aboutsummaryrefslogtreecommitdiff
path: root/arch/x86_64/kernel/time.c
blob: 557e92af7beabdf84b58d265ecda54bb5dbf4f58 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
/*
 *  linux/arch/x86-64/kernel/time.c
 *
 *  "High Precision Event Timer" based timekeeping.
 *
 *  Copyright (c) 1991,1992,1995  Linus Torvalds
 *  Copyright (c) 1994  Alan Modra
 *  Copyright (c) 1995  Markus Kuhn
 *  Copyright (c) 1996  Ingo Molnar
 *  Copyright (c) 1998  Andrea Arcangeli
 *  Copyright (c) 2002,2006  Vojtech Pavlik
 *  Copyright (c) 2003  Andi Kleen
 *  RTC support code taken from arch/i386/kernel/timers/time_hpet.c
 */

#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/mc146818rtc.h>
#include <linux/time.h>
#include <linux/ioport.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/sysdev.h>
#include <linux/bcd.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/kallsyms.h>
#include <linux/acpi.h>
#ifdef CONFIG_ACPI
#include <acpi/achware.h>	/* for PM timer frequency */
#include <acpi/acpi_bus.h>
#endif
#include <asm/8253pit.h>
#include <asm/pgtable.h>
#include <asm/vsyscall.h>
#include <asm/timex.h>
#include <asm/proto.h>
#include <asm/hpet.h>
#include <asm/sections.h>
#include <linux/cpufreq.h>
#include <linux/hpet.h>
#include <asm/apic.h>

#ifdef CONFIG_CPU_FREQ
static void cpufreq_delayed_get(void);
#endif
extern void i8254_timer_resume(void);
extern int using_apic_timer;

static char *timename = NULL;

DEFINE_SPINLOCK(rtc_lock);
EXPORT_SYMBOL(rtc_lock);
DEFINE_SPINLOCK(i8253_lock);

int nohpet __initdata = 0;
static int notsc __initdata = 0;

#define USEC_PER_TICK (USEC_PER_SEC / HZ)
#define NSEC_PER_TICK (NSEC_PER_SEC / HZ)
#define FSEC_PER_TICK (FSEC_PER_SEC / HZ)

#define NS_SCALE	10 /* 2^10, carefully chosen */
#define US_SCALE	32 /* 2^32, arbitralrily chosen */

unsigned int cpu_khz;					/* TSC clocks / usec, not used here */
EXPORT_SYMBOL(cpu_khz);
static unsigned long hpet_period;			/* fsecs / HPET clock */
unsigned long hpet_tick;				/* HPET clocks / interrupt */
int hpet_use_timer;				/* Use counter of hpet for time keeping, otherwise PIT */
unsigned long vxtime_hz = PIT_TICK_RATE;
int report_lost_ticks;				/* command line option */
unsigned long long monotonic_base;

struct vxtime_data __vxtime __section_vxtime;	/* for vsyscalls */

volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
struct timespec __xtime __section_xtime;
struct timezone __sys_tz __section_sys_tz;

/*
 * do_gettimeoffset() returns microseconds since last timer interrupt was
 * triggered by hardware. A memory read of HPET is slower than a register read
 * of TSC, but much more reliable. It's also synchronized to the timer
 * interrupt. Note that do_gettimeoffset() may return more than hpet_tick, if a
 * timer interrupt has happened already, but vxtime.trigger wasn't updated yet.
 * This is not a problem, because jiffies hasn't updated either. They are bound
 * together by xtime_lock.
 */

static inline unsigned int do_gettimeoffset_tsc(void)
{
	unsigned long t;
	unsigned long x;
	t = get_cycles_sync();
	if (t < vxtime.last_tsc) 
		t = vxtime.last_tsc; /* hack */
	x = ((t - vxtime.last_tsc) * vxtime.tsc_quot) >> US_SCALE;
	return x;
}

static inline unsigned int do_gettimeoffset_hpet(void)
{
	/* cap counter read to one tick to avoid inconsistencies */
	unsigned long counter = hpet_readl(HPET_COUNTER) - vxtime.last;
	return (min(counter,hpet_tick) * vxtime.quot) >> US_SCALE;
}

unsigned int (*do_gettimeoffset)(void) = do_gettimeoffset_tsc;

/*
 * This version of gettimeofday() has microsecond resolution and better than
 * microsecond precision, as we're using at least a 10 MHz (usually 14.31818
 * MHz) HPET timer.
 */

void do_gettimeofday(struct timeval *tv)
{
	unsigned long seq;
 	unsigned int sec, usec;

	do {
		seq = read_seqbegin(&xtime_lock);

		sec = xtime.tv_sec;
		usec = xtime.tv_nsec / NSEC_PER_USEC;

		/* i386 does some correction here to keep the clock 
		   monotonous even when ntpd is fixing drift.
		   But they didn't work for me, there is a non monotonic
		   clock anyways with ntp.
		   I dropped all corrections now until a real solution can
		   be found. Note when you fix it here you need to do the same
		   in arch/x86_64/kernel/vsyscall.c and export all needed
		   variables in vmlinux.lds. -AK */ 
		usec += do_gettimeoffset();

	} while (read_seqretry(&xtime_lock, seq));

	tv->tv_sec = sec + usec / USEC_PER_SEC;
	tv->tv_usec = usec % USEC_PER_SEC;
}

EXPORT_SYMBOL(do_gettimeofday);

/*
 * settimeofday() first undoes the correction that gettimeofday would do
 * on the time, and then saves it. This is ugly, but has been like this for
 * ages already.
 */

int do_settimeofday(struct timespec *tv)
{
	time_t wtm_sec, sec = tv->tv_sec;
	long wtm_nsec, nsec = tv->tv_nsec;

