aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/time.c
blob: 23436b6c18811a4ae1e2aa56b763d519aa890bfd (plain) (blame)
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
/*
 * 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/config.h>
#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 <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>
#ifdef CONFIG_PPC64
#include <asm/systemcfg.h>
#include <asm/firmware.h>
#endif
#ifdef CONFIG_PPC_ISERIES
#include <asm/iSeries/ItLpQueue.h>
#include <asm/iSeries/HvCallXm.h>
#endif

/* keep track of when we need to update the rtc */
time_t last_rtc_update;
extern int piranha_simulator;
#ifdef CONFIG_PPC_ISERIES
unsigned long iSeries_recal_titan = 0;
unsigned long iSeries_recal_tb = 0; 
static unsigned long first_settimeofday = 1;
#endif

/* The decrementer counts down by 128 every 128ns on a 601. */
#define DECREMENTER_COUNT_601	(1000000000 / HZ)

#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;
u64 tb_to_xs;
unsigned tb_to_us;
unsigned long processor_freq;
DEFINE_SPINLOCK(rtc_lock);
EXPORT_SYMBOL_GPL(rtc_lock);

u64 tb_to_ns_scale;
unsigned tb_to_ns_shift;

struct gettimeofday_struct do_gtod;

extern unsigned long wall_jiffies;

extern struct timezone sys_tz;
static long timezone_offset;

void ppc_adjtimex(void);

static unsigned adjusting_time = 0;

unsigned long ppc_proc_freq;
unsigned long ppc_tb_freq;

#ifdef CONFIG_PPC32	/* XXX for now */
#define boot_cpuid	0
#endif

u64 tb_last_jiffy __cacheline_aligned_in_smp;
unsigned long tb_last_stamp;

/*
 * Note that on ppc32 this only stores the bottom 32 bits of
 * the timebase value, but that's enough to tell when a jiffy
 * has passed.
 */
DEFINE_PER_CPU(unsigned long, last_jiffy);

static __inline__ void timer_check_rtc(void)
{
        /*
         * update the rtc when needed, this should be performed on the
         * right fraction of a second. Half or full second ?
         * Full second works on mk48t59 clocks, others need testing.
         * Note that this update is basically only used through 
         * the adjtimex system calls. Setting the HW clock in
         * any other way is a /dev/rtc and userland business.
         * This is still wrong by -0.5/+1.5 jiffies because of the
         * timer interrupt resolution and possible delay, but here we 
         * hit a quantization limit which can only be solved by higher
         * resolution timers and decoupling time management from timer
         * interrupts. This is also wrong on the clocks
         * which require being written at the half second boundary.
         * We should have an rtc call that only sets the minutes and
         * seconds like on Intel to avoid problems with non UTC clocks.
         */
        if (ppc_md.set_rtc_time && ntp_synced() &&
	    xtime.tv_sec - last_rtc_update >= 659 &&
	    abs((xtime.tv_nsec/1000) - (1000000-1000000/HZ)) < 500000/HZ &&
	    jiffies - wall_jiffies == 1) {
		struct rtc_time tm;
		to_tm(xtime.tv_sec + 1 + timezone_offset, &tm);
		tm.tm_year -= 1900;
		tm.tm_mon -= 1;
		if (ppc_md.set_rtc_time(&tm) == 0)
			last_rtc_update = xtime.tv_sec + 1;
		else
			/* Try again one minute later */
			last_rtc_update += 60;
        }
}

/*
 * This version of gettimeofday has microsecond resolution.
 */
static inline void __do_gettimeofday(struct timeval *tv, u64 tb_val)
{
	unsigned long sec, usec;
	u64 tb_ticks, xsec;
	struct gettimeofday_vars *temp_varp;
	u64 temp_tb_to_xs, temp_stamp_xsec;

