aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/smpboot.c
blob: 69c17965f48da5ba510a4f62d4820bbe7e12f7d5 (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
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/percpu.h>
#include <linux/bootmem.h>
#include <linux/err.h>
#include <linux/nmi.h>

#include <asm/desc.h>
#include <asm/nmi.h>
#include <asm/irq.h>
#include <asm/smp.h>
#include <asm/cpu.h>
#include <asm/numa.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/mtrr.h>
#include <asm/nmi.h>
#include <linux/mc146818rtc.h>

#include <mach_apic.h>
#include <mach_wakecpu.h>
#include <smpboot_hooks.h>

/* Store all idle threads, this can be reused instead of creating
* a new thread. Also avoids complicated thread destroy functionality
* for idle threads.
*/
#ifdef CONFIG_HOTPLUG_CPU
/*
 * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is
 * removed after init for !CONFIG_HOTPLUG_CPU.
 */
static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
#define get_idle_for_cpu(x)      (per_cpu(idle_thread_array, x))
#define set_idle_for_cpu(x, p)   (per_cpu(idle_thread_array, x) = (p))
#else
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))
#endif

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

/* Last level cache ID of each logical CPU */
DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID;

/* bitmap of online cpus */
cpumask_t cpu_online_map __read_mostly;
EXPORT_SYMBOL(cpu_online_map);

cpumask_t cpu_callin_map;
cpumask_t cpu_callout_map;
cpumask_t cpu_possible_map;
EXPORT_SYMBOL(cpu_possible_map);

/* representing HT siblings of each logical CPU */
DEFINE_PER_CPU(cpumask_t, cpu_sibling_map);
EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);

/* representing HT and core siblings of each logical CPU */
DEFINE_PER_CPU(cpumask_t, cpu_core_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);

/* Per CPU bogomips and other parameters */
DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
EXPORT_PER_CPU_SYMBOL(cpu_info);

static atomic_t init_deasserted;

/* ready for x86_64, no harm for x86, since it will overwrite after alloc */
unsigned char *trampoline_base = __va(SMP_TRAMPOLINE_BASE);

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

/* Set if we find a B stepping CPU */
int __cpuinitdata smp_b_stepping;

#if defined(CONFIG_NUMA) && defined(CONFIG_X86_32)

/* which logical CPUs are on which nodes */
cpumask_t node_to_cpumask_map[MAX_NUMNODES] __read_mostly =
				{ [0 ... MAX_NUMNODES-1] = CPU_MASK_NONE };
EXPORT_SYMBOL(node_to_cpumask_map);
/* which node each logical CPU is on */
int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 };
EXPORT_SYMBOL(cpu_to_node_map);

/* set up a mapping between cpu and node. */
static void map_cpu_to_node(int cpu, int node)
{
	printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node);
	cpu_set(cpu, node_to_cpumask_map[node]);
	cpu_to_node_map[cpu] = node;
}

/* undo a mapping between cpu and node. */
static void unmap_cpu_to_node(int cpu)
{
	int node;

	printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu);
	for (node = 0; node < MAX_NUMNODES; node++)
		cpu_clear(cpu, node_to_cpumask_map[node]);
	cpu_to_node_map[cpu] = 0;
}
#else /* !(CONFIG_NUMA && CONFIG_X86_32) */
#define map_cpu_to_node(cpu, node)	({})
#define unmap_cpu_to_node(cpu)	({})
#endif

#ifdef CONFIG_X86_32
u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly =
					{ [0 ... NR_CPUS-1] = BAD_APICID };

void map_cpu_to_logical_apicid(void)
{
	int cpu = smp_processor_id();
	int apicid = logical_smp_processor_id();
	int node = apicid_to_node(apicid);

	if (!node_online(node))
		node = first_online_node;

	cpu_2_logical_apicid[cpu] = apicid;
	map_cpu_to_node(cpu, node);
}

void unmap_cpu_to_logical_apicid(int cpu)
{
	cpu_2_logical_apicid[cpu] = BAD_APICID;
	unmap_cpu_to_node(cpu);
}
#else
#define unmap_cpu_to_logical_apicid(cpu) do {} while (0)
#define map_cpu_to_logical_apicid()  do {} while (0)
#endif

