summaryrefslogtreecommitdiff
path: root/drivers/cpuidle/cpuidle-pseries.c
blob: a7d33f3ee01e71f2da37f3e977368e2b2ed26663 (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
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
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
// SPDX-License-Identifier: GPL-2.0
/*
 *  cpuidle-pseries - 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>
#include <linux/notifier.h>

#include <asm/paca.h>
#include <asm/reg.h>
#include <asm/machdep.h>
#include <asm/firmware.h>
#include <asm/runlatch.h>
#include <asm/idle.h>
#include <asm/plpar_wrappers.h>
#include <asm/rtas.h>

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

static int max_idle_state __read_mostly;
static struct cpuidle_state *cpuidle_state_table __read_mostly;
static u64 snooze_timeout __read_mostly;
static bool snooze_timeout_en __read_mostly;

static __cpuidle
int snooze_loop(struct cpuidle_device *dev, struct cpuidle_driver *drv,
		int index)
{
	u64 snooze_exit_time;

	set_thread_flag(TIF_POLLING_NRFLAG);

	pseries_idle_prolog();
	raw_local_irq_enable();
	snooze_exit_time = get_tb() + snooze_timeout;
	dev->poll_time_limit = false;

	while (!need_resched()) {
		HMT_low();
		HMT_very_low();
		if (likely(snooze_timeout_en) && get_tb() > snooze_exit_time) {
			/*
			 * Task has not woken up but we are exiting the polling
			 * loop anyway. Require a barrier after polling is
			 * cleared to order subsequent test of need_resched().
			 */
			dev->poll_time_limit = true;
			clear_thread_flag(TIF_POLLING_NRFLAG);
			smp_mb();
			break;
		}
	}

	HMT_medium();
	clear_thread_flag(TIF_POLLING_NRFLAG);

	raw_local_irq_disable();

	pseries_idle_epilog();

	return index;
}

static __cpuidle void check_and_cede_processor(void)
{
	/*
	 * Ensure our interrupt state is properly tracked,
	 * also checks if no interrupt has occurred while we
	 * were soft-disabled
	 */
	if (prep_irq_for_idle()) {
		cede_processor();
#ifdef CONFIG_TRACE_IRQFLAGS
		/* Ensure that H_CEDE returns with IRQs on */
		if (WARN_ON(!(mfmsr() & MSR_EE)))
			__hard_irq_enable();
#endif
	}
}

/*
 * XCEDE: Extended CEDE states discovered through the
 *        "ibm,get-systems-parameter" RTAS call with the token
 *        CEDE_LATENCY_TOKEN
 */

/*
 * Section 7.3.16 System Parameters Option of PAPR version 2.8.1 has a
 * table with all the parameters to ibm,get-system-parameters.
 * CEDE_LATENCY_TOKEN corresponds to the token value for Cede Latency
 * Settings Information.
 */
#define CEDE_LATENCY_TOKEN	45

/*
 * If the platform supports the cede latency settings information system
 * parameter it must provide the following information in the NULL terminated
 * parameter string:
 *
 * a. The first byte is the length “N” of each cede latency setting record minus
 *    one (zero indicates a length of 1 byte).
 *
 * b. For each supported cede latency setting a cede latency setting record
 *    consisting of the first “N” bytes as per the following table.
 *
 *    -----------------------------
 *    | Field           | Field   |
 *    | Name            | Length  |
 *    -----------------------------
 *    | Cede Latency    | 1 Byte  |
 *    | Specifier Value |         |
 *    -----------------------------
 *    | Maximum wakeup  |         |
 *    | latency in      | 8 Bytes |
 *    | tb-ticks        |         |
 *    -----------------------------
 *    | Responsive to   |         |
 *    | external        | 1 Byte  |
 *    | interrupts      |         |
 *    -----------------------------
 *
 * This version has cede latency record size = 10.
 *
 * The structure xcede_latency_payload represents a) and b) with
 * xcede_latency_record representing the table in b).
 *
 * xcede_latency_parameter is what gets returned by
 * ibm,get-systems-parameter RTAS call when made with
 * CEDE_LATENCY_TOKEN.
 *
 * These structures are only used to represent the data obtained by the RTAS
 * call. The data is in big-endian.
 */
struct xcede_latency_record {
	u8	hint;
	__be64	latency_ticks;
	u8	wake_on_irqs;
} __packed;

