summaryrefslogtreecommitdiff
path: root/kernel/sched/ext.c
blob: 5900b06fd0364c76bcca9a37e9ad9e76082b8560 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
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
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst
 *
 * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
 * Copyright (c) 2022 Tejun Heo <tj@kernel.org>
 * Copyright (c) 2022 David Vernet <dvernet@meta.com>
 */
#define SCX_OP_IDX(op)		(offsetof(struct sched_ext_ops, op) / sizeof(void (*)(void)))

enum scx_consts {
	SCX_DSP_DFL_MAX_BATCH		= 32,
	SCX_DSP_MAX_LOOPS		= 32,
	SCX_WATCHDOG_MAX_TIMEOUT	= 30 * HZ,

	SCX_EXIT_BT_LEN			= 64,
	SCX_EXIT_MSG_LEN		= 1024,
	SCX_EXIT_DUMP_DFL_LEN		= 32768,

	SCX_CPUPERF_ONE			= SCHED_CAPACITY_SCALE,

	/*
	 * Iterating all tasks may take a while. Periodically drop
	 * scx_tasks_lock to avoid causing e.g. CSD and RCU stalls.
	 */
	SCX_OPS_TASK_ITER_BATCH		= 32,
};

enum scx_exit_kind {
	SCX_EXIT_NONE,
	SCX_EXIT_DONE,

	SCX_EXIT_UNREG = 64,	/* user-space initiated unregistration */
	SCX_EXIT_UNREG_BPF,	/* BPF-initiated unregistration */
	SCX_EXIT_UNREG_KERN,	/* kernel-initiated unregistration */
	SCX_EXIT_SYSRQ,		/* requested by 'S' sysrq */

	SCX_EXIT_ERROR = 1024,	/* runtime error, error msg contains details */
	SCX_EXIT_ERROR_BPF,	/* ERROR but triggered through scx_bpf_error() */
	SCX_EXIT_ERROR_STALL,	/* watchdog detected stalled runnable tasks */
};

/*
 * An exit code can be specified when exiting with scx_bpf_exit() or
 * scx_ops_exit(), corresponding to exit_kind UNREG_BPF and UNREG_KERN
 * respectively. The codes are 64bit of the format:
 *
 *   Bits: [63  ..  48 47   ..  32 31 .. 0]
 *         [ SYS ACT ] [ SYS RSN ] [ USR  ]
 *
 *   SYS ACT: System-defined exit actions
 *   SYS RSN: System-defined exit reasons
 *   USR    : User-defined exit codes and reasons
 *
 * Using the above, users may communicate intention and context by ORing system
 * actions and/or system reasons with a user-defined exit code.
 */
enum scx_exit_code {
	/* Reasons */
	SCX_ECODE_RSN_HOTPLUG	= 1LLU << 32,

	/* Actions */
	SCX_ECODE_ACT_RESTART	= 1LLU << 48,
};

/*
 * scx_exit_info is passed to ops.exit() to describe why the BPF scheduler is
 * being disabled.
 */
struct scx_exit_info {
	/* %SCX_EXIT_* - broad category of the exit reason */
	enum scx_exit_kind	kind;

	/* exit code if gracefully exiting */
	s64			exit_code;

	/* textual representation of the above */
	const char		*reason;

	/* backtrace if exiting due to an error */
	unsigned long		*bt;
	u32			bt_len;

	/* informational message */
	char			*msg;

	/* debug dump */
	char			*dump;
};

/* sched_ext_ops.flags */
enum scx_ops_flags {
	/*
	 * Keep built-in idle tracking even if ops.update_idle() is implemented.
	 */
	SCX_OPS_KEEP_BUILTIN_IDLE = 1LLU << 0,

	/*
	 * By default, if there are no other task to run on the CPU, ext core
	 * keeps running the current task even after its slice expires. If this
	 * flag is specified, such tasks are passed to ops.enqueue() with
	 * %SCX_ENQ_LAST. See the comment above %SCX_ENQ_LAST for more info.
	 */
	SCX_OPS_ENQ_LAST	= 1LLU << 1,

	/*
	 * An exiting task may schedule after PF_EXITING is set. In such cases,
	 * bpf_task_from_pid() may not be able to find the task and if the BPF
	 * scheduler depends on pid lookup for dispatching, the task will be
	 * lost leading to various issues including RCU grace period stalls.
	 *
	 * To mask this problem, by default, unhashed tasks are automatically
	 * dispatched to the local DSQ on enqueue. If the BPF scheduler doesn't
	 * depend on pid lookups and wants to handle these tasks directly, the
	 * following flag can be used.
	 */
	SCX_OPS_ENQ_EXITING	= 1LLU << 2,

	/*
	 * If set, only tasks with policy set to SCHED_EXT are attached to
	 * sched_ext. If clear, SCHED_NORMAL tasks are also included.
	 */
	SCX_OPS_SWITCH_PARTIAL	= 1LLU << 3,

	/*
	 * CPU cgroup support flags
	 */
	SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16,	/* cpu.weight */

	SCX_OPS_ALL_FLAGS	= SCX_OPS_KEEP_BUILTIN_IDLE |
				  SCX_OPS_ENQ_LAST |
				  SCX_OPS_ENQ_EXITING |
				  SCX_OPS_SWITCH_PARTIAL |
				  SCX_OPS_HAS_CGROUP_WEIGHT,
};

/* argument container for ops.init_task() */
struct scx_init_task_args {
	/*
	 * Set if ops.init_task() is being invoked on the fork path, as opposed
	 * to the scheduler transition path.
	 */
	bool			fork;
#ifdef CONFIG_EXT_GROUP_SCHED
	/* the cgroup the task is joining */
	struct cgroup		*cgroup;
#endif
};

/* argument container for ops.exit_task() */
struct scx_exit_task_args {
	/* Whether the task exited before running on sched_ext. */
	bool cancelled;
};

/* argument container for ops->cgroup_init() */
struct scx_cgroup_init_args {
	/* the weight of the cgroup [1..10000] */
	u32			weight;
};

enum scx_cpu_preempt_reason {
	/* next task is being scheduled by &sched_class_rt */
	SCX_CPU_PREEMPT_RT,
	/* next task is being scheduled by &sched_class_dl */
	SCX_CPU_PREEMPT_DL,
	/* next task is being scheduled by &sched_class_stop */
	SCX_CPU_PREEMPT_STOP,
	/* unknown reason for SCX being preempted */
	SCX_CPU_PREEMPT_UNKNOWN,
};

/*
 * Argument container for ops->cpu_acquire(). Currently empty, but may be
 * expanded in the future.
 */
struct scx_cpu_acquire_args {};

/* argument container for ops->cpu_release() */
struct scx_cpu_release_args {
	/* the reason the CPU was preempted */
	enum scx_cpu_preempt_reason reason;

	/* the task that's going to be scheduled on the CPU */
	struct task_struct	*task;
};

/*
 * Informational context provided to dump operations.
 */
struct scx_dump_ctx {
	enum scx_exit_kind	kind;
	s64			exit_code;
	const char		*reason;
	u64			at_ns;
	u64			at_jiffies;
};

/**
 * struct sched_ext_ops - Operation table for BPF scheduler implementation
 *
 * Userland can implement an arbitrary scheduling policy by implementing and
 * loading operations in this table.
 */
struct sched_ext_ops {
	/**
	 * select_cpu - Pick the target CPU for a task which is being woken up
	 * @p: task being woken up
	 * @prev_cpu: the cpu @p was on before sleeping
	 * @wake_flags: SCX_WAKE_*
	 *
	 * Decision made here isn't final. @p may be moved to any CPU while it
	 * is getting dispatched for execution later. However, as @p is not on
	 * the rq at this point, getting the eventual execution CPU right here
	 * saves a small bit of overhead down the line.
	 *
	 * If an idle CPU is returned, the CPU is kicked and will try to
	 * dispatch. While an explicit custom mechanism can be added,
	 * select_cpu() serves as the default way to wake up idle CPUs.
	 *
	 * @p may be dispatched directly by calling scx_bpf_dispatch(). If @p
	 * is dispatched, the ops.enqueue() callback will be skipped. Finally,
	 * if @p is dispatched to SCX_DSQ_LOCAL, it will be dispatched to the
	 * local DSQ of whatever CPU is returned by this callback.
	 */
	s32 (*select_cpu)(struct task_struct *p, s32 prev_cpu, u64 wake_flags);

	/**
	 * enqueue - Enqueue a task on the BPF scheduler
	 * @p: task being enqueued
	 * @enq_flags: %SCX_ENQ_*
	 *
	 * @p is ready to run. Dispatch directly by calling scx_bpf_dispatch()
	 * or enqueue on the BPF scheduler. If not directly dispatched, the bpf
	 * scheduler owns @p and if it fails to dispatch @p, the task will
	 * stall.
	 *
	 * If @p was dispatched from ops.select_cpu(), this callback is
	 * skipped.
	 */
	void (*enqueue)(struct task_struct *p, u64 enq_flags);

