summaryrefslogtreecommitdiff
path: root/arch/sparc64/kernel/smp.c
blob: 16b8eca9754e71dbb89e7713be2e521bd0d16e26 (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
/* smp.c: Sparc64 SMP support.
 *
 * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/threads.h>
#include <linux/smp.h>
#include <linux/smp_lock.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/cache.h>
#include <linux/jiffies.h>
#include <linux/profile.h>
#include <linux/bootmem.h>

#include <asm/head.h>
#include <asm/ptrace.h>
#include <asm/atomic.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/cpudata.h>

#include <asm/irq.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/oplib.h>
#include <asm/uaccess.h>
#include <asm/timer.h>
#include <asm/starfire.h>
#include <asm/tlb.h>
#include <asm/sections.h>

extern void calibrate_delay(void);

/* Please don't make this stuff initdata!!!  --DaveM */
static unsigned char boot_cpu_id;

cpumask_t cpu_online_map __read_mostly = CPU_MASK_NONE;
cpumask_t phys_cpu_present_map __read_mostly = CPU_MASK_NONE;
static cpumask_t smp_commenced_mask;
static cpumask_t cpu_callout_map;

void smp_info(struct seq_file *m)
{
	int i;
	
	seq_printf(m, "State:\n");
	for (i = 0; i < NR_CPUS; i++) {
		if (cpu_online(i))
			seq_printf(m,
				   "CPU%d:\t\tonline\n", i);
	}
}

void smp_bogo(struct seq_file *m)
{
	int i;
	
	for (i = 0; i < NR_CPUS; i++)
		if (cpu_online(i))
			seq_printf(m,
				   "Cpu%dBogo\t: %lu.%02lu\n"
				   "Cpu%dClkTck\t: %016lx\n",
				   i, cpu_data(i).udelay_val / (500000/HZ),
				   (cpu_data(i).udelay_val / (5000/HZ)) % 100,
				   i, cpu_data(i).clock_tick);
}

void __init smp_store_cpu_info(int id)
{
	int cpu_node;

	/* multiplier and counter set by
	   smp_setup_percpu_timer()  */
	cpu_data(id).udelay_val			= loops_per_jiffy;

	cpu_find_by_mid(id, &cpu_node);
	cpu_data(id).clock_tick = prom_getintdefault(cpu_node,
						     "clock-frequency", 0);

	cpu_data(id).idle_volume		= 1;

	cpu_data(id).dcache_size = prom_getintdefault(cpu_node, "dcache-size",
						      16 * 1024);
	cpu_data(id).dcache_line_size =
		prom_getintdefault(cpu_node, "dcache-line-size", 32);
	cpu_data(id).icache_size = prom_getintdefault(cpu_node, "icache-size",
						      16 * 1024);
	cpu_data(id).icache_line_size =
		prom_getintdefault(cpu_node, "icache-line-size", 32);
	cpu_data(id).ecache_size = prom_getintdefault(cpu_node, "ecache-size",
						      4 * 1024 * 1024);
	cpu_data(id).ecache_line_size =
		prom_getintdefault(cpu_node, "ecache-line-size", 64);
	printk("CPU[%d]: Caches "
	       "D[sz(%d):line_sz(%d)] "
	       "I[sz(%d):line_sz(%d)] "
	       "E[sz(%d):line_sz(%d)]\n",
	       id,
	       cpu_data(id).dcache_size, cpu_data(id).dcache_line_size,
	       cpu_data(id).icache_size, cpu_data(id).icache_line_size,
	       cpu_data(id).ecache_size, cpu_data(id).ecache_line_size);
}

static void smp_setup_percpu_timer(void);

static volatile unsigned long callin_flag = 0;

void __init smp_callin(void)
{
	int cpuid = hard_smp_processor_id();

	__local_per_cpu_offset = __per_cpu_offset(cpuid);

	__flush_tlb_all();

	smp_setup_percpu_timer();

	if (cheetah_pcache_forced_on)
		cheetah_enable_pcache();

	local_irq_enable();

	calibrate_delay();
	smp_store_cpu_info(cpuid);
	callin_flag = 1;
	__asm__ __volatile__("membar #Sync\n\t"
			     "flush  %%g6" : : : "memory");

	/* Clear this or we will die instantly when we
	 * schedule back to this idler...
	 */
	current_thread_info()->new_child = 0;

	/* Attach to the address space of init_task. */
	atomic_inc(&init_mm.mm_count);
	current->active_mm = &init_mm;

	while (!cpu_isset(cpuid, smp_commenced_mask))
		rmb();

	cpu_set(cpuid, cpu_online_map);

