aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/kernel/time.c
blob: ce53dfa7130dfc74f551c2360746f206154cf925 (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
/*
 * Common time routines among all ppc machines.
 *
 * Written by Cort Dougan (cort@cs.nmt.edu) to merge
 * Paul Mackerras' version and mine for PReP and Pmac.
 * MPC8xx/MBX changes by Dan Malek (dmalek@jlc.net).
 * Converted for 64-bit by Mike Corrigan (mikejc@us.ibm.com)
 *
 * First round of bugfixes by Gabriel Paubert (paubert@iram.es)
 * to make clock more stable (2.4.0-test5). The only thing
 * that this code assumes is that the timebases have been synchronized
 * by firmware on SMP and are never stopped (never do sleep
 * on SMP then, nap and doze are OK).
 * 
 * Speeded up do_gettimeofday by getting rid of references to
 * xtime (which required locks for consistency). (mikejc@us.ibm.com)
 *
 * TODO (not necessarily in this file):
 * - improve precision and reproducibility of timebase frequency
 * measurement at boot time. (for iSeries, we calibrate the timebase
 * against the Titan chip's clock.)
 * - for astronomical applications: add a new function to get
 * non ambiguous timestamps even around leap seconds. This needs
 * a new timestamp format and a good name.
 *
 * 1997-09-10  Updated NTP code according to technical memorandum Jan '96
 *             "A Kernel Model for Precision Timekeeping" by Dave Mills
 *
 *      This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

#include <linux/errno.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/param.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/timex.h>
#include <linux/kernel_stat.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/profile.h>
#include <linux/cpu.h>
#include <linux/security.h>
#include <linux/percpu.h>
#include <linux/rtc.h>
#include <linux/jiffies.h>
#include <linux/posix-timers.h>
#include <linux/irq.h>
#include <linux/delay.h>
#include <linux/perf_event.h>
#include <asm/trace.h>

#include <asm/io.h>
#include <asm/processor.h>
#include <asm/nvram.h>
#include <asm/cache.h>
#include <asm/machdep.h>
#include <asm/uaccess.h>
#include <asm/time.h>
#include <asm/prom.h>
#include <asm/irq.h>
#include <asm/div64.h>
#include <asm/smp.h>
#include <asm/vdso_datapage.h>
#include <asm/firmware.h>
#include <asm/cputime.h>
#ifdef CONFIG_PPC_ISERIES
#include <asm/iseries/it_lp_queue.h>
#include <asm/iseries/hv_call_xm.h>
#endif

/* powerpc clocksource/clockevent code */

#include <linux/clockchips.h>
#include <linux/clocksource.h>

static cycle_t rtc_read(struct clocksource *);
static struct clocksource clocksource_rtc = {
	.name         = "rtc",
	.rating       = 400,
	.flags        = CLOCK_SOURCE_IS_CONTINUOUS,
	.mask         = CLOCKSOURCE_MASK(64),
	.shift        = 22,
	.mult         = 0,	/* To be filled in */
	.read         = rtc_read,
};

static cycle_t timebase_read(struct clocksource *);
static struct clocksource clocksource_timebase = {
	.name         = "timebase",
	.rating       = 400,
	.flags        = CLOCK_SOURCE_IS_CONTINUOUS,
	.mask         = CLOCKSOURCE_MASK(64),
	.shift        = 22,
	.mult         = 0,	/* To be filled in */
	.read         = timebase_read,
};

#define DECREMENTER_MAX	0x7fffffff

static int decrementer_set_next_event(unsigned long evt,
				      struct clock_event_device *dev);
static void decrementer_set_mode(enum clock_event_mode mode,
				 struct clock_event_device *dev);

static struct clock_event_device decrementer_clockevent = {
       .name           = "decrementer",
       .rating         = 200,
       .shift          = 0,	/* To be filled in */
       .mult           = 0,	/* To be filled in */
       .irq            = 0,
       .set_next_event = decrementer_set_next_event,
       .set_mode       = decrementer_set_mode,
       .features       = CLOCK_EVT_FEAT_ONESHOT,
};

struct decrementer_clock {
	struct clock_event_device event;
	u64 next_tb;
};

static DEFINE_PER_CPU(struct decrementer_clock, decrementers);

#ifdef CONFIG_PPC_ISERIES
static unsigned long __initdata iSeries_recal_titan;
static signed long __initdata iSeries_recal_tb;

/* Forward declaration is only needed for iSereis compiles */
static void __init clocksource_init(void);
#endif

#define XSEC_PER_SEC (1024*1024)

