summaryrefslogtreecommitdiffstats
path: root/kernel/rcu/srcutree.c
blob: 929dcbc04d29ce8435ee40af97c1b67d68761319 (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
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
// SPDX-License-Identifier: GPL-2.0+
/*
 * Sleepable Read-Copy Update mechanism for mutual exclusion.
 *
 * Copyright (C) IBM Corporation, 2006
 * Copyright (C) Fujitsu, 2012
 *
 * Authors: Paul McKenney <paulmck@linux.ibm.com>
 *	   Lai Jiangshan <laijs@cn.fujitsu.com>
 *
 * For detailed explanation of Read-Copy Update mechanism see -
 *		Documentation/RCU/ *.txt
 *
 */

#define pr_fmt(fmt) "rcu: " fmt

#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
#include <linux/preempt.h>
#include <linux/rcupdate_wait.h>
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/srcu.h>

#include "rcu.h"
#include "rcu_segcblist.h"

/* Holdoff in nanoseconds for auto-expediting. */
#define DEFAULT_SRCU_EXP_HOLDOFF (25 * 1000)
static ulong exp_holdoff = DEFAULT_SRCU_EXP_HOLDOFF;
module_param(exp_holdoff, ulong, 0444);

/* Overflow-check frequency.  N bits roughly says every 2**N grace periods. */
static ulong counter_wrap_check = (ULONG_MAX >> 2);
module_param(counter_wrap_check, ulong, 0444);

/*
 * Control conversion to SRCU_SIZE_BIG:
 *    0: Don't convert at all.
 *    1: Convert at init_srcu_struct() time.
 *    2: Convert when rcutorture invokes srcu_torture_stats_print().
 *    3: Decide at boot time based on system shape (default).
 * 0x1x: Convert when excessive contention encountered.
 */
#define SRCU_SIZING_NONE	0
#define SRCU_SIZING_INIT	1
#define SRCU_SIZING_TORTURE	2
#define SRCU_SIZING_AUTO	3
#define SRCU_SIZING_CONTEND	0x10
#define SRCU_SIZING_IS(x) ((convert_to_big & ~SRCU_SIZING_CONTEND) == x)
#define SRCU_SIZING_IS_NONE() (SRCU_SIZING_IS(SRCU_SIZING_NONE))
#define SRCU_SIZING_IS_INIT() (SRCU_SIZING_IS(SRCU_SIZING_INIT))
#define SRCU_SIZING_IS_TORTURE() (SRCU_SIZING_IS(SRCU_SIZING_TORTURE))
#define SRCU_SIZING_IS_CONTEND() (convert_to_big & SRCU_SIZING_CONTEND)
static int convert_to_big = SRCU_SIZING_AUTO;
module_param(convert_to_big, int, 0444);

/* Number of CPUs to trigger init_srcu_struct()-time transition to big. */
static int big_cpu_lim __read_mostly = 128;
module_param(big_cpu_lim, int, 0444);

/* Contention events per jiffy to initiate transition to big. */
static int small_contention_lim __read_mostly = 100;
module_param(small_contention_lim, int, 0444);

/* Early-boot callback-management, so early that no lock is required! */
static LIST_HEAD(srcu_boot_list);
static bool __read_mostly srcu_init_done;

static void srcu_invoke_callbacks(struct work_struct *work);
static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay);
static void process_srcu(struct work_struct *work);
static void srcu_delay_timer(struct timer_list *t);

/* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */
#define spin_lock_rcu_node(p)							\
do {										\
	spin_lock(&ACCESS_PRIVATE(p, lock));					\
	smp_mb__after_unlock_lock();						\
} while (0)

#define spin_unlock_rcu_node(p) spin_unlock(&ACCESS_PRIVATE(p, lock))

#define spin_lock_irq_rcu_node(p)						\
do {										\
	spin_lock_irq(&ACCESS_PRIVATE(p, lock));				\
	smp_mb__after_unlock_lock();						\
} while (0)

#define spin_unlock_irq_rcu_node(p)						\
	spin_unlock_irq(&ACCESS_PRIVATE(p, lock))

#define spin_lock_irqsave_rcu_node(p, flags)					\
do {										\
	spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags);			\
	smp_mb__after_unlock_lock();						\
} while (0)

#define spin_trylock_irqsave_rcu_node(p, flags)					\
({										\
	bool ___locked = spin_trylock_irqsave(&ACCESS_PRIVATE(p, lock), flags);	\
										\
	if (___locked)								\
		smp_mb__after_unlock_lock();					\
	___locked;								\
})

#define spin_unlock_irqrestore_rcu_node(p, flags)				\
	spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags)			\

/*
 * Initialize SRCU per-CPU data.  Note that statically allocated
 * srcu_struct structures might already have srcu_read_lock() and
 * srcu_read_unlock() running against them.  So if the is_static parameter
 * is set, don't initialize ->srcu_lock_count[] and ->srcu_unlock_count[].
 */
static void init_srcu_struct_data(struct srcu_struct *ssp)
{
	int cpu;
	struct srcu_data *sdp;

	/*
	 * Initialize the per-CPU srcu_data array, which feeds into the
	 * leaves of the srcu_node tree.
	 */
	WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) !=
		     ARRAY_SIZE(sdp->srcu_unlock_count));
	for_each_possible_cpu(cpu) {
		sdp = per_cpu_ptr(ssp->sda, cpu);
		spin_lock_init(&ACCESS_PRIVATE(sdp, lock));
		rcu_segcblist_init(&sdp->srcu_cblist);
		sdp->srcu_cblist_invoking = false;
		sdp->srcu_gp_seq_needed = ssp->srcu_gp_seq;
		sdp->srcu_gp_seq_needed_exp = ssp->srcu_gp_seq;
		sdp->mynode = NULL;
		sdp->cpu = cpu;
		INIT_WORK(&sdp->work, srcu_invoke_callbacks);
		timer_setup(&sdp->delay_work, srcu_delay_timer, 0);
		sdp->ssp = ssp;
	}
}

/* Invalid seq state, used during snp node initialization */
#define SRCU_SNP_INIT_SEQ		0x2

/*
 * Check whether sequence number corresponding to snp node,
 * is invalid.
 */
static inline bool srcu_invl_snp_seq(unsigned long s)
{
	return rcu_seq_state(s) == SRCU_SNP_INIT_SEQ;
}

/*
 * Allocated and initialize SRCU combining tree.  Returns @true if
 * allocation succeeded and @false otherwise.
 */
static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
{
	int cpu;
	int i;
	int level = 0;
	int levelspread[RCU_NUM_LVLS];
	struct srcu_data *sdp;
	struct srcu_node *snp;
	struct srcu_node *snp_first;

	/* Initialize geometry if it has not already been initialized. */
	rcu_init_geometry();
	ssp->node = kcalloc(rcu_num_nodes, sizeof(*ssp->node), gfp_flags);
	if (!ssp->node)
		return false;

	/* Work out the overall tree geometry. */
	ssp->level[0] = &ssp->node[0];
	for (i = 1; i < rcu_num_lvls; i++)
		ssp->level[i] = ssp->level[i - 1] + num_rcu_lvl[i - 1];
	rcu_init_levelspread(levelspread, num_rcu_lvl);

	/* Each pass through this loop initializes one srcu_node structure. */
	srcu_for_each_node_breadth_first(ssp, snp) {
		spin_lock_init(&ACCESS_PRIVATE(snp, lock));
		WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) !=
			     ARRAY_SIZE(snp->srcu_data_have_cbs));
		for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) {
			snp->srcu_have_cbs[i] = SRCU_SNP_INIT_SEQ;
			snp->srcu_data_have_cbs[i] = 0;
		}
		snp->srcu_gp_seq_needed_exp = SRCU_SNP_INIT_SEQ;
		snp->grplo = -1;
		snp->grphi = -1;
		if (snp == &ssp->node[0]) {
			/* Root node, special case. */
			snp->srcu_parent = NULL;
			continue;
		}

		/* Non-root node. */
		if (snp == ssp->level[level + 1])
			level++;
		snp->srcu_parent = ssp->level[level - 1] +
				   (snp - ssp->level[level]) /
				   levelspread[level - 1];
	}

	/*
	 * Initialize the per-CPU srcu_data array, which feeds into the
	 * leaves of the srcu_node tree.
	 */
	level = rcu_num_lvls - 1;
	snp_first = ssp->level[level];
	for_each_possible_cpu(cpu) {
		sdp = per_cpu_ptr(ssp->sda, cpu);
		sdp->mynode = &snp_first[cpu / levelspread[level]];
		for (snp = sdp->mynode; snp != NULL; snp = snp->srcu_parent) {
			if (snp->grplo < 0)
				snp->grplo = cpu;
			snp->grphi = cpu;
		}
		sdp->grpmask = 1UL << (cpu - sdp->mynode->grplo);
	}
	smp_store_release(&ssp->srcu_size_state, SRCU_SIZE_WAIT_BARRIER);
	return true;
}

