aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/smp.c
blob: cbdbb14be4b07b0eb31faefec1bfb06e572761c4 (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
/*
 * SMP support for ppc.
 *
 * Written by Cort Dougan (cort@cs.nmt.edu) borrowing a great
 * deal of code from the sparc and intel versions.
 *
 * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
 *
 * PowerPC-64 Support added by Dave Engebretsen, Peter Bergner, and
 * Mike Corrigan {engebret|bergner|mikec}@us.ibm.com
 *
 *      This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

#undef DEBUG

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/cache.h>
#include <linux/err.h>
#include <linux/sysdev.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/topology.h>

#include <asm/ptrace.h>
#include <asm/atomic.h>
#include <asm/irq.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/prom.h>
#include <asm/smp.h>
#include <asm/time.h>
#include <asm/machdep.h>
#include <asm/cputhreads.h>
#include <asm/cputable.h>
#include <asm/system.h>
#include <asm/mpic.h>
#include <asm/vdso_datapage.h>
#ifdef CONFIG_PPC64
#include <asm/paca.h>
#endif

#ifdef DEBUG
#include <asm/udbg.h>
#define DBG(fmt...) udbg_printf(fmt)
#else
#define DBG(fmt...)
#endif


/* Store all idle threads, this can be reused instead of creating
* a new thread. Also avoids complicated thread destroy functionality
* for idle threads.
*/
#ifdef CONFIG_HOTPLUG_CPU
/*
 * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is
 * removed after init for !CONFIG_HOTPLUG_CPU.
 */
static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
#define get_idle_for_cpu(x)      (per_cpu(idle_thread_array, x))
#define set_idle_for_cpu(x, p)   (per_cpu(idle_thread_array, x) = (p))
#else
static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
#define get_idle_for_cpu(x)      (idle_thread_array[(x)])
#define set_idle_for_cpu(x, p)   (idle_thread_array[(x)] = (p))
#endif

struct thread_info *secondary_ti;

DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);

EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);

/* SMP operations for this machine */
struct smp_ops_t *smp_ops;

/* Can't be static due to PowerMac hackery */
volatile unsigned int cpu_callin_map[NR_CPUS];

int smt_enabled_at_boot = 1;

static void (*crash_ipi_function_ptr)(struct pt_regs *) = NULL;

#ifdef CONFIG_PPC64
void __devinit smp_generic_kick_cpu(int nr)
{
	BUG_ON(nr < 0 || nr >= NR_CPUS);

	/*
	 * The processor is currently spinning, waiting for the
	 * cpu_start field to become non-zero After we set cpu_start,
	 * the processor will continue on to secondary_start
	 */
	paca[nr].cpu_start = 1;
	smp_mb();
}
#endif

void smp_message_recv(int msg)
{
	switch(msg) {
	case PPC_MSG_CALL_FUNCTION:
		generic_smp_call_function_interrupt();
		break;
	case PPC_MSG_RESCHEDULE:
		/* we notice need_resched on exit */
		break;
	case PPC_MSG_CALL_FUNC_SINGLE:
		generic_smp_call_function_single_interrupt();
		break;
	case PPC_MSG_DEBUGGER_BREAK:
		if (crash_ipi_function_ptr) {
			crash_ipi_function_ptr(get_irq_regs());
			break;
		}
#ifdef CONFIG_DEBUGGER
		debugger_ipi(get_irq_regs());
		break;
#endif /* CONFIG_DEBUGGER */
		/* FALLTHROUGH */
	default:
		printk("SMP %d: smp_message_recv(): unknown msg %d\n",
		       smp_processor_id(), msg);
		break;
	}
}

static irqreturn_t call_function_action(int irq, void *data)
{
	generic_smp_call_function_interrupt();
	return IRQ_HANDLED;
}

static irqreturn_t reschedule_action(int irq, void *data)
{
	/* we just need the return path side effect of checking need_resched */
	return IRQ_HANDLED;
}

static irqreturn_t call_function_single_action(int irq, void *data)
{
	generic_smp_call_function_single_interrupt();
	return IRQ_HANDLED;
}

static irqreturn_t debug_ipi_action(int irq, void *data)
{
	smp_message_recv(PPC_MSG_DEBUGGER_BREAK);
	return IRQ_HANDLED;
}

static irq_handler_t smp_ipi_action[] = {
	[PPC_MSG_CALL_FUNCTION] =  call_function_action,
	[PPC_MSG_RESCHEDULE] = reschedule_action,
	[PPC_MSG_CALL_FUNC_SINGLE] = call_function_single_action,
	[PPC_MSG_DEBUGGER_BREAK] = debug_ipi_action,
};

const char *smp_ipi_name[] = {
	[PPC_MSG_CALL_FUNCTION] =  "ipi call function",
	[PPC_MSG_RESCHEDULE] = "ipi reschedule",
	[PPC_MSG_CALL_FUNC_SINGLE] = "ipi call function single",
	[PPC_MSG_DEBUGGER_BREAK] = "ipi debugger",
};