	/* idle thread is expected to have preempt disabled */
	preempt_disable();
}

void cpu_panic(void)
{
	printk("CPU[%d]: Returns from cpu_idle!\n", smp_processor_id());
	panic("SMP bolixed\n");
}

static unsigned long current_tick_offset __read_mostly;

/* This tick register synchronization scheme is taken entirely from
 * the ia64 port, see arch/ia64/kernel/smpboot.c for details and credit.
 *
 * The only change I've made is to rework it so that the master
 * initiates the synchonization instead of the slave. -DaveM
 */

#define MASTER	0
#define SLAVE	(SMP_CACHE_BYTES/sizeof(unsigned long))

#define NUM_ROUNDS	64	/* magic value */
#define NUM_ITERS	5	/* likewise */

static DEFINE_SPINLOCK(itc_sync_lock);
static unsigned long go[SLAVE + 1];

#define DEBUG_TICK_SYNC	0

static inline long get_delta (long *rt, long *master)
{
	unsigned long best_t0 = 0, best_t1 = ~0UL, best_tm = 0;
	unsigned long tcenter, t0, t1, tm;
	unsigned long i;

	for (i = 0; i < NUM_ITERS; i++) {
		t0 = tick_ops->get_tick();
		go[MASTER] = 1;
		membar_storeload();
		while (!(tm = go[SLAVE]))
			rmb();
		go[SLAVE] = 0;
		wmb();
		t1 = tick_ops->get_tick();

		if (t1 - t0 < best_t1 - best_t0)
			best_t0 = t0, best_t1 = t1, best_tm = tm;
	}

	*rt = best_t1 - best_t0;
	*master = best_tm - best_t0;

	/* average best_t0 and best_t1 without overflow: */
	tcenter = (best_t0/2 + best_t1/2);
	if (best_t0 % 2 + best_t1 % 2 == 2)
		tcenter++;
	return tcenter - best_tm;
}

void smp_synchronize_tick_client(void)
{
	long i, delta, adj, adjust_latency = 0, done = 0;
	unsigned long flags, rt, master_time_stamp, bound;
#if DEBUG_TICK_SYNC
	struct {
		long rt;	/* roundtrip time */
		long master;	/* master's timestamp */
		long diff;	/* difference between midpoint and master's timestamp */
		long lat;	/* estimate of itc adjustment latency */
	} t[NUM_ROUNDS];
#endif

	go[MASTER] = 1;

	while (go[MASTER])
		rmb();

	local_irq_save(flags);
	{
		for (i = 0; i < NUM_ROUNDS; i++) {
			delta = get_delta(&rt, &master_time_stamp);
			if (delta == 0) {
				done = 1;	/* let's lock on to this... */
				bound = rt;
			}

			if (!done) {
				if (i > 0) {
					adjust_latency += -delta;
					adj = -delta + adjust_latency/4;
				} else
					adj = -delta;

				tick_ops->add_tick(adj, current_tick_offset);
			}
#if DEBUG_TICK_SYNC
			t[i].rt = rt;
			t[i].master = master_time_stamp;
			t[i].diff = delta;
			t[i].lat = adjust_latency/4;
#endif
		}
	}
	local_irq_restore(flags);

#if DEBUG_TICK_SYNC
	for (i = 0; i < NUM_ROUNDS; i++)
		printk("rt=%5ld master=%5ld diff=%5ld adjlat=%5ld\n",
		       t[i].rt, t[i].master, t[i].diff, t[i].lat);
#endif

	printk(KERN_INFO "CPU %d: synchronized TICK with master CPU (last diff %ld cycles,"
	       "maxerr %lu cycles)\n", smp_processor_id(), delta, rt);
}

static void smp_start_sync_tick_client(int cpu);

static void smp_synchronize_one_tick(int cpu)
{
	unsigned long flags, i;

	go[MASTER] = 0;

	smp_start_sync_tick_client(cpu);

	/* wait for client to be ready */
	while (!go[MASTER])
		rmb();

	/* now let the client proceed into his loop */
	go[MASTER] = 0;
	membar_storeload();

	spin_lock_irqsave(&itc_sync_lock, flags);
	{
		for (i = 0; i < NUM_ROUNDS*NUM_ITERS; i++) {
			while (!go[MASTER])
				rmb();
			go[MASTER] = 0;
			wmb();
			go[SLAVE] = tick_ops->get_tick();
			membar_storeload();
		}
	}
	spin_unlock_irqrestore(&itc_sync_lock, flags);
}

extern unsigned long sparc64_cpu_startup;