/*
 * Initialize non-compile-time initialized fields, including the
 * associated srcu_node and srcu_data structures.  The is_static parameter
 * tells us that ->sda has already been wired up to srcu_data.
 */
static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
{
	ssp->srcu_size_state = SRCU_SIZE_SMALL;
	ssp->node = NULL;
	mutex_init(&ssp->srcu_cb_mutex);
	mutex_init(&ssp->srcu_gp_mutex);
	ssp->srcu_idx = 0;
	ssp->srcu_gp_seq = 0;
	ssp->srcu_barrier_seq = 0;
	mutex_init(&ssp->srcu_barrier_mutex);
	atomic_set(&ssp->srcu_barrier_cpu_cnt, 0);
	INIT_DELAYED_WORK(&ssp->work, process_srcu);
	ssp->sda_is_static = is_static;
	if (!is_static)
		ssp->sda = alloc_percpu(struct srcu_data);
	if (!ssp->sda)
		return -ENOMEM;
	init_srcu_struct_data(ssp);
	ssp->srcu_gp_seq_needed_exp = 0;
	ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
	if (READ_ONCE(ssp->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) {
		if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC)) {
			if (!ssp->sda_is_static) {
				free_percpu(ssp->sda);
				ssp->sda = NULL;
				return -ENOMEM;
			}
		} else {
			WRITE_ONCE(ssp->srcu_size_state, SRCU_SIZE_BIG);
		}
	}
	smp_store_release(&ssp->srcu_gp_seq_needed, 0); /* Init done. */
	return 0;
}

#ifdef CONFIG_DEBUG_LOCK_ALLOC

int __init_srcu_struct(struct srcu_struct *ssp, const char *name,
		       struct lock_class_key *key)
{
	/* Don't re-initialize a lock while it is held. */
	debug_check_no_locks_freed((void *)ssp, sizeof(*ssp));
	lockdep_init_map(&ssp->dep_map, name, key, 0);
	spin_lock_init(&ACCESS_PRIVATE(ssp, lock));
	return init_srcu_struct_fields(ssp, false);
}
EXPORT_SYMBOL_GPL(__init_srcu_struct);

#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */

/**
 * init_srcu_struct - initialize a sleep-RCU structure
 * @ssp: structure to initialize.
 *
 * Must invoke this on a given srcu_struct before passing that srcu_struct
 * to any other function.  Each srcu_struct represents a separate domain
 * of SRCU protection.
 */
int init_srcu_struct(struct srcu_struct *ssp)
{
	spin_lock_init(&ACCESS_PRIVATE(ssp, lock));
	return init_srcu_struct_fields(ssp, false);
}
EXPORT_SYMBOL_GPL(init_srcu_struct);

#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */

/*
 * Initiate a transition to SRCU_SIZE_BIG with lock held.
 */
static void __srcu_transition_to_big(struct srcu_struct *ssp)
{
	lockdep_assert_held(&ACCESS_PRIVATE(ssp, lock));
	smp_store_release(&ssp->srcu_size_state, SRCU_SIZE_ALLOC);
}

/*
 * Initiate an idempotent transition to SRCU_SIZE_BIG.
 */
static void srcu_transition_to_big(struct srcu_struct *ssp)
{
	unsigned long flags;

	/* Double-checked locking on ->srcu_size-state. */
	if (smp_load_acquire(&ssp->srcu_size_state) != SRCU_SIZE_SMALL)
		return;
	spin_lock_irqsave_rcu_node(ssp, flags);
	if (smp_load_acquire(&ssp->srcu_size_state) != SRCU_SIZE_SMALL) {
		spin_unlock_irqrestore_rcu_node(ssp, flags);
		return;
	}
	__srcu_transition_to_big(ssp);
	spin_unlock_irqrestore_rcu_node(ssp, flags);
}

/*
 * Check to see if the just-encountered contention event justifies
 * a transition to SRCU_SIZE_BIG.
 */
static void spin_lock_irqsave_check_contention(struct srcu_struct *ssp)
{
	unsigned long j;

	if (!SRCU_SIZING_IS_CONTEND() || ssp->srcu_size_state)
		return;
	j = jiffies;
	if (ssp->srcu_size_jiffies != j) {
		ssp->srcu_size_jiffies = j;
		ssp->srcu_n_lock_retries = 0;
	}
	if (++ssp->srcu_n_lock_retries <= small_contention_lim)
		return;
	__srcu_transition_to_big(ssp);
}

/*
 * Acquire the specified srcu_data structure's ->lock, but check for
 * excessive contention, which results in initiation of a transition
 * to SRCU_SIZE_BIG.  But only if the srcutree.convert_to_big module
 * parameter permits this.
 */
static void spin_lock_irqsave_sdp_contention(struct srcu_data *sdp, unsigned long *flags)
{
	struct srcu_struct *ssp = sdp->ssp;

	if (spin_trylock_irqsave_rcu_node(sdp, *flags))
		return;
	spin_lock_irqsave_rcu_node(ssp, *flags);
	spin_lock_irqsave_check_contention(ssp);
	spin_unlock_irqrestore_rcu_node(ssp, *flags);
	spin_lock_irqsave_rcu_node(sdp, *flags);
}

/*
 * Acquire the specified srcu_struct structure's ->lock, but check for
 * excessive contention, which results in initiation of a transition
 * to SRCU_SIZE_BIG.  But only if the srcutree.convert_to_big module
 * parameter permits this.
 */
static void spin_lock_irqsave_ssp_contention(struct srcu_struct *ssp, unsigned long *flags)
{
	if (spin_trylock_irqsave_rcu_node(ssp, *flags))
		return;
	spin_lock_irqsave_rcu_node(ssp, *flags);
	spin_lock_irqsave_check_contention(ssp);
}

/*
 * First-use initialization of statically allocated srcu_struct
 * structure.  Wiring up the combining tree is more than can be
 * done with compile-time initialization, so this check is added
 * to each update-side SRCU primitive.  Use ssp->lock, which -is-
 * compile-time initialized, to resolve races involving multiple
 * CPUs trying to garner first-use privileges.
 */
static void check_init_srcu_struct(struct srcu_struct *ssp)
{
	unsigned long flags;

	/* The smp_load_acquire() pairs with the smp_store_release(). */
	if (!rcu_seq_state(smp_load_acquire(&ssp->srcu_gp_seq_needed))) /*^^^*/
		return; /* Already initialized. */
	spin_lock_irqsave_rcu_node(ssp, flags);
	if (!rcu_seq_state(ssp->srcu_gp_seq_needed)) {
		spin_unlock_irqrestore_rcu_node(ssp, flags);
		return;
	}
	init_srcu_struct_fields(ssp, true);
	spin_unlock_irqrestore_rcu_node(ssp, flags);
}

/*
 * Returns approximate total of the readers' ->srcu_lock_count[] values
 * for the rank of per-CPU counters specified by idx.
 */
static unsigned long srcu_readers_lock_idx(struct srcu_struct *ssp, int idx)
{
	int cpu;
	unsigned long sum = 0;

	for_each_possible_cpu(cpu) {
		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);

		sum += READ_ONCE(cpuc->srcu_lock_count[idx]);
	}
	return sum;
}

/*
 * Returns approximate total of the readers' ->srcu_unlock_count[] values
 * for the rank of per-CPU counters specified by idx.
 */
static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx)
{
	int cpu;
	unsigned long sum = 0;

	for_each_possible_cpu(cpu) {
		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);

		sum += READ_ONCE(cpuc->srcu_unlock_count[idx]);
	}
	return sum;
}

/*
 * Return true if the number of pre-existing readers is determined to
 * be zero.
 */
static bool srcu_readers_active_idx_check(struct srcu_struct *ssp, int idx)
{
	unsigned long unlocks;

	unlocks = srcu_readers_unlock_idx(ssp, idx);

	/*
	 * Make sure that a lock is always counted if the corresponding
	 * unlock is counted. Needs to be a smp_mb() as the read side may
	 * contain a read from a variable that is written to before the
	 * synchronize_srcu() in the write side. In this case smp_mb()s
	 * A and B act like the store buffering pattern.
	 *
	 * This smp_mb() also pairs with smp_mb() C to prevent accesses
	 * after the synchronize_srcu() from being executed before the
	 * grace period ends.
	 */
	smp_mb(); /* A */

	/*
	 * If the locks are the same as the unlocks, then there must have
	 * been no readers on this index at some time in between. This does
	 * not mean that there are no more readers, as one could have read
	 * the current index but not have incremented the lock counter yet.
	 *
	 * So suppose that the updater is preempted here for so long
	 * that more than ULONG_MAX non-nested readers come and go in
	 * the meantime.  It turns out that this cannot result in overflow
	 * because if a reader modifies its unlock count after we read it
	 * above, then that reader's next load of ->srcu_idx is guaranteed
	 * to get the new value, which will cause it to operate on the
	 * other bank of counters, where it cannot contribute to the
	 * overflow of these counters.  This means that there is a maximum
	 * of 2*NR_CPUS increments, which cannot overflow given current
	 * systems, especially not on 64-bit systems.
	 *
	 * OK, how about nesting?  This does impose a limit on nesting
	 * of floor(ULONG_MAX/NR_CPUS/2), which should be sufficient,
	 * especially on 64-bit systems.
	 */
	return srcu_readers_lock_idx(ssp, idx) == unlocks;
}

