aboutsummaryrefslogtreecommitdiff
path: root/kernel/posix-cpu-timers.c
blob: 383ba22f0b627613582807ff4051b7f35559dd10 (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
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
/*
 * Implement CPU time clocks for the POSIX clock interface.
 */

#include <linux/sched.h>
#include <linux/posix-timers.h>
#include <asm/uaccess.h>
#include <linux/errno.h>

static int check_clock(clockid_t which_clock)
{
	int error = 0;
	struct task_struct *p;
	const pid_t pid = CPUCLOCK_PID(which_clock);

	if (CPUCLOCK_WHICH(which_clock) >= CPUCLOCK_MAX)
		return -EINVAL;

	if (pid == 0)
		return 0;

	read_lock(&tasklist_lock);
	p = find_task_by_pid(pid);
	if (!p || (CPUCLOCK_PERTHREAD(which_clock) ?
		   p->tgid != current->tgid : p->tgid != pid)) {
		error = -EINVAL;
	}
	read_unlock(&tasklist_lock);

	return error;
}

static inline union cpu_time_count
timespec_to_sample(clockid_t which_clock, const struct timespec *tp)
{
	union cpu_time_count ret;
	ret.sched = 0;		/* high half always zero when .cpu used */
	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
		ret.sched = tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec;
	} else {
		ret.cpu = timespec_to_cputime(tp);
	}
	return ret;
}

static void sample_to_timespec(clockid_t which_clock,
			       union cpu_time_count cpu,
			       struct timespec *tp)
{
	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
		tp->tv_sec = div_long_long_rem(cpu.sched,
					       NSEC_PER_SEC, &tp->tv_nsec);
	} else {
		cputime_to_timespec(cpu.cpu, tp);
	}
}

static inline int cpu_time_before(clockid_t which_clock,
				  union cpu_time_count now,
				  union cpu_time_count then)
{
	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
		return now.sched < then.sched;
	}  else {
		return cputime_lt(now.cpu, then.cpu);
	}
}
static inline void cpu_time_add(clockid_t which_clock,
				union cpu_time_count *acc,
			        union cpu_time_count val)
{
	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
		acc->sched += val.sched;
	}  else {
		acc->cpu = cputime_add(acc->cpu, val.cpu);
	}
}
static inline union cpu_time_count cpu_time_sub(clockid_t which_clock,
						union cpu_time_count a,
						union cpu_time_count b)
{
	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
		a.sched -= b.sched;
	}  else {
		a.cpu = cputime_sub(a.cpu, b.cpu);
	}
	return a;
}

/*
 * Update expiry time from increment, and increase overrun count,
 * given the current clock sample.
 */
static void bump_cpu_timer(struct k_itimer *timer,
				  union cpu_time_count now)
{
	int i;

	if (timer->it.cpu.incr.sched == 0)
		return;

	if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
		unsigned long long delta, incr;

		if (now.sched < timer->it.cpu.expires.sched)
			return;
		incr = timer->it.cpu.incr.sched;
		delta = now.sched + incr - timer->it.cpu.expires.sched;
		/* Don't use (incr*2 < delta), incr*2 might overflow. */
		for (i = 0; incr < delta - incr; i++)
			incr = incr << 1;
		for (; i >= 0; incr >>= 1, i--) {
			if (delta < incr)
				continue;
			timer->it.cpu.expires.sched += incr;
			timer->it_overrun += 1 << i;
			delta -= incr;
		}
	} else {
		cputime_t delta, incr;

		if (cputime_lt(now.cpu, timer->it.cpu.expires.cpu))
			return;
		incr = timer->it.cpu.incr.cpu;
		delta = cputime_sub(cputime_add(now.cpu, incr),
				    timer->it.cpu.expires.cpu);
		/* Don't use (incr*2 < delta), incr*2 might overflow. */
		for (i = 0; cputime_lt(incr, cputime_sub(delta, incr)); i++)
			     incr = cputime_add(incr, incr);
		for (; i >= 0; incr = cputime_halve(incr), i--) {
			if (cputime_lt(delta, incr))
				continue;
			timer->it.cpu.expires.cpu =
				cputime_add(timer->it.cpu.expires.cpu, incr);
			timer->it_overrun += 1 << i;
			delta = cputime_sub(delta, incr);
		}
	}
}

static inline cputime_t prof_ticks(struct task_struct *p)
{
	return cputime_add(p->utime, p->stime);
}
static inline cputime_t virt_ticks(struct task_struct *p)
{
	return p->utime;
}
static inline unsigned long long sched_ns(struct task_struct *p)
{
	return (p == current) ? current_sched_time(p) : p->sched_time;
}

int posix_cpu_clock_getres(clockid_t which_clock, struct timespec *tp)
{
	int error = check_clock(which_clock);
	if (!error) {
		tp->tv_sec = 0;
		tp->tv_nsec = ((NSEC_PER_SEC + HZ - 1) / HZ);
		if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
			/*
			 * If sched_clock is using a cycle counter, we
			 * don't have any idea of its true resolution
			 * exported, but it is much more than 1s/HZ.
			 */
			tp->tv_nsec = 1;
		}
	}
	return error;
}

int posix_cpu_clock_set(clockid_t which_clock, const struct timespec *tp)
{
	/*
	 * You can never reset a CPU clock, but we check for other errors
	 * in the call before failing with EPERM.
	 */
	int error = check_clock(which_clock);
	if (error == 0) {
		error = -EPERM;
	}
	return error;
}


/*
 * Sample a per-thread clock for the given task.
 */
static int cpu_clock_sample(clockid_t which_clock, struct task_struct *p,
			    union cpu_time_count *cpu)
{
	switch (CPUCLOCK_WHICH(which_clock)) {
	default:
		return -EINVAL;
	case CPUCLOCK_PROF:
		cpu->cpu = prof_ticks(p);
		break;
	case CPUCLOCK_VIRT:
		cpu->cpu = virt_ticks(p);
		break;
	case CPUCLOCK_SCHED:
		cpu->sched = sched_ns(p);
		break;
	}
	return 0;
}