#ifdef CONFIG_PPC64
#define SCALE_XSEC(xsec, max)	(((xsec) * max) / XSEC_PER_SEC)
#else
/* compute ((xsec << 12) * max) >> 32 */
#define SCALE_XSEC(xsec, max)	mulhwu((xsec) << 12, max)
#endif

unsigned long tb_ticks_per_jiffy;
unsigned long tb_ticks_per_usec = 100; /* sane default */
EXPORT_SYMBOL(tb_ticks_per_usec);
unsigned long tb_ticks_per_sec;
EXPORT_SYMBOL(tb_ticks_per_sec);	/* for cputime_t conversions */

DEFINE_SPINLOCK(rtc_lock);
EXPORT_SYMBOL_GPL(rtc_lock);

static u64 tb_to_ns_scale __read_mostly;
static unsigned tb_to_ns_shift __read_mostly;
static unsigned long boot_tb __read_mostly;

extern struct timezone sys_tz;
static long timezone_offset;

unsigned long ppc_proc_freq;
EXPORT_SYMBOL(ppc_proc_freq);
unsigned long ppc_tb_freq;

static DEFINE_PER_CPU(u64, last_jiffy);

#ifdef CONFIG_VIRT_CPU_ACCOUNTING
/*
 * Factors for converting from cputime_t (timebase ticks) to
 * jiffies, milliseconds, seconds, and clock_t (1/USER_HZ seconds).
 * These are all stored as 0.64 fixed-point binary fractions.
 */
u64 __cputime_jiffies_factor;
EXPORT_SYMBOL(__cputime_jiffies_factor);
u64 __cputime_msec_factor;
EXPORT_SYMBOL(__cputime_msec_factor);
u64 __cputime_sec_factor;
EXPORT_SYMBOL(__cputime_sec_factor);
u64 __cputime_clockt_factor;
EXPORT_SYMBOL(__cputime_clockt_factor);
DEFINE_PER_CPU(unsigned long, cputime_last_delta);
DEFINE_PER_CPU(unsigned long, cputime_scaled_last_delta);

cputime_t cputime_one_jiffy;

static void calc_cputime_factors(void)
{
	struct div_result res;

	div128_by_32(HZ, 0, tb_ticks_per_sec, &res);
	__cputime_jiffies_factor = res.result_low;
	div128_by_32(1000, 0, tb_ticks_per_sec, &res);
	__cputime_msec_factor = res.result_low;
	div128_by_32(1, 0, tb_ticks_per_sec, &res);
	__cputime_sec_factor = res.result_low;
	div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res);
	__cputime_clockt_factor = res.result_low;
}

/*
 * Read the PURR on systems that have it, otherwise the timebase.
 */
static u64 read_purr(void)
{
	if (cpu_has_feature(CPU_FTR_PURR))
		return mfspr(SPRN_PURR);
	return mftb();
}

/*
 * Read the SPURR on systems that have it, otherwise the purr
 */
static u64 read_spurr(u64 purr)
{
	/*
	 * cpus without PURR won't have a SPURR
	 * We already know the former when we use this, so tell gcc
	 */
	if (cpu_has_feature(CPU_FTR_PURR) && cpu_has_feature(CPU_FTR_SPURR))
		return mfspr(SPRN_SPURR);
	return purr;
}

/*
 * Account time for a transition between system, hard irq
 * or soft irq state.
 */
void account_system_vtime(struct task_struct *tsk)
{
	u64 now, nowscaled, delta, deltascaled, sys_time;
	unsigned long flags;

	local_irq_save(flags);
	now = read_purr();
	nowscaled = read_spurr(now);
	delta = now - get_paca()->startpurr;
	deltascaled = nowscaled - get_paca()->startspurr;
	get_paca()->startpurr = now;
	get_paca()->startspurr = nowscaled;
	if (!in_interrupt()) {
		/* deltascaled includes both user and system time.
		 * Hence scale it based on the purr ratio to estimate
		 * the system time */
		sys_time = get_paca()->system_time;
		if (get_paca()->user_time)
			deltascaled = deltascaled * sys_time /
			     (sys_time + get_paca()->user_time);
		delta += sys_time;
		get_paca()->system_time = 0;
	}
	if (in_irq() || idle_task(smp_processor_id()) != tsk)
		account_system_time(tsk, 0, delta, deltascaled);
	else
		account_idle_time(delta);
	__get_cpu_var(cputime_last_delta) = delta;
	__get_cpu_var(cputime_scaled_last_delta) = deltascaled;
	local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(account_system_vtime);

