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
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
|
// SPDX-License-Identifier: GPL-2.0+
/*
* Read-Copy Update mechanism for mutual exclusion (tree-based version)
*
* Copyright IBM Corporation, 2008
*
* Authors: Dipankar Sarma <dipankar@in.ibm.com>
* Manfred Spraul <manfred@colorfullife.com>
* Paul E. McKenney <paulmck@linux.ibm.com>
*
* Based on the original work by Paul McKenney <paulmck@linux.ibm.com>
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU
*/
#define pr_fmt(fmt) "rcu: " fmt
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/rcupdate_wait.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <linux/sched/debug.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/panic.h>
#include <linux/panic_notifier.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 <uapi/linux/sched/types.h>
#include <linux/prefetch.h>
#include <linux/delay.h>
#include <linux/random.h>
#include <linux/trace_events.h>
#include <linux/suspend.h>
#include <linux/ftrace.h>
#include <linux/tick.h>
#include <linux/sysrq.h>
#include <linux/kprobes.h>
#include <linux/gfp.h>
#include <linux/oom.h>
#include <linux/smpboot.h>
#include <linux/jiffies.h>
#include <linux/slab.h>
#include <linux/sched/isolation.h>
#include <linux/sched/clock.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/kasan.h>
#include "../time/tick-internal.h"
#include "tree.h"
#include "rcu.h"
#ifdef MODULE_PARAM_PREFIX
#undef MODULE_PARAM_PREFIX
#endif
#define MODULE_PARAM_PREFIX "rcutree."
/* Data structures. */
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
.dynticks_nesting = 1,
.dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE,
.dynticks = ATOMIC_INIT(1),
#ifdef CONFIG_RCU_NOCB_CPU
.cblist.flags = SEGCBLIST_RCU_CORE,
#endif
};
static struct rcu_state rcu_state = {
.level = { &rcu_state.node[0] },
.gp_state = RCU_GP_IDLE,
.gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT,
.barrier_mutex = __MUTEX_INITIALIZER(rcu_state.barrier_mutex),
.name = RCU_NAME,
.abbr = RCU_ABBR,
.exp_mutex = __MUTEX_INITIALIZER(rcu_state.exp_mutex),
.exp_wake_mutex = __MUTEX_INITIALIZER(rcu_state.exp_wake_mutex),
.ofl_lock = __RAW_SPIN_LOCK_UNLOCKED(rcu_state.ofl_lock),
};
/* Dump rcu_node combining tree at boot to verify correct setup. */
static bool dump_tree;
module_param(dump_tree, bool, 0444);
/* By default, use RCU_SOFTIRQ instead of rcuc kthreads. */
static bool use_softirq = !IS_ENABLED(CONFIG_PREEMPT_RT);
#ifndef CONFIG_PREEMPT_RT
module_param(use_softirq, bool, 0444);
#endif
/* Control rcu_node-tree auto-balancing at boot time. */
static bool rcu_fanout_exact;
module_param(rcu_fanout_exact, bool, 0444);
/* Increase (but not decrease) the RCU_FANOUT_LEAF at boot time. */
static int rcu_fanout_leaf = RCU_FANOUT_LEAF;
module_param(rcu_fanout_leaf, int, 0444);
int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
/* Number of rcu_nodes at specified level. */
int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
/*
* The rcu_scheduler_active variable is initialized to the value
* RCU_SCHEDULER_INACTIVE and transitions RCU_SCHEDULER_INIT just before the
* first task is spawned. So when this variable is RCU_SCHEDULER_INACTIVE,
* RCU can assume that there is but one task, allowing RCU to (for example)
* optimize synchronize_rcu() to a simple barrier(). When this variable
* is RCU_SCHEDULER_INIT, 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. Finally, it
* transitions from RCU_SCHEDULER_INIT to RCU_SCHEDULER_RUNNING after RCU
* is fully initialized, including all of its kthreads having been spawned.
*/
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;
static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
unsigned long gps, unsigned long flags);
static void rcu_init_new_rnp(struct rcu_node *rnp_leaf);
static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf);
static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
static void invoke_rcu_core(void);
static void rcu_report_exp_rdp(struct rcu_data *rdp);
static void sync_sched_exp_online_cleanup(int cpu);
static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp);
static bool rcu_rdp_is_offloaded(struct rcu_data *rdp);
/* rcuc/rcub kthread realtime priority */
static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
module_param(kthread_prio, int, 0444);
/* Delay in jiffies for grace-period initialization delays, debug only. */
static int gp_preinit_delay;
module_param(gp_preinit_delay, int, 0444);
static int gp_init_delay;
module_param(gp_init_delay, int, 0444);
static int gp_cleanup_delay;
module_param(gp_cleanup_delay, int, 0444);
// Add delay to rcu_read_unlock() for strict grace periods.
static int rcu_unlock_delay;
#ifdef CONFIG_RCU_STRICT_GRACE_PERIOD
module_param(rcu_unlock_delay, int, 0444);
#endif
/*
* This rcu parameter is runtime-read-only. It reflects
* a minimum allowed number of objects which can be cached
* per-CPU. Object size is equal to one page. This value
* can be changed at boot time.
*/
static int rcu_min_cached_objs = 5;
module_param(rcu_min_cached_objs, int, 0444);
// A page shrinker can ask for pages to be freed to make them
// available for other parts of the system. This usually happens
// under low memory conditions, and in that case we should also
// defer page-cache filling for a short time period.
//
// The default value is 5 seconds, which is long enough to reduce
// interference with the shrinker while it asks other systems to
// drain their caches.
static int rcu_delay_page_cache_fill_msec = 5000;
module_param(rcu_delay_page_cache_fill_msec, int, 0444);
/* Retrieve RCU kthreads priority for rcutorture */
int rcu_get_gp_kthreads_prio(void)
{
return kthread_prio;
}
EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio);
/*
* Number of grace periods between delays, normalized by the duration of
* the delay. The longer the delay, the more the grace periods between
* each delay. The reason for this normalization is that it means that,
* for non-zero delays, the overall slowdown of grace periods is constant
* regardless of the duration of the delay. This arrangement balances
* the need for long delays to increase some race probabilities with the
* need for fast grace periods to increase other race probabilities.
*/
#define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays for debugging. */
/*
* Compute the mask of online CPUs for the specified rcu_node structure.
* This will not be stable unless the rcu_node structure's ->lock is
* held, but the bit corresponding to the current CPU will be stable
* in most contexts.
*/
static unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
{
return READ_ONCE(rnp->qsmaskinitnext);
}
/*
* Return true if an RCU grace period is in progress. The READ_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(void)
{
return rcu_seq_state(rcu_seq_current(&rcu_state.gp_seq));
}
/*
* Return the number of callbacks queued on the specified CPU.
* Handles both the nocbs and normal cases.
*/
static long rcu_get_n_cbs_cpu(int cpu)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
if (rcu_segcblist_is_enabled(&rdp->cblist))
return rcu_segcblist_n_cbs(&rdp->cblist);
return 0;
}
void rcu_softirq_qs(void)
{
rcu_qs();
rcu_preempt_deferred_qs(current);
rcu_tasks_qs(current, false);
}
/*
* Increment the current CPU's rcu_data structure's ->dynticks field
* with ordering. Return the new value.
*/
static noinline noinstr unsigned long rcu_dynticks_inc(int incby)
{
return arch_atomic_add_return(incby, this_cpu_ptr(&rcu_data.dynticks));
}
/*
* Record entry into an extended quiescent state. This is only to be
* called when not already in an extended quiescent state, that is,
* RCU is watching prior to the call to this function and is no longer
* watching upon return.
*/
static noinstr void rcu_dynticks_eqs_enter(void)
{
int seq;
/*
* CPUs seeing atomic_add_return() must see prior RCU read-side
* critical sections, and we also must force ordering with the
* next idle sojourn.
*/
rcu_dynticks_task_trace_enter(); // Before ->dynticks update!
seq = rcu_dynticks_inc(1);
// RCU is no longer watching. Better be in extended quiescent state!
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && (seq & 0x1));
}
/*
* Record exit from an extended quiescent state. This is only to be
* called from an extended quiescent state, that is, RCU is not watching
* prior to the call to this function and is watching upon return.
*/
static noinstr void rcu_dynticks_eqs_exit(void)
{
int seq;
/*
* CPUs seeing atomic_add_return() must see prior idle sojourns,
* and we also must force ordering with the next RCU read-side
* critical section.
*/
seq = rcu_dynticks_inc(1);
// RCU is now watching. Better not be in an extended quiescent state!
rcu_dynticks_task_trace_exit(); // After ->dynticks update!
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & 0x1));
}
/*
* Reset the current CPU's ->dynticks counter to indicate that the
* newly onlined CPU is no longer in an extended quiescent state.
* This will either leave the counter unchanged, or increment it
* to the next non-quiescent value.
*
* The non-atomic test/increment sequence works because the upper bits
* of the ->dynticks counter are manipulated only by the corresponding CPU,
* or when the corresponding CPU is offline.
*/
static void rcu_dynticks_eqs_online(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
if (atomic_read(&rdp->dynticks) & 0x1)
return;
rcu_dynticks_inc(1);
}
/*
* Is the current CPU in an extended quiescent state?
*
* No ordering, as we are sampling CPU-local information.
*/
static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
{
return !(arch_atomic_read(this_cpu_ptr(&rcu_data.dynticks)) & 0x1);
}
/*
* Snapshot the ->dynticks counter with full ordering so as to allow
* stable comparison of this counter with past and future snapshots.
*/
static int rcu_dynticks_snap(struct rcu_data *rdp)
{
smp_mb(); // Fundamental RCU ordering guarantee.
return atomic_read_acquire(&rdp->dynticks);
}
/*
* Return true if the snapshot returned from rcu_dynticks_snap()
* indicates that RCU is in an extended quiescent state.
*/
static bool rcu_dynticks_in_eqs(int snap)
{
return !(snap & 0x1);
}
/* Return true if the specified CPU is currently idle from an RCU viewpoint. */
bool rcu_is_idle_cpu(int cpu)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
return rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp));
}
/*
* Return true if the CPU corresponding to the specified rcu_data
* structure has spent some time in an extended quiescent state since
* rcu_dynticks_snap() returned the specified snapshot.
*/
static bool rcu_dynticks_in_eqs_since(struct rcu_data *rdp, int snap)
{
return snap != rcu_dynticks_snap(rdp);
}
/*
* Return true if the referenced integer is zero while the specified
* CPU remains within a single extended quiescent state.
*/
bool rcu_dynticks_zero_in_eqs(int cpu, int *vp)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
int snap;
// If not quiescent, force back to earlier extended quiescent state.
snap = atomic_read(&rdp->dynticks) & ~0x1;
smp_rmb(); // Order ->dynticks and *vp reads.
if (READ_ONCE(*vp))
return false; // Non-zero, so report failure;
smp_rmb(); // Order *vp read and ->dynticks re-read.
// If still in the same extended quiescent state, we are good!
return snap == atomic_read(&rdp->dynticks);
}
/*
* Let the RCU core know that this CPU has gone through the scheduler,
* which is a quiescent state. This is called when the need for a
* quiescent state is urgent, so we burn an atomic operation and full
* memory barriers to let the RCU core know about it, regardless of what
* this CPU might (or might not) do in the near future.
*
* We inform the RCU core by emulating a zero-duration dyntick-idle period.
*
* The caller must have disabled interrupts and must not be idle.
*/
notrace void rcu_momentary_dyntick_idle(void)
{
int seq;
raw_cpu_write(rcu_data.rcu_need_heavy_qs, false);
seq = rcu_dynticks_inc(2);
/* It is illegal to call this from idle state. */
WARN_ON_ONCE(!(seq & 0x1));
rcu_preempt_deferred_qs(current);
}
EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle);
/**
* rcu_is_cpu_rrupt_from_idle - see if 'interrupted' from idle
*
* If the current CPU is idle and running at a first-level (not nested)
* interrupt, or directly, from idle, return true.
*
* The caller must have at least disabled IRQs.
*/
static int rcu_is_cpu_rrupt_from_idle(void)
{
long nesting;
/*
* Usually called from the tick; but also used from smp_function_call()
* for expedited grace periods. This latter can result in running from
* the idle task, instead of an actual IPI.
*/
lockdep_assert_irqs_disabled();
/* Check for counter underflows */
RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) < 0,
"RCU dynticks_nesting counter underflow!");
RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) <= 0,
"RCU dynticks_nmi_nesting counter underflow/zero!");
/* Are we at first interrupt nesting level? */
nesting = __this_cpu_read(rcu_data.dynticks_nmi_nesting);
if (nesting > 1)
return false;
/*
* If we're not in an interrupt, we must be in the idle task!
*/
WARN_ON_ONCE(!nesting && !is_idle_task(current));
/* Does CPU appear to be idle from an RCU standpoint? */
return __this_cpu_read(rcu_data.dynticks_nesting) == 0;
}
#define DEFAULT_RCU_BLIMIT (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 1000 : 10)
// Maximum callbacks per rcu_do_batch ...
#define DEFAULT_MAX_RCU_BLIMIT 10000 // ... even during callback flood.
static long blimit = DEFAULT_RCU_BLIMIT;
#define DEFAULT_RCU_QHIMARK 10000 // If this many pending, ignore blimit.
static long qhimark = DEFAULT_RCU_QHIMARK;
#define DEFAULT_RCU_QLOMARK 100 // Once only this many pending, use blimit.
static long qlowmark = DEFAULT_RCU_QLOMARK;
#define DEFAULT_RCU_QOVLD_MULT 2
#define DEFAULT_RCU_QOVLD (DEFAULT_RCU_QOVLD_MULT * DEFAULT_RCU_QHIMARK)
static long qovld = DEFAULT_RCU_QOVLD; // If this many pending, hammer QS.
static long qovld_calc = -1; // No pre-initialization lock acquisitions!
module_param(blimit, long, 0444);
module_param(qhimark, long, 0444);
module_param(qlowmark, long, 0444);
module_param(qovld, long, 0444);
static ulong jiffies_till_first_fqs = IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 0 : ULONG_MAX;
static ulong jiffies_till_next_fqs = ULONG_MAX;
static bool rcu_kick_kthreads;
static int rcu_divisor = 7;
module_param(rcu_divisor, int, 0644);
/* Force an exit from rcu_do_batch() after 3 milliseconds. */
static long rcu_resched_ns = 3 * NSEC_PER_MSEC;
module_param(rcu_resched_ns, long, 0644);
/*
* How long the grace period must be before we start recruiting
* quiescent-state help from rcu_note_context_switch().
*/
static ulong jiffies_till_sched_qs = ULONG_MAX;
module_param(jiffies_till_sched_qs, ulong, 0444);
static ulong jiffies_to_sched_qs; /* See adjust_jiffies_till_sched_qs(). */
module_param(jiffies_to_sched_qs, ulong, 0444); /* Display only! */
/*
* Make sure that we give the grace-period kthread time to detect any
* idle CPUs before taking active measures to force quiescent states.
* However, don't go below 100 milliseconds, adjusted upwards for really
* large systems.
*/
static void adjust_jiffies_till_sched_qs(void)
{
unsigned long j;
/* If jiffies_till_sched_qs was specified, respect the request. */
if (jiffies_till_sched_qs != ULONG_MAX) {
WRITE_ONCE(jiffies_to_sched_qs, jiffies_till_sched_qs);
return;
}
/* Otherwise, set to third fqs scan, but bound below on large system. */
j = READ_ONCE(jiffies_till_first_fqs) +
2 * READ_ONCE(jiffies_till_next_fqs);
if (j < HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV)
j = HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV;
pr_info("RCU calculated value of scheduler-enlistment delay is %ld jiffies.\n", j);
WRITE_ONCE(jiffies_to_sched_qs, j);
}
static int param_set_first_fqs_jiffies(const char *val, const struct kernel_param *kp)
{
ulong j;
int ret = kstrtoul(val, 0, &j);
if (!ret) {
WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : j);
adjust_jiffies_till_sched_qs();
}
return ret;
}
static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param *kp)
{
ulong j;
int ret = kstrtoul(val, 0, &j);
if (!ret) {
WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1));
adjust_jiffies_till_sched_qs();
}
return ret;
}
static const struct kernel_param_ops first_fqs_jiffies_ops = {
.set = param_set_first_fqs_jiffies,
.get = param_get_ulong,
};
static const struct kernel_param_ops next_fqs_jiffies_ops = {
.set = param_set_next_fqs_jiffies,
.get = param_get_ulong,
};
module_param_cb(jiffies_till_first_fqs, &first_fqs_jiffies_ops, &jiffies_till_first_fqs, 0644);
module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next_fqs, 0644);
module_param(rcu_kick_kthreads, bool, 0644);
static void force_qs_rnp(int (*f)(struct rcu_data *rdp));
static int rcu_pending(int user);
/*
* Return the number of RCU GPs completed thus far for debug & stats.
*/
unsigned long rcu_get_gp_seq(void)
{
return READ_ONCE(rcu_state.gp_seq);
}
EXPORT_SYMBOL_GPL(rcu_get_gp_seq);
/*
* Return the number of RCU expedited batches completed thus far for
* debug & stats. Odd numbers mean that a batch is in progress, even
* numbers mean idle. The value returned will thus be roughly double
* the cumulative batches since boot.
*/
unsigned long rcu_exp_batches_completed(void)
{
return rcu_state.expedited_sequence;
}
EXPORT_SYMBOL_GPL(rcu_exp_batches_completed);
/*
* Return the root node of the rcu_state structure.
*/
static struct rcu_node *rcu_get_root(void)
{
return &rcu_state.node[0];
}
/*
* Send along grace-period-related data for rcutorture diagnostics.
*/
void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
unsigned long *gp_seq)
{
switch (test_type) {
case RCU_FLAVOR:
*flags = READ_ONCE(rcu_state.gp_flags);
*gp_seq = rcu_seq_current(&rcu_state.gp_seq);
break;
default:
break;
}
}
EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
/*
* Enter an RCU extended quiescent state, which can be either the
* idle loop or adaptive-tickless usermode execution.