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

	write_seqlock_irq(&xtime_lock);

	nsec -= do_gettimeoffset() * NSEC_PER_USEC;

	wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
	wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);

	set_normalized_timespec(&xtime, sec, nsec);
	set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);

	ntp_clear();

	write_sequnlock_irq(&xtime_lock);
	clock_was_set();
	return 0;
}

EXPORT_SYMBOL(do_settimeofday);

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

	/* Assume the lock function has either no stack frame or a copy
	   of eflags from PUSHF
	   Eflags always has bits 22 and up cleared unlike kernel addresses. */
	if (!user_mode(regs) && in_lock_functions(pc)) {
		unsigned long *sp = (unsigned long *)regs->rsp;
		if (sp[0] >> 22)
			return sp[0];
		if (sp[1] >> 22)
			return sp[1];
	}
	return pc;
}
EXPORT_SYMBOL(profile_pc);

/*
 * In order to set the CMOS clock precisely, set_rtc_mmss has to be called 500
 * ms after the second nowtime has started, because when nowtime is written
 * into the registers of the CMOS clock, it will jump to the next second
 * precisely 500 ms later. Check the Motorola MC146818A or Dallas DS12887 data
 * sheet for details.
 */

static void set_rtc_mmss(unsigned long nowtime)
{
	int real_seconds, real_minutes, cmos_minutes;
	unsigned char control, freq_select;

/*
 * IRQs are disabled when we're called from the timer interrupt,
 * no need for spin_lock_irqsave()
 */

	spin_lock(&rtc_lock);

/*
 * Tell the clock it's being set and stop it.
 */

	control = CMOS_READ(RTC_CONTROL);
	CMOS_WRITE(control | RTC_SET, RTC_CONTROL);

	freq_select = CMOS_READ(RTC_FREQ_SELECT);
	CMOS_WRITE(freq_select | RTC_DIV_RESET2, RTC_FREQ_SELECT);

	cmos_minutes = CMOS_READ(RTC_MINUTES);
		BCD_TO_BIN(cmos_minutes);

/*
 * since we're only adjusting minutes and seconds, don't interfere with hour
 * overflow. This avoids messing with unknown time zones but requires your RTC
 * not to be off by more than 15 minutes. Since we're calling it only when
 * our clock is externally synchronized using NTP, this shouldn't be a problem.
 */

	real_seconds = nowtime % 60;
	real_minutes = nowtime / 60;
	if (((abs(real_minutes - cmos_minutes) + 15) / 30) & 1)
		real_minutes += 30;		/* correct for half hour time zone */
	real_minutes %= 60;

	if (abs(real_minutes - cmos_minutes) >= 30) {
		printk(KERN_WARNING "time.c: can't update CMOS clock "
		       "from %d to %d\n", cmos_minutes, real_minutes);
	} else {
		BIN_TO_BCD(real_seconds);
		BIN_TO_BCD(real_minutes);
		CMOS_WRITE(real_seconds, RTC_SECONDS);
		CMOS_WRITE(real_minutes, RTC_MINUTES);
	}

/*
 * The following flags have to be released exactly in this order, otherwise the
 * DS12887 (popular MC146818A clone with integrated battery and quartz) will
 * not reset the oscillator and will not update precisely 500 ms later. You
 * won't find this mentioned in the Dallas Semiconductor data sheets, but who
 * believes data sheets anyway ... -- Markus Kuhn
 */

	CMOS_WRITE(control, RTC_CONTROL);
	CMOS_WRITE(freq_select, RTC_FREQ_SELECT);

	spin_unlock(&rtc_lock);
}


/* monotonic_clock(): returns # of nanoseconds passed since time_init()
 *		Note: This function is required to return accurate
 *		time even in the absence of multiple timer ticks.
 */
static inline unsigned long long cycles_2_ns(unsigned long long cyc);
unsigned long long monotonic_clock(void)
{
	unsigned long seq;
 	u32 last_offset, this_offset, offset;
	unsigned long long base;

	if (vxtime.mode == VXTIME_HPET) {
		do {
			seq = read_seqbegin(&xtime_lock);

			last_offset = vxtime.last;
			base = monotonic_base;
			this_offset = hpet_readl(HPET_COUNTER);
		} while (read_seqretry(&xtime_lock, seq));
		offset = (this_offset - last_offset);
		offset *= NSEC_PER_TICK / hpet_tick;
	} else {
		do {
			seq = read_seqbegin(&xtime_lock);

			last_offset = vxtime.last_tsc;
			base = monotonic_base;
		} while (read_seqretry(&xtime_lock, seq));
		this_offset = get_cycles_sync();
		offset = cycles_2_ns(this_offset - last_offset);
	}
	return base + offset;
}
EXPORT_SYMBOL(monotonic_clock);

static noinline void handle_lost_ticks(int lost, struct pt_regs *regs)
{
	static long lost_count;
	static int warned;
	if (report_lost_ticks) {
		printk(KERN_WARNING "time.c: Lost %d timer tick(s)! ", lost);
		print_symbol("rip %s)\n", regs->rip);
	}

	if (lost_count == 1000 && !warned) {
		printk(KERN_WARNING "warning: many lost ticks.\n"
		       KERN_WARNING "Your time source seems to be instable or "
		   		"some driver is hogging interupts\n");
		print_symbol("rip %s\n", regs->rip);
		if (vxtime.mode == VXTIME_TSC && vxtime.hpet_address) {
			printk(KERN_WARNING "Falling back to HPET\n");
			if (hpet_use_timer)
				vxtime.last = hpet_readl(HPET_T0_CMP) - 
							hpet_tick;
			else
				vxtime.last = hpet_readl(HPET_COUNTER);
			vxtime.mode = VXTIME_HPET;
			do_gettimeoffset = do_gettimeoffset_hpet;
		}
		/* else should fall back to PIT, but code missing. */
		warned = 1;
	} else
		lost_count++;

