summaryrefslogtreecommitdiffstats
path: root/arch/arm/kernel/smp.c
blob: 39c74a2c3df9c7370fe2ca9cf2b67ea6dd8985fd (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
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
/*
 *  linux/arch/arm/kernel/smp.c
 *
 *  Copyright (C) 2002 ARM Limited, All Rights Reserved.
 *
 * 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.
 */
#include <linux/module.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/cache.h>
#include <linux/profile.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/cpu.h>
#include <linux/seq_file.h>
#include <linux/irq.h>
#include <linux/percpu.h>
#include <linux/clockchips.h>
#include <linux/completion.h>
#include <linux/cpufreq.h>
#include <linux/irq_work.h>

#include <linux/atomic.h>
#include <asm/smp.h>
#include <asm/cacheflush.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/exception.h>
#include <asm/idmap.h>
#include <asm/topology.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/processor.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
#include <asm/ptrace.h>
#include <asm/smp_plat.h>
#include <asm/virt.h>
#include <asm/mach/arch.h>
#include <asm/mpu.h>

#define CREATE_TRACE_POINTS
#include <trace/events/ipi.h>

/*
 * as from 2.5, kernels no longer have an init_tasks structure
 * so we need some other way of telling a new secondary core
 * where to place its SVC stack
 */
struct secondary_data secondary_data;

/*
 * control for which core is the next to come out of the secondary
 * boot "holding pen"
 */
volatile int pen_release = -1;

enum ipi_msg_type {
	IPI_WAKEUP,
	IPI_TIMER,
	IPI_RESCHEDULE,
	IPI_CALL_FUNC,
	IPI_CALL_FUNC_SINGLE,
	IPI_CPU_STOP,
	IPI_IRQ_WORK,
	IPI_COMPLETION,
};

static DECLARE_COMPLETION(cpu_running);

static struct smp_operations smp_ops;

void __init smp_set_ops(struct smp_operations *ops)
{
	if (ops)
		smp_ops = *ops;
};

static unsigned long get_arch_pgd(pgd_t *pgd)
{
	phys_addr_t pgdir = virt_to_idmap(pgd);
	BUG_ON(pgdir & ARCH_PGD_MASK);
	return pgdir >> ARCH_PGD_SHIFT;
}

int __cpu_up(unsigned int cpu, struct task_struct *idle)
{
	int ret;

	if (!smp_ops.smp_boot_secondary)
		return -ENOSYS;

	/*
	 * We need to tell the secondary core where to find
	 * its stack and the page tables.
	 */
	secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
#ifdef CONFIG_ARM_MPU
	secondary_data.mpu_rgn_szr = mpu_rgn_info.rgns[MPU_RAM_REGION].drsr;
#endif

#ifdef CONFIG_MMU
	secondary_data.pgdir = get_arch_pgd(idmap_pgd);
	secondary_data.swapper_pg_dir = get_arch_pgd(swapper_pg_dir);
#endif
	sync_cache_w(&secondary_data);

	/*
	 * Now bring the CPU into our world.
	 */
	ret = smp_ops.smp_boot_secondary(cpu, idle);
	if (ret == 0) {
		/*
		 * CPU was successfully started, wait for it
		 * to come online or time out.
		 */
		wait_for_completion_timeout(&cpu_running,
						 msecs_to_jiffies(1000));

		if (!cpu_online(cpu)) {
			pr_crit("CPU%u: failed to come online\n", cpu);
			ret = -EIO;
		}
	} else {
		pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
	}


	memset(&secondary_data, 0, sizeof(secondary_data));
	return ret;
}

/* platform specific SMP operations */
void __init smp_init_cpus(void)
{
	if (smp_ops.smp_init_cpus)
		smp_ops.smp_init_cpus();
}

int platform_can_cpu_hotplug(void)
{
#ifdef CONFIG_HOTPLUG_CPU
	if (smp_ops.cpu_kill)
		return 1;
#endif

	return 0;
}

#ifdef CONFIG_HOTPLUG_CPU
static int platform_cpu_kill(unsigned int cpu)
{
	if (smp_ops.cpu_kill)
		return smp_ops.cpu_kill(cpu);
	return 1;
}

static int platform_cpu_disable(unsigned int cpu)
{
	if (smp_ops.cpu_disable)
		return smp_ops.cpu_disable(cpu);