/*
 * Sample a process (thread group) clock for the given group_leader task.
 * Must be called with tasklist_lock held for reading.
 * Must be called with tasklist_lock held for reading, and p->sighand->siglock.
 */
static int cpu_clock_sample_group_locked(unsigned int clock_idx,
					 struct task_struct *p,
					 union cpu_time_count *cpu)
{
	struct task_struct *t = p;
 	switch (clock_idx) {
	default:
		return -EINVAL;
	case CPUCLOCK_PROF:
		cpu->cpu = cputime_add(p->signal->utime, p->signal->stime);
		do {
			cpu->cpu = cputime_add(cpu->cpu, prof_ticks(t));
			t = next_thread(t);
		} while (t != p);
		break;
	case CPUCLOCK_VIRT:
		cpu->cpu = p->signal->utime;
		do {
			cpu->cpu = cputime_add(cpu->cpu, virt_ticks(t));
			t = next_thread(t);
		} while (t != p);
		break;
	case CPUCLOCK_SCHED:
		cpu->sched = p->signal->sched_time;
		/* Add in each other live thread.  */
		while ((t = next_thread(t)) != p) {
			cpu->sched += t->sched_time;
		}
		if (p->tgid == current->tgid) {
			/*
			 * We're sampling ourselves, so include the
			 * cycles not yet banked.  We still omit
			 * other threads running on other CPUs,
			 * so the total can always be behind as
			 * much as max(nthreads-1,ncpus) * (NSEC_PER_SEC/HZ).
			 */
			cpu->sched += current_sched_time(current);
		} else {
			cpu->sched += p->sched_time;
		}
		break;
	}
	return 0;
}

/*
 * Sample a process (thread group) clock for the given group_leader task.
 * Must be called with tasklist_lock held for reading.
 */
static int cpu_clock_sample_group(clockid_t which_clock,
				  struct task_struct *p,
				  union cpu_time_count *cpu)
{
	int ret;
	unsigned long flags;
	spin_lock_irqsave(&p->sighand->siglock, flags);
	ret = cpu_clock_sample_group_locked(CPUCLOCK_WHICH(which_clock), p,
					    cpu);
	spin_unlock_irqrestore(&p->sighand->siglock, flags);
	return ret;
}


int posix_cpu_clock_get(clockid_t which_clock, struct timespec *tp)
{
	const pid_t pid = CPUCLOCK_PID(which_clock);
	int error = -EINVAL;
	union cpu_time_count rtn;

	if (pid == 0) {
		/*
		 * Special case constant value for our own clocks.
		 * We don't have to do any lookup to find ourselves.
		 */
		if (CPUCLOCK_PERTHREAD(which_clock)) {
			/*
			 * Sampling just ourselves we can do with no locking.
			 */
			error = cpu_clock_sample(which_clock,
						 current, &rtn);
		} else {
			read_lock(&tasklist_lock);
			error = cpu_clock_sample_group(which_clock,
						       current, &rtn);
			read_unlock(&tasklist_lock);
		}
	} else {
		/*
		 * Find the given PID, and validate that the caller
		 * should be able to see it.
		 */
		struct task_struct *p;
		read_lock(&tasklist_lock);
		p = find_task_by_pid(pid);
		if (p) {
			if (CPUCLOCK_PERTHREAD(which_clock)) {
				if (p->tgid == current->tgid) {
					error = cpu_clock_sample(which_clock,
								 p, &rtn);
				}
			} else if (p->tgid == pid && p->signal) {
				error = cpu_clock_sample_group(which_clock,
							       p, &rtn);
			}
		}
		read_unlock(&tasklist_lock);
	}

	if (error)
		return error;
	sample_to_timespec(which_clock, rtn, tp);
	return 0;
}


/*
 * Validate the clockid_t for a new CPU-clock timer, and initialize the timer.
 * This is called from sys_timer_create with the new timer already locked.
 */
int posix_cpu_timer_create(struct k_itimer *new_timer)
{
	int ret = 0;
	const pid_t pid = CPUCLOCK_PID(new_timer->it_clock);
	struct task_struct *p;

	if (CPUCLOCK_WHICH(new_timer->it_clock) >= CPUCLOCK_MAX)
		return -EINVAL;

	INIT_LIST_HEAD(&new_timer->it.cpu.entry);
	new_timer->it.cpu.incr.sched = 0;
	new_timer->it.cpu.expires.sched = 0;

	read_lock(&tasklist_lock);
	if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) {
		if (pid == 0) {
			p = current;
		} else {
			p = find_task_by_pid(pid);
			if (p && p->tgid != current->tgid)
				p = NULL;
		}
	} else {
		if (pid == 0) {
			p = current->group_leader;
		} else {
			p = find_task_by_pid(pid);
			if (p && p->tgid != pid)
				p = NULL;
		}
	}
	new_timer->it.cpu.task = p;
	if (p) {
		get_task_struct(p);
	} else {
		ret = -EINVAL;
	}
	read_unlock(&tasklist_lock);

	return ret;
}

/*
 * Clean up a CPU-clock timer that is about to be destroyed.
 * This is called from timer deletion with the timer already locked.
 * If we return TIMER_RETRY, it's necessary to release the timer's lock
 * and try again.  (This happens when the timer is in the middle of firing.)
 */
int posix_cpu_timer_del(struct k_itimer *timer)
{
	struct task_struct *p = timer->it.cpu.task;
	int ret = 0;

	if (likely(p != NULL)) {
		read_lock(&tasklist_lock);
		if (unlikely(p->signal == NULL)) {
			/*
			 * We raced with the reaping of the task.
			 * The deletion should have cleared us off the list.
			 */
			BUG_ON(!list_empty(&timer->it.cpu.entry));
		} else {
			spin_lock(&p->sighand->siglock);
			if (timer->it.cpu.firing)
				ret = TIMER_RETRY;
			else
				list_del(&timer->it.cpu.entry);
			spin_unlock(&p->sighand->siglock);
		}
		read_unlock(&tasklist_lock);

		if (!ret)
			put_task_struct(p);
	}

	return ret;
}

/*
 * Clean out CPU timers still ticking when a thread exited.  The task
 * pointer is cleared, and the expiry time is replaced with the residual
 * time for later timer_gettime calls to return.
 * This must be called with the siglock held.
 */
static void cleanup_timers(struct list_head *head,
			   cputime_t utime, cputime_t stime,
			   unsigned long long sched_time)
{
	struct cpu_timer_list *timer, *next;
	cputime_t ptime = cputime_add(utime, stime);

	list_for_each_entry_safe(timer, next, head, entry) {
		list_del_init(&timer->entry);
		if (cputime_lt(timer->expires.cpu, ptime)) {
			timer->expires.cpu = cputime_zero;
		} else {
			timer->expires.cpu = cputime_sub(timer->expires.cpu,
							 ptime);
		}
	}