	/**
	 * dequeue - Remove a task from the BPF scheduler
	 * @p: task being dequeued
	 * @deq_flags: %SCX_DEQ_*
	 *
	 * Remove @p from the BPF scheduler. This is usually called to isolate
	 * the task while updating its scheduling properties (e.g. priority).
	 *
	 * The ext core keeps track of whether the BPF side owns a given task or
	 * not and can gracefully ignore spurious dispatches from BPF side,
	 * which makes it safe to not implement this method. However, depending
	 * on the scheduling logic, this can lead to confusing behaviors - e.g.
	 * scheduling position not being updated across a priority change.
	 */
	void (*dequeue)(struct task_struct *p, u64 deq_flags);

	/**
	 * dispatch - Dispatch tasks from the BPF scheduler and/or consume DSQs
	 * @cpu: CPU to dispatch tasks for
	 * @prev: previous task being switched out
	 *
	 * Called when a CPU's local dsq is empty. The operation should dispatch
	 * one or more tasks from the BPF scheduler into the DSQs using
	 * scx_bpf_dispatch() and/or consume user DSQs into the local DSQ using
	 * scx_bpf_consume().
	 *
	 * The maximum number of times scx_bpf_dispatch() can be called without
	 * an intervening scx_bpf_consume() is specified by
	 * ops.dispatch_max_batch. See the comments on top of the two functions
	 * for more details.
	 *
	 * When not %NULL, @prev is an SCX task with its slice depleted. If
	 * @prev is still runnable as indicated by set %SCX_TASK_QUEUED in
	 * @prev->scx.flags, it is not enqueued yet and will be enqueued after
	 * ops.dispatch() returns. To keep executing @prev, return without
	 * dispatching or consuming any tasks. Also see %SCX_OPS_ENQ_LAST.
	 */
	void (*dispatch)(s32 cpu, struct task_struct *prev);

	/**
	 * tick - Periodic tick
	 * @p: task running currently
	 *
	 * This operation is called every 1/HZ seconds on CPUs which are
	 * executing an SCX task. Setting @p->scx.slice to 0 will trigger an
	 * immediate dispatch cycle on the CPU.
	 */
	void (*tick)(struct task_struct *p);

	/**
	 * runnable - A task is becoming runnable on its associated CPU
	 * @p: task becoming runnable
	 * @enq_flags: %SCX_ENQ_*
	 *
	 * This and the following three functions can be used to track a task's
	 * execution state transitions. A task becomes ->runnable() on a CPU,
	 * and then goes through one or more ->running() and ->stopping() pairs
	 * as it runs on the CPU, and eventually becomes ->quiescent() when it's
	 * done running on the CPU.
	 *
	 * @p is becoming runnable on the CPU because it's
	 *
	 * - waking up (%SCX_ENQ_WAKEUP)
	 * - being moved from another CPU
	 * - being restored after temporarily taken off the queue for an
	 *   attribute change.
	 *
	 * This and ->enqueue() are related but not coupled. This operation
	 * notifies @p's state transition and may not be followed by ->enqueue()
	 * e.g. when @p is being dispatched to a remote CPU, or when @p is
	 * being enqueued on a CPU experiencing a hotplug event. Likewise, a
	 * task may be ->enqueue()'d without being preceded by this operation
	 * e.g. after exhausting its slice.
	 */
	void (*runnable)(struct task_struct *p, u64 enq_flags);

	/**
	 * running - A task is starting to run on its associated CPU
	 * @p: task starting to run
	 *
	 * See ->runnable() for explanation on the task state notifiers.
	 */
	void (*running)(struct task_struct *p);

	/**
	 * stopping - A task is stopping execution
	 * @p: task stopping to run
	 * @runnable: is task @p still runnable?
	 *
	 * See ->runnable() for explanation on the task state notifiers. If
	 * !@runnable, ->quiescent() will be invoked after this operation
	 * returns.
	 */
	void (*stopping)(struct task_struct *p, bool runnable);

	/**
	 * quiescent - A task is becoming not runnable on its associated CPU
	 * @p: task becoming not runnable
	 * @deq_flags: %SCX_DEQ_*
	 *
	 * See ->runnable() for explanation on the task state notifiers.
	 *
	 * @p is becoming quiescent on the CPU because it's
	 *
	 * - sleeping (%SCX_DEQ_SLEEP)
	 * - being moved to another CPU
	 * - being temporarily taken off the queue for an attribute change
	 *   (%SCX_DEQ_SAVE)
	 *
	 * This and ->dequeue() are related but not coupled. This operation
	 * notifies @p's state transition and may not be preceded by ->dequeue()
	 * e.g. when @p is being dispatched to a remote CPU.
	 */
	void (*quiescent)(struct task_struct *p, u64 deq_flags);

	/**
	 * yield - Yield CPU
	 * @from: yielding task
	 * @to: optional yield target task
	 *
	 * If @to is NULL, @from is yielding the CPU to other runnable tasks.
	 * The BPF scheduler should ensure that other available tasks are
	 * dispatched before the yielding task. Return value is ignored in this
	 * case.
	 *
	 * If @to is not-NULL, @from wants to yield the CPU to @to. If the bpf
	 * scheduler can implement the request, return %true; otherwise, %false.
	 */
	bool (*yield)(struct task_struct *from, struct task_struct *to);

	/**
	 * core_sched_before - Task ordering for core-sched
	 * @a: task A
	 * @b: task B
	 *
	 * Used by core-sched to determine the ordering between two tasks. See
	 * Documentation/admin-guide/hw-vuln/core-scheduling.rst for details on
	 * core-sched.
	 *
	 * Both @a and @b are runnable and may or may not currently be queued on
	 * the BPF scheduler. Should return %true if @a should run before @b.
	 * %false if there's no required ordering or @b should run before @a.
	 *
	 * If not specified, the default is ordering them according to when they
	 * became runnable.
	 */
	bool (*core_sched_before)(struct task_struct *a, struct task_struct *b);

	/**
	 * set_weight - Set task weight
	 * @p: task to set weight for
	 * @weight: new weight [1..10000]
	 *
	 * Update @p's weight to @weight.
	 */
	void (*set_weight)(struct task_struct *p, u32 weight);

	/**
	 * set_cpumask - Set CPU affinity
	 * @p: task to set CPU affinity for
	 * @cpumask: cpumask of cpus that @p can run on
	 *
	 * Update @p's CPU affinity to @cpumask.
	 */
	void (*set_cpumask)(struct task_struct *p,
			    const struct cpumask *cpumask);

	/**
	 * update_idle - Update the idle state of a CPU
	 * @cpu: CPU to udpate the idle state for
	 * @idle: whether entering or exiting the idle state
	 *
	 * This operation is called when @rq's CPU goes or leaves the idle
	 * state. By default, implementing this operation disables the built-in
	 * idle CPU tracking and the following helpers become unavailable:
	 *
	 * - scx_bpf_select_cpu_dfl()
	 * - scx_bpf_test_and_clear_cpu_idle()
	 * - scx_bpf_pick_idle_cpu()
	 *
	 * The user also must implement ops.select_cpu() as the default
	 * implementation relies on scx_bpf_select_cpu_dfl().
	 *
	 * Specify the %SCX_OPS_KEEP_BUILTIN_IDLE flag to keep the built-in idle
	 * tracking.
	 */
	void (*update_idle)(s32 cpu, bool idle);

	/**
	 * cpu_acquire - A CPU is becoming available to the BPF scheduler
	 * @cpu: The CPU being acquired by the BPF scheduler.
	 * @args: Acquire arguments, see the struct definition.
	 *
	 * A CPU that was previously released from the BPF scheduler is now once
	 * again under its control.
	 */
	void (*cpu_acquire)(s32 cpu, struct scx_cpu_acquire_args *args);

	/**
	 * cpu_release - A CPU is taken away from the BPF scheduler
	 * @cpu: The CPU being released by the BPF scheduler.
	 * @args: Release arguments, see the struct definition.
	 *
	 * The specified CPU is no longer under the control of the BPF
	 * scheduler. This could be because it was preempted by a higher
	 * priority sched_class, though there may be other reasons as well. The
	 * caller should consult @args->reason to determine the cause.
	 */
	void (*cpu_release)(s32 cpu, struct scx_cpu_release_args *args);

	/**
	 * init_task - Initialize a task to run in a BPF scheduler
	 * @p: task to initialize for BPF scheduling
	 * @args: init arguments, see the struct definition
	 *
	 * Either we're loading a BPF scheduler or a new task is being forked.
	 * Initialize @p for BPF scheduling. This operation may block and can
	 * be used for allocations, and is called exactly once for a task.
	 *
	 * Return 0 for success, -errno for failure. An error return while
	 * loading will abort loading of the BPF scheduler. During a fork, it
	 * will abort that specific fork.
	 */
	s32 (*init_task)(struct task_struct *p, struct scx_init_task_args *args);

	/**
	 * exit_task - Exit a previously-running task from the system
	 * @p: task to exit
	 *
	 * @p is exiting or the BPF scheduler is being unloaded. Perform any
	 * necessary cleanup for @p.
	 */
	void (*exit_task)(struct task_struct *p, struct scx_exit_task_args *args);

