summaryrefslogtreecommitdiffstats
path: root/arch/s390/kernel/smp.c
blob: 264ea906db4c1cb2b8c5258b4d448e18e9293de9 (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
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
/*
 *  arch/s390/kernel/smp.c
 *
 *    Copyright IBM Corp. 1999,2007
 *    Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
 *		 Martin Schwidefsky (schwidefsky@de.ibm.com)
 *		 Heiko Carstens (heiko.carstens@de.ibm.com)
 *
 *  based on other smp stuff by
 *    (c) 1995 Alan Cox, CymruNET Ltd  <alan@cymru.net>
 *    (c) 1998 Ingo Molnar
 *
 * We work with logical cpu numbering everywhere we can. The only
 * functions using the real cpu address (got from STAP) are the sigp
 * functions. For all other functions we use the identity mapping.
 * That means that cpu_number_map[i] == i for every cpu. cpu_number_map is
 * used e.g. to find the idle task belonging to a logical cpu. Every array
 * in the kernel is sorted by the logical cpu number and not by the physical
 * one which is causing all the confusion with __cpu_logical_map and
 * cpu_number_map in other architectures.
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/spinlock.h>
#include <linux/kernel_stat.h>
#include <linux/delay.h>
#include <linux/cache.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <linux/timex.h>
#include <linux/bootmem.h>
#include <asm/ipl.h>
#include <asm/setup.h>
#include <asm/sigp.h>
#include <asm/pgalloc.h>
#include <asm/irq.h>
#include <asm/s390_ext.h>
#include <asm/cpcmd.h>
#include <asm/tlbflush.h>
#include <asm/timer.h>
#include <asm/lowcore.h>
#include <asm/cpu.h>

/*
 * An array with a pointer the lowcore of every CPU.
 */
struct _lowcore *lowcore_ptr[NR_CPUS];
EXPORT_SYMBOL(lowcore_ptr);

cpumask_t cpu_online_map = CPU_MASK_NONE;
EXPORT_SYMBOL(cpu_online_map);

cpumask_t cpu_possible_map = CPU_MASK_NONE;
EXPORT_SYMBOL(cpu_possible_map);

static struct task_struct *current_set[NR_CPUS];

static void smp_ext_bitcall(int, ec_bit_sig);

/*
 * Structure and data for __smp_call_function_map(). This is designed to
 * minimise static memory requirements. It also looks cleaner.
 */
static DEFINE_SPINLOCK(call_lock);

struct call_data_struct {
	void (*func) (void *info);
	void *info;
	cpumask_t started;
	cpumask_t finished;
	int wait;
};

static struct call_data_struct *call_data;

/*
 * 'Call function' interrupt callback
 */
static void do_call_function(void)
{
	void (*func) (void *info) = call_data->func;
	void *info = call_data->info;
	int wait = call_data->wait;

	cpu_set(smp_processor_id(), call_data->started);
	(*func)(info);
	if (wait)
		cpu_set(smp_processor_id(), call_data->finished);;
}

static void __smp_call_function_map(void (*func) (void *info), void *info,
				    int nonatomic, int wait, cpumask_t map)
{
	struct call_data_struct data;
	int cpu, local = 0;

	/*
	 * Can deadlock when interrupts are disabled or if in wrong context.
	 */
	WARN_ON(irqs_disabled() || in_irq());

	/*
	 * Check for local function call. We have to have the same call order
	 * as in on_each_cpu() because of machine_restart_smp().
	 */
	if (cpu_isset(smp_processor_id(), map)) {
		local = 1;
		cpu_clear(smp_processor_id(), map);
	}

	cpus_and(map, map, cpu_online_map);
	if (cpus_empty(map))
		goto out;

	data.func = func;
	data.info = info;
	data.started = CPU_MASK_NONE;
	data.wait = wait;
	if (wait)
		data.finished = CPU_MASK_NONE;

	spin_lock(&call_lock);
	call_data = &data;

	for_each_cpu_mask(cpu, map)
		smp_ext_bitcall(cpu, ec_call_function);

	/* Wait for response */
	while (!cpus_equal(map, data.started))
		cpu_relax();
	if (wait)
		while (!cpus_equal(map, data.finished))
			cpu_relax();
	spin_unlock(&call_lock);
out:
	if (local) {
		local_irq_disable();
		func(info);
		local_irq_enable();
	}
}

