summaryrefslogtreecommitdiffstats
path: root/drivers/firmware/psci_checker.c
blob: 44bdb78f837b4d89f2aaef6e7d0764b8c2783d87 (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
484
485
486
487
488
489
490
/*
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * Copyright (C) 2016 ARM Limited
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/atomic.h>
#include <linux/completion.h>
#include <linux/cpu.h>
#include <linux/cpuidle.h>
#include <linux/cpu_pm.h>
#include <linux/kernel.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/preempt.h>
#include <linux/psci.h>
#include <linux/slab.h>
#include <linux/tick.h>
#include <linux/topology.h>

#include <asm/cpuidle.h>

#include <uapi/linux/psci.h>

#define NUM_SUSPEND_CYCLE (10)

static unsigned int nb_available_cpus;
static int tos_resident_cpu = -1;

static atomic_t nb_active_threads;
static struct completion suspend_threads_started =
	COMPLETION_INITIALIZER(suspend_threads_started);
static struct completion suspend_threads_done =
	COMPLETION_INITIALIZER(suspend_threads_done);

/*
 * We assume that PSCI operations are used if they are available. This is not
 * necessarily true on arm64, since the decision is based on the
 * "enable-method" property of each CPU in the DT, but given that there is no
 * arch-specific way to check this, we assume that the DT is sensible.
 */
static int psci_ops_check(void)
{
	int migrate_type = -1;
	int cpu;

	if (!(psci_ops.cpu_off && psci_ops.cpu_on && psci_ops.cpu_suspend)) {
		pr_warn("Missing PSCI operations, aborting tests\n");
		return -EOPNOTSUPP;
	}

	if (psci_ops.migrate_info_type)
		migrate_type = psci_ops.migrate_info_type();

	if (migrate_type == PSCI_0_2_TOS_UP_MIGRATE ||
	    migrate_type == PSCI_0_2_TOS_UP_NO_MIGRATE) {
		/* There is a UP Trusted OS, find on which core it resides. */
		for_each_online_cpu(cpu)
			if (psci_tos_resident_on(cpu)) {
				tos_resident_cpu = cpu;
				break;
			}
		if (tos_resident_cpu == -1)
			pr_warn("UP Trusted OS resides on no online CPU\n");
	}

	return 0;
}

static int find_clusters(const struct cpumask *cpus,
			 const struct cpumask **clusters)
{
	unsigned int nb = 0;
	cpumask_var_t tmp;

	if (!alloc_cpumask_var(&tmp, GFP_KERNEL))
		return -ENOMEM;
	cpumask_copy(tmp, cpus);

	while (!cpumask_empty(tmp)) {
		const struct cpumask *cluster =
			topology_core_cpumask(cpumask_any(tmp));

		clusters[nb++] = cluster;
		cpumask_andnot(tmp, tmp, cluster);
	}

	free_cpumask_var(tmp);
	return nb;
}

/*
 * offlined_cpus is a temporary array but passing it as an argument avoids
 * multiple allocations.
 */
static unsigned int down_and_up_cpus(const struct cpumask *cpus,
				     struct cpumask *offlined_cpus)
{
	int cpu;
	int err = 0;

	cpumask_clear(offlined_cpus);

	/* Try to power down all CPUs in the mask. */
	for_each_cpu(cpu, cpus) {
		int ret = cpu_down(cpu);

		/*
		 * cpu_down() checks the number of online CPUs before the TOS
		 * resident CPU.
		 */
		if (cpumask_weight(offlined_cpus) + 1 == nb_available_cpus) {
			if (ret != -EBUSY) {
				pr_err("Unexpected return code %d while trying "
				       "to power down last online CPU %d\n",
				       ret, cpu);
				++err;
			}
		} else if (cpu == tos_resident_cpu) {
			if (ret != -EPERM) {
				pr_err("Unexpected return code %d while trying "
				       "to power down TOS resident CPU %d\n",
				       ret, cpu);
				++err;
			}
		} else if (ret != 0) {
			pr_err("Error occurred (%d) while trying "
			       "to power down CPU %d\n", ret, cpu);
			++err;
		}

		if (ret == 0)
			cpumask_set_cpu(cpu, offlined_cpus);
	}

	/* Try to power up all the CPUs that have been offlined. */
	for_each_cpu(cpu, offlined_cpus) {
		int ret = cpu_up(cpu);

		if (ret != 0) {
			pr_err("Error occurred (%d) while trying "
			       "to power up CPU %d\n", ret, cpu);
			++err;
		} else {
			cpumask_clear_cpu(cpu, offlined_cpus);
		}
	}

