aboutsummaryrefslogtreecommitdiff
path: root/arch/x86_64/kernel/smpboot.c
blob: 4e9755179ecf57022bcb8e4e6adaa76d62612010 (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
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
/*
 *	x86 SMP booting functions
 *
 *	(c) 1995 Alan Cox, Building #3 <alan@redhat.com>
 *	(c) 1998, 1999, 2000 Ingo Molnar <mingo@redhat.com>
 *	Copyright 2001 Andi Kleen, SuSE Labs.
 *
 *	Much of the core SMP work is based on previous work by Thomas Radke, to
 *	whom a great many thanks are extended.
 *
 *	Thanks to Intel for making available several different Pentium,
 *	Pentium Pro and Pentium-II/Xeon MP machines.
 *	Original development of Linux SMP code supported by Caldera.
 *
 *	This code is released under the GNU General Public License version 2
 *
 *	Fixes
 *		Felix Koop	:	NR_CPUS used properly
 *		Jose Renau	:	Handle single CPU case.
 *		Alan Cox	:	By repeated request 8) - Total BogoMIP report.
 *		Greg Wright	:	Fix for kernel stacks panic.
 *		Erich Boleyn	:	MP v1.4 and additional changes.
 *	Matthias Sattler	:	Changes for 2.1 kernel map.
 *	Michel Lespinasse	:	Changes for 2.1 kernel map.
 *	Michael Chastain	:	Change trampoline.S to gnu as.
 *		Alan Cox	:	Dumb bug: 'B' step PPro's are fine
 *		Ingo Molnar	:	Added APIC timers, based on code
 *					from Jose Renau
 *		Ingo Molnar	:	various cleanups and rewrites
 *		Tigran Aivazian	:	fixed "0.00 in /proc/uptime on SMP" bug.
 *	Maciej W. Rozycki	:	Bits for genuine 82489DX APICs
 *	Andi Kleen		:	Changed for SMP boot into long mode.
 *		Rusty Russell	:	Hacked into shape for new "hotplug" boot process.
 *      Andi Kleen              :       Converted to new state machine.
 *					Various cleanups.
 *					Probably mostly hotplug CPU ready now.
 *	Ashok Raj			: CPU hotplug support
 */


#include <linux/config.h>
#include <linux/init.h>

#include <linux/mm.h>
#include <linux/kernel_stat.h>
#include <linux/smp_lock.h>
#include <linux/bootmem.h>
#include <linux/thread_info.h>
#include <linux/module.h>

#include <linux/delay.h>
#include <linux/mc146818rtc.h>
#include <asm/mtrr.h>
#include <asm/pgalloc.h>
#include <asm/desc.h>
#include <asm/kdebug.h>
#include <asm/tlbflush.h>
#include <asm/proto.h>
#include <asm/nmi.h>
#include <asm/irq.h>
#include <asm/hw_irq.h>
#include <asm/numa.h>

/* Number of siblings per CPU package */
int smp_num_siblings = 1;
EXPORT_SYMBOL(smp_num_siblings);

/* Last level cache ID of each logical CPU */
u8 cpu_llc_id[NR_CPUS] __cpuinitdata  = {[0 ... NR_CPUS-1] = BAD_APICID};
EXPORT_SYMBOL(cpu_llc_id);

/* Bitmask of currently online CPUs */
cpumask_t cpu_online_map __read_mostly;

EXPORT_SYMBOL(cpu_online_map);

/*
 * Private maps to synchronize booting between AP and BP.
 * Probably not needed anymore, but it makes for easier debugging. -AK
 */
cpumask_t cpu_callin_map;
cpumask_t cpu_callout_map;
EXPORT_SYMBOL(cpu_callout_map);

cpumask_t cpu_possible_map;
EXPORT_SYMBOL(cpu_possible_map);

/* Per CPU bogomips and other parameters */
struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned;
EXPORT_SYMBOL(cpu_data);

/* Set when the idlers are all forked */
int smp_threads_ready;

/* representing HT siblings of each logical CPU */
cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(cpu_sibling_map);

/* representing HT and core siblings of each logical CPU */
cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(cpu_core_map);

/*
 * Trampoline 80x86 program as an array.
 */

extern unsigned char trampoline_data[];
extern unsigned char trampoline_end[];

/* State of each CPU */
DEFINE_PER_CPU(int, cpu_state) = { 0 };

/*
 * Store all idle threads, this can be reused instead of creating
 * a new thread. Also avoids complicated thread destroy functionality
 * for idle threads.
 */
struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;

#define get_idle_for_cpu(x)     (idle_thread_array[(x)])
#define set_idle_for_cpu(x,p)   (idle_thread_array[(x)] = (p))