/*
 * smp_call_function:
 * @func: the function to run; this must be fast and non-blocking
 * @info: an arbitrary pointer to pass to the function
 * @nonatomic: unused
 * @wait: if true, wait (atomically) until function has completed on other CPUs
 *
 * Run a function on all other CPUs.
 *
 * You must not call this function with disabled interrupts, from a
 * hardware interrupt handler or from a bottom half.
 */
int smp_call_function(void (*func) (void *info), void *info, int nonatomic,
		      int wait)
{
	cpumask_t map;

	preempt_disable();
	map = cpu_online_map;
	cpu_clear(smp_processor_id(), map);
	__smp_call_function_map(func, info, nonatomic, wait, map);
	preempt_enable();
	return 0;
}
EXPORT_SYMBOL(smp_call_function);

/*
 * smp_call_function_single:
 * @cpu: the CPU where func should run
 * @func: the function to run; this must be fast and non-blocking
 * @info: an arbitrary pointer to pass to the function
 * @nonatomic: unused
 * @wait: if true, wait (atomically) until function has completed on other CPUs
 *
 * Run a function on one processor.
 *
 * You must not call this function with disabled interrupts, from a
 * hardware interrupt handler or from a bottom half.
 */
int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
			     int nonatomic, int wait)
{
	preempt_disable();
	__smp_call_function_map(func, info, nonatomic, wait,
				cpumask_of_cpu(cpu));
	preempt_enable();
	return 0;
}
EXPORT_SYMBOL(smp_call_function_single);

void smp_send_stop(void)
{
	int cpu, rc;

	/* Disable all interrupts/machine checks */
	__load_psw_mask(psw_kernel_bits & ~PSW_MASK_MCHECK);

	/* write magic number to zero page (absolute 0) */
	lowcore_ptr[smp_processor_id()]->panic_magic = __PANIC_MAGIC;

	/* stop all processors */
	for_each_online_cpu(cpu) {
		if (cpu == smp_processor_id())
			continue;
		do {
			rc = signal_processor(cpu, sigp_stop);
		} while (rc == sigp_busy);

		while (!smp_cpu_not_running(cpu))
			cpu_relax();
	}
}

/*
 * Reboot, halt and power_off routines for SMP.
 */
void machine_restart_smp(char *__unused)
{
	smp_send_stop();
	do_reipl();
}

void machine_halt_smp(void)
{
	smp_send_stop();
	if (MACHINE_IS_VM && strlen(vmhalt_cmd) > 0)
		__cpcmd(vmhalt_cmd, NULL, 0, NULL);
	signal_processor(smp_processor_id(), sigp_stop_and_store_status);
	for (;;);
}

void machine_power_off_smp(void)
{
	smp_send_stop();
	if (MACHINE_IS_VM && strlen(vmpoff_cmd) > 0)
		__cpcmd(vmpoff_cmd, NULL, 0, NULL);
	signal_processor(smp_processor_id(), sigp_stop_and_store_status);
	for (;;);
}

/*
 * This is the main routine where commands issued by other
 * cpus are handled.
 */

static void do_ext_call_interrupt(__u16 code)
{
	unsigned long bits;

	/*
	 * handle bit signal external calls
	 *
	 * For the ec_schedule signal we have to do nothing. All the work
	 * is done automatically when we return from the interrupt.
	 */
	bits = xchg(&S390_lowcore.ext_call_fast, 0);

	if (test_bit(ec_call_function, &bits))
		do_call_function();
}

/*
 * Send an external call sigp to another cpu and return without waiting
 * for its completion.
 */
static void smp_ext_bitcall(int cpu, ec_bit_sig sig)
{
	/*
	 * Set signaling bit in lowcore of target cpu and kick it
	 */
	set_bit(sig, (unsigned long *) &lowcore_ptr[cpu]->ext_call_fast);
	while (signal_processor(cpu, sigp_emergency_signal) == sigp_busy)
		udelay(10);
}

#ifndef CONFIG_64BIT
/*
 * this function sends a 'purge tlb' signal to another CPU.
 */
void smp_ptlb_callback(void *info)
{
	__tlb_flush_local();
}

void smp_ptlb_all(void)
{
	on_each_cpu(smp_ptlb_callback, NULL, 0, 1);
}
EXPORT_SYMBOL(smp_ptlb_all);
#endif /* ! CONFIG_64BIT */