	/**
	 * enable - Enable BPF scheduling for a task
	 * @p: task to enable BPF scheduling for
	 *
	 * Enable @p for BPF scheduling. enable() is called on @p any time it
	 * enters SCX, and is always paired with a matching disable().
	 */
	void (*enable)(struct task_struct *p);

	/**
	 * disable - Disable BPF scheduling for a task
	 * @p: task to disable BPF scheduling for
	 *
	 * @p is exiting, leaving SCX or the BPF scheduler is being unloaded.
	 * Disable BPF scheduling for @p. A disable() call is always matched
	 * with a prior enable() call.
	 */
	void (*disable)(struct task_struct *p);

	/**
	 * dump - Dump BPF scheduler state on error
	 * @ctx: debug dump context
	 *
	 * Use scx_bpf_dump() to generate BPF scheduler specific debug dump.
	 */
	void (*dump)(struct scx_dump_ctx *ctx);

	/**
	 * dump_cpu - Dump BPF scheduler state for a CPU on error
	 * @ctx: debug dump context
	 * @cpu: CPU to generate debug dump for
	 * @idle: @cpu is currently idle without any runnable tasks
	 *
	 * Use scx_bpf_dump() to generate BPF scheduler specific debug dump for
	 * @cpu. If @idle is %true and this operation doesn't produce any
	 * output, @cpu is skipped for dump.
	 */
	void (*dump_cpu)(struct scx_dump_ctx *ctx, s32 cpu, bool idle);

	/**
	 * dump_task - Dump BPF scheduler state for a runnable task on error
	 * @ctx: debug dump context
	 * @p: runnable task to generate debug dump for
	 *
	 * Use scx_bpf_dump() to generate BPF scheduler specific debug dump for
	 * @p.
	 */
	void (*dump_task)(struct scx_dump_ctx *ctx, struct task_struct *p);

#ifdef CONFIG_EXT_GROUP_SCHED
	/**
	 * cgroup_init - Initialize a cgroup
	 * @cgrp: cgroup being initialized
	 * @args: init arguments, see the struct definition
	 *
	 * Either the BPF scheduler is being loaded or @cgrp created, initialize
	 * @cgrp for sched_ext. This operation may block.
	 *
	 * Return 0 for success, -errno for failure. An error return while
	 * loading will abort loading of the BPF scheduler. During cgroup
	 * creation, it will abort the specific cgroup creation.
	 */
	s32 (*cgroup_init)(struct cgroup *cgrp,
			   struct scx_cgroup_init_args *args);

	/**
	 * cgroup_exit - Exit a cgroup
	 * @cgrp: cgroup being exited
	 *
	 * Either the BPF scheduler is being unloaded or @cgrp destroyed, exit
	 * @cgrp for sched_ext. This operation my block.
	 */
	void (*cgroup_exit)(struct cgroup *cgrp);

	/**
	 * cgroup_prep_move - Prepare a task to be moved to a different cgroup
	 * @p: task being moved
	 * @from: cgroup @p is being moved from
	 * @to: cgroup @p is being moved to
	 *
	 * Prepare @p for move from cgroup @from to @to. This operation may
	 * block and can be used for allocations.
	 *
	 * Return 0 for success, -errno for failure. An error return aborts the
	 * migration.
	 */
	s32 (*cgroup_prep_move)(struct task_struct *p,
				struct cgroup *from, struct cgroup *to);

	/**
	 * cgroup_move - Commit cgroup move
	 * @p: task being moved
	 * @from: cgroup @p is being moved from
	 * @to: cgroup @p is being moved to
	 *
	 * Commit the move. @p is dequeued during this operation.
	 */
	void (*cgroup_move)(struct task_struct *p,
			    struct cgroup *from, struct cgroup *to);

	/**
	 * cgroup_cancel_move - Cancel cgroup move
	 * @p: task whose cgroup move is being canceled
	 * @from: cgroup @p was being moved from
	 * @to: cgroup @p was being moved to
	 *
	 * @p was cgroup_prep_move()'d but failed before reaching cgroup_move().
	 * Undo the preparation.
	 */
	void (*cgroup_cancel_move)(struct task_struct *p,
				   struct cgroup *from, struct cgroup *to);

	/**
	 * cgroup_set_weight - A cgroup's weight is being changed
	 * @cgrp: cgroup whose weight is being updated
	 * @weight: new weight [1..10000]
	 *
	 * Update @tg's weight to @weight.
	 */
	void (*cgroup_set_weight)(struct cgroup *cgrp, u32 weight);
#endif	/* CONFIG_CGROUPS */

	/*
	 * All online ops must come before ops.cpu_online().
	 */

	/**
	 * cpu_online - A CPU became online
	 * @cpu: CPU which just came up
	 *
	 * @cpu just came online. @cpu will not call ops.enqueue() or
	 * ops.dispatch(), nor run tasks associated with other CPUs beforehand.
	 */
	void (*cpu_online)(s32 cpu);

	/**
	 * cpu_offline - A CPU is going offline
	 * @cpu: CPU which is going offline
	 *
	 * @cpu is going offline. @cpu will not call ops.enqueue() or
	 * ops.dispatch(), nor run tasks associated with other CPUs afterwards.
	 */
	void (*cpu_offline)(s32 cpu);

	/*
	 * All CPU hotplug ops must come before ops.init().
	 */

	/**
	 * init - Initialize the BPF scheduler
	 */
	s32 (*init)(void);

	/**
	 * exit - Clean up after the BPF scheduler
	 * @info: Exit info
	 *
	 * ops.exit() is also called on ops.init() failure, which is a bit
	 * unusual. This is to allow rich reporting through @info on how
	 * ops.init() failed.
	 */
	void (*exit)(struct scx_exit_info *info);

	/**
	 * dispatch_max_batch - Max nr of tasks that dispatch() can dispatch
	 */
	u32 dispatch_max_batch;

	/**
	 * flags - %SCX_OPS_* flags
	 */
	u64 flags;

	/**
	 * timeout_ms - The maximum amount of time, in milliseconds, that a
	 * runnable task should be able to wait before being scheduled. The
	 * maximum timeout may not exceed the default timeout of 30 seconds.
	 *
	 * Defaults to the maximum allowed timeout value of 30 seconds.
	 */
	u32 timeout_ms;

	/**
	 * exit_dump_len - scx_exit_info.dump buffer length. If 0, the default
	 * value of 32768 is used.
	 */
	u32 exit_dump_len;

	/**
	 * hotplug_seq - A sequence number that may be set by the scheduler to
	 * detect when a hotplug event has occurred during the loading process.
	 * If 0, no detection occurs. Otherwise, the scheduler will fail to
	 * load if the sequence number does not match @scx_hotplug_seq on the
	 * enable path.
	 */
	u64 hotplug_seq;

	/**
	 * name - BPF scheduler's name
	 *
	 * Must be a non-zero valid BPF object name including only isalnum(),
	 * '_' and '.' chars. Shows up in kernel.sched_ext_ops sysctl while the
	 * BPF scheduler is enabled.
	 */
	char name[SCX_OPS_NAME_LEN];
};

enum scx_opi {
	SCX_OPI_BEGIN			= 0,
	SCX_OPI_NORMAL_BEGIN		= 0,
	SCX_OPI_NORMAL_END		= SCX_OP_IDX(cpu_online),
	SCX_OPI_CPU_HOTPLUG_BEGIN	= SCX_OP_IDX(cpu_online),
	SCX_OPI_CPU_HOTPLUG_END		= SCX_OP_IDX(init),
	SCX_OPI_END			= SCX_OP_IDX(init),
};

enum scx_wake_flags {
	/* expose select WF_* flags as enums */
	SCX_WAKE_FORK		= WF_FORK,
	SCX_WAKE_TTWU		= WF_TTWU,
	SCX_WAKE_SYNC		= WF_SYNC,
};

enum scx_enq_flags {
	/* expose select ENQUEUE_* flags as enums */
	SCX_ENQ_WAKEUP		= ENQUEUE_WAKEUP,
	SCX_ENQ_HEAD		= ENQUEUE_HEAD,
	SCX_ENQ_CPU_SELECTED	= ENQUEUE_RQ_SELECTED,

	/* high 32bits are SCX specific */

	/*
	 * Set the following to trigger preemption when calling
	 * scx_bpf_dispatch() with a local dsq as the target. The slice of the
	 * current task is cleared to zero and the CPU is kicked into the
	 * scheduling path. Implies %SCX_ENQ_HEAD.
	 */
	SCX_ENQ_PREEMPT		= 1LLU << 32,

	/*
	 * The task being enqueued was previously enqueued on the current CPU's
	 * %SCX_DSQ_LOCAL, but was removed from it in a call to the
	 * bpf_scx_reenqueue_local() kfunc. If bpf_scx_reenqueue_local() was
	 * invoked in a ->cpu_release() callback, and the task is again
	 * dispatched back to %SCX_LOCAL_DSQ by this current ->enqueue(), the
	 * task will not be scheduled on the CPU until at least the next invocation
	 * of the ->cpu_acquire() callback.
	 */
	SCX_ENQ_REENQ		= 1LLU << 40,

