summaryrefslogtreecommitdiff
path: root/arch/powerpc/kernel/smp.c
blob: 9ca7148b5881a098abf7bf0a3eff99536f99a7ec (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
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
/*
 * 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/export.h>
#include <linux/sched/mm.h>
#include <linux/sched/topology.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/device.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/topology.h>
#include <linux/profile.h>
#include <linux/processor.h>

#include <asm/ptrace.h>
#include <linux/atomic.h>
#include <asm/irq.h>
#include <asm/hw_irq.h>
#include <asm/kvm_ppc.h>
#include <asm/dbell.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/mpic.h>
#include <asm/vdso_datapage.h>
#ifdef CONFIG_PPC64
#include <asm/paca.h>
#endif
#include <asm/vdso.h>
#include <asm/debug.h>
#include <asm/kexec.h>
#include <asm/asm-prototypes.h>
#include <asm/cpu_has_feature.h>

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

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

struct thread_info *secondary_ti;

DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_l2_cache_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);

EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_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;

/*
 * Returns 1 if the specified cpu should be brought up during boot.
 * Used to inhibit booting threads if they've been disabled or
 * limited on the command line
 */
int smp_generic_cpu_bootable(unsigned int nr)
{
	/* Special case - we inhibit secondary thread startup
	 * during boot if the user requests it.
	 */
	if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) {
		if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
			return 0;
		if (smt_enabled_at_boot
		    && cpu_thread_in_core(nr) >= smt_enabled_at_boot)
			return 0;
	}

	return 1;
}


#ifdef CONFIG_PPC64
int smp_generic_kick_cpu(int nr)
{
	if (nr < 0 || nr >= nr_cpu_ids)
		return -EINVAL;

	/*
	 * 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
	 */
	if (!paca_ptrs[nr]->cpu_start) {
		paca_ptrs[nr]->cpu_start = 1;
		smp_mb();
		return 0;
	}

#ifdef CONFIG_HOTPLUG_CPU
	/*
	 * Ok it's not there, so it might be soft-unplugged, let's
	 * try to bring it back
	 */
	generic_set_cpu_up(nr);
	smp_wmb();
	smp_send_reschedule(nr);
#endif /* CONFIG_HOTPLUG_CPU */

	return 0;
}
#endif /* CONFIG_PPC64 */

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)
{
	scheduler_ipi();
	return IRQ_HANDLED;
}

static irqreturn_t tick_broadcast_ipi_action(int irq, void *data)
{
	tick_broadcast_ipi_handler();
	return IRQ_HANDLED;
}

#ifdef CONFIG_NMI_IPI
static irqreturn_t nmi_ipi_action(int irq, void *data)
{
	smp_handle_nmi_ipi(get_irq_regs());
	return IRQ_HANDLED;
}
#endif

static irq_handler_t smp_ipi_action[] = {
	[PPC_MSG_CALL_FUNCTION] =  call_function_action,
	[PPC_MSG_RESCHEDULE] = reschedule_action,
	[PPC_MSG_TICK_BROADCAST] = tick_broadcast_ipi_action,
#ifdef CONFIG_NMI_IPI
	[PPC_MSG_NMI_IPI] = nmi_ipi_action,
#endif
};

/*
 * The NMI IPI is a fallback and not truly non-maskable. It is simpler
 * than going through the call function infrastructure, and strongly
 * serialized, so it is more appropriate for debugging.
 */
const char *smp_ipi_name[] = {
	[PPC_MSG_CALL_FUNCTION] =  "ipi call function",
	[PPC_MSG_RESCHEDULE] = "ipi reschedule",
	[PPC_MSG_TICK_BROADCAST] = "ipi tick-broadcast",
	[PPC_MSG_NMI_IPI] = "nmi ipi",
};

/* 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_NMI_IPI)
		return -EINVAL;
#ifndef CONFIG_NMI_IPI
	if (msg == PPC_MSG_NMI_IPI)
		return 1;
#endif

	err = request_irq(virq, smp_ipi_action[msg],
			  IRQF_PERCPU | IRQF_NO_THREAD | IRQF_NO_SUSPEND,
			  smp_ipi_name[msg], NULL);
	WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n",
		virq, smp_ipi_name[msg], err);

	return err;
}

#ifdef CONFIG_PPC_SMP_MUXED_IPI
struct cpu_messages {
	long messages;			/* current messages */
};
static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_messages, ipi_message);

void smp_muxed_ipi_set_message(int cpu, int msg)
{
	struct cpu_messages *info = &per_cpu(ipi_message, cpu);
	char *message = (char *)&info->messages;

