summaryrefslogtreecommitdiffstats
path: root/arch/s390/kernel/smp.c
blob: ebfe86d097f0afa6c83f8582e1909eeccda6d620 (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
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
// SPDX-License-Identifier: GPL-2.0
/*
 *  SMP related functions
 *
 *    Copyright IBM Corp. 1999, 2012
 *    Author(s): Denis Joseph Barrow,
 *		 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
 *
 * The code outside of smp.c uses logical cpu numbers, only smp.c does
 * the translation of logical to physical cpu ids. All new code that
 * operates on physical cpu numbers needs to go into smp.c.
 */

#define KMSG_COMPONENT "cpu"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt

#include <linux/workqueue.h>
#include <linux/memblock.h>
#include <linux/export.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/interrupt.h>
#include <linux/irqflags.h>
#include <linux/cpu.h>
#include <linux/slab.h>
#include <linux/sched/hotplug.h>
#include <linux/sched/task_stack.h>
#include <linux/crash_dump.h>
#include <linux/kprobes.h>
#include <asm/asm-offsets.h>
#include <asm/diag.h>
#include <asm/switch_to.h>
#include <asm/facility.h>
#include <asm/ipl.h>
#include <asm/setup.h>
#include <asm/irq.h>
#include <asm/tlbflush.h>
#include <asm/vtimer.h>
#include <asm/lowcore.h>
#include <asm/sclp.h>
#include <asm/vdso.h>
#include <asm/debug.h>
#include <asm/os_info.h>
#include <asm/sigp.h>
#include <asm/idle.h>
#include <asm/nmi.h>
#include <asm/stacktrace.h>
#include <asm/topology.h>
#include "entry.h"

enum {
	ec_schedule = 0,
	ec_call_function_single,
	ec_stop_cpu,
	ec_mcck_pending,
};

enum {
	CPU_STATE_STANDBY,
	CPU_STATE_CONFIGURED,
};

static DEFINE_PER_CPU(struct cpu *, cpu_device);

struct pcpu {
	struct lowcore *lowcore;	/* lowcore page(s) for the cpu */
	unsigned long ec_mask;		/* bit mask for ec_xxx functions */
	unsigned long ec_clk;		/* sigp timestamp for ec_xxx */
	signed char state;		/* physical cpu state */
	signed char polarization;	/* physical polarization */
	u16 address;			/* physical cpu address */
};

static u8 boot_core_type;
static struct pcpu pcpu_devices[NR_CPUS];

unsigned int smp_cpu_mt_shift;
EXPORT_SYMBOL(smp_cpu_mt_shift);

unsigned int smp_cpu_mtid;
EXPORT_SYMBOL(smp_cpu_mtid);

#ifdef CONFIG_CRASH_DUMP
__vector128 __initdata boot_cpu_vector_save_area[__NUM_VXRS];
#endif

static unsigned int smp_max_threads __initdata = -1U;

static int __init early_nosmt(char *s)
{
	smp_max_threads = 1;
	return 0;
}
early_param("nosmt", early_nosmt);

static int __init early_smt(char *s)
{
	get_option(&s, &smp_max_threads);
	return 0;
}
early_param("smt", early_smt);

/*
 * The smp_cpu_state_mutex must be held when changing the state or polarization
 * member of a pcpu data structure within the pcpu_devices arreay.
 */
DEFINE_MUTEX(smp_cpu_state_mutex);

/*
 * Signal processor helper functions.
 */
static inline int __pcpu_sigp_relax(u16 addr, u8 order, unsigned long parm)
{
	int cc;

	while (1) {
		cc = __pcpu_sigp(addr, order, parm, NULL);
		if (cc != SIGP_CC_BUSY)
			return cc;
		cpu_relax();
	}
}

static int pcpu_sigp_retry(struct pcpu *pcpu, u8 order, u32 parm)
{
	int cc, retry;

	for (retry = 0; ; retry++) {
		cc = __pcpu_sigp(pcpu->address, order, parm, NULL);
		if (cc != SIGP_CC_BUSY)
			break;
		if (retry >= 3)
			udelay(10);
	}
	return cc;
}

static inline int pcpu_stopped(struct pcpu *pcpu)
{
	u32 status;

	if (__pcpu_sigp(pcpu->address, SIGP_SENSE,
			0, &status) != SIGP_CC_STATUS_STORED)
		return 0;
	return !!(status & (SIGP_STATUS_CHECK_STOP|SIGP_STATUS_STOPPED));
}

static inline int pcpu_running(struct pcpu *pcpu)
{
	if (__pcpu_sigp(pcpu->address, SIGP_SENSE_RUNNING,
			0, NULL) != SIGP_CC_STATUS_STORED)
		return 1;
	/* Status stored condition code is equivalent to cpu not running. */
	return 0;
}