/**
 * srcu_readers_active - returns true if there are readers. and false
 *                       otherwise
 * @ssp: which srcu_struct to count active readers (holding srcu_read_lock).
 *
 * Note that this is not an atomic primitive, and can therefore suffer
 * severe errors when invoked on an active srcu_struct.  That said, it
 * can be useful as an error check at cleanup time.
 */
static bool srcu_readers_active(struct srcu_struct *ssp)
{
	int cpu;
	unsigned long sum = 0;

	for_each_possible_cpu(cpu) {
		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);

		sum += READ_ONCE(cpuc->srcu_lock_count[0]);
		sum += READ_ONCE(cpuc->srcu_lock_count[1]);
		sum -= READ_ONCE(cpuc->srcu_unlock_count[0]);
		sum -= READ_ONCE(cpuc->srcu_unlock_count[1]);
	}
	return sum;
}

/*
 * We use an adaptive strategy for synchronize_srcu() and especially for
 * synchronize_srcu_expedited().  We spin for a fixed time period
 * (defined below, boot time configurable) to allow SRCU readers to exit
 * their read-side critical sections.  If there are still some readers
 * after one jiffy, we repeatedly block for one jiffy time periods.
 * The blocking time is increased as the grace-period age increases,
 * with max blocking time capped at 10 jiffies.
 */
#define SRCU_DEFAULT_RETRY_CHECK_DELAY		5

static ulong srcu_retry_check_delay = SRCU_DEFAULT_RETRY_CHECK_DELAY;
module_param(srcu_retry_check_delay, ulong, 0444);

#define SRCU_INTERVAL		1		// Base delay if no expedited GPs pending.
#define SRCU_MAX_INTERVAL	10		// Maximum incremental delay from slow readers.

#define SRCU_DEFAULT_MAX_NODELAY_PHASE_LO	3UL	// Lowmark on default per-GP-phase
							// no-delay instances.
#define SRCU_DEFAULT_MAX_NODELAY_PHASE_HI	1000UL	// Highmark on default per-GP-phase
							// no-delay instances.

#define SRCU_UL_CLAMP_LO(val, low)	((val) > (low) ? (val) : (low))
#define SRCU_UL_CLAMP_HI(val, high)	((val) < (high) ? (val) : (high))
#define SRCU_UL_CLAMP(val, low, high)	SRCU_UL_CLAMP_HI(SRCU_UL_CLAMP_LO((val), (low)), (high))
// per-GP-phase no-delay instances adjusted to allow non-sleeping poll upto
// one jiffies time duration. Mult by 2 is done to factor in the srcu_get_delay()
// called from process_srcu().
#define SRCU_DEFAULT_MAX_NODELAY_PHASE_ADJUSTED	\
	(2UL * USEC_PER_SEC / HZ / SRCU_DEFAULT_RETRY_CHECK_DELAY)

// Maximum per-GP-phase consecutive no-delay instances.
#define SRCU_DEFAULT_MAX_NODELAY_PHASE	\
	SRCU_UL_CLAMP(SRCU_DEFAULT_MAX_NODELAY_PHASE_ADJUSTED,	\
		      SRCU_DEFAULT_MAX_NODELAY_PHASE_LO,	\
		      SRCU_DEFAULT_MAX_NODELAY_PHASE_HI)

static ulong srcu_max_nodelay_phase = SRCU_DEFAULT_MAX_NODELAY_PHASE;
module_param(srcu_max_nodelay_phase, ulong, 0444);

// Maximum consecutive no-delay instances.
#define SRCU_DEFAULT_MAX_NODELAY	(SRCU_DEFAULT_MAX_NODELAY_PHASE > 100 ?	\
					 SRCU_DEFAULT_MAX_NODELAY_PHASE : 100)

static ulong srcu_max_nodelay = SRCU_DEFAULT_MAX_NODELAY;
module_param(srcu_max_nodelay, ulong, 0444);

/*
 * Return grace-period delay, zero if there are expedited grace
 * periods pending, SRCU_INTERVAL otherwise.
 */
static unsigned long srcu_get_delay(struct srcu_struct *ssp)
{
	unsigned long gpstart;
	unsigned long j;
	unsigned long jbase = SRCU_INTERVAL;

	if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp)))
		jbase = 0;
	if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq))) {
		j = jiffies - 1;
		gpstart = READ_ONCE(ssp->srcu_gp_start);
		if (time_after(j, gpstart))
			jbase += j - gpstart;
		if (!jbase) {
			WRITE_ONCE(ssp->srcu_n_exp_nodelay, READ_ONCE(ssp->srcu_n_exp_nodelay) + 1);
			if (READ_ONCE(ssp->srcu_n_exp_nodelay) > srcu_max_nodelay_phase)
				jbase = 1;
		}
	}
	return jbase > SRCU_MAX_INTERVAL ? SRCU_MAX_INTERVAL : jbase;
}

/**
 * cleanup_srcu_struct - deconstruct a sleep-RCU structure
 * @ssp: structure to clean up.
 *
 * Must invoke this after you are finished using a given srcu_struct that
 * was initialized via init_srcu_struct(), else you leak memory.
 */
void cleanup_srcu_struct(struct srcu_struct *ssp)
{
	int cpu;

	if (WARN_ON(!srcu_get_delay(ssp)))
		return; /* Just leak it! */
	if (WARN_ON(srcu_readers_active(ssp)))
		return; /* Just leak it! */
	flush_delayed_work(&ssp->work);
	for_each_possible_cpu(cpu) {
		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);

		del_timer_sync(&sdp->delay_work);
		flush_work(&sdp->work);
		if (WARN_ON(rcu_segcblist_n_cbs(&sdp->srcu_cblist)))
			return; /* Forgot srcu_barrier(), so just leak it! */
	}
	if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
	    WARN_ON(rcu_seq_current(&ssp->srcu_gp_seq) != ssp->srcu_gp_seq_needed) ||
	    WARN_ON(srcu_readers_active(ssp))) {
		pr_info("%s: Active srcu_struct %p read state: %d gp state: %lu/%lu\n",
			__func__, ssp, rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)),
			rcu_seq_current(&ssp->srcu_gp_seq), ssp->srcu_gp_seq_needed);
		return; /* Caller forgot to stop doing call_srcu()? */
	}
	if (!ssp->sda_is_static) {
		free_percpu(ssp->sda);
		ssp->sda = NULL;
	}
	kfree(ssp->node);
	ssp->node = NULL;
	ssp->srcu_size_state = SRCU_SIZE_SMALL;
}
EXPORT_SYMBOL_GPL(cleanup_srcu_struct);

/*
 * Counts the new reader in the appropriate per-CPU element of the
 * srcu_struct.
 * Returns an index that must be passed to the matching srcu_read_unlock().
 */
int __srcu_read_lock(struct srcu_struct *ssp)
{
	int idx;

	idx = READ_ONCE(ssp->srcu_idx) & 0x1;
	this_cpu_inc(ssp->sda->srcu_lock_count[idx]);
	smp_mb(); /* B */  /* Avoid leaking the critical section. */
	return idx;
}
EXPORT_SYMBOL_GPL(__srcu_read_lock);

/*
 * Removes the count for the old reader from the appropriate per-CPU
 * element of the srcu_struct.  Note that this may well be a different
 * CPU than that which was incremented by the corresponding srcu_read_lock().
 */
void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
{
	smp_mb(); /* C */  /* Avoid leaking the critical section. */
	this_cpu_inc(ssp->sda->srcu_unlock_count[idx]);
}
EXPORT_SYMBOL_GPL(__srcu_read_unlock);

/*
 * Start an SRCU grace period.
 */
static void srcu_gp_start(struct srcu_struct *ssp)
{
	struct srcu_data *sdp;
	int state;

	if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER)
		sdp = per_cpu_ptr(ssp->sda, get_boot_cpu_id());
	else
		sdp = this_cpu_ptr(ssp->sda);
	lockdep_assert_held(&ACCESS_PRIVATE(ssp, lock));
	WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed));
	spin_lock_rcu_node(sdp);  /* Interrupts already disabled. */
	rcu_segcblist_advance(&sdp->srcu_cblist,
			      rcu_seq_current(&ssp->srcu_gp_seq));
	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
				       rcu_seq_snap(&ssp->srcu_gp_seq));
	spin_unlock_rcu_node(sdp);  /* Interrupts remain disabled. */
	WRITE_ONCE(ssp->srcu_gp_start, jiffies);
	WRITE_ONCE(ssp->srcu_n_exp_nodelay, 0);
	smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */
	rcu_seq_start(&ssp->srcu_gp_seq);
	state = rcu_seq_state(ssp->srcu_gp_seq);
	WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
}


static void srcu_delay_timer(struct timer_list *t)
{
	struct srcu_data *sdp = container_of(t, struct srcu_data, delay_work);

	queue_work_on(sdp->cpu, rcu_gp_wq, &sdp->work);
}

static void srcu_queue_delayed_work_on(struct srcu_data *sdp,
				       unsigned long delay)
{
	if (!delay) {
		queue_work_on(sdp->cpu, rcu_gp_wq, &sdp->work);
		return;
	}

	timer_reduce(&sdp->delay_work, jiffies + delay);
}

/*
 * Schedule callback invocation for the specified srcu_data structure,
 * if possible, on the corresponding CPU.
 */
static void srcu_schedule_cbs_sdp(struct srcu_data *sdp, unsigned long delay)
{
	srcu_queue_delayed_work_on(sdp, delay);
}