/*
 * Currently trivial. Write the real->protected mode
 * bootstrap into the page concerned. The caller
 * has made sure it's suitably aligned.
 */

static unsigned long __cpuinit setup_trampoline(void)
{
	void *tramp = __va(SMP_TRAMPOLINE_BASE); 
	memcpy(tramp, trampoline_data, trampoline_end - trampoline_data);
	return virt_to_phys(tramp);
}

/*
 * The bootstrap kernel entry code has set these up. Save them for
 * a given CPU
 */

static void __cpuinit smp_store_cpu_info(int id)
{
	struct cpuinfo_x86 *c = cpu_data + id;

	*c = boot_cpu_data;
	identify_cpu(c);
	print_cpu_info(c);
}

/*
 * New Funky TSC sync algorithm borrowed from IA64.
 * Main advantage is that it doesn't reset the TSCs fully and
 * in general looks more robust and it works better than my earlier
 * attempts. I believe it was written by David Mosberger. Some minor
 * adjustments for x86-64 by me -AK
 *
 * Original comment reproduced below.
 *
 * Synchronize TSC of the current (slave) CPU with the TSC of the
 * MASTER CPU (normally the time-keeper CPU).  We use a closed loop to
 * eliminate the possibility of unaccounted-for errors (such as
 * getting a machine check in the middle of a calibration step).  The
 * basic idea is for the slave to ask the master what itc value it has
 * and to read its own itc before and after the master responds.  Each
 * iteration gives us three timestamps:
 *
 *	slave		master
 *
 *	t0 ---\
 *             ---\
 *		   --->
 *			tm
 *		   /---
 *	       /---
 *	t1 <---
 *
 *
 * The goal is to adjust the slave's TSC such that tm falls exactly
 * half-way between t0 and t1.  If we achieve this, the clocks are
 * synchronized provided the interconnect between the slave and the
 * master is symmetric.  Even if the interconnect were asymmetric, we
 * would still know that the synchronization error is smaller than the
 * roundtrip latency (t0 - t1).
 *
 * When the interconnect is quiet and symmetric, this lets us
 * synchronize the TSC to within one or two cycles.  However, we can
 * only *guarantee* that the synchronization is accurate to within a
 * round-trip time, which is typically in the range of several hundred
 * cycles (e.g., ~500 cycles).  In practice, this means that the TSCs
 * are usually almost perfectly synchronized, but we shouldn't assume
 * that the accuracy is much better than half a micro second or so.
 *
 * [there are other errors like the latency of RDTSC and of the
 * WRMSR. These can also account to hundreds of cycles. So it's
 * probably worse. It claims 153 cycles error on a dual Opteron,
 * but I suspect the numbers are actually somewhat worse -AK]
 */

#define MASTER	0
#define SLAVE	(SMP_CACHE_BYTES/8)

/* Intentionally don't use cpu_relax() while TSC synchronization
   because we don't want to go into funky power save modi or cause
   hypervisors to schedule us away.  Going to sleep would likely affect
   latency and low latency is the primary objective here. -AK */
#define no_cpu_relax() barrier()

static __cpuinitdata DEFINE_SPINLOCK(tsc_sync_lock);
static volatile __cpuinitdata unsigned long go[SLAVE + 1];
static int notscsync __cpuinitdata;

#undef DEBUG_TSC_SYNC

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

/* Callback on boot CPU */
static __cpuinit void sync_master(void *arg)
{
	unsigned long flags, i;

	go[MASTER] = 0;

	local_irq_save(flags);
	{
		for (i = 0; i < NUM_ROUNDS*NUM_ITERS; ++i) {
			while (!go[MASTER])
				no_cpu_relax();
			go[MASTER] = 0;
			rdtscll(go[SLAVE]);
		}
	}
	local_irq_restore(flags);
}

/*
 * Return the number of cycles by which our tsc differs from the tsc
 * on the master (time-keeper) CPU.  A positive number indicates our
 * tsc is ahead of the master, negative that it is behind.
 */
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;
	int i;

	for (i = 0; i < NUM_ITERS; ++i) {
		rdtscll(t0);
		go[MASTER] = 1;
		while (!(tm = go[SLAVE]))
			no_cpu_relax();
		go[SLAVE] = 0;
		rdtscll(t1);

		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;
}

static __cpuinit void sync_tsc(unsigned int master)
{
	int i, done = 0;
	long delta, adj, adjust_latency = 0;
	unsigned long flags, rt, master_time_stamp, bound;
#ifdef DEBUG_TSC_SYNC
	static struct syncdebug {
		long rt;	/* roundtrip time */
		long master;	/* master's timestamp */
		long diff;	/* difference between midpoint and master's timestamp */
		long lat;	/* estimate of tsc adjustment latency */
	} t[NUM_ROUNDS] __cpuinitdata;
#endif

	printk(KERN_INFO "CPU %d: Syncing TSC to CPU %u.\n",
		smp_processor_id(), master);

	go[MASTER] = 1;