	++head;
	list_for_each_entry_safe(timer, next, head, entry) {
		list_del_init(&timer->entry);
		if (cputime_lt(timer->expires.cpu, utime)) {
			timer->expires.cpu = cputime_zero;
		} else {
			timer->expires.cpu = cputime_sub(timer->expires.cpu,
							 utime);
		}
	}

	++head;
	list_for_each_entry_safe(timer, next, head, entry) {
		list_del_init(&timer->entry);
		if (timer->expires.sched < sched_time) {
			timer->expires.sched = 0;
		} else {
			timer->expires.sched -= sched_time;
		}
	}
}

/*
 * These are both called with the siglock held, when the current thread
 * is being reaped.  When the final (leader) thread in the group is reaped,
 * posix_cpu_timers_exit_group will be called after posix_cpu_timers_exit.
 */
void posix_cpu_timers_exit(struct task_struct *tsk)
{
	cleanup_timers(tsk->cpu_timers,
		       tsk->utime, tsk->stime, tsk->sched_time);

}
void posix_cpu_timers_exit_group(struct task_struct *tsk)
{
	cleanup_timers(tsk->signal->cpu_timers,
		       cputime_add(tsk->utime, tsk->signal->utime),
		       cputime_add(tsk->stime, tsk->signal->stime),
		       tsk->sched_time + tsk->signal->sched_time);
}


/*
 * Set the expiry times of all the threads in the process so one of them
 * will go off before the process cumulative expiry total is reached.
 */
static void process_timer_rebalance(struct task_struct *p,
				    unsigned int clock_idx,
				    union cpu_time_count expires,
				    union cpu_time_count val)
{
	cputime_t ticks, left;
	unsigned long long ns, nsleft;
 	struct task_struct *t = p;
	unsigned int nthreads = atomic_read(&p->signal->live);

	if (!nthreads)
		return;

	switch (clock_idx) {
	default:
		BUG();
		break;
	case CPUCLOCK_PROF:
		left = cputime_div(cputime_sub(expires.cpu, val.cpu),
				   nthreads);
		do {
			if (!unlikely(t->exit_state)) {
				ticks = cputime_add(prof_ticks(t), left);
				if (cputime_eq(t->it_prof_expires,
					       cputime_zero) ||
				    cputime_gt(t->it_prof_expires, ticks)) {
					t->it_prof_expires = ticks;
				}
			}
			t = next_thread(t);
		} while (t != p);
		break;
	case CPUCLOCK_VIRT:
		left = cputime_div(cputime_sub(expires.cpu, val.cpu),
				   nthreads);
		do {
			if (!unlikely(t->exit_state)) {
				ticks = cputime_add(virt_ticks(t), left);
				if (cputime_eq(t->it_virt_expires,
					       cputime_zero) ||
				    cputime_gt(t->it_virt_expires, ticks)) {
					t->it_virt_expires = ticks;
				}
			}
			t = next_thread(t);
		} while (t != p);
		break;
	case CPUCLOCK_SCHED:
		nsleft = expires.sched - val.sched;
		do_div(nsleft, nthreads);
		do {
			if (!unlikely(t->exit_state)) {
				ns = t->sched_time + nsleft;
				if (t->it_sched_expires == 0 ||
				    t->it_sched_expires > ns) {
					t->it_sched_expires = ns;
				}
			}
			t = next_thread(t);
		} while (t != p);
		break;
	}
}

static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
{
	/*
	 * That's all for this thread or process.
	 * We leave our residual in expires to be reported.
	 */
	put_task_struct(timer->it.cpu.task);
	timer->it.cpu.task = NULL;
	timer->it.cpu.expires = cpu_time_sub(timer->it_clock,
					     timer->it.cpu.expires,
					     now);
}

/*
 * Insert the timer on the appropriate list before any timers that
 * expire later.  This must be called with the tasklist_lock held
 * for reading, and interrupts disabled.
 */
static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
{
	struct task_struct *p = timer->it.cpu.task;
	struct list_head *head, *listpos;
	struct cpu_timer_list *const nt = &timer->it.cpu;
	struct cpu_timer_list *next;
	unsigned long i;

	head = (CPUCLOCK_PERTHREAD(timer->it_clock) ?
		p->cpu_timers : p->signal->cpu_timers);
	head += CPUCLOCK_WHICH(timer->it_clock);

	BUG_ON(!irqs_disabled());
	spin_lock(&p->sighand->siglock);

	listpos = head;
	if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
		list_for_each_entry(next, head, entry) {
			if (next->expires.sched > nt->expires.sched)
				break;
			listpos = &next->entry;
		}
	} else {
		list_for_each_entry(next, head, entry) {
			if (cputime_gt(next->expires.cpu, nt->expires.cpu))
				break;
			listpos = &next->entry;
		}
	}
	list_add(&nt->entry, listpos);

	if (listpos == head) {
		/*
		 * We are the new earliest-expiring timer.
		 * If we are a thread timer, there can always
		 * be a process timer telling us to stop earlier.
		 */