	/*
	 * Order previous accesses before accesses in the IPI handler.
	 */
	smp_mb();
	message[msg] = 1;
}

void smp_muxed_ipi_message_pass(int cpu, int msg)
{
	smp_muxed_ipi_set_message(cpu, msg);

	/*
	 * cause_ipi functions are required to include a full barrier
	 * before doing whatever causes the IPI.
	 */
	smp_ops->cause_ipi(cpu);
}

#ifdef __BIG_ENDIAN__
#define IPI_MESSAGE(A) (1uL << ((BITS_PER_LONG - 8) - 8 * (A)))
#else
#define IPI_MESSAGE(A) (1uL << (8 * (A)))
#endif

irqreturn_t smp_ipi_demux(void)
{
	mb();	/* order any irq clear */

	return smp_ipi_demux_relaxed();
}

/* sync-free variant. Callers should ensure synchronization */
irqreturn_t smp_ipi_demux_relaxed(void)
{
	struct cpu_messages *info;
	unsigned long all;

	info = this_cpu_ptr(&ipi_message);
	do {
		all = xchg(&info->messages, 0);
#if defined(CONFIG_KVM_XICS) && defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE)
		/*
		 * Must check for PPC_MSG_RM_HOST_ACTION messages
		 * before PPC_MSG_CALL_FUNCTION messages because when
		 * a VM is destroyed, we call kick_all_cpus_sync()
		 * to ensure that any pending PPC_MSG_RM_HOST_ACTION
		 * messages have completed before we free any VCPUs.
		 */
		if (all & IPI_MESSAGE(PPC_MSG_RM_HOST_ACTION))
			kvmppc_xics_ipi_action();
#endif
		if (all & IPI_MESSAGE(PPC_MSG_CALL_FUNCTION))
			generic_smp_call_function_interrupt();
		if (all & IPI_MESSAGE(PPC_MSG_RESCHEDULE))
			scheduler_ipi();
		if (all & IPI_MESSAGE(PPC_MSG_TICK_BROADCAST))
			tick_broadcast_ipi_handler();
#ifdef CONFIG_NMI_IPI
		if (all & IPI_MESSAGE(PPC_MSG_NMI_IPI))
			nmi_ipi_action(0, NULL);
#endif
	} while (info->messages);

	return IRQ_HANDLED;
}
#endif /* CONFIG_PPC_SMP_MUXED_IPI */

static inline void do_message_pass(int cpu, int msg)
{
	if (smp_ops->message_pass)
		smp_ops->message_pass(cpu, msg);
#ifdef CONFIG_PPC_SMP_MUXED_IPI
	else
		smp_muxed_ipi_message_pass(cpu, msg);
#endif
}

void smp_send_reschedule(int cpu)
{
	if (likely(smp_ops))
		do_message_pass(cpu, PPC_MSG_RESCHEDULE);
}
EXPORT_SYMBOL_GPL(smp_send_reschedule);

void arch_send_call_function_single_ipi(int cpu)
{
	do_message_pass(cpu, PPC_MSG_CALL_FUNCTION);
}

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

	for_each_cpu(cpu, mask)
		do_message_pass(cpu, PPC_MSG_CALL_FUNCTION);
}

#ifdef CONFIG_NMI_IPI

/*
 * "NMI IPI" system.
 *
 * NMI IPIs may not be recoverable, so should not be used as ongoing part of
 * a running system. They can be used for crash, debug, halt/reboot, etc.
 *
 * NMI IPIs are globally single threaded. No more than one in progress at
 * any time.
 *
 * The IPI call waits with interrupts disabled until all targets enter the
 * NMI handler, then the call returns.
 *
 * No new NMI can be initiated until targets exit the handler.
 *
 * The IPI call may time out without all targets entering the NMI handler.
 * In that case, there is some logic to recover (and ignore subsequent
 * NMI interrupts that may eventually be raised), but the platform interrupt
 * handler may not be able to distinguish this from other exception causes,
 * which may cause a crash.
 */

static atomic_t __nmi_ipi_lock = ATOMIC_INIT(0);
static struct cpumask nmi_ipi_pending_mask;
static int nmi_ipi_busy_count = 0;
static void (*nmi_ipi_function)(struct pt_regs *) = NULL;

static void nmi_ipi_lock_start(unsigned long *flags)
{
	raw_local_irq_save(*flags);
	hard_irq_disable();
	while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) {
		raw_local_irq_restore(*flags);
		spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0);
		raw_local_irq_save(*flags);
		hard_irq_disable();
	}
}

static void nmi_ipi_lock(void)
{
	while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1)
		spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0);
}

static void nmi_ipi_unlock(void)
{
	smp_mb();
	WARN_ON(atomic_read(&__nmi_ipi_lock) != 1);
	atomic_set(&__nmi_ipi_lock, 0);
}

static void nmi_ipi_unlock_end(unsigned long *flags)
{
	nmi_ipi_unlock();
	raw_local_irq_restore(*flags);
}