// Make space for 16 records, which "should be enough".
struct xcede_latency_payload {
	u8     record_size;
	struct xcede_latency_record records[16];
} __packed;

struct xcede_latency_parameter {
	__be16  payload_size;
	struct xcede_latency_payload payload;
	u8 null_char;
} __packed;

static unsigned int nr_xcede_records;
static struct xcede_latency_parameter xcede_latency_parameter __initdata;

static int __init parse_cede_parameters(void)
{
	struct xcede_latency_payload *payload;
	u32 total_xcede_records_size;
	u8 xcede_record_size;
	u16 payload_size;
	int ret, i;

	ret = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
			NULL, CEDE_LATENCY_TOKEN, __pa(&xcede_latency_parameter),
			sizeof(xcede_latency_parameter));
	if (ret) {
		pr_err("xcede: Error parsing CEDE_LATENCY_TOKEN\n");
		return ret;
	}

	payload_size = be16_to_cpu(xcede_latency_parameter.payload_size);
	payload = &xcede_latency_parameter.payload;

	xcede_record_size = payload->record_size + 1;

	if (xcede_record_size != sizeof(struct xcede_latency_record)) {
		pr_err("xcede: Expected record-size %lu. Observed size %u.\n",
		       sizeof(struct xcede_latency_record), xcede_record_size);
		return -EINVAL;
	}

	pr_info("xcede: xcede_record_size = %d\n", xcede_record_size);

	/*
	 * Since the payload_size includes the last NULL byte and the
	 * xcede_record_size, the remaining bytes correspond to array of all
	 * cede_latency settings.
	 */
	total_xcede_records_size = payload_size - 2;
	nr_xcede_records = total_xcede_records_size / xcede_record_size;

	for (i = 0; i < nr_xcede_records; i++) {
		struct xcede_latency_record *record = &payload->records[i];
		u64 latency_ticks = be64_to_cpu(record->latency_ticks);
		u8 wake_on_irqs = record->wake_on_irqs;
		u8 hint = record->hint;

		pr_info("xcede: Record %d : hint = %u, latency = 0x%llx tb ticks, Wake-on-irq = %u\n",
			i, hint, latency_ticks, wake_on_irqs);
	}

	return 0;
}

#define NR_DEDICATED_STATES	2 /* snooze, CEDE */
static u8 cede_latency_hint[NR_DEDICATED_STATES];

static __cpuidle
int dedicated_cede_loop(struct cpuidle_device *dev, struct cpuidle_driver *drv,
			int index)
{
	u8 old_latency_hint;

	pseries_idle_prolog();
	get_lppaca()->donate_dedicated_cpu = 1;
	old_latency_hint = get_lppaca()->cede_latency_hint;
	get_lppaca()->cede_latency_hint = cede_latency_hint[index];

	HMT_medium();
	check_and_cede_processor();

	raw_local_irq_disable();
	get_lppaca()->donate_dedicated_cpu = 0;
	get_lppaca()->cede_latency_hint = old_latency_hint;

	pseries_idle_epilog();

	return index;
}

static __cpuidle
int shared_cede_loop(struct cpuidle_device *dev, struct cpuidle_driver *drv,
		     int index)
{

	pseries_idle_prolog();

	/*
	 * 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.
	 */
	check_and_cede_processor();

	raw_local_irq_disable();
	pseries_idle_epilog();

	return index;
}

/*
 * States for dedicated partition case.
 */
static struct cpuidle_state dedicated_states[NR_DEDICATED_STATES] = {
	{ /* Snooze */
		.name = "snooze",
		.desc = "snooze",
		.exit_latency = 0,
		.target_residency = 0,
		.enter = &snooze_loop,
		.flags = CPUIDLE_FLAG_POLLING },
	{ /* CEDE */
		.name = "CEDE",
		.desc = "CEDE",
		.exit_latency = 10,
		.target_residency = 100,
		.enter = &dedicated_cede_loop },
};

/*
 * States for shared partition case.
 */
static struct cpuidle_state shared_states[] = {
	{ /* Snooze */
		.name = "snooze",
		.desc = "snooze",
		.exit_latency = 0,
		.target_residency = 0,
		.enter = &snooze_loop,
		.flags = CPUIDLE_FLAG_POLLING },
	{ /* Shared Cede */
		.name = "Shared Cede",
		.desc = "Shared Cede",
		.exit_latency = 10,
		.target_residency = 100,
		.enter = &shared_cede_loop },
};

static int pseries_cpuidle_cpu_online(unsigned int cpu)
{
	struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);

	if (dev && cpuidle_get_driver()) {
		cpuidle_pause_and_lock();
		cpuidle_enable_device(dev);
		cpuidle_resume_and_unlock();
	}
	return 0;
}

static int pseries_cpuidle_cpu_dead(unsigned int cpu)
{
	struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);

	if (dev && cpuidle_get_driver()) {
		cpuidle_pause_and_lock();
		cpuidle_disable_device(dev);
		cpuidle_resume_and_unlock();
	}
	return 0;
}