/* optional function to request ipi, for controllers with >= 4 ipis */
int smp_request_message_ipi(int virq, int msg)
{
	int err;

	if (msg < 0 || msg > PPC_MSG_DEBUGGER_BREAK) {
		return -EINVAL;
	}
#if !defined(CONFIG_DEBUGGER) && !defined(CONFIG_KEXEC)
	if (msg == PPC_MSG_DEBUGGER_BREAK) {
		return 1;
	}
#endif
	err = request_irq(virq, smp_ipi_action[msg], IRQF_DISABLED|IRQF_PERCPU,
			  smp_ipi_name[msg], 0);
	WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n",
		virq, smp_ipi_name[msg], err);

	return err;
}

void smp_send_reschedule(int cpu)
{
	if (likely(smp_ops))
		smp_ops->message_pass(cpu, PPC_MSG_RESCHEDULE);
}

void arch_send_call_function_single_ipi(int cpu)
{
	smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNC_SINGLE);
}

void arch_send_call_function_ipi_mask(const struct cpumask *mask)
{
	unsigned int cpu;

	for_each_cpu(cpu, mask)
		smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNCTION);
}

#ifdef CONFIG_DEBUGGER
void smp_send_debugger_break(int cpu)
{
	if (likely(smp_ops))
		smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK);
}
#endif

#ifdef CONFIG_KEXEC
void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
{
	crash_ipi_function_ptr = crash_ipi_callback;
	if (crash_ipi_callback && smp_ops) {
		mb();
		smp_ops->message_pass(MSG_ALL_BUT_SELF, PPC_MSG_DEBUGGER_BREAK);
	}
}
#endif

static void stop_this_cpu(void *dummy)
{
	/* Remove this CPU */
	set_cpu_online(smp_processor_id(), false);

	local_irq_disable();
	while (1)
		;
}

void smp_send_stop(void)
{
	smp_call_function(stop_this_cpu, NULL, 0);
}

struct thread_info *current_set[NR_CPUS];

static void __devinit smp_store_cpu_info(int id)
{
	per_cpu(cpu_pvr, id) = mfspr(SPRN_PVR);
}

void __init smp_prepare_cpus(unsigned int max_cpus)
{
	unsigned int cpu;

	DBG("smp_prepare_cpus\n");

	/* 
	 * setup_cpu may need to be called on the boot cpu. We havent
	 * spun any cpus up but lets be paranoid.
	 */
	BUG_ON(boot_cpuid != smp_processor_id());

	/* Fixup boot cpu */
	smp_store_cpu_info(boot_cpuid);
	cpu_callin_map[boot_cpuid] = 1;

	for_each_possible_cpu(cpu) {
		zalloc_cpumask_var_node(&per_cpu(cpu_sibling_map, cpu),
					GFP_KERNEL, cpu_to_node(cpu));
		zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu),
					GFP_KERNEL, cpu_to_node(cpu));
	}

	cpumask_set_cpu(boot_cpuid, cpu_sibling_mask(boot_cpuid));
	cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid));

	if (smp_ops)
		if (smp_ops->probe)
			max_cpus = smp_ops->probe();
		else
			max_cpus = NR_CPUS;
	else
		max_cpus = 1;
}

void __devinit smp_prepare_boot_cpu(void)
{
	BUG_ON(smp_processor_id() != boot_cpuid);
#ifdef CONFIG_PPC64
	paca[boot_cpuid].__current = current;
#endif
	current_set[boot_cpuid] = task_thread_info(current);
}

#ifdef CONFIG_HOTPLUG_CPU
/* State of each CPU during hotplug phases */
static DEFINE_PER_CPU(int, cpu_state) = { 0 };

int generic_cpu_disable(void)
{
	unsigned int cpu = smp_processor_id();

	if (cpu == boot_cpuid)
		return -EBUSY;

	set_cpu_online(cpu, false);
#ifdef CONFIG_PPC64
	vdso_data->processorCount--;
#endif
	migrate_irqs();
	return 0;
}

void generic_cpu_die(unsigned int cpu)
{
	int i;

	for (i = 0; i < 100; i++) {
		smp_rmb();
		if (per_cpu(cpu_state, cpu) == CPU_DEAD)
			return;
		msleep(100);
	}
	printk(KERN_ERR "CPU%d didn't die...\n", cpu);
}

void generic_mach_cpu_die(void)
{
	unsigned int cpu;

	local_irq_disable();
	idle_task_exit();
	cpu = smp_processor_id();
	printk(KERN_DEBUG "CPU%d offline\n", cpu);
	__get_cpu_var(cpu_state) = CPU_DEAD;
	smp_wmb();
	while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
		cpu_relax();
}