	/* It is dangerous to broadcast IPI as cpus are coming up,
	 * as they may not be ready to accept them.  So since
	 * we only need to send the ipi to the boot cpu direct
	 * the message, and avoid the race.
	 */
	smp_call_function_single(master, sync_master, NULL, 1, 0);

	while (go[MASTER])	/* wait for master to be ready */
		no_cpu_relax();

	spin_lock_irqsave(&tsc_sync_lock, 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) {
				unsigned long t;
				if (i > 0) {
					adjust_latency += -delta;
					adj = -delta + adjust_latency/4;
				} else
					adj = -delta;

				rdtscll(t);
				wrmsrl(MSR_IA32_TSC, t + adj);
			}
#ifdef DEBUG_TSC_SYNC
			t[i].rt = rt;
			t[i].master = master_time_stamp;
			t[i].diff = delta;
			t[i].lat = adjust_latency/4;
#endif
		}
	}
	spin_unlock_irqrestore(&tsc_sync_lock, flags);

#ifdef DEBUG_TSC_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 TSC with CPU %u (last diff %ld cycles, "
	       "maxerr %lu cycles)\n",
	       smp_processor_id(), master, delta, rt);
}

static void __cpuinit tsc_sync_wait(void)
{
	/*
	 * When the CPU has synchronized TSCs assume the BIOS
  	 * or the hardware already synced.  Otherwise we could
	 * mess up a possible perfect synchronization with a
	 * not-quite-perfect algorithm.
	 */
	if (notscsync || !cpu_has_tsc || !unsynchronized_tsc())
		return;
	sync_tsc(0);
}

static __init int notscsync_setup(char *s)
{
	notscsync = 1;
	return 1;
}
__setup("notscsync", notscsync_setup);

static atomic_t init_deasserted __cpuinitdata;

/*
 * Report back to the Boot Processor.
 * Running on AP.
 */
void __cpuinit smp_callin(void)
{
	int cpuid, phys_id;
	unsigned long timeout;

	/*
	 * If waken up by an INIT in an 82489DX configuration
	 * we may get here before an INIT-deassert IPI reaches
	 * our local APIC.  We have to wait for the IPI or we'll
	 * lock up on an APIC access.
	 */
	while (!atomic_read(&init_deasserted))
		cpu_relax();

	/*
	 * (This works even if the APIC is not enabled.)
	 */
	phys_id = GET_APIC_ID(apic_read(APIC_ID));
	cpuid = smp_processor_id();
	if (cpu_isset(cpuid, cpu_callin_map)) {
		panic("smp_callin: phys CPU#%d, CPU#%d already present??\n",
					phys_id, cpuid);
	}
	Dprintk("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id);

	/*
	 * STARTUP IPIs are fragile beasts as they might sometimes
	 * trigger some glue motherboard logic. Complete APIC bus
	 * silence for 1 second, this overestimates the time the
	 * boot CPU is spending to send the up to 2 STARTUP IPIs
	 * by a factor of two. This should be enough.
	 */

	/*
	 * Waiting 2s total for startup (udelay is not yet working)
	 */
	timeout = jiffies + 2*HZ;
	while (time_before(jiffies, timeout)) {
		/*
		 * Has the boot CPU finished it's STARTUP sequence?
		 */
		if (cpu_isset(cpuid, cpu_callout_map))
			break;
		cpu_relax();
	}

	if (!time_before(jiffies, timeout)) {
		panic("smp_callin: CPU%d started up but did not get a callout!\n",
			cpuid);
	}

	/*
	 * the boot CPU has finished the init stage and is spinning
	 * on callin_map until we finish. We are free to set up this
	 * CPU, first the APIC. (this is probably redundant on most
	 * boards)
	 */

	Dprintk("CALLIN, before setup_local_APIC().\n");
	setup_local_APIC();

	/*
	 * Get our bogomips.
 	 *
 	 * Need to enable IRQs because it can take longer and then
	 * the NMI watchdog might kill us.
	 */
	local_irq_enable();
	calibrate_delay();
	local_irq_disable();
	Dprintk("Stack at about %p\n",&cpuid);

	disable_APIC_timer();

	/*
	 * Save our processor parameters
	 */
 	smp_store_cpu_info(cpuid);

	/*
	 * Allow the master to continue.
	 */
	cpu_set(cpuid, cpu_callin_map);
}

/* maps the cpu to the sched domain representing multi-core */
cpumask_t cpu_coregroup_map(int cpu)
{
	struct cpuinfo_x86 *c = cpu_data + cpu;
	/*
	 * For perf, we return last level cache shared map.
	 * TBD: when power saving sched policy is added, we will return
	 *      cpu_core_map when power saving policy is enabled
	 */
	return c->llc_shared_map;
}

