summaryrefslogtreecommitdiffstats
path: root/kernel/time/timer_migration.c
blob: 84413114db5c5b34e7b11ceaaeb1167a2ad04635 (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
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Infrastructure for migratable timers
 *
 * Copyright(C) 2022 linutronix GmbH
 */
#include <linux/cpuhotplug.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/spinlock.h>
#include <linux/timerqueue.h>
#include <trace/events/ipi.h>

#include "timer_migration.h"
#include "tick-internal.h"

#define CREATE_TRACE_POINTS
#include <trace/events/timer_migration.h>

/*
 * The timer migration mechanism is built on a hierarchy of groups. The
 * lowest level group contains CPUs, the next level groups of CPU groups
 * and so forth. The CPU groups are kept per node so for the normal case
 * lock contention won't happen across nodes. Depending on the number of
 * CPUs per node even the next level might be kept as groups of CPU groups
 * per node and only the levels above cross the node topology.
 *
 * Example topology for a two node system with 24 CPUs each.
 *
 * LVL 2                           [GRP2:0]
 *                              GRP1:0 = GRP1:M
 *
 * LVL 1            [GRP1:0]                      [GRP1:1]
 *               GRP0:0 - GRP0:2               GRP0:3 - GRP0:5
 *
 * LVL 0  [GRP0:0]  [GRP0:1]  [GRP0:2]  [GRP0:3]  [GRP0:4]  [GRP0:5]
 * CPUS     0-7       8-15      16-23     24-31     32-39     40-47
 *
 * The groups hold a timer queue of events sorted by expiry time. These
 * queues are updated when CPUs go in idle. When they come out of idle
 * ignore flag of events is set.
 *
 * Each group has a designated migrator CPU/group as long as a CPU/group is
 * active in the group. This designated role is necessary to avoid that all
 * active CPUs in a group try to migrate expired timers from other CPUs,
 * which would result in massive lock bouncing.
 *
 * When a CPU is awake, it checks in it's own timer tick the group
 * hierarchy up to the point where it is assigned the migrator role or if
 * no CPU is active, it also checks the groups where no migrator is set
 * (TMIGR_NONE).
 *
 * If it finds expired timers in one of the group queues it pulls them over
 * from the idle CPU and runs the timer function. After that it updates the
 * group and the parent groups if required.
 *
 * CPUs which go idle arm their CPU local timer hardware for the next local
 * (pinned) timer event. If the next migratable timer expires after the
 * next local timer or the CPU has no migratable timer pending then the
 * CPU does not queue an event in the LVL0 group. If the next migratable
 * timer expires before the next local timer then the CPU queues that timer
 * in the LVL0 group. In both cases the CPU marks itself idle in the LVL0
 * group.
 *
 * When CPU comes out of idle and when a group has at least a single active
 * child, the ignore flag of the tmigr_event is set. This indicates, that
 * the event is ignored even if it is still enqueued in the parent groups
 * timer queue. It will be removed when touching the timer queue the next
 * time. This spares locking in active path as the lock protects (after
 * setup) only event information. For more information about locking,
 * please read the section "Locking rules".
 *
 * If the CPU is the migrator of the group then it delegates that role to
 * the next active CPU in the group or sets migrator to TMIGR_NONE when
 * there is no active CPU in the group. This delegation needs to be
 * propagated up the hierarchy so hand over from other leaves can happen at
 * all hierarchy levels w/o doing a search.
 *
 * When the last CPU in the system goes idle, then it drops all migrator
 * duties up to the top level of the hierarchy (LVL2 in the example). It
 * then has to make sure, that it arms it's own local hardware timer for
 * the earliest event in the system.
 *
 *
 * Lifetime rules:
 * ---------------
 *
 * The groups are built up at init time or when CPUs come online. They are
 * not destroyed when a group becomes empty due to offlining. The group
 * just won't participate in the hierarchy management anymore. Destroying
 * groups would result in interesting race conditions which would just make
 * the whole mechanism slow and complex.
 *
 *
 * Locking rules:
 * --------------
 *
 * For setting up new groups and handling events it's required to lock both
 * child and parent group. The lock ordering is always bottom up. This also
 * includes the per CPU locks in struct tmigr_cpu. For updating the migrator and
 * active CPU/group information atomic_try_cmpxchg() is used instead and only
 * the per CPU tmigr_cpu->lock is held.
 *
 * During the setup of groups tmigr_level_list is required. It is protected by
 * @tmigr_mutex.
 *
 * When @timer_base->lock as well as tmigr related locks are required, the lock
 * ordering is: first @timer_base->lock, afterwards tmigr related locks.
 *
 *
 * Protection of the tmigr group state information:
 * ------------------------------------------------
 *
 * The state information with the list of active children and migrator needs to
 * be protected by a sequence counter. It prevents a race when updates in child
 * groups are propagated in changed order. The state update is performed
 * lockless and group wise. The following scenario describes what happens
 * without updating the sequence counter:
 *
 * Therefore, let's take three groups and four CPUs (CPU2 and CPU3 as well
 * as GRP0:1 will not change during the scenario):
 *
 *    LVL 1            [GRP1:0]
 *                     migrator = GRP0:1
 *                     active   = GRP0:0, GRP0:1
 *                   /                \
 *    LVL 0  [GRP0:0]                  [GRP0:1]
 *           migrator = CPU0           migrator = CPU2
 *           active   = CPU0           active   = CPU2
 *              /         \                /         \
 *    CPUs     0           1              2           3
 *             active      idle           active      idle
 *
 *
 * 1. CPU0 goes idle. As the update is performed group wise, in the first step
 *    only GRP0:0 is updated. The update of GRP1:0 is pending as CPU0 has to
 *    walk the hierarchy.
 *
 *    LVL 1            [GRP1:0]
 *                     migrator = GRP0:1
 *                     active   = GRP0:0, GRP0:1
 *                   /                \
 *    LVL 0  [GRP0:0]                  [GRP0:1]
 *       --> migrator = TMIGR_NONE     migrator = CPU2
 *       --> active   =                active   = CPU2
 *              /         \                /         \
 *    CPUs     0           1              2           3
 *         --> idle        idle           active      idle
 *
 * 2. While CPU0 goes idle and continues to update the state, CPU1 comes out of
 *    idle. CPU1 updates GRP0:0. The update for GRP1:0 is pending as CPU1 also
 *    has to walk the hierarchy. Both CPUs (CPU0 and CPU1) now walk the
 *    hierarchy to perform the needed update from their point of view. The
 *    currently visible state looks the following:
 *
 *    LVL 1            [GRP1:0]
 *                     migrator = GRP0:1
 *                     active   = GRP0:0, GRP0:1
 *                   /                \
 *    LVL 0  [GRP0:0]                  [GRP0:1]
 *       --> migrator = CPU1           migrator = CPU2
 *       --> active   = CPU1           active   = CPU2
 *              /         \                /         \
 *    CPUs     0           1              2           3
 *             idle    --> active         active      idle
 *
 * 3. Here is the race condition: CPU1 managed to propagate its changes (from
 *    step 2) through the hierarchy to GRP1:0 before CPU0 (step 1) did. The
 *    active members of GRP1:0 remain unchanged after the update since it is
 *    still valid from CPU1 current point of view:
 *
 *    LVL 1            [GRP1:0]
 *                 --> migrator = GRP0:1
 *                 --> active   = GRP0:0, GRP0:1
 *                   /                \
 *    LVL 0  [GRP0:0]                  [GRP0:1]
 *           migrator = CPU1           migrator = CPU2
 *           active   = CPU1           active   = CPU2
 *              /         \                /         \
 *    CPUs     0           1              2           3
 *             idle        active         active      idle
 *
 * 4. Now CPU0 finally propagates its changes (from step 1) to GRP1:0.
 *
 *    LVL 1            [GRP1:0]
 *                 --> migrator = GRP0:1
 *                 --> active   = GRP0:1
 *                   /                \
 *    LVL 0  [GRP0:0]                  [GRP0:1]
 *           migrator = CPU1           migrator = CPU2
 *           active   = CPU1           active   = CPU2
 *              /         \                /         \
 *    CPUs     0           1              2           3
 *             idle        active         active      idle
 *
 *
 * The race of CPU0 vs. CPU1 led to an inconsistent state in GRP1:0. CPU1 is
 * active and is correctly listed as active in GRP0:0. However GRP1:0 does not
 * have GRP0:0 listed as active, which is wrong. The sequence counter has been
 * added to avoid inconsistent states during updates. The state is updated
 * atomically only if all members, including the sequence counter, match the
 * expected value (compare-and-exchange).
 *
 * Looking back at the previous example with the addition of the sequence
 * counter: The update as performed by CPU0 in step 4 will fail. CPU1 changed
 * the sequence number during the update in step 3 so the expected old value (as
 * seen by CPU0 before starting the walk) does not match.
 *
 * Prevent race between new event and last CPU going inactive
 * ----------------------------------------------------------
 *
 * When the last CPU is going idle and there is a concurrent update of a new
 * first global timer of an idle CPU, the group and child states have to be read