/*
 * Transfer the user and system times accumulated in the paca
 * by the exception entry and exit code to the generic process
 * user and system time records.
 * Must be called with interrupts disabled.
 */
void account_process_tick(struct task_struct *tsk, int user_tick)
{
	cputime_t utime, utimescaled;

	utime = get_paca()->user_time;
	get_paca()->user_time = 0;
	utimescaled = cputime_to_scaled(utime);
	account_user_time(tsk, utime, utimescaled);
}

/*
 * Stuff for accounting stolen time.
 */
struct cpu_purr_data {
	int	initialized;			/* thread is running */
	u64	tb;			/* last TB value read */
	u64	purr;			/* last PURR value read */
	u64	spurr;			/* last SPURR value read */
};

/*
 * Each entry in the cpu_purr_data array is manipulated only by its
 * "owner" cpu -- usually in the timer interrupt but also occasionally
 * in process context for cpu online.  As long as cpus do not touch
 * each others' cpu_purr_data, disabling local interrupts is
 * sufficient to serialize accesses.
 */
static DEFINE_PER_CPU(struct cpu_purr_data, cpu_purr_data);

static void snapshot_tb_and_purr(void *data)
{
	unsigned long flags;
	struct cpu_purr_data *p = &__get_cpu_var(cpu_purr_data);

	local_irq_save(flags);
	p->tb = get_tb_or_rtc();
	p->purr = mfspr(SPRN_PURR);
	wmb();
	p->initialized = 1;
	local_irq_restore(flags);
}

/*
 * Called during boot when all cpus have come up.
 */
void snapshot_timebases(void)
{
	if (!cpu_has_feature(CPU_FTR_PURR))
		return;
	on_each_cpu(snapshot_tb_and_purr, NULL, 1);
}

/*
 * Must be called with interrupts disabled.
 */
void calculate_steal_time(void)
{
	u64 tb, purr;
	s64 stolen;
	struct cpu_purr_data *pme;

	pme = &__get_cpu_var(cpu_purr_data);
	if (!pme->initialized)
		return;		/* !CPU_FTR_PURR or early in early boot */
	tb = mftb();
	purr = mfspr(SPRN_PURR);
	stolen = (tb - pme->tb) - (purr - pme->purr);
	if (stolen > 0) {
		if (idle_task(smp_processor_id()) != current)
			account_steal_time(stolen);
		else
			account_idle_time(stolen);
	}
	pme->tb = tb;
	pme->purr = purr;
}

#ifdef CONFIG_PPC_SPLPAR
/*
 * Must be called before the cpu is added to the online map when
 * a cpu is being brought up at runtime.
 */
static void snapshot_purr(void)
{
	struct cpu_purr_data *pme;
	unsigned long flags;

	if (!cpu_has_feature(CPU_FTR_PURR))
		return;
	local_irq_save(flags);
	pme = &__get_cpu_var(cpu_purr_data);
	pme->tb = mftb();
	pme->purr = mfspr(SPRN_PURR);
	pme->initialized = 1;
	local_irq_restore(flags);
}

#endif /* CONFIG_PPC_SPLPAR */

#else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
#define calc_cputime_factors()
#define calculate_steal_time()		do { } while (0)
#endif

#if !(defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(CONFIG_PPC_SPLPAR))
#define snapshot_purr()			do { } while (0)
#endif

/*
 * Called when a cpu comes up after the system has finished booting,
 * i.e. as a result of a hotplug cpu action.
 */
void snapshot_timebase(void)
{
	__get_cpu_var(last_jiffy) = get_tb_or_rtc();
	snapshot_purr();
}

void __delay(unsigned long loops)
{
	unsigned long start;
	int diff;

	if (__USE_RTC()) {
		start = get_rtcl();
		do {
			/* the RTCL register wraps at 1000000000 */
			diff = get_rtcl() - start;
			if (diff < 0)
				diff += 1000000000;
		} while (diff < loops);
	} else {
		start = get_tbl();
		while (get_tbl() - start < loops)
			HMT_low();
		HMT_medium();
	}
}
EXPORT_SYMBOL(__delay);

void udelay(unsigned long usecs)
{
	__delay(tb_ticks_per_usec * usecs);
}
EXPORT_SYMBOL(udelay);

#ifdef CONFIG_SMP
unsigned long profile_pc(struct pt_regs *regs)
{
	unsigned long pc = instruction_pointer(regs);

	if (in_lock_functions(pc))
		return regs->link;

	return pc;
}
EXPORT_SYMBOL(profile_pc);
#endif

#ifdef CONFIG_PPC_ISERIES

/* 
 * This function recalibrates the timebase based on the 49-bit time-of-day
 * value in the Titan chip.  The Titan is much more accurate than the value
 * returned by the service processor for the timebase frequency.  
 */

static int __init iSeries_tb_recal(void)
{
	unsigned long titan, tb;