/*
 * Find struct pcpu by cpu address.
 */
static struct pcpu *pcpu_find_address(const struct cpumask *mask, u16 address)
{
	int cpu;

	for_each_cpu(cpu, mask)
		if (pcpu_devices[cpu].address == address)
			return pcpu_devices + cpu;
	return NULL;
}

static void pcpu_ec_call(struct pcpu *pcpu, int ec_bit)
{
	int order;

	if (test_and_set_bit(ec_bit, &pcpu->ec_mask))
		return;
	order = pcpu_running(pcpu) ? SIGP_EXTERNAL_CALL : SIGP_EMERGENCY_SIGNAL;
	pcpu->ec_clk = get_tod_clock_fast();
	pcpu_sigp_retry(pcpu, order, 0);
}

static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
{
	unsigned long async_stack, nodat_stack;
	struct lowcore *lc;

	if (pcpu != &pcpu_devices[0]) {
		pcpu->lowcore =	(struct lowcore *)
			__get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER);
		nodat_stack = __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER);
		if (!pcpu->lowcore || !nodat_stack)
			goto out;
	} else {
		nodat_stack = pcpu->lowcore->nodat_stack - STACK_INIT_OFFSET;
	}
	async_stack = stack_alloc();
	if (!async_stack)
		goto out;
	lc = pcpu->lowcore;
	memcpy(lc, &S390_lowcore, 512);
	memset((char *) lc + 512, 0, sizeof(*lc) - 512);
	lc->async_stack = async_stack + STACK_INIT_OFFSET;
	lc->nodat_stack = nodat_stack + STACK_INIT_OFFSET;
	lc->cpu_nr = cpu;
	lc->spinlock_lockval = arch_spin_lockval(cpu);
	lc->spinlock_index = 0;
	lc->br_r1_trampoline = 0x07f1;	/* br %r1 */
	lc->return_lpswe = gen_lpswe(__LC_RETURN_PSW);
	lc->return_mcck_lpswe = gen_lpswe(__LC_RETURN_MCCK_PSW);
	if (nmi_alloc_per_cpu(lc))
		goto out_async;
	if (vdso_alloc_per_cpu(lc))
		goto out_mcesa;
	lowcore_ptr[cpu] = lc;
	pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, (u32)(unsigned long) lc);
	return 0;

out_mcesa:
	nmi_free_per_cpu(lc);
out_async:
	stack_free(async_stack);
out:
	if (pcpu != &pcpu_devices[0]) {
		free_pages(nodat_stack, THREAD_SIZE_ORDER);
		free_pages((unsigned long) pcpu->lowcore, LC_ORDER);
	}
	return -ENOMEM;
}

static void pcpu_free_lowcore(struct pcpu *pcpu)
{
	unsigned long async_stack, nodat_stack, lowcore;

	nodat_stack = pcpu->lowcore->nodat_stack - STACK_INIT_OFFSET;
	async_stack = pcpu->lowcore->async_stack - STACK_INIT_OFFSET;
	lowcore = (unsigned long) pcpu->lowcore;

	pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, 0);
	lowcore_ptr[pcpu - pcpu_devices] = NULL;
	vdso_free_per_cpu(pcpu->lowcore);
	nmi_free_per_cpu(pcpu->lowcore);
	stack_free(async_stack);
	if (pcpu == &pcpu_devices[0])
		return;
	free_pages(nodat_stack, THREAD_SIZE_ORDER);
	free_pages(lowcore, LC_ORDER);
}

static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
{
	struct lowcore *lc = pcpu->lowcore;

	cpumask_set_cpu(cpu, &init_mm.context.cpu_attach_mask);
	cpumask_set_cpu(cpu, mm_cpumask(&init_mm));
	lc->cpu_nr = cpu;
	lc->spinlock_lockval = arch_spin_lockval(cpu);
	lc->spinlock_index = 0;
	lc->percpu_offset = __per_cpu_offset[cpu];
	lc->kernel_asce = S390_lowcore.kernel_asce;
	lc->user_asce = S390_lowcore.kernel_asce;
	lc->machine_flags = S390_lowcore.machine_flags;
	lc->user_timer = lc->system_timer =
		lc->steal_timer = lc->avg_steal_timer = 0;
	__ctl_store(lc->cregs_save_area, 0, 15);
	lc->cregs_save_area[1] = lc->kernel_asce;
	lc->cregs_save_area[7] = lc->vdso_asce;
	save_access_regs((unsigned int *) lc->access_regs_save_area);
	memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
	       sizeof(lc->stfle_fac_list));
	memcpy(lc->alt_stfle_fac_list, S390_lowcore.alt_stfle_fac_list,
	       sizeof(lc->alt_stfle_fac_list));
	arch_spin_lock_setup(cpu);
}

static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk)
{
	struct lowcore *lc = pcpu->lowcore;

	lc->kernel_stack = (unsigned long) task_stack_page(tsk)
		+ THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
	lc->current_task = (unsigned long) tsk;
	lc->lpp = LPP_MAGIC;
	lc->current_pid = tsk->pid;
	lc->user_timer = tsk->thread.user_timer;
	lc->guest_timer = tsk->thread.guest_timer;
	lc->system_timer = tsk->thread.system_timer;
	lc->hardirq_timer = tsk->thread.hardirq_timer;
	lc->softirq_timer = tsk->thread.softirq_timer;
	lc->steal_timer = 0;
}

static void pcpu_start_fn(struct pcpu *pcpu, void (*func)(void *), void *data)
{
	struct lowcore *lc = pcpu->lowcore;

	lc->restart_stack = lc->nodat_stack;
	lc->restart_fn = (unsigned long) func;
	lc->restart_data = (unsigned long) data;
	lc->restart_source = -1UL;
	pcpu_sigp_retry(pcpu, SIGP_RESTART, 0);
}