 * while holding the lock in tmigr_update_events(). The following scenario shows
 * what happens, when this is not done.
 *
 * 1. Only CPU2 is active:
 *
 *    LVL 1            [GRP1:0]
 *                     migrator = GRP0:1
 *                     active   = GRP0:1
 *                     next_expiry = KTIME_MAX
 *                   /                \
 *    LVL 0  [GRP0:0]                  [GRP0:1]
 *           migrator = TMIGR_NONE     migrator = CPU2
 *           active   =                active   = CPU2
 *           next_expiry = KTIME_MAX   next_expiry = KTIME_MAX
 *              /         \                /         \
 *    CPUs     0           1              2           3
 *             idle        idle           active      idle
 *
 * 2. Now CPU 2 goes idle (and has no global timer, that has to be handled) and
 *    propagates that to GRP0:1:
 *
 *    LVL 1            [GRP1:0]
 *                     migrator = GRP0:1
 *                     active   = GRP0:1
 *                     next_expiry = KTIME_MAX
 *                   /                \
 *    LVL 0  [GRP0:0]                  [GRP0:1]
 *           migrator = TMIGR_NONE --> migrator = TMIGR_NONE
 *           active   =            --> active   =
 *           next_expiry = KTIME_MAX   next_expiry = KTIME_MAX
 *              /         \                /         \
 *    CPUs     0           1              2           3
 *             idle        idle       --> idle        idle
 *
 * 3. Now the idle state is propagated up to GRP1:0. As this is now the last
 *    child going idle in top level group, the expiry of the next group event
 *    has to be handed back to make sure no event is lost. As there is no event
 *    enqueued, KTIME_MAX is handed back to CPU2.
 *
 *    LVL 1            [GRP1:0]
 *                 --> migrator = TMIGR_NONE
 *                 --> active   =
 *                     next_expiry = KTIME_MAX
 *                   /                \
 *    LVL 0  [GRP0:0]                  [GRP0:1]
 *           migrator = TMIGR_NONE     migrator = TMIGR_NONE
 *           active   =                active   =
 *           next_expiry = KTIME_MAX   next_expiry = KTIME_MAX
 *              /         \                /         \
 *    CPUs     0           1              2           3
 *             idle        idle       --> idle        idle
 *
 * 4. CPU 0 has a new timer queued from idle and it expires at TIMER0. CPU0
 *    propagates that to GRP0:0:
 *
 *    LVL 1            [GRP1:0]
 *                     migrator = TMIGR_NONE
 *                     active   =
 *                     next_expiry = KTIME_MAX
 *                   /                \
 *    LVL 0  [GRP0:0]                  [GRP0:1]
 *           migrator = TMIGR_NONE     migrator = TMIGR_NONE
 *           active   =                active   =
 *       --> next_expiry = TIMER0      next_expiry  = KTIME_MAX
 *              /         \                /         \
 *    CPUs     0           1              2           3
 *             idle        idle           idle        idle
 *
 * 5. GRP0:0 is not active, so the new timer has to be propagated to
 *    GRP1:0. Therefore the GRP1:0 state has to be read. When the stalled value
 *    (from step 2) is read, the timer is enqueued into GRP1:0, but nothing is
 *    handed back to CPU0, as it seems that there is still an active child in
 *    top level group.
 *
 *    LVL 1            [GRP1:0]
 *                     migrator = TMIGR_NONE
 *                     active   =
 *                 --> next_expiry = TIMER0
 *                   /                \
 *    LVL 0  [GRP0:0]                  [GRP0:1]
 *           migrator = TMIGR_NONE     migrator = TMIGR_NONE
 *           active   =                active   =
 *           next_expiry = TIMER0      next_expiry  = KTIME_MAX
 *              /         \                /         \
 *    CPUs     0           1              2           3
 *             idle        idle           idle        idle
 *
 * This is prevented by reading the state when holding the lock (when a new
 * timer has to be propagated from idle path)::
 *
 *   CPU2 (tmigr_inactive_up())          CPU0 (tmigr_new_timer_up())
 *   --------------------------          ---------------------------
 *   // step 3:
 *   cmpxchg(&GRP1:0->state);
 *   tmigr_update_events() {
 *       spin_lock(&GRP1:0->lock);
 *       // ... update events ...
 *       // hand back first expiry when GRP1:0 is idle
 *       spin_unlock(&GRP1:0->lock);
 *       // ^^^ release state modification
 *   }
 *                                       tmigr_update_events() {
 *                                           spin_lock(&GRP1:0->lock)
 *                                           // ^^^ acquire state modification
 *                                           group_state = atomic_read(&GRP1:0->state)
 *                                           // .... update events ...
 *                                           // hand back first expiry when GRP1:0 is idle
 *                                           spin_unlock(&GRP1:0->lock) <3>
 *                                           // ^^^ makes state visible for other
 *                                           // callers of tmigr_new_timer_up()
 *                                       }
 *
 * When CPU0 grabs the lock directly after cmpxchg, the first timer is reported
 * back to CPU0 and also later on to CPU2. So no timer is missed. A concurrent
 * update of the group state from active path is no problem, as the upcoming CPU
 * will take care of the group events.
 *
 * Required event and timerqueue update after a remote expiry:
 * -----------------------------------------------------------
 *
 * After expiring timers of a remote CPU, a walk through the hierarchy and
 * update of events and timerqueues is required. It is obviously needed if there
 * is a 'new' global timer but also if there is no new global timer but the
 * remote CPU is still idle.
 *
 * 1. CPU0 and CPU1 are idle and have both a global timer expiring at the same
 *    time. So both have an event enqueued in the timerqueue of GRP0:0. CPU3 is
 *    also idle and has no global timer pending. CPU2 is the only active CPU and
 *    thus also the migrator:
 *
 *    LVL 1            [GRP1:0]
 *                     migrator = GRP0:1
 *                     active   = GRP0:1
 *                 --> timerqueue = evt-GRP0:0
 *                   /                \
 *    LVL 0  [GRP0:0]                  [GRP0:1]
 *           migrator = TMIGR_NONE     migrator = CPU2
 *           active   =                active   = CPU2
 *           groupevt.ignore = false   groupevt.ignore = true
 *           groupevt.cpu = CPU0       groupevt.cpu =
 *           timerqueue = evt-CPU0,    timerqueue =
 *                        evt-CPU1
 *              /         \                /         \
 *    CPUs     0           1              2           3
 *             idle        idle           active      idle
 *
 * 2. CPU2 starts to expire remote timers. It starts with LVL0 group
 *    GRP0:1. There is no event queued in the timerqueue, so CPU2 continues with
 *    the parent of GRP0:1: GRP1:0. In GRP1:0 it dequeues the first event. It
 *    looks at tmigr_event::cpu struct member and expires the pending timer(s)
 *    of CPU0.
 *
 *    LVL 1            [GRP1:0]
 *                     migrator = GRP0:1
 *                     active   = GRP0:1
 *                 --> timerqueue =
 *                   /                \
 *    LVL 0  [GRP0:0]                  [GRP0:1]
 *           migrator = TMIGR_NONE     migrator = CPU2
 *           active   =                active   = CPU2
 *           groupevt.ignore = false   groupevt.ignore = true
 *       --> groupevt.cpu = CPU0       groupevt.cpu =
 *           timerqueue = evt-CPU0,    timerqueue =
 *                        evt-CPU1
 *              /         \                /         \
 *    CPUs     0           1              2           3
 *             idle        idle           active      idle
 *
 * 3. Some work has to be done after expiring the timers of CPU0. If we stop
 *    here, then CPU1's pending global timer(s) will not expire in time and the
 *    timerqueue of GRP0:0 has still an event for CPU0 enqueued which has just
 *    been processed. So it is required to walk the hierarchy from CPU0's point
 *    of view and update it accordingly. CPU0's event will be removed from the
 *    timerqueue because it has no pending timer. If CPU0 would have a timer
 *    pending then it has to expire after CPU1's first timer because all timers
 *    from this period were just expired. Either way CPU1's event will be first
 *    in GRP0:0's timerqueue and therefore set in the CPU field of the group
 *    event which is then enqueued in GRP1:0's timerqueue as GRP0:0 is still not
 *    active:
 *
 *    LVL 1            [GRP1:0]
 *                     migrator = GRP0:1
 *                     active   = GRP0:1
 *                 --> timerqueue = evt-GRP0:0
 *                   /                \
 *    LVL 0  [GRP0:0]                  [GRP0:1]
 *           migrator = TMIGR_NONE     migrator = CPU2
 *           active   =                active   = CPU2
 *           groupevt.ignore = false   groupevt.ignore = true
 *       --> groupevt.cpu = CPU1       groupevt.cpu =
 *       --> timerqueue = evt-CPU1     timerqueue =
 *              /         \                /         \
 *    CPUs     0           1              2           3
 *             idle        idle           active      idle
 *
 * Now CPU2 (migrator) will continue step 2 at GRP1:0 and will expire the
 * timer(s) of CPU1.
 *
 * The hierarchy walk in step 3 can be skipped if the migrator notices that a
 * CPU of GRP0:0 is active again. The CPU will mark GRP0:0 active and take care
 * of the group as migrator and any needed updates within the hierarchy.
 */