/* representing cpus for which sibling maps can be computed */
static cpumask_t cpu_sibling_setup_map;

static inline void set_cpu_sibling_map(int cpu)
{
	int i;
	struct cpuinfo_x86 *c = cpu_data;

	cpu_set(cpu, cpu_sibling_setup_map);

	if (smp_num_siblings > 1) {
		for_each_cpu_mask(i, cpu_sibling_setup_map) {
			if (c[cpu].phys_proc_id == c[i].phys_proc_id &&
			    c[cpu].cpu_core_id == c[i].cpu_core_id) {
				cpu_set(i, cpu_sibling_map[cpu]);
				cpu_set(cpu, cpu_sibling_map[i]);
				cpu_set(i, cpu_core_map[cpu]);
				cpu_set(cpu, cpu_core_map[i]);
				cpu_set(i, c[cpu].llc_shared_map);
				cpu_set(cpu, c[i].llc_shared_map);
			}
		}
	} else {
		cpu_set(cpu, cpu_sibling_map[cpu]);
	}

	cpu_set(cpu, c[cpu].llc_shared_map);

	if (current_cpu_data.x86_max_cores == 1) {
		cpu_core_map[cpu] = cpu_sibling_map[cpu];
		c[cpu].booted_cores = 1;
		return;
	}

	for_each_cpu_mask(i, cpu_sibling_setup_map) {
		if (cpu_llc_id[cpu] != BAD_APICID &&
		    cpu_llc_id[cpu] == cpu_llc_id[i]) {
			cpu_set(i, c[cpu].llc_shared_map);
			cpu_set(cpu, c[i].llc_shared_map);
		}
		if (c[cpu].phys_proc_id == c[i].phys_proc_id) {
			cpu_set(i, cpu_core_map[cpu]);
			cpu_set(cpu, cpu_core_map[i]);
			/*
			 *  Does this new cpu bringup a new core?
			 */
			if (cpus_weight(cpu_sibling_map[cpu]) == 1) {
				/*
				 * for each core in package, increment
				 * the booted_cores for this new cpu
				 */
				if (first_cpu(cpu_sibling_map[i]) == i)
					c[cpu].booted_cores++;
				/*
				 * increment the core count for all
				 * the other cpus in this package
				 */
				if (i != cpu)
					c[i].booted_cores++;
			} else if (i != cpu && !c[cpu].booted_cores)
				c[cpu].booted_cores = c[i].booted_cores;
		}
	}
}

/*
 * Setup code on secondary processor (after comming out of the trampoline)
 */
void __cpuinit start_secondary(void)
{
	/*
	 * Dont put anything before smp_callin(), SMP
	 * booting is too fragile that we want to limit the
	 * things done here to the most necessary things.
	 */
	cpu_init();
	preempt_disable();
	smp_callin();

	/* otherwise gcc will move up the smp_processor_id before the cpu_init */
	barrier();

	Dprintk("cpu %d: setting up apic clock\n", smp_processor_id()); 	
	setup_secondary_APIC_clock();

	Dprintk("cpu %d: enabling apic timer\n", smp_processor_id());

	if (nmi_watchdog == NMI_IO_APIC) {
		disable_8259A_irq(0);
		enable_NMI_through_LVT0(NULL);
		enable_8259A_irq(0);
	}

	enable_APIC_timer();

	/*
	 * The sibling maps must be set before turing the online map on for
	 * this cpu
	 */
	set_cpu_sibling_map(smp_processor_id());

	/* 
  	 * Wait for TSC sync to not schedule things before.
	 * We still process interrupts, which could see an inconsistent
	 * time in that window unfortunately. 
	 * Do this here because TSC sync has global unprotected state.
 	 */
	tsc_sync_wait();

	/*
	 * We need to hold call_lock, so there is no inconsistency
	 * between the time smp_call_function() determines number of
	 * IPI receipients, and the time when the determination is made
	 * for which cpus receive the IPI in genapic_flat.c. Holding this
	 * lock helps us to not include this cpu in a currently in progress
	 * smp_call_function().
	 */
	lock_ipi_call_lock();

	/*
	 * Allow the master to continue.
	 */
	cpu_set(smp_processor_id(), cpu_online_map);
	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
	unlock_ipi_call_lock();

	cpu_idle();
}

extern volatile unsigned long init_rsp;
extern void (*initial_code)(void);

#ifdef APIC_DEBUG
static void inquire_remote_apic(int apicid)
{
	unsigned i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 };
	char *names[] = { "ID", "VERSION", "SPIV" };
	int timeout, status;

	printk(KERN_INFO "Inquiring remote APIC #%d...\n", apicid);

	for (i = 0; i < sizeof(regs) / sizeof(*regs); i++) {
		printk("... APIC #%d %s: ", apicid, names[i]);

		/*
		 * Wait for idle.
		 */
		apic_wait_icr_idle();

		apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(apicid));
		apic_write(APIC_ICR, APIC_DM_REMRD | regs[i]);

		timeout = 0;
		do {
			udelay(100);
			status = apic_read(APIC_ICR) & APIC_ICR_RR_MASK;
		} while (status == APIC_ICR_RR_INPROG && timeout++ < 1000);

		switch (status) {
		case APIC_ICR_RR_VALID:
			status = apic_read(APIC_RRR);
			printk("%08x\n", status);
			break;
		default:
			printk("failed\n");
		}
	}
}
#endif