	/*
	 * These calculations are faster (gets rid of divides)
	 * if done in units of 1/2^20 rather than microseconds.
	 * The conversion to microseconds at the end is done
	 * without a divide (and in fact, without a multiply)
	 */
	temp_varp = do_gtod.varp;
	tb_ticks = tb_val - temp_varp->tb_orig_stamp;
	temp_tb_to_xs = temp_varp->tb_to_xs;
	temp_stamp_xsec = temp_varp->stamp_xsec;
	xsec = temp_stamp_xsec + mulhdu(tb_ticks, temp_tb_to_xs);
	sec = xsec / XSEC_PER_SEC;
	usec = (unsigned long)xsec & (XSEC_PER_SEC - 1);
	usec = SCALE_XSEC(usec, 1000000);

	tv->tv_sec = sec;
	tv->tv_usec = usec;
}

void do_gettimeofday(struct timeval *tv)
{
	if (__USE_RTC()) {
		/* do this the old way */
		unsigned long flags, seq;
		unsigned int sec, nsec, usec, lost;

		do {
			seq = read_seqbegin_irqsave(&xtime_lock, flags);
			sec = xtime.tv_sec;
			nsec = xtime.tv_nsec + tb_ticks_since(tb_last_stamp);
			lost = jiffies - wall_jiffies;
		} while (read_seqretry_irqrestore(&xtime_lock, seq, flags));
		usec = nsec / 1000 + lost * (1000000 / HZ);
		while (usec >= 1000000) {
			usec -= 1000000;
			++sec;
		}
		tv->tv_sec = sec;
		tv->tv_usec = usec;
		return;
	}
	__do_gettimeofday(tv, get_tb());
}

EXPORT_SYMBOL(do_gettimeofday);

/* Synchronize xtime with do_gettimeofday */ 

static inline void timer_sync_xtime(unsigned long cur_tb)
{
#ifdef CONFIG_PPC64
	/* why do we do this? */
	struct timeval my_tv;

	__do_gettimeofday(&my_tv, cur_tb);

	if (xtime.tv_sec <= my_tv.tv_sec) {
		xtime.tv_sec = my_tv.tv_sec;
		xtime.tv_nsec = my_tv.tv_usec * 1000;
	}
#endif
}

/*
 * There are two copies of tb_to_xs and stamp_xsec so that no
 * lock is needed to access and use these values in
 * do_gettimeofday.  We alternate the copies and as long as a
 * reasonable time elapses between changes, there will never
 * be inconsistent values.  ntpd has a minimum of one minute
 * between updates.
 */
static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
			       u64 new_tb_to_xs)
{
	unsigned temp_idx;
	struct gettimeofday_vars *temp_varp;

	temp_idx = (do_gtod.var_idx == 0);
	temp_varp = &do_gtod.vars[temp_idx];

	temp_varp->tb_to_xs = new_tb_to_xs;
	temp_varp->tb_orig_stamp = new_tb_stamp;
	temp_varp->stamp_xsec = new_stamp_xsec;
	smp_mb();
	do_gtod.varp = temp_varp;
	do_gtod.var_idx = temp_idx;

#ifdef CONFIG_PPC64
	/*
	 * 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.
	 */
	++(systemcfg->tb_update_count);
	smp_wmb();
	systemcfg->tb_orig_stamp = new_tb_stamp;
	systemcfg->stamp_xsec = new_stamp_xsec;
	systemcfg->tb_to_xs = new_tb_to_xs;
	smp_wmb();
	++(systemcfg->tb_update_count);
#endif
}

/*
 * When the timebase - tb_orig_stamp gets too big, we do a manipulation
 * between tb_orig_stamp and stamp_xsec. The goal here is to keep the
 * difference tb - tb_orig_stamp small enough to always fit inside a
 * 32 bits number. This is a requirement of our fast 32 bits userland
 * implementation in the vdso. If we "miss" a call to this function
 * (interrupt latency, CPU locked in a spinlock, ...) and we end up
 * with a too big difference, then the vdso will fallback to calling
 * the syscall
 */
static __inline__ void timer_recalc_offset(u64 cur_tb)
{
	unsigned long offset;
	u64 new_stamp_xsec;

	if (__USE_RTC())
		return;
	offset = cur_tb - do_gtod.varp->tb_orig_stamp;
	if ((offset & 0x80000000u) == 0)
		return;
	new_stamp_xsec = do_gtod.varp->stamp_xsec
		+ mulhdu(offset, do_gtod.varp->tb_to_xs);
	update_gtod(cur_tb, new_stamp_xsec, do_gtod.varp->tb_to_xs);
}