	/*
	 * The task being enqueued is the only task available for the cpu. By
	 * default, ext core keeps executing such tasks but when
	 * %SCX_OPS_ENQ_LAST is specified, they're ops.enqueue()'d with the
	 * %SCX_ENQ_LAST flag set.
	 *
	 * The BPF scheduler is responsible for triggering a follow-up
	 * scheduling event. Otherwise, Execution may stall.
	 */
	SCX_ENQ_LAST		= 1LLU << 41,

	/* high 8 bits are internal */
	__SCX_ENQ_INTERNAL_MASK	= 0xffLLU << 56,

	SCX_ENQ_CLEAR_OPSS	= 1LLU << 56,
	SCX_ENQ_DSQ_PRIQ	= 1LLU << 57,
};

enum scx_deq_flags {
	/* expose select DEQUEUE_* flags as enums */
	SCX_DEQ_SLEEP		= DEQUEUE_SLEEP,

	/* high 32bits are SCX specific */

	/*
	 * The generic core-sched layer decided to execute the task even though
	 * it hasn't been dispatched yet. Dequeue from the BPF side.
	 */
	SCX_DEQ_CORE_SCHED_EXEC	= 1LLU << 32,
};

enum scx_pick_idle_cpu_flags {
	SCX_PICK_IDLE_CORE	= 1LLU << 0,	/* pick a CPU whose SMT siblings are also idle */
};

enum scx_kick_flags {
	/*
	 * Kick the target CPU if idle. Guarantees that the target CPU goes
	 * through at least one full scheduling cycle before going idle. If the
	 * target CPU can be determined to be currently not idle and going to go
	 * through a scheduling cycle before going idle, noop.
	 */
	SCX_KICK_IDLE		= 1LLU << 0,

	/*
	 * Preempt the current task and execute the dispatch path. If the
	 * current task of the target CPU is an SCX task, its ->scx.slice is
	 * cleared to zero before the scheduling path is invoked so that the
	 * task expires and the dispatch path is invoked.
	 */
	SCX_KICK_PREEMPT	= 1LLU << 1,

	/*
	 * Wait for the CPU to be rescheduled. The scx_bpf_kick_cpu() call will
	 * return after the target CPU finishes picking the next task.
	 */
	SCX_KICK_WAIT		= 1LLU << 2,
};

enum scx_tg_flags {
	SCX_TG_ONLINE		= 1U << 0,
	SCX_TG_INITED		= 1U << 1,
};

enum scx_ops_enable_state {
	SCX_OPS_ENABLING,
	SCX_OPS_ENABLED,
	SCX_OPS_DISABLING,
	SCX_OPS_DISABLED,
};

static const char *scx_ops_enable_state_str[] = {
	[SCX_OPS_ENABLING]	= "enabling",
	[SCX_OPS_ENABLED]	= "enabled",
	[SCX_OPS_DISABLING]	= "disabling",
	[SCX_OPS_DISABLED]	= "disabled",
};

/*
 * sched_ext_entity->ops_state
 *
 * Used to track the task ownership between the SCX core and the BPF scheduler.
 * State transitions look as follows:
 *
 * NONE -> QUEUEING -> QUEUED -> DISPATCHING
 *   ^              |                 |
 *   |              v                 v
 *   \-------------------------------/
 *
 * QUEUEING and DISPATCHING states can be waited upon. See wait_ops_state() call
 * sites for explanations on the conditions being waited upon and why they are
 * safe. Transitions out of them into NONE or QUEUED must store_release and the
 * waiters should load_acquire.
 *
 * Tracking scx_ops_state enables sched_ext core to reliably determine whether
 * any given task can be dispatched by the BPF scheduler at all times and thus
 * relaxes the requirements on the BPF scheduler. This allows the BPF scheduler
 * to try to dispatch any task anytime regardless of its state as the SCX core
 * can safely reject invalid dispatches.
 */
enum scx_ops_state {
	SCX_OPSS_NONE,		/* owned by the SCX core */
	SCX_OPSS_QUEUEING,	/* in transit to the BPF scheduler */
	SCX_OPSS_QUEUED,	/* owned by the BPF scheduler */
	SCX_OPSS_DISPATCHING,	/* in transit back to the SCX core */

	/*
	 * QSEQ brands each QUEUED instance so that, when dispatch races
	 * dequeue/requeue, the dispatcher can tell whether it still has a claim
	 * on the task being dispatched.
	 *
	 * As some 32bit archs can't do 64bit store_release/load_acquire,
	 * p->scx.ops_state is atomic_long_t which leaves 30 bits for QSEQ on
	 * 32bit machines. The dispatch race window QSEQ protects is very narrow
	 * and runs with IRQ disabled. 30 bits should be sufficient.
	 */
	SCX_OPSS_QSEQ_SHIFT	= 2,
};

/* Use macros to ensure that the type is unsigned long for the masks */
#define SCX_OPSS_STATE_MASK	((1LU << SCX_OPSS_QSEQ_SHIFT) - 1)
#define SCX_OPSS_QSEQ_MASK	(~SCX_OPSS_STATE_MASK)

/*
 * During exit, a task may schedule after losing its PIDs. When disabling the
 * BPF scheduler, we need to be able to iterate tasks in every state to
 * guarantee system safety. Maintain a dedicated task list which contains every
 * task between its fork and eventual free.
 */
static DEFINE_SPINLOCK(scx_tasks_lock);
static LIST_HEAD(scx_tasks);

/* ops enable/disable */
static struct kthread_worker *scx_ops_helper;
static DEFINE_MUTEX(scx_ops_enable_mutex);
DEFINE_STATIC_KEY_FALSE(__scx_ops_enabled);
DEFINE_STATIC_PERCPU_RWSEM(scx_fork_rwsem);
static atomic_t scx_ops_enable_state_var = ATOMIC_INIT(SCX_OPS_DISABLED);
static atomic_t scx_ops_bypass_depth = ATOMIC_INIT(0);
static bool scx_ops_init_task_enabled;
static bool scx_switching_all;
DEFINE_STATIC_KEY_FALSE(__scx_switched_all);

static struct sched_ext_ops scx_ops;
static bool scx_warned_zero_slice;

static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_last);
static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_exiting);
static DEFINE_STATIC_KEY_FALSE(scx_ops_cpu_preempt);
static DEFINE_STATIC_KEY_FALSE(scx_builtin_idle_enabled);

static struct static_key_false scx_has_op[SCX_OPI_END] =
	{ [0 ... SCX_OPI_END-1] = STATIC_KEY_FALSE_INIT };

static atomic_t scx_exit_kind = ATOMIC_INIT(SCX_EXIT_DONE);
static struct scx_exit_info *scx_exit_info;

static atomic_long_t scx_nr_rejected = ATOMIC_LONG_INIT(0);
static atomic_long_t scx_hotplug_seq = ATOMIC_LONG_INIT(0);

/*
 * A monotically increasing sequence number that is incremented every time a
 * scheduler is enabled. This can be used by to check if any custom sched_ext
 * scheduler has ever been used in the system.
 */
static atomic_long_t scx_enable_seq = ATOMIC_LONG_INIT(0);

/*
 * The maximum amount of time in jiffies that a task may be runnable without
 * being scheduled on a CPU. If this timeout is exceeded, it will trigger
 * scx_ops_error().
 */
static unsigned long scx_watchdog_timeout;

/*
 * The last time the delayed work was run. This delayed work relies on
 * ksoftirqd being able to run to service timer interrupts, so it's possible
 * that this work itself could get wedged. To account for this, we check that
 * it's not stalled in the timer tick, and trigger an error if it is.
 */
static unsigned long scx_watchdog_timestamp = INITIAL_JIFFIES;

static struct delayed_work scx_watchdog_work;

/* idle tracking */
#ifdef CONFIG_SMP
#ifdef CONFIG_CPUMASK_OFFSTACK
#define CL_ALIGNED_IF_ONSTACK
#else
#define CL_ALIGNED_IF_ONSTACK __cacheline_aligned_in_smp
#endif

static struct {
	cpumask_var_t cpu;
	cpumask_var_t smt;
} idle_masks CL_ALIGNED_IF_ONSTACK;

#endif	/* CONFIG_SMP */

/* for %SCX_KICK_WAIT */
static unsigned long __percpu *scx_kick_cpus_pnt_seqs;

/*
 * Direct dispatch marker.
 *
 * Non-NULL values are used for direct dispatch from enqueue path. A valid
 * pointer points to the task currently being enqueued. An ERR_PTR value is used
 * to indicate that direct dispatch has already happened.
 */
static DEFINE_PER_CPU(struct task_struct *, direct_dispatch_task);

/*
 * Dispatch queues.
 *
 * The global DSQ (%SCX_DSQ_GLOBAL) is split per-node for scalability. This is
 * to avoid live-locking in bypass mode where all tasks are dispatched to
 * %SCX_DSQ_GLOBAL and all CPUs consume from it. If per-node split isn't
 * sufficient, it can be further split.
 */
static struct scx_dispatch_q **global_dsqs;

static const struct rhashtable_params dsq_hash_params = {
	.key_len		= 8,
	.key_offset		= offsetof(struct scx_dispatch_q, id),
	.head_offset		= offsetof(struct scx_dispatch_q, hash_node),
};

static struct rhashtable dsq_hash;
static LLIST_HEAD(dsqs_to_free);