/*
 * Schedule callback invocation for all srcu_data structures associated
 * with the specified srcu_node structure that have callbacks for the
 * just-completed grace period, the one corresponding to idx.  If possible,
 * schedule this invocation on the corresponding CPUs.
 */
static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp,
				  unsigned long mask, unsigned long delay)
{
	int cpu;

	for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
		if (!(mask & (1UL << (cpu - snp->grplo))))
			continue;
		srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, cpu), delay);
	}
}

/*
 * Note the end of an SRCU grace period.  Initiates callback invocation
 * and starts a new grace period if needed.
 *
 * The ->srcu_cb_mutex acquisition does not protect any data, but
 * instead prevents more than one grace period from starting while we
 * are initiating callback invocation.  This allows the ->srcu_have_cbs[]
 * array to have a finite number of elements.
 */
static void srcu_gp_end(struct srcu_struct *ssp)
{
	unsigned long cbdelay = 1;
	bool cbs;
	bool last_lvl;
	int cpu;
	unsigned long flags;
	unsigned long gpseq;
	int idx;
	unsigned long mask;
	struct srcu_data *sdp;
	unsigned long sgsne;
	struct srcu_node *snp;
	int ss_state;

	/* Prevent more than one additional grace period. */
	mutex_lock(&ssp->srcu_cb_mutex);

	/* End the current grace period. */
	spin_lock_irq_rcu_node(ssp);
	idx = rcu_seq_state(ssp->srcu_gp_seq);
	WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
	if (ULONG_CMP_LT(READ_ONCE(ssp->srcu_gp_seq), READ_ONCE(ssp->srcu_gp_seq_needed_exp)))
		cbdelay = 0;

	WRITE_ONCE(ssp->srcu_last_gp_end, ktime_get_mono_fast_ns());
	rcu_seq_end(&ssp->srcu_gp_seq);
	gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, gpseq))
		WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, gpseq);
	spin_unlock_irq_rcu_node(ssp);
	mutex_unlock(&ssp->srcu_gp_mutex);
	/* A new grace period can start at this point.  But only one. */

	/* Initiate callback invocation as needed. */
	ss_state = smp_load_acquire(&ssp->srcu_size_state);
	if (ss_state < SRCU_SIZE_WAIT_BARRIER) {
		srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, get_boot_cpu_id()),
					cbdelay);
	} else {
		idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs);
		srcu_for_each_node_breadth_first(ssp, snp) {
			spin_lock_irq_rcu_node(snp);
			cbs = false;
			last_lvl = snp >= ssp->level[rcu_num_lvls - 1];
			if (last_lvl)
				cbs = ss_state < SRCU_SIZE_BIG || snp->srcu_have_cbs[idx] == gpseq;
			snp->srcu_have_cbs[idx] = gpseq;
			rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1);
			sgsne = snp->srcu_gp_seq_needed_exp;
			if (srcu_invl_snp_seq(sgsne) || ULONG_CMP_LT(sgsne, gpseq))
				WRITE_ONCE(snp->srcu_gp_seq_needed_exp, gpseq);
			if (ss_state < SRCU_SIZE_BIG)
				mask = ~0;
			else
				mask = snp->srcu_data_have_cbs[idx];
			snp->srcu_data_have_cbs[idx] = 0;
			spin_unlock_irq_rcu_node(snp);
			if (cbs)
				srcu_schedule_cbs_snp(ssp, snp, mask, cbdelay);
		}
	}

	/* Occasionally prevent srcu_data counter wrap. */
	if (!(gpseq & counter_wrap_check))
		for_each_possible_cpu(cpu) {
			sdp = per_cpu_ptr(ssp->sda, cpu);
			spin_lock_irqsave_rcu_node(sdp, flags);
			if (ULONG_CMP_GE(gpseq, sdp->srcu_gp_seq_needed + 100))
				sdp->srcu_gp_seq_needed = gpseq;
			if (ULONG_CMP_GE(gpseq, sdp->srcu_gp_seq_needed_exp + 100))
				sdp->srcu_gp_seq_needed_exp = gpseq;
			spin_unlock_irqrestore_rcu_node(sdp, flags);
		}

	/* Callback initiation done, allow grace periods after next. */
	mutex_unlock(&ssp->srcu_cb_mutex);

	/* Start a new grace period if needed. */
	spin_lock_irq_rcu_node(ssp);
	gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
	if (!rcu_seq_state(gpseq) &&
	    ULONG_CMP_LT(gpseq, ssp->srcu_gp_seq_needed)) {
		srcu_gp_start(ssp);
		spin_unlock_irq_rcu_node(ssp);
		srcu_reschedule(ssp, 0);
	} else {
		spin_unlock_irq_rcu_node(ssp);
	}

	/* Transition to big if needed. */
	if (ss_state != SRCU_SIZE_SMALL && ss_state != SRCU_SIZE_BIG) {
		if (ss_state == SRCU_SIZE_ALLOC)
			init_srcu_struct_nodes(ssp, GFP_KERNEL);
		else
			smp_store_release(&ssp->srcu_size_state, ss_state + 1);
	}
}

/*
 * Funnel-locking scheme to scalably mediate many concurrent expedited
 * grace-period requests.  This function is invoked for the first known
 * expedited request for a grace period that has already been requested,
 * but without expediting.  To start a completely new grace period,
 * whether expedited or not, use srcu_funnel_gp_start() instead.
 */
static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp,
				  unsigned long s)
{
	unsigned long flags;
	unsigned long sgsne;

	if (snp)
		for (; snp != NULL; snp = snp->srcu_parent) {
			sgsne = READ_ONCE(snp->srcu_gp_seq_needed_exp);
			if (rcu_seq_done(&ssp->srcu_gp_seq, s) ||
			    (!srcu_invl_snp_seq(sgsne) && ULONG_CMP_GE(sgsne, s)))
				return;
			spin_lock_irqsave_rcu_node(snp, flags);
			sgsne = snp->srcu_gp_seq_needed_exp;
			if (!srcu_invl_snp_seq(sgsne) && ULONG_CMP_GE(sgsne, s)) {
				spin_unlock_irqrestore_rcu_node(snp, flags);
				return;
			}
			WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
			spin_unlock_irqrestore_rcu_node(snp, flags);
		}
	spin_lock_irqsave_ssp_contention(ssp, &flags);
	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
		WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s);
	spin_unlock_irqrestore_rcu_node(ssp, flags);
}

/*
 * Funnel-locking scheme to scalably mediate many concurrent grace-period
 * requests.  The winner has to do the work of actually starting grace
 * period s.  Losers must either ensure that their desired grace-period
 * number is recorded on at least their leaf srcu_node structure, or they
 * must take steps to invoke their own callbacks.
 *
 * Note that this function also does the work of srcu_funnel_exp_start(),
 * in some cases by directly invoking it.
 */
static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
				 unsigned long s, bool do_norm)
{
	unsigned long flags;
	int idx = rcu_seq_ctr(s) % ARRAY_SIZE(sdp->mynode->srcu_have_cbs);
	unsigned long sgsne;
	struct srcu_node *snp;
	struct srcu_node *snp_leaf;
	unsigned long snp_seq;

	/* Ensure that snp node tree is fully initialized before traversing it */
	if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER)
		snp_leaf = NULL;
	else
		snp_leaf = sdp->mynode;

	if (snp_leaf)
		/* Each pass through the loop does one level of the srcu_node tree. */
		for (snp = snp_leaf; snp != NULL; snp = snp->srcu_parent) {
			if (rcu_seq_done(&ssp->srcu_gp_seq, s) && snp != snp_leaf)
				return; /* GP already done and CBs recorded. */
			spin_lock_irqsave_rcu_node(snp, flags);
			snp_seq = snp->srcu_have_cbs[idx];
			if (!srcu_invl_snp_seq(snp_seq) && ULONG_CMP_GE(snp_seq, s)) {
				if (snp == snp_leaf && snp_seq == s)
					snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
				spin_unlock_irqrestore_rcu_node(snp, flags);
				if (snp == snp_leaf && snp_seq != s) {
					srcu_schedule_cbs_sdp(sdp, do_norm ? SRCU_INTERVAL : 0);
					return;
				}
				if (!do_norm)
					srcu_funnel_exp_start(ssp, snp, s);
				return;
			}
			snp->srcu_have_cbs[idx] = s;
			if (snp == snp_leaf)
				snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
			sgsne = snp->srcu_gp_seq_needed_exp;
			if (!do_norm && (srcu_invl_snp_seq(sgsne) || ULONG_CMP_LT(sgsne, s)))
				WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
			spin_unlock_irqrestore_rcu_node(snp, flags);
		}