#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 void iSeries_tb_recal(void)
{
	struct div_result divres;
	unsigned long titan, tb;
	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 = (new_tb_ticks_per_sec+(HZ/2))/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;
				div128_by_32( XSEC_PER_SEC, 0, tb_ticks_per_sec, &divres );
				do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
				tb_to_xs = divres.result_low;
				do_gtod.varp->tb_to_xs = tb_to_xs;
				systemcfg->tb_ticks_per_sec = tb_ticks_per_sec;
				systemcfg->tb_to_xs = tb_to_xs;
			}
			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;
}
#endif

/*
 * 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)
{
	int next_dec;
	int cpu = smp_processor_id();
	unsigned long ticks;

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

	irq_enter();

	profile_tick(CPU_PROFILING, regs);

#ifdef CONFIG_PPC_ISERIES
	get_paca()->lppaca.int_dword.fields.decr_int = 0;
#endif

	while ((ticks = tb_ticks_since(per_cpu(last_jiffy, cpu)))
	       >= tb_ticks_per_jiffy) {
		/* Update last_jiffy */
		per_cpu(last_jiffy, cpu) += tb_ticks_per_jiffy;
		/* Handle RTCL overflow on 601 */
		if (__USE_RTC() && per_cpu(last_jiffy, cpu) >= 1000000000)
			per_cpu(last_jiffy, cpu) -= 1000000000;

		/*
		 * We cannot disable the decrementer, so in the period
		 * between this cpu's being marked offline in cpu_online_map
		 * and calling stop-self, it is taking timer interrupts.
		 * Avoid calling into the scheduler rebalancing code if this
		 * is the case.
		 */
		if (!cpu_is_offline(cpu))
			update_process_times(user_mode(regs));

		/*
		 * No need to check whether cpu is offline here; boot_cpuid
		 * should have been fixed up by now.
		 */
		if (cpu != boot_cpuid)
			continue;

		write_seqlock(&xtime_lock);
		tb_last_jiffy += tb_ticks_per_jiffy;
		tb_last_stamp = per_cpu(last_jiffy, cpu);
		timer_recalc_offset(tb_last_jiffy);
		do_timer(regs);
		timer_sync_xtime(tb_last_jiffy);
		timer_check_rtc();
		write_sequnlock(&xtime_lock);
		if (adjusting_time && (time_adjust == 0))
			ppc_adjtimex();
	}
	
	next_dec = tb_ticks_per_jiffy - ticks;
	set_dec(next_dec);

#ifdef CONFIG_PPC_ISERIES
	if (hvlpevent_is_pending())
		process_hvlpevents(regs);
#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();
}

void wakeup_decrementer(void)
{
	int i;

	set_dec(tb_ticks_per_jiffy);
	/*
	 * We don't expect this to be called on a machine with a 601,
	 * so using get_tbl is fine.
	 */
	tb_last_stamp = tb_last_jiffy = get_tb();
	for_each_cpu(i)
		per_cpu(last_jiffy, i) = tb_last_stamp;
}

#ifdef CONFIG_SMP
void __init smp_space_timers(unsigned int max_cpus)
{
	int i;
	unsigned long offset = tb_ticks_per_jiffy / max_cpus;
	unsigned long previous_tb = per_cpu(last_jiffy, boot_cpuid);

	for_each_cpu(i) {
		if (i != boot_cpuid) {
			previous_tb += offset;
			per_cpu(last_jiffy, i) = previous_tb;
		}
	}
}
#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(), tb_to_ns_scale) << tb_to_ns_shift;
}

int do_settimeofday(struct timespec *tv)
{
	time_t wtm_sec, new_sec = tv->tv_sec;
	long wtm_nsec, new_nsec = tv->tv_nsec;
	unsigned long flags;
	long int tb_delta;
	u64 new_xsec, tb_delta_xs;

	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
		return -EINVAL;

	write_seqlock_irqsave(&xtime_lock, flags);