/*
 * this function sends a 'reschedule' IPI to another CPU.
 * it goes straight through and wastes no time serializing
 * anything. Worst case is that we lose a reschedule ...
 */
void smp_send_reschedule(int cpu)
{
	smp_ext_bitcall(cpu, ec_schedule);
}

/*
 * parameter area for the set/clear control bit callbacks
 */
struct ec_creg_mask_parms {
	unsigned long orvals[16];
	unsigned long andvals[16];
};

/*
 * callback for setting/clearing control bits
 */
static void smp_ctl_bit_callback(void *info)
{
	struct ec_creg_mask_parms *pp = info;
	unsigned long cregs[16];
	int i;

	__ctl_store(cregs, 0, 15);
	for (i = 0; i <= 15; i++)
		cregs[i] = (cregs[i] & pp->andvals[i]) | pp->orvals[i];
	__ctl_load(cregs, 0, 15);
}

/*
 * Set a bit in a control register of all cpus
 */
void smp_ctl_set_bit(int cr, int bit)
{
	struct ec_creg_mask_parms parms;

	memset(&parms.orvals, 0, sizeof(parms.orvals));
	memset(&parms.andvals, 0xff, sizeof(parms.andvals));
	parms.orvals[cr] = 1 << bit;
	on_each_cpu(smp_ctl_bit_callback, &parms, 0, 1);
}
EXPORT_SYMBOL(smp_ctl_set_bit);

/*
 * Clear a bit in a control register of all cpus
 */
void smp_ctl_clear_bit(int cr, int bit)
{
	struct ec_creg_mask_parms parms;

	memset(&parms.orvals, 0, sizeof(parms.orvals));
	memset(&parms.andvals, 0xff, sizeof(parms.andvals));
	parms.andvals[cr] = ~(1L << bit);
	on_each_cpu(smp_ctl_bit_callback, &parms, 0, 1);
}
EXPORT_SYMBOL(smp_ctl_clear_bit);

#if defined(CONFIG_ZFCPDUMP) || defined(CONFIG_ZFCPDUMP_MODULE)

/*
 * zfcpdump_prefix_array holds prefix registers for the following scenario:
 * 64 bit zfcpdump kernel and 31 bit kernel which is to be dumped. We have to
 * save its prefix registers, since they get lost, when switching from 31 bit
 * to 64 bit.
 */
unsigned int zfcpdump_prefix_array[NR_CPUS + 1] \
	__attribute__((__section__(".data")));

static void __init smp_get_save_area(unsigned int cpu, unsigned int phy_cpu)
{
	if (ipl_info.type != IPL_TYPE_FCP_DUMP)
		return;
	if (cpu >= NR_CPUS) {
		printk(KERN_WARNING "Registers for cpu %i not saved since dump "
		       "kernel was compiled with NR_CPUS=%i\n", cpu, NR_CPUS);
		return;
	}
	zfcpdump_save_areas[cpu] = alloc_bootmem(sizeof(union save_area));
	__cpu_logical_map[1] = (__u16) phy_cpu;
	while (signal_processor(1, sigp_stop_and_store_status) == sigp_busy)
		cpu_relax();
	memcpy(zfcpdump_save_areas[cpu],
	       (void *)(unsigned long) store_prefix() + SAVE_AREA_BASE,
	       SAVE_AREA_SIZE);
#ifdef CONFIG_64BIT
	/* copy original prefix register */
	zfcpdump_save_areas[cpu]->s390x.pref_reg = zfcpdump_prefix_array[cpu];
#endif
}

union save_area *zfcpdump_save_areas[NR_CPUS + 1];
EXPORT_SYMBOL_GPL(zfcpdump_save_areas);

#else

static inline void smp_get_save_area(unsigned int cpu, unsigned int phy_cpu) { }

#endif /* CONFIG_ZFCPDUMP || CONFIG_ZFCPDUMP_MODULE */

/*
 * Lets check how many CPUs we have.
 */
static unsigned int __init smp_count_cpus(void)
{
	unsigned int cpu, num_cpus;
	__u16 boot_cpu_addr;

	/*
	 * cpu 0 is the boot cpu. See smp_prepare_boot_cpu.
	 */
	boot_cpu_addr = S390_lowcore.cpu_data.cpu_addr;
	current_thread_info()->cpu = 0;
	num_cpus = 1;
	for (cpu = 0; cpu <= 65535; cpu++) {
		if ((__u16) cpu == boot_cpu_addr)
			continue;
		__cpu_logical_map[1] = (__u16) cpu;
		if (signal_processor(1, sigp_sense) == sigp_not_operational)
			continue;
		smp_get_save_area(num_cpus, cpu);
		num_cpus++;
	}
	printk("Detected %d CPU's\n", (int) num_cpus);
	printk("Boot cpu address %2X\n", boot_cpu_addr);
	return num_cpus;
}