/* The OBP cpu startup callback truncates the 3rd arg cookie to
 * 32-bits (I think) so to be safe we have it read the pointer
 * contained here so we work on >4GB machines. -DaveM
 */
static struct thread_info *cpu_new_thread = NULL;

static int __devinit smp_boot_one_cpu(unsigned int cpu)
{
	unsigned long entry =
		(unsigned long)(&sparc64_cpu_startup);
	unsigned long cookie =
		(unsigned long)(&cpu_new_thread);
	struct task_struct *p;
	int timeout, ret, cpu_node;

	p = fork_idle(cpu);
	callin_flag = 0;
	cpu_new_thread = task_thread_info(p);
	cpu_set(cpu, cpu_callout_map);

	cpu_find_by_mid(cpu, &cpu_node);
	prom_startcpu(cpu_node, entry, cookie);

	for (timeout = 0; timeout < 5000000; timeout++) {
		if (callin_flag)
			break;
		udelay(100);
	}
	if (callin_flag) {
		ret = 0;
	} else {
		printk("Processor %d is stuck.\n", cpu);
		cpu_clear(cpu, cpu_callout_map);
		ret = -ENODEV;
	}
	cpu_new_thread = NULL;

	return ret;
}

static void spitfire_xcall_helper(u64 data0, u64 data1, u64 data2, u64 pstate, unsigned long cpu)
{
	u64 result, target;
	int stuck, tmp;

	if (this_is_starfire) {
		/* map to real upaid */
		cpu = (((cpu & 0x3c) << 1) |
			((cpu & 0x40) >> 4) |
			(cpu & 0x3));
	}

	target = (cpu << 14) | 0x70;
again:
	/* Ok, this is the real Spitfire Errata #54.
	 * One must read back from a UDB internal register
	 * after writes to the UDB interrupt dispatch, but
	 * before the membar Sync for that write.
	 * So we use the high UDB control register (ASI 0x7f,
	 * ADDR 0x20) for the dummy read. -DaveM
	 */
	tmp = 0x40;
	__asm__ __volatile__(
	"wrpr	%1, %2, %%pstate\n\t"
	"stxa	%4, [%0] %3\n\t"
	"stxa	%5, [%0+%8] %3\n\t"
	"add	%0, %8, %0\n\t"
	"stxa	%6, [%0+%8] %3\n\t"
	"membar	#Sync\n\t"
	"stxa	%%g0, [%7] %3\n\t"
	"membar	#Sync\n\t"
	"mov	0x20, %%g1\n\t"
	"ldxa	[%%g1] 0x7f, %%g0\n\t"
	"membar	#Sync"
	: "=r" (tmp)
	: "r" (pstate), "i" (PSTATE_IE), "i" (ASI_INTR_W),
	  "r" (data0), "r" (data1), "r" (data2), "r" (target),
	  "r" (0x10), "0" (tmp)
        : "g1");

	/* NOTE: PSTATE_IE is still clear. */
	stuck = 100000;
	do {
		__asm__ __volatile__("ldxa [%%g0] %1, %0"
			: "=r" (result)
			: "i" (ASI_INTR_DISPATCH_STAT));
		if (result == 0) {
			__asm__ __volatile__("wrpr %0, 0x0, %%pstate"
					     : : "r" (pstate));
			return;
		}
		stuck -= 1;
		if (stuck == 0)
			break;
	} while (result & 0x1);
	__asm__ __volatile__("wrpr %0, 0x0, %%pstate"
			     : : "r" (pstate));
	if (stuck == 0) {
		printk("CPU[%d]: mondo stuckage result[%016lx]\n",
		       smp_processor_id(), result);
	} else {
		udelay(2);
		goto again;
	}
}

static __inline__ void spitfire_xcall_deliver(u64 data0, u64 data1, u64 data2, cpumask_t mask)
{
	u64 pstate;
	int i;

	__asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate));
	for_each_cpu_mask(i, mask)
		spitfire_xcall_helper(data0, data1, data2, pstate, i);
}

/* Cheetah now allows to send the whole 64-bytes of data in the interrupt
 * packet, but we have no use for that.  However we do take advantage of
 * the new pipelining feature (ie. dispatch to multiple cpus simultaneously).
 */
static void cheetah_xcall_deliver(u64 data0, u64 data1, u64 data2, cpumask_t mask)
{
	u64 pstate, ver;
	int nack_busy_id, is_jbus;

	if (cpus_empty(mask))
		return;

	/* Unfortunately, someone at Sun had the brilliant idea to make the
	 * busy/nack fields hard-coded by ITID number for this Ultra-III
	 * derivative processor.
	 */
	__asm__ ("rdpr %%ver, %0" : "=r" (ver));
	is_jbus = ((ver >> 32) == __JALAPENO_ID ||
		   (ver >> 32) == __SERRANO_ID);