	/*
	 * Updating the RTC is not the job of this code. If the time is
	 * stepped under NTP, the RTC will be updated after STA_UNSYNC
	 * is cleared.  Tools like clock/hwclock either copy the RTC
	 * to the system time, in which case there is no point in writing
	 * to the RTC again, or write to the RTC but then they don't call
	 * settimeofday to perform this operation.
	 */
#ifdef CONFIG_PPC_ISERIES
	if (first_settimeofday) {
		iSeries_tb_recal();
		first_settimeofday = 0;
	}
#endif
	tb_delta = tb_ticks_since(tb_last_stamp);
	tb_delta += (jiffies - wall_jiffies) * tb_ticks_per_jiffy;
	tb_delta_xs = mulhdu(tb_delta, do_gtod.varp->tb_to_xs);

	wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - new_sec);
	wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - new_nsec);

 	set_normalized_timespec(&xtime, new_sec, new_nsec);
	set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);

	/* In case of a large backwards jump in time with NTP, we want the 
	 * clock to be updated as soon as the PLL is again in lock.
	 */
	last_rtc_update = new_sec - 658;

	ntp_clear();

	new_xsec = 0;
	if (new_nsec != 0) {
		new_xsec = (u64)new_nsec * XSEC_PER_SEC;
		do_div(new_xsec, NSEC_PER_SEC);
	}
	new_xsec += (u64)new_sec * XSEC_PER_SEC - tb_delta_xs;
	update_gtod(tb_last_jiffy, new_xsec, do_gtod.varp->tb_to_xs);

#ifdef CONFIG_PPC64
	systemcfg->tz_minuteswest = sys_tz.tz_minuteswest;
	systemcfg->tz_dsttime = sys_tz.tz_dsttime;
#endif

	write_sequnlock_irqrestore(&xtime_lock, flags);
	clock_was_set();
	return 0;
}

EXPORT_SYMBOL(do_settimeofday);

void __init generic_calibrate_decr(void)
{
	struct device_node *cpu;
	unsigned int *fp;
	int node_found;

	/*
	 * The cpu node should have a timebase-frequency property
	 * to tell us the rate at which the decrementer counts.
	 */
	cpu = of_find_node_by_type(NULL, "cpu");

	ppc_tb_freq = DEFAULT_TB_FREQ;		/* hardcoded default */
	node_found = 0;
	if (cpu != 0) {
		fp = (unsigned int *)get_property(cpu, "timebase-frequency",
						  NULL);
		if (fp != 0) {
			node_found = 1;
			ppc_tb_freq = *fp;
		}
	}
	if (!node_found)
		printk(KERN_ERR "WARNING: Estimating decrementer frequency "
				"(not found)\n");

	ppc_proc_freq = DEFAULT_PROC_FREQ;
	node_found = 0;
	if (cpu != 0) {
		fp = (unsigned int *)get_property(cpu, "clock-frequency",
						  NULL);
		if (fp != 0) {
			node_found = 1;
			ppc_proc_freq = *fp;
		}
	}
#ifdef CONFIG_BOOKE
	/* Set the time base to zero */
	mtspr(SPRN_TBWL, 0);
	mtspr(SPRN_TBWU, 0);

	/* 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
	if (!node_found)
		printk(KERN_ERR "WARNING: Estimating processor frequency "
				"(not found)\n");

	of_node_put(cpu);
}

unsigned long get_boot_time(void)
{
	struct rtc_time tm;

	if (ppc_md.get_boot_time)
		return ppc_md.get_boot_time();
	if (!ppc_md.get_rtc_time)
		return 0;
	ppc_md.get_rtc_time(&tm);
	return mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday,
		      tm.tm_hour, tm.tm_min, tm.tm_sec);
}

/* This function is only called on the boot processor */
void __init time_init(void)
{
	unsigned long flags;
	unsigned long tm = 0;
	struct div_result res;
	u64 scale;
	unsigned shift;

        if (ppc_md.time_init != NULL)
                timezone_offset = ppc_md.time_init();

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

	tb_ticks_per_jiffy = ppc_tb_freq / HZ;
	tb_ticks_per_sec = tb_ticks_per_jiffy * HZ;
	tb_ticks_per_usec = ppc_tb_freq / 1000000;
	tb_to_us = mulhwu_scale_factor(ppc_tb_freq, 1000000);
	div128_by_32(1024*1024, 0, tb_ticks_per_sec, &res);
	tb_to_xs = res.result_low;