*
* We crowbar the ->dynticks_nmi_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.
*/
static noinstr void rcu_eqs_enter(bool user)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
WARN_ON_ONCE(rdp->dynticks_nmi_nesting != DYNTICK_IRQ_NONIDLE);
WRITE_ONCE(rdp->dynticks_nmi_nesting, 0);
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
rdp->dynticks_nesting == 0);
if (rdp->dynticks_nesting != 1) {
// RCU will still be watching, so just do accounting and leave.
rdp->dynticks_nesting--;
return;
}
lockdep_assert_irqs_disabled();
instrumentation_begin();
trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
rcu_prepare_for_idle();
rcu_preempt_deferred_qs(current);
// instrumentation for the noinstr rcu_dynticks_eqs_enter()
instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
instrumentation_end();
WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */
// RCU is watching here ...
rcu_dynticks_eqs_enter();
// ... but is no longer watching here.
rcu_dynticks_task_enter();
}
/**
* 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().)
*
* If you add or remove a call to rcu_idle_enter(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_idle_enter(void)
{
lockdep_assert_irqs_disabled();
rcu_eqs_enter(false);
}
EXPORT_SYMBOL_GPL(rcu_idle_enter);
#ifdef CONFIG_NO_HZ_FULL
#if !defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)
/*
* An empty function that will trigger a reschedule on
* IRQ tail once IRQs get re-enabled on userspace/guest resume.
*/
static void late_wakeup_func(struct irq_work *work)
{
}
static DEFINE_PER_CPU(struct irq_work, late_wakeup_work) =
IRQ_WORK_INIT(late_wakeup_func);
/*
* If either:
*
* 1) the task is about to enter in guest mode and $ARCH doesn't support KVM generic work
* 2) the task is about to enter in user mode and $ARCH doesn't support generic entry.
*
* In these cases the late RCU wake ups aren't supported in the resched loops and our
* last resort is to fire a local irq_work that will trigger a reschedule once IRQs
* get re-enabled again.
*/
noinstr static void rcu_irq_work_resched(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
if (IS_ENABLED(CONFIG_GENERIC_ENTRY) && !(current->flags & PF_VCPU))
return;
if (IS_ENABLED(CONFIG_KVM_XFER_TO_GUEST_WORK) && (current->flags & PF_VCPU))
return;
instrumentation_begin();
if (do_nocb_deferred_wakeup(rdp) && need_resched()) {
irq_work_queue(this_cpu_ptr(&late_wakeup_work));
}
instrumentation_end();
}
#else
static inline void rcu_irq_work_resched(void) { }
#endif
/**
* 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.
*
* If you add or remove a call to rcu_user_enter(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
noinstr void rcu_user_enter(void)
{
lockdep_assert_irqs_disabled();
/*
* Other than generic entry implementation, we may be past the last
* rescheduling opportunity in the entry code. Trigger a self IPI
* that will fire and reschedule once we resume in user/guest mode.
*/
rcu_irq_work_resched();
rcu_eqs_enter(true);
}
#endif /* CONFIG_NO_HZ_FULL */
/**
* rcu_nmi_exit - inform RCU of exit from NMI context
*
* If we are returning from the outermost NMI handler that interrupted an
* RCU-idle period, update rdp->dynticks and rdp->dynticks_nmi_nesting
* to let the RCU grace-period handling know that the CPU is back to
* being RCU-idle.
*
* If you add or remove a call to rcu_nmi_exit(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
*/
noinstr void rcu_nmi_exit(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
instrumentation_begin();
/*
* Check for ->dynticks_nmi_nesting underflow and bad ->dynticks.
* (We are exiting an NMI handler, so RCU better be paying attention
* to us!)
*/
WARN_ON_ONCE(rdp->dynticks_nmi_nesting <= 0);
WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs());
/*
* If the nesting level is not 1, the CPU wasn't RCU-idle, so
* leave it in non-RCU-idle state.
*/
if (rdp->dynticks_nmi_nesting != 1) {
trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2,
atomic_read(&rdp->dynticks));
WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */
rdp->dynticks_nmi_nesting - 2);
instrumentation_end();
return;
}
/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
if (!in_nmi())
rcu_prepare_for_idle();
// instrumentation for the noinstr rcu_dynticks_eqs_enter()
instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
instrumentation_end();
// RCU is watching here ...
rcu_dynticks_eqs_enter();
// ... but is no longer watching here.
if (!in_nmi())
rcu_dynticks_task_enter();
}
/**
* 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. The caller must have disabled interrupts.
*
* 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's idle loop 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.
*
* If you add or remove a call to rcu_irq_exit(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
void noinstr rcu_irq_exit(void)
{
lockdep_assert_irqs_disabled();
rcu_nmi_exit();
}
#ifdef CONFIG_PROVE_RCU
/**
* rcu_irq_exit_check_preempt - Validate that scheduling is possible
*/
void rcu_irq_exit_check_preempt(void)
{
lockdep_assert_irqs_disabled();
RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) <= 0,
"RCU dynticks_nesting counter underflow/zero!");
RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) !=
DYNTICK_IRQ_NONIDLE,
"Bad RCU dynticks_nmi_nesting counter\n");
RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
"RCU in extended quiescent state!");
}
#endif /* #ifdef CONFIG_PROVE_RCU */
/*
* Wrapper for rcu_irq_exit() where interrupts are enabled.
*
* If you add or remove a call to rcu_irq_exit_irqson(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_irq_exit_irqson(void)
{
unsigned long flags;
local_irq_save(flags);
rcu_irq_exit();
local_irq_restore(flags);
}
/*
* Exit an RCU extended quiescent state, which can be either the
* idle loop or adaptive-tickless usermode execution.
*
* We crowbar the ->dynticks_nmi_nesting field to DYNTICK_IRQ_NONIDLE 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.
*/
static void noinstr rcu_eqs_exit(bool user)
{
struct rcu_data *rdp;
long oldval;
lockdep_assert_irqs_disabled();
rdp = this_cpu_ptr(&rcu_data);
oldval = rdp->dynticks_nesting;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
if (oldval) {
// RCU was already watching, so just do accounting and leave.
rdp->dynticks_nesting++;
return;
}
rcu_dynticks_task_exit();
// RCU is not watching here ...
rcu_dynticks_eqs_exit();
// ... but is watching here.
instrumentation_begin();
// instrumentation for the noinstr rcu_dynticks_eqs_exit()
instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
rcu_cleanup_after_idle();
trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
WRITE_ONCE(rdp->dynticks_nesting, 1);
WARN_ON_ONCE(rdp->dynticks_nmi_nesting);
WRITE_ONCE(rdp->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE);
instrumentation_end();
}
/**
* 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.
*
* If you add or remove a call to rcu_idle_exit(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
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_NO_HZ_FULL
/**
* 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.
*
* If you add or remove a call to rcu_user_exit(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
void noinstr rcu_user_exit(void)
{
rcu_eqs_exit(true);
}
/**
* __rcu_irq_enter_check_tick - Enable scheduler tick on CPU if RCU needs it.
*
* The scheduler tick is not normally enabled when CPUs enter the kernel
* from nohz_full userspace execution. After all, nohz_full userspace
* execution is an RCU quiescent state and the time executing in the kernel
* is quite short. Except of course when it isn't. And it is not hard to
* cause a large system to spend tens of seconds or even minutes looping
* in the kernel, which can cause a number of problems, include RCU CPU
* stall warnings.
*
* Therefore, if a nohz_full CPU fails to report a quiescent state
* in a timely manner, the RCU grace-period kthread sets that CPU's
* ->rcu_urgent_qs flag with the expectation that the next interrupt or
* exception will invoke this function, which will turn on the scheduler
* tick, which will enable RCU to detect that CPU's quiescent states,
* for example, due to cond_resched() calls in CONFIG_PREEMPT=n kernels.
* The tick will be disabled once a quiescent state is reported for
* this CPU.
*
* Of course, in carefully tuned systems, there might never be an
* interrupt or exception. In that case, the RCU grace-period kthread
* will eventually cause one to happen. However, in less carefully
* controlled environments, this function allows RCU to get what it
* needs without creating otherwise useless interruptions.
*/
void __rcu_irq_enter_check_tick(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
// If we're here from NMI there's nothing to do.
if (in_nmi())
return;
RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
"Illegal rcu_irq_enter_check_tick() from extended quiescent state");
if (!tick_nohz_full_cpu(rdp->cpu) ||
!READ_ONCE(rdp->rcu_urgent_qs) ||
READ_ONCE(rdp->rcu_forced_tick)) {
// RCU doesn't need nohz_full help from this CPU, or it is
// already getting that help.
return;
}
// We get here only when not in an extended quiescent state and
// from interrupts (as opposed to NMIs). Therefore, (1) RCU is
// already watching and (2) The fact that we are in an interrupt
// handler and that the rcu_node lock is an irq-disabled lock
// prevents self-deadlock. So we can safely recheck under the lock.
// Note that the nohz_full state currently cannot change.
raw_spin_lock_rcu_node(rdp->mynode);
if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) {
// A nohz_full CPU is in the kernel and RCU needs a
// quiescent state. Turn on the tick!
WRITE_ONCE(rdp->rcu_forced_tick, true);
tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
}
raw_spin_unlock_rcu_node(rdp->mynode);
}
#endif /* CONFIG_NO_HZ_FULL */
/**
* rcu_nmi_enter - inform RCU of entry to NMI context
*
* If the CPU was idle from RCU's viewpoint, update rdp->dynticks and
* rdp->dynticks_nmi_nesting to let the RCU grace-period handling know
* that the CPU is active. This implementation permits nested NMIs, as
* long as the nesting level does not overflow an int. (You will probably
* run out of stack space first.)
*
* If you add or remove a call to rcu_nmi_enter(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
*/
noinstr void rcu_nmi_enter(void)
{
long incby = 2;
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
/* Complain about underflow. */
WARN_ON_ONCE(rdp->dynticks_nmi_nesting < 0);
/*
* If idle from RCU viewpoint, atomically increment ->dynticks
* to mark non-idle and increment ->dynticks_nmi_nesting by one.
* Otherwise, increment ->dynticks_nmi_nesting by two. This means
* if ->dynticks_nmi_nesting is equal to one, we are guaranteed
* to be in the outermost NMI handler that interrupted an RCU-idle
* period (observation due to Andy Lutomirski).
*/
if (rcu_dynticks_curr_cpu_in_eqs()) {
if (!in_nmi())
rcu_dynticks_task_exit();
// RCU is not watching here ...
rcu_dynticks_eqs_exit();
// ... but is watching here.
if (!in_nmi()) {
instrumentation_begin();
rcu_cleanup_after_idle();
instrumentation_end();
}
instrumentation_begin();
// instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs()
instrument_atomic_read(&rdp->dynticks, sizeof(rdp->dynticks));
// instrumentation for the noinstr rcu_dynticks_eqs_exit()
instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
incby = 1;
} else if (!in_nmi()) {
instrumentation_begin();
rcu_irq_enter_check_tick();
} else {
instrumentation_begin();
}
trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
rdp->dynticks_nmi_nesting,
rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks));
instrumentation_end();
WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */
rdp->dynticks_nmi_nesting + incby);
barrier();
}
/**
* 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. The caller must have disabled interrupts.
*
* 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's idle loop does do upcalls to user mode (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.
*
* If you add or remove a call to rcu_irq_enter(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
noinstr void rcu_irq_enter(void)
{
lockdep_assert_irqs_disabled();
rcu_nmi_enter();
}
/*
* Wrapper for rcu_irq_enter() where interrupts are enabled.
*
* If you add or remove a call to rcu_irq_enter_irqson(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_irq_enter_irqson(void)
{
unsigned long flags;
local_irq_save(flags);
rcu_irq_enter();
local_irq_restore(flags);
}
/*
* If any sort of urgency was applied to the current CPU (for example,
* the scheduler-clock interrupt was enabled on a nohz_full CPU) in order
* to get to a quiescent state, disable it.
*/
static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
{
raw_lockdep_assert_held_rcu_node(rdp->mynode);
WRITE_ONCE(rdp->rcu_urgent_qs, false);
WRITE_ONCE(rdp->rcu_need_heavy_qs, false);
if (tick_nohz_full_cpu(rdp->cpu) && rdp->rcu_forced_tick) {
tick_dep_clear_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
WRITE_ONCE(rdp->rcu_forced_tick, false);
}
}
/**
* rcu_is_watching - see if RCU thinks that the current CPU is not idle
*
* Return true if RCU is watching the running CPU, which means that this
* CPU can safely enter RCU read-side critical sections. In other words,
* if the current CPU is not in its idle loop or is in an interrupt or
* NMI handler, return true.
*
* Make notrace because it can be called by the internal functions of
* ftrace, and making this notrace removes unnecessary recursion calls.
*/
notrace bool rcu_is_watching(void)
{
bool ret;
preempt_disable_notrace();
ret = !rcu_dynticks_curr_cpu_in_eqs();
preempt_enable_notrace();
return ret;
}
EXPORT_SYMBOL_GPL(rcu_is_watching);
/*
* If a holdout task is actually running, request an urgent quiescent
* state from its CPU. This is unsynchronized, so migrations can cause
* the request to go to the wrong CPU. Which is OK, all that will happen
* is that the CPU's next context switch will be a bit slower and next
* time around this task will generate another request.
*/
void rcu_request_urgent_qs_task(struct task_struct *t)
{
int cpu;
barrier();
cpu = task_cpu(t);
if (!task_curr(t))
return; /* This task is not running on that CPU. */
smp_store_release(per_cpu_ptr(&rcu_data.rcu_urgent_qs, cpu), true);
}
#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
/*
* Is the current CPU online as far as RCU is concerned?
*
* 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.
*
* Disable checking if in an NMI handler because we cannot safely
* report errors from NMI handlers anyway. In addition, it is OK to use
* RCU on an offline processor during initial boot, hence the check for
* rcu_scheduler_fully_active.
*/
bool rcu_lockdep_current_cpu_online(void)
{
struct rcu_data *rdp;
struct rcu_node *rnp;
bool ret = false;
if (in_nmi() || !rcu_scheduler_fully_active)
return true;
preempt_disable_notrace();
rdp = this_cpu_ptr(&rcu_data);
rnp = rdp->mynode;
if (rdp->grpmask & rcu_rnp_online_cpus(rnp) || READ_ONCE(rnp->ofl_seq) & 0x1)
ret = true;
preempt_enable_notrace();
return ret;
}
EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */
/*
* When trying to report a quiescent state on behalf of some other CPU,
* it is our responsibility to check for and handle potential overflow
* of the rcu_node ->gp_seq counter with respect to the rcu_data counters.
* After all, the CPU might be in deep idle state, and thus executing no
* code whatsoever.
*/
static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp)
{
raw_lockdep_assert_held_rcu_node(rnp);
if (ULONG_CMP_LT(rcu_seq_current(&rdp->gp_seq) + ULONG_MAX / 4,
rnp->gp_seq))
WRITE_ONCE(rdp->gpwrap, true);
if (ULONG_CMP_LT(rdp->rcu_iw_gp_seq + ULONG_MAX / 4, rnp->gp_seq))
rdp->rcu_iw_gp_seq = rnp->gp_seq + ULONG_MAX / 4;
}
/*
* 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 = rcu_dynticks_snap(rdp);
if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) {
trace_rcu_fqs(rcu_state.name, rdp->gp_seq, rdp->cpu, TPS("dti"));
rcu_gpnum_ovf(rdp->mynode, rdp);
return 1;
}
return 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 long jtsq;
struct rcu_node *rnp = rdp->mynode;
/*
* 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 (rcu_dynticks_in_eqs_since(rdp, rdp->dynticks_snap)) {
trace_rcu_fqs(rcu_state.name, rdp->gp_seq, rdp->cpu, TPS("dti"));
rcu_gpnum_ovf(rnp, rdp);
return 1;
}
/*
* Complain if a CPU that is considered to be offline from RCU's
* perspective has not yet reported a quiescent state. After all,
* the offline CPU should have reported a quiescent state during
* the CPU-offline process, or, failing that, by rcu_gp_init()
* if it ran concurrently with either the CPU going offline or the
* last task on a leaf rcu_node structure exiting its RCU read-side
* critical section while all CPUs corresponding to that structure
* are offline. This added warning detects bugs in any of these
* code paths.
*
* The rcu_node structure's ->lock is held here, which excludes
* the relevant portions the CPU-hotplug code, the grace-period
* initialization code, and the rcu_read_unlock() code paths.
*
* For more detail, please refer to the "Hotplug CPU" section
* of RCU's Requirements documentation.
*/
if (WARN_ON_ONCE(!(rdp->grpmask & rcu_rnp_online_cpus(rnp)))) {
bool onl;
struct rcu_node *rnp1;
pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
__func__, rnp->grplo, rnp->grphi, rnp->level,
(long)rnp->gp_seq, (long)rnp->completedqs);
for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx ->rcu_gp_init_mask %#lx\n",
__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext, rnp1->rcu_gp_init_mask);
onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n",
__func__, rdp->cpu, ".o"[onl],
(long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
(long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
return 1; /* Break things loose after complaining. */
}
/*
* A CPU running for an extended time within the kernel can
* delay RCU grace periods: (1) At age jiffies_to_sched_qs,
* set .rcu_urgent_qs, (2) At age 2*jiffies_to_sched_qs, set
* both .rcu_need_heavy_qs and .rcu_urgent_qs. Note that the
* unsynchronized assignments to the per-CPU rcu_need_heavy_qs
* variable are safe because the assignments are repeated if this
* CPU failed to pass through a quiescent state. This code
* also checks .jiffies_resched in case jiffies_to_sched_qs
* is set way high.