/*
 * Platform NMI handler calls this to ack
 */
int smp_handle_nmi_ipi(struct pt_regs *regs)
{
	void (*fn)(struct pt_regs *);
	unsigned long flags;
	int me = raw_smp_processor_id();
	int ret = 0;

	/*
	 * Unexpected NMIs are possible here because the interrupt may not
	 * be able to distinguish NMI IPIs from other types of NMIs, or
	 * because the caller may have timed out.
	 */
	nmi_ipi_lock_start(&flags);
	if (!nmi_ipi_busy_count)
		goto out;
	if (!cpumask_test_cpu(me, &nmi_ipi_pending_mask))
		goto out;

	fn = nmi_ipi_function;
	if (!fn)
		goto out;

	cpumask_clear_cpu(me, &nmi_ipi_pending_mask);
	nmi_ipi_busy_count++;
	nmi_ipi_unlock();

	ret = 1;

	fn(regs);

	nmi_ipi_lock();
	nmi_ipi_busy_count--;
out:
	nmi_ipi_unlock_end(&flags);

	return ret;
}

static void do_smp_send_nmi_ipi(int cpu)
{
	if (smp_ops->cause_nmi_ipi && smp_ops->cause_nmi_ipi(cpu))
		return;

	if (cpu >= 0) {
		do_message_pass(cpu, PPC_MSG_NMI_IPI);
	} else {
		int c;

		for_each_online_cpu(c) {
			if (c == raw_smp_processor_id())
				continue;
			do_message_pass(c, PPC_MSG_NMI_IPI);
		}
	}
}

void smp_flush_nmi_ipi(u64 delay_us)
{
	unsigned long flags;

	nmi_ipi_lock_start(&flags);
	while (nmi_ipi_busy_count) {
		nmi_ipi_unlock_end(&flags);
		udelay(1);
		if (delay_us) {
			delay_us--;
			if (!delay_us)
				return;
		}
		nmi_ipi_lock_start(&flags);
	}
	nmi_ipi_unlock_end(&flags);
}

/*
 * - cpu is the target CPU (must not be this CPU), or NMI_IPI_ALL_OTHERS.
 * - fn is the target callback function.
 * - delay_us > 0 is the delay before giving up waiting for targets to
 *   enter the handler, == 0 specifies indefinite delay.
 */
int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us)
{
	unsigned long flags;
	int me = raw_smp_processor_id();
	int ret = 1;

	BUG_ON(cpu == me);
	BUG_ON(cpu < 0 && cpu != NMI_IPI_ALL_OTHERS);

	if (unlikely(!smp_ops))
		return 0;

	/* Take the nmi_ipi_busy count/lock with interrupts hard disabled */
	nmi_ipi_lock_start(&flags);
	while (nmi_ipi_busy_count) {
		nmi_ipi_unlock_end(&flags);
		spin_until_cond(nmi_ipi_busy_count == 0);
		nmi_ipi_lock_start(&flags);
	}

	nmi_ipi_function = fn;

	if (cpu < 0) {
		/* ALL_OTHERS */
		cpumask_copy(&nmi_ipi_pending_mask, cpu_online_mask);
		cpumask_clear_cpu(me, &nmi_ipi_pending_mask);
	} else {
		/* cpumask starts clear */
		cpumask_set_cpu(cpu, &nmi_ipi_pending_mask);
	}
	nmi_ipi_busy_count++;
	nmi_ipi_unlock();

	do_smp_send_nmi_ipi(cpu);

	while (!cpumask_empty(&nmi_ipi_pending_mask)) {
		udelay(1);
		if (delay_us) {
			delay_us--;
			if (!delay_us)
				break;
		}
	}

	nmi_ipi_lock();
	if (!cpumask_empty(&nmi_ipi_pending_mask)) {
		/* Could not gather all CPUs */
		ret = 0;
		cpumask_clear(&nmi_ipi_pending_mask);
	}
	nmi_ipi_busy_count--;
	nmi_ipi_unlock_end(&flags);