#ifdef CONFIG_PPC64
	get_paca()->default_decr = tb_ticks_per_jiffy;
#endif

	/*
	 * 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;

#ifdef CONFIG_PPC_ISERIES
	if (!piranha_simulator)
#endif
		tm = get_boot_time();

	write_seqlock_irqsave(&xtime_lock, flags);
	xtime.tv_sec = tm;
	xtime.tv_nsec = 0;
	do_gtod.varp = &do_gtod.vars[0];
	do_gtod.var_idx = 0;
	do_gtod.varp->tb_orig_stamp = tb_last_jiffy;
	__get_cpu_var(last_jiffy) = tb_last_stamp;
	do_gtod.varp->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC;
	do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
	do_gtod.varp->tb_to_xs = tb_to_xs;
	do_gtod.tb_to_us = tb_to_us;
#ifdef CONFIG_PPC64
	systemcfg->tb_orig_stamp = tb_last_jiffy;
	systemcfg->tb_update_count = 0;
	systemcfg->tb_ticks_per_sec = tb_ticks_per_sec;
	systemcfg->stamp_xsec = xtime.tv_sec * XSEC_PER_SEC;
	systemcfg->tb_to_xs = tb_to_xs;
#endif

	time_freq = 0;

	/* 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;
		xtime.tv_sec -= timezone_offset;
        }

	last_rtc_update = xtime.tv_sec;
	set_normalized_timespec(&wall_to_monotonic,
	                        -xtime.tv_sec, -xtime.tv_nsec);
	write_sequnlock_irqrestore(&xtime_lock, flags);

	/* Not exact, but the timer interrupt takes care of this */
	set_dec(tb_ticks_per_jiffy);
}

/* 
 * After adjtimex is called, adjust the conversion of tb ticks
 * to microseconds to keep do_gettimeofday synchronized 
 * with ntpd.
 *
 * Use the time_adjust, time_freq and time_offset computed by adjtimex to 
 * adjust the frequency.
 */

/* #define DEBUG_PPC_ADJTIMEX 1 */

void ppc_adjtimex(void)
{
#ifdef CONFIG_PPC64
	unsigned long den, new_tb_ticks_per_sec, tb_ticks, old_xsec,
		new_tb_to_xs, new_xsec, new_stamp_xsec;
	unsigned long tb_ticks_per_sec_delta;
	long delta_freq, ltemp;
	struct div_result divres; 
	unsigned long flags;
	long singleshot_ppm = 0;

	/*
	 * Compute parts per million frequency adjustment to
	 * accomplish the time adjustment implied by time_offset to be
	 * applied over the elapsed time indicated by time_constant.
	 * Use SHIFT_USEC to get it into the same units as
	 * time_freq.
	 */
	if ( time_offset < 0 ) {
		ltemp = -time_offset;
		ltemp <<= SHIFT_USEC - SHIFT_UPDATE;
		ltemp >>= SHIFT_KG + time_constant;
		ltemp = -ltemp;
	} else {
		ltemp = time_offset;
		ltemp <<= SHIFT_USEC - SHIFT_UPDATE;
		ltemp >>= SHIFT_KG + time_constant;
	}
	
	/* If there is a single shot time adjustment in progress */
	if ( time_adjust ) {
#ifdef DEBUG_PPC_ADJTIMEX
		printk("ppc_adjtimex: ");
		if ( adjusting_time == 0 )
			printk("starting ");
		printk("single shot time_adjust = %ld\n", time_adjust);
#endif	
	
		adjusting_time = 1;
		