/*
 * Kick the secondary to wake up.
 */
static int __cpuinit wakeup_secondary_via_INIT(int phys_apicid, unsigned int start_rip)
{
	unsigned long send_status = 0, accept_status = 0;
	int maxlvt, timeout, num_starts, j;

	Dprintk("Asserting INIT.\n");

	/*
	 * Turn INIT on target chip
	 */
	apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));

	/*
	 * Send IPI
	 */
	apic_write(APIC_ICR, APIC_INT_LEVELTRIG | APIC_INT_ASSERT
				| APIC_DM_INIT);

	Dprintk("Waiting for send to finish...\n");
	timeout = 0;
	do {
		Dprintk("+");
		udelay(100);
		send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
	} while (send_status && (timeout++ < 1000));

	mdelay(10);

	Dprintk("Deasserting INIT.\n");

	/* Target chip */
	apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));

	/* Send IPI */
	apic_write(APIC_ICR, APIC_INT_LEVELTRIG | APIC_DM_INIT);

	Dprintk("Waiting for send to finish...\n");
	timeout = 0;
	do {
		Dprintk("+");
		udelay(100);
		send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
	} while (send_status && (timeout++ < 1000));

	mb();
	atomic_set(&init_deasserted, 1);

	num_starts = 2;

	/*
	 * Run STARTUP IPI loop.
	 */
	Dprintk("#startup loops: %d.\n", num_starts);

	maxlvt = get_maxlvt();

	for (j = 1; j <= num_starts; j++) {
		Dprintk("Sending STARTUP #%d.\n",j);
		apic_write(APIC_ESR, 0);
		apic_read(APIC_ESR);
		Dprintk("After apic_write.\n");

		/*
		 * STARTUP IPI
		 */

		/* Target chip */
		apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));

		/* Boot on the stack */
		/* Kick the second */
		apic_write(APIC_ICR, APIC_DM_STARTUP | (start_rip >> 12));

		/*
		 * Give the other CPU some time to accept the IPI.
		 */
		udelay(300);

		Dprintk("Startup point 1.\n");

		Dprintk("Waiting for send to finish...\n");
		timeout = 0;
		do {
			Dprintk("+");
			udelay(100);
			send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY;
		} while (send_status && (timeout++ < 1000));

		/*
		 * Give the other CPU some time to accept the IPI.
		 */
		udelay(200);
		/*
		 * Due to the Pentium erratum 3AP.
		 */
		if (maxlvt > 3) {
			apic_write(APIC_ESR, 0);
		}
		accept_status = (apic_read(APIC_ESR) & 0xEF);
		if (send_status || accept_status)
			break;
	}
	Dprintk("After Startup.\n");

	if (send_status)
		printk(KERN_ERR "APIC never delivered???\n");
	if (accept_status)
		printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status);

	return (send_status | accept_status);
}

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

void do_fork_idle(void *_c_idle)
{
	struct create_idle *c_idle = _c_idle;

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

/*
 * Boot one CPU.
 */
static int __cpuinit do_boot_cpu(int cpu, int apicid)
{
	unsigned long boot_error;
	int timeout;
	unsigned long start_rip;
	struct create_idle c_idle = {
		.cpu = cpu,
		.done = COMPLETION_INITIALIZER(c_idle.done),
	};
	DECLARE_WORK(work, do_fork_idle, &c_idle);

	/* allocate memory for gdts of secondary cpus. Hotplug is considered */
	if (!cpu_gdt_descr[cpu].address &&
		!(cpu_gdt_descr[cpu].address = get_zeroed_page(GFP_KERNEL))) {
		printk(KERN_ERR "Failed to allocate GDT for CPU %d\n", cpu);
		return -1;
	}

	/* Allocate node local memory for AP pdas */
	if (cpu_pda(cpu) == &boot_cpu_pda[cpu]) {
		struct x8664_pda *newpda, *pda;
		int node = cpu_to_node(cpu);
		pda = cpu_pda(cpu);
		newpda = kmalloc_node(sizeof (struct x8664_pda), GFP_ATOMIC,
				      node);
		if (newpda) {
			memcpy(newpda, pda, sizeof (struct x8664_pda));
			cpu_pda(cpu) = newpda;
		} else
			printk(KERN_ERR
		"Could not allocate node local PDA for CPU %d on node %d\n",
				cpu, node);
	}


	alternatives_smp_switch(1);

	c_idle.idle = get_idle_for_cpu(cpu);

	if (c_idle.idle) {
		c_idle.idle->thread.rsp = (unsigned long) (((struct pt_regs *)
			(THREAD_SIZE +  task_stack_page(c_idle.idle))) - 1);
		init_idle(c_idle.idle, cpu);
		goto do_rest;
	}