/*
 *	Activate a secondary processor.
 */
int __cpuinit start_secondary(void *cpuvoid)
{
	/* Setup the cpu */
	cpu_init();
	preempt_disable();
	/* Enable TOD clock interrupts on the secondary cpu. */
	init_cpu_timer();
#ifdef CONFIG_VIRT_TIMER
	/* Enable cpu timer interrupts on the secondary cpu. */
	init_cpu_vtimer();
#endif
	/* Enable pfault pseudo page faults on this cpu. */
	pfault_init();

	/* Mark this cpu as online */
	cpu_set(smp_processor_id(), cpu_online_map);
	/* Switch on interrupts */
	local_irq_enable();
	/* Print info about this processor */
	print_cpu_info(&S390_lowcore.cpu_data);
	/* cpu_idle will call schedule for us */
	cpu_idle();
	return 0;
}

DEFINE_PER_CPU(struct s390_idle_data, s390_idle);

static void __init smp_create_idle(unsigned int cpu)
{
	struct task_struct *p;

	/*
	 *  don't care about the psw and regs settings since we'll never
	 *  reschedule the forked task.
	 */
	p = fork_idle(cpu);
	if (IS_ERR(p))
		panic("failed fork for CPU %u: %li", cpu, PTR_ERR(p));
	current_set[cpu] = p;
	spin_lock_init(&(&per_cpu(s390_idle, cpu))->lock);
}

static int cpu_stopped(int cpu)
{
	__u32 status;

	/* Check for stopped state */
	if (signal_processor_ps(&status, 0, cpu, sigp_sense) ==
	    sigp_status_stored) {
		if (status & 0x40)
			return 1;
	}
	return 0;
}

/* Upping and downing of CPUs */

int __cpu_up(unsigned int cpu)
{
	struct task_struct *idle;
	struct _lowcore *cpu_lowcore;
	struct stack_frame *sf;
	sigp_ccode ccode;
	int curr_cpu;

	for (curr_cpu = 0; curr_cpu <= 65535; curr_cpu++) {
		__cpu_logical_map[cpu] = (__u16) curr_cpu;
		if (cpu_stopped(cpu))
			break;
	}

	if (!cpu_stopped(cpu))
		return -ENODEV;

	ccode = signal_processor_p((__u32)(unsigned long)(lowcore_ptr[cpu]),
				   cpu, sigp_set_prefix);
	if (ccode) {
		printk("sigp_set_prefix failed for cpu %d "
		       "with condition code %d\n",
		       (int) cpu, (int) ccode);
		return -EIO;
	}

	idle = current_set[cpu];
	cpu_lowcore = lowcore_ptr[cpu];
	cpu_lowcore->kernel_stack = (unsigned long)
		task_stack_page(idle) + THREAD_SIZE;
	sf = (struct stack_frame *) (cpu_lowcore->kernel_stack
				     - sizeof(struct pt_regs)
				     - sizeof(struct stack_frame));
	memset(sf, 0, sizeof(struct stack_frame));
	sf->gprs[9] = (unsigned long) sf;
	cpu_lowcore->save_area[15] = (unsigned long) sf;
	__ctl_store(cpu_lowcore->cregs_save_area[0], 0, 15);
	asm volatile(
		"	stam	0,15,0(%0)"
		: : "a" (&cpu_lowcore->access_regs_save_area) : "memory");
	cpu_lowcore->percpu_offset = __per_cpu_offset[cpu];
	cpu_lowcore->current_task = (unsigned long) idle;
	cpu_lowcore->cpu_data.cpu_nr = cpu;
	eieio();

	while (signal_processor(cpu, sigp_restart) == sigp_busy)
		udelay(10);

	while (!cpu_online(cpu))
		cpu_relax();
	return 0;
}

static unsigned int __initdata additional_cpus;
static unsigned int __initdata possible_cpus;

void __init smp_setup_cpu_possible_map(void)
{
	unsigned int phy_cpus, pos_cpus, cpu;

	phy_cpus = smp_count_cpus();
	pos_cpus = min(phy_cpus + additional_cpus, (unsigned int) NR_CPUS);