/*
 * 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.
	 */
	wait_for_init_deassert(&init_deasserted);

	/*
	 * (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("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
					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("%s: CPU%d started up but did not get a callout!\n",
		      __func__, 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");
	smp_callin_clear_local_apic();
	setup_local_APIC();
	end_local_APIC_setup();
	map_cpu_to_logical_apicid();

	/*
	 * 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);

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

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


static void __cpuinit smp_apply_quirks(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_32
	/*
	 * Mask B, Pentium, but not Pentium MMX
	 */
	if (c->x86_vendor == X86_VENDOR_INTEL &&
	    c->x86 == 5 &&
	    c->x86_mask >= 1 && c->x86_mask <= 4 &&
	    c->x86_model <= 3)
		/*
		 * Remember we have B step Pentia with bugs
		 */
		smp_b_stepping = 1;

	/*
	 * Certain Athlons might work (for various values of 'work') in SMP
	 * but they are not certified as MP capable.
	 */
	if ((c->x86_vendor == X86_VENDOR_AMD) && (c->x86 == 6)) {

		if (num_possible_cpus() == 1)
			goto valid_k7;

		/* Athlon 660/661 is valid. */
		if ((c->x86_model == 6) && ((c->x86_mask == 0) ||
		    (c->x86_mask == 1)))
			goto valid_k7;

		/* Duron 670 is valid */
		if ((c->x86_model == 7) && (c->x86_mask == 0))
			goto valid_k7;

		/*
		 * Athlon 662, Duron 671, and Athlon >model 7 have capability
		 * bit. It's worth noting that the A5 stepping (662) of some
		 * Athlon XP's have the MP bit set.
		 * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for
		 * more.
		 */
		if (((c->x86_model == 6) && (c->x86_mask >= 2)) ||
		    ((c->x86_model == 7) && (c->x86_mask >= 1)) ||
		     (c->x86_model > 7))
			if (cpu_has_mp)
				goto valid_k7;

		/* If we get here, not a certified SMP capable AMD system. */
		add_taint(TAINT_UNSAFE_SMP);
	}

valid_k7:
	;
#endif
}

void smp_checks(void)
{
	if (smp_b_stepping)
		printk(KERN_WARNING "WARNING: SMP operation may be unreliable"
				    "with B stepping processors.\n");

	/*
	 * Don't taint if we are running SMP kernel on a single non-MP
	 * approved Athlon
	 */
	if (tainted & TAINT_UNSAFE_SMP) {
		if (num_online_cpus())
			printk(KERN_INFO "WARNING: This combination of AMD"
				"processors is not suitable for SMP.\n");
		else
			tainted &= ~TAINT_UNSAFE_SMP;
	}
}

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

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

	*c = boot_cpu_data;
	c->cpu_index = id;
	if (id != 0)
		identify_secondary_cpu(c);
	smp_apply_quirks(c);
}


void __cpuinit set_cpu_sibling_map(int cpu)
{
	int i;
	struct cpuinfo_x86 *c = &cpu_data(cpu);

	cpu_set(cpu, cpu_sibling_setup_map);

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

	cpu_set(cpu, c->llc_shared_map);

	if (current_cpu_data.x86_max_cores == 1) {
		per_cpu(cpu_core_map, cpu) = per_cpu(cpu_sibling_map, cpu);
		c->booted_cores = 1;
		return;
	}

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

/* 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.
	 * And for power savings, we return cpu_core_map
	 */
	if (sched_mc_power_savings || sched_smt_power_savings)
		return per_cpu(cpu_core_map, cpu);
	else
		return c->llc_shared_map;
}

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

unsigned long __cpuinit setup_trampoline(void)
{
	memcpy(trampoline_base, trampoline_data,
	       trampoline_end - trampoline_data);
	return virt_to_phys(trampoline_base);
}