	/* Top of tree, must ensure the grace period will be started. */
	spin_lock_irqsave_ssp_contention(ssp, &flags);
	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed, s)) {
		/*
		 * Record need for grace period s.  Pair with load
		 * acquire setting up for initialization.
		 */
		smp_store_release(&ssp->srcu_gp_seq_needed, s); /*^^^*/
	}
	if (!do_norm && ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
		WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s);

	/* If grace period not already done and none in progress, start it. */
	if (!rcu_seq_done(&ssp->srcu_gp_seq, s) &&
	    rcu_seq_state(ssp->srcu_gp_seq) == SRCU_STATE_IDLE) {
		WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed));
		srcu_gp_start(ssp);

		// And how can that list_add() in the "else" clause
		// possibly be safe for concurrent execution?  Well,
		// it isn't.  And it does not have to be.  After all, it
		// can only be executed during early boot when there is only
		// the one boot CPU running with interrupts still disabled.
		if (likely(srcu_init_done))
			queue_delayed_work(rcu_gp_wq, &ssp->work,
					   !!srcu_get_delay(ssp));
		else if (list_empty(&ssp->work.work.entry))
			list_add(&ssp->work.work.entry, &srcu_boot_list);
	}
	spin_unlock_irqrestore_rcu_node(ssp, flags);
}

/*
 * Wait until all readers counted by array index idx complete, but
 * loop an additional time if there is an expedited grace period pending.
 * The caller must ensure that ->srcu_idx is not changed while checking.
 */
static bool try_check_zero(struct srcu_struct *ssp, int idx, int trycount)
{
	unsigned long curdelay;

	curdelay = !srcu_get_delay(ssp);

	for (;;) {
		if (srcu_readers_active_idx_check(ssp, idx))
			return true;
		if ((--trycount + curdelay) <= 0)
			return false;
		udelay(srcu_retry_check_delay);
	}
}

/*
 * Increment the ->srcu_idx counter so that future SRCU readers will
 * use the other rank of the ->srcu_(un)lock_count[] arrays.  This allows
 * us to wait for pre-existing readers in a starvation-free manner.
 */
static void srcu_flip(struct srcu_struct *ssp)
{
	/*
	 * Ensure that if this updater saw a given reader's increment
	 * from __srcu_read_lock(), that reader was using an old value
	 * of ->srcu_idx.  Also ensure that if a given reader sees the
	 * new value of ->srcu_idx, this updater's earlier scans cannot
	 * have seen that reader's increments (which is OK, because this
	 * grace period need not wait on that reader).
	 */
	smp_mb(); /* E */  /* Pairs with B and C. */

	WRITE_ONCE(ssp->srcu_idx, ssp->srcu_idx + 1);

	/*
	 * Ensure that if the updater misses an __srcu_read_unlock()
	 * increment, that task's next __srcu_read_lock() will see the
	 * above counter update.  Note that both this memory barrier
	 * and the one in srcu_readers_active_idx_check() provide the
	 * guarantee for __srcu_read_lock().
	 */
	smp_mb(); /* D */  /* Pairs with C. */
}

/*
 * If SRCU is likely idle, return true, otherwise return false.
 *
 * Note that it is OK for several current from-idle requests for a new
 * grace period from idle to specify expediting because they will all end
 * up requesting the same grace period anyhow.  So no loss.
 *
 * Note also that if any CPU (including the current one) is still invoking
 * callbacks, this function will nevertheless say "idle".  This is not
 * ideal, but the overhead of checking all CPUs' callback lists is even
 * less ideal, especially on large systems.  Furthermore, the wakeup
 * can happen before the callback is fully removed, so we have no choice
 * but to accept this type of error.
 *
 * This function is also subject to counter-wrap errors, but let's face
 * it, if this function was preempted for enough time for the counters
 * to wrap, it really doesn't matter whether or not we expedite the grace
 * period.  The extra overhead of a needlessly expedited grace period is
 * negligible when amortized over that time period, and the extra latency
 * of a needlessly non-expedited grace period is similarly negligible.
 */
static bool srcu_might_be_idle(struct srcu_struct *ssp)
{
	unsigned long curseq;
	unsigned long flags;
	struct srcu_data *sdp;
	unsigned long t;
	unsigned long tlast;

	check_init_srcu_struct(ssp);
	/* If the local srcu_data structure has callbacks, not idle.  */
	sdp = raw_cpu_ptr(ssp->sda);
	spin_lock_irqsave_rcu_node(sdp, flags);
	if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) {
		spin_unlock_irqrestore_rcu_node(sdp, flags);
		return false; /* Callbacks already present, so not idle. */
	}
	spin_unlock_irqrestore_rcu_node(sdp, flags);

	/*
	 * No local callbacks, so probabilistically probe global state.
	 * Exact information would require acquiring locks, which would
	 * kill scalability, hence the probabilistic nature of the probe.
	 */

	/* First, see if enough time has passed since the last GP. */
	t = ktime_get_mono_fast_ns();
	tlast = READ_ONCE(ssp->srcu_last_gp_end);
	if (exp_holdoff == 0 ||
	    time_in_range_open(t, tlast, tlast + exp_holdoff))
		return false; /* Too soon after last GP. */

	/* Next, check for probable idleness. */
	curseq = rcu_seq_current(&ssp->srcu_gp_seq);
	smp_mb(); /* Order ->srcu_gp_seq with ->srcu_gp_seq_needed. */
	if (ULONG_CMP_LT(curseq, READ_ONCE(ssp->srcu_gp_seq_needed)))
		return false; /* Grace period in progress, so not idle. */
	smp_mb(); /* Order ->srcu_gp_seq with prior access. */
	if (curseq != rcu_seq_current(&ssp->srcu_gp_seq))
		return false; /* GP # changed, so not idle. */
	return true; /* With reasonable probability, idle! */
}

/*
 * SRCU callback function to leak a callback.
 */
static void srcu_leak_callback(struct rcu_head *rhp)
{
}

/*
 * Start an SRCU grace period, and also queue the callback if non-NULL.
 */
static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
					     struct rcu_head *rhp, bool do_norm)
{
	unsigned long flags;
	int idx;
	bool needexp = false;
	bool needgp = false;
	unsigned long s;
	struct srcu_data *sdp;
	struct srcu_node *sdp_mynode;
	int ss_state;

	check_init_srcu_struct(ssp);
	idx = srcu_read_lock(ssp);
	ss_state = smp_load_acquire(&ssp->srcu_size_state);
	if (ss_state < SRCU_SIZE_WAIT_CALL)
		sdp = per_cpu_ptr(ssp->sda, get_boot_cpu_id());
	else
		sdp = raw_cpu_ptr(ssp->sda);
	spin_lock_irqsave_sdp_contention(sdp, &flags);
	if (rhp)
		rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
	/*
	 * The snapshot for acceleration must be taken _before_ the read of the
	 * current gp sequence used for advancing, otherwise advancing may fail
	 * and acceleration may then fail too.
	 *
	 * This could happen if:
	 *
	 *  1) The RCU_WAIT_TAIL segment has callbacks (gp_num = X + 4) and the
	 *     RCU_NEXT_READY_TAIL also has callbacks (gp_num = X + 8).
	 *
	 *  2) The grace period for RCU_WAIT_TAIL is seen as started but not
	 *     completed so rcu_seq_current() returns X + SRCU_STATE_SCAN1.
	 *
	 *  3) This value is passed to rcu_segcblist_advance() which can't move
	 *     any segment forward and fails.
	 *
	 *  4) srcu_gp_start_if_needed() still proceeds with callback acceleration.
	 *     But then the call to rcu_seq_snap() observes the grace period for the
	 *     RCU_WAIT_TAIL segment as completed and the subsequent one for the
	 *     RCU_NEXT_READY_TAIL segment as started (ie: X + 4 + SRCU_STATE_SCAN1)
	 *     so it returns a snapshot of the next grace period, which is X + 12.
	 *
	 *  5) The value of X + 12 is passed to rcu_segcblist_accelerate() but the
	 *     freshly enqueued callback in RCU_NEXT_TAIL can't move to
	 *     RCU_NEXT_READY_TAIL which already has callbacks for a previous grace
	 *     period (gp_num = X + 8). So acceleration fails.
	 */
	s = rcu_seq_snap(&ssp->srcu_gp_seq);
	rcu_segcblist_advance(&sdp->srcu_cblist,
			      rcu_seq_current(&ssp->srcu_gp_seq));
	WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s) && rhp);
	if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
		sdp->srcu_gp_seq_needed = s;
		needgp = true;
	}
	if (!do_norm && ULONG_CMP_LT(sdp->srcu_gp_seq_needed_exp, s)) {
		sdp->srcu_gp_seq_needed_exp = s;
		needexp = true;
	}
	spin_unlock_irqrestore_rcu_node(sdp, flags);

	/* Ensure that snp node tree is fully initialized before traversing it */
	if (ss_state < SRCU_SIZE_WAIT_BARRIER)
		sdp_mynode = NULL;
	else
		sdp_mynode = sdp->mynode;

	if (needgp)
		srcu_funnel_gp_start(ssp, sdp, s, do_norm);
	else if (needexp)
		srcu_funnel_exp_start(ssp, sdp_mynode, s);
	srcu_read_unlock(ssp, idx);
	return s;
}