/*
 * Call function via PSW restart on pcpu and stop the current cpu.
 */
static void __pcpu_delegate(void (*func)(void*), void *data)
{
	func(data);	/* should not return */
}

static void __no_sanitize_address pcpu_delegate(struct pcpu *pcpu,
						void (*func)(void *),
						void *data, unsigned long stack)
{
	struct lowcore *lc = lowcore_ptr[pcpu - pcpu_devices];
	unsigned long source_cpu = stap();

	__load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT);
	if (pcpu->address == source_cpu)
		CALL_ON_STACK(__pcpu_delegate, stack, 2, func, data);
	/* Stop target cpu (if func returns this stops the current cpu). */
	pcpu_sigp_retry(pcpu, SIGP_STOP, 0);
	/* Restart func on the target cpu and stop the current cpu. */
	mem_assign_absolute(lc->restart_stack, stack);
	mem_assign_absolute(lc->restart_fn, (unsigned long) func);
	mem_assign_absolute(lc->restart_data, (unsigned long) data);
	mem_assign_absolute(lc->restart_source, source_cpu);
	__bpon();
	asm volatile(
		"0:	sigp	0,%0,%2	# sigp restart to target cpu\n"
		"	brc	2,0b	# busy, try again\n"
		"1:	sigp	0,%1,%3	# sigp stop to current cpu\n"
		"	brc	2,1b	# busy, try again\n"
		: : "d" (pcpu->address), "d" (source_cpu),
		    "K" (SIGP_RESTART), "K" (SIGP_STOP)
		: "0", "1", "cc");
	for (;;) ;
}

/*
 * Enable additional logical cpus for multi-threading.
 */
static int pcpu_set_smt(unsigned int mtid)
{
	int cc;

	if (smp_cpu_mtid == mtid)
		return 0;
	cc = __pcpu_sigp(0, SIGP_SET_MULTI_THREADING, mtid, NULL);
	if (cc == 0) {
		smp_cpu_mtid = mtid;
		smp_cpu_mt_shift = 0;
		while (smp_cpu_mtid >= (1U << smp_cpu_mt_shift))
			smp_cpu_mt_shift++;
		pcpu_devices[0].address = stap();
	}
	return cc;
}

/*
 * Call function on an online CPU.
 */
void smp_call_online_cpu(void (*func)(void *), void *data)
{
	struct pcpu *pcpu;

	/* Use the current cpu if it is online. */
	pcpu = pcpu_find_address(cpu_online_mask, stap());
	if (!pcpu)
		/* Use the first online cpu. */
		pcpu = pcpu_devices + cpumask_first(cpu_online_mask);
	pcpu_delegate(pcpu, func, data, (unsigned long) restart_stack);
}

/*
 * Call function on the ipl CPU.
 */
void smp_call_ipl_cpu(void (*func)(void *), void *data)
{
	struct lowcore *lc = pcpu_devices->lowcore;

	if (pcpu_devices[0].address == stap())
		lc = &S390_lowcore;

	pcpu_delegate(&pcpu_devices[0], func, data,
		      lc->nodat_stack);
}

int smp_find_processor_id(u16 address)
{
	int cpu;

	for_each_present_cpu(cpu)
		if (pcpu_devices[cpu].address == address)
			return cpu;
	return -1;
}

void schedule_mcck_handler(void)
{
	pcpu_ec_call(pcpu_devices + smp_processor_id(), ec_mcck_pending);
}

bool notrace arch_vcpu_is_preempted(int cpu)
{
	if (test_cpu_flag_of(CIF_ENABLED_WAIT, cpu))
		return false;
	if (pcpu_running(pcpu_devices + cpu))
		return false;
	return true;
}
EXPORT_SYMBOL(arch_vcpu_is_preempted);

void notrace smp_yield_cpu(int cpu)
{
	if (!MACHINE_HAS_DIAG9C)
		return;
	diag_stat_inc_norecursion(DIAG_STAT_X09C);
	asm volatile("diag %0,0,0x9c"
		     : : "d" (pcpu_devices[cpu].address));
}

/*
 * Send cpus emergency shutdown signal. This gives the cpus the
 * opportunity to complete outstanding interrupts.
 */
void notrace smp_emergency_stop(void)
{
	cpumask_t cpumask;
	u64 end;
	int cpu;

	cpumask_copy(&cpumask, cpu_online_mask);
	cpumask_clear_cpu(smp_processor_id(), &cpumask);

	end = get_tod_clock() + (1000000UL << 12);
	for_each_cpu(cpu, &cpumask) {
		struct pcpu *pcpu = pcpu_devices + cpu;
		set_bit(ec_stop_cpu, &pcpu->ec_mask);
		while (__pcpu_sigp(pcpu->address, SIGP_EMERGENCY_SIGNAL,
				   0, NULL) == SIGP_CC_BUSY &&
		       get_tod_clock() < end)
			cpu_relax();
	}
	while (get_tod_clock() < end) {
		for_each_cpu(cpu, &cpumask)
			if (pcpu_stopped(pcpu_devices + cpu))
				cpumask_clear_cpu(cpu, &cpumask);
		if (cpumask_empty(&cpumask))
			break;
		cpu_relax();
	}
}
NOKPROBE_SYMBOL(smp_emergency_stop);