	return ret;
}
#endif /* CONFIG_NMI_IPI */

#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
void tick_broadcast(const struct cpumask *mask)
{
	unsigned int cpu;

	for_each_cpu(cpu, mask)
		do_message_pass(cpu, PPC_MSG_TICK_BROADCAST);
}
#endif

#ifdef CONFIG_DEBUGGER
void debugger_ipi_callback(struct pt_regs *regs)
{
	debugger_ipi(regs);
}

void smp_send_debugger_break(void)
{
	smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, debugger_ipi_callback, 1000000);
}
#endif

#ifdef CONFIG_KEXEC_CORE
void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
{
	int cpu;

	smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, crash_ipi_callback, 1000000);
	if (kdump_in_progress() && crash_wake_offline) {
		for_each_present_cpu(cpu) {
			if (cpu_online(cpu))
				continue;
			/*
			 * crash_ipi_callback will wait for
			 * all cpus, including offline CPUs.
			 * We don't care about nmi_ipi_function.
			 * Offline cpus will jump straight into
			 * crash_ipi_callback, we can skip the
			 * entire NMI dance and waiting for
			 * cpus to clear pending mask, etc.
			 */
			do_smp_send_nmi_ipi(cpu);
		}
	}
}
#endif

#ifdef CONFIG_NMI_IPI
static void nmi_stop_this_cpu(struct pt_regs *regs)
{
	/*
	 * This is a special case because it never returns, so the NMI IPI
	 * handling would never mark it as done, which makes any later
	 * smp_send_nmi_ipi() call spin forever. Mark it done now.
	 *
	 * IRQs are already hard disabled by the smp_handle_nmi_ipi.
	 */
	nmi_ipi_lock();
	nmi_ipi_busy_count--;
	nmi_ipi_unlock();

	/* Remove this CPU */
	set_cpu_online(smp_processor_id(), false);

	spin_begin();
	while (1)
		spin_cpu_relax();
}

void smp_send_stop(void)
{
	smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, nmi_stop_this_cpu, 1000000);
}

#else /* CONFIG_NMI_IPI */

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

	hard_irq_disable();
	spin_begin();
	while (1)
		spin_cpu_relax();
}

void smp_send_stop(void)
{
	static bool stopped = false;

	/*
	 * Prevent waiting on csd lock from a previous smp_send_stop.
	 * This is racy, but in general callers try to do the right
	 * thing and only fire off one smp_send_stop (e.g., see
	 * kernel/panic.c)
	 */
	if (stopped)
		return;

	stopped = true;

	smp_call_function(stop_this_cpu, NULL, 0);
}
#endif /* CONFIG_NMI_IPI */

struct thread_info *current_set[NR_CPUS];

static void smp_store_cpu_info(int id)
{
	per_cpu(cpu_pvr, id) = mfspr(SPRN_PVR);
#ifdef CONFIG_PPC_FSL_BOOK3E
	per_cpu(next_tlbcam_idx, id)
		= (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) - 1;
#endif
}

/*
 * Relationships between CPUs are maintained in a set of per-cpu cpumasks so
 * rather than just passing around the cpumask we pass around a function that
 * returns the that cpumask for the given CPU.
 */
static void set_cpus_related(int i, int j, struct cpumask *(*get_cpumask)(int))
{
	cpumask_set_cpu(i, get_cpumask(j));
	cpumask_set_cpu(j, get_cpumask(i));
}

#ifdef CONFIG_HOTPLUG_CPU
static void set_cpus_unrelated(int i, int j,
		struct cpumask *(*get_cpumask)(int))
{
	cpumask_clear_cpu(i, get_cpumask(j));
	cpumask_clear_cpu(j, get_cpumask(i));
}
#endif

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_l2_cache_map, cpu),
					GFP_KERNEL, cpu_to_node(cpu));
		zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu),
					GFP_KERNEL, cpu_to_node(cpu));
		/*
		 * numa_node_id() works after this.
		 */
		if (cpu_present(cpu)) {
			set_cpu_numa_node(cpu, numa_cpu_lookup_table[cpu]);
			set_cpu_numa_mem(cpu,
				local_memory_node(numa_cpu_lookup_table[cpu]));
		}
	}

