topology.c 8.4 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19
/*
 * arch/arm/kernel/topology.c
 *
 * Copyright (C) 2011 Linaro Limited.
 * Written by: Vincent Guittot
 *
 * 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/cpu.h>
#include <linux/cpumask.h>
#include <linux/init.h>
#include <linux/percpu.h>
#include <linux/node.h>
#include <linux/nodemask.h>
20
#include <linux/of.h>
21
#include <linux/sched.h>
22
#include <linux/slab.h>
23 24 25 26

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

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
/*
 * cpu power scale management
 */

/*
 * cpu power table
 * This per cpu data structure describes the relative capacity of each core.
 * On a heteregenous system, cores don't have the same computation capacity
 * and we reflect that difference in the cpu_power field so the scheduler can
 * take this difference into account during load balance. A per cpu structure
 * is preferred because each CPU updates its own cpu_power field during the
 * load balance except for idle cores. One idle core is selected to run the
 * rebalance_domains for all idle cores and the cpu_power can be updated
 * during this sequence.
 */
static DEFINE_PER_CPU(unsigned long, cpu_scale);

unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
{
	return per_cpu(cpu_scale, cpu);
}

static void set_power_scale(unsigned int cpu, unsigned long power)
{
	per_cpu(cpu_scale, cpu) = power;
}

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
#ifdef CONFIG_OF
struct cpu_efficiency {
	const char *compatible;
	unsigned long efficiency;
};

/*
 * Table of relative efficiency of each processors
 * The efficiency value must fit in 20bit and the final
 * cpu_scale value must be in the range
 *   0 < cpu_scale < 3*SCHED_POWER_SCALE/2
 * in order to return at most 1 when DIV_ROUND_CLOSEST
 * is used to compute the capacity of a CPU.
 * Processors that are not defined in the table,
 * use the default SCHED_POWER_SCALE value for cpu_scale.
 */
struct cpu_efficiency table_efficiency[] = {
	{"arm,cortex-a15", 3891},
	{"arm,cortex-a7",  2048},
	{NULL, },
};

struct cpu_capacity {
	unsigned long hwid;
	unsigned long capacity;
};

struct cpu_capacity *cpu_capacity;

unsigned long middle_capacity = 1;

/*
 * Iterate all CPUs' descriptor in DT and compute the efficiency
 * (as per table_efficiency). Also calculate a middle efficiency
 * as close as possible to  (max{eff_i} - min{eff_i}) / 2
 * This is later used to scale the cpu_power field such that an
 * 'average' CPU is of middle power. Also see the comments near
 * table_efficiency[] and update_cpu_power().
 */
static void __init parse_dt_topology(void)
{
	struct cpu_efficiency *cpu_eff;
	struct device_node *cn = NULL;
	unsigned long min_capacity = (unsigned long)(-1);
	unsigned long max_capacity = 0;
	unsigned long capacity = 0;
	int alloc_size, cpu = 0;

	alloc_size = nr_cpu_ids * sizeof(struct cpu_capacity);
103
	cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);
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

	while ((cn = of_find_node_by_type(cn, "cpu"))) {
		const u32 *rate, *reg;
		int len;

		if (cpu >= num_possible_cpus())
			break;

		for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++)
			if (of_device_is_compatible(cn, cpu_eff->compatible))
				break;

		if (cpu_eff->compatible == NULL)
			continue;

		rate = of_get_property(cn, "clock-frequency", &len);
		if (!rate || len != 4) {
			pr_err("%s missing clock-frequency property\n",
				cn->full_name);
			continue;
		}

		reg = of_get_property(cn, "reg", &len);
		if (!reg || len != 4) {
			pr_err("%s missing reg property\n", cn->full_name);
			continue;
		}

		capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency;

		/* Save min capacity of the system */
		if (capacity < min_capacity)
			min_capacity = capacity;

		/* Save max capacity of the system */
		if (capacity > max_capacity)
			max_capacity = capacity;

		cpu_capacity[cpu].capacity = capacity;
		cpu_capacity[cpu++].hwid = be32_to_cpup(reg);
	}

	if (cpu < num_possible_cpus())
		cpu_capacity[cpu].hwid = (unsigned long)(-1);