	/*
	 * During cold boot process, keventd thread is not spun up yet.
	 * When we do cpu hot-add, we create idle threads on the fly, we should
	 * not acquire any attributes from the calling context. Hence the clean
	 * way to create kernel_threads() is to do that from keventd().
	 * We do the current_is_keventd() due to the fact that ACPI notifier
	 * was also queuing to keventd() and when the caller is already running
	 * in context of keventd(), we would end up with locking up the keventd
	 * thread.
	 */
	if (!keventd_up() || current_is_keventd())
		work.func(work.data);
	else {
		schedule_work(&work);
		wait_for_completion(&c_idle.done);
	}

	if (IS_ERR(c_idle.idle)) {
		printk("failed fork for CPU %d\n", cpu);
		return PTR_ERR(c_idle.idle);
	}

	set_idle_for_cpu(cpu, c_idle.idle);

do_rest:

	cpu_pda(cpu)->pcurrent = c_idle.idle;

	start_rip = setup_trampoline();

	init_rsp = c_idle.idle->thread.rsp;
	per_cpu(init_tss,cpu).rsp0 = init_rsp;
	initial_code = start_secondary;
	clear_tsk_thread_flag(c_idle.idle, TIF_FORK);

	printk(KERN_INFO "Booting processor %d/%d APIC 0x%x\n", cpu,
		cpus_weight(cpu_present_map),
		apicid);

	/*
	 * This grunge runs the startup process for
	 * the targeted processor.
	 */

	atomic_set(&init_deasserted, 0);

	Dprintk("Setting warm reset code and vector.\n");

	CMOS_WRITE(0xa, 0xf);
	local_flush_tlb();
	Dprintk("1.\n");
	*((volatile unsigned short *) phys_to_virt(0x469)) = start_rip >> 4;
	Dprintk("2.\n");
	*((volatile unsigned short *) phys_to_virt(0x467)) = start_rip & 0xf;
	Dprintk("3.\n");

	/*
	 * Be paranoid about clearing APIC errors.
	 */
	apic_write(APIC_ESR, 0);
	apic_read(APIC_ESR);

	/*
	 * Status is now clean
	 */
	boot_error = 0;

	/*
	 * Starting actual IPI sequence...
	 */
	boot_error = wakeup_secondary_via_INIT(apicid, start_rip);

	if (!boot_error) {
		/*
		 * allow APs to start initializing.
		 */
		Dprintk("Before Callout %d.\n", cpu);
		cpu_set(cpu, cpu_callout_map);
		Dprintk("After Callout %d.\n", cpu);

		/*
		 * Wait 5s total for a response
		 */
		for (timeout = 0; timeout < 50000; timeout++) {
			if (cpu_isset(cpu, cpu_callin_map))
				break;	/* It has booted */
			udelay(100);
		}

		if (cpu_isset(cpu, cpu_callin_map)) {
			/* number CPUs logically, starting from 1 (BSP is 0) */
			Dprintk("CPU has booted.\n");
		} else {
			boot_error = 1;
			if (*((volatile unsigned char *)phys_to_virt(SMP_TRAMPOLINE_BASE))
					== 0xA5)
				/* trampoline started but...? */
				printk("Stuck ??\n");
			else
				/* trampoline code not run */
				printk("Not responding.\n");
#ifdef APIC_DEBUG
			inquire_remote_apic(apicid);
#endif
		}
	}
	if (boot_error) {
		cpu_clear(cpu, cpu_callout_map); /* was set here (do_boot_cpu()) */
		clear_bit(cpu, &cpu_initialized); /* was set by cpu_init() */
		clear_node_cpumask(cpu); /* was set by numa_add_cpu */
		cpu_clear(cpu, cpu_present_map);
		cpu_clear(cpu, cpu_possible_map);
		x86_cpu_to_apicid[cpu] = BAD_APICID;
		x86_cpu_to_log_apicid[cpu] = BAD_APICID;
		return -EIO;
	}

	return 0;
}

cycles_t cacheflush_time;
unsigned long cache_decay_ticks;

/*
 * Cleanup possible dangling ends...
 */
static __cpuinit void smp_cleanup_boot(void)
{
	/*
	 * Paranoid:  Set warm reset code and vector here back
	 * to default values.
	 */
	CMOS_WRITE(0, 0xf);

	/*
	 * Reset trampoline flag
	 */
	*((volatile int *) phys_to_virt(0x467)) = 0;
}

/*
 * Fall back to non SMP mode after errors.
 *
 * RED-PEN audit/test this more. I bet there is more state messed up here.
 */
static __init void disable_smp(void)
{
	cpu_present_map = cpumask_of_cpu(0);
	cpu_possible_map = cpumask_of_cpu(0);
	if (smp_found_config)
		phys_cpu_present_map = physid_mask_of_physid(boot_cpu_id);
	else
		phys_cpu_present_map = physid_mask_of_physid(0);
	cpu_set(0, cpu_sibling_map[0]);
	cpu_set(0, cpu_core_map[0]);
}