#ifdef CONFIG_CPU_FREQ
	/* In some cases the CPU can change frequency without us noticing
	   Give cpufreq a change to catch up. */
	if ((lost_count+1) % 25 == 0)
		cpufreq_delayed_get();
#endif
}

void main_timer_handler(struct pt_regs *regs)
{
	static unsigned long rtc_update = 0;
	unsigned long tsc;
	int delay = 0, offset = 0, lost = 0;

/*
 * Here we are in the timer irq handler. We have irqs locally disabled (so we
 * don't need spin_lock_irqsave()) but we don't know if the timer_bh is running
 * on the other CPU, so we need a lock. We also need to lock the vsyscall
 * variables, because both do_timer() and us change them -arca+vojtech
 */

	write_seqlock(&xtime_lock);

	if (vxtime.hpet_address)
		offset = hpet_readl(HPET_COUNTER);

	if (hpet_use_timer) {
		/* if we're using the hpet timer functionality,
		 * we can more accurately know the counter value
		 * when the timer interrupt occured.
		 */
		offset = hpet_readl(HPET_T0_CMP) - hpet_tick;
		delay = hpet_readl(HPET_COUNTER) - offset;
	} else if (!pmtmr_ioport) {
		spin_lock(&i8253_lock);
		outb_p(0x00, 0x43);
		delay = inb_p(0x40);
		delay |= inb(0x40) << 8;
		spin_unlock(&i8253_lock);
		delay = LATCH - 1 - delay;
	}

	tsc = get_cycles_sync();

	if (vxtime.mode == VXTIME_HPET) {
		if (offset - vxtime.last > hpet_tick) {
			lost = (offset - vxtime.last) / hpet_tick - 1;
		}

		monotonic_base += 
			(offset - vxtime.last) * NSEC_PER_TICK / hpet_tick;

		vxtime.last = offset;
#ifdef CONFIG_X86_PM_TIMER
	} else if (vxtime.mode == VXTIME_PMTMR) {
		lost = pmtimer_mark_offset();
#endif
	} else {
		offset = (((tsc - vxtime.last_tsc) *
			   vxtime.tsc_quot) >> US_SCALE) - USEC_PER_TICK;

		if (offset < 0)
			offset = 0;

		if (offset > USEC_PER_TICK) {
			lost = offset / USEC_PER_TICK;
			offset %= USEC_PER_TICK;
		}

		monotonic_base += cycles_2_ns(tsc - vxtime.last_tsc);

		vxtime.last_tsc = tsc - vxtime.quot * delay / vxtime.tsc_quot;

		if ((((tsc - vxtime.last_tsc) *
		      vxtime.tsc_quot) >> US_SCALE) < offset)
			vxtime.last_tsc = tsc -
				(((long) offset << US_SCALE) / vxtime.tsc_quot) - 1;
	}

	if (lost > 0)
		handle_lost_ticks(lost, regs);
	else
		lost = 0;

/*
 * Do the timer stuff.
 */

	do_timer(lost + 1);
#ifndef CONFIG_SMP
	update_process_times(user_mode(regs));
#endif

/*
 * In the SMP case we use the local APIC timer interrupt to do the profiling,
 * except when we simulate SMP mode on a uniprocessor system, in that case we
 * have to call the local interrupt handler.
 */

	if (!using_apic_timer)
		smp_local_timer_interrupt(regs);

/*
 * If we have an externally synchronized Linux clock, then update CMOS clock
 * accordingly every ~11 minutes. set_rtc_mmss() will be called in the jiffy
 * closest to exactly 500 ms before the next second. If the update fails, we
 * don't care, as it'll be updated on the next turn, and the problem (time way
 * off) isn't likely to go away much sooner anyway.
 */

	if (ntp_synced() && xtime.tv_sec > rtc_update &&
		abs(xtime.tv_nsec - 500000000) <= tick_nsec / 2) {
		set_rtc_mmss(xtime.tv_sec);
		rtc_update = xtime.tv_sec + 660;
	}
 
	write_sequnlock(&xtime_lock);
}

static irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
{
	if (apic_runs_main_timer > 1)
		return IRQ_HANDLED;
	main_timer_handler(regs);
	if (using_apic_timer)
		smp_send_timer_broadcast_ipi();
	return IRQ_HANDLED;
}

static unsigned int cyc2ns_scale __read_mostly;

static inline void set_cyc2ns_scale(unsigned long cpu_khz)
{
	cyc2ns_scale = (NSEC_PER_MSEC << NS_SCALE) / cpu_khz;
}

static inline unsigned long long cycles_2_ns(unsigned long long cyc)
{
	return (cyc * cyc2ns_scale) >> NS_SCALE;
}

unsigned long long sched_clock(void)
{
	unsigned long a = 0;

#if 0
	/* Don't do a HPET read here. Using TSC always is much faster
	   and HPET may not be mapped yet when the scheduler first runs.
           Disadvantage is a small drift between CPUs in some configurations,
	   but that should be tolerable. */
	if (__vxtime.mode == VXTIME_HPET)
		return (hpet_readl(HPET_COUNTER) * vxtime.quot) >> US_SCALE;
#endif

