summaryrefslogtreecommitdiffstats
path: root/kernel/rcutree.c
blob: 068de3a93606980268351ccaf6b19fc45573b4ea (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
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
/*
 * Read-Copy Update mechanism for mutual exclusion
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 *
 * Copyright IBM Corporation, 2008
 *
 * Authors: Dipankar Sarma <dipankar@in.ibm.com>
 *	    Manfred Spraul <manfred@colorfullife.com>
 *	    Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical version
 *
 * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
 * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
 *
 * For detailed explanation of Read-Copy Update mechanism see -
 *	Documentation/RCU
 */
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/rcupdate.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <linux/nmi.h>
#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/export.h>
#include <linux/completion.h>
#include <linux/moduleparam.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/time.h>
#include <linux/kernel_stat.h>
#include <linux/wait.h>
#include <linux/kthread.h>
#include <linux/prefetch.h>
#include <linux/delay.h>
#include <linux/stop_machine.h>
#include <linux/random.h>

#include "rcutree.h"
#include <trace/events/rcu.h>

#include "rcu.h"

/* Data structures. */

static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];

#define RCU_STATE_INITIALIZER(sname, sabbr, cr) { \
	.level = { &sname##_state.node[0] }, \
	.call = cr, \
	.fqs_state = RCU_GP_IDLE, \
	.gpnum = 0UL - 300UL, \
	.completed = 0UL - 300UL, \
	.orphan_lock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.orphan_lock), \
	.orphan_nxttail = &sname##_state.orphan_nxtlist, \
	.orphan_donetail = &sname##_state.orphan_donelist, \
	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
	.onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \
	.name = #sname, \
	.abbr = sabbr, \
}

struct rcu_state rcu_sched_state =
	RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);

struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);

static struct rcu_state *rcu_state;
LIST_HEAD(rcu_struct_flavors);

/* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */
static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF;
module_param(rcu_fanout_leaf, int, 0444);
int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
static int num_rcu_lvl[] = {  /* Number of rcu_nodes at specified level. */
	NUM_RCU_LVL_0,
	NUM_RCU_LVL_1,
	NUM_RCU_LVL_2,
	NUM_RCU_LVL_3,
	NUM_RCU_LVL_4,
};
int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */

/*
 * The rcu_scheduler_active variable transitions from zero to one just
 * before the first task is spawned.  So when this variable is zero, RCU
 * can assume that there is but one task, allowing RCU to (for example)
 * optimize synchronize_sched() to a simple barrier().  When this variable
 * is one, RCU must actually do all the hard work required to detect real
 * grace periods.  This variable is also used to suppress boot-time false
 * positives from lockdep-RCU error checking.
 */
int rcu_scheduler_active __read_mostly;
EXPORT_SYMBOL_GPL(rcu_scheduler_active);

/*
 * The rcu_scheduler_fully_active variable transitions from zero to one
 * during the early_initcall() processing, which is after the scheduler
 * is capable of creating new tasks.  So RCU processing (for example,
 * creating tasks for RCU priority boosting) must be delayed until after
 * rcu_scheduler_fully_active transitions from zero to one.  We also
 * currently delay invocation of any RCU callbacks until after this point.
 *
 * It might later prove better for people registering RCU callbacks during
 * early boot to take responsibility for these callbacks, but one step at
 * a time.
 */
static int rcu_scheduler_fully_active __read_mostly;

#ifdef CONFIG_RCU_BOOST

/*
 * Control variables for per-CPU and per-rcu_node kthreads.  These
 * handle all flavors of RCU.
 */
static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
DEFINE_PER_CPU(char, rcu_cpu_has_work);

#endif /* #ifdef CONFIG_RCU_BOOST */

static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
static void invoke_rcu_core(void);
static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);

/*
 * Track the rcutorture test sequence number and the update version
 * number within a given test.  The rcutorture_testseq is incremented
 * on every rcutorture module load and unload, so has an odd value
 * when a test is running.  The rcutorture_vernum is set to zero
 * when rcutorture starts and is incremented on each rcutorture update.
 * These variables enable correlating rcutorture output with the
 * RCU tracing information.
 */
unsigned long rcutorture_testseq;
unsigned long rcutorture_vernum;

/*
 * Return true if an RCU grace period is in progress.  The ACCESS_ONCE()s
 * permit this function to be invoked without holding the root rcu_node
 * structure's ->lock, but of course results can be subject to change.
 */
static int rcu_gp_in_progress(struct rcu_state *rsp)
{
	return ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum);
}

/*
 * Note a quiescent state.  Because we do not need to know
 * how many quiescent states passed, just if there was at least
 * one since the start of the grace period, this just sets a flag.
 * The caller must have disabled preemption.
 */
void rcu_sched_qs(int cpu)
{
	struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu);

	if (rdp->passed_quiesce == 0)
		trace_rcu_grace_period("rcu_sched", rdp->gpnum, "cpuqs");
	rdp->passed_quiesce = 1;
}

void rcu_bh_qs(int cpu)
{
	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);

	if (rdp->passed_quiesce == 0)
		trace_rcu_grace_period("rcu_bh", rdp->gpnum, "cpuqs");
	rdp->passed_quiesce = 1;
}

/*
 * Note a context switch.  This is a quiescent state for RCU-sched,
 * and requires special handling for preemptible RCU.
 * The caller must have disabled preemption.
 */
void rcu_note_context_switch(int cpu)
{
	trace_rcu_utilization("Start context switch");
	rcu_sched_qs(cpu);
	rcu_preempt_note_context_switch(cpu);
	trace_rcu_utilization("End context switch");
}
EXPORT_SYMBOL_GPL(rcu_note_context_switch);

DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
	.dynticks = ATOMIC_INIT(1),
};

static long blimit = 10;	/* Maximum callbacks per rcu_do_batch. */
static long qhimark = 10000;	/* If this many pending, ignore blimit. */
static long qlowmark = 100;	/* Once only this many pending, use blimit. */

module_param(blimit, long, 0444);
module_param(qhimark, long, 0444);
module_param(qlowmark, long, 0444);

static ulong jiffies_till_first_fqs = ULONG_MAX;
static ulong jiffies_till_next_fqs = ULONG_MAX;

module_param(jiffies_till_first_fqs, ulong, 0644);
module_param(jiffies_till_next_fqs, ulong, 0644);

static void rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
				  struct rcu_data *rdp);
static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *));
static void force_quiescent_state(struct rcu_state *rsp);
static int rcu_pending(int cpu);

/*
 * Return the number of RCU-sched batches processed thus far for debug & stats.
 */
long rcu_batches_completed_sched(void)
{
	return rcu_sched_state.completed;
}
EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);

/*
 * Return the number of RCU BH batches processed thus far for debug & stats.
 */
long rcu_batches_completed_bh(void)
{
	return rcu_bh_state.completed;
}
EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);

/*
 * Force a quiescent state for RCU BH.
 */
void rcu_bh_force_quiescent_state(void)
{
	force_quiescent_state(&rcu_bh_state);
}
EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);

/*
 * Record the number of times rcutorture tests have been initiated and
 * terminated.  This information allows the debugfs tracing stats to be
 * correlated to the rcutorture messages, even when the rcutorture module
 * is being repeatedly loaded and unloaded.  In other words, we cannot
 * store this state in rcutorture itself.
 */
void rcutorture_record_test_transition(void)
{
	rcutorture_testseq++;
	rcutorture_vernum = 0;
}
EXPORT_SYMBOL_GPL(rcutorture_record_test_transition);

/*
 * Record the number of writer passes through the current rcutorture test.
 * This is also used to correlate debugfs tracing stats with the rcutorture
 * messages.
 */
void rcutorture_record_progress(unsigned long vernum)
{
	rcutorture_vernum++;
}
EXPORT_SYMBOL_GPL(rcutorture_record_progress);

/*
 * Force a quiescent state for RCU-sched.
 */
void rcu_sched_force_quiescent_state(void)
{
	force_quiescent_state(&rcu_sched_state);
}
EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state);

/*
 * Does the CPU have callbacks ready to be invoked?
 */
static int
cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
{
	return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL] &&
	       rdp->nxttail[RCU_DONE_TAIL] != NULL;
}

/*
 * Does the current CPU require a not-yet-started grace period?
 * The caller must have disabled interrupts to prevent races with
 * normal callback registry.
 */
static int
cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
{
	int i;

	if (rcu_gp_in_progress(rsp))
		return 0;  /* No, a grace period is already in progress. */
	if (rcu_nocb_needs_gp(rsp))
		return 1;  /* Yes, a no-CBs CPU needs one. */
	if (!rdp->nxttail[RCU_NEXT_TAIL])
		return 0;  /* No, this is a no-CBs (or offline) CPU. */
	if (*rdp->nxttail[RCU_NEXT_READY_TAIL])
		return 1;  /* Yes, this CPU has newly registered callbacks. */
	for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
		if (rdp->nxttail[i - 1] != rdp->nxttail[i] &&
		    ULONG_CMP_LT(ACCESS_ONCE(rsp->completed),
				 rdp->nxtcompleted[i]))
			return 1;  /* Yes, CBs for future grace period. */
	return 0; /* No grace period needed. */
}

/*
 * Return the root node of the specified rcu_state structure.
 */
static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
{
	return &rsp->node[0];
}

/*
 * rcu_eqs_enter_common - current CPU is moving towards extended quiescent state
 *
 * If the new value of the ->dynticks_nesting counter now is zero,
 * we really have entered idle, and must do the appropriate accounting.
 * The caller must have disabled interrupts.
 */
static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
				bool user)
{
	trace_rcu_dyntick("Start", oldval, rdtp->dynticks_nesting);
	if (!user && !is_idle_task(current)) {
		struct task_struct *idle = idle_task(smp_processor_id());

		trace_rcu_dyntick("Error on entry: not idle task", oldval, 0);
		ftrace_dump(DUMP_ORIG);
		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
			  current->pid, current->comm,
			  idle->pid, idle->comm); /* must be idle task! */
	}
	rcu_prepare_for_idle(smp_processor_id());
	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
	smp_mb__before_atomic_inc();  /* See above. */
	atomic_inc(&rdtp->dynticks);
	smp_mb__after_atomic_inc();  /* Force ordering with next sojourn. */
	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);

	/*
	 * It is illegal to enter an extended quiescent state while
	 * in an RCU read-side critical section.
	 */
	rcu_lockdep_assert(!lock_is_held(&rcu_lock_map),
			   "Illegal idle entry in RCU read-side critical section.");
	rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map),
			   "Illegal idle entry in RCU-bh read-side critical section.");
	rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map),
			   "Illegal idle entry in RCU-sched read-side critical section.");
}

/*
 * Enter an RCU extended quiescent state, which can be either the
 * idle loop or adaptive-tickless usermode execution.
 */
static void rcu_eqs_enter(bool user)
{
	long long oldval;
	struct rcu_dynticks *rdtp;

	rdtp = &__get_cpu_var(rcu_dynticks);
	oldval = rdtp->dynticks_nesting;
	WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
		rdtp->dynticks_nesting = 0;
	else
		rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
	rcu_eqs_enter_common(rdtp, oldval, user);
}

/**
 * rcu_idle_enter - inform RCU that current CPU is entering idle
 *
 * Enter idle mode, in other words, -leave- the mode in which RCU
 * read-side critical sections can occur.  (Though RCU read-side
 * critical sections can occur in irq handlers in idle, a possibility
 * handled by irq_enter() and irq_exit().)
 *
 * We crowbar the ->dynticks_nesting field to zero to allow for
 * the possibility of usermode upcalls having messed up our count
 * of interrupt nesting level during the prior busy period.
 */
void rcu_idle_enter(void)
{
	unsigned long flags;

	local_irq_save(flags);
	rcu_eqs_enter(false);
	local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(rcu_idle_enter);

#ifdef CONFIG_RCU_USER_QS
/**
 * rcu_user_enter - inform RCU that we are resuming userspace.
 *
 * Enter RCU idle mode right before resuming userspace.  No use of RCU
 * is permitted between this call and rcu_user_exit(). This way the
 * CPU doesn't need to maintain the tick for RCU maintenance purposes
 * when the CPU runs in userspace.
 */
void rcu_user_enter(void)
{
	rcu_eqs_enter(1);
}

/**
 * rcu_user_enter_after_irq - inform RCU that we are going to resume userspace
 * after the current irq returns.
 *
 * This is similar to rcu_user_enter() but in the context of a non-nesting
 * irq. After this call, RCU enters into idle mode when the interrupt
 * returns.
 */
void rcu_user_enter_after_irq(void)
{
	unsigned long flags;
	struct rcu_dynticks *rdtp;

	local_irq_save(flags);
	rdtp = &__get_cpu_var(rcu_dynticks);
	/* Ensure this irq is interrupting a non-idle RCU state.  */
	WARN_ON_ONCE(!(rdtp->dynticks_nesting & DYNTICK_TASK_MASK));
	rdtp->dynticks_nesting = 1;
	local_irq_restore(flags);
}
#endif /* CONFIG_RCU_USER_QS */