void generic_set_cpu_dead(unsigned int cpu)
{
	per_cpu(cpu_state, cpu) = CPU_DEAD;
}
#endif

struct create_idle {
	struct work_struct work;
	struct task_struct *idle;
	struct completion done;
	int cpu;
};

static void __cpuinit do_fork_idle(struct work_struct *work)
{
	struct create_idle *c_idle =
		container_of(work, struct create_idle, work);

	c_idle->idle = fork_idle(c_idle->cpu);
	complete(&c_idle->done);
}

static int __cpuinit create_idle(unsigned int cpu)
{
	struct thread_info *ti;
	struct create_idle c_idle = {
		.cpu	= cpu,
		.done	= COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
	};
	INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle);

	c_idle.idle = get_idle_for_cpu(cpu);

	/* We can't use kernel_thread since we must avoid to
	 * reschedule the child. We use a workqueue because
	 * we want to fork from a kernel thread, not whatever
	 * userspace process happens to be trying to online us.
	 */
	if (!c_idle.idle) {
		schedule_work(&c_idle.work);
		wait_for_completion(&c_idle.done);
	} else
		init_idle(c_idle.idle, cpu);
	if (IS_ERR(c_idle.idle)) {		
		pr_err("Failed fork for CPU %u: %li", cpu, PTR_ERR(c_idle.idle));
		return PTR_ERR(c_idle.idle);
	}
	ti = task_thread_info(c_idle.idle);

#ifdef CONFIG_PPC64
	paca[cpu].__current = c_idle.idle;
	paca[cpu].kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD;
#endif
	ti->cpu = cpu;
	current_set[cpu] = ti;

	return 0;
}

int __cpuinit __cpu_up(unsigned int cpu)
{
	int rc, c;

	secondary_ti = current_set[cpu];

	if (smp_ops == NULL ||
	    (smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu)))
		return -EINVAL;

	/* Make sure we have an idle thread */
	rc = create_idle(cpu);
	if (rc)
		return rc;

	/* Make sure callin-map entry is 0 (can be leftover a CPU
	 * hotplug
	 */
	cpu_callin_map[cpu] = 0;

	/* The information for processor bringup must
	 * be written out to main store before we release
	 * the processor.
	 */
	smp_mb();

	/* wake up cpus */
	DBG("smp: kicking cpu %d\n", cpu);
	smp_ops->kick_cpu(cpu);

	/*
	 * wait to see if the cpu made a callin (is actually up).
	 * use this value that I found through experimentation.
	 * -- Cort
	 */
	if (system_state < SYSTEM_RUNNING)
		for (c = 50000; c && !cpu_callin_map[cpu]; c--)
			udelay(100);
#ifdef CONFIG_HOTPLUG_CPU
	else
		/*
		 * CPUs can take much longer to come up in the
		 * hotplug case.  Wait five seconds.
		 */
		for (c = 5000; c && !cpu_callin_map[cpu]; c--)
			msleep(1);
#endif

	if (!cpu_callin_map[cpu]) {
		printk(KERN_ERR "Processor %u is stuck.\n", cpu);
		return -ENOENT;
	}

	DBG("Processor %u found.\n", cpu);

	if (smp_ops->give_timebase)
		smp_ops->give_timebase();

	/* Wait until cpu puts itself in the online map */
	while (!cpu_online(cpu))
		cpu_relax();

	return 0;
}

/* Return the value of the reg property corresponding to the given
 * logical cpu.
 */
int cpu_to_core_id(int cpu)
{
	struct device_node *np;
	const int *reg;
	int id = -1;

	np = of_get_cpu_node(cpu, NULL);
	if (!np)
		goto out;

	reg = of_get_property(np, "reg", NULL);
	if (!reg)
		goto out;

	id = *reg;
out:
	of_node_put(np);
	return id;
}

/* Helper routines for cpu to core mapping */
int cpu_core_index_of_thread(int cpu)
{
	return cpu >> threads_shift;
}
EXPORT_SYMBOL_GPL(cpu_core_index_of_thread);

int cpu_first_thread_of_core(int core)
{
	return core << threads_shift;
}
EXPORT_SYMBOL_GPL(cpu_first_thread_of_core);

/* Must be called when no change can occur to cpu_present_map,
 * i.e. during cpu online or offline.
 */
static struct device_node *cpu_to_l2cache(int cpu)
{
	struct device_node *np;
	struct device_node *cache;

	if (!cpu_present(cpu))
		return NULL;

	np = of_get_cpu_node(cpu, NULL);
	if (np == NULL)
		return NULL;

	cache = of_find_next_cache_node(np);

	of_node_put(np);

	return cache;
}

/* Activate a secondary processor. */
void __devinit start_secondary(void *unused)
{
	unsigned int cpu = smp_processor_id();
	struct device_node *l2_cache;
	int i, base;

	atomic_inc(&init_mm.mm_count);
	current->active_mm = &init_mm;

	smp_store_cpu_info(cpu);
	set_dec(tb_ticks_per_jiffy);
	preempt_disable();
	cpu_callin_map[cpu] = 1;

	if (smp_ops->setup_cpu)
		smp_ops->setup_cpu(cpu);
	if (smp_ops->take_timebase)
		smp_ops->take_timebase();

	secondary_cpu_time_init();