*/
jtsq = READ_ONCE(jiffies_to_sched_qs);
if (!READ_ONCE(rdp->rcu_need_heavy_qs) &&
(time_after(jiffies, rcu_state.gp_start + jtsq * 2) ||
time_after(jiffies, rcu_state.jiffies_resched) ||
rcu_state.cbovld)) {
WRITE_ONCE(rdp->rcu_need_heavy_qs, true);
/* Store rcu_need_heavy_qs before rcu_urgent_qs. */
smp_store_release(&rdp->rcu_urgent_qs, true);
} else if (time_after(jiffies, rcu_state.gp_start + jtsq)) {
WRITE_ONCE(rdp->rcu_urgent_qs, true);
}
/*
* NO_HZ_FULL CPUs can run in-kernel without rcu_sched_clock_irq!
* The above code handles this, but only for straight cond_resched().
* And some in-kernel loops check need_resched() before calling
* cond_resched(), which defeats the above code for CPUs that are
* running in-kernel with scheduling-clock interrupts disabled.
* So hit them over the head with the resched_cpu() hammer!
*/
if (tick_nohz_full_cpu(rdp->cpu) &&
(time_after(jiffies, READ_ONCE(rdp->last_fqs_resched) + jtsq * 3) ||
rcu_state.cbovld)) {
WRITE_ONCE(rdp->rcu_urgent_qs, true);
resched_cpu(rdp->cpu);
WRITE_ONCE(rdp->last_fqs_resched, jiffies);
}
/*
* If more than halfway to RCU CPU stall-warning time, invoke
* resched_cpu() more frequently to try to loosen things up a bit.
* Also check to see if the CPU is getting hammered with interrupts,
* but only once per grace period, just to keep the IPIs down to
* a dull roar.
*/
if (time_after(jiffies, rcu_state.jiffies_resched)) {
if (time_after(jiffies,
READ_ONCE(rdp->last_fqs_resched) + jtsq)) {
resched_cpu(rdp->cpu);
WRITE_ONCE(rdp->last_fqs_resched, jiffies);
}
if (IS_ENABLED(CONFIG_IRQ_WORK) &&
!rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq &&
(rnp->ffmask & rdp->grpmask)) {
rdp->rcu_iw_pending = true;
rdp->rcu_iw_gp_seq = rnp->gp_seq;
irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
}
}
return 0;
}
/* Trace-event wrapper function for trace_rcu_future_grace_period. */
static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
unsigned long gp_seq_req, const char *s)
{
trace_rcu_future_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
gp_seq_req, rnp->level,
rnp->grplo, rnp->grphi, s);
}
/*
* rcu_start_this_gp - Request the start of a particular grace period
* @rnp_start: The leaf node of the CPU from which to start.
* @rdp: The rcu_data corresponding to the CPU from which to start.
* @gp_seq_req: The gp_seq of the grace period to start.
*
* Start the specified grace period, as needed to handle newly arrived
* callbacks. The required future grace periods are recorded in each
* rcu_node structure's ->gp_seq_needed field. Returns true if there
* is reason to awaken the grace-period kthread.
*
* The caller must hold the specified rcu_node structure's ->lock, which
* is why the caller is responsible for waking the grace-period kthread.
*
* Returns true if the GP thread needs to be awakened else false.
*/
static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
unsigned long gp_seq_req)
{
bool ret = false;
struct rcu_node *rnp;
/*
* Use funnel locking to either acquire the root rcu_node
* structure's lock or bail out if the need for this grace period
* has already been recorded -- or if that grace period has in
* fact already started. If there is already a grace period in
* progress in a non-leaf node, no recording is needed because the
* end of the grace period will scan the leaf rcu_node structures.
* Note that rnp_start->lock must not be released.
*/
raw_lockdep_assert_held_rcu_node(rnp_start);
trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, TPS("Startleaf"));
for (rnp = rnp_start; 1; rnp = rnp->parent) {
if (rnp != rnp_start)
raw_spin_lock_rcu_node(rnp);
if (ULONG_CMP_GE(rnp->gp_seq_needed, gp_seq_req) ||
rcu_seq_started(&rnp->gp_seq, gp_seq_req) ||
(rnp != rnp_start &&
rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))) {
trace_rcu_this_gp(rnp, rdp, gp_seq_req,
TPS("Prestarted"));
goto unlock_out;
}
WRITE_ONCE(rnp->gp_seq_needed, gp_seq_req);
if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
/*
* We just marked the leaf or internal node, and a
* grace period is in progress, which means that
* rcu_gp_cleanup() will see the marking. Bail to
* reduce contention.
*/
trace_rcu_this_gp(rnp_start, rdp, gp_seq_req,
TPS("Startedleaf"));
goto unlock_out;
}
if (rnp != rnp_start && rnp->parent != NULL)
raw_spin_unlock_rcu_node(rnp);
if (!rnp->parent)
break; /* At root, and perhaps also leaf. */
}
/* If GP already in progress, just leave, otherwise start one. */
if (rcu_gp_in_progress()) {
trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedleafroot"));
goto unlock_out;
}
trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot"));
WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags | RCU_GP_FLAG_INIT);
WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
if (!READ_ONCE(rcu_state.gp_kthread)) {
trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread"));
goto unlock_out;
}
trace_rcu_grace_period(rcu_state.name, data_race(rcu_state.gp_seq), TPS("newreq"));
ret = true; /* Caller must wake GP kthread. */
unlock_out:
/* Push furthest requested GP to leaf node and rcu_data structure. */
if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) {
WRITE_ONCE(rnp_start->gp_seq_needed, rnp->gp_seq_needed);
WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed);
}
if (rnp != rnp_start)
raw_spin_unlock_rcu_node(rnp);
return ret;
}
/*
* Clean up any old requests for the just-ended grace period. Also return
* whether any additional grace periods have been requested.
*/
static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
{
bool needmore;
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed);
if (!needmore)
rnp->gp_seq_needed = rnp->gp_seq; /* Avoid counter wrap. */
trace_rcu_this_gp(rnp, rdp, rnp->gp_seq,
needmore ? TPS("CleanupMore") : TPS("Cleanup"));
return needmore;
}
/*
* Awaken the grace-period kthread. Don't do a self-awaken (unless in an
* interrupt or softirq handler, in which case we just might immediately
* sleep upon return, resulting in a grace-period hang), and don't bother
* awakening when there is nothing for the grace-period kthread to do
* (as in several CPUs raced to awaken, we lost), and finally don't try
* to awaken a kthread that has not yet been created. If all those checks
* are passed, track some debug information and awaken.
*
* So why do the self-wakeup when in an interrupt or softirq handler
* in the grace-period kthread's context? Because the kthread might have
* been interrupted just as it was going to sleep, and just after the final
* pre-sleep check of the awaken condition. In this case, a wakeup really
* is required, and is therefore supplied.
*/
static void rcu_gp_kthread_wake(void)
{
struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
if ((current == t && !in_irq() && !in_serving_softirq()) ||
!READ_ONCE(rcu_state.gp_flags) || !t)
return;
WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq));
swake_up_one(&rcu_state.gp_wq);
}
/*
* If there is room, assign a ->gp_seq number to any callbacks on this
* CPU that have not already been assigned. Also accelerate any callbacks
* that were previously assigned a ->gp_seq number that has since proven
* to be too conservative, which can happen if callbacks get assigned a
* ->gp_seq 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. Returns an flag saying that we should awaken
* the RCU grace-period kthread.
*
* The caller must hold rnp->lock with interrupts disabled.
*/
static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp)
{
unsigned long gp_seq_req;
bool ret = false;
rcu_lockdep_assert_cblist_protected(rdp);
raw_lockdep_assert_held_rcu_node(rnp);
/* If no pending (not yet ready to invoke) callbacks, nothing to do. */
if (!rcu_segcblist_pend_cbs(&rdp->cblist))
return false;
trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbPreAcc"));
/*
* Callbacks are often registered with incomplete grace-period
* information. Something about the fact that getting exact
* information requires acquiring a global lock... RCU therefore
* makes a conservative estimate of the grace period number at which
* a given callback will become ready to invoke. The following
* code checks this estimate and improves it when possible, thus
* accelerating callback invocation to an earlier grace-period
* number.
*/
gp_seq_req = rcu_seq_snap(&rcu_state.gp_seq);
if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req))
ret = rcu_start_this_gp(rnp, rdp, gp_seq_req);
/* Trace depending on how much we were able to accelerate. */
if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccWaitCB"));
else
trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccReadyCB"));
trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbPostAcc"));
return ret;
}
/*
* Similar to rcu_accelerate_cbs(), but does not require that the leaf
* rcu_node structure's ->lock be held. It consults the cached value
* of ->gp_seq_needed in the rcu_data structure, and if that indicates
* that a new grace-period request be made, invokes rcu_accelerate_cbs()
* while holding the leaf rcu_node structure's ->lock.
*/
static void rcu_accelerate_cbs_unlocked(struct rcu_node *rnp,
struct rcu_data *rdp)
{
unsigned long c;
bool needwake;
rcu_lockdep_assert_cblist_protected(rdp);
c = rcu_seq_snap(&rcu_state.gp_seq);
if (!READ_ONCE(rdp->gpwrap) && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
/* Old request still live, so mark recent callbacks. */
(void)rcu_segcblist_accelerate(&rdp->cblist, c);
return;
}
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
needwake = rcu_accelerate_cbs(rnp, rdp);
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
if (needwake)
rcu_gp_kthread_wake();
}
/*
* Move any callbacks whose grace period has completed to the
* RCU_DONE_TAIL sublist, then compact the remaining sublists and
* assign ->gp_seq 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...
* Returns true if the RCU grace-period kthread needs to be awakened.
*
* The caller must hold rnp->lock with interrupts disabled.
*/
static bool rcu_advance_cbs(struct rcu_node *rnp, struct rcu_data *rdp)
{
rcu_lockdep_assert_cblist_protected(rdp);
raw_lockdep_assert_held_rcu_node(rnp);
/* If no pending (not yet ready to invoke) callbacks, nothing to do. */
if (!rcu_segcblist_pend_cbs(&rdp->cblist))
return false;
/*
* Find all callbacks whose ->gp_seq numbers indicate that they
* are ready to invoke, and put them into the RCU_DONE_TAIL sublist.
*/
rcu_segcblist_advance(&rdp->cblist, rnp->gp_seq);
/* Classify any remaining callbacks. */
return rcu_accelerate_cbs(rnp, rdp);
}
/*
* Move and classify callbacks, but only if doing so won't require
* that the RCU grace-period kthread be awakened.
*/
static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp,
struct rcu_data *rdp)
{
rcu_lockdep_assert_cblist_protected(rdp);
if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) || !raw_spin_trylock_rcu_node(rnp))
return;
// The grace period cannot end while we hold the rcu_node lock.
if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))
WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
raw_spin_unlock_rcu_node(rnp);
}
/*
* In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels, attempt to generate a
* quiescent state. This is intended to be invoked when the CPU notices
* a new grace period.
*/
static void rcu_strict_gp_check_qs(void)
{
if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) {
rcu_read_lock();
rcu_read_unlock();
}
}
/*
* 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.
* Returns true if the grace-period kthread needs to be awakened.
*/
static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
{
bool ret = false;
bool need_qs;
const bool offloaded = rcu_rdp_is_offloaded(rdp);
raw_lockdep_assert_held_rcu_node(rnp);
if (rdp->gp_seq == rnp->gp_seq)
return false; /* Nothing to do. */
/* Handle the ends of any preceding grace periods first. */
if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) ||
unlikely(READ_ONCE(rdp->gpwrap))) {
if (!offloaded)
ret = rcu_advance_cbs(rnp, rdp); /* Advance CBs. */
rdp->core_needs_qs = false;
trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuend"));
} else {
if (!offloaded)
ret = rcu_accelerate_cbs(rnp, rdp); /* Recent CBs. */
if (rdp->core_needs_qs)
rdp->core_needs_qs = !!(rnp->qsmask & rdp->grpmask);
}
/* Now handle the beginnings of any new-to-this-CPU grace periods. */
if (rcu_seq_new_gp(rdp->gp_seq, rnp->gp_seq) ||
unlikely(READ_ONCE(rdp->gpwrap))) {
/*
* If the current grace period is waiting for this CPU,
* set up to detect a quiescent state, otherwise don't
* go looking for one.
*/
trace_rcu_grace_period(rcu_state.name, rnp->gp_seq, TPS("cpustart"));
need_qs = !!(rnp->qsmask & rdp->grpmask);
rdp->cpu_no_qs.b.norm = need_qs;
rdp->core_needs_qs = need_qs;
zero_cpu_stall_ticks(rdp);
}
rdp->gp_seq = rnp->gp_seq; /* Remember new grace-period state. */
if (ULONG_CMP_LT(rdp->gp_seq_needed, rnp->gp_seq_needed) || rdp->gpwrap)
WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed);
WRITE_ONCE(rdp->gpwrap, false);
rcu_gpnum_ovf(rnp, rdp);
return ret;
}
static void note_gp_changes(struct rcu_data *rdp)
{
unsigned long flags;
bool needwake;
struct rcu_node *rnp;
local_irq_save(flags);
rnp = rdp->mynode;
if ((rdp->gp_seq == rcu_seq_current(&rnp->gp_seq) &&
!unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
!raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */
local_irq_restore(flags);
return;
}
needwake = __note_gp_changes(rnp, rdp);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rcu_strict_gp_check_qs();
if (needwake)
rcu_gp_kthread_wake();
}
static void rcu_gp_slow(int delay)
{
if (delay > 0 &&
!(rcu_seq_ctr(rcu_state.gp_seq) %
(rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
schedule_timeout_idle(delay);
}
static unsigned long sleep_duration;
/* Allow rcutorture to stall the grace-period kthread. */
void rcu_gp_set_torture_wait(int duration)
{
if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST) && duration > 0)
WRITE_ONCE(sleep_duration, duration);
}
EXPORT_SYMBOL_GPL(rcu_gp_set_torture_wait);
/* Actually implement the aforementioned wait. */
static void rcu_gp_torture_wait(void)
{
unsigned long duration;
if (!IS_ENABLED(CONFIG_RCU_TORTURE_TEST))
return;
duration = xchg(&sleep_duration, 0UL);
if (duration > 0) {
pr_alert("%s: Waiting %lu jiffies\n", __func__, duration);
schedule_timeout_idle(duration);
pr_alert("%s: Wait complete\n", __func__);
}
}
/*
* Handler for on_each_cpu() to invoke the target CPU's RCU core
* processing.
*/
static void rcu_strict_gp_boundary(void *unused)
{
invoke_rcu_core();
}
/*
* Initialize a new grace period. Return false if no grace period required.
*/
static noinline_for_stack bool rcu_gp_init(void)
{
unsigned long firstseq;
unsigned long flags;
unsigned long oldmask;
unsigned long mask;
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
raw_spin_lock_irq_rcu_node(rnp);
if (!READ_ONCE(rcu_state.gp_flags)) {
/* Spurious wakeup, tell caller to go back to sleep. */
raw_spin_unlock_irq_rcu_node(rnp);
return false;
}
WRITE_ONCE(rcu_state.gp_flags, 0); /* Clear all flags: New GP. */
if (WARN_ON_ONCE(rcu_gp_in_progress())) {
/*
* Grace period already in progress, don't start another.
* Not supposed to be able to happen.
*/
raw_spin_unlock_irq_rcu_node(rnp);
return false;
}
/* Advance to a new grace period and initialize state. */
record_gp_stall_check_time();
/* Record GP times before starting GP, hence rcu_seq_start(). */
rcu_seq_start(&rcu_state.gp_seq);
ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("start"));
raw_spin_unlock_irq_rcu_node(rnp);
/*
* Apply per-leaf buffered online and offline operations to
* the rcu_node tree. Note that this new grace period need not
* wait for subsequent online CPUs, and that RCU hooks in the CPU
* offlining path, when combined with checks in this function,
* will handle CPUs that are currently going offline or that will
* go offline later. Please also refer to "Hotplug CPU" section
* of RCU's Requirements documentation.
*/
WRITE_ONCE(rcu_state.gp_state, RCU_GP_ONOFF);
rcu_for_each_leaf_node(rnp) {
// Wait for CPU-hotplug operations that might have
// started before this grace period did.
smp_mb(); // Pair with barriers used when updating ->ofl_seq to odd values.
firstseq = READ_ONCE(rnp->ofl_seq);
if (firstseq & 0x1)
while (firstseq == READ_ONCE(rnp->ofl_seq))
schedule_timeout_idle(1); // Can't wake unless RCU is watching.
smp_mb(); // Pair with barriers used when updating ->ofl_seq to even values.
raw_spin_lock(&rcu_state.ofl_lock);
raw_spin_lock_irq_rcu_node(rnp);
if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
!rnp->wait_blkd_tasks) {
/* Nothing to do on this leaf rcu_node structure. */
raw_spin_unlock_irq_rcu_node(rnp);
raw_spin_unlock(&rcu_state.ofl_lock);
continue;
}
/* Record old state, apply changes to ->qsmaskinit field. */
oldmask = rnp->qsmaskinit;
rnp->qsmaskinit = rnp->qsmaskinitnext;
/* If zero-ness of ->qsmaskinit changed, propagate up tree. */
if (!oldmask != !rnp->qsmaskinit) {
if (!oldmask) { /* First online CPU for rcu_node. */
if (!rnp->wait_blkd_tasks) /* Ever offline? */
rcu_init_new_rnp(rnp);
} else if (rcu_preempt_has_tasks(rnp)) {
rnp->wait_blkd_tasks = true; /* blocked tasks */
} else { /* Last offline CPU and can propagate. */
rcu_cleanup_dead_rnp(rnp);
}
}
/*
* If all waited-on tasks from prior grace period are
* done, and if all this rcu_node structure's CPUs are
* still offline, propagate up the rcu_node tree and
* clear ->wait_blkd_tasks. Otherwise, if one of this
* rcu_node structure's CPUs has since come back online,
* simply clear ->wait_blkd_tasks.
*/
if (rnp->wait_blkd_tasks &&
(!rcu_preempt_has_tasks(rnp) || rnp->qsmaskinit)) {
rnp->wait_blkd_tasks = false;
if (!rnp->qsmaskinit)
rcu_cleanup_dead_rnp(rnp);
}
raw_spin_unlock_irq_rcu_node(rnp);
raw_spin_unlock(&rcu_state.ofl_lock);
}
rcu_gp_slow(gp_preinit_delay); /* Races with CPU hotplug. */
/*
* 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 rcu_state.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.