	/*
	 * By default, allow disabling all CPUs except the first one,
	 * since this is special on a lot of platforms, e.g. because
	 * of clock tick interrupts.
	 */
	return cpu == 0 ? -EPERM : 0;
}
/*
 * __cpu_disable runs on the processor to be shutdown.
 */
int __cpu_disable(void)
{
	unsigned int cpu = smp_processor_id();
	int ret;

	ret = platform_cpu_disable(cpu);
	if (ret)
		return ret;

	/*
	 * Take this CPU offline.  Once we clear this, we can't return,
	 * and we must not schedule until we're ready to give up the cpu.
	 */
	set_cpu_online(cpu, false);

	/*
	 * OK - migrate IRQs away from this CPU
	 */
	migrate_irqs();

	/*
	 * Flush user cache and TLB mappings, and then remove this CPU
	 * from the vm mask set of all processes.
	 *
	 * Caches are flushed to the Level of Unification Inner Shareable
	 * to write-back dirty lines to unified caches shared by all CPUs.
	 */
	flush_cache_louis();
	local_flush_tlb_all();

	clear_tasks_mm_cpumask(cpu);

	return 0;
}

static DECLARE_COMPLETION(cpu_died);

/*
 * called on the thread which is asking for a CPU to be shutdown -
 * waits until shutdown has completed, or it is timed out.
 */
void __cpu_die(unsigned int cpu)
{
	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
		pr_err("CPU%u: cpu didn't die\n", cpu);
		return;
	}
	printk(KERN_NOTICE "CPU%u: shutdown\n", cpu);

	/*
	 * platform_cpu_kill() is generally expected to do the powering off
	 * and/or cutting of clocks to the dying CPU.  Optionally, this may
	 * be done by the CPU which is dying in preference to supporting
	 * this call, but that means there is _no_ synchronisation between
	 * the requesting CPU and the dying CPU actually losing power.
	 */
	if (!platform_cpu_kill(cpu))
		printk("CPU%u: unable to kill\n", cpu);
}

/*
 * Called from the idle thread for the CPU which has been shutdown.
 *
 * Note that we disable IRQs here, but do not re-enable them
 * before returning to the caller. This is also the behaviour
 * of the other hotplug-cpu capable cores, so presumably coming
 * out of idle fixes this.
 */
void __ref cpu_die(void)
{
	unsigned int cpu = smp_processor_id();

	idle_task_exit();

	local_irq_disable();

	/*
	 * Flush the data out of the L1 cache for this CPU.  This must be
	 * before the completion to ensure that data is safely written out
	 * before platform_cpu_kill() gets called - which may disable
	 * *this* CPU and power down its cache.
	 */
	flush_cache_louis();

	/*
	 * Tell __cpu_die() that this CPU is now safe to dispose of.  Once
	 * this returns, power and/or clocks can be removed at any point
	 * from this CPU and its cache by platform_cpu_kill().
	 */
	complete(&cpu_died);

	/*
	 * Ensure that the cache lines associated with that completion are
	 * written out.  This covers the case where _this_ CPU is doing the
	 * powering down, to ensure that the completion is visible to the
	 * CPU waiting for this one.
	 */
	flush_cache_louis();