	/*
	 * Something went bad at some point and some CPUs could not be turned
	 * back on.
	 */
	WARN_ON(!cpumask_empty(offlined_cpus) ||
		num_online_cpus() != nb_available_cpus);

	return err;
}

static int hotplug_tests(void)
{
	int err;
	cpumask_var_t offlined_cpus;
	int i, nb_cluster;
	const struct cpumask **clusters;
	char *page_buf;

	err = -ENOMEM;
	if (!alloc_cpumask_var(&offlined_cpus, GFP_KERNEL))
		return err;
	/* We may have up to nb_available_cpus clusters. */
	clusters = kmalloc_array(nb_available_cpus, sizeof(*clusters),
				 GFP_KERNEL);
	if (!clusters)
		goto out_free_cpus;
	page_buf = (char *)__get_free_page(GFP_KERNEL);
	if (!page_buf)
		goto out_free_clusters;

	err = 0;
	nb_cluster = find_clusters(cpu_online_mask, clusters);

	/*
	 * Of course the last CPU cannot be powered down and cpu_down() should
	 * refuse doing that.
	 */
	pr_info("Trying to turn off and on again all CPUs\n");
	err += down_and_up_cpus(cpu_online_mask, offlined_cpus);

	/*
	 * Take down CPUs by cluster this time. When the last CPU is turned
	 * off, the cluster itself should shut down.
	 */
	for (i = 0; i < nb_cluster; ++i) {
		int cluster_id =
			topology_physical_package_id(cpumask_any(clusters[i]));
		ssize_t len = cpumap_print_to_pagebuf(true, page_buf,
						      clusters[i]);
		/* Remove trailing newline. */
		page_buf[len - 1] = '\0';
		pr_info("Trying to turn off and on again cluster %d "
			"(CPUs %s)\n", cluster_id, page_buf);
		err += down_and_up_cpus(clusters[i], offlined_cpus);
	}

	free_page((unsigned long)page_buf);
out_free_clusters:
	kfree(clusters);
out_free_cpus:
	free_cpumask_var(offlined_cpus);
	return err;
}

static void dummy_callback(unsigned long ignored) {}

static int suspend_cpu(int index, bool broadcast)
{
	int ret;

	arch_cpu_idle_enter();

	if (broadcast) {
		/*
		 * The local timer will be shut down, we need to enter tick
		 * broadcast.
		 */
		ret = tick_broadcast_enter();
		if (ret) {
			/*
			 * In the absence of hardware broadcast mechanism,
			 * this CPU might be used to broadcast wakeups, which
			 * may be why entering tick broadcast has failed.
			 * There is little the kernel can do to work around
			 * that, so enter WFI instead (idle state 0).
			 */
			cpu_do_idle();
			ret = 0;
			goto out_arch_exit;
		}
	}

	/*
	 * Replicate the common ARM cpuidle enter function
	 * (arm_enter_idle_state).
	 */
	ret = CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, index);

	if (broadcast)
		tick_broadcast_exit();

out_arch_exit:
	arch_cpu_idle_exit();

	return ret;
}

static int suspend_test_thread(void *arg)
{
	int cpu = (long)arg;
	int i, nb_suspend = 0, nb_shallow_sleep = 0, nb_err = 0;
	struct sched_param sched_priority = { .sched_priority = MAX_RT_PRIO-1 };
	struct cpuidle_device *dev;
	struct cpuidle_driver *drv;
	/* No need for an actual callback, we just want to wake up the CPU. */
	struct timer_list wakeup_timer =
		TIMER_INITIALIZER(dummy_callback, 0, 0);

	/* Wait for the main thread to give the start signal. */
	wait_for_completion(&suspend_threads_started);

	/* Set maximum priority to preempt all other threads on this CPU. */
	if (sched_setscheduler_nocheck(current, SCHED_FIFO, &sched_priority))
		pr_warn("Failed to set suspend thread scheduler on CPU %d\n",
			cpu);

	dev = this_cpu_read(cpuidle_devices);
	drv = cpuidle_get_cpu_driver(dev);

	pr_info("CPU %d entering suspend cycles, states 1 through %d\n",
		cpu, drv->state_count - 1);

	for (i = 0; i < NUM_SUSPEND_CYCLE; ++i) {
		int index;
		/*
		 * Test all possible states, except 0 (which is usually WFI and
		 * doesn't use PSCI).
		 */
		for (index = 1; index < drv->state_count; ++index) {
			struct cpuidle_state *state = &drv->states[index];
			bool broadcast = state->flags & CPUIDLE_FLAG_TIMER_STOP;
			int ret;

			/*
			 * Set the timer to wake this CPU up in some time (which
			 * should be largely sufficient for entering suspend).
			 * If the local tick is disabled when entering suspend,
			 * suspend_cpu() takes care of switching to a broadcast
			 * tick, so the timer will still wake us up.
			 */
			mod_timer(&wakeup_timer, jiffies +
				  usecs_to_jiffies(state->target_residency));

			/* IRQs must be disabled during suspend operations. */
			local_irq_disable();

			ret = suspend_cpu(index, broadcast);

			/*
			 * We have woken up. Re-enable IRQs to handle any
			 * pending interrupt, do not wait until the end of the
			 * loop.
			 */
			local_irq_enable();

			if (ret == index) {
				++nb_suspend;
			} else if (ret >= 0) {
				/* We did not enter the expected state. */
				++nb_shallow_sleep;
			} else {
				pr_err("Failed to suspend CPU %d: error %d "
				       "(requested state %d, cycle %d)\n",
				       cpu, ret, index, i);
				++nb_err;
			}
		}
	}