/*
 * Stop all cpus but the current one.
 */
void smp_send_stop(void)
{
	int cpu;

	/* Disable all interrupts/machine checks */
	__load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT);
	trace_hardirqs_off();

	debug_set_critical();

	if (oops_in_progress)
		smp_emergency_stop();

	/* stop all processors */
	for_each_online_cpu(cpu) {
		if (cpu == smp_processor_id())
			continue;
		pcpu_sigp_retry(pcpu_devices + cpu, SIGP_STOP, 0);
		while (!pcpu_stopped(pcpu_devices + cpu))
			cpu_relax();
	}
}

/*
 * This is the main routine where commands issued by other
 * cpus are handled.
 */
static void smp_handle_ext_call(void)
{
	unsigned long bits;

	/* handle bit signal external calls */
	bits = xchg(&pcpu_devices[smp_processor_id()].ec_mask, 0);
	if (test_bit(ec_stop_cpu, &bits))
		smp_stop_cpu();
	if (test_bit(ec_schedule, &bits))
		scheduler_ipi();
	if (test_bit(ec_call_function_single, &bits))
		generic_smp_call_function_single_interrupt();
	if (test_bit(ec_mcck_pending, &bits))
		s390_handle_mcck();
}

static void do_ext_call_interrupt(struct ext_code ext_code,
				  unsigned int param32, unsigned long param64)
{
	inc_irq_stat(ext_code.code == 0x1202 ? IRQEXT_EXC : IRQEXT_EMS);
	smp_handle_ext_call();
}

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

	for_each_cpu(cpu, mask)
		pcpu_ec_call(pcpu_devices + cpu, ec_call_function_single);
}

void arch_send_call_function_single_ipi(int cpu)
{
	pcpu_ec_call(pcpu_devices + cpu, ec_call_function_single);
}

/*
 * 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)
{
	pcpu_ec_call(pcpu_devices + cpu, ec_schedule);
}

/*
 * parameter area for the set/clear control bit callbacks
 */
struct ec_creg_mask_parms {
	unsigned long orval;
	unsigned long andval;
	int cr;
};

/*
 * 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];

	__ctl_store(cregs, 0, 15);
	cregs[pp->cr] = (cregs[pp->cr] & pp->andval) | pp->orval;
	__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 = { 1UL << bit, -1UL, cr };

	on_each_cpu(smp_ctl_bit_callback, &parms, 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 = { 0, ~(1UL << bit), cr };

	on_each_cpu(smp_ctl_bit_callback, &parms, 1);
}
EXPORT_SYMBOL(smp_ctl_clear_bit);

#ifdef CONFIG_CRASH_DUMP

int smp_store_status(int cpu)
{
	struct pcpu *pcpu = pcpu_devices + cpu;
	unsigned long pa;

	pa = __pa(&pcpu->lowcore->floating_pt_save_area);
	if (__pcpu_sigp_relax(pcpu->address, SIGP_STORE_STATUS_AT_ADDRESS,
			      pa) != SIGP_CC_ORDER_CODE_ACCEPTED)
		return -EIO;
	if (!MACHINE_HAS_VX && !MACHINE_HAS_GS)
		return 0;
	pa = __pa(pcpu->lowcore->mcesad & MCESA_ORIGIN_MASK);
	if (MACHINE_HAS_GS)
		pa |= pcpu->lowcore->mcesad & MCESA_LC_MASK;
	if (__pcpu_sigp_relax(pcpu->address, SIGP_STORE_ADDITIONAL_STATUS,
			      pa) != SIGP_CC_ORDER_CODE_ACCEPTED)
		return -EIO;
	return 0;
}

/*
 * Collect CPU state of the previous, crashed system.
 * There are four cases:
 * 1) standard zfcp/nvme dump
 *    condition: OLDMEM_BASE == NULL && is_ipl_type_dump() == true
 *    The state for all CPUs except the boot CPU needs to be collected
 *    with sigp stop-and-store-status. The boot CPU state is located in
 *    the absolute lowcore of the memory stored in the HSA. The zcore code
 *    will copy the boot CPU state from the HSA.
 * 2) stand-alone kdump for SCSI/NVMe (zfcp/nvme dump with swapped memory)
 *    condition: OLDMEM_BASE != NULL && is_ipl_type_dump() == true
 *    The state for all CPUs except the boot CPU needs to be collected
 *    with sigp stop-and-store-status. The firmware or the boot-loader
 *    stored the registers of the boot CPU in the absolute lowcore in the
 *    memory of the old system.
 * 3) kdump and the old kernel did not store the CPU state,
 *    or stand-alone kdump for DASD
 *    condition: OLDMEM_BASE != NULL && !is_kdump_kernel()
 *    The state for all CPUs except the boot CPU needs to be collected
 *    with sigp stop-and-store-status. The kexec code or the boot-loader
 *    stored the registers of the boot CPU in the memory of the old system.
 * 4) kdump and the old kernel stored the CPU state
 *    condition: OLDMEM_BASE != NULL && is_kdump_kernel()
 *    This case does not exist for s390 anymore, setup_arch explicitly
 *    deactivates the elfcorehdr= kernel parameter
 */
static __init void smp_save_cpu_vxrs(struct save_area *sa, u16 addr,
				     bool is_boot_cpu, unsigned long page)
{
	__vector128 *vxrs = (__vector128 *) page;