	/* Make sure we only run on iSeries */
	if (!firmware_has_feature(FW_FEATURE_ISERIES))
		return -ENODEV;

	tb = get_tb();
	titan = HvCallXm_loadTod();
	if ( iSeries_recal_titan ) {
		unsigned long tb_ticks = tb - iSeries_recal_tb;
		unsigned long titan_usec = (titan - iSeries_recal_titan) >> 12;
		unsigned long new_tb_ticks_per_sec   = (tb_ticks * USEC_PER_SEC)/titan_usec;
		unsigned long new_tb_ticks_per_jiffy =
			DIV_ROUND_CLOSEST(new_tb_ticks_per_sec, HZ);
		long tick_diff = new_tb_ticks_per_jiffy - tb_ticks_per_jiffy;
		char sign = '+';		
		/* make sure tb_ticks_per_sec and tb_ticks_per_jiffy are consistent */
		new_tb_ticks_per_sec = new_tb_ticks_per_jiffy * HZ;

		if ( tick_diff < 0 ) {
			tick_diff = -tick_diff;
			sign = '-';
		}
		if ( tick_diff ) {
			if ( tick_diff < tb_ticks_per_jiffy/25 ) {
				printk( "Titan recalibrate: new tb_ticks_per_jiffy = %lu (%c%ld)\n",
						new_tb_ticks_per_jiffy, sign, tick_diff );
				tb_ticks_per_jiffy = new_tb_ticks_per_jiffy;
				tb_ticks_per_sec   = new_tb_ticks_per_sec;
				calc_cputime_factors();
				vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
				setup_cputime_one_jiffy();
			}
			else {
				printk( "Titan recalibrate: FAILED (difference > 4 percent)\n"
					"                   new tb_ticks_per_jiffy = %lu\n"
					"                   old tb_ticks_per_jiffy = %lu\n",
					new_tb_ticks_per_jiffy, tb_ticks_per_jiffy );
			}
		}
	}
	iSeries_recal_titan = titan;
	iSeries_recal_tb = tb;

	/* Called here as now we know accurate values for the timebase */
	clocksource_init();
	return 0;
}
late_initcall(iSeries_tb_recal);

/* Called from platform early init */
void __init iSeries_time_init_early(void)
{
	iSeries_recal_tb = get_tb();
	iSeries_recal_titan = HvCallXm_loadTod();
}
#endif /* CONFIG_PPC_ISERIES */

#ifdef CONFIG_PERF_EVENTS

/*
 * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
 */
#ifdef CONFIG_PPC64
static inline unsigned long test_perf_event_pending(void)
{
	unsigned long x;

	asm volatile("lbz %0,%1(13)"
		: "=r" (x)
		: "i" (offsetof(struct paca_struct, perf_event_pending)));
	return x;
}

static inline void set_perf_event_pending_flag(void)
{
	asm volatile("stb %0,%1(13)" : :
		"r" (1),
		"i" (offsetof(struct paca_struct, perf_event_pending)));
}

static inline void clear_perf_event_pending(void)
{
	asm volatile("stb %0,%1(13)" : :
		"r" (0),
		"i" (offsetof(struct paca_struct, perf_event_pending)));
}

#else /* 32-bit */

DEFINE_PER_CPU(u8, perf_event_pending);

#define set_perf_event_pending_flag()	__get_cpu_var(perf_event_pending) = 1
#define test_perf_event_pending()	__get_cpu_var(perf_event_pending)
#define clear_perf_event_pending()	__get_cpu_var(perf_event_pending) = 0

#endif /* 32 vs 64 bit */

void set_perf_event_pending(void)
{
	preempt_disable();
	set_perf_event_pending_flag();
	set_dec(1);
	preempt_enable();
}

#else  /* CONFIG_PERF_EVENTS */

#define test_perf_event_pending()	0
#define clear_perf_event_pending()

#endif /* CONFIG_PERF_EVENTS */

/*
 * For iSeries shared processors, we have to let the hypervisor
 * set the hardware decrementer.  We set a virtual decrementer
 * in the lppaca and call the hypervisor if the virtual
 * decrementer is less than the current value in the hardware
 * decrementer. (almost always the new decrementer value will
 * be greater than the current hardware decementer so the hypervisor
 * call will not be needed)
 */