/**
 * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
 *
 * Exit from an interrupt handler, which might possibly result in entering
 * idle mode, in other words, leaving the mode in which read-side critical
 * sections can occur.
 *
 * This code assumes that the idle loop never does anything that might
 * result in unbalanced calls to irq_enter() and irq_exit().  If your
 * architecture violates this assumption, RCU will give you what you
 * deserve, good and hard.  But very infrequently and irreproducibly.
 *
 * Use things like work queues to work around this limitation.
 *
 * You have been warned.
 */
void rcu_irq_exit(void)
{
	unsigned long flags;
	long long oldval;
	struct rcu_dynticks *rdtp;

	local_irq_save(flags);
	rdtp = &__get_cpu_var(rcu_dynticks);
	oldval = rdtp->dynticks_nesting;
	rdtp->dynticks_nesting--;
	WARN_ON_ONCE(rdtp->dynticks_nesting < 0);
	if (rdtp->dynticks_nesting)
		trace_rcu_dyntick("--=", oldval, rdtp->dynticks_nesting);
	else
		rcu_eqs_enter_common(rdtp, oldval, true);
	local_irq_restore(flags);
}

/*
 * rcu_eqs_exit_common - current CPU moving away from extended quiescent state
 *
 * If the new value of the ->dynticks_nesting counter was previously zero,
 * we really have exited idle, and must do the appropriate accounting.
 * The caller must have disabled interrupts.
 */
static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval,
			       int user)
{
	smp_mb__before_atomic_inc();  /* Force ordering w/previous sojourn. */
	atomic_inc(&rdtp->dynticks);
	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
	smp_mb__after_atomic_inc();  /* See above. */
	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
	rcu_cleanup_after_idle(smp_processor_id());
	trace_rcu_dyntick("End", oldval, rdtp->dynticks_nesting);
	if (!user && !is_idle_task(current)) {
		struct task_struct *idle = idle_task(smp_processor_id());

		trace_rcu_dyntick("Error on exit: not idle task",
				  oldval, rdtp->dynticks_nesting);
		ftrace_dump(DUMP_ORIG);
		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
			  current->pid, current->comm,
			  idle->pid, idle->comm); /* must be idle task! */
	}
}

/*
 * Exit an RCU extended quiescent state, which can be either the
 * idle loop or adaptive-tickless usermode execution.
 */
static void rcu_eqs_exit(bool user)
{
	struct rcu_dynticks *rdtp;
	long long oldval;

	rdtp = &__get_cpu_var(rcu_dynticks);
	oldval = rdtp->dynticks_nesting;
	WARN_ON_ONCE(oldval < 0);
	if (oldval & DYNTICK_TASK_NEST_MASK)
		rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
	else
		rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
	rcu_eqs_exit_common(rdtp, oldval, user);
}

/**
 * rcu_idle_exit - inform RCU that current CPU is leaving idle
 *
 * Exit idle mode, in other words, -enter- the mode in which RCU
 * read-side critical sections can occur.
 *
 * We crowbar the ->dynticks_nesting field to DYNTICK_TASK_NEST to
 * allow for the possibility of usermode upcalls messing up our count
 * of interrupt nesting level during the busy period that is just
 * now starting.
 */
void rcu_idle_exit(void)
{
	unsigned long flags;

	local_irq_save(flags);
	rcu_eqs_exit(false);
	local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(rcu_idle_exit);

#ifdef CONFIG_RCU_USER_QS
/**
 * rcu_user_exit - inform RCU that we are exiting userspace.
 *
 * Exit RCU idle mode while entering the kernel because it can
 * run a RCU read side critical section anytime.
 */
void rcu_user_exit(void)
{
	rcu_eqs_exit(1);
}

/**
 * rcu_user_exit_after_irq - inform RCU that we won't resume to userspace
 * idle mode after the current non-nesting irq returns.
 *
 * This is similar to rcu_user_exit() but in the context of an irq.
 * This is called when the irq has interrupted a userspace RCU idle mode
 * context. When the current non-nesting interrupt returns after this call,
 * the CPU won't restore the RCU idle mode.
 */
void rcu_user_exit_after_irq(void)
{
	unsigned long flags;
	struct rcu_dynticks *rdtp;

	local_irq_save(flags);
	rdtp = &__get_cpu_var(rcu_dynticks);
	/* Ensure we are interrupting an RCU idle mode. */
	WARN_ON_ONCE(rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK);
	rdtp->dynticks_nesting += DYNTICK_TASK_EXIT_IDLE;
	local_irq_restore(flags);
}
#endif /* CONFIG_RCU_USER_QS */

/**
 * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
 *
 * Enter an interrupt handler, which might possibly result in exiting
 * idle mode, in other words, entering the mode in which read-side critical
 * sections can occur.
 *
 * Note that the Linux kernel is fully capable of entering an interrupt
 * handler that it never exits, for example when doing upcalls to
 * user mode!  This code assumes that the idle loop never does upcalls to
 * user mode.  If your architecture does do upcalls from the idle loop (or
 * does anything else that results in unbalanced calls to the irq_enter()
 * and irq_exit() functions), RCU will give you what you deserve, good
 * and hard.  But very infrequently and irreproducibly.
 *
 * Use things like work queues to work around this limitation.
 *
 * You have been warned.
 */
void rcu_irq_enter(void)
{
	unsigned long flags;
	struct rcu_dynticks *rdtp;
	long long oldval;

	local_irq_save(flags);
	rdtp = &__get_cpu_var(rcu_dynticks);
	oldval = rdtp->dynticks_nesting;
	rdtp->dynticks_nesting++;
	WARN_ON_ONCE(rdtp->dynticks_nesting == 0);
	if (oldval)
		trace_rcu_dyntick("++=", oldval, rdtp->dynticks_nesting);
	else
		rcu_eqs_exit_common(rdtp, oldval, true);
	local_irq_restore(flags);
}

/**
 * rcu_nmi_enter - inform RCU of entry to NMI context
 *
 * If the CPU was idle with dynamic ticks active, and there is no
 * irq handler running, this updates rdtp->dynticks_nmi to let the
 * RCU grace-period handling know that the CPU is active.
 */
void rcu_nmi_enter(void)
{
	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);

	if (rdtp->dynticks_nmi_nesting == 0 &&
	    (atomic_read(&rdtp->dynticks) & 0x1))
		return;
	rdtp->dynticks_nmi_nesting++;
	smp_mb__before_atomic_inc();  /* Force delay from prior write. */
	atomic_inc(&rdtp->dynticks);
	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
	smp_mb__after_atomic_inc();  /* See above. */
	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
}

/**
 * rcu_nmi_exit - inform RCU of exit from NMI context
 *
 * If the CPU was idle with dynamic ticks active, and there is no
 * irq handler running, this updates rdtp->dynticks_nmi to let the
 * RCU grace-period handling know that the CPU is no longer active.
 */
void rcu_nmi_exit(void)
{
	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);

	if (rdtp->dynticks_nmi_nesting == 0 ||
	    --rdtp->dynticks_nmi_nesting != 0)
		return;
	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
	smp_mb__before_atomic_inc();  /* See above. */
	atomic_inc(&rdtp->dynticks);
	smp_mb__after_atomic_inc();  /* Force delay to next write. */
	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
}

/**
 * rcu_is_cpu_idle - see if RCU thinks that the current CPU is idle
 *
 * If the current CPU is in its idle loop and is neither in an interrupt
 * or NMI handler, return true.
 */
int rcu_is_cpu_idle(void)
{
	int ret;

	preempt_disable();
	ret = (atomic_read(&__get_cpu_var(rcu_dynticks).dynticks) & 0x1) == 0;
	preempt_enable();
	return ret;
}
EXPORT_SYMBOL(rcu_is_cpu_idle);

#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)

/*
 * Is the current CPU online?  Disable preemption to avoid false positives
 * that could otherwise happen due to the current CPU number being sampled,
 * this task being preempted, its old CPU being taken offline, resuming
 * on some other CPU, then determining that its old CPU is now offline.
 * It is OK to use RCU on an offline processor during initial boot, hence
 * the check for rcu_scheduler_fully_active.  Note also that it is OK
 * for a CPU coming online to use RCU for one jiffy prior to marking itself
 * online in the cpu_online_mask.  Similarly, it is OK for a CPU going
 * offline to continue to use RCU for one jiffy after marking itself
 * offline in the cpu_online_mask.  This leniency is necessary given the
 * non-atomic nature of the online and offline processing, for example,
 * the fact that a CPU enters the scheduler after completing the CPU_DYING
 * notifiers.
 *
 * This is also why RCU internally marks CPUs online during the
 * CPU_UP_PREPARE phase and offline during the CPU_DEAD phase.
 *
 * Disable checking if in an NMI handler because we cannot safely report
 * errors from NMI handlers anyway.
 */
bool rcu_lockdep_current_cpu_online(void)
{
	struct rcu_data *rdp;
	struct rcu_node *rnp;
	bool ret;

	if (in_nmi())
		return 1;
	preempt_disable();
	rdp = &__get_cpu_var(rcu_sched_data);
	rnp = rdp->mynode;
	ret = (rdp->grpmask & rnp->qsmaskinit) ||
	      !rcu_scheduler_fully_active;
	preempt_enable();
	return ret;
}
EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);

#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */

/**
 * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle
 *
 * If the current CPU is idle or running at a first-level (not nested)
 * interrupt from idle, return true.  The caller must have at least
 * disabled preemption.
 */
static int rcu_is_cpu_rrupt_from_idle(void)
{
	return __get_cpu_var(rcu_dynticks).dynticks_nesting <= 1;
}

/*
 * Snapshot the specified CPU's dynticks counter so that we can later
 * credit them with an implicit quiescent state.  Return 1 if this CPU
 * is in dynticks idle mode, which is an extended quiescent state.
 */
static int dyntick_save_progress_counter(struct rcu_data *rdp)
{
	rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
	return (rdp->dynticks_snap & 0x1) == 0;
}

/*
 * Return true if the specified CPU has passed through a quiescent
 * state by virtue of being in or having passed through an dynticks
 * idle state since the last call to dyntick_save_progress_counter()
 * for this same CPU, or by virtue of having been offline.
 */
static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
{
	unsigned int curr;
	unsigned int snap;

	curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks);
	snap = (unsigned int)rdp->dynticks_snap;

	/*
	 * If the CPU passed through or entered a dynticks idle phase with
	 * no active irq/NMI handlers, then we can safely pretend that the CPU
	 * already acknowledged the request to pass through a quiescent
	 * state.  Either way, that CPU cannot possibly be in an RCU
	 * read-side critical section that started before the beginning
	 * of the current RCU grace period.
	 */
	if ((curr & 0x1) == 0 || UINT_CMP_GE(curr, snap + 2)) {
		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "dti");
		rdp->dynticks_fqs++;
		return 1;
	}

	/*
	 * Check for the CPU being offline, but only if the grace period
	 * is old enough.  We don't need to worry about the CPU changing
	 * state: If we see it offline even once, it has been through a
	 * quiescent state.
	 *
	 * The reason for insisting that the grace period be at least
	 * one jiffy old is that CPUs that are not quite online and that
	 * have just gone offline can still execute RCU read-side critical
	 * sections.
	 */
	if (ULONG_CMP_GE(rdp->rsp->gp_start + 2, jiffies))
		return 0;  /* Grace period is not old enough. */
	barrier();
	if (cpu_is_offline(rdp->cpu)) {
		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "ofl");
		rdp->offline_fqs++;
		return 1;
	}

	/*
	 * There is a possibility that a CPU in adaptive-ticks state
	 * might run in the kernel with the scheduling-clock tick disabled
	 * for an extended time period.  Invoke rcu_kick_nohz_cpu() to
	 * force the CPU to restart the scheduling-clock tick in this
	 * CPU is in this state.
	 */
	rcu_kick_nohz_cpu(rdp->cpu);

	return 0;
}

static void record_gp_stall_check_time(struct rcu_state *rsp)
{
	rsp->gp_start = jiffies;
	rsp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();
}

/*
 * Dump stacks of all tasks running on stalled CPUs.  This is a fallback
 * for architectures that do not implement trigger_all_cpu_backtrace().
 * The NMI-triggered stack traces are more accurate because they are
 * printed by the target CPU.
 */
static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
{
	int cpu;
	unsigned long flags;
	struct rcu_node *rnp;

	rcu_for_each_leaf_node(rsp, rnp) {
		raw_spin_lock_irqsave(&rnp->lock, flags);
		if (rnp->qsmask != 0) {
			for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
				if (rnp->qsmask & (1UL << cpu))
					dump_cpu_task(rnp->grplo + cpu);
		}
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
	}
}

static void print_other_cpu_stall(struct rcu_state *rsp)
{
	int cpu;
	long delta;
	unsigned long flags;
	int ndetected = 0;
	struct rcu_node *rnp = rcu_get_root(rsp);
	long totqlen = 0;

	/* Only let one CPU complain about others per time interval. */

	raw_spin_lock_irqsave(&rnp->lock, flags);
	delta = jiffies - rsp->jiffies_stall;
	if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
		return;
	}
	rsp->jiffies_stall = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
	raw_spin_unlock_irqrestore(&rnp->lock, flags);

	/*
	 * OK, time to rat on our buddy...
	 * See Documentation/RCU/stallwarn.txt for info on how to debug
	 * RCU CPU stall warnings.
	 */
	pr_err("INFO: %s detected stalls on CPUs/tasks:",
	       rsp->name);
	print_cpu_stall_info_begin();
	rcu_for_each_leaf_node(rsp, rnp) {
		raw_spin_lock_irqsave(&rnp->lock, flags);
		ndetected += rcu_print_task_stall(rnp);
		if (rnp->qsmask != 0) {
			for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
				if (rnp->qsmask & (1UL << cpu)) {
					print_cpu_stall_info(rsp,
							     rnp->grplo + cpu);
					ndetected++;
				}
		}
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
	}