/*
 * Enqueue an SRCU callback on the srcu_data structure associated with
 * the current CPU and the specified srcu_struct structure, initiating
 * grace-period processing if it is not already running.
 *
 * Note that all CPUs must agree that the grace period extended beyond
 * all pre-existing SRCU read-side critical section.  On systems with
 * more than one CPU, this means that when "func()" is invoked, each CPU
 * is guaranteed to have executed a full memory barrier since the end of
 * its last corresponding SRCU read-side critical section whose beginning
 * preceded the call to call_srcu().  It also means that each CPU executing
 * an SRCU read-side critical section that continues beyond the start of
 * "func()" must have executed a memory barrier after the call_srcu()
 * but before the beginning of that SRCU read-side critical section.
 * Note that these guarantees include CPUs that are offline, idle, or
 * executing in user mode, as well as CPUs that are executing in the kernel.
 *
 * Furthermore, if CPU A invoked call_srcu() and CPU B invoked the
 * resulting SRCU callback function "func()", then both CPU A and CPU
 * B are guaranteed to execute a full memory barrier during the time
 * interval between the call to call_srcu() and the invocation of "func()".
 * This guarantee applies even if CPU A and CPU B are the same CPU (but
 * again only if the system has more than one CPU).
 *
 * Of course, these guarantees apply only for invocations of call_srcu(),
 * srcu_read_lock(), and srcu_read_unlock() that are all passed the same
 * srcu_struct structure.
 */
static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
			rcu_callback_t func, bool do_norm)
{
	if (debug_rcu_head_queue(rhp)) {
		/* Probable double call_srcu(), so leak the callback. */
		WRITE_ONCE(rhp->func, srcu_leak_callback);
		WARN_ONCE(1, "call_srcu(): Leaked duplicate callback\n");
		return;
	}
	rhp->func = func;
	(void)srcu_gp_start_if_needed(ssp, rhp, do_norm);
}

/**
 * call_srcu() - Queue a callback for invocation after an SRCU grace period
 * @ssp: srcu_struct in queue the callback
 * @rhp: structure to be used for queueing the SRCU callback.
 * @func: function to be invoked after the SRCU grace period
 *
 * The callback function will be invoked some time after a full SRCU
 * grace period elapses, in other words after all pre-existing SRCU
 * read-side critical sections have completed.  However, the callback
 * function might well execute concurrently with other SRCU read-side
 * critical sections that started after call_srcu() was invoked.  SRCU
 * read-side critical sections are delimited by srcu_read_lock() and
 * srcu_read_unlock(), and may be nested.
 *
 * The callback will be invoked from process context, but must nevertheless
 * be fast and must not block.
 */
void call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
	       rcu_callback_t func)
{
	__call_srcu(ssp, rhp, func, true);
}
EXPORT_SYMBOL_GPL(call_srcu);

/*
 * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
 */
static void __synchronize_srcu(struct srcu_struct *ssp, bool do_norm)
{
	struct rcu_synchronize rcu;

	RCU_LOCKDEP_WARN(lockdep_is_held(ssp) ||
			 lock_is_held(&rcu_bh_lock_map) ||
			 lock_is_held(&rcu_lock_map) ||
			 lock_is_held(&rcu_sched_lock_map),
			 "Illegal synchronize_srcu() in same-type SRCU (or in RCU) read-side critical section");

	if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
		return;
	might_sleep();
	check_init_srcu_struct(ssp);
	init_completion(&rcu.completion);
	init_rcu_head_on_stack(&rcu.head);
	__call_srcu(ssp, &rcu.head, wakeme_after_rcu, do_norm);
	wait_for_completion(&rcu.completion);
	destroy_rcu_head_on_stack(&rcu.head);

	/*
	 * Make sure that later code is ordered after the SRCU grace
	 * period.  This pairs with the spin_lock_irq_rcu_node()
	 * in srcu_invoke_callbacks().  Unlike Tree RCU, this is needed
	 * because the current CPU might have been totally uninvolved with
	 * (and thus unordered against) that grace period.
	 */
	smp_mb();
}

/**
 * synchronize_srcu_expedited - Brute-force SRCU grace period
 * @ssp: srcu_struct with which to synchronize.
 *
 * Wait for an SRCU grace period to elapse, but be more aggressive about
 * spinning rather than blocking when waiting.
 *
 * Note that synchronize_srcu_expedited() has the same deadlock and
 * memory-ordering properties as does synchronize_srcu().
 */
void synchronize_srcu_expedited(struct srcu_struct *ssp)
{
	__synchronize_srcu(ssp, rcu_gp_is_normal());
}
EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);

/**
 * synchronize_srcu - wait for prior SRCU read-side critical-section completion
 * @ssp: srcu_struct with which to synchronize.
 *
 * Wait for the count to drain to zero of both indexes. To avoid the
 * possible starvation of synchronize_srcu(), it waits for the count of
 * the index=((->srcu_idx & 1) ^ 1) to drain to zero at first,
 * and then flip the srcu_idx and wait for the count of the other index.
 *
 * Can block; must be called from process context.
 *
 * Note that it is illegal to call synchronize_srcu() from the corresponding
 * SRCU read-side critical section; doing so will result in deadlock.
 * However, it is perfectly legal to call synchronize_srcu() on one
 * srcu_struct from some other srcu_struct's read-side critical section,
 * as long as the resulting graph of srcu_structs is acyclic.
 *
 * There are memory-ordering constraints implied by synchronize_srcu().
 * On systems with more than one CPU, when synchronize_srcu() returns,
 * each CPU is guaranteed to have executed a full memory barrier since
 * the end of its last corresponding SRCU read-side critical section
 * whose beginning preceded the call to synchronize_srcu().  In addition,
 * each CPU having an SRCU read-side critical section that extends beyond
 * the return from synchronize_srcu() is guaranteed to have executed a
 * full memory barrier after the beginning of synchronize_srcu() and before
 * the beginning of that SRCU read-side critical section.  Note that these
 * guarantees include CPUs that are offline, idle, or executing in user mode,
 * as well as CPUs that are executing in the kernel.
 *
 * Furthermore, if CPU A invoked synchronize_srcu(), which returned
 * to its caller on CPU B, then both CPU A and CPU B are guaranteed
 * to have executed a full memory barrier during the execution of
 * synchronize_srcu().  This guarantee applies even if CPU A and CPU B
 * are the same CPU, but again only if the system has more than one CPU.
 *
 * Of course, these memory-ordering guarantees apply only when
 * synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are
 * passed the same srcu_struct structure.
 *
 * Implementation of these memory-ordering guarantees is similar to
 * that of synchronize_rcu().
 *
 * If SRCU is likely idle, expedite the first request.  This semantic
 * was provided by Classic SRCU, and is relied upon by its users, so TREE
 * SRCU must also provide it.  Note that detecting idleness is heuristic
 * and subject to both false positives and negatives.
 */
void synchronize_srcu(struct srcu_struct *ssp)
{
	if (srcu_might_be_idle(ssp) || rcu_gp_is_expedited())
		synchronize_srcu_expedited(ssp);
	else
		__synchronize_srcu(ssp, true);
}
EXPORT_SYMBOL_GPL(synchronize_srcu);

/**
 * get_state_synchronize_srcu - Provide an end-of-grace-period cookie
 * @ssp: srcu_struct to provide cookie for.
 *
 * This function returns a cookie that can be passed to
 * poll_state_synchronize_srcu(), which will return true if a full grace
 * period has elapsed in the meantime.  It is the caller's responsibility
 * to make sure that grace period happens, for example, by invoking
 * call_srcu() after return from get_state_synchronize_srcu().
 */
unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp)
{
	// Any prior manipulation of SRCU-protected data must happen
	// before the load from ->srcu_gp_seq.
	smp_mb();
	return rcu_seq_snap(&ssp->srcu_gp_seq);
}
EXPORT_SYMBOL_GPL(get_state_synchronize_srcu);

/**
 * start_poll_synchronize_srcu - Provide cookie and start grace period
 * @ssp: srcu_struct to provide cookie for.
 *
 * This function returns a cookie that can be passed to
 * poll_state_synchronize_srcu(), which will return true if a full grace
 * period has elapsed in the meantime.  Unlike get_state_synchronize_srcu(),
 * this function also ensures that any needed SRCU grace period will be
 * started.  This convenience does come at a cost in terms of CPU overhead.
 */
unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp)
{
	return srcu_gp_start_if_needed(ssp, NULL, true);
}
EXPORT_SYMBOL_GPL(start_poll_synchronize_srcu);