	/*
	 * Disable the timer to make sure that the timer will not trigger
	 * later.
	 */
	del_timer(&wakeup_timer);

	if (atomic_dec_return_relaxed(&nb_active_threads) == 0)
		complete(&suspend_threads_done);

	/* Give up on RT scheduling and wait for termination. */
	sched_priority.sched_priority = 0;
	if (sched_setscheduler_nocheck(current, SCHED_NORMAL, &sched_priority))
		pr_warn("Failed to set suspend thread scheduler on CPU %d\n",
			cpu);
	for (;;) {
		/* Needs to be set first to avoid missing a wakeup. */
		set_current_state(TASK_INTERRUPTIBLE);
		if (kthread_should_stop()) {
			__set_current_state(TASK_RUNNING);
			break;
		}
		schedule();
	}

	pr_info("CPU %d suspend test results: success %d, shallow states %d, errors %d\n",
		cpu, nb_suspend, nb_shallow_sleep, nb_err);

	return nb_err;
}

static int suspend_tests(void)
{
	int i, cpu, err = 0;
	struct task_struct **threads;
	int nb_threads = 0;

	threads = kmalloc_array(nb_available_cpus, sizeof(*threads),
				GFP_KERNEL);
	if (!threads)
		return -ENOMEM;

	/*
	 * Stop cpuidle to prevent the idle tasks from entering a deep sleep
	 * mode, as it might interfere with the suspend threads on other CPUs.
	 * This does not prevent the suspend threads from using cpuidle (only
	 * the idle tasks check this status). Take the idle lock so that
	 * the cpuidle driver and device look-up can be carried out safely.
	 */
	cpuidle_pause_and_lock();

	for_each_online_cpu(cpu) {
		struct task_struct *thread;
		/* Check that cpuidle is available on that CPU. */
		struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
		struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);

		if (!dev || !drv) {
			pr_warn("cpuidle not available on CPU %d, ignoring\n",
				cpu);
			continue;
		}

		thread = kthread_create_on_cpu(suspend_test_thread,
					       (void *)(long)cpu, cpu,
					       "psci_suspend_test");
		if (IS_ERR(thread))
			pr_err("Failed to create kthread on CPU %d\n", cpu);
		else
			threads[nb_threads++] = thread;
	}

	if (nb_threads < 1) {
		err = -ENODEV;
		goto out;
	}

	atomic_set(&nb_active_threads, nb_threads);

	/*
	 * Wake up the suspend threads. To avoid the main thread being preempted
	 * before all the threads have been unparked, the suspend threads will
	 * wait for the completion of suspend_threads_started.
	 */
	for (i = 0; i < nb_threads; ++i)
		wake_up_process(threads[i]);
	complete_all(&suspend_threads_started);

	wait_for_completion(&suspend_threads_done);


	/* Stop and destroy all threads, get return status. */
	for (i = 0; i < nb_threads; ++i)
		err += kthread_stop(threads[i]);
 out:
	cpuidle_resume_and_unlock();
	kfree(threads);
	return err;
}

static int __init psci_checker(void)
{
	int ret;

	/*
	 * Since we're in an initcall, we assume that all the CPUs that all
	 * CPUs that can be onlined have been onlined.
	 *
	 * The tests assume that hotplug is enabled but nobody else is using it,
	 * otherwise the results will be unpredictable. However, since there
	 * is no userspace yet in initcalls, that should be fine, as long as
	 * no torture test is running at the same time (see Kconfig).
	 */
	nb_available_cpus = num_online_cpus();

	/* Check PSCI operations are set up and working. */
	ret = psci_ops_check();
	if (ret)
		return ret;

	pr_info("PSCI checker started using %u CPUs\n", nb_available_cpus);

	pr_info("Starting hotplug tests\n");
	ret = hotplug_tests();
	if (ret == 0)
		pr_info("Hotplug tests passed OK\n");
	else if (ret > 0)
		pr_err("%d error(s) encountered in hotplug tests\n", ret);
	else {
		pr_err("Out of memory\n");
		return ret;
	}

	pr_info("Starting suspend tests (%d cycles per state)\n",
		NUM_SUSPEND_CYCLE);
	ret = suspend_tests();
	if (ret == 0)
		pr_info("Suspend tests passed OK\n");
	else if (ret > 0)
		pr_err("%d error(s) encountered in suspend tests\n", ret);
	else {
		switch (ret) {
		case -ENOMEM:
			pr_err("Out of memory\n");
			break;
		case -ENODEV:
			pr_warn("Could not start suspend tests on any CPU\n");
			break;
		}
	}

	pr_info("PSCI checker completed\n");
	return ret < 0 ? ret : 0;
}
late_initcall(psci_checker);
OpenPOWER on IntegriCloud