	/* Could do CPU core sync here. Opteron can execute rdtsc speculatively,
	   which means it is not completely exact and may not be monotonous between
	   CPUs. But the errors should be too small to matter for scheduling
	   purposes. */

	rdtscll(a);
	return cycles_2_ns(a);
}

static unsigned long get_cmos_time(void)
{
	unsigned int year, mon, day, hour, min, sec;
	unsigned long flags;
	unsigned extyear = 0;

	spin_lock_irqsave(&rtc_lock, flags);

	do {
		sec = CMOS_READ(RTC_SECONDS);
		min = CMOS_READ(RTC_MINUTES);
		hour = CMOS_READ(RTC_HOURS);
		day = CMOS_READ(RTC_DAY_OF_MONTH);
		mon = CMOS_READ(RTC_MONTH);
		year = CMOS_READ(RTC_YEAR);
#ifdef CONFIG_ACPI
		if (acpi_fadt.revision >= FADT2_REVISION_ID &&
					acpi_fadt.century)
			extyear = CMOS_READ(acpi_fadt.century);
#endif
	} while (sec != CMOS_READ(RTC_SECONDS));

	spin_unlock_irqrestore(&rtc_lock, flags);

	/*
	 * We know that x86-64 always uses BCD format, no need to check the
	 * config register.
 	 */

	BCD_TO_BIN(sec);
	BCD_TO_BIN(min);
	BCD_TO_BIN(hour);
	BCD_TO_BIN(day);
	BCD_TO_BIN(mon);
	BCD_TO_BIN(year);

	if (extyear) {
		BCD_TO_BIN(extyear);
		year += extyear;
		printk(KERN_INFO "Extended CMOS year: %d\n", extyear);
	} else { 
		/*
		 * x86-64 systems only exists since 2002.
		 * This will work up to Dec 31, 2100
	 	 */
		year += 2000;
	}

	return mktime(year, mon, day, hour, min, sec);
}

#ifdef CONFIG_CPU_FREQ

/* Frequency scaling support. Adjust the TSC based timer when the cpu frequency
   changes.
   
   RED-PEN: On SMP we assume all CPUs run with the same frequency.  It's
   not that important because current Opteron setups do not support
   scaling on SMP anyroads.

   Should fix up last_tsc too. Currently gettimeofday in the
   first tick after the change will be slightly wrong. */

#include <linux/workqueue.h>

static unsigned int cpufreq_delayed_issched = 0;
static unsigned int cpufreq_init = 0;
static struct work_struct cpufreq_delayed_get_work;

static void handle_cpufreq_delayed_get(void *v)
{
	unsigned int cpu;
	for_each_online_cpu(cpu) {
		cpufreq_get(cpu);
	}
	cpufreq_delayed_issched = 0;
}

/* if we notice lost ticks, schedule a call to cpufreq_get() as it tries
 * to verify the CPU frequency the timing core thinks the CPU is running
 * at is still correct.
 */
static void cpufreq_delayed_get(void)
{
	static int warned;
	if (cpufreq_init && !cpufreq_delayed_issched) {
		cpufreq_delayed_issched = 1;
		if (!warned) {
			warned = 1;
			printk(KERN_DEBUG 
	"Losing some ticks... checking if CPU frequency changed.\n");
		}
		schedule_work(&cpufreq_delayed_get_work);
	}
}

static unsigned int  ref_freq = 0;
static unsigned long loops_per_jiffy_ref = 0;

static unsigned long cpu_khz_ref = 0;

static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
				 void *data)
{
        struct cpufreq_freqs *freq = data;
	unsigned long *lpj, dummy;

	if (cpu_has(&cpu_data[freq->cpu], X86_FEATURE_CONSTANT_TSC))
		return 0;

	lpj = &dummy;
	if (!(freq->flags & CPUFREQ_CONST_LOOPS))
#ifdef CONFIG_SMP
		lpj = &cpu_data[freq->cpu].loops_per_jiffy;
#else
		lpj = &boot_cpu_data.loops_per_jiffy;
#endif

	if (!ref_freq) {
		ref_freq = freq->old;
		loops_per_jiffy_ref = *lpj;
		cpu_khz_ref = cpu_khz;
	}
        if ((val == CPUFREQ_PRECHANGE  && freq->old < freq->new) ||
            (val == CPUFREQ_POSTCHANGE && freq->old > freq->new) ||
	    (val == CPUFREQ_RESUMECHANGE)) {
                *lpj =
		cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);

		cpu_khz = cpufreq_scale(cpu_khz_ref, ref_freq, freq->new);
		if (!(freq->flags & CPUFREQ_CONST_LOOPS))
			vxtime.tsc_quot = (USEC_PER_MSEC << US_SCALE) / cpu_khz;
	}
	
	set_cyc2ns_scale(cpu_khz_ref);

	return 0;
}
 
static struct notifier_block time_cpufreq_notifier_block = {
         .notifier_call  = time_cpufreq_notifier
};

static int __init cpufreq_tsc(void)
{
	INIT_WORK(&cpufreq_delayed_get_work, handle_cpufreq_delayed_get, NULL);
	if (!cpufreq_register_notifier(&time_cpufreq_notifier_block,
				       CPUFREQ_TRANSITION_NOTIFIER))
		cpufreq_init = 1;
	return 0;
}

core_initcall(cpufreq_tsc);

#endif

/*
 * calibrate_tsc() calibrates the processor TSC in a very simple way, comparing
 * it to the HPET timer of known frequency.
 */