	if (possible_cpus)
		pos_cpus = min(possible_cpus, (unsigned int) NR_CPUS);

	for (cpu = 0; cpu < pos_cpus; cpu++)
		cpu_set(cpu, cpu_possible_map);

	phy_cpus = min(phy_cpus, pos_cpus);

	for (cpu = 0; cpu < phy_cpus; cpu++)
		cpu_set(cpu, cpu_present_map);
}

#ifdef CONFIG_HOTPLUG_CPU

static int __init setup_additional_cpus(char *s)
{
	additional_cpus = simple_strtoul(s, NULL, 0);
	return 0;
}
early_param("additional_cpus", setup_additional_cpus);

static int __init setup_possible_cpus(char *s)
{
	possible_cpus = simple_strtoul(s, NULL, 0);
	return 0;
}
early_param("possible_cpus", setup_possible_cpus);

int __cpu_disable(void)
{
	struct ec_creg_mask_parms cr_parms;
	int cpu = smp_processor_id();

	cpu_clear(cpu, cpu_online_map);

	/* Disable pfault pseudo page faults on this cpu. */
	pfault_fini();

	memset(&cr_parms.orvals, 0, sizeof(cr_parms.orvals));
	memset(&cr_parms.andvals, 0xff, sizeof(cr_parms.andvals));

	/* disable all external interrupts */
	cr_parms.orvals[0] = 0;
	cr_parms.andvals[0] = ~(1 << 15 | 1 << 14 | 1 << 13 | 1 << 12 |
				1 << 11 | 1 << 10 | 1 <<  6 | 1 <<  4);
	/* disable all I/O interrupts */
	cr_parms.orvals[6] = 0;
	cr_parms.andvals[6] = ~(1 << 31 | 1 << 30 | 1 << 29 | 1 << 28 |
				1 << 27 | 1 << 26 | 1 << 25 | 1 << 24);
	/* disable most machine checks */
	cr_parms.orvals[14] = 0;
	cr_parms.andvals[14] = ~(1 << 28 | 1 << 27 | 1 << 26 |
				 1 << 25 | 1 << 24);

	smp_ctl_bit_callback(&cr_parms);

	return 0;
}

void __cpu_die(unsigned int cpu)
{
	/* Wait until target cpu is down */
	while (!smp_cpu_not_running(cpu))
		cpu_relax();
	printk("Processor %d spun down\n", cpu);
}

void cpu_die(void)
{
	idle_task_exit();
	signal_processor(smp_processor_id(), sigp_stop);
	BUG();
	for (;;);
}

#endif /* CONFIG_HOTPLUG_CPU */

/*
 *	Cycle through the processors and setup structures.
 */

void __init smp_prepare_cpus(unsigned int max_cpus)
{
	unsigned long stack;
	unsigned int cpu;
	int i;

	/* request the 0x1201 emergency signal external interrupt */
	if (register_external_interrupt(0x1201, do_ext_call_interrupt) != 0)
		panic("Couldn't request external interrupt 0x1201");
	memset(lowcore_ptr, 0, sizeof(lowcore_ptr));
	/*
	 *  Initialize prefix pages and stacks for all possible cpus
	 */
	print_cpu_info(&S390_lowcore.cpu_data);

	for_each_possible_cpu(i) {
		lowcore_ptr[i] = (struct _lowcore *)
			__get_free_pages(GFP_KERNEL | GFP_DMA,
					 sizeof(void*) == 8 ? 1 : 0);
		stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER);
		if (!lowcore_ptr[i] || !stack)
			panic("smp_boot_cpus failed to allocate memory\n");

		*(lowcore_ptr[i]) = S390_lowcore;
		lowcore_ptr[i]->async_stack = stack + ASYNC_SIZE;
		stack = __get_free_pages(GFP_KERNEL, 0);
		if (!stack)
			panic("smp_boot_cpus failed to allocate memory\n");
		lowcore_ptr[i]->panic_stack = stack + PAGE_SIZE;
#ifndef CONFIG_64BIT
		if (MACHINE_HAS_IEEE) {
			lowcore_ptr[i]->extended_save_area_addr =
				(__u32) __get_free_pages(GFP_KERNEL, 0);
			if (!lowcore_ptr[i]->extended_save_area_addr)
				panic("smp_boot_cpus failed to "
				      "allocate memory\n");
		}
#endif
	}
#ifndef CONFIG_64BIT
	if (MACHINE_HAS_IEEE)
		ctl_set_bit(14, 29); /* enable extended save area */
#endif
	set_prefix((u32)(unsigned long) lowcore_ptr[smp_processor_id()]);