*
* The grace period cannot complete until the initialization
* process finishes, because this kthread handles both.
*/
WRITE_ONCE(rcu_state.gp_state, RCU_GP_INIT);
rcu_for_each_node_breadth_first(rnp) {
rcu_gp_slow(gp_init_delay);
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rdp = this_cpu_ptr(&rcu_data);
rcu_preempt_check_blocked_tasks(rnp);
rnp->qsmask = rnp->qsmaskinit;
WRITE_ONCE(rnp->gp_seq, rcu_state.gp_seq);
if (rnp == rdp->mynode)
(void)__note_gp_changes(rnp, rdp);
rcu_preempt_boost_start_gp(rnp);
trace_rcu_grace_period_init(rcu_state.name, rnp->gp_seq,
rnp->level, rnp->grplo,
rnp->grphi, rnp->qsmask);
/* Quiescent states for tasks on any now-offline CPUs. */
mask = rnp->qsmask & ~rnp->qsmaskinitnext;
rnp->rcu_gp_init_mask = mask;
if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp))
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
else
raw_spin_unlock_irq_rcu_node(rnp);
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
}
// If strict, make all CPUs aware of new grace period.
if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
on_each_cpu(rcu_strict_gp_boundary, NULL, 0);
return true;
}
/*
* Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state
* time.
*/
static bool rcu_gp_fqs_check_wake(int *gfp)
{
struct rcu_node *rnp = rcu_get_root();
// If under overload conditions, force an immediate FQS scan.
if (*gfp & RCU_GP_FLAG_OVLD)
return true;
// Someone like call_rcu() requested a force-quiescent-state scan.
*gfp = READ_ONCE(rcu_state.gp_flags);
if (*gfp & RCU_GP_FLAG_FQS)
return true;
// The current grace period has completed.
if (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp))
return true;
return false;
}
/*
* Do one round of quiescent-state forcing.
*/
static void rcu_gp_fqs(bool first_time)
{
struct rcu_node *rnp = rcu_get_root();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
WRITE_ONCE(rcu_state.n_force_qs, rcu_state.n_force_qs + 1);
if (first_time) {
/* Collect dyntick-idle snapshots. */
force_qs_rnp(dyntick_save_progress_counter);
} else {
/* Handle dyntick-idle and offline CPUs. */
force_qs_rnp(rcu_implicit_dynticks_qs);
}
/* Clear flag to prevent immediate re-entry. */
if (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) {
raw_spin_lock_irq_rcu_node(rnp);
WRITE_ONCE(rcu_state.gp_flags,
READ_ONCE(rcu_state.gp_flags) & ~RCU_GP_FLAG_FQS);
raw_spin_unlock_irq_rcu_node(rnp);
}
}
/*
* Loop doing repeated quiescent-state forcing until the grace period ends.
*/
static noinline_for_stack void rcu_gp_fqs_loop(void)
{
bool first_gp_fqs;
int gf = 0;
unsigned long j;
int ret;
struct rcu_node *rnp = rcu_get_root();
first_gp_fqs = true;
j = READ_ONCE(jiffies_till_first_fqs);
if (rcu_state.cbovld)
gf = RCU_GP_FLAG_OVLD;
ret = 0;
for (;;) {
if (!ret) {
WRITE_ONCE(rcu_state.jiffies_force_qs, jiffies + j);
/*
* jiffies_force_qs before RCU_GP_WAIT_FQS state
* update; required for stall checks.
*/
smp_wmb();
WRITE_ONCE(rcu_state.jiffies_kick_kthreads,
jiffies + (j ? 3 * j : 2));
}
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("fqswait"));
WRITE_ONCE(rcu_state.gp_state, RCU_GP_WAIT_FQS);
(void)swait_event_idle_timeout_exclusive(rcu_state.gp_wq,
rcu_gp_fqs_check_wake(&gf), j);
rcu_gp_torture_wait();
WRITE_ONCE(rcu_state.gp_state, RCU_GP_DOING_FQS);
/* Locking provides needed memory barriers. */
/* If grace period done, leave loop. */
if (!READ_ONCE(rnp->qsmask) &&
!rcu_preempt_blocked_readers_cgp(rnp))
break;
/* If time for quiescent-state forcing, do it. */
if (!time_after(rcu_state.jiffies_force_qs, jiffies) ||
(gf & (RCU_GP_FLAG_FQS | RCU_GP_FLAG_OVLD))) {
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("fqsstart"));
rcu_gp_fqs(first_gp_fqs);
gf = 0;
if (first_gp_fqs) {
first_gp_fqs = false;
gf = rcu_state.cbovld ? RCU_GP_FLAG_OVLD : 0;
}
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("fqsend"));
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
ret = 0; /* Force full wait till next FQS. */
j = READ_ONCE(jiffies_till_next_fqs);
} else {
/* Deal with stray signal. */
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("fqswaitsig"));
ret = 1; /* Keep old FQS timing. */
j = jiffies;
if (time_after(jiffies, rcu_state.jiffies_force_qs))
j = 1;
else
j = rcu_state.jiffies_force_qs - j;
gf = 0;
}
}
}
/*
* Clean up after the old grace period.
*/
static noinline void rcu_gp_cleanup(void)
{
int cpu;
bool needgp = false;
unsigned long gp_duration;
unsigned long new_gp_seq;
bool offloaded;
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root();
struct swait_queue_head *sq;
WRITE_ONCE(rcu_state.gp_activity, jiffies);
raw_spin_lock_irq_rcu_node(rnp);
rcu_state.gp_end = jiffies;
gp_duration = rcu_state.gp_end - rcu_state.gp_start;
if (gp_duration > rcu_state.gp_max)
rcu_state.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_rcu_node(rnp);
/*
* Propagate new ->gp_seq 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.
*/
new_gp_seq = rcu_state.gp_seq;
rcu_seq_end(&new_gp_seq);
rcu_for_each_node_breadth_first(rnp) {
raw_spin_lock_irq_rcu_node(rnp);
if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
dump_blkd_tasks(rnp, 10);
WARN_ON_ONCE(rnp->qsmask);
WRITE_ONCE(rnp->gp_seq, new_gp_seq);
rdp = this_cpu_ptr(&rcu_data);
if (rnp == rdp->mynode)
needgp = __note_gp_changes(rnp, rdp) || needgp;
/* smp_mb() provided by prior unlock-lock pair. */
needgp = rcu_future_gp_cleanup(rnp) || needgp;
// Reset overload indication for CPUs no longer overloaded
if (rcu_is_leaf_node(rnp))
for_each_leaf_node_cpu_mask(rnp, cpu, rnp->cbovldmask) {
rdp = per_cpu_ptr(&rcu_data, cpu);
check_cb_ovld_locked(rdp, rnp);
}
sq = rcu_nocb_gp_get(rnp);
raw_spin_unlock_irq_rcu_node(rnp);
rcu_nocb_gp_cleanup(sq);
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
rcu_gp_slow(gp_cleanup_delay);
}
rnp = rcu_get_root();
raw_spin_lock_irq_rcu_node(rnp); /* GP before ->gp_seq update. */
/* Declare grace period done, trace first to use old GP number. */
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end"));
rcu_seq_end(&rcu_state.gp_seq);
ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
WRITE_ONCE(rcu_state.gp_state, RCU_GP_IDLE);
/* Check for GP requests since above loop. */
rdp = this_cpu_ptr(&rcu_data);
if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) {
trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed,
TPS("CleanupMore"));
needgp = true;
}
/* Advance CBs to reduce false positives below. */
offloaded = rcu_rdp_is_offloaded(rdp);
if ((offloaded || !rcu_accelerate_cbs(rnp, rdp)) && needgp) {
WRITE_ONCE(rcu_state.gp_flags, RCU_GP_FLAG_INIT);
WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
trace_rcu_grace_period(rcu_state.name,
rcu_state.gp_seq,
TPS("newreq"));
} else {
WRITE_ONCE(rcu_state.gp_flags,
rcu_state.gp_flags & RCU_GP_FLAG_INIT);
}
raw_spin_unlock_irq_rcu_node(rnp);
// If strict, make all CPUs aware of the end of the old grace period.
if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
on_each_cpu(rcu_strict_gp_boundary, NULL, 0);
}
/*
* Body of kthread that handles grace periods.
*/
static int __noreturn rcu_gp_kthread(void *unused)
{
rcu_bind_gp_kthread();
for (;;) {
/* Handle grace-period start. */
for (;;) {
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("reqwait"));
WRITE_ONCE(rcu_state.gp_state, RCU_GP_WAIT_GPS);
swait_event_idle_exclusive(rcu_state.gp_wq,
READ_ONCE(rcu_state.gp_flags) &
RCU_GP_FLAG_INIT);
rcu_gp_torture_wait();
WRITE_ONCE(rcu_state.gp_state, RCU_GP_DONE_GPS);
/* Locking provides needed memory barrier. */
if (rcu_gp_init())
break;
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("reqwaitsig"));
}
/* Handle quiescent-state forcing. */
rcu_gp_fqs_loop();
/* Handle grace-period end. */
WRITE_ONCE(rcu_state.gp_state, RCU_GP_CLEANUP);
rcu_gp_cleanup();
WRITE_ONCE(rcu_state.gp_state, RCU_GP_CLEANED);
}
}
/*
* Report a full set of quiescent states to the rcu_state data structure.
* Invoke rcu_gp_kthread_wake() to awaken the grace-period kthread if
* another grace period is required. Whether we wake the grace-period
* kthread or it awakens itself for the next round of quiescent-state
* forcing, that kthread will clean up after the just-completed grace
* period. Note that the caller must hold rnp->lock, which is released
* before return.
*/
static void rcu_report_qs_rsp(unsigned long flags)
__releases(rcu_get_root()->lock)
{
raw_lockdep_assert_held_rcu_node(rcu_get_root());
WARN_ON_ONCE(!rcu_gp_in_progress());
WRITE_ONCE(rcu_state.gp_flags,
READ_ONCE(rcu_state.gp_flags) | RCU_GP_FLAG_FQS);
raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(), flags);
rcu_gp_kthread_wake();
}
/*
* 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). The gps parameter
* is the grace-period snapshot, which means that the quiescent states
* are valid only if rnp->gp_seq is equal to gps. That structure's lock
* must be held upon entry, and it is released before return.
*
* As a special case, if mask is zero, the bit-already-cleared check is
* disabled. This allows propagating quiescent state due to resumed tasks
* during grace-period initialization.
*/
static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
unsigned long gps, unsigned long flags)
__releases(rnp->lock)
{
unsigned long oldmask = 0;
struct rcu_node *rnp_c;
raw_lockdep_assert_held_rcu_node(rnp);
/* Walk up the rcu_node hierarchy. */
for (;;) {
if ((!(rnp->qsmask & mask) && mask) || rnp->gp_seq != gps) {
/*
* Our bit has already been cleared, or the
* relevant grace period is already over, so done.
*/
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */
WARN_ON_ONCE(!rcu_is_leaf_node(rnp) &&
rcu_preempt_blocked_readers_cgp(rnp));
WRITE_ONCE(rnp->qsmask, rnp->qsmask & ~mask);
trace_rcu_quiescent_state_report(rcu_state.name, rnp->gp_seq,
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_rcu_node(rnp, flags);
return;
}
rnp->completedqs = rnp->gp_seq;
mask = rnp->grpmask;
if (rnp->parent == NULL) {
/* No more levels. Exit loop holding root lock. */
break;
}
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rnp_c = rnp;
rnp = rnp->parent;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
oldmask = READ_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(flags); /* releases rnp->lock. */
}
/*
* Record a quiescent state for all tasks that were previously queued
* on the specified rcu_node structure and that were blocking the current
* RCU grace period. The caller must hold the corresponding rnp->lock with
* irqs disabled, and this lock is released upon return, but irqs remain
* disabled.
*/
static void __maybe_unused
rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
__releases(rnp->lock)
{
unsigned long gps;
unsigned long mask;
struct rcu_node *rnp_p;
raw_lockdep_assert_held_rcu_node(rnp);
if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_RCU)) ||
WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) ||
rnp->qsmask != 0) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return; /* Still need more quiescent states! */
}
rnp->completedqs = rnp->gp_seq;
rnp_p = rnp->parent;
if (rnp_p == NULL) {
/*
* Only one rcu_node structure in the tree, so don't
* try to report up to its nonexistent parent!
*/
rcu_report_qs_rsp(flags);
return;
}
/* Report up the rest of the hierarchy, tracking current ->gp_seq. */
gps = rnp->gp_seq;
mask = rnp->grpmask;
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
raw_spin_lock_rcu_node(rnp_p); /* irqs already disabled. */
rcu_report_qs_rnp(mask, rnp_p, gps, flags);
}
/*
* Record a quiescent state for the specified CPU to that CPU's rcu_data
* structure. This must be called from the specified CPU.
*/
static void
rcu_report_qs_rdp(struct rcu_data *rdp)
{
unsigned long flags;
unsigned long mask;
bool needwake = false;
bool needacc = false;
struct rcu_node *rnp;
WARN_ON_ONCE(rdp->cpu != smp_processor_id());
rnp = rdp->mynode;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq ||
rdp->gpwrap) {
/*
* 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->cpu_no_qs.b.norm = true; /* need qs for new gp. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
mask = rdp->grpmask;
rdp->core_needs_qs = false;
if ((rnp->qsmask & mask) == 0) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
} else {
/*
* This GP can't end until cpu checks in, so all of our
* callbacks can be processed during the next GP.
*
* NOCB kthreads have their own way to deal with that...
*/
if (!rcu_rdp_is_offloaded(rdp)) {
needwake = rcu_accelerate_cbs(rnp, rdp);
} else if (!rcu_segcblist_completely_offloaded(&rdp->cblist)) {
/*
* ...but NOCB kthreads may miss or delay callbacks acceleration
* if in the middle of a (de-)offloading process.
*/
needacc = true;
}
rcu_disable_urgency_upon_qs(rdp);
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
/* ^^^ Released rnp->lock */
if (needwake)
rcu_gp_kthread_wake();
if (needacc) {
rcu_nocb_lock_irqsave(rdp, flags);
rcu_accelerate_cbs_unlocked(rnp, rdp);
rcu_nocb_unlock_irqrestore(rdp, flags);
}
}
}
/*
* 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_data *rdp)
{
/* Check for grace-period ends and beginnings. */
note_gp_changes(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->core_needs_qs)
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->cpu_no_qs.b.norm)
return;
/*
* Tell RCU we are done (but rcu_report_qs_rdp() will be the
* judge of that).
*/
rcu_report_qs_rdp(rdp);
}
/*
* Near the end of the offline process. Trace the fact that this CPU
* is going offline.
*/
int rcutree_dying_cpu(unsigned int cpu)
{
bool blkd;
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
struct rcu_node *rnp = rdp->mynode;
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return 0;
blkd = !!(rnp->qsmask & rdp->grpmask);
trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
return 0;
}
/*
* All CPUs for the specified rcu_node structure have gone offline,
* and all tasks that were preempted within an RCU read-side critical
* section while running on one of those CPUs have since exited their RCU
* read-side critical section. Some other CPU is reporting this fact with
* the specified rcu_node structure's ->lock held and interrupts disabled.
* This function therefore goes up the tree of rcu_node structures,
* clearing the corresponding bits in the ->qsmaskinit fields. Note that
* the leaf rcu_node structure's ->qsmaskinit field has already been
* updated.
*
* This function does check that the specified rcu_node structure has
* all CPUs offline and no blocked tasks, so it is OK to invoke it
* prematurely. That said, invoking it after the fact will cost you
* a needless lock acquisition. So once it has done its work, don't
* invoke it again.
*/
static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
{
long mask;
struct rcu_node *rnp = rnp_leaf;
raw_lockdep_assert_held_rcu_node(rnp_leaf);
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
WARN_ON_ONCE(rnp_leaf->qsmaskinit) ||
WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf)))
return;
for (;;) {
mask = rnp->grpmask;
rnp = rnp->parent;
if (!rnp)
break;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
rnp->qsmaskinit &= ~mask;
/* Between grace periods, so better already be zero! */
WARN_ON_ONCE(rnp->qsmask);
if (rnp->qsmaskinit) {
raw_spin_unlock_rcu_node(rnp);
/* irqs remain disabled. */
return;
}
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
}
}
/*
* The CPU has been completely removed, and some other CPU is reporting
* this fact from process context. Do the remainder of the cleanup.
* There can only be one CPU hotplug operation at a time, so no need for
* explicit locking.
*/
int rcutree_dead_cpu(unsigned int cpu)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return 0;
WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
/* Adjust any no-longer-needed kthreads. */
rcu_boost_kthread_setaffinity(rnp, -1);
// Stop-machine done, so allow nohz_full to disable tick.
tick_dep_clear(TICK_DEP_BIT_RCU);
return 0;
}
/*
* Invoke any RCU callbacks that have made it to the end of their grace
* period. Throttle as specified by rdp->blimit.
*/
static void rcu_do_batch(struct rcu_data *rdp)
{
int div;
bool __maybe_unused empty;
unsigned long flags;
const bool offloaded = rcu_rdp_is_offloaded(rdp);
struct rcu_head *rhp;
struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
long bl, count = 0;
long pending, tlimit = 0;
/* If no callbacks are ready, just return. */
if (!rcu_segcblist_ready_cbs(&rdp->cblist)) {
trace_rcu_batch_start(rcu_state.name,
rcu_segcblist_n_cbs(&rdp->cblist), 0);
trace_rcu_batch_end(rcu_state.name, 0,
!rcu_segcblist_empty(&rdp->cblist),
need_resched(), is_idle_task(current),
rcu_is_callbacks_kthread());
return;
}
/*
* Extract the list of ready callbacks, disabling IRQs to prevent
* races with call_rcu() from interrupt handlers. Leave the
* callback counts, as rcu_barrier() needs to be conservative.