/*
 * timer_interrupt - gets called when the decrementer overflows,
 * with interrupts disabled.
 */
void timer_interrupt(struct pt_regs * regs)
{
	struct pt_regs *old_regs;
	struct decrementer_clock *decrementer =  &__get_cpu_var(decrementers);
	struct clock_event_device *evt = &decrementer->event;
	u64 now;

	trace_timer_interrupt_entry(regs);

	__get_cpu_var(irq_stat).timer_irqs++;

	/* Ensure a positive value is written to the decrementer, or else
	 * some CPUs will continuue to take decrementer exceptions */
	set_dec(DECREMENTER_MAX);

#ifdef CONFIG_PPC32
	if (atomic_read(&ppc_n_lost_interrupts) != 0)
		do_IRQ(regs);
#endif

	now = get_tb_or_rtc();
	if (now < decrementer->next_tb) {
		/* not time for this event yet */
		now = decrementer->next_tb - now;
		if (now <= DECREMENTER_MAX)
			set_dec((int)now);
		trace_timer_interrupt_exit(regs);
		return;
	}
	old_regs = set_irq_regs(regs);
	irq_enter();

	calculate_steal_time();

	if (test_perf_event_pending()) {
		clear_perf_event_pending();
		perf_event_do_pending();
	}

#ifdef CONFIG_PPC_ISERIES
	if (firmware_has_feature(FW_FEATURE_ISERIES))
		get_lppaca()->int_dword.fields.decr_int = 0;
#endif

	if (evt->event_handler)
		evt->event_handler(evt);

#ifdef CONFIG_PPC_ISERIES
	if (firmware_has_feature(FW_FEATURE_ISERIES) && hvlpevent_is_pending())
		process_hvlpevents();
#endif

#ifdef CONFIG_PPC64
	/* collect purr register values often, for accurate calculations */
	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
		cu->current_tb = mfspr(SPRN_PURR);
	}
#endif

	irq_exit();
	set_irq_regs(old_regs);

	trace_timer_interrupt_exit(regs);
}

#ifdef CONFIG_SUSPEND
static void generic_suspend_disable_irqs(void)
{
	/* Disable the decrementer, so that it doesn't interfere
	 * with suspending.
	 */

	set_dec(0x7fffffff);
	local_irq_disable();
	set_dec(0x7fffffff);
}

static void generic_suspend_enable_irqs(void)
{
	local_irq_enable();
}

/* Overrides the weak version in kernel/power/main.c */
void arch_suspend_disable_irqs(void)
{
	if (ppc_md.suspend_disable_irqs)
		ppc_md.suspend_disable_irqs();
	generic_suspend_disable_irqs();
}

/* Overrides the weak version in kernel/power/main.c */
void arch_suspend_enable_irqs(void)
{
	generic_suspend_enable_irqs();
	if (ppc_md.suspend_enable_irqs)
		ppc_md.suspend_enable_irqs();
}
#endif

/*
 * Scheduler clock - returns current time in nanosec units.
 *
 * Note: mulhdu(a, b) (multiply high double unsigned) returns
 * the high 64 bits of a * b, i.e. (a * b) >> 64, where a and b
 * are 64-bit unsigned numbers.
 */
unsigned long long sched_clock(void)
{
	if (__USE_RTC())
		return get_rtc();
	return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
}

static int __init get_freq(char *name, int cells, unsigned long *val)
{
	struct device_node *cpu;
	const unsigned int *fp;
	int found = 0;

	/* The cpu node should have timebase and clock frequency properties */
	cpu = of_find_node_by_type(NULL, "cpu");

	if (cpu) {
		fp = of_get_property(cpu, name, NULL);
		if (fp) {
			found = 1;
			*val = of_read_ulong(fp, cells);
		}

		of_node_put(cpu);
	}

	return found;
}

/* should become __cpuinit when secondary_cpu_time_init also is */
void start_cpu_decrementer(void)
{
#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
	/* Clear any pending timer interrupts */
	mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS);