	/* If min and max capacities are equals, we bypass the update of the
	 * cpu_scale because all CPUs have the same capacity. Otherwise, we
	 * compute a middle_capacity factor that will ensure that the capacity
	 * of an 'average' CPU of the system will be as close as possible to
	 * SCHED_POWER_SCALE, which is the default value, but with the
	 * constraint explained near table_efficiency[].
	 */
	if (min_capacity == max_capacity)
		cpu_capacity[0].hwid = (unsigned long)(-1);
	else if (4*max_capacity < (3*(max_capacity + min_capacity)))
		middle_capacity = (min_capacity + max_capacity)
				>> (SCHED_POWER_SHIFT+1);
	else
		middle_capacity = ((max_capacity / 3)
				>> (SCHED_POWER_SHIFT-1)) + 1;

}

/*
 * Look for a customed capacity of a CPU in the cpu_capacity table during the
 * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
 * function returns directly for SMP system.
 */
void update_cpu_power(unsigned int cpu, unsigned long hwid)
{
	unsigned int idx = 0;

	/* look for the cpu's hwid in the cpu capacity table */
	for (idx = 0; idx < num_possible_cpus(); idx++) {
		if (cpu_capacity[idx].hwid == hwid)
			break;

		if (cpu_capacity[idx].hwid == -1)
			return;
	}

	if (idx == num_possible_cpus())
		return;

	set_power_scale(cpu, cpu_capacity[idx].capacity / middle_capacity);

	printk(KERN_INFO "CPU%u: update cpu_power %lu\n",
		cpu, arch_scale_freq_power(NULL, cpu));
}

#else
static inline void parse_dt_topology(void) {}
static inline void update_cpu_power(unsigned int cpuid, unsigned int mpidr) {}
#endif

199
 /*
200 201
 * cpu topology table
 */
202 203
struct cputopo_arm cpu_topology[NR_CPUS];

204
const struct cpumask *cpu_coregroup_mask(int cpu)
205 206 207 208
{
	return &cpu_topology[cpu].core_sibling;
}

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
void update_siblings_masks(unsigned int cpuid)
{
	struct cputopo_arm *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->socket_id != cpu_topo->socket_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);
	}
	smp_wmb();
}

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
/*
 * store_cpu_topology is called at boot when only one cpu is running
 * and with the mutex cpu_hotplug.lock locked, when several cpus have booted,
 * which prevents simultaneous write access to cpu_topology array
 */
void store_cpu_topology(unsigned int cpuid)
{
	struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid];
	unsigned int mpidr;

	/* If the cpu topology has been already set, just return */
	if (cpuid_topo->core_id != -1)
		return;

	mpidr = read_cpuid_mpidr();

	/* create cpu topology mapping */
	if ((mpidr & MPIDR_SMP_BITMASK) == MPIDR_SMP_VALUE) {
		/*
		 * This is a multiprocessor system
		 * multiprocessor format & multiprocessor mode field are set
		 */

		if (mpidr & MPIDR_MT_BITMASK) {
			/* core performance interdependency */
260 261 262
			cpuid_topo->thread_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
			cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
			cpuid_topo->socket_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
263 264 265
		} else {
			/* largely independent cores */
			cpuid_topo->thread_id = -1;
266 267
			cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
			cpuid_topo->socket_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
268 269 270 271 272 273 274 275 276 277 278 279
		}
	} else {
		/*
		 * This is an uniprocessor system
		 * we are in multiprocessor format but uniprocessor system
		 * or in the old uniprocessor format
		 */
		cpuid_topo->thread_id = -1;
		cpuid_topo->core_id = 0;
		cpuid_topo->socket_id = -1;
	}

280
	update_siblings_masks(cpuid);
281

282 283
	update_cpu_power(cpuid, mpidr & MPIDR_HWID_BITMASK);

284 285 286 287 288 289 290 291 292 293
	printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n",
		cpuid, cpu_topology[cpuid].thread_id,
		cpu_topology[cpuid].core_id,
		cpu_topology[cpuid].socket_id, mpidr);
}

/*
 * init_cpu_topology is called at boot when only one cpu is running
 * which prevent simultaneous write access to cpu_topology array
 */
294
void __init init_cpu_topology(void)
295 296 297
{
	unsigned int cpu;

298
	/* init core mask and power*/
299 300 301 302 303 304 305 306
	for_each_possible_cpu(cpu) {
		struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);

		cpu_topo->thread_id = -1;
		cpu_topo->core_id =  -1;
		cpu_topo->socket_id = -1;
		cpumask_clear(&cpu_topo->core_sibling);
		cpumask_clear(&cpu_topo->thread_sibling);
307 308

		set_power_scale(cpu, SCHED_POWER_SCALE);
309 310
	}
	smp_wmb();
311 312

	parse_dt_topology();
313
}