	/*
	 * The actual CPU shutdown procedure is at least platform (if not
	 * CPU) specific.  This may remove power, or it may simply spin.
	 *
	 * Platforms are generally expected *NOT* to return from this call,
	 * although there are some which do because they have no way to
	 * power down the CPU.  These platforms are the _only_ reason we
	 * have a return path which uses the fragment of assembly below.
	 *
	 * The return path should not be used for platforms which can
	 * power off the CPU.
	 */
	if (smp_ops.cpu_die)
		smp_ops.cpu_die(cpu);

	pr_warn("CPU%u: smp_ops.cpu_die() returned, trying to resuscitate\n",
		cpu);

	/*
	 * Do not return to the idle loop - jump back to the secondary
	 * cpu initialisation.  There's some initialisation which needs
	 * to be repeated to undo the effects of taking the CPU offline.
	 */
	__asm__("mov	sp, %0\n"
	"	mov	fp, #0\n"
	"	b	secondary_start_kernel"
		:
		: "r" (task_stack_page(current) + THREAD_SIZE - 8));
}
#endif /* CONFIG_HOTPLUG_CPU */

/*
 * Called by both boot and secondaries to move global data into
 * per-processor storage.
 */
static void smp_store_cpu_info(unsigned int cpuid)
{
	struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid);

	cpu_info->loops_per_jiffy = loops_per_jiffy;
	cpu_info->cpuid = read_cpuid_id();

	store_cpu_topology(cpuid);
}

/*
 * This is the secondary CPU boot entry.  We're using this CPUs
 * idle thread stack, but a set of temporary page tables.
 */
asmlinkage void secondary_start_kernel(void)
{
	struct mm_struct *mm = &init_mm;
	unsigned int cpu;

	/*
	 * The identity mapping is uncached (strongly ordered), so
	 * switch away from it before attempting any exclusive accesses.
	 */
	cpu_switch_mm(mm->pgd, mm);
	local_flush_bp_all();
	enter_lazy_tlb(mm, current);
	local_flush_tlb_all();

	/*
	 * All kernel threads share the same mm context; grab a
	 * reference and switch to it.
	 */
	cpu = smp_processor_id();
	atomic_inc(&mm->mm_count);
	current->active_mm = mm;
	cpumask_set_cpu(cpu, mm_cpumask(mm));

	cpu_init();

	printk("CPU%u: Booted secondary processor\n", cpu);

	preempt_disable();
	trace_hardirqs_off();

	/*
	 * Give the platform a chance to do its own initialisation.
	 */
	if (smp_ops.smp_secondary_init)
		smp_ops.smp_secondary_init(cpu);

	notify_cpu_starting(cpu);

	calibrate_delay();

	smp_store_cpu_info(cpu);

	/*
	 * OK, now it's safe to let the boot CPU continue.  Wait for
	 * the CPU migration code to notice that the CPU is online
	 * before we continue - which happens after __cpu_up returns.
	 */
	set_cpu_online(cpu, true);
	complete(&cpu_running);

	local_irq_enable();
	local_fiq_enable();

	/*
	 * OK, it's off to the idle thread for us
	 */
	cpu_startup_entry(CPUHP_ONLINE);
}

void __init smp_cpus_done(unsigned int max_cpus)
{
	printk(KERN_INFO "SMP: Total of %d processors activated.\n",
	       num_online_cpus());

	hyp_mode_check();
}

void __init smp_prepare_boot_cpu(void)
{
	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
}

void __init smp_prepare_cpus(unsigned int max_cpus)
{
	unsigned int ncores = num_possible_cpus();

	init_cpu_topology();

	smp_store_cpu_info(smp_processor_id());

	/*
	 * are we trying to boot more cores than exist?
	 */
	if (max_cpus > ncores)
		max_cpus = ncores;
	if (ncores > 1 && max_cpus) {
		/*
		 * Initialise the present map, which describes the set of CPUs
		 * actually populated at the present time. A platform should
		 * re-initialize the map in the platforms smp_prepare_cpus()
		 * if present != possible (e.g. physical hotplug).
		 */
		init_cpu_present(cpu_possible_mask);