	/* Enable decrementer interrupt */
	mtspr(SPRN_TCR, TCR_DIE);
#endif /* defined(CONFIG_BOOKE) || defined(CONFIG_40x) */
}

void __init generic_calibrate_decr(void)
{
	ppc_tb_freq = DEFAULT_TB_FREQ;		/* hardcoded default */

	if (!get_freq("ibm,extended-timebase-frequency", 2, &ppc_tb_freq) &&
	    !get_freq("timebase-frequency", 1, &ppc_tb_freq)) {

		printk(KERN_ERR "WARNING: Estimating decrementer frequency "
				"(not found)\n");
	}

	ppc_proc_freq = DEFAULT_PROC_FREQ;	/* hardcoded default */

	if (!get_freq("ibm,extended-clock-frequency", 2, &ppc_proc_freq) &&
	    !get_freq("clock-frequency", 1, &ppc_proc_freq)) {

		printk(KERN_ERR "WARNING: Estimating processor frequency "
				"(not found)\n");
	}
}

int update_persistent_clock(struct timespec now)
{
	struct rtc_time tm;

	if (!ppc_md.set_rtc_time)
		return 0;

	to_tm(now.tv_sec + 1 + timezone_offset, &tm);
	tm.tm_year -= 1900;
	tm.tm_mon -= 1;

	return ppc_md.set_rtc_time(&tm);
}

static void __read_persistent_clock(struct timespec *ts)
{
	struct rtc_time tm;
	static int first = 1;

	ts->tv_nsec = 0;
	/* XXX this is a litle fragile but will work okay in the short term */
	if (first) {
		first = 0;
		if (ppc_md.time_init)
			timezone_offset = ppc_md.time_init();

		/* get_boot_time() isn't guaranteed to be safe to call late */
		if (ppc_md.get_boot_time) {
			ts->tv_sec = ppc_md.get_boot_time() - timezone_offset;
			return;
		}
	}
	if (!ppc_md.get_rtc_time) {
		ts->tv_sec = 0;
		return;
	}
	ppc_md.get_rtc_time(&tm);

	ts->tv_sec = mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday,
			    tm.tm_hour, tm.tm_min, tm.tm_sec);
}

void read_persistent_clock(struct timespec *ts)
{
	__read_persistent_clock(ts);

	/* Sanitize it in case real time clock is set below EPOCH */
	if (ts->tv_sec < 0) {
		ts->tv_sec = 0;
		ts->tv_nsec = 0;
	}
		
}

/* clocksource code */
static cycle_t rtc_read(struct clocksource *cs)
{
	return (cycle_t)get_rtc();
}

static cycle_t timebase_read(struct clocksource *cs)
{
	return (cycle_t)get_tb();
}

void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
			struct clocksource *clock, u32 mult)
{
	u64 new_tb_to_xs, new_stamp_xsec;
	u32 frac_sec;

	if (clock != &clocksource_timebase)
		return;

	/* Make userspace gettimeofday spin until we're done. */
	++vdso_data->tb_update_count;
	smp_mb();

	/* XXX this assumes clock->shift == 22 */
	/* 4611686018 ~= 2^(20+64-22) / 1e9 */
	new_tb_to_xs = (u64) mult * 4611686018ULL;
	new_stamp_xsec = (u64) wall_time->tv_nsec * XSEC_PER_SEC;
	do_div(new_stamp_xsec, 1000000000);
	new_stamp_xsec += (u64) wall_time->tv_sec * XSEC_PER_SEC;

	BUG_ON(wall_time->tv_nsec >= NSEC_PER_SEC);
	/* this is tv_nsec / 1e9 as a 0.32 fraction */
	frac_sec = ((u64) wall_time->tv_nsec * 18446744073ULL) >> 32;

	/*
	 * tb_update_count is used to allow the userspace gettimeofday code
	 * to assure itself that it sees a consistent view of the tb_to_xs and
	 * stamp_xsec variables.  It reads the tb_update_count, then reads
	 * tb_to_xs and stamp_xsec and then reads tb_update_count again.  If
	 * the two values of tb_update_count match and are even then the
	 * tb_to_xs and stamp_xsec values are consistent.  If not, then it
	 * loops back and reads them again until this criteria is met.
	 * We expect the caller to have done the first increment of
	 * vdso_data->tb_update_count already.
	 */
	vdso_data->tb_orig_stamp = clock->cycle_last;
	vdso_data->stamp_xsec = new_stamp_xsec;
	vdso_data->tb_to_xs = new_tb_to_xs;
	vdso_data->wtom_clock_sec = wtm->tv_sec;
	vdso_data->wtom_clock_nsec = wtm->tv_nsec;
	vdso_data->stamp_xtime = *wall_time;
	vdso_data->stamp_sec_fraction = frac_sec;
	smp_wmb();
	++(vdso_data->tb_update_count);
}

void update_vsyscall_tz(void)
{
	/* Make userspace gettimeofday spin until we're done. */
	++vdso_data->tb_update_count;
	smp_mb();
	vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
	vdso_data->tz_dsttime = sys_tz.tz_dsttime;
	smp_mb();
	++vdso_data->tb_update_count;
}

static void __init clocksource_init(void)
{
	struct clocksource *clock;