/* dispatch buf */
struct scx_dsp_buf_ent {
	struct task_struct	*task;
	unsigned long		qseq;
	u64			dsq_id;
	u64			enq_flags;
};

static u32 scx_dsp_max_batch;

struct scx_dsp_ctx {
	struct rq		*rq;
	u32			cursor;
	u32			nr_tasks;
	struct scx_dsp_buf_ent	buf[];
};

static struct scx_dsp_ctx __percpu *scx_dsp_ctx;

/* string formatting from BPF */
struct scx_bstr_buf {
	u64			data[MAX_BPRINTF_VARARGS];
	char			line[SCX_EXIT_MSG_LEN];
};

static DEFINE_RAW_SPINLOCK(scx_exit_bstr_buf_lock);
static struct scx_bstr_buf scx_exit_bstr_buf;

/* ops debug dump */
struct scx_dump_data {
	s32			cpu;
	bool			first;
	s32			cursor;
	struct seq_buf		*s;
	const char		*prefix;
	struct scx_bstr_buf	buf;
};

static struct scx_dump_data scx_dump_data = {
	.cpu			= -1,
};

/* /sys/kernel/sched_ext interface */
static struct kset *scx_kset;
static struct kobject *scx_root_kobj;

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

static void process_ddsp_deferred_locals(struct rq *rq);
static void scx_bpf_kick_cpu(s32 cpu, u64 flags);
static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind,
					     s64 exit_code,
					     const char *fmt, ...);

#define scx_ops_error_kind(err, fmt, args...)					\
	scx_ops_exit_kind((err), 0, fmt, ##args)

#define scx_ops_exit(code, fmt, args...)					\
	scx_ops_exit_kind(SCX_EXIT_UNREG_KERN, (code), fmt, ##args)

#define scx_ops_error(fmt, args...)						\
	scx_ops_error_kind(SCX_EXIT_ERROR, fmt, ##args)

#define SCX_HAS_OP(op)	static_branch_likely(&scx_has_op[SCX_OP_IDX(op)])

static long jiffies_delta_msecs(unsigned long at, unsigned long now)
{
	if (time_after(at, now))
		return jiffies_to_msecs(at - now);
	else
		return -(long)jiffies_to_msecs(now - at);
}

/* if the highest set bit is N, return a mask with bits [N+1, 31] set */
static u32 higher_bits(u32 flags)
{
	return ~((1 << fls(flags)) - 1);
}

/* return the mask with only the highest bit set */
static u32 highest_bit(u32 flags)
{
	int bit = fls(flags);
	return ((u64)1 << bit) >> 1;
}

static bool u32_before(u32 a, u32 b)
{
	return (s32)(a - b) < 0;
}

static struct scx_dispatch_q *find_global_dsq(struct task_struct *p)
{
	return global_dsqs[cpu_to_node(task_cpu(p))];
}

static struct scx_dispatch_q *find_user_dsq(u64 dsq_id)
{
	return rhashtable_lookup_fast(&dsq_hash, &dsq_id, dsq_hash_params);
}

/*
 * scx_kf_mask enforcement. Some kfuncs can only be called from specific SCX
 * ops. When invoking SCX ops, SCX_CALL_OP[_RET]() should be used to indicate
 * the allowed kfuncs and those kfuncs should use scx_kf_allowed() to check
 * whether it's running from an allowed context.
 *
 * @mask is constant, always inline to cull the mask calculations.
 */
static __always_inline void scx_kf_allow(u32 mask)
{
	/* nesting is allowed only in increasing scx_kf_mask order */
	WARN_ONCE((mask | higher_bits(mask)) & current->scx.kf_mask,
		  "invalid nesting current->scx.kf_mask=0x%x mask=0x%x\n",
		  current->scx.kf_mask, mask);
	current->scx.kf_mask |= mask;
	barrier();
}

static void scx_kf_disallow(u32 mask)
{
	barrier();
	current->scx.kf_mask &= ~mask;
}

#define SCX_CALL_OP(mask, op, args...)						\
do {										\
	if (mask) {								\
		scx_kf_allow(mask);						\
		scx_ops.op(args);						\
		scx_kf_disallow(mask);						\
	} else {								\
		scx_ops.op(args);						\
	}									\
} while (0)

#define SCX_CALL_OP_RET(mask, op, args...)					\
({										\
	__typeof__(scx_ops.op(args)) __ret;					\
	if (mask) {								\
		scx_kf_allow(mask);						\
		__ret = scx_ops.op(args);					\
		scx_kf_disallow(mask);						\
	} else {								\
		__ret = scx_ops.op(args);					\
	}									\
	__ret;									\
})

/*
 * Some kfuncs are allowed only on the tasks that are subjects of the
 * in-progress scx_ops operation for, e.g., locking guarantees. To enforce such
 * restrictions, the following SCX_CALL_OP_*() variants should be used when
 * invoking scx_ops operations that take task arguments. These can only be used
 * for non-nesting operations due to the way the tasks are tracked.
 *
 * kfuncs which can only operate on such tasks can in turn use
 * scx_kf_allowed_on_arg_tasks() to test whether the invocation is allowed on
 * the specific task.
 */
#define SCX_CALL_OP_TASK(mask, op, task, args...)				\
do {										\
	BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL);				\
	current->scx.kf_tasks[0] = task;					\
	SCX_CALL_OP(mask, op, task, ##args);					\
	current->scx.kf_tasks[0] = NULL;					\
} while (0)

#define SCX_CALL_OP_TASK_RET(mask, op, task, args...)				\
({										\
	__typeof__(scx_ops.op(task, ##args)) __ret;				\
	BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL);				\
	current->scx.kf_tasks[0] = task;					\
	__ret = SCX_CALL_OP_RET(mask, op, task, ##args);			\
	current->scx.kf_tasks[0] = NULL;					\
	__ret;									\
})

#define SCX_CALL_OP_2TASKS_RET(mask, op, task0, task1, args...)			\
({										\
	__typeof__(scx_ops.op(task0, task1, ##args)) __ret;			\
	BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL);				\
	current->scx.kf_tasks[0] = task0;					\
	current->scx.kf_tasks[1] = task1;					\
	__ret = SCX_CALL_OP_RET(mask, op, task0, task1, ##args);		\
	current->scx.kf_tasks[0] = NULL;					\
	current->scx.kf_tasks[1] = NULL;					\
	__ret;									\
})

/* @mask is constant, always inline to cull unnecessary branches */
static __always_inline bool scx_kf_allowed(u32 mask)
{
	if (unlikely(!(current->scx.kf_mask & mask))) {
		scx_ops_error("kfunc with mask 0x%x called from an operation only allowing 0x%x",
			      mask, current->scx.kf_mask);
		return false;
	}

	/*
	 * Enforce nesting boundaries. e.g. A kfunc which can be called from
	 * DISPATCH must not be called if we're running DEQUEUE which is nested
	 * inside ops.dispatch(). We don't need to check boundaries for any
	 * blocking kfuncs as the verifier ensures they're only called from
	 * sleepable progs.
	 */
	if (unlikely(highest_bit(mask) == SCX_KF_CPU_RELEASE &&
		     (current->scx.kf_mask & higher_bits(SCX_KF_CPU_RELEASE)))) {
		scx_ops_error("cpu_release kfunc called from a nested operation");
		return false;
	}

	if (unlikely(highest_bit(mask) == SCX_KF_DISPATCH &&
		     (current->scx.kf_mask & higher_bits(SCX_KF_DISPATCH)))) {
		scx_ops_error("dispatch kfunc called from a nested operation");
		return false;
	}

	return true;
}

/* see SCX_CALL_OP_TASK() */
static __always_inline bool scx_kf_allowed_on_arg_tasks(u32 mask,
							struct task_struct *p)
{
	if (!scx_kf_allowed(mask))
		return false;

	if (unlikely((p != current->scx.kf_tasks[0] &&
		      p != current->scx.kf_tasks[1]))) {
		scx_ops_error("called on a task not being operated on");
		return false;
	}

	return true;
}

static bool scx_kf_allowed_if_unlocked(void)
{
	return !current->scx.kf_mask;
}

/**
 * nldsq_next_task - Iterate to the next task in a non-local DSQ
 * @dsq: user dsq being interated
 * @cur: current position, %NULL to start iteration
 * @rev: walk backwards
 *
 * Returns %NULL when iteration is finished.
 */
static struct task_struct *nldsq_next_task(struct scx_dispatch_q *dsq,
					   struct task_struct *cur, bool rev)
{
	struct list_head *list_node;
	struct scx_dsq_list_node *dsq_lnode;

	lockdep_assert_held(&dsq->lock);

	if (cur)
		list_node = &cur->scx.dsq_list.node;
	else
		list_node = &dsq->list;