static DEFINE_MUTEX(tmigr_mutex);
static struct list_head *tmigr_level_list __read_mostly;

static unsigned int tmigr_hierarchy_levels __read_mostly;
static unsigned int tmigr_crossnode_level __read_mostly;

static DEFINE_PER_CPU(struct tmigr_cpu, tmigr_cpu);

#define TMIGR_NONE	0xFF
#define BIT_CNT		8

static inline bool tmigr_is_not_available(struct tmigr_cpu *tmc)
{
	return !(tmc->tmgroup && tmc->online);
}

/*
 * Returns true, when @childmask corresponds to the group migrator or when the
 * group is not active - so no migrator is set.
 */
static bool tmigr_check_migrator(struct tmigr_group *group, u8 childmask)
{
	union tmigr_state s;

	s.state = atomic_read(&group->migr_state);

	if ((s.migrator == childmask) || (s.migrator == TMIGR_NONE))
		return true;

	return false;
}

static bool tmigr_check_migrator_and_lonely(struct tmigr_group *group, u8 childmask)
{
	bool lonely, migrator = false;
	unsigned long active;
	union tmigr_state s;

	s.state = atomic_read(&group->migr_state);

	if ((s.migrator == childmask) || (s.migrator == TMIGR_NONE))
		migrator = true;

	active = s.active;
	lonely = bitmap_weight(&active, BIT_CNT) <= 1;

	return (migrator && lonely);
}

static bool tmigr_check_lonely(struct tmigr_group *group)
{
	unsigned long active;
	union tmigr_state s;

	s.state = atomic_read(&group->migr_state);

	active = s.active;

	return bitmap_weight(&active, BIT_CNT) <= 1;
}

typedef bool (*up_f)(struct tmigr_group *, struct tmigr_group *, void *);

static void __walk_groups(up_f up, void *data,
			  struct tmigr_cpu *tmc)
{
	struct tmigr_group *child = NULL, *group = tmc->tmgroup;

	do {
		WARN_ON_ONCE(group->level >= tmigr_hierarchy_levels);

		if (up(group, child, data))
			break;

		child = group;
		group = group->parent;
	} while (group);
}

static void walk_groups(up_f up, void *data, struct tmigr_cpu *tmc)
{
	lockdep_assert_held(&tmc->lock);

	__walk_groups(up, data, tmc);
}

/**
 * struct tmigr_walk - data required for walking the hierarchy
 * @nextexp:		Next CPU event expiry information which is handed into
 *			the timer migration code by the timer code
 *			(get_next_timer_interrupt())
 * @firstexp:		Contains the first event expiry information when last
 *			active CPU of hierarchy is on the way to idle to make
 *			sure CPU will be back in time.
 * @evt:		Pointer to tmigr_event which needs to be queued (of idle
 *			child group)
 * @childmask:		childmask of child group
 * @remote:		Is set, when the new timer path is executed in
 *			tmigr_handle_remote_cpu()
 */
struct tmigr_walk {
	u64			nextexp;
	u64			firstexp;
	struct tmigr_event	*evt;
	u8			childmask;
	bool			remote;
};

/**
 * struct tmigr_remote_data - data required for remote expiry hierarchy walk
 * @basej:		timer base in jiffies
 * @now:		timer base monotonic
 * @firstexp:		returns expiry of the first timer in the idle timer
 *			migration hierarchy to make sure the timer is handled in
 *			time; it is stored in the per CPU tmigr_cpu struct of
 *			CPU which expires remote timers
 * @childmask:		childmask of child group
 * @check:		is set if there is the need to handle remote timers;
 *			required in tmigr_requires_handle_remote() only
 * @tmc_active:		this flag indicates, whether the CPU which triggers
 *			the hierarchy walk is !idle in the timer migration
 *			hierarchy. When the CPU is idle and the whole hierarchy is
 *			idle, only the first event of the top level has to be
 *			considered.
 */
struct tmigr_remote_data {
	unsigned long	basej;
	u64		now;
	u64		firstexp;
	u8		childmask;
	bool		check;
	bool		tmc_active;
};

/*
 * Returns the next event of the timerqueue @group->events
 *
 * Removes timers with ignore flag and update next_expiry of the group. Values
 * of the group event are updated in tmigr_update_events() only.
 */
static struct tmigr_event *tmigr_next_groupevt(struct tmigr_group *group)
{
	struct timerqueue_node *node = NULL;
	struct tmigr_event *evt = NULL;

	lockdep_assert_held(&group->lock);