	__asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate));

retry:
	__asm__ __volatile__("wrpr %0, %1, %%pstate\n\t"
			     : : "r" (pstate), "i" (PSTATE_IE));

	/* Setup the dispatch data registers. */
	__asm__ __volatile__("stxa	%0, [%3] %6\n\t"
			     "stxa	%1, [%4] %6\n\t"
			     "stxa	%2, [%5] %6\n\t"
			     "membar	#Sync\n\t"
			     : /* no outputs */
			     : "r" (data0), "r" (data1), "r" (data2),
			       "r" (0x40), "r" (0x50), "r" (0x60),
			       "i" (ASI_INTR_W));

	nack_busy_id = 0;
	{
		int i;

		for_each_cpu_mask(i, mask) {
			u64 target = (i << 14) | 0x70;

			if (!is_jbus)
				target |= (nack_busy_id << 24);
			__asm__ __volatile__(
				"stxa	%%g0, [%0] %1\n\t"
				"membar	#Sync\n\t"
				: /* no outputs */
				: "r" (target), "i" (ASI_INTR_W));
			nack_busy_id++;
		}
	}

	/* Now, poll for completion. */
	{
		u64 dispatch_stat;
		long stuck;

		stuck = 100000 * nack_busy_id;
		do {
			__asm__ __volatile__("ldxa	[%%g0] %1, %0"
					     : "=r" (dispatch_stat)
					     : "i" (ASI_INTR_DISPATCH_STAT));
			if (dispatch_stat == 0UL) {
				__asm__ __volatile__("wrpr %0, 0x0, %%pstate"
						     : : "r" (pstate));
				return;
			}
			if (!--stuck)
				break;
		} while (dispatch_stat & 0x5555555555555555UL);

		__asm__ __volatile__("wrpr %0, 0x0, %%pstate"
				     : : "r" (pstate));

		if ((dispatch_stat & ~(0x5555555555555555UL)) == 0) {
			/* Busy bits will not clear, continue instead
			 * of freezing up on this cpu.
			 */
			printk("CPU[%d]: mondo stuckage result[%016lx]\n",
			       smp_processor_id(), dispatch_stat);
		} else {
			int i, this_busy_nack = 0;

			/* Delay some random time with interrupts enabled
			 * to prevent deadlock.
			 */
			udelay(2 * nack_busy_id);

			/* Clear out the mask bits for cpus which did not
			 * NACK us.
			 */
			for_each_cpu_mask(i, mask) {
				u64 check_mask;

				if (is_jbus)
					check_mask = (0x2UL << (2*i));
				else
					check_mask = (0x2UL <<
						      this_busy_nack);
				if ((dispatch_stat & check_mask) == 0)
					cpu_clear(i, mask);
				this_busy_nack += 2;
			}

			goto retry;
		}
	}
}

/* Send cross call to all processors mentioned in MASK
 * except self.
 */
static void smp_cross_call_masked(unsigned long *func, u32 ctx, u64 data1, u64 data2, cpumask_t mask)
{
	u64 data0 = (((u64)ctx)<<32 | (((u64)func) & 0xffffffff));
	int this_cpu = get_cpu();

	cpus_and(mask, mask, cpu_online_map);
	cpu_clear(this_cpu, mask);

	if (tlb_type == spitfire)
		spitfire_xcall_deliver(data0, data1, data2, mask);
	else
		cheetah_xcall_deliver(data0, data1, data2, mask);
	/* NOTE: Caller runs local copy on master. */

	put_cpu();
}

extern unsigned long xcall_sync_tick;

static void smp_start_sync_tick_client(int cpu)
{
	cpumask_t mask = cpumask_of_cpu(cpu);

	smp_cross_call_masked(&xcall_sync_tick,
			      0, 0, 0, mask);
}

/* Send cross call to all processors except self. */
#define smp_cross_call(func, ctx, data1, data2) \
	smp_cross_call_masked(func, ctx, data1, data2, cpu_online_map)

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

static DEFINE_SPINLOCK(call_lock);
static struct call_data_struct *call_data;

extern unsigned long xcall_call_function;

/*
 * You must not call this function with disabled interrupts or from a
 * hardware interrupt handler or from a bottom half handler.
 */
static int smp_call_function_mask(void (*func)(void *info), void *info,
				  int nonatomic, int wait, cpumask_t mask)
{
	struct call_data_struct data;
	int cpus = cpus_weight(mask) - 1;
	long timeout;

	if (!cpus)
		return 0;