#define TICK_COUNT 100000000

static unsigned int __init hpet_calibrate_tsc(void)
{
	int tsc_start, hpet_start;
	int tsc_now, hpet_now;
	unsigned long flags;

	local_irq_save(flags);
	local_irq_disable();

	hpet_start = hpet_readl(HPET_COUNTER);
	rdtscl(tsc_start);

	do {
		local_irq_disable();
		hpet_now = hpet_readl(HPET_COUNTER);
		tsc_now = get_cycles_sync();
		local_irq_restore(flags);
	} while ((tsc_now - tsc_start) < TICK_COUNT &&
		 (hpet_now - hpet_start) < TICK_COUNT);

	return (tsc_now - tsc_start) * 1000000000L
		/ ((hpet_now - hpet_start) * hpet_period / 1000);
}


/*
 * pit_calibrate_tsc() uses the speaker output (channel 2) of
 * the PIT. This is better than using the timer interrupt output,
 * because we can read the value of the speaker with just one inb(),
 * where we need three i/o operations for the interrupt channel.
 * We count how many ticks the TSC does in 50 ms.
 */

static unsigned int __init pit_calibrate_tsc(void)
{
	unsigned long start, end;
	unsigned long flags;

	spin_lock_irqsave(&i8253_lock, flags);

	outb((inb(0x61) & ~0x02) | 0x01, 0x61);

	outb(0xb0, 0x43);
	outb((PIT_TICK_RATE / (1000 / 50)) & 0xff, 0x42);
	outb((PIT_TICK_RATE / (1000 / 50)) >> 8, 0x42);
	start = get_cycles_sync();
	while ((inb(0x61) & 0x20) == 0);
	end = get_cycles_sync();

	spin_unlock_irqrestore(&i8253_lock, flags);
	
	return (end - start) / 50;
}

#ifdef	CONFIG_HPET
static __init int late_hpet_init(void)
{
	struct hpet_data	hd;
	unsigned int 		ntimer;

	if (!vxtime.hpet_address)
        	return 0;

	memset(&hd, 0, sizeof (hd));

	ntimer = hpet_readl(HPET_ID);
	ntimer = (ntimer & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT;
	ntimer++;

	/*
	 * Register with driver.
	 * Timer0 and Timer1 is used by platform.
	 */
	hd.hd_phys_address = vxtime.hpet_address;
	hd.hd_address = (void __iomem *)fix_to_virt(FIX_HPET_BASE);
	hd.hd_nirqs = ntimer;
	hd.hd_flags = HPET_DATA_PLATFORM;
	hpet_reserve_timer(&hd, 0);
#ifdef	CONFIG_HPET_EMULATE_RTC
	hpet_reserve_timer(&hd, 1);
#endif
	hd.hd_irq[0] = HPET_LEGACY_8254;
	hd.hd_irq[1] = HPET_LEGACY_RTC;
	if (ntimer > 2) {
		struct hpet		*hpet;
		struct hpet_timer	*timer;
		int			i;

		hpet = (struct hpet *) fix_to_virt(FIX_HPET_BASE);
		timer = &hpet->hpet_timers[2];
		for (i = 2; i < ntimer; timer++, i++)
			hd.hd_irq[i] = (timer->hpet_config &
					Tn_INT_ROUTE_CNF_MASK) >>
				Tn_INT_ROUTE_CNF_SHIFT;

	}

	hpet_alloc(&hd);
	return 0;
}
fs_initcall(late_hpet_init);
#endif

static int hpet_timer_stop_set_go(unsigned long tick)
{
	unsigned int cfg;

/*
 * Stop the timers and reset the main counter.
 */

	cfg = hpet_readl(HPET_CFG);
	cfg &= ~(HPET_CFG_ENABLE | HPET_CFG_LEGACY);
	hpet_writel(cfg, HPET_CFG);
	hpet_writel(0, HPET_COUNTER);
	hpet_writel(0, HPET_COUNTER + 4);

/*
 * Set up timer 0, as periodic with first interrupt to happen at hpet_tick,
 * and period also hpet_tick.
 */
	if (hpet_use_timer) {
		hpet_writel(HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL |
		    HPET_TN_32BIT, HPET_T0_CFG);
		hpet_writel(hpet_tick, HPET_T0_CMP); /* next interrupt */
		hpet_writel(hpet_tick, HPET_T0_CMP); /* period */
		cfg |= HPET_CFG_LEGACY;
	}
/*
 * Go!
 */

	cfg |= HPET_CFG_ENABLE;
	hpet_writel(cfg, HPET_CFG);

	return 0;
}

static int hpet_init(void)
{
	unsigned int id;

	if (!vxtime.hpet_address)
		return -1;
	set_fixmap_nocache(FIX_HPET_BASE, vxtime.hpet_address);
	__set_fixmap(VSYSCALL_HPET, vxtime.hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE);

/*
 * Read the period, compute tick and quotient.
 */

	id = hpet_readl(HPET_ID);

	if (!(id & HPET_ID_VENDOR) || !(id & HPET_ID_NUMBER))
		return -1;

	hpet_period = hpet_readl(HPET_PERIOD);
	if (hpet_period < 100000 || hpet_period > 100000000)
		return -1;

	hpet_tick = (FSEC_PER_TICK + hpet_period / 2) / hpet_period;

	hpet_use_timer = (id & HPET_ID_LEGSUP);

	return hpet_timer_stop_set_go(hpet_tick);
}

static int hpet_reenable(void)
{
	return hpet_timer_stop_set_go(hpet_tick);
}

#define PIT_MODE 0x43
#define PIT_CH0  0x40

static void __init __pit_init(int val, u8 mode)
{
	unsigned long flags;

	spin_lock_irqsave(&i8253_lock, flags);
	outb_p(mode, PIT_MODE);
	outb_p(val & 0xff, PIT_CH0);	/* LSB */
	outb_p(val >> 8, PIT_CH0);	/* MSB */
	spin_unlock_irqrestore(&i8253_lock, flags);
}