	/* Init the cpumasks so the boot CPU is related to itself */
	cpumask_set_cpu(boot_cpuid, cpu_sibling_mask(boot_cpuid));
	cpumask_set_cpu(boot_cpuid, cpu_l2_cache_mask(boot_cpuid));
	cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid));

	if (smp_ops && smp_ops->probe)
		smp_ops->probe();
}

void smp_prepare_boot_cpu(void)
{
	BUG_ON(smp_processor_id() != boot_cpuid);
#ifdef CONFIG_PPC64
	paca_ptrs[boot_cpuid]->__current = current;
#endif
	set_numa_node(numa_cpu_lookup_table[boot_cpuid]);
	current_set[boot_cpuid] = task_thread_info(current);
}

#ifdef CONFIG_HOTPLUG_CPU

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
	/* Update affinity of all IRQs previously aimed at this CPU */
	irq_migrate_all_off_this_cpu();

	/*
	 * Depending on the details of the interrupt controller, it's possible
	 * that one of the interrupts we just migrated away from this CPU is
	 * actually already pending on this CPU. If we leave it in that state
	 * the interrupt will never be EOI'ed, and will never fire again. So
	 * temporarily enable interrupts here, to allow any pending interrupt to
	 * be received (and EOI'ed), before we take this CPU offline.
	 */
	local_irq_enable();
	mdelay(1);
	local_irq_disable();

	return 0;
}

void generic_cpu_die(unsigned int cpu)
{
	int i;

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

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

/*
 * The cpu_state should be set to CPU_UP_PREPARE in kick_cpu(), otherwise
 * the cpu_state is always CPU_DEAD after calling generic_set_cpu_dead(),
 * which makes the delay in generic_cpu_die() not happen.
 */
void generic_set_cpu_up(unsigned int cpu)
{
	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
}

int generic_check_cpu_restart(unsigned int cpu)
{
	return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE;
}

int is_cpu_dead(unsigned int cpu)
{
	return per_cpu(cpu_state, cpu) == CPU_DEAD;
}

static bool secondaries_inhibited(void)
{
	return kvm_hv_mode_active();
}

#else /* HOTPLUG_CPU */

#define secondaries_inhibited()		0

#endif

static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
{
	struct thread_info *ti = task_thread_info(idle);

#ifdef CONFIG_PPC64
	paca_ptrs[cpu]->__current = idle;
	paca_ptrs[cpu]->kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD;
#endif
	ti->cpu = cpu;
	secondary_ti = current_set[cpu] = ti;
}

int __cpu_up(unsigned int cpu, struct task_struct *tidle)
{
	int rc, c;

	/*
	 * Don't allow secondary threads to come online if inhibited
	 */
	if (threads_per_core > 1 && secondaries_inhibited() &&
	    cpu_thread_in_subcore(cpu))
		return -EBUSY;

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

	cpu_idle_thread_init(cpu, tidle);

	/*
	 * The platform might need to allocate resources prior to bringing
	 * up the CPU
	 */
	if (smp_ops->prepare_cpu) {
		rc = smp_ops->prepare_cpu(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);
	rc = smp_ops->kick_cpu(cpu);
	if (rc) {
		pr_err("smp: failed starting cpu %d (rc %d)\n", cpu, rc);
		return rc;
	}

	/*
	 * 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 & active maps */
	spin_until_cond(cpu_online(cpu));

	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 __be32 *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 = be32_to_cpup(reg);
out:
	of_node_put(np);
	return id;
}
EXPORT_SYMBOL_GPL(cpu_to_core_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_mask,
 * 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;
}

static bool update_mask_by_l2(int cpu, struct cpumask *(*mask_fn)(int))
{
	struct device_node *l2_cache, *np;
	int i;

	l2_cache = cpu_to_l2cache(cpu);
	if (!l2_cache)
		return false;

	for_each_cpu(i, cpu_online_mask) {
		/*
		 * when updating the marks the current CPU has not been marked
		 * online, but we need to update the cache masks
		 */
		np = cpu_to_l2cache(i);
		if (!np)
			continue;

		if (np == l2_cache)
			set_cpus_related(cpu, i, mask_fn);

		of_node_put(np);
	}
	of_node_put(l2_cache);

	return true;
}

#ifdef CONFIG_HOTPLUG_CPU
static void remove_cpu_from_masks(int cpu)
{
	int i;

