processor_idle.c 8.2 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13
/*
 *  processor_idle - idle state cpuidle driver.
 *  Adapted from drivers/idle/intel_idle.c and
 *  drivers/acpi/processor_idle.c
 *
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/moduleparam.h>
#include <linux/cpuidle.h>
#include <linux/cpu.h>
14
#include <linux/notifier.h>
15 16 17 18 19

#include <asm/paca.h>
#include <asm/reg.h>
#include <asm/machdep.h>
#include <asm/firmware.h>
20
#include <asm/runlatch.h>
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

#include "plpar_wrappers.h"
#include "pseries.h"

struct cpuidle_driver pseries_idle_driver = {
	.name =		"pseries_idle",
	.owner =	THIS_MODULE,
};

#define MAX_IDLE_STATE_COUNT	2

static int max_idle_state = MAX_IDLE_STATE_COUNT - 1;
static struct cpuidle_device __percpu *pseries_cpuidle_devices;
static struct cpuidle_state *cpuidle_state_table;

static inline void idle_loop_prolog(unsigned long *in_purr, ktime_t *kt_before)
{

	*kt_before = ktime_get_real();
	*in_purr = mfspr(SPRN_PURR);
	/*
	 * Indicate to the HV that we are idle. Now would be
	 * a good time to find other work to dispatch.
	 */
	get_lppaca()->idle = 1;
}

static inline  s64 idle_loop_epilog(unsigned long in_purr, ktime_t kt_before)
{
	get_lppaca()->wait_state_cycles += mfspr(SPRN_PURR) - in_purr;
	get_lppaca()->idle = 0;

	return ktime_to_us(ktime_sub(ktime_get_real(), kt_before));
}

static int snooze_loop(struct cpuidle_device *dev,
			struct cpuidle_driver *drv,
			int index)
{
	unsigned long in_purr;
	ktime_t kt_before;
	unsigned long start_snooze;
	long snooze = drv->states[0].target_residency;

	idle_loop_prolog(&in_purr, &kt_before);

	if (snooze) {
		start_snooze = get_tb() + snooze * tb_ticks_per_usec;
		local_irq_enable();
		set_thread_flag(TIF_POLLING_NRFLAG);

		while ((snooze < 0) || (get_tb() < start_snooze)) {
			if (need_resched() || cpu_is_offline(dev->cpu))
				goto out;
			ppc64_runlatch_off();
			HMT_low();
			HMT_very_low();
		}

		HMT_medium();
		clear_thread_flag(TIF_POLLING_NRFLAG);
		smp_mb();
		local_irq_disable();
	}

out:
	HMT_medium();
	dev->last_residency =
		(int)idle_loop_epilog(in_purr, kt_before);
	return index;
}

93 94 95
static void check_and_cede_processor(void)
{
	/*
96 97 98
	 * Ensure our interrupt state is properly tracked,
	 * also checks if no interrupt has occurred while we
	 * were soft-disabled
99
	 */
100
	if (prep_irq_for_idle()) {
101
		cede_processor();
102 103 104 105 106 107
#ifdef CONFIG_TRACE_IRQFLAGS
		/* Ensure that H_CEDE returns with IRQs on */
		if (WARN_ON(!(mfmsr() & MSR_EE)))
			__hard_irq_enable();
#endif
	}
108 109
}

110 111 112 113 114 115 116 117 118 119 120 121
static int dedicated_cede_loop(struct cpuidle_device *dev,
				struct cpuidle_driver *drv,
				int index)
{
	unsigned long in_purr;
	ktime_t kt_before;

	idle_loop_prolog(&in_purr, &kt_before);
	get_lppaca()->donate_dedicated_cpu = 1;

	ppc64_runlatch_off();
	HMT_medium();
122
	check_and_cede_processor();
123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145

	get_lppaca()->donate_dedicated_cpu = 0;
	dev->last_residency =
		(int)idle_loop_epilog(in_purr, kt_before);
	return index;
}

static int shared_cede_loop(struct cpuidle_device *dev,
			struct cpuidle_driver *drv,
			int index)
{
	unsigned long in_purr;
	ktime_t kt_before;

	idle_loop_prolog(&in_purr, &kt_before);

	/*
	 * Yield the processor to the hypervisor.  We return if
	 * an external interrupt occurs (which are driven prior
	 * to returning here) or if a prod occurs from another
	 * processor. When returning here, external interrupts
	 * are enabled.
	 */
146
	check_and_cede_processor();
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

	dev->last_residency =
		(int)idle_loop_epilog(in_purr, kt_before);
	return index;
}

/*
 * States for dedicated partition case.
 */
static struct cpuidle_state dedicated_states[MAX_IDLE_STATE_COUNT] = {
	{ /* Snooze */
		.name = "snooze",
		.desc = "snooze",
		.flags = CPUIDLE_FLAG_TIME_VALID,
		.exit_latency = 0,
		.target_residency = 0,
		.enter = &snooze_loop },
	{ /* CEDE */
		.name = "CEDE",
		.desc = "CEDE",
		.flags = CPUIDLE_FLAG_TIME_VALID,
		.exit_latency = 1,
		.target_residency = 10,
		.enter = &dedicated_cede_loop },
};

/*
 * States for shared partition case.
 */
static struct cpuidle_state shared_states[MAX_IDLE_STATE_COUNT] = {
	{ /* Shared Cede */
		.name = "Shared Cede",
		.desc = "Shared Cede",
		.flags = CPUIDLE_FLAG_TIME_VALID,
		.exit_latency = 0,
		.target_residency = 0,
		.enter = &shared_cede_loop },
};