void __init pit_init(void)
{
	__pit_init(LATCH, 0x34); /* binary, mode 2, LSB/MSB, ch 0 */
}

void __init pit_stop_interrupt(void)
{
	__pit_init(0, 0x30); /* mode 0 */
}

void __init stop_timer_interrupt(void)
{
	char *name;
	if (vxtime.hpet_address) {
		name = "HPET";
		hpet_timer_stop_set_go(0);
	} else {
		name = "PIT";
		pit_stop_interrupt();
	}
	printk(KERN_INFO "timer: %s interrupt stopped.\n", name);
}

int __init time_setup(char *str)
{
	report_lost_ticks = 1;
	return 1;
}

static struct irqaction irq0 = {
	timer_interrupt, IRQF_DISABLED, CPU_MASK_NONE, "timer", NULL, NULL
};

static int __cpuinit
time_cpu_notifier(struct notifier_block *nb, unsigned long action, void *hcpu)
{
	unsigned cpu = (unsigned long) hcpu;
	if (action == CPU_ONLINE)
		vsyscall_set_cpu(cpu);
	return NOTIFY_DONE;
}

void __init time_init(void)
{
	if (nohpet)
		vxtime.hpet_address = 0;

	xtime.tv_sec = get_cmos_time();
	xtime.tv_nsec = 0;

	set_normalized_timespec(&wall_to_monotonic,
	                        -xtime.tv_sec, -xtime.tv_nsec);

	if (!hpet_init())
                vxtime_hz = (FSEC_PER_SEC + hpet_period / 2) / hpet_period;
	else
		vxtime.hpet_address = 0;

	if (hpet_use_timer) {
		/* set tick_nsec to use the proper rate for HPET */
	  	tick_nsec = TICK_NSEC_HPET;
		cpu_khz = hpet_calibrate_tsc();
		timename = "HPET";
#ifdef CONFIG_X86_PM_TIMER
	} else if (pmtmr_ioport && !vxtime.hpet_address) {
		vxtime_hz = PM_TIMER_FREQUENCY;
		timename = "PM";
		pit_init();
		cpu_khz = pit_calibrate_tsc();
#endif
	} else {
		pit_init();
		cpu_khz = pit_calibrate_tsc();
		timename = "PIT";
	}

	vxtime.mode = VXTIME_TSC;
	vxtime.quot = (USEC_PER_SEC << US_SCALE) / vxtime_hz;
	vxtime.tsc_quot = (USEC_PER_MSEC << US_SCALE) / cpu_khz;
	vxtime.last_tsc = get_cycles_sync();
	set_cyc2ns_scale(cpu_khz);
	setup_irq(0, &irq0);
	hotcpu_notifier(time_cpu_notifier, 0);
	time_cpu_notifier(NULL, CPU_ONLINE, (void *)(long)smp_processor_id());

#ifndef CONFIG_SMP
	time_init_gtod();
#endif
}

/*
 * Make an educated guess if the TSC is trustworthy and synchronized
 * over all CPUs.
 */
__cpuinit int unsynchronized_tsc(void)
{
#ifdef CONFIG_SMP
	if (apic_is_clustered_box())
		return 1;
#endif
	/* Most intel systems have synchronized TSCs except for
	   multi node systems */
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
#ifdef CONFIG_ACPI
		/* But TSC doesn't tick in C3 so don't use it there */
		if (acpi_fadt.length > 0 && acpi_fadt.plvl3_lat < 100)
			return 1;
#endif
 		return 0;
	}

 	/* Assume multi socket systems are not synchronized */
 	return num_present_cpus() > 1;
}

/*
 * Decide what mode gettimeofday should use.
 */
void time_init_gtod(void)
{
	char *timetype;

	if (unsynchronized_tsc())
		notsc = 1;

 	if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP))
		vgetcpu_mode = VGETCPU_RDTSCP;
	else
		vgetcpu_mode = VGETCPU_LSL;

	if (vxtime.hpet_address && notsc) {
		timetype = hpet_use_timer ? "HPET" : "PIT/HPET";
		if (hpet_use_timer)
			vxtime.last = hpet_readl(HPET_T0_CMP) - hpet_tick;
		else
			vxtime.last = hpet_readl(HPET_COUNTER);
		vxtime.mode = VXTIME_HPET;
		do_gettimeoffset = do_gettimeoffset_hpet;
#ifdef CONFIG_X86_PM_TIMER
	/* Using PM for gettimeofday is quite slow, but we have no other
	   choice because the TSC is too unreliable on some systems. */
	} else if (pmtmr_ioport && !vxtime.hpet_address && notsc) {
		timetype = "PM";
		do_gettimeoffset = do_gettimeoffset_pm;
		vxtime.mode = VXTIME_PMTMR;
		sysctl_vsyscall = 0;
		printk(KERN_INFO "Disabling vsyscall due to use of PM timer\n");
#endif
	} else {
		timetype = hpet_use_timer ? "HPET/TSC" : "PIT/TSC";
		vxtime.mode = VXTIME_TSC;
	}

	printk(KERN_INFO "time.c: Using %ld.%06ld MHz WALL %s GTOD %s timer.\n",
	       vxtime_hz / 1000000, vxtime_hz % 1000000, timename, timetype);
	printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n",
		cpu_khz / 1000, cpu_khz % 1000);
	vxtime.quot = (USEC_PER_SEC << US_SCALE) / vxtime_hz;
	vxtime.tsc_quot = (USEC_PER_MSEC << US_SCALE) / cpu_khz;
	vxtime.last_tsc = get_cycles_sync();

	set_cyc2ns_scale(cpu_khz);
}

__setup("report_lost_ticks", time_setup);

static long clock_cmos_diff;
static unsigned long sleep_start;