	if (__USE_RTC())
		clock = &clocksource_rtc;
	else
		clock = &clocksource_timebase;

	clock->mult = clocksource_hz2mult(tb_ticks_per_sec, clock->shift);

	if (clocksource_register(clock)) {
		printk(KERN_ERR "clocksource: %s is already registered\n",
		       clock->name);
		return;
	}

	printk(KERN_INFO "clocksource: %s mult[%x] shift[%d] registered\n",
	       clock->name, clock->mult, clock->shift);
}

static int decrementer_set_next_event(unsigned long evt,
				      struct clock_event_device *dev)
{
	__get_cpu_var(decrementers).next_tb = get_tb_or_rtc() + evt;
	set_dec(evt);
	return 0;
}

static void decrementer_set_mode(enum clock_event_mode mode,
				 struct clock_event_device *dev)
{
	if (mode != CLOCK_EVT_MODE_ONESHOT)
		decrementer_set_next_event(DECREMENTER_MAX, dev);
}

static inline uint64_t div_sc64(unsigned long ticks, unsigned long nsec,
				int shift)
{
	uint64_t tmp = ((uint64_t)ticks) << shift;

	do_div(tmp, nsec);
	return tmp;
}

static void __init setup_clockevent_multiplier(unsigned long hz)
{
	u64 mult, shift = 32;

	while (1) {
		mult = div_sc64(hz, NSEC_PER_SEC, shift);
		if (mult && (mult >> 32UL) == 0UL)
			break;

		shift--;
	}

	decrementer_clockevent.shift = shift;
	decrementer_clockevent.mult = mult;
}

static void register_decrementer_clockevent(int cpu)
{
	struct clock_event_device *dec = &per_cpu(decrementers, cpu).event;

	*dec = decrementer_clockevent;
	dec->cpumask = cpumask_of(cpu);

	printk_once(KERN_DEBUG "clockevent: %s mult[%x] shift[%d] cpu[%d]\n",
		    dec->name, dec->mult, dec->shift, cpu);

	clockevents_register_device(dec);
}

static void __init init_decrementer_clockevent(void)
{
	int cpu = smp_processor_id();

	setup_clockevent_multiplier(ppc_tb_freq);
	decrementer_clockevent.max_delta_ns =
		clockevent_delta2ns(DECREMENTER_MAX, &decrementer_clockevent);
	decrementer_clockevent.min_delta_ns =
		clockevent_delta2ns(2, &decrementer_clockevent);

	register_decrementer_clockevent(cpu);
}

void secondary_cpu_time_init(void)
{
	/* Start the decrementer on CPUs that have manual control
	 * such as BookE
	 */
	start_cpu_decrementer();

	/* FIME: Should make unrelatred change to move snapshot_timebase
	 * call here ! */
	register_decrementer_clockevent(smp_processor_id());
}

/* This function is only called on the boot processor */
void __init time_init(void)
{
	struct div_result res;
	u64 scale;
	unsigned shift;

	if (__USE_RTC()) {
		/* 601 processor: dec counts down by 128 every 128ns */
		ppc_tb_freq = 1000000000;
	} else {
		/* Normal PowerPC with timebase register */
		ppc_md.calibrate_decr();
		printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n",
		       ppc_tb_freq / 1000000, ppc_tb_freq % 1000000);
		printk(KERN_DEBUG "time_init: processor frequency   = %lu.%.6lu MHz\n",
		       ppc_proc_freq / 1000000, ppc_proc_freq % 1000000);
	}

	tb_ticks_per_jiffy = ppc_tb_freq / HZ;
	tb_ticks_per_sec = ppc_tb_freq;
	tb_ticks_per_usec = ppc_tb_freq / 1000000;
	calc_cputime_factors();
	setup_cputime_one_jiffy();

	/*
	 * Compute scale factor for sched_clock.
	 * The calibrate_decr() function has set tb_ticks_per_sec,
	 * which is the timebase frequency.
	 * We compute 1e9 * 2^64 / tb_ticks_per_sec and interpret
	 * the 128-bit result as a 64.64 fixed-point number.
	 * We then shift that number right until it is less than 1.0,
	 * giving us the scale factor and shift count to use in
	 * sched_clock().
	 */
	div128_by_32(1000000000, 0, tb_ticks_per_sec, &res);
	scale = res.result_low;
	for (shift = 0; res.result_high != 0; ++shift) {
		scale = (scale >> 1) | (res.result_high << 63);
		res.result_high >>= 1;
	}
	tb_to_ns_scale = scale;
	tb_to_ns_shift = shift;
	/* Save the current timebase to pretty up CONFIG_PRINTK_TIME */
	boot_tb = get_tb_or_rtc();