	/*
	 * Now rat on any tasks that got kicked up to the root rcu_node
	 * due to CPU offlining.
	 */
	rnp = rcu_get_root(rsp);
	raw_spin_lock_irqsave(&rnp->lock, flags);
	ndetected += rcu_print_task_stall(rnp);
	raw_spin_unlock_irqrestore(&rnp->lock, flags);

	print_cpu_stall_info_end();
	for_each_possible_cpu(cpu)
		totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
	pr_cont("(detected by %d, t=%ld jiffies, g=%lu, c=%lu, q=%lu)\n",
	       smp_processor_id(), (long)(jiffies - rsp->gp_start),
	       rsp->gpnum, rsp->completed, totqlen);
	if (ndetected == 0)
		pr_err("INFO: Stall ended before state dump start\n");
	else if (!trigger_all_cpu_backtrace())
		rcu_dump_cpu_stacks(rsp);

	/* Complain about tasks blocking the grace period. */

	rcu_print_detail_task_stall(rsp);

	force_quiescent_state(rsp);  /* Kick them all. */
}

static void print_cpu_stall(struct rcu_state *rsp)
{
	int cpu;
	unsigned long flags;
	struct rcu_node *rnp = rcu_get_root(rsp);
	long totqlen = 0;

	/*
	 * OK, time to rat on ourselves...
	 * See Documentation/RCU/stallwarn.txt for info on how to debug
	 * RCU CPU stall warnings.
	 */
	pr_err("INFO: %s self-detected stall on CPU", rsp->name);
	print_cpu_stall_info_begin();
	print_cpu_stall_info(rsp, smp_processor_id());
	print_cpu_stall_info_end();
	for_each_possible_cpu(cpu)
		totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
	pr_cont(" (t=%lu jiffies g=%lu c=%lu q=%lu)\n",
		jiffies - rsp->gp_start, rsp->gpnum, rsp->completed, totqlen);
	if (!trigger_all_cpu_backtrace())
		dump_stack();

	raw_spin_lock_irqsave(&rnp->lock, flags);
	if (ULONG_CMP_GE(jiffies, rsp->jiffies_stall))
		rsp->jiffies_stall = jiffies +
				     3 * rcu_jiffies_till_stall_check() + 3;
	raw_spin_unlock_irqrestore(&rnp->lock, flags);

	set_need_resched();  /* kick ourselves to get things going. */
}

static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
{
	unsigned long j;
	unsigned long js;
	struct rcu_node *rnp;

	if (rcu_cpu_stall_suppress)
		return;
	j = ACCESS_ONCE(jiffies);
	js = ACCESS_ONCE(rsp->jiffies_stall);
	rnp = rdp->mynode;
	if (rcu_gp_in_progress(rsp) &&
	    (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) {

		/* We haven't checked in, so go dump stack. */
		print_cpu_stall(rsp);

	} else if (rcu_gp_in_progress(rsp) &&
		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) {

		/* They had a few time units to dump stack, so complain. */
		print_other_cpu_stall(rsp);
	}
}

/**
 * rcu_cpu_stall_reset - prevent further stall warnings in current grace period
 *
 * Set the stall-warning timeout way off into the future, thus preventing
 * any RCU CPU stall-warning messages from appearing in the current set of
 * RCU grace periods.
 *
 * The caller must disable hard irqs.
 */
void rcu_cpu_stall_reset(void)
{
	struct rcu_state *rsp;

	for_each_rcu_flavor(rsp)
		rsp->jiffies_stall = jiffies + ULONG_MAX / 2;
}

/*
 * Initialize the specified rcu_data structure's callback list to empty.
 */
static void init_callback_list(struct rcu_data *rdp)
{
	int i;

	if (init_nocb_callback_list(rdp))
		return;
	rdp->nxtlist = NULL;
	for (i = 0; i < RCU_NEXT_SIZE; i++)
		rdp->nxttail[i] = &rdp->nxtlist;
}

/*
 * Determine the value that ->completed will have at the end of the
 * next subsequent grace period.  This is used to tag callbacks so that
 * a CPU can invoke callbacks in a timely fashion even if that CPU has
 * been dyntick-idle for an extended period with callbacks under the
 * influence of RCU_FAST_NO_HZ.
 *
 * The caller must hold rnp->lock with interrupts disabled.
 */
static unsigned long rcu_cbs_completed(struct rcu_state *rsp,
				       struct rcu_node *rnp)
{
	/*
	 * If RCU is idle, we just wait for the next grace period.
	 * But we can only be sure that RCU is idle if we are looking
	 * at the root rcu_node structure -- otherwise, a new grace
	 * period might have started, but just not yet gotten around
	 * to initializing the current non-root rcu_node structure.
	 */
	if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed)
		return rnp->completed + 1;

	/*
	 * Otherwise, wait for a possible partial grace period and
	 * then the subsequent full grace period.
	 */
	return rnp->completed + 2;
}

/*
 * Trace-event helper function for rcu_start_future_gp() and
 * rcu_nocb_wait_gp().
 */
static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
				unsigned long c, char *s)
{
	trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum,
				      rnp->completed, c, rnp->level,
				      rnp->grplo, rnp->grphi, s);
}

/*
 * Start some future grace period, as needed to handle newly arrived
 * callbacks.  The required future grace periods are recorded in each
 * rcu_node structure's ->need_future_gp field.
 *
 * The caller must hold the specified rcu_node structure's ->lock.
 */
static unsigned long __maybe_unused
rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
{
	unsigned long c;
	int i;
	struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);

	/*
	 * Pick up grace-period number for new callbacks.  If this
	 * grace period is already marked as needed, return to the caller.
	 */
	c = rcu_cbs_completed(rdp->rsp, rnp);
	trace_rcu_future_gp(rnp, rdp, c, "Startleaf");
	if (rnp->need_future_gp[c & 0x1]) {
		trace_rcu_future_gp(rnp, rdp, c, "Prestartleaf");
		return c;
	}

	/*
	 * If either this rcu_node structure or the root rcu_node structure
	 * believe that a grace period is in progress, then we must wait
	 * for the one following, which is in "c".  Because our request
	 * will be noticed at the end of the current grace period, we don't
	 * need to explicitly start one.
	 */
	if (rnp->gpnum != rnp->completed ||
	    ACCESS_ONCE(rnp->gpnum) != ACCESS_ONCE(rnp->completed)) {
		rnp->need_future_gp[c & 0x1]++;
		trace_rcu_future_gp(rnp, rdp, c, "Startedleaf");
		return c;
	}

	/*
	 * There might be no grace period in progress.  If we don't already
	 * hold it, acquire the root rcu_node structure's lock in order to
	 * start one (if needed).
	 */
	if (rnp != rnp_root)
		raw_spin_lock(&rnp_root->lock);

	/*
	 * Get a new grace-period number.  If there really is no grace
	 * period in progress, it will be smaller than the one we obtained
	 * earlier.  Adjust callbacks as needed.  Note that even no-CBs
	 * CPUs have a ->nxtcompleted[] array, so no no-CBs checks needed.
	 */
	c = rcu_cbs_completed(rdp->rsp, rnp_root);
	for (i = RCU_DONE_TAIL; i < RCU_NEXT_TAIL; i++)
		if (ULONG_CMP_LT(c, rdp->nxtcompleted[i]))
			rdp->nxtcompleted[i] = c;

	/*
	 * If the needed for the required grace period is already
	 * recorded, trace and leave.
	 */
	if (rnp_root->need_future_gp[c & 0x1]) {
		trace_rcu_future_gp(rnp, rdp, c, "Prestartedroot");
		goto unlock_out;
	}

	/* Record the need for the future grace period. */
	rnp_root->need_future_gp[c & 0x1]++;

	/* If a grace period is not already in progress, start one. */
	if (rnp_root->gpnum != rnp_root->completed) {
		trace_rcu_future_gp(rnp, rdp, c, "Startedleafroot");
	} else {
		trace_rcu_future_gp(rnp, rdp, c, "Startedroot");
		rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp);
	}
unlock_out:
	if (rnp != rnp_root)
		raw_spin_unlock(&rnp_root->lock);
	return c;
}

/*
 * Clean up any old requests for the just-ended grace period.  Also return
 * whether any additional grace periods have been requested.  Also invoke
 * rcu_nocb_gp_cleanup() in order to wake up any no-callbacks kthreads
 * waiting for this grace period to complete.
 */
static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
{
	int c = rnp->completed;
	int needmore;
	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);

	rcu_nocb_gp_cleanup(rsp, rnp);
	rnp->need_future_gp[c & 0x1] = 0;
	needmore = rnp->need_future_gp[(c + 1) & 0x1];
	trace_rcu_future_gp(rnp, rdp, c, needmore ? "CleanupMore" : "Cleanup");
	return needmore;
}

/*
 * If there is room, assign a ->completed number to any callbacks on
 * this CPU that have not already been assigned.  Also accelerate any
 * callbacks that were previously assigned a ->completed number that has
 * since proven to be too conservative, which can happen if callbacks get
 * assigned a ->completed number while RCU is idle, but with reference to
 * a non-root rcu_node structure.  This function is idempotent, so it does
 * not hurt to call it repeatedly.
 *
 * The caller must hold rnp->lock with interrupts disabled.
 */
static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
			       struct rcu_data *rdp)
{
	unsigned long c;
	int i;

	/* If the CPU has no callbacks, nothing to do. */
	if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL])
		return;

	/*
	 * Starting from the sublist containing the callbacks most
	 * recently assigned a ->completed number and working down, find the
	 * first sublist that is not assignable to an upcoming grace period.
	 * Such a sublist has something in it (first two tests) and has
	 * a ->completed number assigned that will complete sooner than
	 * the ->completed number for newly arrived callbacks (last test).
	 *
	 * The key point is that any later sublist can be assigned the
	 * same ->completed number as the newly arrived callbacks, which
	 * means that the callbacks in any of these later sublist can be
	 * grouped into a single sublist, whether or not they have already
	 * been assigned a ->completed number.
	 */
	c = rcu_cbs_completed(rsp, rnp);
	for (i = RCU_NEXT_TAIL - 1; i > RCU_DONE_TAIL; i--)
		if (rdp->nxttail[i] != rdp->nxttail[i - 1] &&
		    !ULONG_CMP_GE(rdp->nxtcompleted[i], c))
			break;

	/*
	 * If there are no sublist for unassigned callbacks, leave.
	 * At the same time, advance "i" one sublist, so that "i" will
	 * index into the sublist where all the remaining callbacks should
	 * be grouped into.
	 */
	if (++i >= RCU_NEXT_TAIL)
		return;

	/*
	 * Assign all subsequent callbacks' ->completed number to the next
	 * full grace period and group them all in the sublist initially
	 * indexed by "i".
	 */
	for (; i <= RCU_NEXT_TAIL; i++) {
		rdp->nxttail[i] = rdp->nxttail[RCU_NEXT_TAIL];
		rdp->nxtcompleted[i] = c;
	}
	/* Record any needed additional grace periods. */
	rcu_start_future_gp(rnp, rdp);

	/* Trace depending on how much we were able to accelerate. */
	if (!*rdp->nxttail[RCU_WAIT_TAIL])
		trace_rcu_grace_period(rsp->name, rdp->gpnum, "AccWaitCB");
	else
		trace_rcu_grace_period(rsp->name, rdp->gpnum, "AccReadyCB");
}

/*
 * Move any callbacks whose grace period has completed to the
 * RCU_DONE_TAIL sublist, then compact the remaining sublists and
 * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL
 * sublist.  This function is idempotent, so it does not hurt to
 * invoke it repeatedly.  As long as it is not invoked -too- often...
 *
 * The caller must hold rnp->lock with interrupts disabled.
 */
static void rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
			    struct rcu_data *rdp)
{
	int i, j;

	/* If the CPU has no callbacks, nothing to do. */
	if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL])
		return;

	/*
	 * Find all callbacks whose ->completed numbers indicate that they
	 * are ready to invoke, and put them into the RCU_DONE_TAIL sublist.
	 */
	for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) {
		if (ULONG_CMP_LT(rnp->completed, rdp->nxtcompleted[i]))
			break;
		rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[i];
	}
	/* Clean up any sublist tail pointers that were misordered above. */
	for (j = RCU_WAIT_TAIL; j < i; j++)
		rdp->nxttail[j] = rdp->nxttail[RCU_DONE_TAIL];

	/* Copy down callbacks to fill in empty sublists. */
	for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) {
		if (rdp->nxttail[j] == rdp->nxttail[RCU_NEXT_TAIL])
			break;
		rdp->nxttail[j] = rdp->nxttail[i];
		rdp->nxtcompleted[j] = rdp->nxtcompleted[i];
	}

	/* Classify any remaining callbacks. */
	rcu_accelerate_cbs(rsp, rnp, rdp);
}

/*
 * Update CPU-local rcu_data state to record the beginnings and ends of
 * grace periods.  The caller must hold the ->lock of the leaf rcu_node
 * structure corresponding to the current CPU, and must have irqs disabled.
 */
static void __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
{
	/* Handle the ends of any preceding grace periods first. */
	if (rdp->completed == rnp->completed) {

		/* No grace period end, so just accelerate recent callbacks. */
		rcu_accelerate_cbs(rsp, rnp, rdp);

	} else {

		/* Advance callbacks. */
		rcu_advance_cbs(rsp, rnp, rdp);