		if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
			switch (CPUCLOCK_WHICH(timer->it_clock)) {
			default:
				BUG();
			case CPUCLOCK_PROF:
				if (cputime_eq(p->it_prof_expires,
					       cputime_zero) ||
				    cputime_gt(p->it_prof_expires,
					       nt->expires.cpu))
					p->it_prof_expires = nt->expires.cpu;
				break;
			case CPUCLOCK_VIRT:
				if (cputime_eq(p->it_virt_expires,
					       cputime_zero) ||
				    cputime_gt(p->it_virt_expires,
					       nt->expires.cpu))
					p->it_virt_expires = nt->expires.cpu;
				break;
			case CPUCLOCK_SCHED:
				if (p->it_sched_expires == 0 ||
				    p->it_sched_expires > nt->expires.sched)
					p->it_sched_expires = nt->expires.sched;
				break;
			}
		} else {
			/*
			 * For a process timer, we must balance
			 * all the live threads' expirations.
			 */
			switch (CPUCLOCK_WHICH(timer->it_clock)) {
			default:
				BUG();
			case CPUCLOCK_VIRT:
				if (!cputime_eq(p->signal->it_virt_expires,
						cputime_zero) &&
				    cputime_lt(p->signal->it_virt_expires,
					       timer->it.cpu.expires.cpu))
					break;
				goto rebalance;
			case CPUCLOCK_PROF:
				if (!cputime_eq(p->signal->it_prof_expires,
						cputime_zero) &&
				    cputime_lt(p->signal->it_prof_expires,
					       timer->it.cpu.expires.cpu))
					break;
				i = p->signal->rlim[RLIMIT_CPU].rlim_cur;
				if (i != RLIM_INFINITY &&
				    i <= cputime_to_secs(timer->it.cpu.expires.cpu))
					break;
				goto rebalance;
			case CPUCLOCK_SCHED:
			rebalance:
				process_timer_rebalance(
					timer->it.cpu.task,
					CPUCLOCK_WHICH(timer->it_clock),
					timer->it.cpu.expires, now);
				break;
			}
		}
	}

	spin_unlock(&p->sighand->siglock);
}

/*
 * The timer is locked, fire it and arrange for its reload.
 */
static void cpu_timer_fire(struct k_itimer *timer)
{
	if (unlikely(timer->sigq == NULL)) {
		/*
		 * This a special case for clock_nanosleep,
		 * not a normal timer from sys_timer_create.
		 */
		wake_up_process(timer->it_process);
		timer->it.cpu.expires.sched = 0;
	} else if (timer->it.cpu.incr.sched == 0) {
		/*
		 * One-shot timer.  Clear it as soon as it's fired.
		 */
		posix_timer_event(timer, 0);
		timer->it.cpu.expires.sched = 0;
	} else if (posix_timer_event(timer, ++timer->it_requeue_pending)) {
		/*
		 * The signal did not get queued because the signal
		 * was ignored, so we won't get any callback to
		 * reload the timer.  But we need to keep it
		 * ticking in case the signal is deliverable next time.
		 */
		posix_cpu_timer_schedule(timer);
	}
}

/*
 * Guts of sys_timer_settime for CPU timers.
 * This is called with the timer locked and interrupts disabled.
 * If we return TIMER_RETRY, it's necessary to release the timer's lock
 * and try again.  (This happens when the timer is in the middle of firing.)
 */
int posix_cpu_timer_set(struct k_itimer *timer, int flags,
			struct itimerspec *new, struct itimerspec *old)
{
	struct task_struct *p = timer->it.cpu.task;
	union cpu_time_count old_expires, new_expires, val;
	int ret;

	if (unlikely(p == NULL)) {
		/*
		 * Timer refers to a dead task's clock.
		 */
		return -ESRCH;
	}

	new_expires = timespec_to_sample(timer->it_clock, &new->it_value);

	read_lock(&tasklist_lock);
	/*
	 * We need the tasklist_lock to protect against reaping that
	 * clears p->signal.  If p has just been reaped, we can no
	 * longer get any information about it at all.
	 */
	if (unlikely(p->signal == NULL)) {
		read_unlock(&tasklist_lock);
		put_task_struct(p);
		timer->it.cpu.task = NULL;
		return -ESRCH;
	}

	/*
	 * Disarm any old timer after extracting its expiry time.
	 */
	BUG_ON(!irqs_disabled());

	ret = 0;
	spin_lock(&p->sighand->siglock);
	old_expires = timer->it.cpu.expires;
	if (unlikely(timer->it.cpu.firing)) {
		timer->it.cpu.firing = -1;
		ret = TIMER_RETRY;
	} else
		list_del_init(&timer->it.cpu.entry);
	spin_unlock(&p->sighand->siglock);

	/*
	 * We need to sample the current value to convert the new
	 * value from to relative and absolute, and to convert the
	 * old value from absolute to relative.  To set a process
	 * timer, we need a sample to balance the thread expiry
	 * times (in arm_timer).  With an absolute time, we must
	 * check if it's already passed.  In short, we need a sample.
	 */
	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
		cpu_clock_sample(timer->it_clock, p, &val);
	} else {
		cpu_clock_sample_group(timer->it_clock, p, &val);
	}

	if (old) {
		if (old_expires.sched == 0) {
			old->it_value.tv_sec = 0;
			old->it_value.tv_nsec = 0;
		} else {
			/*
			 * Update the timer in case it has
			 * overrun already.  If it has,
			 * we'll report it as having overrun
			 * and with the next reloaded timer
			 * already ticking, though we are
			 * swallowing that pending
			 * notification here to install the
			 * new setting.
			 */
			bump_cpu_timer(timer, val);
			if (cpu_time_before(timer->it_clock, val,
					    timer->it.cpu.expires)) {
				old_expires = cpu_time_sub(
					timer->it_clock,
					timer->it.cpu.expires, val);
				sample_to_timespec(timer->it_clock,
						   old_expires,
						   &old->it_value);
			} else {
				old->it_value.tv_nsec = 1;
				old->it_value.tv_sec = 0;
			}
		}
	}

	if (unlikely(ret)) {
		/*
		 * We are colliding with the timer actually firing.
		 * Punt after filling in the timer's old value, and
		 * disable this firing since we are already reporting
		 * it as an overrun (thanks to bump_cpu_timer above).
		 */
		read_unlock(&tasklist_lock);
		goto out;
	}

	if (new_expires.sched != 0 && !(flags & TIMER_ABSTIME)) {
		cpu_time_add(timer->it_clock, &new_expires, val);
	}