/*
 * 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; ++idle_state) {
		/* 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;
}

static void __init fixup_cede0_latency(void)
{
	struct xcede_latency_payload *payload;
	u64 min_xcede_latency_us = UINT_MAX;
	int i;

	if (parse_cede_parameters())
		return;

	pr_info("cpuidle: Skipping the %d Extended CEDE idle states\n",
		nr_xcede_records);

	payload = &xcede_latency_parameter.payload;

	/*
	 * The CEDE idle state maps to CEDE(0). While the hypervisor
	 * does not advertise CEDE(0) exit latency values, it does
	 * advertise the latency values of the extended CEDE states.
	 * We use the lowest advertised exit latency value as a proxy
	 * for the exit latency of CEDE(0).
	 */
	for (i = 0; i < nr_xcede_records; i++) {
		struct xcede_latency_record *record = &payload->records[i];
		u8 hint = record->hint;
		u64 latency_tb = be64_to_cpu(record->latency_ticks);
		u64 latency_us = DIV_ROUND_UP_ULL(tb_to_ns(latency_tb), NSEC_PER_USEC);

		/*
		 * We expect the exit latency of an extended CEDE
		 * state to be non-zero, it to since it takes at least
		 * a few nanoseconds to wakeup the idle CPU and
		 * dispatch the virtual processor into the Linux
		 * Guest.
		 *
		 * So we consider only non-zero value for performing
		 * the fixup of CEDE(0) latency.
		 */
		if (latency_us == 0) {
			pr_warn("cpuidle: Skipping xcede record %d [hint=%d]. Exit latency = 0us\n",
				i, hint);
			continue;
		}

		if (latency_us < min_xcede_latency_us)
			min_xcede_latency_us = latency_us;
	}

	if (min_xcede_latency_us != UINT_MAX) {
		dedicated_states[1].exit_latency = min_xcede_latency_us;
		dedicated_states[1].target_residency = 10 * (min_xcede_latency_us);
		pr_info("cpuidle: Fixed up CEDE exit latency to %llu us\n",
			min_xcede_latency_us);
	}

}

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

	if (cpuidle_disable != IDLE_NO_OVERRIDE)
		return -ENODEV;

	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
		/*
		 * Use local_paca instead of get_lppaca() since
		 * preemption is not disabled, and it is not required in
		 * fact, since lppaca_ptr does not need to be the value
		 * associated to the current CPU, it can be from any CPU.
		 */
		if (lppaca_shared_proc(local_paca->lppaca_ptr)) {
			cpuidle_state_table = shared_states;
			max_idle_state = ARRAY_SIZE(shared_states);
		} else {
			/*
			 * Use firmware provided latency values
			 * starting with POWER10 platforms. In the
			 * case that we are running on a POWER10
			 * platform but in an earlier compat mode, we
			 * can still use the firmware provided values.
			 *
			 * However, on platforms prior to POWER10, we
			 * cannot rely on the accuracy of the firmware
			 * provided latency values. On such platforms,
			 * go with the conservative default estimate
			 * of 10us.
			 */
			if (cpu_has_feature(CPU_FTR_ARCH_31) || pvr_version_is(PVR_POWER10))
				fixup_cede0_latency();
			cpuidle_state_table = dedicated_states;
			max_idle_state = NR_DEDICATED_STATES;
		}
	} else
		return -ENODEV;

	if (max_idle_state > 1) {
		snooze_timeout_en = true;
		snooze_timeout = cpuidle_state_table[1].target_residency *
				 tb_ticks_per_usec;
	}
	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(&pseries_idle_driver, NULL);
	if (retval) {
		printk(KERN_DEBUG "Registration of pseries driver failed.\n");
		return retval;
	}

	retval = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
					   "cpuidle/pseries:online",
					   pseries_cpuidle_cpu_online, NULL);
	WARN_ON(retval < 0);
	retval = cpuhp_setup_state_nocalls(CPUHP_CPUIDLE_DEAD,
					   "cpuidle/pseries:DEAD", NULL,
					   pseries_cpuidle_cpu_dead);
	WARN_ON(retval < 0);
	printk(KERN_DEBUG "pseries_idle_driver registered\n");
	return 0;
}

device_initcall(pseries_processor_idle_init);