186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202
void update_smt_snooze_delay(int cpu, int residency)
{
	struct cpuidle_driver *drv = cpuidle_get_driver();
	struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);

	if (cpuidle_state_table != dedicated_states)
		return;

	if (residency < 0) {
		/* Disable the Nap state on that cpu */
		if (dev)
			dev->states_usage[1].disable = 1;
	} else
		if (drv)
			drv->states[0].target_residency = residency;
}

203 204
static int pseries_cpuidle_add_cpu_notifier(struct notifier_block *n,
			unsigned long action, void *hcpu)
205
{
206
	int hotcpu = (unsigned long)hcpu;
207
	struct cpuidle_device *dev =
208 209
			per_cpu_ptr(pseries_cpuidle_devices, hotcpu);

210 211 212 213 214
	if (dev && cpuidle_get_driver()) {
		switch (action) {
		case CPU_ONLINE:
		case CPU_ONLINE_FROZEN:
			cpuidle_pause_and_lock();
215
			cpuidle_enable_device(dev);
216 217 218 219 220 221 222 223 224 225 226 227
			cpuidle_resume_and_unlock();
			break;

		case CPU_DEAD:
		case CPU_DEAD_FROZEN:
			cpuidle_pause_and_lock();
			cpuidle_disable_device(dev);
			cpuidle_resume_and_unlock();
			break;

		default:
			return NOTIFY_DONE;
228
		}
229
	}
230
	return NOTIFY_OK;
231 232
}

233 234 235 236
static struct notifier_block setup_hotplug_notifier = {
	.notifier_call = pseries_cpuidle_add_cpu_notifier,
};

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
/*
 * pseries_cpuidle_driver_init()
 */
static int pseries_cpuidle_driver_init(void)
{
	int idle_state;
	struct cpuidle_driver *drv = &pseries_idle_driver;

	drv->state_count = 0;

	for (idle_state = 0; idle_state < MAX_IDLE_STATE_COUNT; ++idle_state) {

		if (idle_state > max_idle_state)
			break;

		/* is the state not enabled? */
		if (cpuidle_state_table[idle_state].enter == NULL)
			continue;

		drv->states[drv->state_count] =	/* structure copy */
			cpuidle_state_table[idle_state];

		drv->state_count += 1;
	}

	return 0;
}

/* pseries_idle_devices_uninit(void)
 * unregister cpuidle devices and de-allocate memory
 */
static void pseries_idle_devices_uninit(void)
{
	int i;
	struct cpuidle_device *dev;

	for_each_possible_cpu(i) {
		dev = per_cpu_ptr(pseries_cpuidle_devices, i);
		cpuidle_unregister_device(dev);
	}

	free_percpu(pseries_cpuidle_devices);
	return;
}

/* pseries_idle_devices_init()
 * allocate, initialize and register cpuidle device
 */
static int pseries_idle_devices_init(void)
{
	int i;
	struct cpuidle_driver *drv = &pseries_idle_driver;
	struct cpuidle_device *dev;

	pseries_cpuidle_devices = alloc_percpu(struct cpuidle_device);
	if (pseries_cpuidle_devices == NULL)
		return -ENOMEM;

	for_each_possible_cpu(i) {
		dev = per_cpu_ptr(pseries_cpuidle_devices, i);
		dev->state_count = drv->state_count;
		dev->cpu = i;
		if (cpuidle_register_device(dev)) {
			printk(KERN_DEBUG \
				"cpuidle_register_device %d failed!\n", i);
			return -EIO;
		}
	}

	return 0;
}

/*
 * pseries_idle_probe()
 * Choose state table for shared versus dedicated partition
 */
static int pseries_idle_probe(void)
{

	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
		return -ENODEV;

319 320 321
	if (cpuidle_disable != IDLE_NO_OVERRIDE)
		return -ENODEV;

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
	if (max_idle_state == 0) {
		printk(KERN_DEBUG "pseries processor idle disabled.\n");
		return -EPERM;
	}

	if (get_lppaca()->shared_proc)
		cpuidle_state_table = shared_states;
	else
		cpuidle_state_table = dedicated_states;

	return 0;
}

static int __init pseries_processor_idle_init(void)
{
	int retval;

	retval = pseries_idle_probe();
	if (retval)
		return retval;

	pseries_cpuidle_driver_init();
	retval = cpuidle_register_driver(&pseries_idle_driver);
	if (retval) {
		printk(KERN_DEBUG "Registration of pseries driver failed.\n");
		return retval;
	}

	retval = pseries_idle_devices_init();
	if (retval) {
		pseries_idle_devices_uninit();
		cpuidle_unregister_driver(&pseries_idle_driver);
		return retval;
	}

357
	register_cpu_notifier(&setup_hotplug_notifier);
358 359 360 361 362 363 364 365
	printk(KERN_DEBUG "pseries_idle_driver registered\n");

	return 0;
}

static void __exit pseries_processor_idle_exit(void)
{

366
	unregister_cpu_notifier(&setup_hotplug_notifier);
367 368 369 370 371 372 373 374 375 376 377 378
	pseries_idle_devices_uninit();
	cpuidle_unregister_driver(&pseries_idle_driver);

	return;
}

module_init(pseries_processor_idle_init);
module_exit(pseries_processor_idle_exit);

MODULE_AUTHOR("Deepthi Dharwar <deepthi@linux.vnet.ibm.com>");
MODULE_DESCRIPTION("Cpuidle driver for POWER");
MODULE_LICENSE("GPL");