	/* Can deadlock when called with interrupts disabled */
	WARN_ON(irqs_disabled());

	data.func = func;
	data.info = info;
	atomic_set(&data.finished, 0);
	data.wait = wait;

	spin_lock(&call_lock);

	call_data = &data;

	smp_cross_call_masked(&xcall_call_function, 0, 0, 0, mask);

	/* 
	 * Wait for other cpus to complete function or at
	 * least snap the call data.
	 */
	timeout = 1000000;
	while (atomic_read(&data.finished) != cpus) {
		if (--timeout <= 0)
			goto out_timeout;
		barrier();
		udelay(1);
	}

	spin_unlock(&call_lock);

	return 0;

out_timeout:
	spin_unlock(&call_lock);
	printk("XCALL: Remote cpus not responding, ncpus=%ld finished=%ld\n",
	       (long) num_online_cpus() - 1L,
	       (long) atomic_read(&data.finished));
	return 0;
}

int smp_call_function(void (*func)(void *info), void *info,
		      int nonatomic, int wait)
{
	return smp_call_function_mask(func, info, nonatomic, wait,
				      cpu_online_map);
}

void smp_call_function_client(int irq, struct pt_regs *regs)
{
	void (*func) (void *info) = call_data->func;
	void *info = call_data->info;

	clear_softint(1 << irq);
	if (call_data->wait) {
		/* let initiator proceed only after completion */
		func(info);
		atomic_inc(&call_data->finished);
	} else {
		/* let initiator proceed after getting data */
		atomic_inc(&call_data->finished);
		func(info);
	}
}

static void tsb_sync(void *info)
{
	struct mm_struct *mm = info;

	if (current->active_mm == mm)
		tsb_context_switch(mm);
}

void smp_tsb_sync(struct mm_struct *mm)
{
	smp_call_function_mask(tsb_sync, mm, 0, 1, mm->cpu_vm_mask);
}

extern unsigned long xcall_flush_tlb_mm;
extern unsigned long xcall_flush_tlb_pending;
extern unsigned long xcall_flush_tlb_kernel_range;
extern unsigned long xcall_report_regs;
extern unsigned long xcall_receive_signal;

#ifdef DCACHE_ALIASING_POSSIBLE
extern unsigned long xcall_flush_dcache_page_cheetah;
#endif
extern unsigned long xcall_flush_dcache_page_spitfire;

#ifdef CONFIG_DEBUG_DCFLUSH
extern atomic_t dcpage_flushes;
extern atomic_t dcpage_flushes_xcall;
#endif

static __inline__ void __local_flush_dcache_page(struct page *page)
{
#ifdef DCACHE_ALIASING_POSSIBLE
	__flush_dcache_page(page_address(page),
			    ((tlb_type == spitfire) &&
			     page_mapping(page) != NULL));
#else
	if (page_mapping(page) != NULL &&
	    tlb_type == spitfire)
		__flush_icache_page(__pa(page_address(page)));
#endif
}

void smp_flush_dcache_page_impl(struct page *page, int cpu)
{
	cpumask_t mask = cpumask_of_cpu(cpu);
	int this_cpu = get_cpu();

#ifdef CONFIG_DEBUG_DCFLUSH
	atomic_inc(&dcpage_flushes);
#endif
	if (cpu == this_cpu) {
		__local_flush_dcache_page(page);
	} else if (cpu_online(cpu)) {
		void *pg_addr = page_address(page);
		u64 data0;

		if (tlb_type == spitfire) {
			data0 =
				((u64)&xcall_flush_dcache_page_spitfire);
			if (page_mapping(page) != NULL)
				data0 |= ((u64)1 << 32);
			spitfire_xcall_deliver(data0,
					       __pa(pg_addr),
					       (u64) pg_addr,
					       mask);
		} else {
#ifdef DCACHE_ALIASING_POSSIBLE
			data0 =
				((u64)&xcall_flush_dcache_page_cheetah);
			cheetah_xcall_deliver(data0,
					      __pa(pg_addr),
					      0, mask);
#endif
		}
#ifdef CONFIG_DEBUG_DCFLUSH
		atomic_inc(&dcpage_flushes_xcall);
#endif
	}

	put_cpu();
}

void flush_dcache_page_all(struct mm_struct *mm, struct page *page)
{
	void *pg_addr = page_address(page);
	cpumask_t mask = cpu_online_map;
	u64 data0;
	int this_cpu = get_cpu();

	cpu_clear(this_cpu, mask);