		/*
		 * Compute parts per million frequency adjustment
		 * to match time_adjust
		 */
		singleshot_ppm = tickadj * HZ;	
		/*
		 * The adjustment should be tickadj*HZ to match the code in
		 * linux/kernel/timer.c, but experiments show that this is too
		 * large. 3/4 of tickadj*HZ seems about right
		 */
		singleshot_ppm -= singleshot_ppm / 4;
		/* Use SHIFT_USEC to get it into the same units as time_freq */
		singleshot_ppm <<= SHIFT_USEC;
		if ( time_adjust < 0 )
			singleshot_ppm = -singleshot_ppm;
	}
	else {
#ifdef DEBUG_PPC_ADJTIMEX
		if ( adjusting_time )
			printk("ppc_adjtimex: ending single shot time_adjust\n");
#endif
		adjusting_time = 0;
	}
	
	/* Add up all of the frequency adjustments */
	delta_freq = time_freq + ltemp + singleshot_ppm;
	
	/*
	 * Compute a new value for tb_ticks_per_sec based on
	 * the frequency adjustment
	 */
	den = 1000000 * (1 << (SHIFT_USEC - 8));
	if ( delta_freq < 0 ) {
		tb_ticks_per_sec_delta = ( tb_ticks_per_sec * ( (-delta_freq) >> (SHIFT_USEC - 8))) / den;
		new_tb_ticks_per_sec = tb_ticks_per_sec + tb_ticks_per_sec_delta;
	}
	else {
		tb_ticks_per_sec_delta = ( tb_ticks_per_sec * ( delta_freq >> (SHIFT_USEC - 8))) / den;
		new_tb_ticks_per_sec = tb_ticks_per_sec - tb_ticks_per_sec_delta;
	}
	
#ifdef DEBUG_PPC_ADJTIMEX
	printk("ppc_adjtimex: ltemp = %ld, time_freq = %ld, singleshot_ppm = %ld\n", ltemp, time_freq, singleshot_ppm);
	printk("ppc_adjtimex: tb_ticks_per_sec - base = %ld  new = %ld\n", tb_ticks_per_sec, new_tb_ticks_per_sec);
#endif

	/*
	 * Compute a new value of tb_to_xs (used to convert tb to
	 * microseconds) and a new value of stamp_xsec which is the
	 * time (in 1/2^20 second units) corresponding to
	 * tb_orig_stamp.  This new value of stamp_xsec compensates
	 * for the change in frequency (implied by the new tb_to_xs)
	 * which guarantees that the current time remains the same.
	 */
	write_seqlock_irqsave( &xtime_lock, flags );
	tb_ticks = get_tb() - do_gtod.varp->tb_orig_stamp;
	div128_by_32(1024*1024, 0, new_tb_ticks_per_sec, &divres);
	new_tb_to_xs = divres.result_low;
	new_xsec = mulhdu(tb_ticks, new_tb_to_xs);

	old_xsec = mulhdu(tb_ticks, do_gtod.varp->tb_to_xs);
	new_stamp_xsec = do_gtod.varp->stamp_xsec + old_xsec - new_xsec;

	update_gtod(do_gtod.varp->tb_orig_stamp, new_stamp_xsec, new_tb_to_xs);

	write_sequnlock_irqrestore( &xtime_lock, flags );
#endif /* CONFIG_PPC64 */
}


#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);
}

/* Auxiliary function to compute scaling factors */
/* Actually the choice of a timebase running at 1/4 the of the bus
 * frequency giving resolution of a few tens of nanoseconds is quite nice.
 * It makes this computation very precise (27-28 bits typically) which
 * is optimistic considering the stability of most processor clock
 * oscillators and the precision with which the timebase frequency
 * is measured but does not harm.
 */
unsigned mulhwu_scale_factor(unsigned inscale, unsigned outscale)
{
        unsigned mlt=0, tmp, err;
        /* No concern for performance, it's done once: use a stupid
         * but safe and compact method to find the multiplier.
         */
  
        for (tmp = 1U<<31; tmp != 0; tmp >>= 1) {
                if (mulhwu(inscale, mlt|tmp) < outscale)
			mlt |= tmp;
        }
  
        /* We might still be off by 1 for the best approximation.
         * A side effect of this is that if outscale is too large
         * the returned value will be zero.
         * Many corner cases have been checked and seem to work,
         * some might have been forgotten in the test however.
         */
  
        err = inscale * (mlt+1);
        if (err <= inscale/2)
		mlt++;
        return mlt;
}

/*
 * 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;

}