		/*
		 * Initialise the SCU if there are more than one CPU
		 * and let them know where to start.
		 */
		if (smp_ops.smp_prepare_cpus)
			smp_ops.smp_prepare_cpus(max_cpus);
	}
}

static void (*__smp_cross_call)(const struct cpumask *, unsigned int);

void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
{
	if (!__smp_cross_call)
		__smp_cross_call = fn;
}

static const char *ipi_types[NR_IPI] __tracepoint_string = {
#define S(x,s)	[x] = s
	S(IPI_WAKEUP, "CPU wakeup interrupts"),
	S(IPI_TIMER, "Timer broadcast interrupts"),
	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
	S(IPI_CALL_FUNC, "Function call interrupts"),
	S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
	S(IPI_CPU_STOP, "CPU stop interrupts"),
	S(IPI_IRQ_WORK, "IRQ work interrupts"),
	S(IPI_COMPLETION, "completion interrupts"),
};

static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
{
	trace_ipi_raise(target, ipi_types[ipinr]);
	__smp_cross_call(target, ipinr);
}

void show_ipi_list(struct seq_file *p, int prec)
{
	unsigned int cpu, i;

	for (i = 0; i < NR_IPI; i++) {
		seq_printf(p, "%*s%u: ", prec - 1, "IPI", i);

		for_each_online_cpu(cpu)
			seq_printf(p, "%10u ",
				   __get_irq_stat(cpu, ipi_irqs[i]));

		seq_printf(p, " %s\n", ipi_types[i]);
	}
}

u64 smp_irq_stat_cpu(unsigned int cpu)
{
	u64 sum = 0;
	int i;

	for (i = 0; i < NR_IPI; i++)
		sum += __get_irq_stat(cpu, ipi_irqs[i]);

	return sum;
}

void arch_send_call_function_ipi_mask(const struct cpumask *mask)
{
	smp_cross_call(mask, IPI_CALL_FUNC);
}

void arch_send_wakeup_ipi_mask(const struct cpumask *mask)
{
	smp_cross_call(mask, IPI_WAKEUP);
}

void arch_send_call_function_single_ipi(int cpu)
{
	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
}

#ifdef CONFIG_IRQ_WORK
void arch_irq_work_raise(void)
{
	if (is_smp())
		smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
}
#endif

#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
void tick_broadcast(const struct cpumask *mask)
{
	smp_cross_call(mask, IPI_TIMER);
}
#endif

static DEFINE_RAW_SPINLOCK(stop_lock);

/*
 * ipi_cpu_stop - handle IPI from smp_send_stop()
 */
static void ipi_cpu_stop(unsigned int cpu)
{
	if (system_state == SYSTEM_BOOTING ||
	    system_state == SYSTEM_RUNNING) {
		raw_spin_lock(&stop_lock);
		printk(KERN_CRIT "CPU%u: stopping\n", cpu);
		dump_stack();
		raw_spin_unlock(&stop_lock);
	}

	set_cpu_online(cpu, false);

	local_fiq_disable();
	local_irq_disable();

	while (1)
		cpu_relax();
}

static DEFINE_PER_CPU(struct completion *, cpu_completion);

int register_ipi_completion(struct completion *completion, int cpu)
{
	per_cpu(cpu_completion, cpu) = completion;
	return IPI_COMPLETION;
}

static void ipi_complete(unsigned int cpu)
{
	complete(per_cpu(cpu_completion, cpu));
}

/*
 * Main handler for inter-processor interrupts
 */
asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs)
{
	handle_IPI(ipinr, regs);
}

void handle_IPI(int ipinr, struct pt_regs *regs)
{
	unsigned int cpu = smp_processor_id();
	struct pt_regs *old_regs = set_irq_regs(regs);

	if ((unsigned)ipinr < NR_IPI) {
		trace_ipi_entry(ipi_types[ipinr]);
		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
	}

	switch (ipinr) {
	case IPI_WAKEUP:
		break;