	/*
	 * Install the new expiry time (or zero).
	 * For a timer with no notification action, we don't actually
	 * arm the timer (we'll just fake it for timer_gettime).
	 */
	timer->it.cpu.expires = new_expires;
	if (new_expires.sched != 0 &&
	    (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE &&
	    cpu_time_before(timer->it_clock, val, new_expires)) {
		arm_timer(timer, val);
	}

	read_unlock(&tasklist_lock);

	/*
	 * Install the new reload setting, and
	 * set up the signal and overrun bookkeeping.
	 */
	timer->it.cpu.incr = timespec_to_sample(timer->it_clock,
						&new->it_interval);

	/*
	 * This acts as a modification timestamp for the timer,
	 * so any automatic reload attempt will punt on seeing
	 * that we have reset the timer manually.
	 */
	timer->it_requeue_pending = (timer->it_requeue_pending + 2) &
		~REQUEUE_PENDING;
	timer->it_overrun_last = 0;
	timer->it_overrun = -1;

	if (new_expires.sched != 0 &&
	    (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE &&
	    !cpu_time_before(timer->it_clock, val, new_expires)) {
		/*
		 * The designated time already passed, so we notify
		 * immediately, even if the thread never runs to
		 * accumulate more time on this clock.
		 */
		cpu_timer_fire(timer);
	}

	ret = 0;
 out:
	if (old) {
		sample_to_timespec(timer->it_clock,
				   timer->it.cpu.incr, &old->it_interval);
	}
	return ret;
}

void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
{
	union cpu_time_count now;
	struct task_struct *p = timer->it.cpu.task;
	int clear_dead;

	/*
	 * Easy part: convert the reload time.
	 */
	sample_to_timespec(timer->it_clock,
			   timer->it.cpu.incr, &itp->it_interval);

	if (timer->it.cpu.expires.sched == 0) {	/* Timer not armed at all.  */
		itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
		return;
	}

	if (unlikely(p == NULL)) {
		/*
		 * This task already died and the timer will never fire.
		 * In this case, expires is actually the dead value.
		 */
	dead:
		sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
				   &itp->it_value);
		return;
	}

	/*
	 * Sample the clock to take the difference with the expiry time.
	 */
	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
		cpu_clock_sample(timer->it_clock, p, &now);
		clear_dead = p->exit_state;
	} else {
		read_lock(&tasklist_lock);
		if (unlikely(p->signal == NULL)) {
			/*
			 * The process has been reaped.
			 * We can't even collect a sample any more.
			 * Call the timer disarmed, nothing else to do.
			 */
			put_task_struct(p);
			timer->it.cpu.task = NULL;
			timer->it.cpu.expires.sched = 0;
			read_unlock(&tasklist_lock);
			goto dead;
		} else {
			cpu_clock_sample_group(timer->it_clock, p, &now);
			clear_dead = (unlikely(p->exit_state) &&
				      thread_group_empty(p));
		}
		read_unlock(&tasklist_lock);
	}

	if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) {
		if (timer->it.cpu.incr.sched == 0 &&
		    cpu_time_before(timer->it_clock,
				    timer->it.cpu.expires, now)) {
			/*
			 * Do-nothing timer expired and has no reload,
			 * so it's as if it was never set.
			 */
			timer->it.cpu.expires.sched = 0;
			itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
			return;
		}
		/*
		 * Account for any expirations and reloads that should
		 * have happened.
		 */
		bump_cpu_timer(timer, now);
	}

	if (unlikely(clear_dead)) {
		/*
		 * We've noticed that the thread is dead, but
		 * not yet reaped.  Take this opportunity to
		 * drop our task ref.
		 */
		clear_dead_task(timer, now);
		goto dead;
	}

	if (cpu_time_before(timer->it_clock, now, timer->it.cpu.expires)) {
		sample_to_timespec(timer->it_clock,
				   cpu_time_sub(timer->it_clock,
						timer->it.cpu.expires, now),
				   &itp->it_value);
	} else {
		/*
		 * The timer should have expired already, but the firing
		 * hasn't taken place yet.  Say it's just about to expire.
		 */
		itp->it_value.tv_nsec = 1;
		itp->it_value.tv_sec = 0;
	}
}

/*
 * Check for any per-thread CPU timers that have fired and move them off
 * the tsk->cpu_timers[N] list onto the firing list.  Here we update the
 * tsk->it_*_expires values to reflect the remaining thread CPU timers.
 */
static void check_thread_timers(struct task_struct *tsk,
				struct list_head *firing)
{
	int maxfire;
	struct list_head *timers = tsk->cpu_timers;

	maxfire = 20;
	tsk->it_prof_expires = cputime_zero;
	while (!list_empty(timers)) {
		struct cpu_timer_list *t = list_entry(timers->next,
						      struct cpu_timer_list,
						      entry);
		if (!--maxfire || cputime_lt(prof_ticks(tsk), t->expires.cpu)) {
			tsk->it_prof_expires = t->expires.cpu;
			break;
		}
		t->firing = 1;
		list_move_tail(&t->entry, firing);
	}

	++timers;
	maxfire = 20;
	tsk->it_virt_expires = cputime_zero;
	while (!list_empty(timers)) {
		struct cpu_timer_list *t = list_entry(timers->next,
						      struct cpu_timer_list,
						      entry);
		if (!--maxfire || cputime_lt(virt_ticks(tsk), t->expires.cpu)) {
			tsk->it_virt_expires = t->expires.cpu;
			break;
		}
		t->firing = 1;
		list_move_tail(&t->entry, firing);
	}

	++timers;
	maxfire = 20;
	tsk->it_sched_expires = 0;
	while (!list_empty(timers)) {
		struct cpu_timer_list *t = list_entry(timers->next,
						      struct cpu_timer_list,
						      entry);
		if (!--maxfire || tsk->sched_time < t->expires.sched) {
			tsk->it_sched_expires = t->expires.sched;
			break;
		}
		t->firing = 1;
		list_move_tail(&t->entry, firing);
	}
}