	/* NB: cpu_core_mask is a superset of the others */
	for_each_cpu(i, cpu_core_mask(cpu)) {
		set_cpus_unrelated(cpu, i, cpu_core_mask);
		set_cpus_unrelated(cpu, i, cpu_l2_cache_mask);
		set_cpus_unrelated(cpu, i, cpu_sibling_mask);
	}
}
#endif

static void add_cpu_to_masks(int cpu)
{
	int first_thread = cpu_first_thread_sibling(cpu);
	int chipid = cpu_to_chip_id(cpu);
	int i;

	/*
	 * This CPU will not be in the online mask yet so we need to manually
	 * add it to it's own thread sibling mask.
	 */
	cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));

	for (i = first_thread; i < first_thread + threads_per_core; i++)
		if (cpu_online(i))
			set_cpus_related(i, cpu, cpu_sibling_mask);

	/*
	 * Copy the thread sibling mask into the cache sibling mask
	 * and mark any CPUs that share an L2 with this CPU.
	 */
	for_each_cpu(i, cpu_sibling_mask(cpu))
		set_cpus_related(cpu, i, cpu_l2_cache_mask);
	update_mask_by_l2(cpu, cpu_l2_cache_mask);

	/*
	 * Copy the cache sibling mask into core sibling mask and mark
	 * any CPUs on the same chip as this CPU.
	 */
	for_each_cpu(i, cpu_l2_cache_mask(cpu))
		set_cpus_related(cpu, i, cpu_core_mask);

	if (chipid == -1)
		return;

	for_each_cpu(i, cpu_online_mask)
		if (cpu_to_chip_id(i) == chipid)
			set_cpus_related(cpu, i, cpu_core_mask);
}

static bool shared_caches;

/* Activate a secondary processor. */
void start_secondary(void *unused)
{
	unsigned int cpu = smp_processor_id();

	mmgrab(&init_mm);
	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++;

	vdso_getcpu_init();
#endif
	/* Update topology CPU masks */
	add_cpu_to_masks(cpu);

	/*
	 * Check for any shared caches. Note that this must be done on a
	 * per-core basis because one core in the pair might be disabled.
	 */
	if (!cpumask_equal(cpu_l2_cache_mask(cpu), cpu_sibling_mask(cpu)))
		shared_caches = true;

	set_numa_node(numa_cpu_lookup_table[cpu]);
	set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu]));

	smp_wmb();
	notify_cpu_starting(cpu);
	set_cpu_online(cpu, true);

	local_irq_enable();

	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);

	BUG();
}

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

#ifdef CONFIG_SCHED_SMT
/* cpumask of CPUs with asymetric SMT dependancy */
static int powerpc_smt_flags(void)
{
	int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;

	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
		flags |= SD_ASYM_PACKING;
	}
	return flags;
}
#endif

static struct sched_domain_topology_level powerpc_topology[] = {
#ifdef CONFIG_SCHED_SMT
	{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
#endif
	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
	{ NULL, },
};

/*
 * P9 has a slightly odd architecture where pairs of cores share an L2 cache.
 * This topology makes it *much* cheaper to migrate tasks between adjacent cores
 * since the migrated task remains cache hot. We want to take advantage of this
 * at the scheduler level so an extra topology level is required.
 */
static int powerpc_shared_cache_flags(void)
{
	return SD_SHARE_PKG_RESOURCES;
}

/*
 * We can't just pass cpu_l2_cache_mask() directly because
 * returns a non-const pointer and the compiler barfs on that.
 */
static const struct cpumask *shared_cache_mask(int cpu)
{
	return cpu_l2_cache_mask(cpu);
}

static struct sched_domain_topology_level power9_topology[] = {
#ifdef CONFIG_SCHED_SMT
	{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
#endif
	{ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
	{ NULL, },
};

void __init smp_cpus_done(unsigned int max_cpus)
{
	/*
	 * We are running pinned to the boot CPU, see rest_init().
	 */
	if (smp_ops && smp_ops->setup_cpu)
		smp_ops->setup_cpu(boot_cpuid);

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

	dump_numa_cpu_topology();

	/*
	 * If any CPU detects that it's sharing a cache with another CPU then
	 * use the deeper topology that is aware of this sharing.
	 */
	if (shared_caches) {
		pr_info("Using shared cache scheduler topology\n");
		set_sched_topology(power9_topology);
	} else {
		pr_info("Using standard scheduler topology\n");
		set_sched_topology(powerpc_topology);
	}
}

#ifdef CONFIG_HOTPLUG_CPU
int __cpu_disable(void)
{
	int cpu = smp_processor_id();
	int err;

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

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

	/* Update sibling maps */
	remove_cpu_from_masks(cpu);

	return 0;
}

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

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