/**
 * poll_state_synchronize_srcu - Has cookie's grace period ended?
 * @ssp: srcu_struct to provide cookie for.
 * @cookie: Return value from get_state_synchronize_srcu() or start_poll_synchronize_srcu().
 *
 * This function takes the cookie that was returned from either
 * get_state_synchronize_srcu() or start_poll_synchronize_srcu(), and
 * returns @true if an SRCU grace period elapsed since the time that the
 * cookie was created.
 *
 * Because cookies are finite in size, wrapping/overflow is possible.
 * This is more pronounced on 32-bit systems where cookies are 32 bits,
 * where in theory wrapping could happen in about 14 hours assuming
 * 25-microsecond expedited SRCU grace periods.  However, a more likely
 * overflow lower bound is on the order of 24 days in the case of
 * one-millisecond SRCU grace periods.  Of course, wrapping in a 64-bit
 * system requires geologic timespans, as in more than seven million years
 * even for expedited SRCU grace periods.
 *
 * Wrapping/overflow is much more of an issue for CONFIG_SMP=n systems
 * that also have CONFIG_PREEMPTION=n, which selects Tiny SRCU.  This uses
 * a 16-bit cookie, which rcutorture routinely wraps in a matter of a
 * few minutes.  If this proves to be a problem, this counter will be
 * expanded to the same size as for Tree SRCU.
 */
bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie)
{
	if (!rcu_seq_done(&ssp->srcu_gp_seq, cookie))
		return false;
	// Ensure that the end of the SRCU grace period happens before
	// any subsequent code that the caller might execute.
	smp_mb(); // ^^^
	return true;
}
EXPORT_SYMBOL_GPL(poll_state_synchronize_srcu);

/*
 * Callback function for srcu_barrier() use.
 */
static void srcu_barrier_cb(struct rcu_head *rhp)
{
	struct srcu_data *sdp;
	struct srcu_struct *ssp;

	sdp = container_of(rhp, struct srcu_data, srcu_barrier_head);
	ssp = sdp->ssp;
	if (atomic_dec_and_test(&ssp->srcu_barrier_cpu_cnt))
		complete(&ssp->srcu_barrier_completion);
}

/*
 * Enqueue an srcu_barrier() callback on the specified srcu_data
 * structure's ->cblist.  but only if that ->cblist already has at least one
 * callback enqueued.  Note that if a CPU already has callbacks enqueue,
 * it must have already registered the need for a future grace period,
 * so all we need do is enqueue a callback that will use the same grace
 * period as the last callback already in the queue.
 */
static void srcu_barrier_one_cpu(struct srcu_struct *ssp, struct srcu_data *sdp)
{
	spin_lock_irq_rcu_node(sdp);
	atomic_inc(&ssp->srcu_barrier_cpu_cnt);
	sdp->srcu_barrier_head.func = srcu_barrier_cb;
	debug_rcu_head_queue(&sdp->srcu_barrier_head);
	if (!rcu_segcblist_entrain(&sdp->srcu_cblist,
				   &sdp->srcu_barrier_head)) {
		debug_rcu_head_unqueue(&sdp->srcu_barrier_head);
		atomic_dec(&ssp->srcu_barrier_cpu_cnt);
	}
	spin_unlock_irq_rcu_node(sdp);
}

/**
 * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
 * @ssp: srcu_struct on which to wait for in-flight callbacks.
 */
void srcu_barrier(struct srcu_struct *ssp)
{
	int cpu;
	int idx;
	unsigned long s = rcu_seq_snap(&ssp->srcu_barrier_seq);

	check_init_srcu_struct(ssp);
	mutex_lock(&ssp->srcu_barrier_mutex);
	if (rcu_seq_done(&ssp->srcu_barrier_seq, s)) {
		smp_mb(); /* Force ordering following return. */
		mutex_unlock(&ssp->srcu_barrier_mutex);
		return; /* Someone else did our work for us. */
	}
	rcu_seq_start(&ssp->srcu_barrier_seq);
	init_completion(&ssp->srcu_barrier_completion);

	/* Initial count prevents reaching zero until all CBs are posted. */
	atomic_set(&ssp->srcu_barrier_cpu_cnt, 1);

	idx = srcu_read_lock(ssp);
	if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER)
		srcu_barrier_one_cpu(ssp, per_cpu_ptr(ssp->sda,	get_boot_cpu_id()));
	else
		for_each_possible_cpu(cpu)
			srcu_barrier_one_cpu(ssp, per_cpu_ptr(ssp->sda, cpu));
	srcu_read_unlock(ssp, idx);

	/* Remove the initial count, at which point reaching zero can happen. */
	if (atomic_dec_and_test(&ssp->srcu_barrier_cpu_cnt))
		complete(&ssp->srcu_barrier_completion);
	wait_for_completion(&ssp->srcu_barrier_completion);

	rcu_seq_end(&ssp->srcu_barrier_seq);
	mutex_unlock(&ssp->srcu_barrier_mutex);
}
EXPORT_SYMBOL_GPL(srcu_barrier);

/**
 * srcu_batches_completed - return batches completed.
 * @ssp: srcu_struct on which to report batch completion.
 *
 * Report the number of batches, correlated with, but not necessarily
 * precisely the same as, the number of grace periods that have elapsed.
 */
unsigned long srcu_batches_completed(struct srcu_struct *ssp)
{
	return READ_ONCE(ssp->srcu_idx);
}
EXPORT_SYMBOL_GPL(srcu_batches_completed);

/*
 * Core SRCU state machine.  Push state bits of ->srcu_gp_seq
 * to SRCU_STATE_SCAN2, and invoke srcu_gp_end() when scan has
 * completed in that state.
 */
static void srcu_advance_state(struct srcu_struct *ssp)
{
	int idx;

	mutex_lock(&ssp->srcu_gp_mutex);

	/*
	 * Because readers might be delayed for an extended period after
	 * fetching ->srcu_idx for their index, at any point in time there
	 * might well be readers using both idx=0 and idx=1.  We therefore
	 * need to wait for readers to clear from both index values before
	 * invoking a callback.
	 *
	 * The load-acquire ensures that we see the accesses performed
	 * by the prior grace period.
	 */
	idx = rcu_seq_state(smp_load_acquire(&ssp->srcu_gp_seq)); /* ^^^ */
	if (idx == SRCU_STATE_IDLE) {
		spin_lock_irq_rcu_node(ssp);
		if (ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)) {
			WARN_ON_ONCE(rcu_seq_state(ssp->srcu_gp_seq));
			spin_unlock_irq_rcu_node(ssp);
			mutex_unlock(&ssp->srcu_gp_mutex);
			return;
		}
		idx = rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq));
		if (idx == SRCU_STATE_IDLE)
			srcu_gp_start(ssp);
		spin_unlock_irq_rcu_node(ssp);
		if (idx != SRCU_STATE_IDLE) {
			mutex_unlock(&ssp->srcu_gp_mutex);
			return; /* Someone else started the grace period. */
		}
	}

	if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) == SRCU_STATE_SCAN1) {
		idx = 1 ^ (ssp->srcu_idx & 1);
		if (!try_check_zero(ssp, idx, 1)) {
			mutex_unlock(&ssp->srcu_gp_mutex);
			return; /* readers present, retry later. */
		}
		srcu_flip(ssp);
		spin_lock_irq_rcu_node(ssp);
		rcu_seq_set_state(&ssp->srcu_gp_seq, SRCU_STATE_SCAN2);
		ssp->srcu_n_exp_nodelay = 0;
		spin_unlock_irq_rcu_node(ssp);
	}

	if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) == SRCU_STATE_SCAN2) {

		/*
		 * SRCU read-side critical sections are normally short,
		 * so check at least twice in quick succession after a flip.
		 */
		idx = 1 ^ (ssp->srcu_idx & 1);
		if (!try_check_zero(ssp, idx, 2)) {
			mutex_unlock(&ssp->srcu_gp_mutex);
			return; /* readers present, retry later. */
		}
		ssp->srcu_n_exp_nodelay = 0;
		srcu_gp_end(ssp);  /* Releases ->srcu_gp_mutex. */
	}
}

/*
 * Invoke a limited number of SRCU callbacks that have passed through
 * their grace period.  If there are more to do, SRCU will reschedule
 * the workqueue.  Note that needed memory barriers have been executed
 * in this task's context by srcu_readers_active_idx_check().
 */
static void srcu_invoke_callbacks(struct work_struct *work)
{
	long len;
	bool more;
	struct rcu_cblist ready_cbs;
	struct rcu_head *rhp;
	struct srcu_data *sdp;
	struct srcu_struct *ssp;

	sdp = container_of(work, struct srcu_data, work);

	ssp = sdp->ssp;
	rcu_cblist_init(&ready_cbs);
	spin_lock_irq_rcu_node(sdp);
	rcu_segcblist_advance(&sdp->srcu_cblist,
			      rcu_seq_current(&ssp->srcu_gp_seq));
	if (sdp->srcu_cblist_invoking ||
	    !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
		spin_unlock_irq_rcu_node(sdp);
		return;  /* Someone else on the job or nothing to do. */
	}

	/* We are on the job!  Extract and invoke ready callbacks. */
	sdp->srcu_cblist_invoking = true;
	rcu_segcblist_extract_done_cbs(&sdp->srcu_cblist, &ready_cbs);
	len = ready_cbs.len;
	spin_unlock_irq_rcu_node(sdp);
	rhp = rcu_cblist_dequeue(&ready_cbs);
	for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
		debug_rcu_head_unqueue(rhp);
		local_bh_disable();
		rhp->func(rhp);
		local_bh_enable();
	}
	WARN_ON_ONCE(ready_cbs.len);