/*
 * Check for any per-thread CPU timers that have fired and move them
 * off the tsk->*_timers list onto the firing list.  Per-thread timers
 * have already been taken off.
 */
static void check_process_timers(struct task_struct *tsk,
				 struct list_head *firing)
{
	int maxfire;
	struct signal_struct *const sig = tsk->signal;
	cputime_t utime, stime, ptime, virt_expires, prof_expires;
	unsigned long long sched_time, sched_expires;
	struct task_struct *t;
	struct list_head *timers = sig->cpu_timers;

	/*
	 * Don't sample the current process CPU clocks if there are no timers.
	 */
	if (list_empty(&timers[CPUCLOCK_PROF]) &&
	    cputime_eq(sig->it_prof_expires, cputime_zero) &&
	    sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
	    list_empty(&timers[CPUCLOCK_VIRT]) &&
	    cputime_eq(sig->it_virt_expires, cputime_zero) &&
	    list_empty(&timers[CPUCLOCK_SCHED]))
		return;

	/*
	 * Collect the current process totals.
	 */
	utime = sig->utime;
	stime = sig->stime;
	sched_time = sig->sched_time;
	t = tsk;
	do {
		utime = cputime_add(utime, t->utime);
		stime = cputime_add(stime, t->stime);
		sched_time += t->sched_time;
		t = next_thread(t);
	} while (t != tsk);
	ptime = cputime_add(utime, stime);

	maxfire = 20;
	prof_expires = cputime_zero;
	while (!list_empty(timers)) {
		struct cpu_timer_list *t = list_entry(timers->next,
						      struct cpu_timer_list,
						      entry);
		if (!--maxfire || cputime_lt(ptime, t->expires.cpu)) {
			prof_expires = t->expires.cpu;
			break;
		}
		t->firing = 1;
		list_move_tail(&t->entry, firing);
	}

	++timers;
	maxfire = 20;
	virt_expires = cputime_zero;
	while (!list_empty(timers)) {
		struct cpu_timer_list *t = list_entry(timers->next,
						      struct cpu_timer_list,
						      entry);
		if (!--maxfire || cputime_lt(utime, t->expires.cpu)) {
			virt_expires = t->expires.cpu;
			break;
		}
		t->firing = 1;
		list_move_tail(&t->entry, firing);
	}

	++timers;
	maxfire = 20;
	sched_expires = 0;
	while (!list_empty(timers)) {
		struct cpu_timer_list *t = list_entry(timers->next,
						      struct cpu_timer_list,
						      entry);
		if (!--maxfire || sched_time < t->expires.sched) {
			sched_expires = t->expires.sched;
			break;
		}
		t->firing = 1;
		list_move_tail(&t->entry, firing);
	}

	/*
	 * Check for the special case process timers.
	 */
	if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
		if (cputime_ge(ptime, sig->it_prof_expires)) {
			/* ITIMER_PROF fires and reloads.  */
			sig->it_prof_expires = sig->it_prof_incr;
			if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
				sig->it_prof_expires = cputime_add(
					sig->it_prof_expires, ptime);
			}
			__group_send_sig_info(SIGPROF, SEND_SIG_PRIV, tsk);
		}
		if (!cputime_eq(sig->it_prof_expires, cputime_zero) &&
		    (cputime_eq(prof_expires, cputime_zero) ||
		     cputime_lt(sig->it_prof_expires, prof_expires))) {
			prof_expires = sig->it_prof_expires;
		}
	}
	if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
		if (cputime_ge(utime, sig->it_virt_expires)) {
			/* ITIMER_VIRTUAL fires and reloads.  */
			sig->it_virt_expires = sig->it_virt_incr;
			if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
				sig->it_virt_expires = cputime_add(
					sig->it_virt_expires, utime);
			}
			__group_send_sig_info(SIGVTALRM, SEND_SIG_PRIV, tsk);
		}
		if (!cputime_eq(sig->it_virt_expires, cputime_zero) &&
		    (cputime_eq(virt_expires, cputime_zero) ||
		     cputime_lt(sig->it_virt_expires, virt_expires))) {
			virt_expires = sig->it_virt_expires;
		}
	}
	if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
		unsigned long psecs = cputime_to_secs(ptime);
		cputime_t x;
		if (psecs >= sig->rlim[RLIMIT_CPU].rlim_max) {
			/*
			 * At the hard limit, we just die.
			 * No need to calculate anything else now.
			 */
			__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
			return;
		}
		if (psecs >= sig->rlim[RLIMIT_CPU].rlim_cur) {
			/*
			 * At the soft limit, send a SIGXCPU every second.
			 */
			__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
			if (sig->rlim[RLIMIT_CPU].rlim_cur
			    < sig->rlim[RLIMIT_CPU].rlim_max) {
				sig->rlim[RLIMIT_CPU].rlim_cur++;
			}
		}
		x = secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
		if (cputime_eq(prof_expires, cputime_zero) ||
		    cputime_lt(x, prof_expires)) {
			prof_expires = x;
		}
	}

	if (!cputime_eq(prof_expires, cputime_zero) ||
	    !cputime_eq(virt_expires, cputime_zero) ||
	    sched_expires != 0) {
		/*
		 * Rebalance the threads' expiry times for the remaining
		 * process CPU timers.
		 */

		cputime_t prof_left, virt_left, ticks;
		unsigned long long sched_left, sched;
		const unsigned int nthreads = atomic_read(&sig->live);

		if (!nthreads)
			return;

		prof_left = cputime_sub(prof_expires, utime);
		prof_left = cputime_sub(prof_left, stime);
		prof_left = cputime_div(prof_left, nthreads);
		virt_left = cputime_sub(virt_expires, utime);
		virt_left = cputime_div(virt_left, nthreads);
		if (sched_expires) {
			sched_left = sched_expires - sched_time;
			do_div(sched_left, nthreads);
		} else {
			sched_left = 0;
		}
		t = tsk;
		do {
			ticks = cputime_add(cputime_add(t->utime, t->stime),
					    prof_left);
			if (!cputime_eq(prof_expires, cputime_zero) &&
			    (cputime_eq(t->it_prof_expires, cputime_zero) ||
			     cputime_gt(t->it_prof_expires, ticks))) {
				t->it_prof_expires = ticks;
			}

			ticks = cputime_add(t->utime, virt_left);
			if (!cputime_eq(virt_expires, cputime_zero) &&
			    (cputime_eq(t->it_virt_expires, cputime_zero) ||
			     cputime_gt(t->it_virt_expires, ticks))) {
				t->it_virt_expires = ticks;
			}

			sched = t->sched_time + sched_left;
			if (sched_expires && (t->it_sched_expires == 0 ||
					      t->it_sched_expires > sched)) {
				t->it_sched_expires = sched;
			}

			do {
				t = next_thread(t);
			} while (unlikely(t->exit_state));
		} while (t != tsk);
	}
}