	if (is_boot_cpu)
		vxrs = boot_cpu_vector_save_area;
	else
		__pcpu_sigp_relax(addr, SIGP_STORE_ADDITIONAL_STATUS, page);
	save_area_add_vxrs(sa, vxrs);
}

static __init void smp_save_cpu_regs(struct save_area *sa, u16 addr,
				     bool is_boot_cpu, unsigned long page)
{
	void *regs = (void *) page;

	if (is_boot_cpu)
		copy_oldmem_kernel(regs, (void *) __LC_FPREGS_SAVE_AREA, 512);
	else
		__pcpu_sigp_relax(addr, SIGP_STORE_STATUS_AT_ADDRESS, page);
	save_area_add_regs(sa, regs);
}

void __init smp_save_dump_cpus(void)
{
	int addr, boot_cpu_addr, max_cpu_addr;
	struct save_area *sa;
	unsigned long page;
	bool is_boot_cpu;

	if (!(OLDMEM_BASE || is_ipl_type_dump()))
		/* No previous system present, normal boot. */
		return;
	/* Allocate a page as dumping area for the store status sigps */
	page = memblock_phys_alloc_range(PAGE_SIZE, PAGE_SIZE, 0, 1UL << 31);
	if (!page)
		panic("ERROR: Failed to allocate %lx bytes below %lx\n",
		      PAGE_SIZE, 1UL << 31);

	/* Set multi-threading state to the previous system. */
	pcpu_set_smt(sclp.mtid_prev);
	boot_cpu_addr = stap();
	max_cpu_addr = SCLP_MAX_CORES << sclp.mtid_prev;
	for (addr = 0; addr <= max_cpu_addr; addr++) {
		if (__pcpu_sigp_relax(addr, SIGP_SENSE, 0) ==
		    SIGP_CC_NOT_OPERATIONAL)
			continue;
		is_boot_cpu = (addr == boot_cpu_addr);
		/* Allocate save area */
		sa = save_area_alloc(is_boot_cpu);
		if (!sa)
			panic("could not allocate memory for save area\n");
		if (MACHINE_HAS_VX)
			/* Get the vector registers */
			smp_save_cpu_vxrs(sa, addr, is_boot_cpu, page);
		/*
		 * For a zfcp/nvme dump OLDMEM_BASE == NULL and the registers
		 * of the boot CPU are stored in the HSA. To retrieve
		 * these registers an SCLP request is required which is
		 * done by drivers/s390/char/zcore.c:init_cpu_info()
		 */
		if (!is_boot_cpu || OLDMEM_BASE)
			/* Get the CPU registers */
			smp_save_cpu_regs(sa, addr, is_boot_cpu, page);
	}
	memblock_free(page, PAGE_SIZE);
	diag_dma_ops.diag308_reset();
	pcpu_set_smt(0);
}
#endif /* CONFIG_CRASH_DUMP */

void smp_cpu_set_polarization(int cpu, int val)
{
	pcpu_devices[cpu].polarization = val;
}

int smp_cpu_get_polarization(int cpu)
{
	return pcpu_devices[cpu].polarization;
}

int smp_cpu_get_cpu_address(int cpu)
{
	return pcpu_devices[cpu].address;
}

static void __ref smp_get_core_info(struct sclp_core_info *info, int early)
{
	static int use_sigp_detection;
	int address;

	if (use_sigp_detection || sclp_get_core_info(info, early)) {
		use_sigp_detection = 1;
		for (address = 0;
		     address < (SCLP_MAX_CORES << smp_cpu_mt_shift);
		     address += (1U << smp_cpu_mt_shift)) {
			if (__pcpu_sigp_relax(address, SIGP_SENSE, 0) ==
			    SIGP_CC_NOT_OPERATIONAL)
				continue;
			info->core[info->configured].core_id =
				address >> smp_cpu_mt_shift;
			info->configured++;
		}
		info->combined = info->configured;
	}
}

static int smp_add_present_cpu(int cpu);

static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail,
			bool configured, bool early)
{
	struct pcpu *pcpu;
	int cpu, nr, i;
	u16 address;