	/*
	 * Update counts, accelerate new callbacks, and if needed,
	 * schedule another round of callback invocation.
	 */
	spin_lock_irq_rcu_node(sdp);
	rcu_segcblist_add_len(&sdp->srcu_cblist, -len);
	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
				       rcu_seq_snap(&ssp->srcu_gp_seq));
	sdp->srcu_cblist_invoking = false;
	more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
	spin_unlock_irq_rcu_node(sdp);
	if (more)
		srcu_schedule_cbs_sdp(sdp, 0);
}

/*
 * Finished one round of SRCU grace period.  Start another if there are
 * more SRCU callbacks queued, otherwise put SRCU into not-running state.
 */
static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay)
{
	bool pushgp = true;

	spin_lock_irq_rcu_node(ssp);
	if (ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)) {
		if (!WARN_ON_ONCE(rcu_seq_state(ssp->srcu_gp_seq))) {
			/* All requests fulfilled, time to go idle. */
			pushgp = false;
		}
	} else if (!rcu_seq_state(ssp->srcu_gp_seq)) {
		/* Outstanding request and no GP.  Start one. */
		srcu_gp_start(ssp);
	}
	spin_unlock_irq_rcu_node(ssp);

	if (pushgp)
		queue_delayed_work(rcu_gp_wq, &ssp->work, delay);
}

/*
 * This is the work-queue function that handles SRCU grace periods.
 */
static void process_srcu(struct work_struct *work)
{
	unsigned long curdelay;
	unsigned long j;
	struct srcu_struct *ssp;

	ssp = container_of(work, struct srcu_struct, work.work);

	srcu_advance_state(ssp);
	curdelay = srcu_get_delay(ssp);
	if (curdelay) {
		WRITE_ONCE(ssp->reschedule_count, 0);
	} else {
		j = jiffies;
		if (READ_ONCE(ssp->reschedule_jiffies) == j) {
			WRITE_ONCE(ssp->reschedule_count, READ_ONCE(ssp->reschedule_count) + 1);
			if (READ_ONCE(ssp->reschedule_count) > srcu_max_nodelay)
				curdelay = 1;
		} else {
			WRITE_ONCE(ssp->reschedule_count, 1);
			WRITE_ONCE(ssp->reschedule_jiffies, j);
		}
	}
	srcu_reschedule(ssp, curdelay);
}

void srcutorture_get_gp_data(enum rcutorture_type test_type,
			     struct srcu_struct *ssp, int *flags,
			     unsigned long *gp_seq)
{
	if (test_type != SRCU_FLAVOR)
		return;
	*flags = 0;
	*gp_seq = rcu_seq_current(&ssp->srcu_gp_seq);
}
EXPORT_SYMBOL_GPL(srcutorture_get_gp_data);

static const char * const srcu_size_state_name[] = {
	"SRCU_SIZE_SMALL",
	"SRCU_SIZE_ALLOC",
	"SRCU_SIZE_WAIT_BARRIER",
	"SRCU_SIZE_WAIT_CALL",
	"SRCU_SIZE_WAIT_CBS1",
	"SRCU_SIZE_WAIT_CBS2",
	"SRCU_SIZE_WAIT_CBS3",
	"SRCU_SIZE_WAIT_CBS4",
	"SRCU_SIZE_BIG",
	"SRCU_SIZE_???",
};

void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf)
{
	int cpu;
	int idx;
	unsigned long s0 = 0, s1 = 0;
	int ss_state = READ_ONCE(ssp->srcu_size_state);
	int ss_state_idx = ss_state;

	idx = ssp->srcu_idx & 0x1;
	if (ss_state < 0 || ss_state >= ARRAY_SIZE(srcu_size_state_name))
		ss_state_idx = ARRAY_SIZE(srcu_size_state_name) - 1;
	pr_alert("%s%s Tree SRCU g%ld state %d (%s)",
		 tt, tf, rcu_seq_current(&ssp->srcu_gp_seq), ss_state,
		 srcu_size_state_name[ss_state_idx]);
	if (!ssp->sda) {
		// Called after cleanup_srcu_struct(), perhaps.
		pr_cont(" No per-CPU srcu_data structures (->sda == NULL).\n");
	} else {
		pr_cont(" per-CPU(idx=%d):", idx);
		for_each_possible_cpu(cpu) {
			unsigned long l0, l1;
			unsigned long u0, u1;
			long c0, c1;
			struct srcu_data *sdp;

			sdp = per_cpu_ptr(ssp->sda, cpu);
			u0 = data_race(sdp->srcu_unlock_count[!idx]);
			u1 = data_race(sdp->srcu_unlock_count[idx]);

			/*
			 * Make sure that a lock is always counted if the corresponding
			 * unlock is counted.
			 */
			smp_rmb();

			l0 = data_race(sdp->srcu_lock_count[!idx]);
			l1 = data_race(sdp->srcu_lock_count[idx]);

			c0 = l0 - u0;
			c1 = l1 - u1;
			pr_cont(" %d(%ld,%ld %c)",
				cpu, c0, c1,
				"C."[rcu_segcblist_empty(&sdp->srcu_cblist)]);
			s0 += c0;
			s1 += c1;
		}
		pr_cont(" T(%ld,%ld)\n", s0, s1);
	}
	if (SRCU_SIZING_IS_TORTURE())
		srcu_transition_to_big(ssp);
}
EXPORT_SYMBOL_GPL(srcu_torture_stats_print);

static int __init srcu_bootup_announce(void)
{
	pr_info("Hierarchical SRCU implementation.\n");
	if (exp_holdoff != DEFAULT_SRCU_EXP_HOLDOFF)
		pr_info("\tNon-default auto-expedite holdoff of %lu ns.\n", exp_holdoff);
	if (srcu_retry_check_delay != SRCU_DEFAULT_RETRY_CHECK_DELAY)
		pr_info("\tNon-default retry check delay of %lu us.\n", srcu_retry_check_delay);
	if (srcu_max_nodelay != SRCU_DEFAULT_MAX_NODELAY)
		pr_info("\tNon-default max no-delay of %lu.\n", srcu_max_nodelay);
	pr_info("\tMax phase no-delay instances is %lu.\n", srcu_max_nodelay_phase);
	return 0;
}
early_initcall(srcu_bootup_announce);

void __init srcu_init(void)
{
	struct srcu_struct *ssp;

	/* Decide on srcu_struct-size strategy. */
	if (SRCU_SIZING_IS(SRCU_SIZING_AUTO)) {
		if (nr_cpu_ids >= big_cpu_lim) {
			convert_to_big = SRCU_SIZING_INIT; // Don't bother waiting for contention.
			pr_info("%s: Setting srcu_struct sizes to big.\n", __func__);
		} else {
			convert_to_big = SRCU_SIZING_NONE | SRCU_SIZING_CONTEND;
			pr_info("%s: Setting srcu_struct sizes based on contention.\n", __func__);
		}
	}

	/*
	 * Once that is set, call_srcu() can follow the normal path and
	 * queue delayed work. This must follow RCU workqueues creation
	 * and timers initialization.
	 */
	srcu_init_done = true;
	while (!list_empty(&srcu_boot_list)) {
		ssp = list_first_entry(&srcu_boot_list, struct srcu_struct,
				      work.work.entry);
		list_del_init(&ssp->work.work.entry);
		if (SRCU_SIZING_IS(SRCU_SIZING_INIT) && ssp->srcu_size_state == SRCU_SIZE_SMALL)
			ssp->srcu_size_state = SRCU_SIZE_ALLOC;
		queue_work(rcu_gp_wq, &ssp->work.work);
	}
}

#ifdef CONFIG_MODULES

/* Initialize any global-scope srcu_struct structures used by this module. */
static int srcu_module_coming(struct module *mod)
{
	int i;
	struct srcu_struct **sspp = mod->srcu_struct_ptrs;
	int ret;

	for (i = 0; i < mod->num_srcu_structs; i++) {
		ret = init_srcu_struct(*(sspp++));
		if (WARN_ON_ONCE(ret))
			return ret;
	}
	return 0;
}

/* Clean up any global-scope srcu_struct structures used by this module. */
static void srcu_module_going(struct module *mod)
{
	int i;
	struct srcu_struct **sspp = mod->srcu_struct_ptrs;

	for (i = 0; i < mod->num_srcu_structs; i++)
		cleanup_srcu_struct(*(sspp++));
}

/* Handle one module, either coming or going. */
static int srcu_module_notify(struct notifier_block *self,
			      unsigned long val, void *data)
{
	struct module *mod = data;
	int ret = 0;

	switch (val) {
	case MODULE_STATE_COMING:
		ret = srcu_module_coming(mod);
		break;
	case MODULE_STATE_GOING:
		srcu_module_going(mod);
		break;
	default:
		break;
	}
	return ret;
}

static struct notifier_block srcu_module_nb = {
	.notifier_call = srcu_module_notify,
	.priority = 0,
};

static __init int init_srcu_module_notifier(void)
{
	int ret;

	ret = register_module_notifier(&srcu_module_nb);
	if (ret)
		pr_warn("Failed to register srcu module notifier\n");
	return ret;
}
late_initcall(init_srcu_module_notifier);

#endif /* #ifdef CONFIG_MODULES */