default_map,
				&cpu_to_allnodes_group);

	for (i = 0; i < MAX_NUMNODES; i++) {
		/* Set up node groups */
		struct sched_group *sg, *prev;
		cpumask_t nodemask = node_to_cpumask(i);
		cpumask_t domainspan;
		cpumask_t covered = CPU_MASK_NONE;
		int j;

		cpus_and(nodemask, nodemask, cpu_default_map);
		if (cpus_empty(nodemask))
			continue;

		domainspan = sched_domain_node_span(i);
		cpus_and(domainspan, domainspan, cpu_default_map);

		sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL);
		sched_group_nodes[i] = sg;
		for_each_cpu_mask(j, nodemask) {
			struct sched_domain *sd;
			sd = &per_cpu(node_domains, j);
			sd->groups = sg;
			if (sd->groups == NULL) {
				/* Turn off balancing if we have no groups */
				sd->flags = 0;
			}
		}
		if (!sg) {
			printk(KERN_WARNING
			"Can not alloc domain group for node %d\n", i);
			continue;
		}
		sg->cpu_power = 0;
		sg->cpumask = nodemask;
		cpus_or(covered, covered, nodemask);
		prev = sg;

		for (j = 0; j < MAX_NUMNODES; j++) {
			cpumask_t tmp, notcovered;
			int n = (i + j) % MAX_NUMNODES;

			cpus_complement(notcovered, covered);
			cpus_and(tmp, notcovered, cpu_default_map);
			cpus_and(tmp, tmp, domainspan);
			if (cpus_empty(tmp))
				break;

			nodemask = node_to_cpumask(n);
			cpus_and(tmp, tmp, nodemask);
			if (cpus_empty(tmp))
				continue;

			sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL);
			if (!sg) {
				printk(KERN_WARNING
				"Can not alloc domain group for node %d\n", j);
				break;
			}
			sg->cpu_power = 0;
			sg->cpumask = tmp;
			cpus_or(covered, covered, tmp);
			prev->next = sg;
			prev = sg;
		}
		prev->next = sched_group_nodes[i];
	}
#endif

	/* Calculate CPU power for physical packages and nodes */
	for_each_cpu_mask(i, cpu_default_map) {
		int power;
		struct sched_domain *sd;
#ifdef CONFIG_SCHED_SMT
		sd = &per_cpu(cpu_domains, i);
		power = SCHED_LOAD_SCALE;
		sd->groups->cpu_power = power;
#endif

		sd = &per_cpu(phys_domains, i);
		power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
				(cpus_weight(sd->groups->cpumask)-1) / 10;
		sd->groups->cpu_power = power;

#ifdef CONFIG_NUMA
		sd = &per_cpu(allnodes_domains, i);
		if (sd->groups) {
			power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
				(cpus_weight(sd->groups->cpumask)-1) / 10;
			sd->groups->cpu_power = power;
		}
#endif
	}

#ifdef CONFIG_NUMA
	for (i = 0; i < MAX_NUMNODES; i++) {
		struct sched_group *sg = sched_group_nodes[i];
		int j;

		if (sg == NULL)
			continue;
next_sg:
		for_each_cpu_mask(j, sg->cpumask) {
			struct sched_domain *sd;
			int power;

			sd = &per_cpu(phys_domains, j);
			if (j != first_cpu(sd->groups->cpumask)) {
				/*
				 * Only add "power" once for each
				 * physical package.
				 */
				continue;
			}
			power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
				(cpus_weight(sd->groups->cpumask)-1) / 10;

			sg->cpu_power += power;
		}
		sg = sg->next;
		if (sg != sched_group_nodes[i])
			goto next_sg;
	}
#endif

	/* Attach the domains */
	for_each_online_cpu(i) {
		struct sched_domain *sd;
#ifdef CONFIG_SCHED_SMT
		sd = &per_cpu(cpu_domains, i);
#else
		sd = &per_cpu(phys_domains, i);
#endif
		cpu_attach_domain(sd, i);
	}
}

void __devinit arch_destroy_sched_domains(void)
{
#ifdef CONFIG_NUMA
	int i;
	for (i = 0; i < MAX_NUMNODES; i++) {
		struct sched_group *oldsg, *sg = sched_group_nodes[i];
		if (sg == NULL)
			continue;
		sg = sg->next;
next_sg:
		oldsg = sg;
		sg = sg->next;
		kfree(oldsg);
		if (oldsg != sched_group_nodes[i])
			goto next_sg;
		sched_group_nodes[i] = NULL;
	}
#endif
}