	for_each_possible_cpu(cpu)
		if (cpu != smp_processor_id())
			smp_create_idle(cpu);
}

void __init smp_prepare_boot_cpu(void)
{
	BUG_ON(smp_processor_id() != 0);

	cpu_set(0, cpu_online_map);
	S390_lowcore.percpu_offset = __per_cpu_offset[0];
	current_set[0] = current;
	spin_lock_init(&(&__get_cpu_var(s390_idle))->lock);
}

void __init smp_cpus_done(unsigned int max_cpus)
{
	cpu_present_map = cpu_possible_map;
}

/*
 * the frequency of the profiling timer can be changed
 * by writing a multiplier value into /proc/profile.
 *
 * usually you want to run this on all CPUs ;)
 */
int setup_profiling_timer(unsigned int multiplier)
{
	return 0;
}

static DEFINE_PER_CPU(struct cpu, cpu_devices);

static ssize_t show_capability(struct sys_device *dev, char *buf)
{
	unsigned int capability;
	int rc;

	rc = get_cpu_capability(&capability);
	if (rc)
		return rc;
	return sprintf(buf, "%u\n", capability);
}
static SYSDEV_ATTR(capability, 0444, show_capability, NULL);

static ssize_t show_idle_count(struct sys_device *dev, char *buf)
{
	struct s390_idle_data *idle;
	unsigned long long idle_count;

	idle = &per_cpu(s390_idle, dev->id);
	spin_lock_irq(&idle->lock);
	idle_count = idle->idle_count;
	spin_unlock_irq(&idle->lock);
	return sprintf(buf, "%llu\n", idle_count);
}
static SYSDEV_ATTR(idle_count, 0444, show_idle_count, NULL);

static ssize_t show_idle_time(struct sys_device *dev, char *buf)
{
	struct s390_idle_data *idle;
	unsigned long long new_time;

	idle = &per_cpu(s390_idle, dev->id);
	spin_lock_irq(&idle->lock);
	if (idle->in_idle) {
		new_time = get_clock();
		idle->idle_time += new_time - idle->idle_enter;
		idle->idle_enter = new_time;
	}
	new_time = idle->idle_time;
	spin_unlock_irq(&idle->lock);
	return sprintf(buf, "%llu\n", new_time >> 12);
}
static SYSDEV_ATTR(idle_time_us, 0444, show_idle_time, NULL);

static struct attribute *cpu_attrs[] = {
	&attr_capability.attr,
	&attr_idle_count.attr,
	&attr_idle_time_us.attr,
	NULL,
};

static struct attribute_group cpu_attr_group = {
	.attrs = cpu_attrs,
};

static int __cpuinit smp_cpu_notify(struct notifier_block *self,
				    unsigned long action, void *hcpu)
{
	unsigned int cpu = (unsigned int)(long)hcpu;
	struct cpu *c = &per_cpu(cpu_devices, cpu);
	struct sys_device *s = &c->sysdev;
	struct s390_idle_data *idle;

	switch (action) {
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		idle = &per_cpu(s390_idle, cpu);
		spin_lock_irq(&idle->lock);
		idle->idle_enter = 0;
		idle->idle_time = 0;
		idle->idle_count = 0;
		spin_unlock_irq(&idle->lock);
		if (sysfs_create_group(&s->kobj, &cpu_attr_group))
			return NOTIFY_BAD;
		break;
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		sysfs_remove_group(&s->kobj, &cpu_attr_group);
		break;
	}
	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata smp_cpu_nb = {
	.notifier_call = smp_cpu_notify,
};

static int __init topology_init(void)
{
	int cpu;
	int rc;

	register_cpu_notifier(&smp_cpu_nb);

	for_each_possible_cpu(cpu) {
		struct cpu *c = &per_cpu(cpu_devices, cpu);
		struct sys_device *s = &c->sysdev;

		c->hotpluggable = 1;
		register_cpu(c, cpu);
		if (!cpu_online(cpu))
			continue;
		s = &c->sysdev;
		rc = sysfs_create_group(&s->kobj, &cpu_attr_group);
		if (rc)
			return rc;
	}
	return 0;
}
subsys_initcall(topology_init);