*/
rcu_nocb_lock_irqsave(rdp, flags);
WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
pending = rcu_segcblist_n_cbs(&rdp->cblist);
div = READ_ONCE(rcu_divisor);
div = div < 0 ? 7 : div > sizeof(long) * 8 - 2 ? sizeof(long) * 8 - 2 : div;
bl = max(rdp->blimit, pending >> div);
if (unlikely(bl > 100)) {
long rrn = READ_ONCE(rcu_resched_ns);
rrn = rrn < NSEC_PER_MSEC ? NSEC_PER_MSEC : rrn > NSEC_PER_SEC ? NSEC_PER_SEC : rrn;
tlimit = local_clock() + rrn;
}
trace_rcu_batch_start(rcu_state.name,
rcu_segcblist_n_cbs(&rdp->cblist), bl);
rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl);
if (rcu_rdp_is_offloaded(rdp))
rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbDequeued"));
rcu_nocb_unlock_irqrestore(rdp, flags);
/* Invoke callbacks. */
tick_dep_set_task(current, TICK_DEP_BIT_RCU);
rhp = rcu_cblist_dequeue(&rcl);
for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) {
rcu_callback_t f;
count++;
debug_rcu_head_unqueue(rhp);
rcu_lock_acquire(&rcu_callback_map);
trace_rcu_invoke_callback(rcu_state.name, rhp);
f = rhp->func;
WRITE_ONCE(rhp->func, (rcu_callback_t)0L);
f(rhp);
rcu_lock_release(&rcu_callback_map);
/*
* Stop only if limit reached and CPU has something to do.
*/
if (in_serving_softirq()) {
if (count >= bl && (need_resched() || !is_idle_task(current)))
break;
} else {
local_bh_enable();
lockdep_assert_irqs_enabled();
cond_resched_tasks_rcu_qs();
lockdep_assert_irqs_enabled();
local_bh_disable();
}
/*
* Make sure we don't spend too much time here and deprive other
* softirq vectors of CPU cycles.
*/
if (unlikely(tlimit)) {
/* only call local_clock() every 32 callbacks */
if (likely((count & 31) || local_clock() < tlimit))
continue;
/* Exceeded the time limit, so leave. */
break;
}
}
rcu_nocb_lock_irqsave(rdp, flags);
rdp->n_cbs_invoked += count;
trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(),
is_idle_task(current), rcu_is_callbacks_kthread());
/* Update counts and requeue any remaining callbacks. */
rcu_segcblist_insert_done_cbs(&rdp->cblist, &rcl);
rcu_segcblist_add_len(&rdp->cblist, -count);
/* Reinstate batch limit if we have worked down the excess. */
count = rcu_segcblist_n_cbs(&rdp->cblist);
if (rdp->blimit >= DEFAULT_MAX_RCU_BLIMIT && count <= qlowmark)
rdp->blimit = blimit;
/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
if (count == 0 && rdp->qlen_last_fqs_check != 0) {
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
} else if (count < rdp->qlen_last_fqs_check - qhimark)
rdp->qlen_last_fqs_check = count;
/*
* The following usually indicates a double call_rcu(). To track
* this down, try building with CONFIG_DEBUG_OBJECTS_RCU_HEAD=y.
*/
empty = rcu_segcblist_empty(&rdp->cblist);
WARN_ON_ONCE(count == 0 && !empty);
WARN_ON_ONCE(!IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
count != 0 && empty);
WARN_ON_ONCE(count == 0 && rcu_segcblist_n_segment_cbs(&rdp->cblist) != 0);
WARN_ON_ONCE(!empty && rcu_segcblist_n_segment_cbs(&rdp->cblist) == 0);
rcu_nocb_unlock_irqrestore(rdp, flags);
/* Re-invoke RCU core processing if there are callbacks remaining. */
if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist))
invoke_rcu_core();
tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
}
/*
* This function is invoked from each scheduling-clock interrupt,
* and checks to see if this CPU is in a non-context-switch quiescent
* state, for example, user mode or idle loop. It also schedules RCU
* core processing. If the current grace period has gone on too long,
* it will ask the scheduler to manufacture a context switch for the sole
* purpose of providing the needed quiescent state.
*/
void rcu_sched_clock_irq(int user)
{
trace_rcu_utilization(TPS("Start scheduler-tick"));
lockdep_assert_irqs_disabled();
raw_cpu_inc(rcu_data.ticks_this_gp);
/* The load-acquire pairs with the store-release setting to true. */
if (smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) {
/* Idle and userspace execution already are quiescent states. */
if (!rcu_is_cpu_rrupt_from_idle() && !user) {
set_tsk_need_resched(current);
set_preempt_need_resched();
}
__this_cpu_write(rcu_data.rcu_urgent_qs, false);
}
rcu_flavor_sched_clock_irq(user);
if (rcu_pending(user))
invoke_rcu_core();
lockdep_assert_irqs_disabled();
trace_rcu_utilization(TPS("End scheduler-tick"));
}
/*
* Scan the leaf rcu_node structures. For each structure on which all
* CPUs have reported a quiescent state and on which there are tasks
* blocking the current grace period, initiate RCU priority boosting.
* Otherwise, invoke the specified function to check dyntick state for
* each CPU that has not yet reported a quiescent state.
*/
static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
{
int cpu;
unsigned long flags;
unsigned long mask;
struct rcu_data *rdp;
struct rcu_node *rnp;
rcu_state.cbovld = rcu_state.cbovldnext;
rcu_state.cbovldnext = false;
rcu_for_each_leaf_node(rnp) {
cond_resched_tasks_rcu_qs();
mask = 0;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rcu_state.cbovldnext |= !!rnp->cbovldmask;
if (rnp->qsmask == 0) {
if (rcu_preempt_blocked_readers_cgp(rnp)) {
/*
* No point in scanning bits because they
* are all zero. But we might need to
* priority-boost blocked readers.
*/
rcu_initiate_boost(rnp, flags);
/* rcu_initiate_boost() releases rnp->lock */
continue;
}
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
continue;
}
for_each_leaf_node_cpu_mask(rnp, cpu, rnp->qsmask) {
rdp = per_cpu_ptr(&rcu_data, cpu);
if (f(rdp)) {
mask |= rdp->grpmask;
rcu_disable_urgency_upon_qs(rdp);
}
}
if (mask != 0) {
/* Idle/offline CPUs, report (releases rnp->lock). */
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
} else {
/* Nothing to do here, so just drop the lock. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
}
}
/*
* Force quiescent states on reluctant CPUs, and also detect which
* CPUs are in dyntick-idle mode.
*/
void rcu_force_quiescent_state(void)
{
unsigned long flags;
bool ret;
struct rcu_node *rnp;
struct rcu_node *rnp_old = NULL;
/* Funnel through hierarchy to reduce memory contention. */
rnp = __this_cpu_read(rcu_data.mynode);
for (; rnp != NULL; rnp = rnp->parent) {
ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) ||
!raw_spin_trylock(&rnp->fqslock);
if (rnp_old != NULL)
raw_spin_unlock(&rnp_old->fqslock);
if (ret)
return;
rnp_old = rnp;
}
/* rnp_old == rcu_get_root(), rnp == NULL. */
/* Reached the root of the rcu_node tree, acquire lock. */
raw_spin_lock_irqsave_rcu_node(rnp_old, flags);
raw_spin_unlock(&rnp_old->fqslock);
if (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) {
raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags);
return; /* Someone beat us to it. */
}
WRITE_ONCE(rcu_state.gp_flags,
READ_ONCE(rcu_state.gp_flags) | RCU_GP_FLAG_FQS);
raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags);
rcu_gp_kthread_wake();
}
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
// Workqueue handler for an RCU reader for kernels enforcing struct RCU
// grace periods.
static void strict_work_handler(struct work_struct *work)
{
rcu_read_lock();
rcu_read_unlock();
}
/* Perform RCU core processing work for the current CPU. */
static __latent_entropy void rcu_core(void)
{
unsigned long flags;
struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rdp->mynode;
/*
* On RT rcu_core() can be preempted when IRQs aren't disabled.
* Therefore this function can race with concurrent NOCB (de-)offloading
* on this CPU and the below condition must be considered volatile.
* However if we race with:
*
* _ Offloading: In the worst case we accelerate or process callbacks
* concurrently with NOCB kthreads. We are guaranteed to
* call rcu_nocb_lock() if that happens.
*
* _ Deoffloading: In the worst case we miss callbacks acceleration or
* processing. This is fine because the early stage
* of deoffloading invokes rcu_core() after setting
* SEGCBLIST_RCU_CORE. So we guarantee that we'll process
* what could have been dismissed without the need to wait
* for the next rcu_pending() check in the next jiffy.
*/
const bool do_batch = !rcu_segcblist_completely_offloaded(&rdp->cblist);
if (cpu_is_offline(smp_processor_id()))
return;
trace_rcu_utilization(TPS("Start RCU core"));
WARN_ON_ONCE(!rdp->beenonline);
/* Report any deferred quiescent states if preemption enabled. */
if (!(preempt_count() & PREEMPT_MASK)) {
rcu_preempt_deferred_qs(current);
} else if (rcu_preempt_need_deferred_qs(current)) {
set_tsk_need_resched(current);
set_preempt_need_resched();
}
/* Update RCU state based on any recent quiescent states. */
rcu_check_quiescent_state(rdp);
/* No grace period and unregistered callbacks? */
if (!rcu_gp_in_progress() &&
rcu_segcblist_is_enabled(&rdp->cblist) && do_batch) {
rcu_nocb_lock_irqsave(rdp, flags);
if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
rcu_accelerate_cbs_unlocked(rnp, rdp);
rcu_nocb_unlock_irqrestore(rdp, flags);
}
rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check());
/* If there are callbacks ready, invoke them. */
if (do_batch && rcu_segcblist_ready_cbs(&rdp->cblist) &&
likely(READ_ONCE(rcu_scheduler_fully_active)))
rcu_do_batch(rdp);
/* Do any needed deferred wakeups of rcuo kthreads. */
do_nocb_deferred_wakeup(rdp);
trace_rcu_utilization(TPS("End RCU core"));
// If strict GPs, schedule an RCU reader in a clean environment.
if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
queue_work_on(rdp->cpu, rcu_gp_wq, &rdp->strict_work);
}
static void rcu_core_si(struct softirq_action *h)
{
rcu_core();
}
static void rcu_wake_cond(struct task_struct *t, int status)
{
/*
* If the thread is yielding, only wake it when this
* is invoked from idle
*/
if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current)))
wake_up_process(t);
}
static void invoke_rcu_core_kthread(void)
{
struct task_struct *t;
unsigned long flags;
local_irq_save(flags);
__this_cpu_write(rcu_data.rcu_cpu_has_work, 1);
t = __this_cpu_read(rcu_data.rcu_cpu_kthread_task);
if (t != NULL && t != current)
rcu_wake_cond(t, __this_cpu_read(rcu_data.rcu_cpu_kthread_status));
local_irq_restore(flags);
}
/*
* Wake up this CPU's rcuc kthread to do RCU core processing.
*/
static void invoke_rcu_core(void)
{
if (!cpu_online(smp_processor_id()))
return;
if (use_softirq)
raise_softirq(RCU_SOFTIRQ);
else
invoke_rcu_core_kthread();
}
static void rcu_cpu_kthread_park(unsigned int cpu)
{
per_cpu(rcu_data.rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
}
static int rcu_cpu_kthread_should_run(unsigned int cpu)
{
return __this_cpu_read(rcu_data.rcu_cpu_has_work);
}
/*
* Per-CPU kernel thread that invokes RCU callbacks. This replaces
* the RCU softirq used in configurations of RCU that do not support RCU
* priority boosting.
*/
static void rcu_cpu_kthread(unsigned int cpu)
{
unsigned int *statusp = this_cpu_ptr(&rcu_data.rcu_cpu_kthread_status);
char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work);
int spincnt;
trace_rcu_utilization(TPS("Start CPU kthread@rcu_run"));
for (spincnt = 0; spincnt < 10; spincnt++) {
local_bh_disable();
*statusp = RCU_KTHREAD_RUNNING;
local_irq_disable();
work = *workp;
*workp = 0;
local_irq_enable();
if (work)
rcu_core();
local_bh_enable();
if (*workp == 0) {
trace_rcu_utilization(TPS("End CPU kthread@rcu_wait"));
*statusp = RCU_KTHREAD_WAITING;
return;
}
}
*statusp = RCU_KTHREAD_YIELDING;
trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield"));
schedule_timeout_idle(2);
trace_rcu_utilization(TPS("End CPU kthread@rcu_yield"));
*statusp = RCU_KTHREAD_WAITING;
}
static struct smp_hotplug_thread rcu_cpu_thread_spec = {
.store = &rcu_data.rcu_cpu_kthread_task,
.thread_should_run = rcu_cpu_kthread_should_run,
.thread_fn = rcu_cpu_kthread,
.thread_comm = "rcuc/%u",
.setup = rcu_cpu_kthread_setup,
.park = rcu_cpu_kthread_park,
};
/*
* Spawn per-CPU RCU core processing kthreads.
*/
static int __init rcu_spawn_core_kthreads(void)
{
int cpu;
for_each_possible_cpu(cpu)
per_cpu(rcu_data.rcu_cpu_has_work, cpu) = 0;
if (!IS_ENABLED(CONFIG_RCU_BOOST) && use_softirq)
return 0;
WARN_ONCE(smpboot_register_percpu_thread(&rcu_cpu_thread_spec),
"%s: Could not start rcuc kthread, OOM is now expected behavior\n", __func__);
return 0;
}
/*
* Handle any core-RCU processing required by a call_rcu() invocation.
*/
static void __call_rcu_core(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_watching())
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 rcu_force_quiescent_state()
* if some other CPU has recently done so. Also, don't bother
* invoking rcu_force_quiescent_state() if the newly enqueued callback
* is the only one waiting for a grace period to complete.
*/
if (unlikely(rcu_segcblist_n_cbs(&rdp->cblist) >
rdp->qlen_last_fqs_check + qhimark)) {
/* Are we ignoring a completed grace period? */
note_gp_changes(rdp);
/* Start a new grace period if one not already started. */
if (!rcu_gp_in_progress()) {
rcu_accelerate_cbs_unlocked(rdp->mynode, rdp);
} else {
/* Give the grace period a kick. */
rdp->blimit = DEFAULT_MAX_RCU_BLIMIT;
if (READ_ONCE(rcu_state.n_force_qs) == rdp->n_force_qs_snap &&
rcu_segcblist_first_pend_cb(&rdp->cblist) != head)
rcu_force_quiescent_state();
rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
}
}
}
/*
* RCU callback function to leak a callback.
*/
static void rcu_leak_callback(struct rcu_head *rhp)
{
}
/*
* Check and if necessary update the leaf rcu_node structure's
* ->cbovldmask bit corresponding to the current CPU based on that CPU's
* number of queued RCU callbacks. The caller must hold the leaf rcu_node
* structure's ->lock.
*/
static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp)
{
raw_lockdep_assert_held_rcu_node(rnp);
if (qovld_calc <= 0)
return; // Early boot and wildcard value set.
if (rcu_segcblist_n_cbs(&rdp->cblist) >= qovld_calc)
WRITE_ONCE(rnp->cbovldmask, rnp->cbovldmask | rdp->grpmask);
else
WRITE_ONCE(rnp->cbovldmask, rnp->cbovldmask & ~rdp->grpmask);
}
/*
* Check and if necessary update the leaf rcu_node structure's
* ->cbovldmask bit corresponding to the current CPU based on that CPU's
* number of queued RCU callbacks. No locks need be held, but the
* caller must have disabled interrupts.
*
* Note that this function ignores the possibility that there are a lot
* of callbacks all of which have already seen the end of their respective
* grace periods. This omission is due to the need for no-CBs CPUs to
* be holding ->nocb_lock to do this check, which is too heavy for a
* common-case operation.
*/
static void check_cb_ovld(struct rcu_data *rdp)
{
struct rcu_node *const rnp = rdp->mynode;
if (qovld_calc <= 0 ||
((rcu_segcblist_n_cbs(&rdp->cblist) >= qovld_calc) ==
!!(READ_ONCE(rnp->cbovldmask) & rdp->grpmask)))
return; // Early boot wildcard value or already set correctly.
raw_spin_lock_rcu_node(rnp);
check_cb_ovld_locked(rdp, rnp);
raw_spin_unlock_rcu_node(rnp);
}
/* Helper function for call_rcu() and friends. */
static void
__call_rcu(struct rcu_head *head, rcu_callback_t func)
{
static atomic_t doublefrees;
unsigned long flags;
struct rcu_data *rdp;
bool was_alldone;
/* Misaligned rcu_head! */
WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1));
if (debug_rcu_head_queue(head)) {
/*
* Probable double call_rcu(), so leak the callback.
* Use rcu:rcu_callback trace event to find the previous
* time callback was passed to __call_rcu().
*/
if (atomic_inc_return(&doublefrees) < 4) {
pr_err("%s(): Double-freed CB %p->%pS()!!! ", __func__, head, head->func);
mem_dump_obj(head);
}
WRITE_ONCE(head->func, rcu_leak_callback);
return;
}
head->func = func;
head->next = NULL;
local_irq_save(flags);
kasan_record_aux_stack(head);
rdp = this_cpu_ptr(&rcu_data);
/* Add the callback to our list. */
if (unlikely(!rcu_segcblist_is_enabled(&rdp->cblist))) {
// This can trigger due to call_rcu() from offline CPU:
WARN_ON_ONCE(rcu_scheduler_active != RCU_SCHEDULER_INACTIVE);
WARN_ON_ONCE(!rcu_is_watching());
// Very early boot, before rcu_init(). Initialize if needed
// and then drop through to queue the callback.
if (rcu_segcblist_empty(&rdp->cblist))
rcu_segcblist_init(&rdp->cblist);
}
check_cb_ovld(rdp);
if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags))
return; // Enqueued onto ->nocb_bypass, so just leave.