#ifdef CONFIG_HOTPLUG_CPU

int additional_cpus __initdata = -1;

/*
 * cpu_possible_map should be static, it cannot change as cpu's
 * are onlined, or offlined. The reason is per-cpu data-structures
 * are allocated by some modules at init time, and dont expect to
 * do this dynamically on cpu arrival/departure.
 * cpu_present_map on the other hand can change dynamically.
 * In case when cpu_hotplug is not compiled, then we resort to current
 * behaviour, which is cpu_possible == cpu_present.
 * - Ashok Raj
 *
 * Three ways to find out the number of additional hotplug CPUs:
 * - If the BIOS specified disabled CPUs in ACPI/mptables use that.
 * - The user can overwrite it with additional_cpus=NUM
 * - Otherwise don't reserve additional CPUs.
 * We do this because additional CPUs waste a lot of memory.
 * -AK
 */
__init void prefill_possible_map(void)
{
	int i;
	int possible;

 	if (additional_cpus == -1) {
 		if (disabled_cpus > 0)
 			additional_cpus = disabled_cpus;
 		else
			additional_cpus = 0;
 	}
	possible = num_processors + additional_cpus;
	if (possible > NR_CPUS) 
		possible = NR_CPUS;

	printk(KERN_INFO "SMP: Allowing %d CPUs, %d hotplug CPUs\n",
		possible,
	        max_t(int, possible - num_processors, 0));

	for (i = 0; i < possible; i++)
		cpu_set(i, cpu_possible_map);
}
#endif

/*
 * Various sanity checks.
 */
static int __init smp_sanity_check(unsigned max_cpus)
{
	if (!physid_isset(hard_smp_processor_id(), phys_cpu_present_map)) {
		printk("weird, boot CPU (#%d) not listed by the BIOS.\n",
		       hard_smp_processor_id());
		physid_set(hard_smp_processor_id(), phys_cpu_present_map);
	}

	/*
	 * If we couldn't find an SMP configuration at boot time,
	 * get out of here now!
	 */
	if (!smp_found_config) {
		printk(KERN_NOTICE "SMP motherboard not detected.\n");
		disable_smp();
		if (APIC_init_uniprocessor())
			printk(KERN_NOTICE "Local APIC not detected."
					   " Using dummy APIC emulation.\n");
		return -1;
	}

	/*
	 * Should not be necessary because the MP table should list the boot
	 * CPU too, but we do it for the sake of robustness anyway.
	 */
	if (!physid_isset(boot_cpu_id, phys_cpu_present_map)) {
		printk(KERN_NOTICE "weird, boot CPU (#%d) not listed by the BIOS.\n",
								 boot_cpu_id);
		physid_set(hard_smp_processor_id(), phys_cpu_present_map);
	}

	/*
	 * If we couldn't find a local APIC, then get out of here now!
	 */
	if (!cpu_has_apic) {
		printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n",
			boot_cpu_id);
		printk(KERN_ERR "... forcing use of dummy APIC emulation. (tell your hw vendor)\n");
		nr_ioapics = 0;
		return -1;
	}

	/*
	 * If SMP should be disabled, then really disable it!
	 */
	if (!max_cpus) {
		printk(KERN_INFO "SMP mode deactivated, forcing use of dummy APIC emulation.\n");
		nr_ioapics = 0;
		return -1;
	}

	return 0;
}

/*
 * Prepare for SMP bootup.  The MP table or ACPI has been read
 * earlier.  Just do some sanity checking here and enable APIC mode.
 */
void __init smp_prepare_cpus(unsigned int max_cpus)
{
	nmi_watchdog_default();
	current_cpu_data = boot_cpu_data;
	current_thread_info()->cpu = 0;  /* needed? */
	set_cpu_sibling_map(0);

	if (smp_sanity_check(max_cpus) < 0) {
		printk(KERN_INFO "SMP disabled\n");
		disable_smp();
		return;
	}


	/*
	 * Switch from PIC to APIC mode.
	 */
	connect_bsp_APIC();
	setup_local_APIC();

	if (GET_APIC_ID(apic_read(APIC_ID)) != boot_cpu_id) {
		panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
		      GET_APIC_ID(apic_read(APIC_ID)), boot_cpu_id);
		/* Or can we switch back to PIC here? */
	}

	/*
	 * Now start the IO-APICs
	 */
	if (!skip_ioapic_setup && nr_ioapics)
		setup_IO_APIC();
	else
		nr_ioapics = 0;