#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
	case IPI_TIMER:
		irq_enter();
		tick_receive_broadcast();
		irq_exit();
		break;
#endif

	case IPI_RESCHEDULE:
		scheduler_ipi();
		break;

	case IPI_CALL_FUNC:
		irq_enter();
		generic_smp_call_function_interrupt();
		irq_exit();
		break;

	case IPI_CALL_FUNC_SINGLE:
		irq_enter();
		generic_smp_call_function_single_interrupt();
		irq_exit();
		break;

	case IPI_CPU_STOP:
		irq_enter();
		ipi_cpu_stop(cpu);
		irq_exit();
		break;

#ifdef CONFIG_IRQ_WORK
	case IPI_IRQ_WORK:
		irq_enter();
		irq_work_run();
		irq_exit();
		break;
#endif

	case IPI_COMPLETION:
		irq_enter();
		ipi_complete(cpu);
		irq_exit();
		break;

	default:
		printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
		       cpu, ipinr);
		break;
	}

	if ((unsigned)ipinr < NR_IPI)
		trace_ipi_exit(ipi_types[ipinr]);
	set_irq_regs(old_regs);
}

void smp_send_reschedule(int cpu)
{
	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
}

void smp_send_stop(void)
{
	unsigned long timeout;
	struct cpumask mask;

	cpumask_copy(&mask, cpu_online_mask);
	cpumask_clear_cpu(smp_processor_id(), &mask);
	if (!cpumask_empty(&mask))
		smp_cross_call(&mask, IPI_CPU_STOP);

	/* Wait up to one second for other CPUs to stop */
	timeout = USEC_PER_SEC;
	while (num_online_cpus() > 1 && timeout--)
		udelay(1);

	if (num_online_cpus() > 1)
		pr_warn("SMP: failed to stop secondary CPUs\n");
}

/*
 * not supported here
 */
int setup_profiling_timer(unsigned int multiplier)
{
	return -EINVAL;
}

#ifdef CONFIG_CPU_FREQ

static DEFINE_PER_CPU(unsigned long, l_p_j_ref);
static DEFINE_PER_CPU(unsigned long, l_p_j_ref_freq);
static unsigned long global_l_p_j_ref;
static unsigned long global_l_p_j_ref_freq;

static int cpufreq_callback(struct notifier_block *nb,
					unsigned long val, void *data)
{
	struct cpufreq_freqs *freq = data;
	int cpu = freq->cpu;

	if (freq->flags & CPUFREQ_CONST_LOOPS)
		return NOTIFY_OK;

	if (!per_cpu(l_p_j_ref, cpu)) {
		per_cpu(l_p_j_ref, cpu) =
			per_cpu(cpu_data, cpu).loops_per_jiffy;
		per_cpu(l_p_j_ref_freq, cpu) = freq->old;
		if (!global_l_p_j_ref) {
			global_l_p_j_ref = loops_per_jiffy;
			global_l_p_j_ref_freq = freq->old;
		}
	}

	if ((val == CPUFREQ_PRECHANGE  && freq->old < freq->new) ||
	    (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
		loops_per_jiffy = cpufreq_scale(global_l_p_j_ref,
						global_l_p_j_ref_freq,
						freq->new);
		per_cpu(cpu_data, cpu).loops_per_jiffy =
			cpufreq_scale(per_cpu(l_p_j_ref, cpu),
					per_cpu(l_p_j_ref_freq, cpu),
					freq->new);
	}
	return NOTIFY_OK;
}

static struct notifier_block cpufreq_notifier = {
	.notifier_call  = cpufreq_callback,
};

static int __init register_cpufreq_notifier(void)
{
	return cpufreq_register_notifier(&cpufreq_notifier,
						CPUFREQ_TRANSITION_NOTIFIER);
}
core_initcall(register_cpufreq_notifier);

#endif