// If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock.
rcu_segcblist_enqueue(&rdp->cblist, head);
if (__is_kvfree_rcu_offset((unsigned long)func))
trace_rcu_kvfree_callback(rcu_state.name, head,
(unsigned long)func,
rcu_segcblist_n_cbs(&rdp->cblist));
else
trace_rcu_callback(rcu_state.name, head,
rcu_segcblist_n_cbs(&rdp->cblist));
trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCBQueued"));
/* Go handle any RCU core processing required. */
if (unlikely(rcu_rdp_is_offloaded(rdp))) {
__call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */
} else {
__call_rcu_core(rdp, head, flags);
local_irq_restore(flags);
}
}
/**
* call_rcu() - Queue an RCU callback for invocation after a grace period.
* @head: structure to be used for queueing the RCU updates.
* @func: actual callback function to be invoked after the grace period
*
* The callback function will be invoked some time after a full grace
* period elapses, in other words after all pre-existing RCU read-side
* critical sections have completed. However, the callback function
* might well execute concurrently with RCU read-side critical sections
* that started after call_rcu() was invoked.
*
* RCU read-side critical sections are delimited by rcu_read_lock()
* and rcu_read_unlock(), and may be nested. In addition, but only in
* v5.0 and later, regions of code across which interrupts, preemption,
* or softirqs have been disabled also serve as RCU read-side critical
* sections. This includes hardware interrupt handlers, softirq handlers,
* and NMI handlers.
*
* Note that all CPUs must agree that the grace period extended beyond
* all pre-existing RCU read-side critical section. On systems with more
* than one CPU, this means that when "func()" is invoked, each CPU is
* guaranteed to have executed a full memory barrier since the end of its
* last RCU read-side critical section whose beginning preceded the call
* to call_rcu(). It also means that each CPU executing an RCU read-side
* critical section that continues beyond the start of "func()" must have
* executed a memory barrier after the call_rcu() but 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 call_rcu() and CPU B invoked the
* resulting RCU callback function "func()", then both CPU A and CPU B are
* guaranteed to execute a full memory barrier during the time interval
* between the call to call_rcu() and the invocation of "func()" -- even
* if CPU A and CPU B are the same CPU (but again only if the system has
* more than one CPU).
*
* Implementation of these memory-ordering guarantees is described here:
* Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst.
*/
void call_rcu(struct rcu_head *head, rcu_callback_t func)
{
__call_rcu(head, func);
}
EXPORT_SYMBOL_GPL(call_rcu);
/* Maximum number of jiffies to wait before draining a batch. */
#define KFREE_DRAIN_JIFFIES (HZ / 50)
#define KFREE_N_BATCHES 2
#define FREE_N_CHANNELS 2
/**
* struct kvfree_rcu_bulk_data - single block to store kvfree_rcu() pointers
* @nr_records: Number of active pointers in the array
* @next: Next bulk object in the block chain
* @records: Array of the kvfree_rcu() pointers
*/
struct kvfree_rcu_bulk_data {
unsigned long nr_records;
struct kvfree_rcu_bulk_data *next;
void *records[];
};
/*
* This macro defines how many entries the "records" array
* will contain. It is based on the fact that the size of
* kvfree_rcu_bulk_data structure becomes exactly one page.
*/
#define KVFREE_BULK_MAX_ENTR \
((PAGE_SIZE - sizeof(struct kvfree_rcu_bulk_data)) / sizeof(void *))
/**
* struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests
* @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period
* @head_free: List of kfree_rcu() objects waiting for a grace period
* @bkvhead_free: Bulk-List of kvfree_rcu() objects waiting for a grace period
* @krcp: Pointer to @kfree_rcu_cpu structure
*/
struct kfree_rcu_cpu_work {
struct rcu_work rcu_work;
struct rcu_head *head_free;
struct kvfree_rcu_bulk_data *bkvhead_free[FREE_N_CHANNELS];
struct kfree_rcu_cpu *krcp;
};
/**
* struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period
* @head: List of kfree_rcu() objects not yet waiting for a grace period
* @bkvhead: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period
* @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period
* @lock: Synchronize access to this structure
* @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES
* @monitor_todo: Tracks whether a @monitor_work delayed work is pending
* @initialized: The @rcu_work fields have been initialized
* @count: Number of objects for which GP not started
* @bkvcache:
* A simple cache list that contains objects for reuse purpose.
* In order to save some per-cpu space the list is singular.
* Even though it is lockless an access has to be protected by the
* per-cpu lock.
* @page_cache_work: A work to refill the cache when it is empty
* @backoff_page_cache_fill: Delay cache refills
* @work_in_progress: Indicates that page_cache_work is running
* @hrtimer: A hrtimer for scheduling a page_cache_work
* @nr_bkv_objs: number of allocated objects at @bkvcache.
*
* This is a per-CPU structure. The reason that it is not included in
* the rcu_data structure is to permit this code to be extracted from
* the RCU files. Such extraction could allow further optimization of
* the interactions with the slab allocators.
*/
struct kfree_rcu_cpu {
struct rcu_head *head;
struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS];
struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
raw_spinlock_t lock;
struct delayed_work monitor_work;
bool monitor_todo;
bool initialized;
int count;
struct delayed_work page_cache_work;
atomic_t backoff_page_cache_fill;
atomic_t work_in_progress;
struct hrtimer hrtimer;
struct llist_head bkvcache;
int nr_bkv_objs;
};
static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = {
.lock = __RAW_SPIN_LOCK_UNLOCKED(krc.lock),
};
static __always_inline void
debug_rcu_bhead_unqueue(struct kvfree_rcu_bulk_data *bhead)
{
#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
int i;
for (i = 0; i < bhead->nr_records; i++)
debug_rcu_head_unqueue((struct rcu_head *)(bhead->records[i]));
#endif
}
static inline struct kfree_rcu_cpu *
krc_this_cpu_lock(unsigned long *flags)
{
struct kfree_rcu_cpu *krcp;
local_irq_save(*flags); // For safely calling this_cpu_ptr().
krcp = this_cpu_ptr(&krc);
raw_spin_lock(&krcp->lock);
return krcp;
}
static inline void
krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags)
{
raw_spin_unlock_irqrestore(&krcp->lock, flags);
}
static inline struct kvfree_rcu_bulk_data *
get_cached_bnode(struct kfree_rcu_cpu *krcp)
{
if (!krcp->nr_bkv_objs)
return NULL;
WRITE_ONCE(krcp->nr_bkv_objs, krcp->nr_bkv_objs - 1);
return (struct kvfree_rcu_bulk_data *)
llist_del_first(&krcp->bkvcache);
}
static inline bool
put_cached_bnode(struct kfree_rcu_cpu *krcp,
struct kvfree_rcu_bulk_data *bnode)
{
// Check the limit.
if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
return false;
llist_add((struct llist_node *) bnode, &krcp->bkvcache);
WRITE_ONCE(krcp->nr_bkv_objs, krcp->nr_bkv_objs + 1);
return true;
}
static int
drain_page_cache(struct kfree_rcu_cpu *krcp)
{
unsigned long flags;
struct llist_node *page_list, *pos, *n;
int freed = 0;
raw_spin_lock_irqsave(&krcp->lock, flags);
page_list = llist_del_all(&krcp->bkvcache);
WRITE_ONCE(krcp->nr_bkv_objs, 0);
raw_spin_unlock_irqrestore(&krcp->lock, flags);
llist_for_each_safe(pos, n, page_list) {
free_page((unsigned long)pos);
freed++;
}
return freed;
}
/*
* This function is invoked in workqueue context after a grace period.
* It frees all the objects queued on ->bkvhead_free or ->head_free.
*/
static void kfree_rcu_work(struct work_struct *work)
{
unsigned long flags;
struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS], *bnext;
struct rcu_head *head, *next;
struct kfree_rcu_cpu *krcp;
struct kfree_rcu_cpu_work *krwp;
int i, j;
krwp = container_of(to_rcu_work(work),
struct kfree_rcu_cpu_work, rcu_work);
krcp = krwp->krcp;
raw_spin_lock_irqsave(&krcp->lock, flags);
// Channels 1 and 2.
for (i = 0; i < FREE_N_CHANNELS; i++) {
bkvhead[i] = krwp->bkvhead_free[i];
krwp->bkvhead_free[i] = NULL;
}
// Channel 3.
head = krwp->head_free;
krwp->head_free = NULL;
raw_spin_unlock_irqrestore(&krcp->lock, flags);
// Handle the first two channels.
for (i = 0; i < FREE_N_CHANNELS; i++) {
for (; bkvhead[i]; bkvhead[i] = bnext) {
bnext = bkvhead[i]->next;
debug_rcu_bhead_unqueue(bkvhead[i]);
rcu_lock_acquire(&rcu_callback_map);
if (i == 0) { // kmalloc() / kfree().
trace_rcu_invoke_kfree_bulk_callback(
rcu_state.name, bkvhead[i]->nr_records,
bkvhead[i]->records);
kfree_bulk(bkvhead[i]->nr_records,
bkvhead[i]->records);
} else { // vmalloc() / vfree().
for (j = 0; j < bkvhead[i]->nr_records; j++) {
trace_rcu_invoke_kvfree_callback(
rcu_state.name,
bkvhead[i]->records[j], 0);
vfree(bkvhead[i]->records[j]);
}
}
rcu_lock_release(&rcu_callback_map);
raw_spin_lock_irqsave(&krcp->lock, flags);
if (put_cached_bnode(krcp, bkvhead[i]))
bkvhead[i] = NULL;
raw_spin_unlock_irqrestore(&krcp->lock, flags);
if (bkvhead[i])
free_page((unsigned long) bkvhead[i]);
cond_resched_tasks_rcu_qs();
}
}
/*
* This is used when the "bulk" path can not be used for the
* double-argument of kvfree_rcu(). This happens when the
* page-cache is empty, which means that objects are instead
* queued on a linked list through their rcu_head structures.
* This list is named "Channel 3".
*/
for (; head; head = next) {
unsigned long offset = (unsigned long)head->func;
void *ptr = (void *)head - offset;
next = head->next;
debug_rcu_head_unqueue((struct rcu_head *)ptr);
rcu_lock_acquire(&rcu_callback_map);
trace_rcu_invoke_kvfree_callback(rcu_state.name, head, offset);
if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset)))
kvfree(ptr);
rcu_lock_release(&rcu_callback_map);
cond_resched_tasks_rcu_qs();
}
}
/*
* This function is invoked after the KFREE_DRAIN_JIFFIES timeout.
*/
static void kfree_rcu_monitor(struct work_struct *work)
{
struct kfree_rcu_cpu *krcp = container_of(work,
struct kfree_rcu_cpu, monitor_work.work);
unsigned long flags;
int i, j;
raw_spin_lock_irqsave(&krcp->lock, flags);
// Attempt to start a new batch.
for (i = 0; i < KFREE_N_BATCHES; i++) {
struct kfree_rcu_cpu_work *krwp = &(krcp->krw_arr[i]);
// Try to detach bkvhead or head and attach it over any
// available corresponding free channel. It can be that
// a previous RCU batch is in progress, it means that
// immediately to queue another one is not possible so
// in that case the monitor work is rearmed.
if ((krcp->bkvhead[0] && !krwp->bkvhead_free[0]) ||
(krcp->bkvhead[1] && !krwp->bkvhead_free[1]) ||
(krcp->head && !krwp->head_free)) {
// Channel 1 corresponds to the SLAB-pointer bulk path.
// Channel 2 corresponds to vmalloc-pointer bulk path.
for (j = 0; j < FREE_N_CHANNELS; j++) {
if (!krwp->bkvhead_free[j]) {
krwp->bkvhead_free[j] = krcp->bkvhead[j];
krcp->bkvhead[j] = NULL;
}
}
// Channel 3 corresponds to both SLAB and vmalloc
// objects queued on the linked list.
if (!krwp->head_free) {
krwp->head_free = krcp->head;
krcp->head = NULL;
}
WRITE_ONCE(krcp->count, 0);
// One work is per one batch, so there are three
// "free channels", the batch can handle. It can
// be that the work is in the pending state when
// channels have been detached following by each
// other.
queue_rcu_work(system_wq, &krwp->rcu_work);
}
}
// If there is nothing to detach, it means that our job is
// successfully done here. In case of having at least one
// of the channels that is still busy we should rearm the
// work to repeat an attempt. Because previous batches are
// still in progress.
if (!krcp->bkvhead[0] && !krcp->bkvhead[1] && !krcp->head)
krcp->monitor_todo = false;
else
schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
raw_spin_unlock_irqrestore(&krcp->lock, flags);
}
static enum hrtimer_restart
schedule_page_work_fn(struct hrtimer *t)
{
struct kfree_rcu_cpu *krcp =
container_of(t, struct kfree_rcu_cpu, hrtimer);
queue_delayed_work(system_highpri_wq, &krcp->page_cache_work, 0);
return HRTIMER_NORESTART;
}
static void fill_page_cache_func(struct work_struct *work)
{
struct kvfree_rcu_bulk_data *bnode;
struct kfree_rcu_cpu *krcp =
container_of(work, struct kfree_rcu_cpu,
page_cache_work.work);
unsigned long flags;
int nr_pages;
bool pushed;
int i;
nr_pages = atomic_read(&krcp->backoff_page_cache_fill) ?
1 : rcu_min_cached_objs;
for (i = 0; i < nr_pages; i++) {
bnode = (struct kvfree_rcu_bulk_data *)
__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
if (bnode) {
raw_spin_lock_irqsave(&krcp->lock, flags);
pushed = put_cached_bnode(krcp, bnode);
raw_spin_unlock_irqrestore(&krcp->lock, flags);
if (!pushed) {
free_page((unsigned long) bnode);
break;
}
}
}
atomic_set(&krcp->work_in_progress, 0);
atomic_set(&krcp->backoff_page_cache_fill, 0);
}
static void
run_page_cache_worker(struct kfree_rcu_cpu *krcp)
{
if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
!atomic_xchg(&krcp->work_in_progress, 1)) {
if (atomic_read(&krcp->backoff_page_cache_fill)) {
queue_delayed_work(system_wq,
&krcp->page_cache_work,
msecs_to_jiffies(rcu_delay_page_cache_fill_msec));
} else {
hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
krcp->hrtimer.function = schedule_page_work_fn;
hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL);
}
}
}
// Record ptr in a page managed by krcp, with the pre-krc_this_cpu_lock()
// state specified by flags. If can_alloc is true, the caller must
// be schedulable and not be holding any locks or mutexes that might be
// acquired by the memory allocator or anything that it might invoke.
// Returns true if ptr was successfully recorded, else the caller must
// use a fallback.
static inline bool
add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp,
unsigned long *flags, void *ptr, bool can_alloc)
{
struct kvfree_rcu_bulk_data *bnode;
int idx;
*krcp = krc_this_cpu_lock(flags);
if (unlikely(!(*krcp)->initialized))
return false;
idx = !!is_vmalloc_addr(ptr);
/* Check if a new block is required. */
if (!(*krcp)->bkvhead[idx] ||
(*krcp)->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
bnode = get_cached_bnode(*krcp);
if (!bnode && can_alloc) {
krc_this_cpu_unlock(*krcp, *flags);
// __GFP_NORETRY - allows a light-weight direct reclaim
// what is OK from minimizing of fallback hitting point of
// view. Apart of that it forbids any OOM invoking what is
// also beneficial since we are about to release memory soon.
//
// __GFP_NOMEMALLOC - prevents from consuming of all the
// memory reserves. Please note we have a fallback path.
//
// __GFP_NOWARN - it is supposed that an allocation can
// be failed under low memory or high memory pressure
// scenarios.
bnode = (struct kvfree_rcu_bulk_data *)
__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
*krcp = krc_this_cpu_lock(flags);
}
if (!bnode)
return false;
/* Initialize the new block. */
bnode->nr_records = 0;
bnode->next = (*krcp)->bkvhead[idx];
/* Attach it to the head. */
(*krcp)->bkvhead[idx] = bnode;
}
/* Finally insert. */
(*krcp)->bkvhead[idx]->records
[(*krcp)->bkvhead[idx]->nr_records++] = ptr;
return true;
}
/*
* Queue a request for lazy invocation of the appropriate free routine
* after a grace period. Please note that three paths are maintained,
* two for the common case using arrays of pointers and a third one that
* is used only when the main paths cannot be used, for example, due to
* memory pressure.
*
* Each kvfree_call_rcu() request is added to a batch. The batch will be drained
* every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will
* be free'd in workqueue context. This allows us to: batch requests together to
* reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load.
*/
void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
{
unsigned long flags;
struct kfree_rcu_cpu *krcp;
bool success;
void *ptr;
if (head) {
ptr = (void *) head - (unsigned long) func;
} else {
/*
* Please note there is a limitation for the head-less
* variant, that is why there is a clear rule for such
* objects: it can be used from might_sleep() context
* only. For other places please embed an rcu_head to
* your data.
*/
might_sleep();
ptr = (unsigned long *) func;
}
// Queue the object but don't yet schedule the batch.
if (debug_rcu_head_queue(ptr)) {
// Probable double kfree_rcu(), just leak.
WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n",
__func__, head);
// Mark as success and leave.
return;
}
kasan_record_aux_stack(ptr);
success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head);
if (!success) {
run_page_cache_worker(krcp);
if (head == NULL)
// Inline if kvfree_rcu(one_arg) call.
goto unlock_return;
head->func = func;
head->next = krcp->head;
krcp->head = head;
success = true;
}
WRITE_ONCE(krcp->count, krcp->count + 1);
// Set timer to drain after KFREE_DRAIN_JIFFIES.
if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
!krcp->monitor_todo) {
krcp->monitor_todo = true;
schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
}
unlock_return:
krc_this_cpu_unlock(krcp, flags);
/*
* Inline kvfree() after synchronize_rcu(). We can do
* it from might_sleep() context only, so the current
* CPU can pass the QS state.