#ifdef CONFIG_PPC64
	if (system_state == SYSTEM_RUNNING)
		vdso_data->processorCount++;
#endif
	ipi_call_lock();
	notify_cpu_starting(cpu);
	set_cpu_online(cpu, true);
	/* Update sibling maps */
	base = cpu_first_thread_sibling(cpu);
	for (i = 0; i < threads_per_core; i++) {
		if (cpu_is_offline(base + i))
			continue;
		cpumask_set_cpu(cpu, cpu_sibling_mask(base + i));
		cpumask_set_cpu(base + i, cpu_sibling_mask(cpu));

		/* cpu_core_map should be a superset of
		 * cpu_sibling_map even if we don't have cache
		 * information, so update the former here, too.
		 */
		cpumask_set_cpu(cpu, cpu_core_mask(base + i));
		cpumask_set_cpu(base + i, cpu_core_mask(cpu));
	}
	l2_cache = cpu_to_l2cache(cpu);
	for_each_online_cpu(i) {
		struct device_node *np = cpu_to_l2cache(i);
		if (!np)
			continue;
		if (np == l2_cache) {
			cpumask_set_cpu(cpu, cpu_core_mask(i));
			cpumask_set_cpu(i, cpu_core_mask(cpu));
		}
		of_node_put(np);
	}
	of_node_put(l2_cache);
	ipi_call_unlock();

	local_irq_enable();

	cpu_idle();

	BUG();
}

int setup_profiling_timer(unsigned int multiplier)
{
	return 0;
}

void __init smp_cpus_done(unsigned int max_cpus)
{
	cpumask_var_t old_mask;

	/* We want the setup_cpu() here to be called from CPU 0, but our
	 * init thread may have been "borrowed" by another CPU in the meantime
	 * se we pin us down to CPU 0 for a short while
	 */
	alloc_cpumask_var(&old_mask, GFP_NOWAIT);
	cpumask_copy(old_mask, &current->cpus_allowed);
	set_cpus_allowed_ptr(current, cpumask_of(boot_cpuid));
	
	if (smp_ops && smp_ops->setup_cpu)
		smp_ops->setup_cpu(boot_cpuid);

	set_cpus_allowed_ptr(current, old_mask);

	free_cpumask_var(old_mask);

	if (smp_ops && smp_ops->bringup_done)
		smp_ops->bringup_done();

	dump_numa_cpu_topology();

}

int arch_sd_sibling_asym_packing(void)
{
	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
		return SD_ASYM_PACKING;
	}
	return 0;
}

#ifdef CONFIG_HOTPLUG_CPU
int __cpu_disable(void)
{
	struct device_node *l2_cache;
	int cpu = smp_processor_id();
	int base, i;
	int err;

	if (!smp_ops->cpu_disable)
		return -ENOSYS;

	err = smp_ops->cpu_disable();
	if (err)
		return err;

	/* Update sibling maps */
	base = cpu_first_thread_sibling(cpu);
	for (i = 0; i < threads_per_core; i++) {
		cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i));
		cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu));
		cpumask_clear_cpu(cpu, cpu_core_mask(base + i));
		cpumask_clear_cpu(base + i, cpu_core_mask(cpu));
	}

	l2_cache = cpu_to_l2cache(cpu);
	for_each_present_cpu(i) {
		struct device_node *np = cpu_to_l2cache(i);
		if (!np)
			continue;
		if (np == l2_cache) {
			cpumask_clear_cpu(cpu, cpu_core_mask(i));
			cpumask_clear_cpu(i, cpu_core_mask(cpu));
		}
		of_node_put(np);
	}
	of_node_put(l2_cache);


	return 0;
}

void __cpu_die(unsigned int cpu)
{
	if (smp_ops->cpu_die)
		smp_ops->cpu_die(cpu);
}

static DEFINE_MUTEX(powerpc_cpu_hotplug_driver_mutex);

void cpu_hotplug_driver_lock()
{
	mutex_lock(&powerpc_cpu_hotplug_driver_mutex);
}

void cpu_hotplug_driver_unlock()
{
	mutex_unlock(&powerpc_cpu_hotplug_driver_mutex);
}

void cpu_die(void)
{
	if (ppc_md.cpu_die)
		ppc_md.cpu_die();

	/* If we return, we re-enter start_secondary */
	start_secondary_resume();
}

#endif