		/* Remember that we saw this grace-period completion. */
		rdp->completed = rnp->completed;
		trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpuend");
	}

	if (rdp->gpnum != rnp->gpnum) {
		/*
		 * If the current grace period is waiting for this CPU,
		 * set up to detect a quiescent state, otherwise don't
		 * go looking for one.
		 */
		rdp->gpnum = rnp->gpnum;
		trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpustart");
		rdp->passed_quiesce = 0;
		rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
		zero_cpu_stall_ticks(rdp);
	}
}

static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
{
	unsigned long flags;
	struct rcu_node *rnp;

	local_irq_save(flags);
	rnp = rdp->mynode;
	if ((rdp->gpnum == ACCESS_ONCE(rnp->gpnum) &&
	     rdp->completed == ACCESS_ONCE(rnp->completed)) || /* w/out lock. */
	    !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
		local_irq_restore(flags);
		return;
	}
	__note_gp_changes(rsp, rnp, rdp);
	raw_spin_unlock_irqrestore(&rnp->lock, flags);
}

/*
 * Initialize a new grace period.
 */
static int rcu_gp_init(struct rcu_state *rsp)
{
	struct rcu_data *rdp;
	struct rcu_node *rnp = rcu_get_root(rsp);

	raw_spin_lock_irq(&rnp->lock);
	rsp->gp_flags = 0; /* Clear all flags: New grace period. */

	if (rcu_gp_in_progress(rsp)) {
		/* Grace period already in progress, don't start another.  */
		raw_spin_unlock_irq(&rnp->lock);
		return 0;
	}

	/* Advance to a new grace period and initialize state. */
	rsp->gpnum++;
	trace_rcu_grace_period(rsp->name, rsp->gpnum, "start");
	record_gp_stall_check_time(rsp);
	raw_spin_unlock_irq(&rnp->lock);

	/* Exclude any concurrent CPU-hotplug operations. */
	mutex_lock(&rsp->onoff_mutex);

	/*
	 * Set the quiescent-state-needed bits in all the rcu_node
	 * structures for all currently online CPUs in breadth-first order,
	 * starting from the root rcu_node structure, relying on the layout
	 * of the tree within the rsp->node[] array.  Note that other CPUs
	 * will access only the leaves of the hierarchy, thus seeing that no
	 * grace period is in progress, at least until the corresponding
	 * leaf node has been initialized.  In addition, we have excluded
	 * CPU-hotplug operations.
	 *
	 * The grace period cannot complete until the initialization
	 * process finishes, because this kthread handles both.
	 */
	rcu_for_each_node_breadth_first(rsp, rnp) {
		raw_spin_lock_irq(&rnp->lock);
		rdp = this_cpu_ptr(rsp->rda);
		rcu_preempt_check_blocked_tasks(rnp);
		rnp->qsmask = rnp->qsmaskinit;
		ACCESS_ONCE(rnp->gpnum) = rsp->gpnum;
		WARN_ON_ONCE(rnp->completed != rsp->completed);
		ACCESS_ONCE(rnp->completed) = rsp->completed;
		if (rnp == rdp->mynode)
			__note_gp_changes(rsp, rnp, rdp);
		rcu_preempt_boost_start_gp(rnp);
		trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
					    rnp->level, rnp->grplo,
					    rnp->grphi, rnp->qsmask);
		raw_spin_unlock_irq(&rnp->lock);
#ifdef CONFIG_PROVE_RCU_DELAY
		if ((prandom_u32() % (rcu_num_nodes + 1)) == 0 &&
		    system_state == SYSTEM_RUNNING)
			udelay(200);
#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
		cond_resched();
	}

	mutex_unlock(&rsp->onoff_mutex);
	return 1;
}

/*
 * Do one round of quiescent-state forcing.
 */
int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
{
	int fqs_state = fqs_state_in;
	struct rcu_node *rnp = rcu_get_root(rsp);

	rsp->n_force_qs++;
	if (fqs_state == RCU_SAVE_DYNTICK) {
		/* Collect dyntick-idle snapshots. */
		force_qs_rnp(rsp, dyntick_save_progress_counter);
		fqs_state = RCU_FORCE_QS;
	} else {
		/* Handle dyntick-idle and offline CPUs. */
		force_qs_rnp(rsp, rcu_implicit_dynticks_qs);
	}
	/* Clear flag to prevent immediate re-entry. */
	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
		raw_spin_lock_irq(&rnp->lock);
		rsp->gp_flags &= ~RCU_GP_FLAG_FQS;
		raw_spin_unlock_irq(&rnp->lock);
	}
	return fqs_state;
}

/*
 * Clean up after the old grace period.
 */
static void rcu_gp_cleanup(struct rcu_state *rsp)
{
	unsigned long gp_duration;
	int nocb = 0;
	struct rcu_data *rdp;
	struct rcu_node *rnp = rcu_get_root(rsp);

	raw_spin_lock_irq(&rnp->lock);
	gp_duration = jiffies - rsp->gp_start;
	if (gp_duration > rsp->gp_max)
		rsp->gp_max = gp_duration;

	/*
	 * We know the grace period is complete, but to everyone else
	 * it appears to still be ongoing.  But it is also the case
	 * that to everyone else it looks like there is nothing that
	 * they can do to advance the grace period.  It is therefore
	 * safe for us to drop the lock in order to mark the grace
	 * period as completed in all of the rcu_node structures.
	 */
	raw_spin_unlock_irq(&rnp->lock);

	/*
	 * Propagate new ->completed value to rcu_node structures so
	 * that other CPUs don't have to wait until the start of the next
	 * grace period to process their callbacks.  This also avoids
	 * some nasty RCU grace-period initialization races by forcing
	 * the end of the current grace period to be completely recorded in
	 * all of the rcu_node structures before the beginning of the next
	 * grace period is recorded in any of the rcu_node structures.
	 */
	rcu_for_each_node_breadth_first(rsp, rnp) {
		raw_spin_lock_irq(&rnp->lock);
		ACCESS_ONCE(rnp->completed) = rsp->gpnum;
		rdp = this_cpu_ptr(rsp->rda);
		if (rnp == rdp->mynode)
			__note_gp_changes(rsp, rnp, rdp);
		nocb += rcu_future_gp_cleanup(rsp, rnp);
		raw_spin_unlock_irq(&rnp->lock);
		cond_resched();
	}
	rnp = rcu_get_root(rsp);
	raw_spin_lock_irq(&rnp->lock);
	rcu_nocb_gp_set(rnp, nocb);

	rsp->completed = rsp->gpnum; /* Declare grace period done. */
	trace_rcu_grace_period(rsp->name, rsp->completed, "end");
	rsp->fqs_state = RCU_GP_IDLE;
	rdp = this_cpu_ptr(rsp->rda);
	rcu_advance_cbs(rsp, rnp, rdp);  /* Reduce false positives below. */
	if (cpu_needs_another_gp(rsp, rdp))
		rsp->gp_flags = 1;
	raw_spin_unlock_irq(&rnp->lock);
}

/*
 * Body of kthread that handles grace periods.
 */
static int __noreturn rcu_gp_kthread(void *arg)
{
	int fqs_state;
	unsigned long j;
	int ret;
	struct rcu_state *rsp = arg;
	struct rcu_node *rnp = rcu_get_root(rsp);

	for (;;) {

		/* Handle grace-period start. */
		for (;;) {
			wait_event_interruptible(rsp->gp_wq,
						 rsp->gp_flags &
						 RCU_GP_FLAG_INIT);
			if ((rsp->gp_flags & RCU_GP_FLAG_INIT) &&
			    rcu_gp_init(rsp))
				break;
			cond_resched();
			flush_signals(current);
		}

		/* Handle quiescent-state forcing. */
		fqs_state = RCU_SAVE_DYNTICK;
		j = jiffies_till_first_fqs;
		if (j > HZ) {
			j = HZ;
			jiffies_till_first_fqs = HZ;
		}
		for (;;) {
			rsp->jiffies_force_qs = jiffies + j;
			ret = wait_event_interruptible_timeout(rsp->gp_wq,
					(rsp->gp_flags & RCU_GP_FLAG_FQS) ||
					(!ACCESS_ONCE(rnp->qsmask) &&
					 !rcu_preempt_blocked_readers_cgp(rnp)),
					j);
			/* If grace period done, leave loop. */
			if (!ACCESS_ONCE(rnp->qsmask) &&
			    !rcu_preempt_blocked_readers_cgp(rnp))
				break;
			/* If time for quiescent-state forcing, do it. */
			if (ret == 0 || (rsp->gp_flags & RCU_GP_FLAG_FQS)) {
				fqs_state = rcu_gp_fqs(rsp, fqs_state);
				cond_resched();
			} else {
				/* Deal with stray signal. */
				cond_resched();
				flush_signals(current);
			}
			j = jiffies_till_next_fqs;
			if (j > HZ) {
				j = HZ;
				jiffies_till_next_fqs = HZ;
			} else if (j < 1) {
				j = 1;
				jiffies_till_next_fqs = 1;
			}
		}

		/* Handle grace-period end. */
		rcu_gp_cleanup(rsp);
	}
}

static void rsp_wakeup(struct irq_work *work)
{
	struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work);

	/* Wake up rcu_gp_kthread() to start the grace period. */
	wake_up(&rsp->gp_wq);
}

/*
 * Start a new RCU grace period if warranted, re-initializing the hierarchy
 * in preparation for detecting the next grace period.  The caller must hold
 * the root node's ->lock and hard irqs must be disabled.
 *
 * Note that it is legal for a dying CPU (which is marked as offline) to
 * invoke this function.  This can happen when the dying CPU reports its
 * quiescent state.
 */
static void
rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
		      struct rcu_data *rdp)
{
	if (!rsp->gp_kthread || !cpu_needs_another_gp(rsp, rdp)) {
		/*
		 * Either we have not yet spawned the grace-period
		 * task, this CPU does not need another grace period,
		 * or a grace period is already in progress.
		 * Either way, don't start a new grace period.
		 */
		return;
	}
	rsp->gp_flags = RCU_GP_FLAG_INIT;

	/*
	 * We can't do wakeups while holding the rnp->lock, as that
	 * could cause possible deadlocks with the rq->lock. Deter
	 * the wakeup to interrupt context.
	 */
	irq_work_queue(&rsp->wakeup_work);
}

/*
 * Similar to rcu_start_gp_advanced(), but also advance the calling CPU's
 * callbacks.  Note that rcu_start_gp_advanced() cannot do this because it
 * is invoked indirectly from rcu_advance_cbs(), which would result in
 * endless recursion -- or would do so if it wasn't for the self-deadlock
 * that is encountered beforehand.
 */
static void
rcu_start_gp(struct rcu_state *rsp)
{
	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
	struct rcu_node *rnp = rcu_get_root(rsp);

	/*
	 * If there is no grace period in progress right now, any
	 * callbacks we have up to this point will be satisfied by the
	 * next grace period.  Also, advancing the callbacks reduces the
	 * probability of false positives from cpu_needs_another_gp()
	 * resulting in pointless grace periods.  So, advance callbacks
	 * then start the grace period!
	 */
	rcu_advance_cbs(rsp, rnp, rdp);
	rcu_start_gp_advanced(rsp, rnp, rdp);
}

/*
 * Report a full set of quiescent states to the specified rcu_state
 * data structure.  This involves cleaning up after the prior grace
 * period and letting rcu_start_gp() start up the next grace period
 * if one is needed.  Note that the caller must hold rnp->lock, which
 * is released before return.
 */
static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
	__releases(rcu_get_root(rsp)->lock)
{
	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
	raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
	wake_up(&rsp->gp_wq);  /* Memory barrier implied by wake_up() path. */
}

/*
 * Similar to rcu_report_qs_rdp(), for which it is a helper function.
 * Allows quiescent states for a group of CPUs to be reported at one go
 * to the specified rcu_node structure, though all the CPUs in the group
 * must be represented by the same rcu_node structure (which need not be
 * a leaf rcu_node structure, though it often will be).  That structure's
 * lock must be held upon entry, and it is released before return.
 */
static void
rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
		  struct rcu_node *rnp, unsigned long flags)
	__releases(rnp->lock)
{
	struct rcu_node *rnp_c;

	/* Walk up the rcu_node hierarchy. */
	for (;;) {
		if (!(rnp->qsmask & mask)) {

			/* Our bit has already been cleared, so done. */
			raw_spin_unlock_irqrestore(&rnp->lock, flags);
			return;
		}
		rnp->qsmask &= ~mask;
		trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum,
						 mask, rnp->qsmask, rnp->level,
						 rnp->grplo, rnp->grphi,
						 !!rnp->gp_tasks);
		if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {

			/* Other bits still set at this level, so done. */
			raw_spin_unlock_irqrestore(&rnp->lock, flags);
			return;
		}
		mask = rnp->grpmask;
		if (rnp->parent == NULL) {

			/* No more levels.  Exit loop holding root lock. */

			break;
		}
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
		rnp_c = rnp;
		rnp = rnp->parent;
		raw_spin_lock_irqsave(&rnp->lock, flags);
		WARN_ON_ONCE(rnp_c->qsmask);
	}

	/*
	 * Get here if we are the last CPU to pass through a quiescent
	 * state for this grace period.  Invoke rcu_report_qs_rsp()
	 * to clean up and start the next grace period if one is needed.
	 */
	rcu_report_qs_rsp(rsp, flags); /* releases rnp->lock. */
}