	WRITE_ONCE(group->next_expiry, KTIME_MAX);

	while ((node = timerqueue_getnext(&group->events))) {
		evt = container_of(node, struct tmigr_event, nextevt);

		if (!evt->ignore) {
			WRITE_ONCE(group->next_expiry, evt->nextevt.expires);
			return evt;
		}

		/*
		 * Remove next timers with ignore flag, because the group lock
		 * is held anyway
		 */
		if (!timerqueue_del(&group->events, node))
			break;
	}

	return NULL;
}

/*
 * Return the next event (with the expiry equal or before @now)
 *
 * Event, which is returned, is also removed from the queue.
 */
static struct tmigr_event *tmigr_next_expired_groupevt(struct tmigr_group *group,
						       u64 now)
{
	struct tmigr_event *evt = tmigr_next_groupevt(group);

	if (!evt || now < evt->nextevt.expires)
		return NULL;

	/*
	 * The event is ready to expire. Remove it and update next group event.
	 */
	timerqueue_del(&group->events, &evt->nextevt);
	tmigr_next_groupevt(group);

	return evt;
}

static u64 tmigr_next_groupevt_expires(struct tmigr_group *group)
{
	struct tmigr_event *evt;

	evt = tmigr_next_groupevt(group);

	if (!evt)
		return KTIME_MAX;
	else
		return evt->nextevt.expires;
}

static bool tmigr_active_up(struct tmigr_group *group,
			    struct tmigr_group *child,
			    void *ptr)
{
	union tmigr_state curstate, newstate;
	struct tmigr_walk *data = ptr;
	bool walk_done;
	u8 childmask;

	childmask = data->childmask;
	/*
	 * No memory barrier is required here in contrast to
	 * tmigr_inactive_up(), as the group state change does not depend on the
	 * child state.
	 */
	curstate.state = atomic_read(&group->migr_state);

	do {
		newstate = curstate;
		walk_done = true;

		if (newstate.migrator == TMIGR_NONE) {
			newstate.migrator = childmask;

			/* Changes need to be propagated */
			walk_done = false;
		}

		newstate.active |= childmask;
		newstate.seq++;

	} while (!atomic_try_cmpxchg(&group->migr_state, &curstate.state, newstate.state));

	if ((walk_done == false) && group->parent)
		data->childmask = group->childmask;

	/*
	 * The group is active (again). The group event might be still queued
	 * into the parent group's timerqueue but can now be handled by the
	 * migrator of this group. Therefore the ignore flag for the group event
	 * is updated to reflect this.
	 *
	 * The update of the ignore flag in the active path is done lockless. In
	 * worst case the migrator of the parent group observes the change too
	 * late and expires remotely all events belonging to this group. The
	 * lock is held while updating the ignore flag in idle path. So this
	 * state change will not be lost.
	 */
	group->groupevt.ignore = true;

	trace_tmigr_group_set_cpu_active(group, newstate, childmask);

	return walk_done;
}

static void __tmigr_cpu_activate(struct tmigr_cpu *tmc)
{
	struct tmigr_walk data;

	data.childmask = tmc->childmask;

	trace_tmigr_cpu_active(tmc);

	tmc->cpuevt.ignore = true;
	WRITE_ONCE(tmc->wakeup, KTIME_MAX);

	walk_groups(&tmigr_active_up, &data, tmc);
}

/**
 * tmigr_cpu_activate() - set this CPU active in timer migration hierarchy
 *
 * Call site timer_clear_idle() is called with interrupts disabled.
 */
void tmigr_cpu_activate(void)
{
	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);

	if (tmigr_is_not_available(tmc))
		return;

	if (WARN_ON_ONCE(!tmc->idle))
		return;

	raw_spin_lock(&tmc->lock);
	tmc->idle = false;
	__tmigr_cpu_activate(tmc);
	raw_spin_unlock(&tmc->lock);
}

/*
 * Returns true, if there is nothing to be propagated to the next level
 *
 * @data->firstexp is set to expiry of first gobal event of the (top level of
 * the) hierarchy, but only when hierarchy is completely idle.
 *
 * The child and group states need to be read under the lock, to prevent a race
 * against a concurrent tmigr_inactive_up() run when the last CPU goes idle. See
 * also section "Prevent race between new event and last CPU going inactive" in
 * the documentation at the top.
 *
 * This is the only place where the group event expiry value is set.
 */
static
bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
			 struct tmigr_walk *data)
{
	struct tmigr_event *evt, *first_childevt;
	union tmigr_state childstate, groupstate;
	bool remote = data->remote;
	bool walk_done = false;
	u64 nextexp;

	if (child) {
		raw_spin_lock(&child->lock);
		raw_spin_lock_nested(&group->lock, SINGLE_DEPTH_NESTING);

		childstate.state = atomic_read(&child->migr_state);
		groupstate.state = atomic_read(&group->migr_state);

		if (childstate.active) {
			walk_done = true;
			goto unlock;
		}

		first_childevt = tmigr_next_groupevt(child);
		nextexp = child->next_expiry;
		evt = &child->groupevt;

		evt->ignore = (nextexp == KTIME_MAX) ? true : false;
	} else {
		nextexp = data->nextexp;

		first_childevt = evt = data->evt;

		/*
		 * Walking the hierarchy is required in any case when a
		 * remote expiry was done before. This ensures to not lose
		 * already queued events in non active groups (see section
		 * "Required event and timerqueue update after a remote
		 * expiry" in the documentation at the top).
		 *
		 * The two call sites which are executed without a remote expiry
		 * before, are not prevented from propagating changes through
		 * the hierarchy by the return:
		 *  - When entering this path by tmigr_new_timer(), @evt->ignore
		 *    is never set.
		 *  - tmigr_inactive_up() takes care of the propagation by
		 *    itself and ignores the return value. But an immediate
		 *    return is possible if there is a parent, sparing group
		 *    locking at this level, because the upper walking call to
		 *    the parent will take care about removing this event from
		 *    within the group and update next_expiry accordingly.
		 *
		 * However if there is no parent, ie: the hierarchy has only a
		 * single level so @group is the top level group, make sure the
		 * first event information of the group is updated properly and
		 * also handled properly, so skip this fast return path.
		 */
		if (evt->ignore && !remote && group->parent)
			return true;

		raw_spin_lock(&group->lock);

		childstate.state = 0;
		groupstate.state = atomic_read(&group->migr_state);
	}

	/*
	 * If the child event is already queued in the group, remove it from the
	 * queue when the expiry time changed only or when it could be ignored.
	 */
	if (timerqueue_node_queued(&evt->nextevt)) {
		if ((evt->nextevt.expires == nextexp) && !evt->ignore) {
			/* Make sure not to miss a new CPU event with the same expiry */
			evt->cpu = first_childevt->cpu;
			goto check_toplvl;
		}

		if (!timerqueue_del(&group->events, &evt->nextevt))
			WRITE_ONCE(group->next_expiry, KTIME_MAX);
	}

	if (evt->ignore) {
		/*
		 * When the next child event could be ignored (nextexp is
		 * KTIME_MAX) and there was no remote timer handling before or
		 * the group is already active, there is no need to walk the
		 * hierarchy even if there is a parent group.
		 *
		 * The other way round: even if the event could be ignored, but
		 * if a remote timer handling was executed before and the group
		 * is not active, walking the hierarchy is required to not miss
		 * an enqueued timer in the non active group. The enqueued timer
		 * of the group needs to be propagated to a higher level to
		 * ensure it is handled.
		 */
		if (!remote || groupstate.active)
			walk_done = true;
	} else {
		evt->nextevt.expires = nextexp;
		evt->cpu = first_childevt->cpu;

		if (timerqueue_add(&group->events, &evt->nextevt))
			WRITE_ONCE(group->next_expiry, nextexp);
	}

check_toplvl:
	if (!group->parent && (groupstate.migrator == TMIGR_NONE)) {
		walk_done = true;