#ifdef CONFIG_X86_32
/*
 * We are called very early to get the low memory for the
 * SMP bootup trampoline page.
 */
void __init smp_alloc_memory(void)
{
	trampoline_base = alloc_bootmem_low_pages(PAGE_SIZE);
	/*
	 * Has to be in very low memory so we can execute
	 * real-mode AP code.
	 */
	if (__pa(trampoline_base) >= 0x9F000)
		BUG();
}
#endif

void impress_friends(void)
{
	int cpu;
	unsigned long bogosum = 0;
	/*
	 * Allow the user to impress friends.
	 */
	Dprintk("Before bogomips.\n");
	for_each_possible_cpu(cpu)
		if (cpu_isset(cpu, cpu_callout_map))
			bogosum += cpu_data(cpu).loops_per_jiffy;
	printk(KERN_INFO
		"Total of %d processors activated (%lu.%02lu BogoMIPS).\n",
		num_online_cpus(),
		bogosum/(500000/HZ),
		(bogosum/(5000/HZ))%100);

	Dprintk("Before bogocount - setting activated=1.\n");
}

static inline 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;
	u32 status;

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

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

		/*
		 * Wait for idle.
		 */
		status = safe_apic_wait_icr_idle();
		if (status)
			printk(KERN_CONT
			       "a previous APIC delivery may have failed\n");

		apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(apicid));
		apic_write_around(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(KERN_CONT "%08x\n", status);
			break;
		default:
			printk(KERN_CONT "failed\n");
		}
	}
}

#ifdef WAKE_SECONDARY_VIA_NMI
/*
 * Poke the other CPU in the eye via NMI to wake it up. Remember that the normal
 * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
 * won't ... remember to clear down the APIC, etc later.
 */
static int __devinit
wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
{
	unsigned long send_status, accept_status = 0;
	int maxlvt;

	/* Target chip */
	apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(logical_apicid));

	/* Boot on the stack */
	/* Kick the second */
	apic_write_around(APIC_ICR, APIC_DM_NMI | APIC_DEST_LOGICAL);

	Dprintk("Waiting for send to finish...\n");
	send_status = safe_apic_wait_icr_idle();

	/*
	 * Give the other CPU some time to accept the IPI.
	 */
	udelay(200);
	/*
	 * Due to the Pentium erratum 3AP.
	 */
	maxlvt = lapic_get_maxlvt();
	if (maxlvt > 3) {
		apic_read_around(APIC_SPIV);
		apic_write(APIC_ESR, 0);
	}
	accept_status = (apic_read(APIC_ESR) & 0xEF);
	Dprintk("NMI sent.\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);
}
#endif	/* WAKE_SECONDARY_VIA_NMI */

extern void start_secondary(void *unused);
#ifdef WAKE_SECONDARY_VIA_INIT
static int __devinit
wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
{
	unsigned long send_status, accept_status = 0;
	int maxlvt, num_starts, j;

	/*
	 * Be paranoid about clearing APIC errors.
	 */
	if (APIC_INTEGRATED(apic_version[phys_apicid])) {
		apic_read_around(APIC_SPIV);
		apic_write(APIC_ESR, 0);
		apic_read(APIC_ESR);
	}

	Dprintk("Asserting INIT.\n");

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

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

	Dprintk("Waiting for send to finish...\n");
	send_status = safe_apic_wait_icr_idle();

	mdelay(10);

	Dprintk("Deasserting INIT.\n");

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

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

	Dprintk("Waiting for send to finish...\n");
	send_status = safe_apic_wait_icr_idle();

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

	/*
	 * Should we send STARTUP IPIs ?
	 *
	 * Determine this based on the APIC version.
	 * If we don't have an integrated APIC, don't send the STARTUP IPIs.
	 */
	if (APIC_INTEGRATED(apic_version[phys_apicid]))
		num_starts = 2;
	else
		num_starts = 0;

	/*
	 * Paravirt / VMI wants a startup IPI hook here to set up the
	 * target processor state.
	 */
	startup_ipi_hook(phys_apicid, (unsigned long) start_secondary,
#ifdef CONFIG_X86_64
			 (unsigned long)init_rsp);
#else
			 (unsigned long)stack_start.sp);
#endif