/*
 * This is called from the signal code (via do_schedule_next_timer)
 * when the last timer signal was delivered and we have to reload the timer.
 */
void posix_cpu_timer_schedule(struct k_itimer *timer)
{
	struct task_struct *p = timer->it.cpu.task;
	union cpu_time_count now;

	if (unlikely(p == NULL))
		/*
		 * The task was cleaned up already, no future firings.
		 */
		return;

	/*
	 * Fetch the current sample and update the timer's expiry time.
	 */
	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
		cpu_clock_sample(timer->it_clock, p, &now);
		bump_cpu_timer(timer, now);
		if (unlikely(p->exit_state)) {
			clear_dead_task(timer, now);
			return;
		}
		read_lock(&tasklist_lock); /* arm_timer needs it.  */
	} else {
		read_lock(&tasklist_lock);
		if (unlikely(p->signal == NULL)) {
			/*
			 * The process has been reaped.
			 * We can't even collect a sample any more.
			 */
			put_task_struct(p);
			timer->it.cpu.task = p = NULL;
			timer->it.cpu.expires.sched = 0;
			read_unlock(&tasklist_lock);
			return;
		} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
			/*
			 * We've noticed that the thread is dead, but
			 * not yet reaped.  Take this opportunity to
			 * drop our task ref.
			 */
			clear_dead_task(timer, now);
			read_unlock(&tasklist_lock);
			return;
		}
		cpu_clock_sample_group(timer->it_clock, p, &now);
		bump_cpu_timer(timer, now);
		/* Leave the tasklist_lock locked for the call below.  */
	}

	/*
	 * Now re-arm for the new expiry time.
	 */
	arm_timer(timer, now);

	read_unlock(&tasklist_lock);
}

/*
 * This is called from the timer interrupt handler.  The irq handler has
 * already updated our counts.  We need to check if any timers fire now.
 * Interrupts are disabled.
 */
void run_posix_cpu_timers(struct task_struct *tsk)
{
	LIST_HEAD(firing);
	struct k_itimer *timer, *next;

	BUG_ON(!irqs_disabled());

#define UNEXPIRED(clock) \
		(cputime_eq(tsk->it_##clock##_expires, cputime_zero) || \
		 cputime_lt(clock##_ticks(tsk), tsk->it_##clock##_expires))

	if (UNEXPIRED(prof) && UNEXPIRED(virt) &&
	    (tsk->it_sched_expires == 0 ||
	     tsk->sched_time < tsk->it_sched_expires))
		return;

#undef	UNEXPIRED

	/*
	 * Double-check with locks held.
	 */
	read_lock(&tasklist_lock);
	if (likely(tsk->signal != NULL)) {
		spin_lock(&tsk->sighand->siglock);

		/*
		 * Here we take off tsk->cpu_timers[N] and tsk->signal->cpu_timers[N]
		 * all the timers that are firing, and put them on the firing list.
		 */
		check_thread_timers(tsk, &firing);
		check_process_timers(tsk, &firing);

		/*
		 * We must release these locks before taking any timer's lock.
		 * There is a potential race with timer deletion here, as the
		 * siglock now protects our private firing list.  We have set
		 * the firing flag in each timer, so that a deletion attempt
		 * that gets the timer lock before we do will give it up and
		 * spin until we've taken care of that timer below.
		 */
		spin_unlock(&tsk->sighand->siglock);
	}
	read_unlock(&tasklist_lock);

	/*
	 * Now that all the timers on our list have the firing flag,
	 * noone will touch their list entries but us.  We'll take
	 * each timer's lock before clearing its firing flag, so no
	 * timer call will interfere.
	 */
	list_for_each_entry_safe(timer, next, &firing, it.cpu.entry) {
		int firing;
		spin_lock(&timer->it_lock);
		list_del_init(&timer->it.cpu.entry);
		firing = timer->it.cpu.firing;
		timer->it.cpu.firing = 0;
		/*
		 * The firing flag is -1 if we collided with a reset
		 * of the timer, which already reported this
		 * almost-firing as an overrun.  So don't generate an event.
		 */
		if (likely(firing >= 0)) {
			cpu_timer_fire(timer);
		}
		spin_unlock(&timer->it_lock);
	}
}

/*
 * Set one of the process-wide special case CPU timers.
 * The tasklist_lock and tsk->sighand->siglock must be held by the caller.
 * The oldval argument is null for the RLIMIT_CPU timer, where *newval is
 * absolute; non-null for ITIMER_*, where *newval is relative and we update
 * it to be absolute, *oldval is absolute and we update it to be relative.
 */
void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
			   cputime_t *newval, cputime_t *oldval)
{
	union cpu_time_count now;
	struct list_head *head;

	BUG_ON(clock_idx == CPUCLOCK_SCHED);
	cpu_clock_sample_group_locked(clock_idx, tsk, &now);

	if (oldval) {
		if (!cputime_eq(*oldval, cputime_zero)) {
			if (cputime_le(*oldval, now.cpu)) {
				/* Just about to fire. */
				*oldval = jiffies_to_cputime(1);
			} else {
				*oldval = cputime_sub(*oldval, now.cpu);
			}
		}

		if (cputime_eq(*newval, cputime_zero))
			return;
		*newval = cputime_add(*newval, now.cpu);