*/
if (!success) {
debug_rcu_head_unqueue((struct rcu_head *) ptr);
synchronize_rcu();
kvfree(ptr);
}
}
EXPORT_SYMBOL_GPL(kvfree_call_rcu);
static unsigned long
kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
{
int cpu;
unsigned long count = 0;
/* Snapshot count of all CPUs */
for_each_possible_cpu(cpu) {
struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
count += READ_ONCE(krcp->count);
count += READ_ONCE(krcp->nr_bkv_objs);
atomic_set(&krcp->backoff_page_cache_fill, 1);
}
return count;
}
static unsigned long
kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
int cpu, freed = 0;
for_each_possible_cpu(cpu) {
int count;
struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
count = krcp->count;
count += drain_page_cache(krcp);
kfree_rcu_monitor(&krcp->monitor_work.work);
sc->nr_to_scan -= count;
freed += count;
if (sc->nr_to_scan <= 0)
break;
}
return freed == 0 ? SHRINK_STOP : freed;
}
static struct shrinker kfree_rcu_shrinker = {
.count_objects = kfree_rcu_shrink_count,
.scan_objects = kfree_rcu_shrink_scan,
.batch = 0,
.seeks = DEFAULT_SEEKS,
};
void __init kfree_rcu_scheduler_running(void)
{
int cpu;
unsigned long flags;
for_each_possible_cpu(cpu) {
struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
raw_spin_lock_irqsave(&krcp->lock, flags);
if ((!krcp->bkvhead[0] && !krcp->bkvhead[1] && !krcp->head) ||
krcp->monitor_todo) {
raw_spin_unlock_irqrestore(&krcp->lock, flags);
continue;
}
krcp->monitor_todo = true;
schedule_delayed_work_on(cpu, &krcp->monitor_work,
KFREE_DRAIN_JIFFIES);
raw_spin_unlock_irqrestore(&krcp->lock, flags);
}
}
/*
* During early boot, any blocking grace-period wait automatically
* implies a grace period. Later on, this is never the case for PREEMPTION.
*
* However, because a context switch is a grace period for !PREEMPTION, 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_rcu() or synchronize_rcu_expedited(). 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 int rcu_blocking_is_gp(void)
{
int ret;
if (IS_ENABLED(CONFIG_PREEMPTION))
return rcu_scheduler_active == RCU_SCHEDULER_INACTIVE;
might_sleep(); /* Check for RCU read-side critical section. */
preempt_disable();
/*
* If the rcu_state.n_online_cpus counter is equal to one,
* there is only one CPU, and that CPU sees all prior accesses
* made by any CPU that was online at the time of its access.
* Furthermore, if this counter is equal to one, its value cannot
* change until after the preempt_enable() below.
*
* Furthermore, if rcu_state.n_online_cpus is equal to one here,
* all later CPUs (both this one and any that come online later
* on) are guaranteed to see all accesses prior to this point
* in the code, without the need for additional memory barriers.
* Those memory barriers are provided by CPU-hotplug code.
*/
ret = READ_ONCE(rcu_state.n_online_cpus) <= 1;
preempt_enable();
return ret;
}
/**
* synchronize_rcu - wait until a grace period has elapsed.
*
* Control will return to the caller some time after a full grace
* period has elapsed, in other words after all currently executing RCU
* read-side critical sections have completed. Note, however, that
* upon return from synchronize_rcu(), the caller might well be executing
* concurrently with new RCU read-side critical sections that began while
* synchronize_rcu() was waiting.
*
* RCU read-side critical sections are delimited by rcu_read_lock()
* and rcu_read_unlock(), and may be nested. In addition, but only in
* v5.0 and later, regions of code across which interrupts, preemption,
* or softirqs have been disabled also serve as RCU read-side critical
* sections. This includes hardware interrupt handlers, softirq handlers,
* and NMI handlers.
*
* Note that this guarantee implies further memory-ordering guarantees.
* On systems with more than one CPU, when synchronize_rcu() returns,
* each CPU is guaranteed to have executed a full memory barrier since
* the end of its last RCU read-side critical section whose beginning
* preceded the call to synchronize_rcu(). In addition, each CPU having
* an RCU read-side critical section that extends beyond the return from
* synchronize_rcu() is guaranteed to have executed a full memory barrier
* after the beginning of synchronize_rcu() 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_rcu(), 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_rcu() -- even if CPU A and CPU B are the same CPU (but
* again only if the system has more than one CPU).
*
* Implementation of these memory-ordering guarantees is described here:
* Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst.
*/
void synchronize_rcu(void)
{
RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
lock_is_held(&rcu_lock_map) ||
lock_is_held(&rcu_sched_lock_map),
"Illegal synchronize_rcu() in RCU read-side critical section");
if (rcu_blocking_is_gp())
return; // Context allows vacuous grace periods.
if (rcu_gp_is_expedited())
synchronize_rcu_expedited();
else
wait_rcu_gp(call_rcu);
}
EXPORT_SYMBOL_GPL(synchronize_rcu);
/**
* get_state_synchronize_rcu - Snapshot current RCU state
*
* Returns a cookie that is used by a later call to cond_synchronize_rcu()
* or poll_state_synchronize_rcu() to determine whether or not a full
* grace period has elapsed in the meantime.
*/
unsigned long get_state_synchronize_rcu(void)
{
/*
* Any prior manipulation of RCU-protected data must happen
* before the load from ->gp_seq.
*/
smp_mb(); /* ^^^ */
return rcu_seq_snap(&rcu_state.gp_seq);
}
EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
/**
* start_poll_synchronize_rcu - Snapshot and start RCU grace period
*
* Returns a cookie that is used by a later call to cond_synchronize_rcu()
* or poll_state_synchronize_rcu() to determine whether or not a full
* grace period has elapsed in the meantime. If the needed grace period
* is not already slated to start, notifies RCU core of the need for that
* grace period.
*
* Interrupts must be enabled for the case where it is necessary to awaken
* the grace-period kthread.
*/
unsigned long start_poll_synchronize_rcu(void)
{
unsigned long flags;
unsigned long gp_seq = get_state_synchronize_rcu();
bool needwake;
struct rcu_data *rdp;
struct rcu_node *rnp;
lockdep_assert_irqs_enabled();
local_irq_save(flags);
rdp = this_cpu_ptr(&rcu_data);
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp); // irqs already disabled.
needwake = rcu_start_this_gp(rnp, rdp, gp_seq);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
if (needwake)
rcu_gp_kthread_wake();
return gp_seq;
}
EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
/**
* poll_state_synchronize_rcu - Conditionally wait for an RCU grace period
*
* @oldstate: value from get_state_synchronize_rcu() or start_poll_synchronize_rcu()
*
* If a full RCU grace period has elapsed since the earlier call from
* which oldstate was obtained, return @true, otherwise return @false.
* If @false is returned, it is the caller's responsibility to invoke this
* function later on until it does return @true. Alternatively, the caller
* can explicitly wait for a grace period, for example, by passing @oldstate
* to cond_synchronize_rcu() or by directly invoking synchronize_rcu().
*
* Yes, this function does not take counter wrap into account.
* But counter wrap is harmless. If the counter wraps, we have waited for
* more than 2 billion grace periods (and way more on a 64-bit system!).
* Those needing to keep oldstate values for very long time periods
* (many hours even on 32-bit systems) should check them occasionally
* and either refresh them or set a flag indicating that the grace period
* has completed.
*
* This function provides the same memory-ordering guarantees that
* would be provided by a synchronize_rcu() that was invoked at the call
* to the function that provided @oldstate, and that returned at the end
* of this function.
*/
bool poll_state_synchronize_rcu(unsigned long oldstate)
{
if (rcu_seq_done(&rcu_state.gp_seq, oldstate)) {
smp_mb(); /* Ensure GP ends before subsequent accesses. */
return true;
}
return false;
}
EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
/**
* cond_synchronize_rcu - Conditionally wait for an RCU grace period
*
* @oldstate: value from get_state_synchronize_rcu() or start_poll_synchronize_rcu()
*
* If a full RCU grace period has elapsed since the earlier call to
* get_state_synchronize_rcu() or start_poll_synchronize_rcu(), just return.
* Otherwise, invoke synchronize_rcu() to wait for a full grace period.
*
* Yes, this function does not take counter wrap into account. But
* counter wrap is harmless. If the counter wraps, we have waited for
* more than 2 billion grace periods (and way more on a 64-bit system!),
* so waiting for one additional grace period should be just fine.
*
* This function provides the same memory-ordering guarantees that
* would be provided by a synchronize_rcu() that was invoked at the call
* to the function that provided @oldstate, and that returned at the end
* of this function.
*/
void cond_synchronize_rcu(unsigned long oldstate)
{
if (!poll_state_synchronize_rcu(oldstate))
synchronize_rcu();
}
EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
/*
* Check to see if there is any immediate RCU-related work to be done by
* the current CPU, returning 1 if so and zero otherwise. 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(int user)
{
bool gp_in_progress;
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rdp->mynode;
lockdep_assert_irqs_disabled();
/* Check for CPU stalls, if enabled. */
check_cpu_stall(rdp);
/* Does this CPU need a deferred NOCB wakeup? */
if (rcu_nocb_need_deferred_wakeup(rdp, RCU_NOCB_WAKE))
return 1;
/* Is this a nohz_full CPU in userspace or idle? (Ignore RCU if so.) */
if ((user || rcu_is_cpu_rrupt_from_idle()) && rcu_nohz_full_cpu())
return 0;
/* Is the RCU core waiting for a quiescent state from this CPU? */
gp_in_progress = rcu_gp_in_progress();
if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm && gp_in_progress)
return 1;
/* Does this CPU have callbacks ready to invoke? */
if (!rcu_rdp_is_offloaded(rdp) &&
rcu_segcblist_ready_cbs(&rdp->cblist))
return 1;
/* Has RCU gone idle with this CPU needing another grace period? */
if (!gp_in_progress && rcu_segcblist_is_enabled(&rdp->cblist) &&
!rcu_rdp_is_offloaded(rdp) &&
!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
return 1;
/* Have RCU grace period completed or started? */
if (rcu_seq_current(&rnp->gp_seq) != rdp->gp_seq ||
unlikely(READ_ONCE(rdp->gpwrap))) /* outside lock */
return 1;
/* nothing to do */
return 0;
}
/*
* Helper function for rcu_barrier() tracing. If tracing is disabled,
* the compiler is expected to optimize this away.
*/
static void rcu_barrier_trace(const char *s, int cpu, unsigned long done)
{
trace_rcu_barrier(rcu_state.name, s, cpu,
atomic_read(&rcu_state.barrier_cpu_count), done);
}
/*
* RCU callback function for rcu_barrier(). If we are last, wake
* up the task executing rcu_barrier().
*
* Note that the value of rcu_state.barrier_sequence must be captured
* before the atomic_dec_and_test(). Otherwise, if this CPU is not last,
* other CPUs might count the value down to zero before this CPU gets
* around to invoking rcu_barrier_trace(), which might result in bogus
* data from the next instance of rcu_barrier().
*/
static void rcu_barrier_callback(struct rcu_head *rhp)
{
unsigned long __maybe_unused s = rcu_state.barrier_sequence;
if (atomic_dec_and_test(&rcu_state.barrier_cpu_count)) {
rcu_barrier_trace(TPS("LastCB"), -1, s);
complete(&rcu_state.barrier_completion);
} else {
rcu_barrier_trace(TPS("CB"), -1, s);
}
}
/*
* Called with preemption disabled, and from cross-cpu IRQ context.
*/
static void rcu_barrier_func(void *cpu_in)
{
uintptr_t cpu = (uintptr_t)cpu_in;
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
rcu_barrier_trace(TPS("IRQ"), -1, rcu_state.barrier_sequence);
rdp->barrier_head.func = rcu_barrier_callback;
debug_rcu_head_queue(&rdp->barrier_head);
rcu_nocb_lock(rdp);
WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head)) {
atomic_inc(&rcu_state.barrier_cpu_count);
} else {
debug_rcu_head_unqueue(&rdp->barrier_head);
rcu_barrier_trace(TPS("IRQNQ"), -1,
rcu_state.barrier_sequence);
}
rcu_nocb_unlock(rdp);
}
/**
* rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
*
* Note that this primitive does not necessarily wait for an RCU grace period
* to complete. For example, if there are no RCU callbacks queued anywhere
* in the system, then rcu_barrier() is within its rights to return
* immediately, without waiting for anything, much less an RCU grace period.
*/
void rcu_barrier(void)
{
uintptr_t cpu;
struct rcu_data *rdp;
unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence);
rcu_barrier_trace(TPS("Begin"), -1, s);
/* Take mutex to serialize concurrent rcu_barrier() requests. */
mutex_lock(&rcu_state.barrier_mutex);
/* Did someone else do our work for us? */
if (rcu_seq_done(&rcu_state.barrier_sequence, s)) {
rcu_barrier_trace(TPS("EarlyExit"), -1,
rcu_state.barrier_sequence);
smp_mb(); /* caller's subsequent code after above check. */
mutex_unlock(&rcu_state.barrier_mutex);
return;
}
/* Mark the start of the barrier operation. */
rcu_seq_start(&rcu_state.barrier_sequence);
rcu_barrier_trace(TPS("Inc1"), -1, rcu_state.barrier_sequence);
/*
* Initialize the count to two rather than to zero in order
* to avoid a too-soon return to zero in case of an immediate
* invocation of the just-enqueued callback (or preemption of
* this task). Exclude CPU-hotplug operations to ensure that no
* offline non-offloaded CPU has callbacks queued.
*/
init_completion(&rcu_state.barrier_completion);
atomic_set(&rcu_state.barrier_cpu_count, 2);
cpus_read_lock();
/*
* 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) {
rdp = per_cpu_ptr(&rcu_data, cpu);
if (cpu_is_offline(cpu) &&
!rcu_rdp_is_offloaded(rdp))
continue;
if (rcu_segcblist_n_cbs(&rdp->cblist) && cpu_online(cpu)) {
rcu_barrier_trace(TPS("OnlineQ"), cpu,
rcu_state.barrier_sequence);
smp_call_function_single(cpu, rcu_barrier_func, (void *)cpu, 1);
} else if (rcu_segcblist_n_cbs(&rdp->cblist) &&
cpu_is_offline(cpu)) {
rcu_barrier_trace(TPS("OfflineNoCBQ"), cpu,
rcu_state.barrier_sequence);
local_irq_disable();
rcu_barrier_func((void *)cpu);
local_irq_enable();
} else if (cpu_is_offline(cpu)) {
rcu_barrier_trace(TPS("OfflineNoCBNoQ"), cpu,
rcu_state.barrier_sequence);
} else {
rcu_barrier_trace(TPS("OnlineNQ"), cpu,
rcu_state.barrier_sequence);
}
}
cpus_read_unlock();
/*
* Now that we have an rcu_barrier_callback() callback on each
* CPU, and thus each counted, remove the initial count.
*/
if (atomic_sub_and_test(2, &rcu_state.barrier_cpu_count))
complete(&rcu_state.barrier_completion);
/* Wait for all rcu_barrier_callback() callbacks to be invoked. */
wait_for_completion(&rcu_state.barrier_completion);
/* Mark the end of the barrier operation. */
rcu_barrier_trace(TPS("Inc2"), -1, rcu_state.barrier_sequence);
rcu_seq_end(&rcu_state.barrier_sequence);
/* Other rcu_barrier() invocations can now safely proceed. */
mutex_unlock(&rcu_state.barrier_mutex);
}
EXPORT_SYMBOL_GPL(rcu_barrier);
/*
* Propagate ->qsinitmask bits up the rcu_node tree to account for the
* first CPU in a given leaf rcu_node structure coming online. The caller
* must hold the corresponding leaf rcu_node ->lock with interrupts
* disabled.
*/
static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
{
long mask;
long oldmask;
struct rcu_node *rnp = rnp_leaf;
raw_lockdep_assert_held_rcu_node(rnp_leaf);
WARN_ON_ONCE(rnp->wait_blkd_tasks);
for (;;) {
mask = rnp->grpmask;
rnp = rnp->parent;
if (rnp == NULL)
return;
raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */
oldmask = rnp->qsmaskinit;
rnp->qsmaskinit |= mask;
raw_spin_unlock_rcu_node(rnp); /* Interrupts remain disabled. */
if (oldmask)
return;
}
}
/*
* Do boot-time initialization of a CPU's per-CPU RCU data.
*/
static void __init
rcu_boot_init_percpu_data(int cpu)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
/* Set up local state, ensuring consistent view of global state. */
rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu);
INIT_WORK(&rdp->strict_work, strict_work_handler);
WARN_ON_ONCE(rdp->dynticks_nesting != 1);
WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp)));
rdp->rcu_ofl_gp_seq = rcu_state.gp_seq;
rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED;
rdp->rcu_onl_gp_seq = rcu_state.gp_seq;
rdp->rcu_onl_gp_flags = RCU_GP_CLEANED;
rdp->cpu = cpu;
rcu_boot_init_nocb_percpu_data(rdp);
}
/*
* Invoked early in the CPU-online process, when pretty much all services
* are available. The incoming CPU is not present.
*
* Initializes 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->gp_seq access due to the fact that this
* CPU cannot possibly have any non-offloaded RCU callbacks in flight yet.
* And any offloaded callbacks are being numbered elsewhere.
*/
int rcutree_prepare_cpu(unsigned int cpu)
{
unsigned long flags;
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
struct rcu_node *rnp = rcu_get_root();
/* Set up local state, ensuring consistent view of global state. */
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
rdp->blimit = blimit;
rdp->dynticks_nesting = 1; /* CPU not up, no tearing. */
raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
/*
* Only non-NOCB CPUs that didn't have early-boot callbacks need to be
* (re-)initialized.
*/
if (!rcu_segcblist_is_enabled(&rdp->cblist))
rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */
/*
* Add CPU to leaf rcu_node pending-online bitmask. Any needed
* propagation up the rcu_node tree will happen at the beginning
* of the next grace period.
*/
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
rdp->beenonline = true; /* We have now been online. */
rdp->gp_seq = READ_ONCE(rnp->gp_seq);
rdp->gp_seq_needed = rdp->gp_seq;
rdp->cpu_no_qs.b.norm = true;
rdp->core_needs_qs = false;
rdp->rcu_iw_pending = false;
rdp->rcu_iw = IRQ_WORK_INIT_HARD(rcu_iw_handler);
rdp->rcu_iw_gp_seq = rdp->gp_seq - 1;
trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl"));
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rcu_spawn_one_boost_kthread(rnp);
rcu_spawn_cpu_nocb_kthread(cpu);
WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus + 1);
return 0;
}
/*
* Update RCU priority boot kthread affinity for CPU-hotplug changes.