	/* find the next task, need to skip BPF iteration cursors */
	do {
		if (rev)
			list_node = list_node->prev;
		else
			list_node = list_node->next;

		if (list_node == &dsq->list)
			return NULL;

		dsq_lnode = container_of(list_node, struct scx_dsq_list_node,
					 node);
	} while (dsq_lnode->flags & SCX_DSQ_LNODE_ITER_CURSOR);

	return container_of(dsq_lnode, struct task_struct, scx.dsq_list);
}

#define nldsq_for_each_task(p, dsq)						\
	for ((p) = nldsq_next_task((dsq), NULL, false); (p);			\
	     (p) = nldsq_next_task((dsq), (p), false))


/*
 * BPF DSQ iterator. Tasks in a non-local DSQ can be iterated in [reverse]
 * dispatch order. BPF-visible iterator is opaque and larger to allow future
 * changes without breaking backward compatibility. Can be used with
 * bpf_for_each(). See bpf_iter_scx_dsq_*().
 */
enum scx_dsq_iter_flags {
	/* iterate in the reverse dispatch order */
	SCX_DSQ_ITER_REV		= 1U << 16,

	__SCX_DSQ_ITER_HAS_SLICE	= 1U << 30,
	__SCX_DSQ_ITER_HAS_VTIME	= 1U << 31,

	__SCX_DSQ_ITER_USER_FLAGS	= SCX_DSQ_ITER_REV,
	__SCX_DSQ_ITER_ALL_FLAGS	= __SCX_DSQ_ITER_USER_FLAGS |
					  __SCX_DSQ_ITER_HAS_SLICE |
					  __SCX_DSQ_ITER_HAS_VTIME,
};

struct bpf_iter_scx_dsq_kern {
	struct scx_dsq_list_node	cursor;
	struct scx_dispatch_q		*dsq;
	u64				slice;
	u64				vtime;
} __attribute__((aligned(8)));

struct bpf_iter_scx_dsq {
	u64				__opaque[6];
} __attribute__((aligned(8)));


/*
 * SCX task iterator.
 */
struct scx_task_iter {
	struct sched_ext_entity		cursor;
	struct task_struct		*locked;
	struct rq			*rq;
	struct rq_flags			rf;
	u32				cnt;
};

/**
 * scx_task_iter_start - Lock scx_tasks_lock and start a task iteration
 * @iter: iterator to init
 *
 * Initialize @iter and return with scx_tasks_lock held. Once initialized, @iter
 * must eventually be stopped with scx_task_iter_stop().
 *
 * scx_tasks_lock and the rq lock may be released using scx_task_iter_unlock()
 * between this and the first next() call or between any two next() calls. If
 * the locks are released between two next() calls, the caller is responsible
 * for ensuring that the task being iterated remains accessible either through
 * RCU read lock or obtaining a reference count.
 *
 * All tasks which existed when the iteration started are guaranteed to be
 * visited as long as they still exist.
 */
static void scx_task_iter_start(struct scx_task_iter *iter)
{
	BUILD_BUG_ON(__SCX_DSQ_ITER_ALL_FLAGS &
		     ((1U << __SCX_DSQ_LNODE_PRIV_SHIFT) - 1));

	spin_lock_irq(&scx_tasks_lock);

	iter->cursor = (struct sched_ext_entity){ .flags = SCX_TASK_CURSOR };
	list_add(&iter->cursor.tasks_node, &scx_tasks);
	iter->locked = NULL;
	iter->cnt = 0;
}

static void __scx_task_iter_rq_unlock(struct scx_task_iter *iter)
{
	if (iter->locked) {
		task_rq_unlock(iter->rq, iter->locked, &iter->rf);
		iter->locked = NULL;
	}
}

/**
 * scx_task_iter_unlock - Unlock rq and scx_tasks_lock held by a task iterator
 * @iter: iterator to unlock
 *
 * If @iter is in the middle of a locked iteration, it may be locking the rq of
 * the task currently being visited in addition to scx_tasks_lock. Unlock both.
 * This function can be safely called anytime during an iteration.
 */
static void scx_task_iter_unlock(struct scx_task_iter *iter)
{
	__scx_task_iter_rq_unlock(iter);
	spin_unlock_irq(&scx_tasks_lock);
}

/**
 * scx_task_iter_relock - Lock scx_tasks_lock released by scx_task_iter_unlock()
 * @iter: iterator to re-lock
 *
 * Re-lock scx_tasks_lock unlocked by scx_task_iter_unlock(). Note that it
 * doesn't re-lock the rq lock. Must be called before other iterator operations.
 */
static void scx_task_iter_relock(struct scx_task_iter *iter)
{
	spin_lock_irq(&scx_tasks_lock);
}

/**
 * scx_task_iter_stop - Stop a task iteration and unlock scx_tasks_lock
 * @iter: iterator to exit
 *
 * Exit a previously initialized @iter. Must be called with scx_tasks_lock held
 * which is released on return. If the iterator holds a task's rq lock, that rq
 * lock is also released. See scx_task_iter_start() for details.
 */
static void scx_task_iter_stop(struct scx_task_iter *iter)
{
	list_del_init(&iter->cursor.tasks_node);
	scx_task_iter_unlock(iter);
}

/**
 * scx_task_iter_next - Next task
 * @iter: iterator to walk
 *
 * Visit the next task. See scx_task_iter_start() for details. Locks are dropped
 * and re-acquired every %SCX_OPS_TASK_ITER_BATCH iterations to avoid causing
 * stalls by holding scx_tasks_lock for too long.
 */
static struct task_struct *scx_task_iter_next(struct scx_task_iter *iter)
{
	struct list_head *cursor = &iter->cursor.tasks_node;
	struct sched_ext_entity *pos;

	if (!(++iter->cnt % SCX_OPS_TASK_ITER_BATCH)) {
		scx_task_iter_unlock(iter);
		cond_resched();
		scx_task_iter_relock(iter);
	}

	list_for_each_entry(pos, cursor, tasks_node) {
		if (&pos->tasks_node == &scx_tasks)
			return NULL;
		if (!(pos->flags & SCX_TASK_CURSOR)) {
			list_move(cursor, &pos->tasks_node);
			return container_of(pos, struct task_struct, scx);
		}
	}

	/* can't happen, should always terminate at scx_tasks above */
	BUG();
}

/**
 * scx_task_iter_next_locked - Next non-idle task with its rq locked
 * @iter: iterator to walk
 * @include_dead: Whether we should include dead tasks in the iteration
 *
 * Visit the non-idle task with its rq lock held. Allows callers to specify
 * whether they would like to filter out dead tasks. See scx_task_iter_start()
 * for details.
 */
static struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter)
{
	struct task_struct *p;

	__scx_task_iter_rq_unlock(iter);

	while ((p = scx_task_iter_next(iter))) {
		/*
		 * scx_task_iter is used to prepare and move tasks into SCX
		 * while loading the BPF scheduler and vice-versa while
		 * unloading. The init_tasks ("swappers") should be excluded
		 * from the iteration because:
		 *
		 * - It's unsafe to use __setschduler_prio() on an init_task to
		 *   determine the sched_class to use as it won't preserve its
		 *   idle_sched_class.
		 *
		 * - ops.init/exit_task() can easily be confused if called with
		 *   init_tasks as they, e.g., share PID 0.
		 *
		 * As init_tasks are never scheduled through SCX, they can be
		 * skipped safely. Note that is_idle_task() which tests %PF_IDLE
		 * doesn't work here:
		 *
		 * - %PF_IDLE may not be set for an init_task whose CPU hasn't
		 *   yet been onlined.
		 *
		 * - %PF_IDLE can be set on tasks that are not init_tasks. See
		 *   play_idle_precise() used by CONFIG_IDLE_INJECT.
		 *
		 * Test for idle_sched_class as only init_tasks are on it.
		 */
		if (p->sched_class != &idle_sched_class)
			break;
	}
	if (!p)
		return NULL;

	iter->rq = task_rq_lock(p, &iter->rf);
	iter->locked = p;

	return p;
}

static enum scx_ops_enable_state scx_ops_enable_state(void)
{
	return atomic_read(&scx_ops_enable_state_var);
}

static enum scx_ops_enable_state
scx_ops_set_enable_state(enum scx_ops_enable_state to)
{
	return atomic_xchg(&scx_ops_enable_state_var, to);
}

static bool scx_ops_tryset_enable_state(enum scx_ops_enable_state to,
					enum scx_ops_enable_state from)
{
	int from_v = from;

	return atomic_try_cmpxchg(&scx_ops_enable_state_var, &from_v, to);
}

static bool scx_rq_bypassing(struct rq *rq)
{
	return unlikely(rq->scx.flags & SCX_RQ_BYPASSING);
}

/**
 * wait_ops_state - Busy-wait the specified ops state to end
 * @p: target task
 * @opss: state to wait the end of
 *
 * Busy-wait for @p to transition out of @opss. This can only be used when the
 * state part of @opss is %SCX_QUEUEING or %SCX_DISPATCHING. This function also
 * has load_acquire semantics to ensure that the caller can see the updates made
 * in the enqueueing and dispatching paths.
 */
static void wait_ops_state(struct task_struct *p, unsigned long opss)
{
	do {
		cpu_relax();
	} while (atomic_long_read_acquire(&p->scx.ops_state) == opss);
}