		/*
		 * If the RLIMIT_CPU timer will expire before the
		 * ITIMER_PROF timer, we have nothing else to do.
		 */
		if (tsk->signal->rlim[RLIMIT_CPU].rlim_cur
		    < cputime_to_secs(*newval))
			return;
	}

	/*
	 * Check whether there are any process timers already set to fire
	 * before this one.  If so, we don't have anything more to do.
	 */
	head = &tsk->signal->cpu_timers[clock_idx];
	if (list_empty(head) ||
	    cputime_ge(list_entry(head->next,
				  struct cpu_timer_list, entry)->expires.cpu,
		       *newval)) {
		/*
		 * Rejigger each thread's expiry time so that one will
		 * notice before we hit the process-cumulative expiry time.
		 */
		union cpu_time_count expires = { .sched = 0 };
		expires.cpu = *newval;
		process_timer_rebalance(tsk, clock_idx, expires, now);
	}
}

static long posix_cpu_clock_nanosleep_restart(struct restart_block *);

int posix_cpu_nsleep(clockid_t which_clock, int flags,
		     struct timespec *rqtp)
{
	struct restart_block *restart_block =
	    &current_thread_info()->restart_block;
	struct k_itimer timer;
	int error;

	/*
	 * Diagnose required errors first.
	 */
	if (CPUCLOCK_PERTHREAD(which_clock) &&
	    (CPUCLOCK_PID(which_clock) == 0 ||
	     CPUCLOCK_PID(which_clock) == current->pid))
		return -EINVAL;

	/*
	 * Set up a temporary timer and then wait for it to go off.
	 */
	memset(&timer, 0, sizeof timer);
	spin_lock_init(&timer.it_lock);
	timer.it_clock = which_clock;
	timer.it_overrun = -1;
	error = posix_cpu_timer_create(&timer);
	timer.it_process = current;
	if (!error) {
		struct timespec __user *rmtp;
		static struct itimerspec zero_it;
		struct itimerspec it = { .it_value = *rqtp,
					 .it_interval = {} };

		spin_lock_irq(&timer.it_lock);
		error = posix_cpu_timer_set(&timer, flags, &it, NULL);
		if (error) {
			spin_unlock_irq(&timer.it_lock);
			return error;
		}

		while (!signal_pending(current)) {
			if (timer.it.cpu.expires.sched == 0) {
				/*
				 * Our timer fired and was reset.
				 */
				spin_unlock_irq(&timer.it_lock);
				return 0;
			}

			/*
			 * Block until cpu_timer_fire (or a signal) wakes us.
			 */
			__set_current_state(TASK_INTERRUPTIBLE);
			spin_unlock_irq(&timer.it_lock);
			schedule();
			spin_lock_irq(&timer.it_lock);
		}

		/*
		 * We were interrupted by a signal.
		 */
		sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp);
		posix_cpu_timer_set(&timer, 0, &zero_it, &it);
		spin_unlock_irq(&timer.it_lock);

		if ((it.it_value.tv_sec | it.it_value.tv_nsec) == 0) {
			/*
			 * It actually did fire already.
			 */
			return 0;
		}

		/*
		 * Report back to the user the time still remaining.
		 */
		rmtp = (struct timespec __user *) restart_block->arg1;
		if (rmtp != NULL && !(flags & TIMER_ABSTIME) &&
		    copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
			return -EFAULT;

		restart_block->fn = posix_cpu_clock_nanosleep_restart;
		/* Caller already set restart_block->arg1 */
		restart_block->arg0 = which_clock;
		restart_block->arg2 = rqtp->tv_sec;
		restart_block->arg3 = rqtp->tv_nsec;

		error = -ERESTART_RESTARTBLOCK;
	}

	return error;
}

static long
posix_cpu_clock_nanosleep_restart(struct restart_block *restart_block)
{
	clockid_t which_clock = restart_block->arg0;
	struct timespec t = { .tv_sec = restart_block->arg2,
			      .tv_nsec = restart_block->arg3 };
	restart_block->fn = do_no_restart_syscall;
	return posix_cpu_nsleep(which_clock, TIMER_ABSTIME, &t);
}


#define PROCESS_CLOCK	MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED)
#define THREAD_CLOCK	MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED)

static int process_cpu_clock_getres(clockid_t which_clock, struct timespec *tp)
{
	return posix_cpu_clock_getres(PROCESS_CLOCK, tp);
}
static int process_cpu_clock_get(clockid_t which_clock, struct timespec *tp)
{
	return posix_cpu_clock_get(PROCESS_CLOCK, tp);
}
static int process_cpu_timer_create(struct k_itimer *timer)
{
	timer->it_clock = PROCESS_CLOCK;
	return posix_cpu_timer_create(timer);
}
static int process_cpu_nsleep(clockid_t which_clock, int flags,
			      struct timespec *rqtp)
{
	return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp);
}
static int thread_cpu_clock_getres(clockid_t which_clock, struct timespec *tp)
{
	return posix_cpu_clock_getres(THREAD_CLOCK, tp);
}
static int thread_cpu_clock_get(clockid_t which_clock, struct timespec *tp)
{
	return posix_cpu_clock_get(THREAD_CLOCK, tp);
}
static int thread_cpu_timer_create(struct k_itimer *timer)
{
	timer->it_clock = THREAD_CLOCK;
	return posix_cpu_timer_create(timer);
}
static int thread_cpu_nsleep(clockid_t which_clock, int flags,
			      struct timespec *rqtp)
{
	return -EINVAL;
}

static __init int init_posix_cpu_timers(void)
{
	struct k_clock process = {
		.clock_getres = process_cpu_clock_getres,
		.clock_get = process_cpu_clock_get,
		.clock_set = do_posix_clock_nosettime,
		.timer_create = process_cpu_timer_create,
		.nsleep = process_cpu_nsleep,
	};
	struct k_clock thread = {
		.clock_getres = thread_cpu_clock_getres,
		.clock_get = thread_cpu_clock_get,
		.clock_set = do_posix_clock_nosettime,
		.timer_create = thread_cpu_timer_create,
		.nsleep = thread_cpu_nsleep,
	};

	register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
	register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);

	return 0;
}
__initcall(init_posix_cpu_timers);