*/
static void rcutree_affinity_setting(unsigned int cpu, int outgoing)
{
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
rcu_boost_kthread_setaffinity(rdp->mynode, outgoing);
}
/*
* Near the end of the CPU-online process. Pretty much all services
* enabled, and the CPU is now very much alive.
*/
int rcutree_online_cpu(unsigned int cpu)
{
unsigned long flags;
struct rcu_data *rdp;
struct rcu_node *rnp;
rdp = per_cpu_ptr(&rcu_data, cpu);
rnp = rdp->mynode;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rnp->ffmask |= rdp->grpmask;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
return 0; /* Too early in boot for scheduler work. */
sync_sched_exp_online_cleanup(cpu);
rcutree_affinity_setting(cpu, -1);
// Stop-machine done, so allow nohz_full to disable tick.
tick_dep_clear(TICK_DEP_BIT_RCU);
return 0;
}
/*
* Near the beginning of the process. The CPU is still very much alive
* with pretty much all services enabled.
*/
int rcutree_offline_cpu(unsigned int cpu)
{
unsigned long flags;
struct rcu_data *rdp;
struct rcu_node *rnp;
rdp = per_cpu_ptr(&rcu_data, cpu);
rnp = rdp->mynode;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rnp->ffmask &= ~rdp->grpmask;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rcutree_affinity_setting(cpu, cpu);
// nohz_full CPUs need the tick for stop-machine to work quickly
tick_dep_set(TICK_DEP_BIT_RCU);
return 0;
}
/*
* Mark the specified CPU as being online so that subsequent grace periods
* (both expedited and normal) will wait on it. Note that this means that
* incoming CPUs are not allowed to use RCU read-side critical sections
* until this function is called. Failing to observe this restriction
* will result in lockdep splats.
*
* Note that this function is special in that it is invoked directly
* from the incoming CPU rather than from the cpuhp_step mechanism.
* This is because this function must be invoked at a precise location.
*/
void rcu_cpu_starting(unsigned int cpu)
{
unsigned long flags;
unsigned long mask;
struct rcu_data *rdp;
struct rcu_node *rnp;
bool newcpu;
rdp = per_cpu_ptr(&rcu_data, cpu);
if (rdp->cpu_started)
return;
rdp->cpu_started = true;
rnp = rdp->mynode;
mask = rdp->grpmask;
WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
WARN_ON_ONCE(!(rnp->ofl_seq & 0x1));
rcu_dynticks_eqs_online();
smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
raw_spin_lock_irqsave_rcu_node(rnp, flags);
WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask);
newcpu = !(rnp->expmaskinitnext & mask);
rnp->expmaskinitnext |= mask;
/* Allow lockless access for expedited grace periods. */
smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + newcpu); /* ^^^ */
ASSERT_EXCLUSIVE_WRITER(rcu_state.ncpus);
rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq);
rdp->rcu_onl_gp_flags = READ_ONCE(rcu_state.gp_flags);
/* An incoming CPU should never be blocking a grace period. */
if (WARN_ON_ONCE(rnp->qsmask & mask)) { /* RCU waiting on incoming CPU? */
rcu_disable_urgency_upon_qs(rdp);
/* Report QS -after- changing ->qsmaskinitnext! */
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
} else {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
WARN_ON_ONCE(rnp->ofl_seq & 0x1);
smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
}
/*
* The outgoing function has no further need of RCU, so remove it from
* the rcu_node tree's ->qsmaskinitnext bit masks.
*
* Note that this function is special in that it is invoked directly
* from the outgoing CPU rather than from the cpuhp_step mechanism.
* This is because this function must be invoked at a precise location.
*/
void rcu_report_dead(unsigned int cpu)
{
unsigned long flags;
unsigned long mask;
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
// Do any dangling deferred wakeups.
do_nocb_deferred_wakeup(rdp);
/* QS for any half-done expedited grace period. */
rcu_report_exp_rdp(rdp);
rcu_preempt_deferred_qs(current);
/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
mask = rdp->grpmask;
WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
WARN_ON_ONCE(!(rnp->ofl_seq & 0x1));
smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
raw_spin_lock(&rcu_state.ofl_lock);
raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq);
rdp->rcu_ofl_gp_flags = READ_ONCE(rcu_state.gp_flags);
if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */
/* Report quiescent state -before- changing ->qsmaskinitnext! */
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
raw_spin_lock_irqsave_rcu_node(rnp, flags);
}
WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
raw_spin_unlock(&rcu_state.ofl_lock);
smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
WARN_ON_ONCE(rnp->ofl_seq & 0x1);
rdp->cpu_started = false;
}
#ifdef CONFIG_HOTPLUG_CPU
/*
* The outgoing CPU has just passed through the dying-idle state, and we
* are being invoked from the CPU that was IPIed to continue the offline
* operation. Migrate the outgoing CPU's callbacks to the current CPU.
*/
void rcutree_migrate_callbacks(int cpu)
{
unsigned long flags;
struct rcu_data *my_rdp;
struct rcu_node *my_rnp;
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
bool needwake;
if (rcu_rdp_is_offloaded(rdp) ||
rcu_segcblist_empty(&rdp->cblist))
return; /* No callbacks to migrate. */
local_irq_save(flags);
my_rdp = this_cpu_ptr(&rcu_data);
my_rnp = my_rdp->mynode;
rcu_nocb_lock(my_rdp); /* irqs already disabled. */
WARN_ON_ONCE(!rcu_nocb_flush_bypass(my_rdp, NULL, jiffies));
raw_spin_lock_rcu_node(my_rnp); /* irqs already disabled. */
/* Leverage recent GPs and set GP for new callbacks. */
needwake = rcu_advance_cbs(my_rnp, rdp) ||
rcu_advance_cbs(my_rnp, my_rdp);
rcu_segcblist_merge(&my_rdp->cblist, &rdp->cblist);
needwake = needwake || rcu_advance_cbs(my_rnp, my_rdp);
rcu_segcblist_disable(&rdp->cblist);
WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) !=
!rcu_segcblist_n_cbs(&my_rdp->cblist));
if (rcu_rdp_is_offloaded(my_rdp)) {
raw_spin_unlock_rcu_node(my_rnp); /* irqs remain disabled. */
__call_rcu_nocb_wake(my_rdp, true, flags);
} else {
rcu_nocb_unlock(my_rdp); /* irqs remain disabled. */
raw_spin_unlock_irqrestore_rcu_node(my_rnp, flags);
}
if (needwake)
rcu_gp_kthread_wake();
lockdep_assert_irqs_enabled();
WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 ||
!rcu_segcblist_empty(&rdp->cblist),
"rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n",
cpu, rcu_segcblist_n_cbs(&rdp->cblist),
rcu_segcblist_first_cb(&rdp->cblist));
}
#endif
/*
* On non-huge systems, use expedited RCU grace periods to make suspend
* and hibernation run faster.
*/
static int rcu_pm_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
{
switch (action) {
case PM_HIBERNATION_PREPARE:
case PM_SUSPEND_PREPARE:
rcu_expedite_gp();
break;
case PM_POST_HIBERNATION:
case PM_POST_SUSPEND:
rcu_unexpedite_gp();
break;
default:
break;
}
return NOTIFY_OK;
}
/*
* Spawn the kthreads that handle RCU's grace periods.
*/
static int __init rcu_spawn_gp_kthread(void)
{
unsigned long flags;
int kthread_prio_in = kthread_prio;
struct rcu_node *rnp;
struct sched_param sp;
struct task_struct *t;
/* Force priority into range. */
if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 2
&& IS_BUILTIN(CONFIG_RCU_TORTURE_TEST))
kthread_prio = 2;
else if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1)
kthread_prio = 1;
else if (kthread_prio < 0)
kthread_prio = 0;
else if (kthread_prio > 99)
kthread_prio = 99;
if (kthread_prio != kthread_prio_in)
pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n",
kthread_prio, kthread_prio_in);
rcu_scheduler_fully_active = 1;
t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name);
if (WARN_ONCE(IS_ERR(t), "%s: Could not start grace-period kthread, OOM is now expected behavior\n", __func__))
return 0;
if (kthread_prio) {
sp.sched_priority = kthread_prio;
sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
}
rnp = rcu_get_root();
raw_spin_lock_irqsave_rcu_node(rnp, flags);
WRITE_ONCE(rcu_state.gp_activity, jiffies);
WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
// Reset .gp_activity and .gp_req_activity before setting .gp_kthread.
smp_store_release(&rcu_state.gp_kthread, t); /* ^^^ */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
wake_up_process(t);
rcu_spawn_nocb_kthreads();
rcu_spawn_boost_kthreads();
rcu_spawn_core_kthreads();
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 synchronous grace-period primitives (during which time, this idle
* task is booting the system, and such primitives are no-ops). After this
* function is called, any synchronous grace-period primitives are run as
* expedited, with the requesting task driving the grace period forward.
* A later core_initcall() rcu_set_runtime_mode() will switch to full
* runtime RCU functionality.
*/
void rcu_scheduler_starting(void)
{
WARN_ON(num_online_cpus() != 1);
WARN_ON(nr_context_switches() > 0);
rcu_test_sync_prims();
rcu_scheduler_active = RCU_SCHEDULER_INIT;
rcu_test_sync_prims();
}
/*
* Helper function for rcu_init() that initializes the rcu_state structure.
*/
static void __init rcu_init_one(void)
{
static const char * const buf[] = RCU_NODE_NAME_INIT;
static const char * const fqs[] = RCU_FQS_NAME_INIT;
static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
int levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */
int cpustride = 1;
int i;
int j;
struct rcu_node *rnp;
BUILD_BUG_ON(RCU_NUM_LVLS > ARRAY_SIZE(buf)); /* Fix buf[] init! */
/* Silence gcc 4.8 false positive about array index out of range. */
if (rcu_num_lvls <= 0 || rcu_num_lvls > RCU_NUM_LVLS)
panic("rcu_init_one: rcu_num_lvls out of range");
/* Initialize the level-tracking arrays. */
for (i = 1; i < rcu_num_lvls; i++)
rcu_state.level[i] =
rcu_state.level[i - 1] + num_rcu_lvl[i - 1];
rcu_init_levelspread(levelspread, num_rcu_lvl);
/* Initialize the elements themselves, starting from the leaves. */
for (i = rcu_num_lvls - 1; i >= 0; i--) {
cpustride *= levelspread[i];
rnp = rcu_state.level[i];
for (j = 0; j < num_rcu_lvl[i]; j++, rnp++) {
raw_spin_lock_init(&ACCESS_PRIVATE(rnp, lock));
lockdep_set_class_and_name(&ACCESS_PRIVATE(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->gp_seq = rcu_state.gp_seq;
rnp->gp_seq_needed = rcu_state.gp_seq;
rnp->completedqs = rcu_state.gp_seq;
rnp->qsmask = 0;
rnp->qsmaskinit = 0;
rnp->grplo = j * cpustride;
rnp->grphi = (j + 1) * cpustride - 1;
if (rnp->grphi >= nr_cpu_ids)
rnp->grphi = nr_cpu_ids - 1;
if (i == 0) {
rnp->grpnum = 0;
rnp->grpmask = 0;
rnp->parent = NULL;
} else {
rnp->grpnum = j % levelspread[i - 1];
rnp->grpmask = BIT(rnp->grpnum);
rnp->parent = rcu_state.level[i - 1] +
j / levelspread[i - 1];
}
rnp->level = i;
INIT_LIST_HEAD(&rnp->blkd_tasks);
rcu_init_one_nocb(rnp);
init_waitqueue_head(&rnp->exp_wq[0]);
init_waitqueue_head(&rnp->exp_wq[1]);
init_waitqueue_head(&rnp->exp_wq[2]);
init_waitqueue_head(&rnp->exp_wq[3]);
spin_lock_init(&rnp->exp_lock);
}
}
init_swait_queue_head(&rcu_state.gp_wq);
init_swait_queue_head(&rcu_state.expedited_wq);
rnp = rcu_first_leaf_node();
for_each_possible_cpu(i) {
while (i > rnp->grphi)
rnp++;
per_cpu_ptr(&rcu_data, i)->mynode = rnp;
rcu_boot_init_percpu_data(i);
}
}
/*
* Compute the rcu_node tree geometry from kernel parameters. This cannot
* replace the definitions in tree.h because those are needed to size
* the ->node array in the rcu_state structure.
*/
void rcu_init_geometry(void)
{
ulong d;
int i;
static unsigned long old_nr_cpu_ids;
int rcu_capacity[RCU_NUM_LVLS];
static bool initialized;
if (initialized) {
/*
* Warn if setup_nr_cpu_ids() had not yet been invoked,
* unless nr_cpus_ids == NR_CPUS, in which case who cares?
*/
WARN_ON_ONCE(old_nr_cpu_ids != nr_cpu_ids);
return;
}
old_nr_cpu_ids = nr_cpu_ids;
initialized = true;
/*
* 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;
adjust_jiffies_till_sched_qs();
/* If the compile-time values are accurate, just leave. */
if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
nr_cpu_ids == NR_CPUS)
return;
pr_info("Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n",
rcu_fanout_leaf, nr_cpu_ids);
/*
* The boot-time rcu_fanout_leaf parameter must be at least two
* and cannot exceed the number of bits in the rcu_node masks.
* Complain and fall back to the compile-time values if this
* limit is exceeded.
*/
if (rcu_fanout_leaf < 2 ||
rcu_fanout_leaf > sizeof(unsigned long) * 8) {
rcu_fanout_leaf = RCU_FANOUT_LEAF;
WARN_ON(1);
return;
}
/*
* Compute number of nodes that can be handled an rcu_node tree
* with the given number of levels.
*/
rcu_capacity[0] = rcu_fanout_leaf;
for (i = 1; i < RCU_NUM_LVLS; i++)
rcu_capacity[i] = rcu_capacity[i - 1] * RCU_FANOUT;
/*
* The tree must be able to accommodate the configured number of CPUs.
* If this limit is exceeded, fall back to the compile-time values.
*/
if (nr_cpu_ids > rcu_capacity[RCU_NUM_LVLS - 1]) {
rcu_fanout_leaf = RCU_FANOUT_LEAF;
WARN_ON(1);
return;
}
/* Calculate the number of levels in the tree. */
for (i = 0; nr_cpu_ids > rcu_capacity[i]; i++) {
}
rcu_num_lvls = i + 1;
/* Calculate the number of rcu_nodes at each level of the tree. */
for (i = 0; i < rcu_num_lvls; i++) {
int cap = rcu_capacity[(rcu_num_lvls - 1) - i];
num_rcu_lvl[i] = DIV_ROUND_UP(nr_cpu_ids, cap);
}
/* Calculate the total number of rcu_node structures. */
rcu_num_nodes = 0;
for (i = 0; i < rcu_num_lvls; i++)
rcu_num_nodes += num_rcu_lvl[i];
}
/*
* Dump out the structure of the rcu_node combining tree associated
* with the rcu_state structure.
*/
static void __init rcu_dump_rcu_node_tree(void)
{
int level = 0;
struct rcu_node *rnp;
pr_info("rcu_node tree layout dump\n");
pr_info(" ");
rcu_for_each_node_breadth_first(rnp) {
if (rnp->level != level) {
pr_cont("\n");
pr_info(" ");
level = rnp->level;
}
pr_cont("%d:%d ^%d ", rnp->grplo, rnp->grphi, rnp->grpnum);
}
pr_cont("\n");
}
struct workqueue_struct *rcu_gp_wq;
struct workqueue_struct *rcu_par_gp_wq;
static void __init kfree_rcu_batch_init(void)
{
int cpu;
int i;
/* Clamp it to [0:100] seconds interval. */
if (rcu_delay_page_cache_fill_msec < 0 ||
rcu_delay_page_cache_fill_msec > 100 * MSEC_PER_SEC) {
rcu_delay_page_cache_fill_msec =
clamp(rcu_delay_page_cache_fill_msec, 0,
(int) (100 * MSEC_PER_SEC));
pr_info("Adjusting rcutree.rcu_delay_page_cache_fill_msec to %d ms.\n",
rcu_delay_page_cache_fill_msec);
}
for_each_possible_cpu(cpu) {
struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
for (i = 0; i < KFREE_N_BATCHES; i++) {
INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work);
krcp->krw_arr[i].krcp = krcp;
}
INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func);
krcp->initialized = true;
}
if (register_shrinker(&kfree_rcu_shrinker))
pr_err("Failed to register kfree_rcu() shrinker!\n");
}
void __init rcu_init(void)
{
int cpu;
rcu_early_boot_tests();
kfree_rcu_batch_init();
rcu_bootup_announce();
rcu_init_geometry();
rcu_init_one();
if (dump_tree)
rcu_dump_rcu_node_tree();
if (use_softirq)
open_softirq(RCU_SOFTIRQ, rcu_core_si);
/*
* We don't need protection against CPU-hotplug here because
* this is called early in boot, before either interrupts
* or the scheduler are operational.
*/
pm_notifier(rcu_pm_notify, 0);
for_each_online_cpu(cpu) {
rcutree_prepare_cpu(cpu);
rcu_cpu_starting(cpu);
rcutree_online_cpu(cpu);
}
/* Create workqueue for Tree SRCU and for expedited GPs. */
rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0);
WARN_ON(!rcu_gp_wq);
rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
WARN_ON(!rcu_par_gp_wq);
/* Fill in default value for rcutree.qovld boot parameter. */
/* -After- the rcu_node ->lock fields are initialized! */
if (qovld < 0)
qovld_calc = DEFAULT_RCU_QOVLD_MULT * qhimark;
else
qovld_calc = qovld;
}
#include "tree_stall.h"
#include "tree_exp.h"
#include "tree_nocb.h"
#include "tree_plugin.h"
|