	nr = 0;
	if (sclp.has_core_type && core->type != boot_core_type)
		return nr;
	cpu = cpumask_first(avail);
	address = core->core_id << smp_cpu_mt_shift;
	for (i = 0; (i <= smp_cpu_mtid) && (cpu < nr_cpu_ids); i++) {
		if (pcpu_find_address(cpu_present_mask, address + i))
			continue;
		pcpu = pcpu_devices + cpu;
		pcpu->address = address + i;
		if (configured)
			pcpu->state = CPU_STATE_CONFIGURED;
		else
			pcpu->state = CPU_STATE_STANDBY;
		smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
		set_cpu_present(cpu, true);
		if (!early && smp_add_present_cpu(cpu) != 0)
			set_cpu_present(cpu, false);
		else
			nr++;
		cpumask_clear_cpu(cpu, avail);
		cpu = cpumask_next(cpu, avail);
	}
	return nr;
}

static int __smp_rescan_cpus(struct sclp_core_info *info, bool early)
{
	struct sclp_core_entry *core;
	cpumask_t avail;
	bool configured;
	u16 core_id;
	int nr, i;

	nr = 0;
	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
	/*
	 * Add IPL core first (which got logical CPU number 0) to make sure
	 * that all SMT threads get subsequent logical CPU numbers.
	 */
	if (early) {
		core_id = pcpu_devices[0].address >> smp_cpu_mt_shift;
		for (i = 0; i < info->configured; i++) {
			core = &info->core[i];
			if (core->core_id == core_id) {
				nr += smp_add_core(core, &avail, true, early);
				break;
			}
		}
	}
	for (i = 0; i < info->combined; i++) {
		configured = i < info->configured;
		nr += smp_add_core(&info->core[i], &avail, configured, early);
	}
	return nr;
}

void __init smp_detect_cpus(void)
{
	unsigned int cpu, mtid, c_cpus, s_cpus;
	struct sclp_core_info *info;
	u16 address;

	/* Get CPU information */
	info = memblock_alloc(sizeof(*info), 8);
	if (!info)
		panic("%s: Failed to allocate %zu bytes align=0x%x\n",
		      __func__, sizeof(*info), 8);
	smp_get_core_info(info, 1);
	/* Find boot CPU type */
	if (sclp.has_core_type) {
		address = stap();
		for (cpu = 0; cpu < info->combined; cpu++)
			if (info->core[cpu].core_id == address) {
				/* The boot cpu dictates the cpu type. */
				boot_core_type = info->core[cpu].type;
				break;
			}
		if (cpu >= info->combined)
			panic("Could not find boot CPU type");
	}

	/* Set multi-threading state for the current system */
	mtid = boot_core_type ? sclp.mtid : sclp.mtid_cp;
	mtid = (mtid < smp_max_threads) ? mtid : smp_max_threads - 1;
	pcpu_set_smt(mtid);

	/* Print number of CPUs */
	c_cpus = s_cpus = 0;
	for (cpu = 0; cpu < info->combined; cpu++) {
		if (sclp.has_core_type &&
		    info->core[cpu].type != boot_core_type)
			continue;
		if (cpu < info->configured)
			c_cpus += smp_cpu_mtid + 1;
		else
			s_cpus += smp_cpu_mtid + 1;
	}
	pr_info("%d configured CPUs, %d standby CPUs\n", c_cpus, s_cpus);

	/* Add CPUs present at boot */
	get_online_cpus();
	__smp_rescan_cpus(info, true);
	put_online_cpus();
	memblock_free_early((unsigned long)info, sizeof(*info));
}

static void smp_init_secondary(void)
{
	int cpu = smp_processor_id();

	S390_lowcore.last_update_clock = get_tod_clock();
	restore_access_regs(S390_lowcore.access_regs_save_area);
	set_cpu_flag(CIF_ASCE_PRIMARY);
	set_cpu_flag(CIF_ASCE_SECONDARY);
	cpu_init();
	preempt_disable();
	init_cpu_timer();
	vtime_init();
	pfault_init();
	notify_cpu_starting(cpu);
	if (topology_cpu_dedicated(cpu))
		set_cpu_flag(CIF_DEDICATED_CPU);
	else
		clear_cpu_flag(CIF_DEDICATED_CPU);
	set_cpu_online(cpu, true);
	update_cpu_masks();
	inc_irq_stat(CPU_RST);
	local_irq_enable();
	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}

/*
 *	Activate a secondary processor.
 */
static void __no_sanitize_address smp_start_secondary(void *cpuvoid)
{
	S390_lowcore.restart_stack = (unsigned long) restart_stack;
	S390_lowcore.restart_fn = (unsigned long) do_restart;
	S390_lowcore.restart_data = 0;
	S390_lowcore.restart_source = -1UL;
	__ctl_load(S390_lowcore.cregs_save_area, 0, 15);
	__load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT);
	CALL_ON_STACK_NORETURN(smp_init_secondary, S390_lowcore.kernel_stack);
}