/*
 * sysfs support for the timer.
 */

static int timer_suspend(struct sys_device *dev, pm_message_t state)
{
	/*
	 * Estimate time zone so that set_time can update the clock
	 */
	long cmos_time =  get_cmos_time();

	clock_cmos_diff = -cmos_time;
	clock_cmos_diff += get_seconds();
	sleep_start = cmos_time;
	return 0;
}

static int timer_resume(struct sys_device *dev)
{
	unsigned long flags;
	unsigned long sec;
	unsigned long ctime = get_cmos_time();
	long sleep_length = (ctime - sleep_start) * HZ;

	if (sleep_length < 0) {
		printk(KERN_WARNING "Time skew detected in timer resume!\n");
		/* The time after the resume must not be earlier than the time
		 * before the suspend or some nasty things will happen
		 */
		sleep_length = 0;
		ctime = sleep_start;
	}
	if (vxtime.hpet_address)
		hpet_reenable();
	else
		i8254_timer_resume();

	sec = ctime + clock_cmos_diff;
	write_seqlock_irqsave(&xtime_lock,flags);
	xtime.tv_sec = sec;
	xtime.tv_nsec = 0;
	if (vxtime.mode == VXTIME_HPET) {
		if (hpet_use_timer)
			vxtime.last = hpet_readl(HPET_T0_CMP) - hpet_tick;
		else
			vxtime.last = hpet_readl(HPET_COUNTER);
#ifdef CONFIG_X86_PM_TIMER
	} else if (vxtime.mode == VXTIME_PMTMR) {
		pmtimer_resume();
#endif
	} else
		vxtime.last_tsc = get_cycles_sync();
	write_sequnlock_irqrestore(&xtime_lock,flags);
	jiffies += sleep_length;
	monotonic_base += sleep_length * (NSEC_PER_SEC/HZ);
	touch_softlockup_watchdog();
	return 0;
}

static struct sysdev_class timer_sysclass = {
	.resume = timer_resume,
	.suspend = timer_suspend,
	set_kset_name("timer"),
};

/* XXX this driverfs stuff should probably go elsewhere later -john */
static struct sys_device device_timer = {
	.id	= 0,
	.cls	= &timer_sysclass,
};

static int time_init_device(void)
{
	int error = sysdev_class_register(&timer_sysclass);
	if (!error)
		error = sysdev_register(&device_timer);
	return error;
}

device_initcall(time_init_device);

#ifdef CONFIG_HPET_EMULATE_RTC
/* HPET in LegacyReplacement Mode eats up RTC interrupt line. When, HPET
 * is enabled, we support RTC interrupt functionality in software.
 * RTC has 3 kinds of interrupts:
 * 1) Update Interrupt - generate an interrupt, every sec, when RTC clock
 *    is updated
 * 2) Alarm Interrupt - generate an interrupt at a specific time of day
 * 3) Periodic Interrupt - generate periodic interrupt, with frequencies
 *    2Hz-8192Hz (2Hz-64Hz for non-root user) (all freqs in powers of 2)
 * (1) and (2) above are implemented using polling at a frequency of
 * 64 Hz. The exact frequency is a tradeoff between accuracy and interrupt
 * overhead. (DEFAULT_RTC_INT_FREQ)
 * For (3), we use interrupts at 64Hz or user specified periodic
 * frequency, whichever is higher.
 */
#include <linux/rtc.h>

#define DEFAULT_RTC_INT_FREQ 	64
#define RTC_NUM_INTS 		1

static unsigned long UIE_on;
static unsigned long prev_update_sec;

static unsigned long AIE_on;
static struct rtc_time alarm_time;

static unsigned long PIE_on;
static unsigned long PIE_freq = DEFAULT_RTC_INT_FREQ;
static unsigned long PIE_count;

static unsigned long hpet_rtc_int_freq; /* RTC interrupt frequency */
static unsigned int hpet_t1_cmp; /* cached comparator register */

int is_hpet_enabled(void)
{
	return vxtime.hpet_address != 0;
}

/*
 * Timer 1 for RTC, we do not use periodic interrupt feature,
 * even if HPET supports periodic interrupts on Timer 1.
 * The reason being, to set up a periodic interrupt in HPET, we need to
 * stop the main counter. And if we do that everytime someone diables/enables
 * RTC, we will have adverse effect on main kernel timer running on Timer 0.
 * So, for the time being, simulate the periodic interrupt in software.
 *
 * hpet_rtc_timer_init() is called for the first time and during subsequent
 * interuppts reinit happens through hpet_rtc_timer_reinit().
 */
int hpet_rtc_timer_init(void)
{
	unsigned int cfg, cnt;
	unsigned long flags;

	if (!is_hpet_enabled())
		return 0;
	/*
	 * Set the counter 1 and enable the interrupts.
	 */
	if (PIE_on && (PIE_freq > DEFAULT_RTC_INT_FREQ))
		hpet_rtc_int_freq = PIE_freq;
	else
		hpet_rtc_int_freq = DEFAULT_RTC_INT_FREQ;

	local_irq_save(flags);

	cnt = hpet_readl(HPET_COUNTER);
	cnt += ((hpet_tick*HZ)/hpet_rtc_int_freq);
	hpet_writel(cnt, HPET_T1_CMP);
	hpet_t1_cmp = cnt;

	cfg = hpet_readl(HPET_T1_CFG);
	cfg &= ~HPET_TN_PERIODIC;
	cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
	hpet_writel(cfg, HPET_T1_CFG);

	local_irq_restore(flags);

	return 1;
}

static void hpet_rtc_timer_reinit(void)
{
	unsigned int cfg, cnt, ticks_per_int, lost_ints;

	if (unlikely(!(PIE_on | AIE_on | UIE_on))) {
		cfg = hpet_readl(HPET_T1_CFG);
		cfg &= ~HPET_TN_ENABLE;
		hpet_writel(cfg, HPET_T1_CFG);
		return;
	}

	if (PIE_on && (PIE_freq > DEFAULT_RTC_INT_FREQ))
		hpet_rtc_int_freq = PIE_freq;
	else
		hpet_rtc_int_freq = DEFAULT_RTC_INT_FREQ;