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

	maxlvt = lapic_get_maxlvt();

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

		/*
		 * STARTUP IPI
		 */

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

		/* Boot on the stack */
		/* Kick the second */
		apic_write_around(APIC_ICR, APIC_DM_STARTUP
					| (start_eip >> 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");
		send_status = safe_apic_wait_icr_idle();

		/*
		 * Give the other CPU some time to accept the IPI.
		 */
		udelay(200);
		/*
		 * Due to the Pentium erratum 3AP.
		 */
		if (maxlvt > 3) {
			apic_read_around(APIC_SPIV);
			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);
}
#endif	/* WAKE_SECONDARY_VIA_INIT */

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

static void __cpuinit do_fork_idle(struct work_struct *work)
{
	struct create_idle *c_idle =
		container_of(work, struct create_idle, work);

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

static int __cpuinit do_boot_cpu(int apicid, int cpu)
/*
 * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
 * (ie clustered apic addressing mode), this is a LOGICAL apic ID.
 * Returns zero if CPU booted OK, else error code from wakeup_secondary_cpu.
 */
{
	unsigned long boot_error = 0;
	int timeout;
	unsigned long start_ip;
	unsigned short nmi_high = 0, nmi_low = 0;
	struct create_idle c_idle = {
		.cpu = cpu,
		.done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
	};
	INIT_WORK(&c_idle.work, do_fork_idle);
#ifdef CONFIG_X86_64
	/* 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);
	}
#endif

	alternatives_smp_switch(1);

	c_idle.idle = get_idle_for_cpu(cpu);

	/*
	 * We can't use kernel_thread since we must avoid to
	 * reschedule the child.
	 */
	if (c_idle.idle) {
		c_idle.idle->thread.sp = (unsigned long) (((struct pt_regs *)
			(THREAD_SIZE +  task_stack_page(c_idle.idle))) - 1);
		init_idle(c_idle.idle, cpu);
		goto do_rest;
	}

	if (!keventd_up() || current_is_keventd())
		c_idle.work.func(&c_idle.work);
	else {
		schedule_work(&c_idle.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:
#ifdef CONFIG_X86_32
	per_cpu(current_task, cpu) = c_idle.idle;
	init_gdt(cpu);
	early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
	c_idle.idle->thread.ip = (unsigned long) start_secondary;
	/* Stack for startup_32 can be just as for start_secondary onwards */
	stack_start.sp = (void *) c_idle.idle->thread.sp;
	irq_ctx_init(cpu);
#else
	cpu_pda(cpu)->pcurrent = c_idle.idle;
	init_rsp = c_idle.idle->thread.sp;
	load_sp0(&per_cpu(init_tss, cpu), &c_idle.idle->thread);
	initial_code = (unsigned long)start_secondary;
	clear_tsk_thread_flag(c_idle.idle, TIF_FORK);
#endif

	/* start_ip had better be page-aligned! */
	start_ip = setup_trampoline();

	/* So we see what's up   */
	printk(KERN_INFO "Booting processor %d/%d ip %lx\n",
			  cpu, apicid, start_ip);

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

	atomic_set(&init_deasserted, 0);

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

	store_NMI_vector(&nmi_high, &nmi_low);

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


	/*
	 * Starting actual IPI sequence...
	 */
	boot_error = wakeup_secondary_cpu(apicid, start_ip);

	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("OK.\n");
			printk(KERN_INFO "CPU%d: ", cpu);
			print_cpu_info(&cpu_data(cpu));
			Dprintk("CPU has booted.\n");
		} else {
			boot_error = 1;
			if (*((volatile unsigned char *)trampoline_base)
					== 0xA5)
				/* trampoline started but...? */
				printk(KERN_ERR "Stuck ??\n");
			else
				/* trampoline code not run */
				printk(KERN_ERR "Not responding.\n");
			inquire_remote_apic(apicid);
		}
	}

	if (boot_error) {
		/* Try to put things back the way they were before ... */
		unmap_cpu_to_logical_apicid(cpu);
#ifdef CONFIG_X86_64
		clear_node_cpumask(cpu); /* was set by numa_add_cpu */
#endif
		cpu_clear(cpu, cpu_callout_map); /* was set by do_boot_cpu() */
		cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */
		cpu_clear(cpu, cpu_possible_map);
		cpu_clear(cpu, cpu_present_map);
		per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
	}