/**
 * ops_cpu_valid - Verify a cpu number
 * @cpu: cpu number which came from a BPF ops
 * @where: extra information reported on error
 *
 * @cpu is a cpu number which came from the BPF scheduler and can be any value.
 * Verify that it is in range and one of the possible cpus. If invalid, trigger
 * an ops error.
 */
static bool ops_cpu_valid(s32 cpu, const char *where)
{
	if (likely(cpu >= 0 && cpu < nr_cpu_ids && cpu_possible(cpu))) {
		return true;
	} else {
		scx_ops_error("invalid CPU %d%s%s", cpu,
			      where ? " " : "", where ?: "");
		return false;
	}
}

/**
 * ops_sanitize_err - Sanitize a -errno value
 * @ops_name: operation to blame on failure
 * @err: -errno value to sanitize
 *
 * Verify @err is a valid -errno. If not, trigger scx_ops_error() and return
 * -%EPROTO. This is necessary because returning a rogue -errno up the chain can
 * cause misbehaviors. For an example, a large negative return from
 * ops.init_task() triggers an oops when passed up the call chain because the
 * value fails IS_ERR() test after being encoded with ERR_PTR() and then is
 * handled as a pointer.
 */
static int ops_sanitize_err(const char *ops_name, s32 err)
{
	if (err < 0 && err >= -MAX_ERRNO)
		return err;

	scx_ops_error("ops.%s() returned an invalid errno %d", ops_name, err);
	return -EPROTO;
}

static void run_deferred(struct rq *rq)
{
	process_ddsp_deferred_locals(rq);
}

#ifdef CONFIG_SMP
static void deferred_bal_cb_workfn(struct rq *rq)
{
	run_deferred(rq);
}
#endif

static void deferred_irq_workfn(struct irq_work *irq_work)
{
	struct rq *rq = container_of(irq_work, struct rq, scx.deferred_irq_work);

	raw_spin_rq_lock(rq);
	run_deferred(rq);
	raw_spin_rq_unlock(rq);
}

/**
 * schedule_deferred - Schedule execution of deferred actions on an rq
 * @rq: target rq
 *
 * Schedule execution of deferred actions on @rq. Must be called with @rq
 * locked. Deferred actions are executed with @rq locked but unpinned, and thus
 * can unlock @rq to e.g. migrate tasks to other rqs.
 */
static void schedule_deferred(struct rq *rq)
{
	lockdep_assert_rq_held(rq);

#ifdef CONFIG_SMP
	/*
	 * If in the middle of waking up a task, task_woken_scx() will be called
	 * afterwards which will then run the deferred actions, no need to
	 * schedule anything.
	 */
	if (rq->scx.flags & SCX_RQ_IN_WAKEUP)
		return;

	/*
	 * If in balance, the balance callbacks will be called before rq lock is
	 * released. Schedule one.
	 */
	if (rq->scx.flags & SCX_RQ_IN_BALANCE) {
		queue_balance_callback(rq, &rq->scx.deferred_bal_cb,
				       deferred_bal_cb_workfn);
		return;
	}
#endif
	/*
	 * No scheduler hooks available. Queue an irq work. They are executed on
	 * IRQ re-enable which may take a bit longer than the scheduler hooks.
	 * The above WAKEUP and BALANCE paths should cover most of the cases and
	 * the time to IRQ re-enable shouldn't be long.
	 */
	irq_work_queue(&rq->scx.deferred_irq_work);
}

/**
 * touch_core_sched - Update timestamp used for core-sched task ordering
 * @rq: rq to read clock from, must be locked
 * @p: task to update the timestamp for
 *
 * Update @p->scx.core_sched_at timestamp. This is used by scx_prio_less() to
 * implement global or local-DSQ FIFO ordering for core-sched. Should be called
 * when a task becomes runnable and its turn on the CPU ends (e.g. slice
 * exhaustion).
 */
static void touch_core_sched(struct rq *rq, struct task_struct *p)
{
	lockdep_assert_rq_held(rq);

#ifdef CONFIG_SCHED_CORE
	/*
	 * It's okay to update the timestamp spuriously. Use
	 * sched_core_disabled() which is cheaper than enabled().
	 *
	 * As this is used to determine ordering between tasks of sibling CPUs,
	 * it may be better to use per-core dispatch sequence instead.
	 */
	if (!sched_core_disabled())
		p->scx.core_sched_at = sched_clock_cpu(cpu_of(rq));
#endif
}

/**
 * touch_core_sched_dispatch - Update core-sched timestamp on dispatch
 * @rq: rq to read clock from, must be locked
 * @p: task being dispatched
 *
 * If the BPF scheduler implements custom core-sched ordering via
 * ops.core_sched_before(), @p->scx.core_sched_at is used to implement FIFO
 * ordering within each local DSQ. This function is called from dispatch paths
 * and updates @p->scx.core_sched_at if custom core-sched ordering is in effect.
 */
static void touch_core_sched_dispatch(struct rq *rq, struct task_struct *p)
{
	lockdep_assert_rq_held(rq);

#ifdef CONFIG_SCHED_CORE
	if (SCX_HAS_OP(core_sched_before))
		touch_core_sched(rq, p);
#endif
}

static void update_curr_scx(struct rq *rq)
{
	struct task_struct *curr = rq->curr;
	s64 delta_exec;

	delta_exec = update_curr_common(rq);
	if (unlikely(delta_exec <= 0))
		return;

	if (curr->scx.slice != SCX_SLICE_INF) {
		curr->scx.slice -= min_t(u64, curr->scx.slice, delta_exec);
		if (!curr->scx.slice)
			touch_core_sched(rq, curr);
	}
}

static bool scx_dsq_priq_less(struct rb_node *node_a,
			      const struct rb_node *node_b)
{
	const struct task_struct *a =
		container_of(node_a, struct task_struct, scx.dsq_priq);
	const struct task_struct *b =
		container_of(node_b, struct task_struct, scx.dsq_priq);

	return time_before64(a->scx.dsq_vtime, b->scx.dsq_vtime);
}

static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta)
{
	/* scx_bpf_dsq_nr_queued() reads ->nr without locking, use WRITE_ONCE() */
	WRITE_ONCE(dsq->nr, dsq->nr + delta);
}

static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p,
			     u64 enq_flags)
{
	bool is_local = dsq->id == SCX_DSQ_LOCAL;

	WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_list.node));
	WARN_ON_ONCE((p->scx.dsq_flags & SCX_TASK_DSQ_ON_PRIQ) ||
		     !RB_EMPTY_NODE(&p->scx.dsq_priq));

	if (!is_local) {
		raw_spin_lock(&dsq->lock);
		if (unlikely(dsq->id == SCX_DSQ_INVALID)) {
			scx_ops_error("attempting to dispatch to a destroyed dsq");
			/* fall back to the global dsq */
			raw_spin_unlock(&dsq->lock);
			dsq = find_global_dsq(p);
			raw_spin_lock(&dsq->lock);
		}
	}

	if (unlikely((dsq->id & SCX_DSQ_FLAG_BUILTIN) &&
		     (enq_flags & SCX_ENQ_DSQ_PRIQ))) {
		/*
		 * SCX_DSQ_LOCAL and SCX_DSQ_GLOBAL DSQs always consume from
		 * their FIFO queues. To avoid confusion and accidentally
		 * starving vtime-dispatched tasks by FIFO-dispatched tasks, we
		 * disallow any internal DSQ from doing vtime ordering of
		 * tasks.
		 */
		scx_ops_error("cannot use vtime ordering for built-in DSQs");
		enq_flags &= ~SCX_ENQ_DSQ_PRIQ;
	}

	if (enq_flags & SCX_ENQ_DSQ_PRIQ) {
		struct rb_node *rbp;

		/*
		 * A PRIQ DSQ shouldn't be using FIFO enqueueing. As tasks are
		 * linked to both the rbtree and list on PRIQs, this can only be
		 * tested easily when adding the first task.
		 */
		if (unlikely(RB_EMPTY_ROOT(&dsq->priq) &&
			     nldsq_next_task(dsq, NULL, false)))
			scx_ops_error("DSQ ID 0x%016llx already had FIFO-enqueued tasks",
				      dsq->id);

		p->scx.dsq_flags |= SCX_TASK_DSQ_ON_PRIQ;
		rb_add(&p->scx.dsq_priq, &dsq->priq, scx_dsq_priq_less);

		/*
		 * Find the previous task and insert after it on the list so
		 * that @dsq->list is vtime ordered.
		 */
		rbp = rb_prev(&p->scx.dsq_priq);
		if (rbp) {
			struct task_struct *prev =
				container_of(rbp, struct task_struct,
					     scx.dsq_priq);
			list_add(&p->scx.dsq_list.node, &prev->scx.dsq_list.node);
		} else {
			list_add(&p->scx.dsq_list.node, &dsq->list);
		}
	} else {
		/* a FIFO DSQ shouldn't be using PRIQ enqueuing */
		if (unlikely(!RB_EMPTY_ROOT(&dsq->priq)))
			scx_ops_error("DSQ ID 0x%016llx already had PRIQ-enqueued tasks",
				      dsq->id);

		if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT))
			list_add(&p->scx.dsq_list.node, &dsq->list);
		else
			list_add_tail(&p->scx.dsq_list.node, &dsq->list);
	}