		/*
		 * Nothing to do when update was done during remote timer
		 * handling. First timer in top level group which needs to be
		 * handled when top level group is not active, is calculated
		 * directly in tmigr_handle_remote_up().
		 */
		if (remote)
			goto unlock;

		/*
		 * The top level group is idle and it has to be ensured the
		 * global timers are handled in time. (This could be optimized
		 * by keeping track of the last global scheduled event and only
		 * arming it on the CPU if the new event is earlier. Not sure if
		 * its worth the complexity.)
		 */
		data->firstexp = tmigr_next_groupevt_expires(group);
	}

	trace_tmigr_update_events(child, group, childstate, groupstate,
				  nextexp);

unlock:
	raw_spin_unlock(&group->lock);

	if (child)
		raw_spin_unlock(&child->lock);

	return walk_done;
}

static bool tmigr_new_timer_up(struct tmigr_group *group,
			       struct tmigr_group *child,
			       void *ptr)
{
	struct tmigr_walk *data = ptr;

	return tmigr_update_events(group, child, data);
}

/*
 * Returns the expiry of the next timer that needs to be handled. KTIME_MAX is
 * returned, if an active CPU will handle all the timer migration hierarchy
 * timers.
 */
static u64 tmigr_new_timer(struct tmigr_cpu *tmc, u64 nextexp)
{
	struct tmigr_walk data = { .nextexp = nextexp,
				   .firstexp = KTIME_MAX,
				   .evt = &tmc->cpuevt };

	lockdep_assert_held(&tmc->lock);

	if (tmc->remote)
		return KTIME_MAX;

	trace_tmigr_cpu_new_timer(tmc);

	tmc->cpuevt.ignore = false;
	data.remote = false;

	walk_groups(&tmigr_new_timer_up, &data, tmc);

	/* If there is a new first global event, make sure it is handled */
	return data.firstexp;
}

static void tmigr_handle_remote_cpu(unsigned int cpu, u64 now,
				    unsigned long jif)
{
	struct timer_events tevt;
	struct tmigr_walk data;
	struct tmigr_cpu *tmc;

	tmc = per_cpu_ptr(&tmigr_cpu, cpu);

	raw_spin_lock_irq(&tmc->lock);

	/*
	 * If the remote CPU is offline then the timers have been migrated to
	 * another CPU.
	 *
	 * If tmigr_cpu::remote is set, at the moment another CPU already
	 * expires the timers of the remote CPU.
	 *
	 * If tmigr_event::ignore is set, then the CPU returns from idle and
	 * takes care of its timers.
	 *
	 * If the next event expires in the future, then the event has been
	 * updated and there are no timers to expire right now. The CPU which
	 * updated the event takes care when hierarchy is completely
	 * idle. Otherwise the migrator does it as the event is enqueued.
	 */
	if (!tmc->online || tmc->remote || tmc->cpuevt.ignore ||
	    now < tmc->cpuevt.nextevt.expires) {
		raw_spin_unlock_irq(&tmc->lock);
		return;
	}

	trace_tmigr_handle_remote_cpu(tmc);

	tmc->remote = true;
	WRITE_ONCE(tmc->wakeup, KTIME_MAX);

	/* Drop the lock to allow the remote CPU to exit idle */
	raw_spin_unlock_irq(&tmc->lock);

	if (cpu != smp_processor_id())
		timer_expire_remote(cpu);

	/*
	 * Lock ordering needs to be preserved - timer_base locks before tmigr
	 * related locks (see section "Locking rules" in the documentation at
	 * the top). During fetching the next timer interrupt, also tmc->lock
	 * needs to be held. Otherwise there is a possible race window against
	 * the CPU itself when it comes out of idle, updates the first timer in
	 * the hierarchy and goes back to idle.
	 *
	 * timer base locks are dropped as fast as possible: After checking
	 * whether the remote CPU went offline in the meantime and after
	 * fetching the next remote timer interrupt. Dropping the locks as fast
	 * as possible keeps the locking region small and prevents holding
	 * several (unnecessary) locks during walking the hierarchy for updating
	 * the timerqueue and group events.
	 */
	local_irq_disable();
	timer_lock_remote_bases(cpu);
	raw_spin_lock(&tmc->lock);

	/*
	 * When the CPU went offline in the meantime, no hierarchy walk has to
	 * be done for updating the queued events, because the walk was
	 * already done during marking the CPU offline in the hierarchy.
	 *
	 * When the CPU is no longer idle, the CPU takes care of the timers and
	 * also of the timers in the hierarchy.
	 *
	 * (See also section "Required event and timerqueue update after a
	 * remote expiry" in the documentation at the top)
	 */
	if (!tmc->online || !tmc->idle) {
		timer_unlock_remote_bases(cpu);
		goto unlock;
	}

	/* next	event of CPU */
	fetch_next_timer_interrupt_remote(jif, now, &tevt, cpu);
	timer_unlock_remote_bases(cpu);

	data.nextexp = tevt.global;
	data.firstexp = KTIME_MAX;
	data.evt = &tmc->cpuevt;
	data.remote = true;

	/*
	 * The update is done even when there is no 'new' global timer pending
	 * on the remote CPU (see section "Required event and timerqueue update
	 * after a remote expiry" in the documentation at the top)
	 */
	walk_groups(&tmigr_new_timer_up, &data, tmc);

unlock:
	tmc->remote = false;
	raw_spin_unlock_irq(&tmc->lock);
}

static bool tmigr_handle_remote_up(struct tmigr_group *group,
				   struct tmigr_group *child,
				   void *ptr)
{
	struct tmigr_remote_data *data = ptr;
	struct tmigr_event *evt;
	unsigned long jif;
	u8 childmask;
	u64 now;

	jif = data->basej;
	now = data->now;

	childmask = data->childmask;

	trace_tmigr_handle_remote(group);
again:
	/*
	 * Handle the group only if @childmask is the migrator or if the
	 * group has no migrator. Otherwise the group is active and is
	 * handled by its own migrator.
	 */
	if (!tmigr_check_migrator(group, childmask))
		return true;

	raw_spin_lock_irq(&group->lock);

	evt = tmigr_next_expired_groupevt(group, now);

	if (evt) {
		unsigned int remote_cpu = evt->cpu;

		raw_spin_unlock_irq(&group->lock);

		tmigr_handle_remote_cpu(remote_cpu, now, jif);

		/* check if there is another event, that needs to be handled */
		goto again;
	}

	/*
	 * Update of childmask for the next level and keep track of the expiry
	 * of the first event that needs to be handled (group->next_expiry was
	 * updated by tmigr_next_expired_groupevt(), next was set by
	 * tmigr_handle_remote_cpu()).
	 */
	data->childmask = group->childmask;
	data->firstexp = group->next_expiry;

	raw_spin_unlock_irq(&group->lock);

	return false;
}

/**
 * tmigr_handle_remote() - Handle global timers of remote idle CPUs
 *
 * Called from the timer soft interrupt with interrupts enabled.
 */
void tmigr_handle_remote(void)
{
	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
	struct tmigr_remote_data data;

	if (tmigr_is_not_available(tmc))
		return;

	data.childmask = tmc->childmask;
	data.firstexp = KTIME_MAX;