	/* mark "stuck" area as not stuck */
	*((volatile unsigned long *)trampoline_base) = 0;

	return boot_error;
}

int __cpuinit native_cpu_up(unsigned int cpu)
{
	int apicid = cpu_present_to_apicid(cpu);
	unsigned long flags;
	int err;

	WARN_ON(irqs_disabled());

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

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

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

	/*
	 * Save current MTRR state in case it was changed since early boot
	 * (e.g. by the ACPI SMI) to initialize new CPUs with MTRRs in sync:
	 */
	mtrr_save_state();

	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;

#ifdef CONFIG_X86_32
	/* init low mem mapping */
	clone_pgd_range(swapper_pg_dir, swapper_pg_dir + USER_PGD_PTRS,
			min_t(unsigned long, KERNEL_PGD_PTRS, USER_PGD_PTRS));
	flush_tlb_all();
#endif

	err = do_boot_cpu(apicid, cpu);
	if (err < 0) {
		Dprintk("do_boot_cpu failed %d\n", err);
		return err;
	}

	/*
	 * Check TSC synchronization with the AP (keep irqs disabled
	 * while doing so):
	 */
	local_irq_save(flags);
	check_tsc_sync_source(cpu);
	local_irq_restore(flags);

	while (!cpu_isset(cpu, cpu_online_map)) {
		cpu_relax();
		touch_nmi_watchdog();
	}

	return 0;
}

#ifdef CONFIG_HOTPLUG_CPU
void remove_siblinginfo(int cpu)
{
	int sibling;
	struct cpuinfo_x86 *c = &cpu_data(cpu);

	for_each_cpu_mask(sibling, per_cpu(cpu_core_map, cpu)) {
		cpu_clear(cpu, per_cpu(cpu_core_map, sibling));
		/*/
		 * last thread sibling in this cpu core going down
		 */
		if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1)
			cpu_data(sibling).booted_cores--;
	}

	for_each_cpu_mask(sibling, per_cpu(cpu_sibling_map, cpu))
		cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling));
	cpus_clear(per_cpu(cpu_sibling_map, cpu));
	cpus_clear(per_cpu(cpu_core_map, cpu));
	c->phys_proc_id = 0;
	c->cpu_core_id = 0;
	cpu_clear(cpu, cpu_sibling_setup_map);
}

int additional_cpus __initdata = -1;

static __init int setup_additional_cpus(char *s)
{
	return s && get_option(&s, &additional_cpus) ? 0 : -EINVAL;
}
early_param("additional_cpus", setup_additional_cpus);

/*
 * 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);
}

static void __ref remove_cpu_from_maps(int cpu)
{
	cpu_clear(cpu, cpu_online_map);
#ifdef CONFIG_X86_64
	cpu_clear(cpu, cpu_callout_map);
	cpu_clear(cpu, cpu_callin_map);
	/* was set by cpu_init() */
	clear_bit(cpu, (unsigned long *)&cpu_initialized);
	clear_node_cpumask(cpu);
#endif
}

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;

	if (nmi_watchdog == NMI_LOCAL_APIC)
		stop_apic_nmi_watchdog(NULL);
	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 */
	remove_cpu_from_maps(cpu);
	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(KERN_INFO "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);
}
#else /* ... !CONFIG_HOTPLUG_CPU */
int __cpu_disable(void)
{
	return -ENOSYS;
}

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

/*
 * If the BIOS enumerates physical processors before logical,
 * maxcpus=N at enumeration-time can be used to disable HT.
 */
static int __init parse_maxcpus(char *arg)
{
	extern unsigned int maxcpus;

	maxcpus = simple_strtoul(arg, NULL, 0);
	return 0;
}
early_param("maxcpus", parse_maxcpus);