	/* It is more accurate to use the comparator value than current count.*/
	ticks_per_int = hpet_tick * HZ / hpet_rtc_int_freq;
	hpet_t1_cmp += ticks_per_int;
	hpet_writel(hpet_t1_cmp, HPET_T1_CMP);

	/*
	 * If the interrupt handler was delayed too long, the write above tries
	 * to schedule the next interrupt in the past and the hardware would
	 * not interrupt until the counter had wrapped around.
	 * So we have to check that the comparator wasn't set to a past time.
	 */
	cnt = hpet_readl(HPET_COUNTER);
	if (unlikely((int)(cnt - hpet_t1_cmp) > 0)) {
		lost_ints = (cnt - hpet_t1_cmp) / ticks_per_int + 1;
		/* Make sure that, even with the time needed to execute
		 * this code, the next scheduled interrupt has been moved
		 * back to the future: */
		lost_ints++;

		hpet_t1_cmp += lost_ints * ticks_per_int;
		hpet_writel(hpet_t1_cmp, HPET_T1_CMP);

		if (PIE_on)
			PIE_count += lost_ints;

		printk(KERN_WARNING "rtc: lost some interrupts at %ldHz.\n",
		       hpet_rtc_int_freq);
	}
}

/*
 * The functions below are called from rtc driver.
 * Return 0 if HPET is not being used.
 * Otherwise do the necessary changes and return 1.
 */
int hpet_mask_rtc_irq_bit(unsigned long bit_mask)
{
	if (!is_hpet_enabled())
		return 0;

	if (bit_mask & RTC_UIE)
		UIE_on = 0;
	if (bit_mask & RTC_PIE)
		PIE_on = 0;
	if (bit_mask & RTC_AIE)
		AIE_on = 0;

	return 1;
}

int hpet_set_rtc_irq_bit(unsigned long bit_mask)
{
	int timer_init_reqd = 0;

	if (!is_hpet_enabled())
		return 0;

	if (!(PIE_on | AIE_on | UIE_on))
		timer_init_reqd = 1;

	if (bit_mask & RTC_UIE) {
		UIE_on = 1;
	}
	if (bit_mask & RTC_PIE) {
		PIE_on = 1;
		PIE_count = 0;
	}
	if (bit_mask & RTC_AIE) {
		AIE_on = 1;
	}

	if (timer_init_reqd)
		hpet_rtc_timer_init();

	return 1;
}

int hpet_set_alarm_time(unsigned char hrs, unsigned char min, unsigned char sec)
{
	if (!is_hpet_enabled())
		return 0;

	alarm_time.tm_hour = hrs;
	alarm_time.tm_min = min;
	alarm_time.tm_sec = sec;

	return 1;
}

int hpet_set_periodic_freq(unsigned long freq)
{
	if (!is_hpet_enabled())
		return 0;

	PIE_freq = freq;
	PIE_count = 0;

	return 1;
}

int hpet_rtc_dropped_irq(void)
{
	if (!is_hpet_enabled())
		return 0;

	return 1;
}

irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id, struct pt_regs *regs)
{
	struct rtc_time curr_time;
	unsigned long rtc_int_flag = 0;
	int call_rtc_interrupt = 0;

	hpet_rtc_timer_reinit();

	if (UIE_on | AIE_on) {
		rtc_get_rtc_time(&curr_time);
	}
	if (UIE_on) {
		if (curr_time.tm_sec != prev_update_sec) {
			/* Set update int info, call real rtc int routine */
			call_rtc_interrupt = 1;
			rtc_int_flag = RTC_UF;
			prev_update_sec = curr_time.tm_sec;
		}
	}
	if (PIE_on) {
		PIE_count++;
		if (PIE_count >= hpet_rtc_int_freq/PIE_freq) {
			/* Set periodic int info, call real rtc int routine */
			call_rtc_interrupt = 1;
			rtc_int_flag |= RTC_PF;
			PIE_count = 0;
		}
	}
	if (AIE_on) {
		if ((curr_time.tm_sec == alarm_time.tm_sec) &&
		    (curr_time.tm_min == alarm_time.tm_min) &&
		    (curr_time.tm_hour == alarm_time.tm_hour)) {
			/* Set alarm int info, call real rtc int routine */
			call_rtc_interrupt = 1;
			rtc_int_flag |= RTC_AF;
		}
	}
	if (call_rtc_interrupt) {
		rtc_int_flag |= (RTC_IRQF | (RTC_NUM_INTS << 8));
		rtc_interrupt(rtc_int_flag, dev_id, regs);
	}
	return IRQ_HANDLED;
}
#endif

static int __init nohpet_setup(char *s) 
{ 
	nohpet = 1;
	return 1;
} 

__setup("nohpet", nohpet_setup);

int __init notsc_setup(char *s)
{
	notsc = 1;
	return 1;
}

__setup("notsc", notsc_setup);