	/*
	 * NOTE: This is a doubled check because the migrator test will be done
	 * in tmigr_handle_remote_up() anyway. Keep this check to speed up the
	 * return when nothing has to be done.
	 */
	if (!tmigr_check_migrator(tmc->tmgroup, tmc->childmask)) {
		/*
		 * If this CPU was an idle migrator, make sure to clear its wakeup
		 * value so it won't chase timers that have already expired elsewhere.
		 * This avoids endless requeue from tmigr_new_timer().
		 */
		if (READ_ONCE(tmc->wakeup) == KTIME_MAX)
			return;
	}

	data.now = get_jiffies_update(&data.basej);

	/*
	 * Update @tmc->wakeup only at the end and do not reset @tmc->wakeup to
	 * KTIME_MAX. Even if tmc->lock is not held during the whole remote
	 * handling, tmc->wakeup is fine to be stale as it is called in
	 * interrupt context and tick_nohz_next_event() is executed in interrupt
	 * exit path only after processing the last pending interrupt.
	 */

	__walk_groups(&tmigr_handle_remote_up, &data, tmc);

	raw_spin_lock_irq(&tmc->lock);
	WRITE_ONCE(tmc->wakeup, data.firstexp);
	raw_spin_unlock_irq(&tmc->lock);
}

static bool tmigr_requires_handle_remote_up(struct tmigr_group *group,
					    struct tmigr_group *child,
					    void *ptr)
{
	struct tmigr_remote_data *data = ptr;
	u8 childmask;

	childmask = data->childmask;

	/*
	 * Handle the group only if the child is the migrator or if the group
	 * has no migrator. Otherwise the group is active and is handled by its
	 * own migrator.
	 */
	if (!tmigr_check_migrator(group, childmask))
		return true;

	/*
	 * When there is a parent group and the CPU which triggered the
	 * hierarchy walk is not active, proceed the walk to reach the top level
	 * group before reading the next_expiry value.
	 */
	if (group->parent && !data->tmc_active)
		goto out;

	/*
	 * The lock is required on 32bit architectures to read the variable
	 * consistently with a concurrent writer. On 64bit the lock is not
	 * required because the read operation is not split and so it is always
	 * consistent.
	 */
	if (IS_ENABLED(CONFIG_64BIT)) {
		data->firstexp = READ_ONCE(group->next_expiry);
		if (data->now >= data->firstexp) {
			data->check = true;
			return true;
		}
	} else {
		raw_spin_lock(&group->lock);
		data->firstexp = group->next_expiry;
		if (data->now >= group->next_expiry) {
			data->check = true;
			raw_spin_unlock(&group->lock);
			return true;
		}
		raw_spin_unlock(&group->lock);
	}

out:
	/* Update of childmask for the next level */
	data->childmask = group->childmask;
	return false;
}

/**
 * tmigr_requires_handle_remote() - Check the need of remote timer handling
 *
 * Must be called with interrupts disabled.
 */
bool tmigr_requires_handle_remote(void)
{
	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
	struct tmigr_remote_data data;
	unsigned long jif;
	bool ret = false;

	if (tmigr_is_not_available(tmc))
		return ret;

	data.now = get_jiffies_update(&jif);
	data.childmask = tmc->childmask;
	data.firstexp = KTIME_MAX;
	data.tmc_active = !tmc->idle;
	data.check = false;

	/*
	 * If the CPU is active, walk the hierarchy to check whether a remote
	 * expiry is required.
	 *
	 * Check is done lockless as interrupts are disabled and @tmc->idle is
	 * set only by the local CPU.
	 */
	if (!tmc->idle) {
		__walk_groups(&tmigr_requires_handle_remote_up, &data, tmc);

		return data.check;
	}

	/*
	 * When the CPU is idle, compare @tmc->wakeup with @data.now. The lock
	 * is required on 32bit architectures to read the variable consistently
	 * with a concurrent writer. On 64bit the lock is not required because
	 * the read operation is not split and so it is always consistent.
	 */
	if (IS_ENABLED(CONFIG_64BIT)) {
		if (data.now >= READ_ONCE(tmc->wakeup))
			return true;
	} else {
		raw_spin_lock(&tmc->lock);
		if (data.now >= tmc->wakeup)
			ret = true;
		raw_spin_unlock(&tmc->lock);
	}

	return ret;
}

/**
 * tmigr_cpu_new_timer() - enqueue next global timer into hierarchy (idle tmc)
 * @nextexp:	Next expiry of global timer (or KTIME_MAX if not)
 *
 * The CPU is already deactivated in the timer migration
 * hierarchy. tick_nohz_get_sleep_length() calls tick_nohz_next_event()
 * and thereby the timer idle path is executed once more. @tmc->wakeup
 * holds the first timer, when the timer migration hierarchy is
 * completely idle.
 *
 * Returns the first timer that needs to be handled by this CPU or KTIME_MAX if
 * nothing needs to be done.
 */
u64 tmigr_cpu_new_timer(u64 nextexp)
{
	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
	u64 ret;

	if (tmigr_is_not_available(tmc))
		return nextexp;

	raw_spin_lock(&tmc->lock);

	ret = READ_ONCE(tmc->wakeup);
	if (nextexp != KTIME_MAX) {
		if (nextexp != tmc->cpuevt.nextevt.expires ||
		    tmc->cpuevt.ignore) {
			ret = tmigr_new_timer(tmc, nextexp);
		}
	}
	/*
	 * Make sure the reevaluation of timers in idle path will not miss an
	 * event.
	 */
	WRITE_ONCE(tmc->wakeup, ret);

	trace_tmigr_cpu_new_timer_idle(tmc, nextexp);
	raw_spin_unlock(&tmc->lock);
	return ret;
}

static bool tmigr_inactive_up(struct tmigr_group *group,
			      struct tmigr_group *child,
			      void *ptr)
{
	union tmigr_state curstate, newstate, childstate;
	struct tmigr_walk *data = ptr;
	bool walk_done;
	u8 childmask;

	childmask = data->childmask;
	childstate.state = 0;

	/*
	 * The memory barrier is paired with the cmpxchg() in tmigr_active_up()
	 * to make sure the updates of child and group states are ordered. The
	 * ordering is mandatory, as the group state change depends on the child
	 * state.
	 */
	curstate.state = atomic_read_acquire(&group->migr_state);

	for (;;) {
		if (child)
			childstate.state = atomic_read(&child->migr_state);

		newstate = curstate;
		walk_done = true;

		/* Reset active bit when the child is no longer active */
		if (!childstate.active)
			newstate.active &= ~childmask;

		if (newstate.migrator == childmask) {
			/*
			 * Find a new migrator for the group, because the child
			 * group is idle!
			 */
			if (!childstate.active) {
				unsigned long new_migr_bit, active = newstate.active;

				new_migr_bit = find_first_bit(&active, BIT_CNT);

				if (new_migr_bit != BIT_CNT) {
					newstate.migrator = BIT(new_migr_bit);
				} else {
					newstate.migrator = TMIGR_NONE;

					/* Changes need to be propagated */
					walk_done = false;
				}
			}
		}

		newstate.seq++;

		WARN_ON_ONCE((newstate.migrator != TMIGR_NONE) && !(newstate.active));

		if (atomic_try_cmpxchg(&group->migr_state, &curstate.state,
				       newstate.state))
			break;

		/*
		 * The memory barrier is paired with the cmpxchg() in
		 * tmigr_active_up() to make sure the updates of child and group
		 * states are ordered. It is required only when the above
		 * try_cmpxchg() fails.
		 */
		smp_mb__after_atomic();
	}

	data->remote = false;