#ifdef CONFIG_DEBUG_DCFLUSH
	atomic_inc(&dcpage_flushes);
#endif
	if (cpus_empty(mask))
		goto flush_self;
	if (tlb_type == spitfire) {
		data0 = ((u64)&xcall_flush_dcache_page_spitfire);
		if (page_mapping(page) != NULL)
			data0 |= ((u64)1 << 32);
		spitfire_xcall_deliver(data0,
				       __pa(pg_addr),
				       (u64) pg_addr,
				       mask);
	} else {
#ifdef DCACHE_ALIASING_POSSIBLE
		data0 = ((u64)&xcall_flush_dcache_page_cheetah);
		cheetah_xcall_deliver(data0,
				      __pa(pg_addr),
				      0, mask);
#endif
	}
#ifdef CONFIG_DEBUG_DCFLUSH
	atomic_inc(&dcpage_flushes_xcall);
#endif
 flush_self:
	__local_flush_dcache_page(page);

	put_cpu();
}

void smp_receive_signal(int cpu)
{
	cpumask_t mask = cpumask_of_cpu(cpu);

	if (cpu_online(cpu)) {
		u64 data0 = (((u64)&xcall_receive_signal) & 0xffffffff);

		if (tlb_type == spitfire)
			spitfire_xcall_deliver(data0, 0, 0, mask);
		else
			cheetah_xcall_deliver(data0, 0, 0, mask);
	}
}

void smp_receive_signal_client(int irq, struct pt_regs *regs)
{
	/* Just return, rtrap takes care of the rest. */
	clear_softint(1 << irq);
}

void smp_report_regs(void)
{
	smp_cross_call(&xcall_report_regs, 0, 0, 0);
}

/* We know that the window frames of the user have been flushed
 * to the stack before we get here because all callers of us
 * are flush_tlb_*() routines, and these run after flush_cache_*()
 * which performs the flushw.
 *
 * The SMP TLB coherency scheme we use works as follows:
 *
 * 1) mm->cpu_vm_mask is a bit mask of which cpus an address
 *    space has (potentially) executed on, this is the heuristic
 *    we use to avoid doing cross calls.
 *
 *    Also, for flushing from kswapd and also for clones, we
 *    use cpu_vm_mask as the list of cpus to make run the TLB.
 *
 * 2) TLB context numbers are shared globally across all processors
 *    in the system, this allows us to play several games to avoid
 *    cross calls.
 *
 *    One invariant is that when a cpu switches to a process, and
 *    that processes tsk->active_mm->cpu_vm_mask does not have the
 *    current cpu's bit set, that tlb context is flushed locally.
 *
 *    If the address space is non-shared (ie. mm->count == 1) we avoid
 *    cross calls when we want to flush the currently running process's
 *    tlb state.  This is done by clearing all cpu bits except the current
 *    processor's in current->active_mm->cpu_vm_mask and performing the
 *    flush locally only.  This will force any subsequent cpus which run
 *    this task to flush the context from the local tlb if the process
 *    migrates to another cpu (again).
 *
 * 3) For shared address spaces (threads) and swapping we bite the
 *    bullet for most cases and perform the cross call (but only to
 *    the cpus listed in cpu_vm_mask).
 *
 *    The performance gain from "optimizing" away the cross call for threads is
 *    questionable (in theory the big win for threads is the massive sharing of
 *    address space state across processors).
 */

/* This currently is only used by the hugetlb arch pre-fault
 * hook on UltraSPARC-III+ and later when changing the pagesize
 * bits of the context register for an address space.
 */
void smp_flush_tlb_mm(struct mm_struct *mm)
{
	u32 ctx = CTX_HWBITS(mm->context);
	int cpu = get_cpu();

	if (atomic_read(&mm->mm_users) == 1) {
		mm->cpu_vm_mask = cpumask_of_cpu(cpu);
		goto local_flush_and_out;
	}

	smp_cross_call_masked(&xcall_flush_tlb_mm,
			      ctx, 0, 0,
			      mm->cpu_vm_mask);

local_flush_and_out:
	__flush_tlb_mm(ctx, SECONDARY_CONTEXT);

	put_cpu();
}

void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long *vaddrs)
{
	u32 ctx = CTX_HWBITS(mm->context);
	int cpu = get_cpu();

	if (mm == current->active_mm && atomic_read(&mm->mm_users) == 1)
		mm->cpu_vm_mask = cpumask_of_cpu(cpu);
	else
		smp_cross_call_masked(&xcall_flush_tlb_pending,
				      ctx, nr, (unsigned long) vaddrs,
				      mm->cpu_vm_mask);