/*
 * Record a quiescent state for the specified CPU to that CPU's rcu_data
 * structure.  This must be either called from the specified CPU, or
 * called when the specified CPU is known to be offline (and when it is
 * also known that no other CPU is concurrently trying to help the offline
 * CPU).  The lastcomp argument is used to make sure we are still in the
 * grace period of interest.  We don't want to end the current grace period
 * based on quiescent states detected in an earlier grace period!
 */
static void
rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
{
	unsigned long flags;
	unsigned long mask;
	struct rcu_node *rnp;

	rnp = rdp->mynode;
	raw_spin_lock_irqsave(&rnp->lock, flags);
	if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum ||
	    rnp->completed == rnp->gpnum) {

		/*
		 * The grace period in which this quiescent state was
		 * recorded has ended, so don't report it upwards.
		 * We will instead need a new quiescent state that lies
		 * within the current grace period.
		 */
		rdp->passed_quiesce = 0;	/* need qs for new gp. */
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
		return;
	}
	mask = rdp->grpmask;
	if ((rnp->qsmask & mask) == 0) {
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
	} else {
		rdp->qs_pending = 0;

		/*
		 * This GP can't end until cpu checks in, so all of our
		 * callbacks can be processed during the next GP.
		 */
		rcu_accelerate_cbs(rsp, rnp, rdp);

		rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */
	}
}

/*
 * Check to see if there is a new grace period of which this CPU
 * is not yet aware, and if so, set up local rcu_data state for it.
 * Otherwise, see if this CPU has just passed through its first
 * quiescent state for this grace period, and record that fact if so.
 */
static void
rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
{
	/* Check for grace-period ends and beginnings. */
	note_gp_changes(rsp, rdp);

	/*
	 * Does this CPU still need to do its part for current grace period?
	 * If no, return and let the other CPUs do their part as well.
	 */
	if (!rdp->qs_pending)
		return;

	/*
	 * Was there a quiescent state since the beginning of the grace
	 * period? If no, then exit and wait for the next call.
	 */
	if (!rdp->passed_quiesce)
		return;

	/*
	 * Tell RCU we are done (but rcu_report_qs_rdp() will be the
	 * judge of that).
	 */
	rcu_report_qs_rdp(rdp->cpu, rsp, rdp);
}

#ifdef CONFIG_HOTPLUG_CPU

/*
 * Send the specified CPU's RCU callbacks to the orphanage.  The
 * specified CPU must be offline, and the caller must hold the
 * ->orphan_lock.
 */
static void
rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
			  struct rcu_node *rnp, struct rcu_data *rdp)
{
	/* No-CBs CPUs do not have orphanable callbacks. */
	if (rcu_is_nocb_cpu(rdp->cpu))
		return;

	/*
	 * Orphan the callbacks.  First adjust the counts.  This is safe
	 * because _rcu_barrier() excludes CPU-hotplug operations, so it
	 * cannot be running now.  Thus no memory barrier is required.
	 */
	if (rdp->nxtlist != NULL) {
		rsp->qlen_lazy += rdp->qlen_lazy;
		rsp->qlen += rdp->qlen;
		rdp->n_cbs_orphaned += rdp->qlen;
		rdp->qlen_lazy = 0;
		ACCESS_ONCE(rdp->qlen) = 0;
	}

	/*
	 * Next, move those callbacks still needing a grace period to
	 * the orphanage, where some other CPU will pick them up.
	 * Some of the callbacks might have gone partway through a grace
	 * period, but that is too bad.  They get to start over because we
	 * cannot assume that grace periods are synchronized across CPUs.
	 * We don't bother updating the ->nxttail[] array yet, instead
	 * we just reset the whole thing later on.
	 */
	if (*rdp->nxttail[RCU_DONE_TAIL] != NULL) {
		*rsp->orphan_nxttail = *rdp->nxttail[RCU_DONE_TAIL];
		rsp->orphan_nxttail = rdp->nxttail[RCU_NEXT_TAIL];
		*rdp->nxttail[RCU_DONE_TAIL] = NULL;
	}

	/*
	 * Then move the ready-to-invoke callbacks to the orphanage,
	 * where some other CPU will pick them up.  These will not be
	 * required to pass though another grace period: They are done.
	 */
	if (rdp->nxtlist != NULL) {
		*rsp->orphan_donetail = rdp->nxtlist;
		rsp->orphan_donetail = rdp->nxttail[RCU_DONE_TAIL];
	}

	/* Finally, initialize the rcu_data structure's list to empty.  */
	init_callback_list(rdp);
}

/*
 * Adopt the RCU callbacks from the specified rcu_state structure's
 * orphanage.  The caller must hold the ->orphan_lock.
 */
static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
{
	int i;
	struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);

	/* No-CBs CPUs are handled specially. */
	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp))
		return;

	/* Do the accounting first. */
	rdp->qlen_lazy += rsp->qlen_lazy;
	rdp->qlen += rsp->qlen;
	rdp->n_cbs_adopted += rsp->qlen;
	if (rsp->qlen_lazy != rsp->qlen)
		rcu_idle_count_callbacks_posted();
	rsp->qlen_lazy = 0;
	rsp->qlen = 0;

	/*
	 * We do not need a memory barrier here because the only way we
	 * can get here if there is an rcu_barrier() in flight is if
	 * we are the task doing the rcu_barrier().
	 */

	/* First adopt the ready-to-invoke callbacks. */
	if (rsp->orphan_donelist != NULL) {
		*rsp->orphan_donetail = *rdp->nxttail[RCU_DONE_TAIL];
		*rdp->nxttail[RCU_DONE_TAIL] = rsp->orphan_donelist;
		for (i = RCU_NEXT_SIZE - 1; i >= RCU_DONE_TAIL; i--)
			if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
				rdp->nxttail[i] = rsp->orphan_donetail;
		rsp->orphan_donelist = NULL;
		rsp->orphan_donetail = &rsp->orphan_donelist;
	}

	/* And then adopt the callbacks that still need a grace period. */
	if (rsp->orphan_nxtlist != NULL) {
		*rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_nxtlist;
		rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_nxttail;
		rsp->orphan_nxtlist = NULL;
		rsp->orphan_nxttail = &rsp->orphan_nxtlist;
	}
}

/*
 * Trace the fact that this CPU is going offline.
 */
static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
{
	RCU_TRACE(unsigned long mask);
	RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda));
	RCU_TRACE(struct rcu_node *rnp = rdp->mynode);

	RCU_TRACE(mask = rdp->grpmask);
	trace_rcu_grace_period(rsp->name,
			       rnp->gpnum + 1 - !!(rnp->qsmask & mask),
			       "cpuofl");
}

/*
 * The CPU has been completely removed, and some other CPU is reporting
 * this fact from process context.  Do the remainder of the cleanup,
 * including orphaning the outgoing CPU's RCU callbacks, and also
 * adopting them.  There can only be one CPU hotplug operation at a time,
 * so no other CPU can be attempting to update rcu_cpu_kthread_task.
 */
static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
{
	unsigned long flags;
	unsigned long mask;
	int need_report = 0;
	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */

	/* Adjust any no-longer-needed kthreads. */
	rcu_boost_kthread_setaffinity(rnp, -1);

	/* Remove the dead CPU from the bitmasks in the rcu_node hierarchy. */

	/* Exclude any attempts to start a new grace period. */
	mutex_lock(&rsp->onoff_mutex);
	raw_spin_lock_irqsave(&rsp->orphan_lock, flags);

	/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
	rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
	rcu_adopt_orphan_cbs(rsp);

	/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
	mask = rdp->grpmask;	/* rnp->grplo is constant. */
	do {
		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
		rnp->qsmaskinit &= ~mask;
		if (rnp->qsmaskinit != 0) {
			if (rnp != rdp->mynode)
				raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
			break;
		}
		if (rnp == rdp->mynode)
			need_report = rcu_preempt_offline_tasks(rsp, rnp, rdp);
		else
			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
		mask = rnp->grpmask;
		rnp = rnp->parent;
	} while (rnp != NULL);

	/*
	 * We still hold the leaf rcu_node structure lock here, and
	 * irqs are still disabled.  The reason for this subterfuge is
	 * because invoking rcu_report_unblock_qs_rnp() with ->orphan_lock
	 * held leads to deadlock.
	 */
	raw_spin_unlock(&rsp->orphan_lock); /* irqs remain disabled. */
	rnp = rdp->mynode;
	if (need_report & RCU_OFL_TASKS_NORM_GP)
		rcu_report_unblock_qs_rnp(rnp, flags);
	else
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
	if (need_report & RCU_OFL_TASKS_EXP_GP)
		rcu_report_exp_rnp(rsp, rnp, true);
	WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL,
		  "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n",
		  cpu, rdp->qlen, rdp->nxtlist);
	init_callback_list(rdp);
	/* Disallow further callbacks on this CPU. */
	rdp->nxttail[RCU_NEXT_TAIL] = NULL;
	mutex_unlock(&rsp->onoff_mutex);
}

#else /* #ifdef CONFIG_HOTPLUG_CPU */

static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
{
}

static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
{
}

#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */

/*
 * Invoke any RCU callbacks that have made it to the end of their grace
 * period.  Thottle as specified by rdp->blimit.
 */
static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
{
	unsigned long flags;
	struct rcu_head *next, *list, **tail;
	long bl, count, count_lazy;
	int i;

	/* If no callbacks are ready, just return. */
	if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
		trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0);
		trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist),
				    need_resched(), is_idle_task(current),
				    rcu_is_callbacks_kthread());
		return;
	}

	/*
	 * Extract the list of ready callbacks, disabling to prevent
	 * races with call_rcu() from interrupt handlers.
	 */
	local_irq_save(flags);
	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
	bl = rdp->blimit;
	trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, bl);
	list = rdp->nxtlist;
	rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL];
	*rdp->nxttail[RCU_DONE_TAIL] = NULL;
	tail = rdp->nxttail[RCU_DONE_TAIL];
	for (i = RCU_NEXT_SIZE - 1; i >= 0; i--)
		if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
			rdp->nxttail[i] = &rdp->nxtlist;
	local_irq_restore(flags);

	/* Invoke callbacks. */
	count = count_lazy = 0;
	while (list) {
		next = list->next;
		prefetch(next);
		debug_rcu_head_unqueue(list);
		if (__rcu_reclaim(rsp->name, list))
			count_lazy++;
		list = next;
		/* Stop only if limit reached and CPU has something to do. */
		if (++count >= bl &&
		    (need_resched() ||
		     (!is_idle_task(current) && !rcu_is_callbacks_kthread())))
			break;
	}

	local_irq_save(flags);
	trace_rcu_batch_end(rsp->name, count, !!list, need_resched(),
			    is_idle_task(current),
			    rcu_is_callbacks_kthread());

	/* Update count, and requeue any remaining callbacks. */
	if (list != NULL) {
		*tail = rdp->nxtlist;
		rdp->nxtlist = list;
		for (i = 0; i < RCU_NEXT_SIZE; i++)
			if (&rdp->nxtlist == rdp->nxttail[i])
				rdp->nxttail[i] = tail;
			else
				break;
	}
	smp_mb(); /* List handling before counting for rcu_barrier(). */
	rdp->qlen_lazy -= count_lazy;
	ACCESS_ONCE(rdp->qlen) -= count;
	rdp->n_cbs_invoked += count;

	/* Reinstate batch limit if we have worked down the excess. */
	if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark)
		rdp->blimit = blimit;

	/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
	if (rdp->qlen == 0 && rdp->qlen_last_fqs_check != 0) {
		rdp->qlen_last_fqs_check = 0;
		rdp->n_force_qs_snap = rsp->n_force_qs;
	} else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark)
		rdp->qlen_last_fqs_check = rdp->qlen;
	WARN_ON_ONCE((rdp->nxtlist == NULL) != (rdp->qlen == 0));

	local_irq_restore(flags);

	/* Re-invoke RCU core processing if there are callbacks remaining. */
	if (cpu_has_callbacks_ready_to_invoke(rdp))
		invoke_rcu_core();
}

/*
 * Check to see if this CPU is in a non-context-switch quiescent state
 * (user mode or idle loop for rcu, non-softirq execution for rcu_bh).
 * Also schedule RCU core processing.
 *
 * This function must be called from hardirq context.  It is normally
 * invoked from the scheduling-clock interrupt.  If rcu_pending returns
 * false, there is no point in invoking rcu_check_callbacks().
 */
void rcu_check_callbacks(int cpu, int user)
{
	trace_rcu_utilization("Start scheduler-tick");
	increment_cpu_stall_ticks();
	if (user || rcu_is_cpu_rrupt_from_idle()) {

		/*
		 * Get here if this CPU took its interrupt from user
		 * mode or from the idle loop, and if this is not a
		 * nested interrupt.  In this case, the CPU is in
		 * a quiescent state, so note it.
		 *
		 * No memory barrier is required here because both
		 * rcu_sched_qs() and rcu_bh_qs() reference only CPU-local
		 * variables that other CPUs neither access nor modify,
		 * at least not while the corresponding CPU is online.
		 */

		rcu_sched_qs(cpu);
		rcu_bh_qs(cpu);

	} else if (!in_softirq()) {

		/*
		 * Get here if this CPU did not take its interrupt from
		 * softirq, in other words, if it is not interrupting
		 * a rcu_bh read-side critical section.  This is an _bh
		 * critical section, so note it.
		 */

		rcu_bh_qs(cpu);
	}
	rcu_preempt_check_callbacks(cpu);
	if (rcu_pending(cpu))
		invoke_rcu_core();
	trace_rcu_utilization("End scheduler-tick");
}