	/* Event Handling */
	tmigr_update_events(group, child, data);

	if (group->parent && (walk_done == false))
		data->childmask = group->childmask;

	/*
	 * data->firstexp was set by tmigr_update_events() and contains the
	 * expiry of the first global event which needs to be handled. It
	 * differs from KTIME_MAX if:
	 * - group is the top level group and
	 * - group is idle (which means CPU was the last active CPU in the
	 *   hierarchy) and
	 * - there is a pending event in the hierarchy
	 */
	WARN_ON_ONCE(data->firstexp != KTIME_MAX && group->parent);

	trace_tmigr_group_set_cpu_inactive(group, newstate, childmask);

	return walk_done;
}

static u64 __tmigr_cpu_deactivate(struct tmigr_cpu *tmc, u64 nextexp)
{
	struct tmigr_walk data = { .nextexp = nextexp,
				   .firstexp = KTIME_MAX,
				   .evt = &tmc->cpuevt,
				   .childmask = tmc->childmask };

	/*
	 * If nextexp is KTIME_MAX, the CPU event will be ignored because the
	 * local timer expires before the global timer, no global timer is set
	 * or CPU goes offline.
	 */
	if (nextexp != KTIME_MAX)
		tmc->cpuevt.ignore = false;

	walk_groups(&tmigr_inactive_up, &data, tmc);
	return data.firstexp;
}

/**
 * tmigr_cpu_deactivate() - Put current CPU into inactive state
 * @nextexp:	The next global timer expiry of the current CPU
 *
 * Must be called with interrupts disabled.
 *
 * Return: the next event expiry of the current CPU or the next event expiry
 * from the hierarchy if this CPU is the top level migrator or the hierarchy is
 * completely idle.
 */
u64 tmigr_cpu_deactivate(u64 nextexp)
{
	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
	u64 ret;

	if (tmigr_is_not_available(tmc))
		return nextexp;

	raw_spin_lock(&tmc->lock);

	ret = __tmigr_cpu_deactivate(tmc, nextexp);

	tmc->idle = true;

	/*
	 * Make sure the reevaluation of timers in idle path will not miss an
	 * event.
	 */
	WRITE_ONCE(tmc->wakeup, ret);

	trace_tmigr_cpu_idle(tmc, nextexp);
	raw_spin_unlock(&tmc->lock);
	return ret;
}

/**
 * tmigr_quick_check() - Quick forecast of next tmigr event when CPU wants to
 *			 go idle
 * @nextevt:	The next global timer expiry of the current CPU
 *
 * Return:
 * * KTIME_MAX		- when it is probable that nothing has to be done (not
 *			  the only one in the level 0 group; and if it is the
 *			  only one in level 0 group, but there are more than a
 *			  single group active on the way to top level)
 * * nextevt		- when CPU is offline and has to handle timer on his own
 *			  or when on the way to top in every group only a single
 *			  child is active but @nextevt is before the lowest
 *			  next_expiry encountered while walking up to top level.
 * * next_expiry	- value of lowest expiry encountered while walking groups
 *			  if only a single child is active on each and @nextevt
 *			  is after this lowest expiry.
 */
u64 tmigr_quick_check(u64 nextevt)
{
	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
	struct tmigr_group *group = tmc->tmgroup;

	if (tmigr_is_not_available(tmc))
		return nextevt;

	if (WARN_ON_ONCE(tmc->idle))
		return nextevt;

	if (!tmigr_check_migrator_and_lonely(tmc->tmgroup, tmc->childmask))
		return KTIME_MAX;

	do {
		if (!tmigr_check_lonely(group)) {
			return KTIME_MAX;
		} else {
			/*
			 * Since current CPU is active, events may not be sorted
			 * from bottom to the top because the CPU's event is ignored
			 * up to the top and its sibling's events not propagated upwards.
			 * Thus keep track of the lowest observed expiry.
			 */
			nextevt = min_t(u64, nextevt, READ_ONCE(group->next_expiry));
			if (!group->parent)
				return nextevt;
		}
		group = group->parent;
	} while (group);

	return KTIME_MAX;
}

static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl,
			     int node)
{
	union tmigr_state s;

	raw_spin_lock_init(&group->lock);

	group->level = lvl;
	group->numa_node = lvl < tmigr_crossnode_level ? node : NUMA_NO_NODE;

	group->num_children = 0;

	s.migrator = TMIGR_NONE;
	s.active = 0;
	s.seq = 0;
	atomic_set(&group->migr_state, s.state);

	timerqueue_init_head(&group->events);
	timerqueue_init(&group->groupevt.nextevt);
	group->groupevt.nextevt.expires = KTIME_MAX;
	WRITE_ONCE(group->next_expiry, KTIME_MAX);
	group->groupevt.ignore = true;
}

static struct tmigr_group *tmigr_get_group(unsigned int cpu, int node,
					   unsigned int lvl)
{
	struct tmigr_group *tmp, *group = NULL;

	lockdep_assert_held(&tmigr_mutex);

	/* Try to attach to an existing group first */
	list_for_each_entry(tmp, &tmigr_level_list[lvl], list) {
		/*
		 * If @lvl is below the cross NUMA node level, check whether
		 * this group belongs to the same NUMA node.
		 */
		if (lvl < tmigr_crossnode_level && tmp->numa_node != node)
			continue;

		/* Capacity left? */
		if (tmp->num_children >= TMIGR_CHILDREN_PER_GROUP)
			continue;

		/*
		 * TODO: A possible further improvement: Make sure that all CPU
		 * siblings end up in the same group of the lowest level of the
		 * hierarchy. Rely on the topology sibling mask would be a
		 * reasonable solution.
		 */

		group = tmp;
		break;
	}

	if (group)
		return group;

	/* Allocate and	set up a new group */
	group = kzalloc_node(sizeof(*group), GFP_KERNEL, node);
	if (!group)
		return ERR_PTR(-ENOMEM);

	tmigr_init_group(group, lvl, node);

	/* Setup successful. Add it to the hierarchy */
	list_add(&group->list, &tmigr_level_list[lvl]);
	trace_tmigr_group_set(group);
	return group;
}

static void tmigr_connect_child_parent(struct tmigr_group *child,
				       struct tmigr_group *parent)
{
	union tmigr_state childstate;

	raw_spin_lock_irq(&child->lock);
	raw_spin_lock_nested(&parent->lock, SINGLE_DEPTH_NESTING);

	child->parent = parent;
	child->childmask = BIT(parent->num_children++);

	raw_spin_unlock(&parent->lock);
	raw_spin_unlock_irq(&child->lock);

	trace_tmigr_connect_child_parent(child);

	/*
	 * To prevent inconsistent states, active children need to be active in
	 * the new parent as well. Inactive children are already marked inactive
	 * in the parent group:
	 *
	 * * When new groups were created by tmigr_setup_groups() starting from
	 *   the lowest level (and not higher then one level below the current
	 *   top level), then they are not active. They will be set active when
	 *   the new online CPU comes active.
	 *
	 * * But if a new group above the current top level is required, it is
	 *   mandatory to propagate the active state of the already existing
	 *   child to the new parent. So tmigr_connect_child_parent() is
	 *   executed with the formerly top level group (child) and the newly
	 *   created group (parent).
	 */
	childstate.state = atomic_read(&child->migr_state);
	if (childstate.migrator != TMIGR_NONE) {
		struct tmigr_walk data;

		data.childmask = child->childmask;