	__flush_tlb_pending(ctx, nr, vaddrs);

	put_cpu();
}

void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
	start &= PAGE_MASK;
	end    = PAGE_ALIGN(end);
	if (start != end) {
		smp_cross_call(&xcall_flush_tlb_kernel_range,
			       0, start, end);

		__flush_tlb_kernel_range(start, end);
	}
}

/* CPU capture. */
/* #define CAPTURE_DEBUG */
extern unsigned long xcall_capture;

static atomic_t smp_capture_depth = ATOMIC_INIT(0);
static atomic_t smp_capture_registry = ATOMIC_INIT(0);
static unsigned long penguins_are_doing_time;

void smp_capture(void)
{
	int result = atomic_add_ret(1, &smp_capture_depth);

	if (result == 1) {
		int ncpus = num_online_cpus();

#ifdef CAPTURE_DEBUG
		printk("CPU[%d]: Sending penguins to jail...",
		       smp_processor_id());
#endif
		penguins_are_doing_time = 1;
		membar_storestore_loadstore();
		atomic_inc(&smp_capture_registry);
		smp_cross_call(&xcall_capture, 0, 0, 0);
		while (atomic_read(&smp_capture_registry) != ncpus)
			rmb();
#ifdef CAPTURE_DEBUG
		printk("done\n");
#endif
	}
}

void smp_release(void)
{
	if (atomic_dec_and_test(&smp_capture_depth)) {
#ifdef CAPTURE_DEBUG
		printk("CPU[%d]: Giving pardon to "
		       "imprisoned penguins\n",
		       smp_processor_id());
#endif
		penguins_are_doing_time = 0;
		membar_storeload_storestore();
		atomic_dec(&smp_capture_registry);
	}
}

/* Imprisoned penguins run with %pil == 15, but PSTATE_IE set, so they
 * can service tlb flush xcalls...
 */
extern void prom_world(int);

void smp_penguin_jailcell(int irq, struct pt_regs *regs)
{
	clear_softint(1 << irq);

	preempt_disable();

	__asm__ __volatile__("flushw");
	prom_world(1);
	atomic_inc(&smp_capture_registry);
	membar_storeload_storestore();
	while (penguins_are_doing_time)
		rmb();
	atomic_dec(&smp_capture_registry);
	prom_world(0);

	preempt_enable();
}

#define prof_multiplier(__cpu)		cpu_data(__cpu).multiplier
#define prof_counter(__cpu)		cpu_data(__cpu).counter

void smp_percpu_timer_interrupt(struct pt_regs *regs)
{
	unsigned long compare, tick, pstate;
	int cpu = smp_processor_id();
	int user = user_mode(regs);

	/*
	 * Check for level 14 softint.
	 */
	{
		unsigned long tick_mask = tick_ops->softint_mask;

		if (!(get_softint() & tick_mask)) {
			extern void handler_irq(int, struct pt_regs *);

			handler_irq(14, regs);
			return;
		}
		clear_softint(tick_mask);
	}

	do {
		profile_tick(CPU_PROFILING, regs);
		if (!--prof_counter(cpu)) {
			irq_enter();

			if (cpu == boot_cpu_id) {
				kstat_this_cpu.irqs[0]++;
				timer_tick_interrupt(regs);
			}

			update_process_times(user);

			irq_exit();

			prof_counter(cpu) = prof_multiplier(cpu);
		}

		/* Guarantee that the following sequences execute
		 * uninterrupted.
		 */
		__asm__ __volatile__("rdpr	%%pstate, %0\n\t"
				     "wrpr	%0, %1, %%pstate"
				     : "=r" (pstate)
				     : "i" (PSTATE_IE));

		compare = tick_ops->add_compare(current_tick_offset);
		tick = tick_ops->get_tick();

		/* Restore PSTATE_IE. */
		__asm__ __volatile__("wrpr	%0, 0x0, %%pstate"
				     : /* no outputs */
				     : "r" (pstate));
	} while (time_after_eq(tick, compare));
}

static void __init smp_setup_percpu_timer(void)
{
	int cpu = smp_processor_id();
	unsigned long pstate;

	prof_counter(cpu) = prof_multiplier(cpu) = 1;

	/* Guarantee that the following sequences execute
	 * uninterrupted.
	 */
	__asm__ __volatile__("rdpr	%%pstate, %0\n\t"
			     "wrpr	%0, %1, %%pstate"
			     : "=r" (pstate)
			     : "i" (PSTATE_IE));

	tick_ops->init_tick(current_tick_offset);