	/* If platform provided a timezone (pmac), we correct the time */
        if (timezone_offset) {
		sys_tz.tz_minuteswest = -timezone_offset / 60;
		sys_tz.tz_dsttime = 0;
        }

	vdso_data->tb_update_count = 0;
	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;

	/* Start the decrementer on CPUs that have manual control
	 * such as BookE
	 */
	start_cpu_decrementer();

	/* Register the clocksource, if we're not running on iSeries */
	if (!firmware_has_feature(FW_FEATURE_ISERIES))
		clocksource_init();

	init_decrementer_clockevent();
}


#define FEBRUARY	2
#define	STARTOFTIME	1970
#define SECDAY		86400L
#define SECYR		(SECDAY * 365)
#define	leapyear(year)		((year) % 4 == 0 && \
				 ((year) % 100 != 0 || (year) % 400 == 0))
#define	days_in_year(a) 	(leapyear(a) ? 366 : 365)
#define	days_in_month(a) 	(month_days[(a) - 1])

static int month_days[12] = {
	31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31
};

/*
 * This only works for the Gregorian calendar - i.e. after 1752 (in the UK)
 */
void GregorianDay(struct rtc_time * tm)
{
	int leapsToDate;
	int lastYear;
	int day;
	int MonthOffset[] = { 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334 };

	lastYear = tm->tm_year - 1;

	/*
	 * Number of leap corrections to apply up to end of last year
	 */
	leapsToDate = lastYear / 4 - lastYear / 100 + lastYear / 400;

	/*
	 * This year is a leap year if it is divisible by 4 except when it is
	 * divisible by 100 unless it is divisible by 400
	 *
	 * e.g. 1904 was a leap year, 1900 was not, 1996 is, and 2000 was
	 */
	day = tm->tm_mon > 2 && leapyear(tm->tm_year);

	day += lastYear*365 + leapsToDate + MonthOffset[tm->tm_mon-1] +
		   tm->tm_mday;

	tm->tm_wday = day % 7;
}

void to_tm(int tim, struct rtc_time * tm)
{
	register int    i;
	register long   hms, day;

	day = tim / SECDAY;
	hms = tim % SECDAY;

	/* Hours, minutes, seconds are easy */
	tm->tm_hour = hms / 3600;
	tm->tm_min = (hms % 3600) / 60;
	tm->tm_sec = (hms % 3600) % 60;

	/* Number of years in days */
	for (i = STARTOFTIME; day >= days_in_year(i); i++)
		day -= days_in_year(i);
	tm->tm_year = i;

	/* Number of months in days left */
	if (leapyear(tm->tm_year))
		days_in_month(FEBRUARY) = 29;
	for (i = 1; day >= days_in_month(i); i++)
		day -= days_in_month(i);
	days_in_month(FEBRUARY) = 28;
	tm->tm_mon = i;

	/* Days are what is left over (+1) from all that. */
	tm->tm_mday = day + 1;

	/*
	 * Determine the day of week
	 */
	GregorianDay(tm);
}

/*
 * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit
 * result.
 */
void div128_by_32(u64 dividend_high, u64 dividend_low,
		  unsigned divisor, struct div_result *dr)
{
	unsigned long a, b, c, d;
	unsigned long w, x, y, z;
	u64 ra, rb, rc;

	a = dividend_high >> 32;
	b = dividend_high & 0xffffffff;
	c = dividend_low >> 32;
	d = dividend_low & 0xffffffff;

	w = a / divisor;
	ra = ((u64)(a - (w * divisor)) << 32) + b;

	rb = ((u64) do_div(ra, divisor) << 32) + c;
	x = ra;

	rc = ((u64) do_div(rb, divisor) << 32) + d;
	y = rb;

	do_div(rc, divisor);
	z = rc;

	dr->result_high = ((u64)w << 32) + x;
	dr->result_low  = ((u64)y << 32) + z;

}

/* We don't need to calibrate delay, we use the CPU timebase for that */
void calibrate_delay(void)
{
	/* Some generic code (such as spinlock debug) use loops_per_jiffy
	 * as the number of __delay(1) in a jiffy, so make it so
	 */
	loops_per_jiffy = tb_ticks_per_jiffy;
}

static int __init rtc_init(void)
{
	struct platform_device *pdev;

	if (!ppc_md.get_rtc_time)
		return -ENODEV;

	pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0);
	if (IS_ERR(pdev))
		return PTR_ERR(pdev);

	return 0;
}

module_init(rtc_init);