/* Upping and downing of CPUs */
int __cpu_up(unsigned int cpu, struct task_struct *tidle)
{
	struct pcpu *pcpu;
	int base, i, rc;

	pcpu = pcpu_devices + cpu;
	if (pcpu->state != CPU_STATE_CONFIGURED)
		return -EIO;
	base = smp_get_base_cpu(cpu);
	for (i = 0; i <= smp_cpu_mtid; i++) {
		if (base + i < nr_cpu_ids)
			if (cpu_online(base + i))
				break;
	}
	/*
	 * If this is the first CPU of the core to get online
	 * do an initial CPU reset.
	 */
	if (i > smp_cpu_mtid &&
	    pcpu_sigp_retry(pcpu_devices + base, SIGP_INITIAL_CPU_RESET, 0) !=
	    SIGP_CC_ORDER_CODE_ACCEPTED)
		return -EIO;

	rc = pcpu_alloc_lowcore(pcpu, cpu);
	if (rc)
		return rc;
	pcpu_prepare_secondary(pcpu, cpu);
	pcpu_attach_task(pcpu, tidle);
	pcpu_start_fn(pcpu, smp_start_secondary, NULL);
	/* Wait until cpu puts itself in the online & active maps */
	while (!cpu_online(cpu))
		cpu_relax();
	return 0;
}

static unsigned int setup_possible_cpus __initdata;

static int __init _setup_possible_cpus(char *s)
{
	get_option(&s, &setup_possible_cpus);
	return 0;
}
early_param("possible_cpus", _setup_possible_cpus);

int __cpu_disable(void)
{
	unsigned long cregs[16];

	/* Handle possible pending IPIs */
	smp_handle_ext_call();
	set_cpu_online(smp_processor_id(), false);
	update_cpu_masks();
	/* Disable pseudo page faults on this cpu. */
	pfault_fini();
	/* Disable interrupt sources via control register. */
	__ctl_store(cregs, 0, 15);
	cregs[0]  &= ~0x0000ee70UL;	/* disable all external interrupts */
	cregs[6]  &= ~0xff000000UL;	/* disable all I/O interrupts */
	cregs[14] &= ~0x1f000000UL;	/* disable most machine checks */
	__ctl_load(cregs, 0, 15);
	clear_cpu_flag(CIF_NOHZ_DELAY);
	return 0;
}

void __cpu_die(unsigned int cpu)
{
	struct pcpu *pcpu;

	/* Wait until target cpu is down */
	pcpu = pcpu_devices + cpu;
	while (!pcpu_stopped(pcpu))
		cpu_relax();
	pcpu_free_lowcore(pcpu);
	cpumask_clear_cpu(cpu, mm_cpumask(&init_mm));
	cpumask_clear_cpu(cpu, &init_mm.context.cpu_attach_mask);
}

void __noreturn cpu_die(void)
{
	idle_task_exit();
	__bpon();
	pcpu_sigp_retry(pcpu_devices + smp_processor_id(), SIGP_STOP, 0);
	for (;;) ;
}

void __init smp_fill_possible_mask(void)
{
	unsigned int possible, sclp_max, cpu;

	sclp_max = max(sclp.mtid, sclp.mtid_cp) + 1;
	sclp_max = min(smp_max_threads, sclp_max);
	sclp_max = (sclp.max_cores * sclp_max) ?: nr_cpu_ids;
	possible = setup_possible_cpus ?: nr_cpu_ids;
	possible = min(possible, sclp_max);
	for (cpu = 0; cpu < possible && cpu < nr_cpu_ids; cpu++)
		set_cpu_possible(cpu, true);
}

void __init smp_prepare_cpus(unsigned int max_cpus)
{
	/* request the 0x1201 emergency signal external interrupt */
	if (register_external_irq(EXT_IRQ_EMERGENCY_SIG, do_ext_call_interrupt))
		panic("Couldn't request external interrupt 0x1201");
	/* request the 0x1202 external call external interrupt */
	if (register_external_irq(EXT_IRQ_EXTERNAL_CALL, do_ext_call_interrupt))
		panic("Couldn't request external interrupt 0x1202");
}

void __init smp_prepare_boot_cpu(void)
{
	struct pcpu *pcpu = pcpu_devices;

	WARN_ON(!cpu_present(0) || !cpu_online(0));
	pcpu->state = CPU_STATE_CONFIGURED;
	pcpu->lowcore = (struct lowcore *)(unsigned long) store_prefix();
	S390_lowcore.percpu_offset = __per_cpu_offset[0];
	smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN);
}

void __init smp_setup_processor_id(void)
{
	pcpu_devices[0].address = stap();
	S390_lowcore.cpu_nr = 0;
	S390_lowcore.spinlock_lockval = arch_spin_lockval(0);
	S390_lowcore.spinlock_index = 0;
}

/*
 * 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 ssize_t cpu_configure_show(struct device *dev,
				  struct device_attribute *attr, char *buf)
{
	ssize_t count;

	mutex_lock(&smp_cpu_state_mutex);
	count = sprintf(buf, "%d\n", pcpu_devices[dev->id].state);
	mutex_unlock(&smp_cpu_state_mutex);
	return count;
}

static ssize_t cpu_configure_store(struct device *dev,
				   struct device_attribute *attr,
				   const char *buf, size_t count)
{
	struct pcpu *pcpu;
	int cpu, val, rc, i;
	char delim;