		/*
		 * There is only one new level per time. When connecting the
		 * child and the parent and set the child active when the parent
		 * is inactive, the parent needs to be the uppermost
		 * level. Otherwise there went something wrong!
		 */
		WARN_ON(!tmigr_active_up(parent, child, &data) && parent->parent);
	}
}

static int tmigr_setup_groups(unsigned int cpu, unsigned int node)
{
	struct tmigr_group *group, *child, **stack;
	int top = 0, err = 0, i = 0;
	struct list_head *lvllist;

	stack = kcalloc(tmigr_hierarchy_levels, sizeof(*stack), GFP_KERNEL);
	if (!stack)
		return -ENOMEM;

	do {
		group = tmigr_get_group(cpu, node, i);
		if (IS_ERR(group)) {
			err = PTR_ERR(group);
			break;
		}

		top = i;
		stack[i++] = group;

		/*
		 * When booting only less CPUs of a system than CPUs are
		 * available, not all calculated hierarchy levels are required.
		 *
		 * The loop is aborted as soon as the highest level, which might
		 * be different from tmigr_hierarchy_levels, contains only a
		 * single group.
		 */
		if (group->parent || i == tmigr_hierarchy_levels ||
		    (list_empty(&tmigr_level_list[i]) &&
		     list_is_singular(&tmigr_level_list[i - 1])))
			break;

	} while (i < tmigr_hierarchy_levels);

	while (i > 0) {
		group = stack[--i];

		if (err < 0) {
			list_del(&group->list);
			kfree(group);
			continue;
		}

		WARN_ON_ONCE(i != group->level);

		/*
		 * Update tmc -> group / child -> group connection
		 */
		if (i == 0) {
			struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);

			raw_spin_lock_irq(&group->lock);

			tmc->tmgroup = group;
			tmc->childmask = BIT(group->num_children++);

			raw_spin_unlock_irq(&group->lock);

			trace_tmigr_connect_cpu_parent(tmc);

			/* There are no children that need to be connected */
			continue;
		} else {
			child = stack[i - 1];
			tmigr_connect_child_parent(child, group);
		}

		/* check if uppermost level was newly created */
		if (top != i)
			continue;

		WARN_ON_ONCE(top == 0);

		lvllist = &tmigr_level_list[top];
		if (group->num_children == 1 && list_is_singular(lvllist)) {
			lvllist = &tmigr_level_list[top - 1];
			list_for_each_entry(child, lvllist, list) {
				if (child->parent)
					continue;

				tmigr_connect_child_parent(child, group);
			}
		}
	}

	kfree(stack);

	return err;
}

static int tmigr_add_cpu(unsigned int cpu)
{
	int node = cpu_to_node(cpu);
	int ret;

	mutex_lock(&tmigr_mutex);
	ret = tmigr_setup_groups(cpu, node);
	mutex_unlock(&tmigr_mutex);

	return ret;
}

static int tmigr_cpu_online(unsigned int cpu)
{
	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
	int ret;

	/* First online attempt? Initialize CPU data */
	if (!tmc->tmgroup) {
		raw_spin_lock_init(&tmc->lock);

		ret = tmigr_add_cpu(cpu);
		if (ret < 0)
			return ret;

		if (tmc->childmask == 0)
			return -EINVAL;

		timerqueue_init(&tmc->cpuevt.nextevt);
		tmc->cpuevt.nextevt.expires = KTIME_MAX;
		tmc->cpuevt.ignore = true;
		tmc->cpuevt.cpu = cpu;

		tmc->remote = false;
		WRITE_ONCE(tmc->wakeup, KTIME_MAX);
	}
	raw_spin_lock_irq(&tmc->lock);
	trace_tmigr_cpu_online(tmc);
	tmc->idle = timer_base_is_idle();
	if (!tmc->idle)
		__tmigr_cpu_activate(tmc);
	tmc->online = true;
	raw_spin_unlock_irq(&tmc->lock);
	return 0;
}

/*
 * tmigr_trigger_active() - trigger a CPU to become active again
 *
 * This function is executed on a CPU which is part of cpu_online_mask, when the
 * last active CPU in the hierarchy is offlining. With this, it is ensured that
 * the other CPU is active and takes over the migrator duty.
 */
static long tmigr_trigger_active(void *unused)
{
	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);

	WARN_ON_ONCE(!tmc->online || tmc->idle);

	return 0;
}

static int tmigr_cpu_offline(unsigned int cpu)
{
	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
	int migrator;
	u64 firstexp;

	raw_spin_lock_irq(&tmc->lock);
	tmc->online = false;
	WRITE_ONCE(tmc->wakeup, KTIME_MAX);

	/*
	 * CPU has to handle the local events on his own, when on the way to
	 * offline; Therefore nextevt value is set to KTIME_MAX
	 */
	firstexp = __tmigr_cpu_deactivate(tmc, KTIME_MAX);
	trace_tmigr_cpu_offline(tmc);
	raw_spin_unlock_irq(&tmc->lock);

	if (firstexp != KTIME_MAX) {
		migrator = cpumask_any_but(cpu_online_mask, cpu);
		work_on_cpu(migrator, tmigr_trigger_active, NULL);
	}

	return 0;
}

static int __init tmigr_init(void)
{
	unsigned int cpulvl, nodelvl, cpus_per_node, i;
	unsigned int nnodes = num_possible_nodes();
	unsigned int ncpus = num_possible_cpus();
	int ret = -ENOMEM;

	BUILD_BUG_ON_NOT_POWER_OF_2(TMIGR_CHILDREN_PER_GROUP);

	/* Nothing to do if running on UP */
	if (ncpus == 1)
		return 0;

	/*
	 * Calculate the required hierarchy levels. Unfortunately there is no
	 * reliable information available, unless all possible CPUs have been
	 * brought up and all NUMA nodes are populated.
	 *
	 * Estimate the number of levels with the number of possible nodes and
	 * the number of possible CPUs. Assume CPUs are spread evenly across
	 * nodes. We cannot rely on cpumask_of_node() because it only works for
	 * online CPUs.
	 */
	cpus_per_node = DIV_ROUND_UP(ncpus, nnodes);

	/* Calc the hierarchy levels required to hold the CPUs of a node */
	cpulvl = DIV_ROUND_UP(order_base_2(cpus_per_node),
			      ilog2(TMIGR_CHILDREN_PER_GROUP));

	/* Calculate the extra levels to connect all nodes */
	nodelvl = DIV_ROUND_UP(order_base_2(nnodes),
			       ilog2(TMIGR_CHILDREN_PER_GROUP));

	tmigr_hierarchy_levels = cpulvl + nodelvl;

	/*
	 * If a NUMA node spawns more than one CPU level group then the next
	 * level(s) of the hierarchy contains groups which handle all CPU groups
	 * of the same NUMA node. The level above goes across NUMA nodes. Store
	 * this information for the setup code to decide in which level node
	 * matching is no longer required.
	 */
	tmigr_crossnode_level = cpulvl;

	tmigr_level_list = kcalloc(tmigr_hierarchy_levels, sizeof(struct list_head), GFP_KERNEL);
	if (!tmigr_level_list)
		goto err;

	for (i = 0; i < tmigr_hierarchy_levels; i++)
		INIT_LIST_HEAD(&tmigr_level_list[i]);

	pr_info("Timer migration: %d hierarchy levels; %d children per group;"
		" %d crossnode level\n",
		tmigr_hierarchy_levels, TMIGR_CHILDREN_PER_GROUP,
		tmigr_crossnode_level);

	ret = cpuhp_setup_state(CPUHP_AP_TMIGR_ONLINE, "tmigr:online",
				tmigr_cpu_online, tmigr_cpu_offline);
	if (ret)
		goto err;

	return 0;

err:
	pr_err("Timer migration setup failed\n");
	return ret;
}
late_initcall(tmigr_init);