/*
 * Scan the leaf rcu_node structures, processing dyntick state for any that
 * have not yet encountered a quiescent state, using the function specified.
 * Also initiate boosting for any threads blocked on the root rcu_node.
 *
 * The caller must have suppressed start of new grace periods.
 */
static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *))
{
	unsigned long bit;
	int cpu;
	unsigned long flags;
	unsigned long mask;
	struct rcu_node *rnp;

	rcu_for_each_leaf_node(rsp, rnp) {
		cond_resched();
		mask = 0;
		raw_spin_lock_irqsave(&rnp->lock, flags);
		if (!rcu_gp_in_progress(rsp)) {
			raw_spin_unlock_irqrestore(&rnp->lock, flags);
			return;
		}
		if (rnp->qsmask == 0) {
			rcu_initiate_boost(rnp, flags); /* releases rnp->lock */
			continue;
		}
		cpu = rnp->grplo;
		bit = 1;
		for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
			if ((rnp->qsmask & bit) != 0 &&
			    f(per_cpu_ptr(rsp->rda, cpu)))
				mask |= bit;
		}
		if (mask != 0) {

			/* rcu_report_qs_rnp() releases rnp->lock. */
			rcu_report_qs_rnp(mask, rsp, rnp, flags);
			continue;
		}
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
	}
	rnp = rcu_get_root(rsp);
	if (rnp->qsmask == 0) {
		raw_spin_lock_irqsave(&rnp->lock, flags);
		rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
	}
}

/*
 * Force quiescent states on reluctant CPUs, and also detect which
 * CPUs are in dyntick-idle mode.
 */
static void force_quiescent_state(struct rcu_state *rsp)
{
	unsigned long flags;
	bool ret;
	struct rcu_node *rnp;
	struct rcu_node *rnp_old = NULL;

	/* Funnel through hierarchy to reduce memory contention. */
	rnp = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode;
	for (; rnp != NULL; rnp = rnp->parent) {
		ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
		      !raw_spin_trylock(&rnp->fqslock);
		if (rnp_old != NULL)
			raw_spin_unlock(&rnp_old->fqslock);
		if (ret) {
			rsp->n_force_qs_lh++;
			return;
		}
		rnp_old = rnp;
	}
	/* rnp_old == rcu_get_root(rsp), rnp == NULL. */

	/* Reached the root of the rcu_node tree, acquire lock. */
	raw_spin_lock_irqsave(&rnp_old->lock, flags);
	raw_spin_unlock(&rnp_old->fqslock);
	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
		rsp->n_force_qs_lh++;
		raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
		return;  /* Someone beat us to it. */
	}
	rsp->gp_flags |= RCU_GP_FLAG_FQS;
	raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
	wake_up(&rsp->gp_wq);  /* Memory barrier implied by wake_up() path. */
}

/*
 * This does the RCU core processing work for the specified rcu_state
 * and rcu_data structures.  This may be called only from the CPU to
 * whom the rdp belongs.
 */
static void
__rcu_process_callbacks(struct rcu_state *rsp)
{
	unsigned long flags;
	struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);

	WARN_ON_ONCE(rdp->beenonline == 0);

	/* Update RCU state based on any recent quiescent states. */
	rcu_check_quiescent_state(rsp, rdp);

	/* Does this CPU require a not-yet-started grace period? */
	local_irq_save(flags);
	if (cpu_needs_another_gp(rsp, rdp)) {
		raw_spin_lock(&rcu_get_root(rsp)->lock); /* irqs disabled. */
		rcu_start_gp(rsp);
		raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
	} else {
		local_irq_restore(flags);
	}

	/* If there are callbacks ready, invoke them. */
	if (cpu_has_callbacks_ready_to_invoke(rdp))
		invoke_rcu_callbacks(rsp, rdp);
}

/*
 * Do RCU core processing for the current CPU.
 */
static void rcu_process_callbacks(struct softirq_action *unused)
{
	struct rcu_state *rsp;

	if (cpu_is_offline(smp_processor_id()))
		return;
	trace_rcu_utilization("Start RCU core");
	for_each_rcu_flavor(rsp)
		__rcu_process_callbacks(rsp);
	trace_rcu_utilization("End RCU core");
}

/*
 * Schedule RCU callback invocation.  If the specified type of RCU
 * does not support RCU priority boosting, just do a direct call,
 * otherwise wake up the per-CPU kernel kthread.  Note that because we
 * are running on the current CPU with interrupts disabled, the
 * rcu_cpu_kthread_task cannot disappear out from under us.
 */
static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
{
	if (unlikely(!ACCESS_ONCE(rcu_scheduler_fully_active)))
		return;
	if (likely(!rsp->boost)) {
		rcu_do_batch(rsp, rdp);
		return;
	}
	invoke_rcu_callbacks_kthread();
}

static void invoke_rcu_core(void)
{
	if (cpu_online(smp_processor_id()))
		raise_softirq(RCU_SOFTIRQ);
}

/*
 * Handle any core-RCU processing required by a call_rcu() invocation.
 */
static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
			    struct rcu_head *head, unsigned long flags)
{
	/*
	 * If called from an extended quiescent state, invoke the RCU
	 * core in order to force a re-evaluation of RCU's idleness.
	 */
	if (rcu_is_cpu_idle() && cpu_online(smp_processor_id()))
		invoke_rcu_core();

	/* If interrupts were disabled or CPU offline, don't invoke RCU core. */
	if (irqs_disabled_flags(flags) || cpu_is_offline(smp_processor_id()))
		return;

	/*
	 * Force the grace period if too many callbacks or too long waiting.
	 * Enforce hysteresis, and don't invoke force_quiescent_state()
	 * if some other CPU has recently done so.  Also, don't bother
	 * invoking force_quiescent_state() if the newly enqueued callback
	 * is the only one waiting for a grace period to complete.
	 */
	if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {

		/* Are we ignoring a completed grace period? */
		note_gp_changes(rsp, rdp);

		/* Start a new grace period if one not already started. */
		if (!rcu_gp_in_progress(rsp)) {
			struct rcu_node *rnp_root = rcu_get_root(rsp);

			raw_spin_lock(&rnp_root->lock);
			rcu_start_gp(rsp);
			raw_spin_unlock(&rnp_root->lock);
		} else {
			/* Give the grace period a kick. */
			rdp->blimit = LONG_MAX;
			if (rsp->n_force_qs == rdp->n_force_qs_snap &&
			    *rdp->nxttail[RCU_DONE_TAIL] != head)
				force_quiescent_state(rsp);
			rdp->n_force_qs_snap = rsp->n_force_qs;
			rdp->qlen_last_fqs_check = rdp->qlen;
		}
	}
}

/*
 * Helper function for call_rcu() and friends.  The cpu argument will
 * normally be -1, indicating "currently running CPU".  It may specify
 * a CPU only if that CPU is a no-CBs CPU.  Currently, only _rcu_barrier()
 * is expected to specify a CPU.
 */
static void
__call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
	   struct rcu_state *rsp, int cpu, bool lazy)
{
	unsigned long flags;
	struct rcu_data *rdp;

	WARN_ON_ONCE((unsigned long)head & 0x3); /* Misaligned rcu_head! */
	debug_rcu_head_queue(head);
	head->func = func;
	head->next = NULL;

	/*
	 * Opportunistically note grace-period endings and beginnings.
	 * Note that we might see a beginning right after we see an
	 * end, but never vice versa, since this CPU has to pass through
	 * a quiescent state betweentimes.
	 */
	local_irq_save(flags);
	rdp = this_cpu_ptr(rsp->rda);

	/* Add the callback to our list. */
	if (unlikely(rdp->nxttail[RCU_NEXT_TAIL] == NULL) || cpu != -1) {
		int offline;

		if (cpu != -1)
			rdp = per_cpu_ptr(rsp->rda, cpu);
		offline = !__call_rcu_nocb(rdp, head, lazy);
		WARN_ON_ONCE(offline);
		/* _call_rcu() is illegal on offline CPU; leak the callback. */
		local_irq_restore(flags);
		return;
	}
	ACCESS_ONCE(rdp->qlen)++;
	if (lazy)
		rdp->qlen_lazy++;
	else
		rcu_idle_count_callbacks_posted();
	smp_mb();  /* Count before adding callback for rcu_barrier(). */
	*rdp->nxttail[RCU_NEXT_TAIL] = head;
	rdp->nxttail[RCU_NEXT_TAIL] = &head->next;

	if (__is_kfree_rcu_offset((unsigned long)func))
		trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func,
					 rdp->qlen_lazy, rdp->qlen);
	else
		trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen);

	/* Go handle any RCU core processing required. */
	__call_rcu_core(rsp, rdp, head, flags);
	local_irq_restore(flags);
}

/*
 * Queue an RCU-sched callback for invocation after a grace period.
 */
void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
	__call_rcu(head, func, &rcu_sched_state, -1, 0);
}
EXPORT_SYMBOL_GPL(call_rcu_sched);

/*
 * Queue an RCU callback for invocation after a quicker grace period.
 */
void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
{
	__call_rcu(head, func, &rcu_bh_state, -1, 0);
}
EXPORT_SYMBOL_GPL(call_rcu_bh);

/*
 * Because a context switch is a grace period for RCU-sched and RCU-bh,
 * any blocking grace-period wait automatically implies a grace period
 * if there is only one CPU online at any point time during execution
 * of either synchronize_sched() or synchronize_rcu_bh().  It is OK to
 * occasionally incorrectly indicate that there are multiple CPUs online
 * when there was in fact only one the whole time, as this just adds
 * some overhead: RCU still operates correctly.
 */
static inline int rcu_blocking_is_gp(void)
{
	int ret;

	might_sleep();  /* Check for RCU read-side critical section. */
	preempt_disable();
	ret = num_online_cpus() <= 1;
	preempt_enable();
	return ret;
}

/**
 * synchronize_sched - wait until an rcu-sched grace period has elapsed.
 *
 * Control will return to the caller some time after a full rcu-sched
 * grace period has elapsed, in other words after all currently executing
 * rcu-sched read-side critical sections have completed.   These read-side
 * critical sections are delimited by rcu_read_lock_sched() and
 * rcu_read_unlock_sched(), and may be nested.  Note that preempt_disable(),
 * local_irq_disable(), and so on may be used in place of
 * rcu_read_lock_sched().
 *
 * This means that all preempt_disable code sequences, including NMI and
 * non-threaded hardware-interrupt handlers, in progress on entry will
 * have completed before this primitive returns.  However, this does not
 * guarantee that softirq handlers will have completed, since in some
 * kernels, these handlers can run in process context, and can block.
 *
 * Note that this guarantee implies further memory-ordering guarantees.
 * On systems with more than one CPU, when synchronize_sched() returns,
 * each CPU is guaranteed to have executed a full memory barrier since the
 * end of its last RCU-sched read-side critical section whose beginning
 * preceded the call to synchronize_sched().  In addition, each CPU having
 * an RCU read-side critical section that extends beyond the return from
 * synchronize_sched() is guaranteed to have executed a full memory barrier
 * after the beginning of synchronize_sched() and before the beginning of
 * that RCU 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_sched(), 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_sched() -- even if CPU A and CPU B are the same CPU (but
 * again only if the system has more than one CPU).
 *
 * This primitive provides the guarantees made by the (now removed)
 * synchronize_kernel() API.  In contrast, synchronize_rcu() only
 * guarantees that rcu_read_lock() sections will have completed.
 * In "classic RCU", these two guarantees happen to be one and
 * the same, but can differ in realtime RCU implementations.
 */
void synchronize_sched(void)
{
	rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) &&
			   !lock_is_held(&rcu_lock_map) &&
			   !lock_is_held(&rcu_sched_lock_map),
			   "Illegal synchronize_sched() in RCU-sched read-side critical section");
	if (rcu_blocking_is_gp())
		return;
	if (rcu_expedited)
		synchronize_sched_expedited();
	else
		wait_rcu_gp(call_rcu_sched);
}
EXPORT_SYMBOL_GPL(synchronize_sched);

/**
 * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
 *
 * Control will return to the caller some time after a full rcu_bh grace
 * period has elapsed, in other words after all currently executing rcu_bh
 * read-side critical sections have completed.  RCU read-side critical
 * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(),
 * and may be nested.
 *
 * See the description of synchronize_sched() for more detailed information
 * on memory ordering guarantees.
 */
void synchronize_rcu_bh(void)
{
	rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) &&
			   !lock_is_held(&rcu_lock_map) &&
			   !lock_is_held(&rcu_sched_lock_map),
			   "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section");
	if (rcu_blocking_is_gp())
		return;
	if (rcu_expedited)
		synchronize_rcu_bh_expedited();
	else
		wait_rcu_gp(call_rcu_bh);
}
EXPORT_SYMBOL_GPL(synchronize_rcu_bh);

static int synchronize_sched_expedited_cpu_stop(void *data)
{
	/*
	 * There must be a full memory barrier on each affected CPU
	 * between the time that try_stop_cpus() is called and the
	 * time that it returns.
	 *
	 * In the current initial implementation of cpu_stop, the
	 * above condition is already met when the control reaches
	 * this point and the following smp_mb() is not strictly
	 * necessary.  Do smp_mb() anyway for documentation and
	 * robustness against future implementation changes.
	 */
	smp_mb(); /* See above comment block. */
	return 0;
}