	/* Restore PSTATE_IE. */
	__asm__ __volatile__("wrpr	%0, 0x0, %%pstate"
			     : /* no outputs */
			     : "r" (pstate));
}

void __init smp_tick_init(void)
{
	boot_cpu_id = hard_smp_processor_id();
	current_tick_offset = timer_tick_offset;

	cpu_set(boot_cpu_id, cpu_online_map);
	prof_counter(boot_cpu_id) = prof_multiplier(boot_cpu_id) = 1;
}

/* /proc/profile writes can call this, don't __init it please. */
static DEFINE_SPINLOCK(prof_setup_lock);

int setup_profiling_timer(unsigned int multiplier)
{
	unsigned long flags;
	int i;

	if ((!multiplier) || (timer_tick_offset / multiplier) < 1000)
		return -EINVAL;

	spin_lock_irqsave(&prof_setup_lock, flags);
	for (i = 0; i < NR_CPUS; i++)
		prof_multiplier(i) = multiplier;
	current_tick_offset = (timer_tick_offset / multiplier);
	spin_unlock_irqrestore(&prof_setup_lock, flags);

	return 0;
}

/* Constrain the number of cpus to max_cpus.  */
void __init smp_prepare_cpus(unsigned int max_cpus)
{
	if (num_possible_cpus() > max_cpus) {
		int instance, mid;

		instance = 0;
		while (!cpu_find_by_instance(instance, NULL, &mid)) {
			if (mid != boot_cpu_id) {
				cpu_clear(mid, phys_cpu_present_map);
				if (num_possible_cpus() <= max_cpus)
					break;
			}
			instance++;
		}
	}

	smp_store_cpu_info(boot_cpu_id);
}

/* Set this up early so that things like the scheduler can init
 * properly.  We use the same cpu mask for both the present and
 * possible cpu map.
 */
void __init smp_setup_cpu_possible_map(void)
{
	int instance, mid;

	instance = 0;
	while (!cpu_find_by_instance(instance, NULL, &mid)) {
		if (mid < NR_CPUS)
			cpu_set(mid, phys_cpu_present_map);
		instance++;
	}
}

void __devinit smp_prepare_boot_cpu(void)
{
	int cpu = hard_smp_processor_id();

	if (cpu >= NR_CPUS) {
		prom_printf("Serious problem, boot cpu id >= NR_CPUS\n");
		prom_halt();
	}

	current_thread_info()->cpu = cpu;
	__local_per_cpu_offset = __per_cpu_offset(cpu);

	cpu_set(smp_processor_id(), cpu_online_map);
	cpu_set(smp_processor_id(), phys_cpu_present_map);
}

int __devinit __cpu_up(unsigned int cpu)
{
	int ret = smp_boot_one_cpu(cpu);

	if (!ret) {
		cpu_set(cpu, smp_commenced_mask);
		while (!cpu_isset(cpu, cpu_online_map))
			mb();
		if (!cpu_isset(cpu, cpu_online_map)) {
			ret = -ENODEV;
		} else {
			smp_synchronize_one_tick(cpu);
		}
	}
	return ret;
}

void __init smp_cpus_done(unsigned int max_cpus)
{
	unsigned long bogosum = 0;
	int i;

	for (i = 0; i < NR_CPUS; i++) {
		if (cpu_online(i))
			bogosum += cpu_data(i).udelay_val;
	}
	printk("Total of %ld processors activated "
	       "(%lu.%02lu BogoMIPS).\n",
	       (long) num_online_cpus(),
	       bogosum/(500000/HZ),
	       (bogosum/(5000/HZ))%100);
}

void smp_send_reschedule(int cpu)
{
	smp_receive_signal(cpu);
}

/* This is a nop because we capture all other cpus
 * anyways when making the PROM active.
 */
void smp_send_stop(void)
{
}

unsigned long __per_cpu_base __read_mostly;
unsigned long __per_cpu_shift __read_mostly;

EXPORT_SYMBOL(__per_cpu_base);
EXPORT_SYMBOL(__per_cpu_shift);

void __init setup_per_cpu_areas(void)
{
	unsigned long goal, size, i;
	char *ptr;

	/* Copy section for each CPU (we discard the original) */
	goal = ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES);
#ifdef CONFIG_MODULES
	if (goal < PERCPU_ENOUGH_ROOM)
		goal = PERCPU_ENOUGH_ROOM;
#endif
	__per_cpu_shift = 0;
	for (size = 1UL; size < goal; size <<= 1UL)
		__per_cpu_shift++;

	ptr = alloc_bootmem(size * NR_CPUS);

	__per_cpu_base = ptr - __per_cpu_start;

	for (i = 0; i < NR_CPUS; i++, ptr += size)
		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
}