	if (sscanf(buf, "%d %c", &val, &delim) != 1)
		return -EINVAL;
	if (val != 0 && val != 1)
		return -EINVAL;
	get_online_cpus();
	mutex_lock(&smp_cpu_state_mutex);
	rc = -EBUSY;
	/* disallow configuration changes of online cpus and cpu 0 */
	cpu = dev->id;
	cpu = smp_get_base_cpu(cpu);
	if (cpu == 0)
		goto out;
	for (i = 0; i <= smp_cpu_mtid; i++)
		if (cpu_online(cpu + i))
			goto out;
	pcpu = pcpu_devices + cpu;
	rc = 0;
	switch (val) {
	case 0:
		if (pcpu->state != CPU_STATE_CONFIGURED)
			break;
		rc = sclp_core_deconfigure(pcpu->address >> smp_cpu_mt_shift);
		if (rc)
			break;
		for (i = 0; i <= smp_cpu_mtid; i++) {
			if (cpu + i >= nr_cpu_ids || !cpu_present(cpu + i))
				continue;
			pcpu[i].state = CPU_STATE_STANDBY;
			smp_cpu_set_polarization(cpu + i,
						 POLARIZATION_UNKNOWN);
		}
		topology_expect_change();
		break;
	case 1:
		if (pcpu->state != CPU_STATE_STANDBY)
			break;
		rc = sclp_core_configure(pcpu->address >> smp_cpu_mt_shift);
		if (rc)
			break;
		for (i = 0; i <= smp_cpu_mtid; i++) {
			if (cpu + i >= nr_cpu_ids || !cpu_present(cpu + i))
				continue;
			pcpu[i].state = CPU_STATE_CONFIGURED;
			smp_cpu_set_polarization(cpu + i,
						 POLARIZATION_UNKNOWN);
		}
		topology_expect_change();
		break;
	default:
		break;
	}
out:
	mutex_unlock(&smp_cpu_state_mutex);
	put_online_cpus();
	return rc ? rc : count;
}
static DEVICE_ATTR(configure, 0644, cpu_configure_show, cpu_configure_store);

static ssize_t show_cpu_address(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", pcpu_devices[dev->id].address);
}
static DEVICE_ATTR(address, 0444, show_cpu_address, NULL);

static struct attribute *cpu_common_attrs[] = {
	&dev_attr_configure.attr,
	&dev_attr_address.attr,
	NULL,
};

static struct attribute_group cpu_common_attr_group = {
	.attrs = cpu_common_attrs,
};

static struct attribute *cpu_online_attrs[] = {
	&dev_attr_idle_count.attr,
	&dev_attr_idle_time_us.attr,
	NULL,
};

static struct attribute_group cpu_online_attr_group = {
	.attrs = cpu_online_attrs,
};

static int smp_cpu_online(unsigned int cpu)
{
	struct device *s = &per_cpu(cpu_device, cpu)->dev;

	return sysfs_create_group(&s->kobj, &cpu_online_attr_group);
}

static int smp_cpu_pre_down(unsigned int cpu)
{
	struct device *s = &per_cpu(cpu_device, cpu)->dev;

	sysfs_remove_group(&s->kobj, &cpu_online_attr_group);
	return 0;
}

static int smp_add_present_cpu(int cpu)
{
	struct device *s;
	struct cpu *c;
	int rc;

	c = kzalloc(sizeof(*c), GFP_KERNEL);
	if (!c)
		return -ENOMEM;
	per_cpu(cpu_device, cpu) = c;
	s = &c->dev;
	c->hotpluggable = 1;
	rc = register_cpu(c, cpu);
	if (rc)
		goto out;
	rc = sysfs_create_group(&s->kobj, &cpu_common_attr_group);
	if (rc)
		goto out_cpu;
	rc = topology_cpu_init(c);
	if (rc)
		goto out_topology;
	return 0;

out_topology:
	sysfs_remove_group(&s->kobj, &cpu_common_attr_group);
out_cpu:
	unregister_cpu(c);
out:
	return rc;
}

int __ref smp_rescan_cpus(void)
{
	struct sclp_core_info *info;
	int nr;

	info = kzalloc(sizeof(*info), GFP_KERNEL);
	if (!info)
		return -ENOMEM;
	smp_get_core_info(info, 0);
	get_online_cpus();
	mutex_lock(&smp_cpu_state_mutex);
	nr = __smp_rescan_cpus(info, false);
	mutex_unlock(&smp_cpu_state_mutex);
	put_online_cpus();
	kfree(info);
	if (nr)
		topology_schedule_update();
	return 0;
}

static ssize_t __ref rescan_store(struct device *dev,
				  struct device_attribute *attr,
				  const char *buf,
				  size_t count)
{
	int rc;

	rc = lock_device_hotplug_sysfs();
	if (rc)
		return rc;
	rc = smp_rescan_cpus();
	unlock_device_hotplug();
	return rc ? rc : count;
}
static DEVICE_ATTR_WO(rescan);

static int __init s390_smp_init(void)
{
	int cpu, rc = 0;

	rc = device_create_file(cpu_subsys.dev_root, &dev_attr_rescan);
	if (rc)
		return rc;
	for_each_present_cpu(cpu) {
		rc = smp_add_present_cpu(cpu);
		if (rc)
			goto out;
	}

	rc = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "s390/smp:online",
			       smp_cpu_online, smp_cpu_pre_down);
	rc = rc <= 0 ? rc : 0;
out:
	return rc;
}
subsys_initcall(s390_smp_init);