/**
 * synchronize_sched_expedited - Brute-force RCU-sched grace period
 *
 * Wait for an RCU-sched grace period to elapse, but use a "big hammer"
 * approach to force the grace period to end quickly.  This consumes
 * significant time on all CPUs and is unfriendly to real-time workloads,
 * so is thus not recommended for any sort of common-case code.  In fact,
 * if you are using synchronize_sched_expedited() in a loop, please
 * restructure your code to batch your updates, and then use a single
 * synchronize_sched() instead.
 *
 * Note that it is illegal to call this function while holding any lock
 * that is acquired by a CPU-hotplug notifier.  And yes, it is also illegal
 * to call this function from a CPU-hotplug notifier.  Failing to observe
 * these restriction will result in deadlock.
 *
 * This implementation can be thought of as an application of ticket
 * locking to RCU, with sync_sched_expedited_started and
 * sync_sched_expedited_done taking on the roles of the halves
 * of the ticket-lock word.  Each task atomically increments
 * sync_sched_expedited_started upon entry, snapshotting the old value,
 * then attempts to stop all the CPUs.  If this succeeds, then each
 * CPU will have executed a context switch, resulting in an RCU-sched
 * grace period.  We are then done, so we use atomic_cmpxchg() to
 * update sync_sched_expedited_done to match our snapshot -- but
 * only if someone else has not already advanced past our snapshot.
 *
 * On the other hand, if try_stop_cpus() fails, we check the value
 * of sync_sched_expedited_done.  If it has advanced past our
 * initial snapshot, then someone else must have forced a grace period
 * some time after we took our snapshot.  In this case, our work is
 * done for us, and we can simply return.  Otherwise, we try again,
 * but keep our initial snapshot for purposes of checking for someone
 * doing our work for us.
 *
 * If we fail too many times in a row, we fall back to synchronize_sched().
 */
void synchronize_sched_expedited(void)
{
	long firstsnap, s, snap;
	int trycount = 0;
	struct rcu_state *rsp = &rcu_sched_state;

	/*
	 * If we are in danger of counter wrap, just do synchronize_sched().
	 * By allowing sync_sched_expedited_started to advance no more than
	 * ULONG_MAX/8 ahead of sync_sched_expedited_done, we are ensuring
	 * that more than 3.5 billion CPUs would be required to force a
	 * counter wrap on a 32-bit system.  Quite a few more CPUs would of
	 * course be required on a 64-bit system.
	 */
	if (ULONG_CMP_GE((ulong)atomic_long_read(&rsp->expedited_start),
			 (ulong)atomic_long_read(&rsp->expedited_done) +
			 ULONG_MAX / 8)) {
		synchronize_sched();
		atomic_long_inc(&rsp->expedited_wrap);
		return;
	}

	/*
	 * Take a ticket.  Note that atomic_inc_return() implies a
	 * full memory barrier.
	 */
	snap = atomic_long_inc_return(&rsp->expedited_start);
	firstsnap = snap;
	get_online_cpus();
	WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id()));

	/*
	 * Each pass through the following loop attempts to force a
	 * context switch on each CPU.
	 */
	while (try_stop_cpus(cpu_online_mask,
			     synchronize_sched_expedited_cpu_stop,
			     NULL) == -EAGAIN) {
		put_online_cpus();
		atomic_long_inc(&rsp->expedited_tryfail);

		/* Check to see if someone else did our work for us. */
		s = atomic_long_read(&rsp->expedited_done);
		if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) {
			/* ensure test happens before caller kfree */
			smp_mb__before_atomic_inc(); /* ^^^ */
			atomic_long_inc(&rsp->expedited_workdone1);
			return;
		}

		/* No joy, try again later.  Or just synchronize_sched(). */
		if (trycount++ < 10) {
			udelay(trycount * num_online_cpus());
		} else {
			wait_rcu_gp(call_rcu_sched);
			atomic_long_inc(&rsp->expedited_normal);
			return;
		}

		/* Recheck to see if someone else did our work for us. */
		s = atomic_long_read(&rsp->expedited_done);
		if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) {
			/* ensure test happens before caller kfree */
			smp_mb__before_atomic_inc(); /* ^^^ */
			atomic_long_inc(&rsp->expedited_workdone2);
			return;
		}

		/*
		 * Refetching sync_sched_expedited_started allows later
		 * callers to piggyback on our grace period.  We retry
		 * after they started, so our grace period works for them,
		 * and they started after our first try, so their grace
		 * period works for us.
		 */
		get_online_cpus();
		snap = atomic_long_read(&rsp->expedited_start);
		smp_mb(); /* ensure read is before try_stop_cpus(). */
	}
	atomic_long_inc(&rsp->expedited_stoppedcpus);

	/*
	 * Everyone up to our most recent fetch is covered by our grace
	 * period.  Update the counter, but only if our work is still
	 * relevant -- which it won't be if someone who started later
	 * than we did already did their update.
	 */
	do {
		atomic_long_inc(&rsp->expedited_done_tries);
		s = atomic_long_read(&rsp->expedited_done);
		if (ULONG_CMP_GE((ulong)s, (ulong)snap)) {
			/* ensure test happens before caller kfree */
			smp_mb__before_atomic_inc(); /* ^^^ */
			atomic_long_inc(&rsp->expedited_done_lost);
			break;
		}
	} while (atomic_long_cmpxchg(&rsp->expedited_done, s, snap) != s);
	atomic_long_inc(&rsp->expedited_done_exit);

	put_online_cpus();
}
EXPORT_SYMBOL_GPL(synchronize_sched_expedited);

/*
 * Check to see if there is any immediate RCU-related work to be done
 * by the current CPU, for the specified type of RCU, returning 1 if so.
 * The checks are in order of increasing expense: checks that can be
 * carried out against CPU-local state are performed first.  However,
 * we must check for CPU stalls first, else we might not get a chance.
 */
static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
{
	struct rcu_node *rnp = rdp->mynode;

	rdp->n_rcu_pending++;

	/* Check for CPU stalls, if enabled. */
	check_cpu_stall(rsp, rdp);

	/* Is the RCU core waiting for a quiescent state from this CPU? */
	if (rcu_scheduler_fully_active &&
	    rdp->qs_pending && !rdp->passed_quiesce) {
		rdp->n_rp_qs_pending++;
	} else if (rdp->qs_pending && rdp->passed_quiesce) {
		rdp->n_rp_report_qs++;
		return 1;
	}

	/* Does this CPU have callbacks ready to invoke? */
	if (cpu_has_callbacks_ready_to_invoke(rdp)) {
		rdp->n_rp_cb_ready++;
		return 1;
	}

	/* Has RCU gone idle with this CPU needing another grace period? */
	if (cpu_needs_another_gp(rsp, rdp)) {
		rdp->n_rp_cpu_needs_gp++;
		return 1;
	}

	/* Has another RCU grace period completed?  */
	if (ACCESS_ONCE(rnp->completed) != rdp->completed) { /* outside lock */
		rdp->n_rp_gp_completed++;
		return 1;
	}

	/* Has a new RCU grace period started? */
	if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum) { /* outside lock */
		rdp->n_rp_gp_started++;
		return 1;
	}

	/* nothing to do */
	rdp->n_rp_need_nothing++;
	return 0;
}

/*
 * Check to see if there is any immediate RCU-related work to be done
 * by the current CPU, returning 1 if so.  This function is part of the
 * RCU implementation; it is -not- an exported member of the RCU API.
 */
static int rcu_pending(int cpu)
{
	struct rcu_state *rsp;

	for_each_rcu_flavor(rsp)
		if (__rcu_pending(rsp, per_cpu_ptr(rsp->rda, cpu)))
			return 1;
	return 0;
}

/*
 * Return true if the specified CPU has any callback.  If all_lazy is
 * non-NULL, store an indication of whether all callbacks are lazy.
 * (If there are no callbacks, all of them are deemed to be lazy.)
 */
static int rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
{
	bool al = true;
	bool hc = false;
	struct rcu_data *rdp;
	struct rcu_state *rsp;

	for_each_rcu_flavor(rsp) {
		rdp = per_cpu_ptr(rsp->rda, cpu);
		if (rdp->qlen != rdp->qlen_lazy)
			al = false;
		if (rdp->nxtlist)
			hc = true;
	}
	if (all_lazy)
		*all_lazy = al;
	return hc;
}

/*
 * Helper function for _rcu_barrier() tracing.  If tracing is disabled,
 * the compiler is expected to optimize this away.
 */
static void _rcu_barrier_trace(struct rcu_state *rsp, char *s,
			       int cpu, unsigned long done)
{
	trace_rcu_barrier(rsp->name, s, cpu,
			  atomic_read(&rsp->barrier_cpu_count), done);
}

/*
 * RCU callback function for _rcu_barrier().  If we are last, wake
 * up the task executing _rcu_barrier().
 */
static void rcu_barrier_callback(struct rcu_head *rhp)
{
	struct rcu_data *rdp = container_of(rhp, struct rcu_data, barrier_head);
	struct rcu_state *rsp = rdp->rsp;

	if (atomic_dec_and_test(&rsp->barrier_cpu_count)) {
		_rcu_barrier_trace(rsp, "LastCB", -1, rsp->n_barrier_done);
		complete(&rsp->barrier_completion);
	} else {
		_rcu_barrier_trace(rsp, "CB", -1, rsp->n_barrier_done);
	}
}

/*
 * Called with preemption disabled, and from cross-cpu IRQ context.
 */
static void rcu_barrier_func(void *type)
{
	struct rcu_state *rsp = type;
	struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);

	_rcu_barrier_trace(rsp, "IRQ", -1, rsp->n_barrier_done);
	atomic_inc(&rsp->barrier_cpu_count);
	rsp->call(&rdp->barrier_head, rcu_barrier_callback);
}

/*
 * Orchestrate the specified type of RCU barrier, waiting for all
 * RCU callbacks of the specified type to complete.
 */
static void _rcu_barrier(struct rcu_state *rsp)
{
	int cpu;
	struct rcu_data *rdp;
	unsigned long snap = ACCESS_ONCE(rsp->n_barrier_done);
	unsigned long snap_done;

	_rcu_barrier_trace(rsp, "Begin", -1, snap);

	/* Take mutex to serialize concurrent rcu_barrier() requests. */
	mutex_lock(&rsp->barrier_mutex);

	/*
	 * Ensure that all prior references, including to ->n_barrier_done,
	 * are ordered before the _rcu_barrier() machinery.
	 */
	smp_mb();  /* See above block comment. */

	/*
	 * Recheck ->n_barrier_done to see if others did our work for us.
	 * This means checking ->n_barrier_done for an even-to-odd-to-even
	 * transition.  The "if" expression below therefore rounds the old
	 * value up to the next even number and adds two before comparing.
	 */
	snap_done = ACCESS_ONCE(rsp->n_barrier_done);
	_rcu_barrier_trace(rsp, "Check", -1, snap_done);
	if (ULONG_CMP_GE(snap_done, ((snap + 1) & ~0x1) + 2)) {
		_rcu_barrier_trace(rsp, "EarlyExit", -1, snap_done);
		smp_mb(); /* caller's subsequent code after above check. */
		mutex_unlock(&rsp->barrier_mutex);
		return;
	}

	/*
	 * Increment ->n_barrier_done to avoid duplicate work.  Use
	 * ACCESS_ONCE() to prevent the compiler from speculating
	 * the increment to precede the early-exit check.
	 */
	ACCESS_ONCE(rsp->n_barrier_done)++;
	WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1);
	_rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done);
	smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */

	/*
	 * Initialize the count to one rather than to zero in order to
	 * avoid a too-soon return to zero in case of a short grace period
	 * (or preemption of this task).  Exclude CPU-hotplug operations
	 * to ensure that no offline CPU has callbacks queued.
	 */
	init_completion(&rsp->barrier_completion);
	atomic_set(&rsp->barrier_cpu_count, 1);
	get_online_cpus();

	/*
	 * Force each CPU with callbacks to register a new callback.
	 * When that callback is invoked, we will know that all of the
	 * corresponding CPU's preceding callbacks have been invoked.
	 */
	for_each_possible_cpu(cpu) {
		if (!cpu_online(cpu) && !rcu_is_nocb_cpu(cpu))
			continue;
		rdp = per_cpu_ptr(rsp->rda, cpu);
		if (rcu_is_nocb_cpu(cpu)) {
			_rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
					   rsp->n_barrier_done);
			atomic_inc(&rsp->barrier_cpu_count);
			__call_rcu(&rdp->barrier_head, rcu_barrier_callback,
				   rsp, cpu, 0);
		} else if (ACCESS_ONCE(rdp->qlen)) {
			_rcu_barrier_trace(rsp, "OnlineQ", cpu,
					   rsp->n_barrier_done);
			smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
		} else {
			_rcu_barrier_trace(rsp, "OnlineNQ", cpu,
					   rsp->n_barrier_done);
		}
	}
	put_online_cpus();

	/*
	 * Now that we have an rcu_barrier_callback() callback on each
	 * CPU, and thus each counted, remove the initial count.
	 */
	if (atomic_dec_and_test(&rsp->barrier_cpu_count))
		complete(&rsp->barrier_completion);

	/* Increment ->n_barrier_done to prevent duplicate work. */
	smp_mb(); /* Keep increment after above mechanism. */
	ACCESS_ONCE(rsp->n_barrier_done)++;
	WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0);
	_rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done);
	smp_mb(); /* Keep increment before caller's subsequent code. */

	/* Wait for all rcu_barrier_callback() callbacks to be invoked. */
	wait_for_completion(&rsp->barrier_completion);

	/* Other rcu_barrier() invocations can now safely proceed. */
	mutex_unlock(&rsp->barrier_mutex);
}