	/*
	 * Set up local APIC timer on boot CPU.
	 */

	setup_boot_APIC_clock();
}

/*
 * Early setup to make printk work.
 */
void __init smp_prepare_boot_cpu(void)
{
	int me = smp_processor_id();
	cpu_set(me, cpu_online_map);
	cpu_set(me, cpu_callout_map);
	per_cpu(cpu_state, me) = CPU_ONLINE;
}

/*
 * Entry point to boot a CPU.
 */
int __cpuinit __cpu_up(unsigned int cpu)
{
	int err;
	int apicid = cpu_present_to_apicid(cpu);

	WARN_ON(irqs_disabled());

	Dprintk("++++++++++++++++++++=_---CPU UP  %u\n", cpu);

	if (apicid == BAD_APICID || apicid == boot_cpu_id ||
	    !physid_isset(apicid, phys_cpu_present_map)) {
		printk("__cpu_up: bad cpu %d\n", cpu);
		return -EINVAL;
	}

	/*
	 * Already booted CPU?
	 */
 	if (cpu_isset(cpu, cpu_callin_map)) {
		Dprintk("do_boot_cpu %d Already started\n", cpu);
 		return -ENOSYS;
	}

	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
	/* Boot it! */
	err = do_boot_cpu(cpu, apicid);
	if (err < 0) {
		Dprintk("do_boot_cpu failed %d\n", err);
		return err;
	}

	/* Unleash the CPU! */
	Dprintk("waiting for cpu %d\n", cpu);

	while (!cpu_isset(cpu, cpu_online_map))
		cpu_relax();
	err = 0;

	return err;
}

/*
 * Finish the SMP boot.
 */
void __init smp_cpus_done(unsigned int max_cpus)
{
	smp_cleanup_boot();

#ifdef CONFIG_X86_IO_APIC
	setup_ioapic_dest();
#endif

	check_nmi_watchdog();
}

#ifdef CONFIG_HOTPLUG_CPU

static void remove_siblinginfo(int cpu)
{
	int sibling;
	struct cpuinfo_x86 *c = cpu_data;

	for_each_cpu_mask(sibling, cpu_core_map[cpu]) {
		cpu_clear(cpu, cpu_core_map[sibling]);
		/*
		 * last thread sibling in this cpu core going down
		 */
		if (cpus_weight(cpu_sibling_map[cpu]) == 1)
			c[sibling].booted_cores--;
	}
			
	for_each_cpu_mask(sibling, cpu_sibling_map[cpu])
		cpu_clear(cpu, cpu_sibling_map[sibling]);
	cpus_clear(cpu_sibling_map[cpu]);
	cpus_clear(cpu_core_map[cpu]);
	c[cpu].phys_proc_id = 0;
	c[cpu].cpu_core_id = 0;
	cpu_clear(cpu, cpu_sibling_setup_map);
}

void remove_cpu_from_maps(void)
{
	int cpu = smp_processor_id();

	cpu_clear(cpu, cpu_callout_map);
	cpu_clear(cpu, cpu_callin_map);
	clear_bit(cpu, &cpu_initialized); /* was set by cpu_init() */
	clear_node_cpumask(cpu);
}

int __cpu_disable(void)
{
	int cpu = smp_processor_id();

	/*
	 * Perhaps use cpufreq to drop frequency, but that could go
	 * into generic code.
 	 *
	 * We won't take down the boot processor on i386 due to some
	 * interrupts only being able to be serviced by the BSP.
	 * Especially so if we're not using an IOAPIC	-zwane
	 */
	if (cpu == 0)
		return -EBUSY;

	clear_local_APIC();

	/*
	 * HACK:
	 * Allow any queued timer interrupts to get serviced
	 * This is only a temporary solution until we cleanup
	 * fixup_irqs as we do for IA64.
	 */
	local_irq_enable();
	mdelay(1);

	local_irq_disable();
	remove_siblinginfo(cpu);

	/* It's now safe to remove this processor from the online map */
	cpu_clear(cpu, cpu_online_map);
	remove_cpu_from_maps();
	fixup_irqs(cpu_online_map);
	return 0;
}

void __cpu_die(unsigned int cpu)
{
	/* We don't do anything here: idle task is faking death itself. */
	unsigned int i;

	for (i = 0; i < 10; i++) {
		/* They ack this in play_dead by setting CPU_DEAD */
		if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
			printk ("CPU %d is now offline\n", cpu);
			if (1 == num_online_cpus())
				alternatives_smp_switch(0);
			return;
		}
		msleep(100);
	}
 	printk(KERN_ERR "CPU %u didn't die...\n", cpu);
}

__init int setup_additional_cpus(char *s)
{
	return get_option(&s, &additional_cpus);
}
__setup("additional_cpus=", setup_additional_cpus);

#else /* ... !CONFIG_HOTPLUG_CPU */

int __cpu_disable(void)
{
	return -ENOSYS;
}

void __cpu_die(unsigned int cpu)
{
	/* We said "no" in __cpu_disable */
	BUG();
}
#endif /* CONFIG_HOTPLUG_CPU */