/**
 * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
 */
void rcu_barrier_bh(void)
{
	_rcu_barrier(&rcu_bh_state);
}
EXPORT_SYMBOL_GPL(rcu_barrier_bh);

/**
 * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
 */
void rcu_barrier_sched(void)
{
	_rcu_barrier(&rcu_sched_state);
}
EXPORT_SYMBOL_GPL(rcu_barrier_sched);

/*
 * Do boot-time initialization of a CPU's per-CPU RCU data.
 */
static void __init
rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
{
	unsigned long flags;
	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
	struct rcu_node *rnp = rcu_get_root(rsp);

	/* Set up local state, ensuring consistent view of global state. */
	raw_spin_lock_irqsave(&rnp->lock, flags);
	rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo);
	init_callback_list(rdp);
	rdp->qlen_lazy = 0;
	ACCESS_ONCE(rdp->qlen) = 0;
	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE);
	WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
	rdp->cpu = cpu;
	rdp->rsp = rsp;
	rcu_boot_init_nocb_percpu_data(rdp);
	raw_spin_unlock_irqrestore(&rnp->lock, flags);
}

/*
 * Initialize a CPU's per-CPU RCU data.  Note that only one online or
 * offline event can be happening at a given time.  Note also that we
 * can accept some slop in the rsp->completed access due to the fact
 * that this CPU cannot possibly have any RCU callbacks in flight yet.
 */
static void
rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
{
	unsigned long flags;
	unsigned long mask;
	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
	struct rcu_node *rnp = rcu_get_root(rsp);

	/* Exclude new grace periods. */
	mutex_lock(&rsp->onoff_mutex);

	/* Set up local state, ensuring consistent view of global state. */
	raw_spin_lock_irqsave(&rnp->lock, flags);
	rdp->beenonline = 1;	 /* We have now been online. */
	rdp->preemptible = preemptible;
	rdp->qlen_last_fqs_check = 0;
	rdp->n_force_qs_snap = rsp->n_force_qs;
	rdp->blimit = blimit;
	init_callback_list(rdp);  /* Re-enable callbacks on this CPU. */
	rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
	atomic_set(&rdp->dynticks->dynticks,
		   (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
	raw_spin_unlock(&rnp->lock);		/* irqs remain disabled. */

	/* Add CPU to rcu_node bitmasks. */
	rnp = rdp->mynode;
	mask = rdp->grpmask;
	do {
		/* Exclude any attempts to start a new GP on small systems. */
		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
		rnp->qsmaskinit |= mask;
		mask = rnp->grpmask;
		if (rnp == rdp->mynode) {
			/*
			 * If there is a grace period in progress, we will
			 * set up to wait for it next time we run the
			 * RCU core code.
			 */
			rdp->gpnum = rnp->completed;
			rdp->completed = rnp->completed;
			rdp->passed_quiesce = 0;
			rdp->qs_pending = 0;
			trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpuonl");
		}
		raw_spin_unlock(&rnp->lock); /* irqs already disabled. */
		rnp = rnp->parent;
	} while (rnp != NULL && !(rnp->qsmaskinit & mask));
	local_irq_restore(flags);

	mutex_unlock(&rsp->onoff_mutex);
}

static void rcu_prepare_cpu(int cpu)
{
	struct rcu_state *rsp;

	for_each_rcu_flavor(rsp)
		rcu_init_percpu_data(cpu, rsp,
				     strcmp(rsp->name, "rcu_preempt") == 0);
}

/*
 * Handle CPU online/offline notification events.
 */
static int rcu_cpu_notify(struct notifier_block *self,
				    unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;
	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
	struct rcu_node *rnp = rdp->mynode;
	struct rcu_state *rsp;

	trace_rcu_utilization("Start CPU hotplug");
	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		rcu_prepare_cpu(cpu);
		rcu_prepare_kthreads(cpu);
		break;
	case CPU_ONLINE:
	case CPU_DOWN_FAILED:
		rcu_boost_kthread_setaffinity(rnp, -1);
		break;
	case CPU_DOWN_PREPARE:
		rcu_boost_kthread_setaffinity(rnp, cpu);
		break;
	case CPU_DYING:
	case CPU_DYING_FROZEN:
		for_each_rcu_flavor(rsp)
			rcu_cleanup_dying_cpu(rsp);
		break;
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
	case CPU_UP_CANCELED:
	case CPU_UP_CANCELED_FROZEN:
		for_each_rcu_flavor(rsp)
			rcu_cleanup_dead_cpu(cpu, rsp);
		break;
	default:
		break;
	}
	trace_rcu_utilization("End CPU hotplug");
	return NOTIFY_OK;
}

/*
 * Spawn the kthread that handles this RCU flavor's grace periods.
 */
static int __init rcu_spawn_gp_kthread(void)
{
	unsigned long flags;
	struct rcu_node *rnp;
	struct rcu_state *rsp;
	struct task_struct *t;

	for_each_rcu_flavor(rsp) {
		t = kthread_run(rcu_gp_kthread, rsp, "%s", rsp->name);
		BUG_ON(IS_ERR(t));
		rnp = rcu_get_root(rsp);
		raw_spin_lock_irqsave(&rnp->lock, flags);
		rsp->gp_kthread = t;
		raw_spin_unlock_irqrestore(&rnp->lock, flags);
		rcu_spawn_nocb_kthreads(rsp);
	}
	return 0;
}
early_initcall(rcu_spawn_gp_kthread);

/*
 * This function is invoked towards the end of the scheduler's initialization
 * process.  Before this is called, the idle task might contain
 * RCU read-side critical sections (during which time, this idle
 * task is booting the system).  After this function is called, the
 * idle tasks are prohibited from containing RCU read-side critical
 * sections.  This function also enables RCU lockdep checking.
 */
void rcu_scheduler_starting(void)
{
	WARN_ON(num_online_cpus() != 1);
	WARN_ON(nr_context_switches() > 0);
	rcu_scheduler_active = 1;
}

/*
 * Compute the per-level fanout, either using the exact fanout specified
 * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT.
 */
#ifdef CONFIG_RCU_FANOUT_EXACT
static void __init rcu_init_levelspread(struct rcu_state *rsp)
{
	int i;

	for (i = rcu_num_lvls - 1; i > 0; i--)
		rsp->levelspread[i] = CONFIG_RCU_FANOUT;
	rsp->levelspread[0] = rcu_fanout_leaf;
}
#else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
static void __init rcu_init_levelspread(struct rcu_state *rsp)
{
	int ccur;
	int cprv;
	int i;

	cprv = nr_cpu_ids;
	for (i = rcu_num_lvls - 1; i >= 0; i--) {
		ccur = rsp->levelcnt[i];
		rsp->levelspread[i] = (cprv + ccur - 1) / ccur;
		cprv = ccur;
	}
}
#endif /* #else #ifdef CONFIG_RCU_FANOUT_EXACT */

/*
 * Helper function for rcu_init() that initializes one rcu_state structure.
 */
static void __init rcu_init_one(struct rcu_state *rsp,
		struct rcu_data __percpu *rda)
{
	static char *buf[] = { "rcu_node_0",
			       "rcu_node_1",
			       "rcu_node_2",
			       "rcu_node_3" };  /* Match MAX_RCU_LVLS */
	static char *fqs[] = { "rcu_node_fqs_0",
			       "rcu_node_fqs_1",
			       "rcu_node_fqs_2",
			       "rcu_node_fqs_3" };  /* Match MAX_RCU_LVLS */
	int cpustride = 1;
	int i;
	int j;
	struct rcu_node *rnp;

	BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf));  /* Fix buf[] init! */

	/* Silence gcc 4.8 warning about array index out of range. */
	if (rcu_num_lvls > RCU_NUM_LVLS)
		panic("rcu_init_one: rcu_num_lvls overflow");

	/* Initialize the level-tracking arrays. */

	for (i = 0; i < rcu_num_lvls; i++)
		rsp->levelcnt[i] = num_rcu_lvl[i];
	for (i = 1; i < rcu_num_lvls; i++)
		rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1];
	rcu_init_levelspread(rsp);

	/* Initialize the elements themselves, starting from the leaves. */

	for (i = rcu_num_lvls - 1; i >= 0; i--) {
		cpustride *= rsp->levelspread[i];
		rnp = rsp->level[i];
		for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) {
			raw_spin_lock_init(&rnp->lock);
			lockdep_set_class_and_name(&rnp->lock,
						   &rcu_node_class[i], buf[i]);
			raw_spin_lock_init(&rnp->fqslock);
			lockdep_set_class_and_name(&rnp->fqslock,
						   &rcu_fqs_class[i], fqs[i]);
			rnp->gpnum = rsp->gpnum;
			rnp->completed = rsp->completed;
			rnp->qsmask = 0;
			rnp->qsmaskinit = 0;
			rnp->grplo = j * cpustride;
			rnp->grphi = (j + 1) * cpustride - 1;
			if (rnp->grphi >= NR_CPUS)
				rnp->grphi = NR_CPUS - 1;
			if (i == 0) {
				rnp->grpnum = 0;
				rnp->grpmask = 0;
				rnp->parent = NULL;
			} else {
				rnp->grpnum = j % rsp->levelspread[i - 1];
				rnp->grpmask = 1UL << rnp->grpnum;
				rnp->parent = rsp->level[i - 1] +
					      j / rsp->levelspread[i - 1];
			}
			rnp->level = i;
			INIT_LIST_HEAD(&rnp->blkd_tasks);
			rcu_init_one_nocb(rnp);
		}
	}

	rsp->rda = rda;
	init_waitqueue_head(&rsp->gp_wq);
	init_irq_work(&rsp->wakeup_work, rsp_wakeup);
	rnp = rsp->level[rcu_num_lvls - 1];
	for_each_possible_cpu(i) {
		while (i > rnp->grphi)
			rnp++;
		per_cpu_ptr(rsp->rda, i)->mynode = rnp;
		rcu_boot_init_percpu_data(i, rsp);
	}
	list_add(&rsp->flavors, &rcu_struct_flavors);
}

/*
 * Compute the rcu_node tree geometry from kernel parameters.  This cannot
 * replace the definitions in rcutree.h because those are needed to size
 * the ->node array in the rcu_state structure.
 */
static void __init rcu_init_geometry(void)
{
	ulong d;
	int i;
	int j;
	int n = nr_cpu_ids;
	int rcu_capacity[MAX_RCU_LVLS + 1];

	/*
	 * Initialize any unspecified boot parameters.
	 * The default values of jiffies_till_first_fqs and
	 * jiffies_till_next_fqs are set to the RCU_JIFFIES_TILL_FORCE_QS
	 * value, which is a function of HZ, then adding one for each
	 * RCU_JIFFIES_FQS_DIV CPUs that might be on the system.
	 */
	d = RCU_JIFFIES_TILL_FORCE_QS + nr_cpu_ids / RCU_JIFFIES_FQS_DIV;
	if (jiffies_till_first_fqs == ULONG_MAX)
		jiffies_till_first_fqs = d;
	if (jiffies_till_next_fqs == ULONG_MAX)
		jiffies_till_next_fqs = d;

	/* If the compile-time values are accurate, just leave. */
	if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
	    nr_cpu_ids == NR_CPUS)
		return;

	/*
	 * Compute number of nodes that can be handled an rcu_node tree
	 * with the given number of levels.  Setting rcu_capacity[0] makes
	 * some of the arithmetic easier.
	 */
	rcu_capacity[0] = 1;
	rcu_capacity[1] = rcu_fanout_leaf;
	for (i = 2; i <= MAX_RCU_LVLS; i++)
		rcu_capacity[i] = rcu_capacity[i - 1] * CONFIG_RCU_FANOUT;

	/*
	 * The boot-time rcu_fanout_leaf parameter is only permitted
	 * to increase the leaf-level fanout, not decrease it.  Of course,
	 * the leaf-level fanout cannot exceed the number of bits in
	 * the rcu_node masks.  Finally, the tree must be able to accommodate
	 * the configured number of CPUs.  Complain and fall back to the
	 * compile-time values if these limits are exceeded.
	 */
	if (rcu_fanout_leaf < CONFIG_RCU_FANOUT_LEAF ||
	    rcu_fanout_leaf > sizeof(unsigned long) * 8 ||
	    n > rcu_capacity[MAX_RCU_LVLS]) {
		WARN_ON(1);
		return;
	}

	/* Calculate the number of rcu_nodes at each level of the tree. */
	for (i = 1; i <= MAX_RCU_LVLS; i++)
		if (n <= rcu_capacity[i]) {
			for (j = 0; j <= i; j++)
				num_rcu_lvl[j] =
					DIV_ROUND_UP(n, rcu_capacity[i - j]);
			rcu_num_lvls = i;
			for (j = i + 1; j <= MAX_RCU_LVLS; j++)
				num_rcu_lvl[j] = 0;
			break;
		}

	/* Calculate the total number of rcu_node structures. */
	rcu_num_nodes = 0;
	for (i = 0; i <= MAX_RCU_LVLS; i++)
		rcu_num_nodes += num_rcu_lvl[i];
	rcu_num_nodes -= n;
}

void __init rcu_init(void)
{
	int cpu;

	rcu_bootup_announce();
	rcu_init_geometry();
	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
	__rcu_init_preempt();
	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);

	/*
	 * We don't need protection against CPU-hotplug here because
	 * this is called early in boot, before either interrupts
	 * or the scheduler are operational.
	 */
	cpu_notifier(rcu_cpu_notify, 0);
	for_each_online_cpu(cpu)
		rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
}

#include "rcutree_plugin.h"
OpenPOWER on IntegriCloud