	/* seq records the order tasks are queued, used by BPF DSQ iterator */
	dsq->seq++;
	p->scx.dsq_seq = dsq->seq;

	dsq_mod_nr(dsq, 1);
	p->scx.dsq = dsq;

	/*
	 * scx.ddsp_dsq_id and scx.ddsp_enq_flags are only relevant on the
	 * direct dispatch path, but we clear them here because the direct
	 * dispatch verdict may be overridden on the enqueue path during e.g.
	 * bypass.
	 */
	p->scx.ddsp_dsq_id = SCX_DSQ_INVALID;
	p->scx.ddsp_enq_flags = 0;

	/*
	 * We're transitioning out of QUEUEING or DISPATCHING. store_release to
	 * match waiters' load_acquire.
	 */
	if (enq_flags & SCX_ENQ_CLEAR_OPSS)
		atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE);

	if (is_local) {
		struct rq *rq = container_of(dsq, struct rq, scx.local_dsq);
		bool preempt = false;

		if ((enq_flags & SCX_ENQ_PREEMPT) && p != rq->curr &&
		    rq->curr->sched_class == &ext_sched_class) {
			rq->curr->scx.slice = 0;
			preempt = true;
		}

		if (preempt || sched_class_above(&ext_sched_class,
						 rq->curr->sched_class))
			resched_curr(rq);
	} else {
		raw_spin_unlock(&dsq->lock);
	}
}

static void task_unlink_from_dsq(struct task_struct *p,
				 struct scx_dispatch_q *dsq)
{
	WARN_ON_ONCE(list_empty(&p->scx.dsq_list.node));

	if (p->scx.dsq_flags & SCX_TASK_DSQ_ON_PRIQ) {
		rb_erase(&p->scx.dsq_priq, &dsq->priq);
		RB_CLEAR_NODE(&p->scx.dsq_priq);
		p->scx.dsq_flags &= ~SCX_TASK_DSQ_ON_PRIQ;
	}

	list_del_init(&p->scx.dsq_list.node);
	dsq_mod_nr(dsq, -1);
}

static void dispatch_dequeue(struct rq *rq, struct task_struct *p)
{
	struct scx_dispatch_q *dsq = p->scx.dsq;
	bool is_local = dsq == &rq->scx.local_dsq;

	if (!dsq) {
		/*
		 * If !dsq && on-list, @p is on @rq's ddsp_deferred_locals.
		 * Unlinking is all that's needed to cancel.
		 */
		if (unlikely(!list_empty(&p->scx.dsq_list.node)))
			list_del_init(&p->scx.dsq_list.node);

		/*
		 * When dispatching directly from the BPF scheduler to a local
		 * DSQ, the task isn't associated with any DSQ but
		 * @p->scx.holding_cpu may be set under the protection of
		 * %SCX_OPSS_DISPATCHING.
		 */
		if (p->scx.holding_cpu >= 0)
			p->scx.holding_cpu = -1;

		return;
	}

	if (!is_local)
		raw_spin_lock(&dsq->lock);

	/*
	 * Now that we hold @dsq->lock, @p->holding_cpu and @p->scx.dsq_* can't
	 * change underneath us.
	*/
	if (p->scx.holding_cpu < 0) {
		/* @p must still be on @dsq, dequeue */
		task_unlink_from_dsq(p, dsq);
	} else {
		/*
		 * We're racing against dispatch_to_local_dsq() which already
		 * removed @p from @dsq and set @p->scx.holding_cpu. Clear the
		 * holding_cpu which tells dispatch_to_local_dsq() that it lost
		 * the race.
		 */
		WARN_ON_ONCE(!list_empty(&p->scx.dsq_list.node));
		p->scx.holding_cpu = -1;
	}
	p->scx.dsq = NULL;

	if (!is_local)
		raw_spin_unlock(&dsq->lock);
}

static struct scx_dispatch_q *find_dsq_for_dispatch(struct rq *rq, u64 dsq_id,
						    struct task_struct *p)
{
	struct scx_dispatch_q *dsq;

	if (dsq_id == SCX_DSQ_LOCAL)
		return &rq->scx.local_dsq;

	if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) {
		s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK;

		if (!ops_cpu_valid(cpu, "in SCX_DSQ_LOCAL_ON dispatch verdict"))
			return find_global_dsq(p);

		return &cpu_rq(cpu)->scx.local_dsq;
	}

	if (dsq_id == SCX_DSQ_GLOBAL)
		dsq = find_global_dsq(p);
	else
		dsq = find_user_dsq(dsq_id);

	if (unlikely(!dsq)) {
		scx_ops_error("non-existent DSQ 0x%llx for %s[%d]",
			      dsq_id, p->comm, p->pid);
		return find_global_dsq(p);
	}

	return dsq;
}

static void mark_direct_dispatch(struct task_struct *ddsp_task,
				 struct task_struct *p, u64 dsq_id,
				 u64 enq_flags)
{
	/*
	 * Mark that dispatch already happened from ops.select_cpu() or
	 * ops.enqueue() by spoiling direct_dispatch_task with a non-NULL value
	 * which can never match a valid task pointer.
	 */
	__this_cpu_write(direct_dispatch_task, ERR_PTR(-ESRCH));

	/* @p must match the task on the enqueue path */
	if (unlikely(p != ddsp_task)) {
		if (IS_ERR(ddsp_task))
			scx_ops_error("%s[%d] already direct-dispatched",
				      p->comm, p->pid);
		else
			scx_ops_error("scheduling for %s[%d] but trying to direct-dispatch %s[%d]",
				      ddsp_task->comm, ddsp_task->pid,
				      p->comm, p->pid);
		return;
	}

	WARN_ON_ONCE(p->scx.ddsp_dsq_id != SCX_DSQ_INVALID);
	WARN_ON_ONCE(p->scx.ddsp_enq_flags);

	p->scx.ddsp_dsq_id = dsq_id;
	p->scx.ddsp_enq_flags = enq_flags;
}

static void direct_dispatch(struct task_struct *p, u64 enq_flags)
{
	struct rq *rq = task_rq(p);
	struct scx_dispatch_q *dsq =
		find_dsq_for_dispatch(rq, p->scx.ddsp_dsq_id, p);

	touch_core_sched_dispatch(rq, p);

	p->scx.ddsp_enq_flags |= enq_flags;

	/*
	 * We are in the enqueue path with @rq locked and pinned, and thus can't
	 * double lock a remote rq and enqueue to its local DSQ. For
	 * DSQ_LOCAL_ON verdicts targeting the local DSQ of a remote CPU, defer
	 * the enqueue so that it's executed when @rq can be unlocked.
	 */
	if (dsq->id == SCX_DSQ_LOCAL && dsq != &rq->scx.local_dsq) {
		unsigned long opss;

		opss = atomic_long_read(&p->scx.ops_state) & SCX_OPSS_STATE_MASK;

		switch (opss & SCX_OPSS_STATE_MASK) {
		case SCX_OPSS_NONE:
			break;
		case SCX_OPSS_QUEUEING:
			/*
			 * As @p was never passed to the BPF side, _release is
			 * not strictly necessary. Still do it for consistency.
			 */
			atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE);
			break;
		default:
			WARN_ONCE(true, "sched_ext: %s[%d] has invalid ops state 0x%lx in direct_dispatch()",
				  p->comm, p->pid, opss);
			atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE);
			break;
		}

		WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_list.node));
		list_add_tail(&p->scx.dsq_list.node,
			      &rq->scx.ddsp_deferred_locals);
		schedule_deferred(rq);
		return;
	}

	dispatch_enqueue(dsq, p, p->scx.ddsp_enq_flags | SCX_ENQ_CLEAR_OPSS);
}

static bool scx_rq_online(struct rq *rq)
{
	/*
	 * Test both cpu_active() and %SCX_RQ_ONLINE. %SCX_RQ_ONLINE indicates
	 * the online state as seen from the BPF scheduler. cpu_active() test
	 * guarantees that, if this function returns %true, %SCX_RQ_ONLINE will
	 * stay set until the current scheduling operation is complete even if
	 * we aren't locking @rq.
	 */
	return likely((rq->scx.flags & SCX_RQ_ONLINE) && cpu_active(cpu_of(rq)));
}

static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
			    int sticky_cpu)
{
	struct task_struct **ddsp_taskp;
	unsigned long qseq;

	WARN_ON_ONCE(!(p->scx.flags & SCX_TASK_QUEUED));

	/* rq migration */
	if (sticky_cpu == cpu_of(rq))
		goto local_norefill;

	/*
	 * If !scx_rq_online(), we already told the BPF scheduler that the CPU
	 * is offline and are just running the hotplug path. Don't bother the
	 * BPF scheduler.
	 */
	if (!scx_rq_online(rq))
		goto local;

	if (scx_rq_bypassing(rq))
		goto global;

	if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID)
		goto direct;

	/* see %SCX_OPS_ENQ_EXITING */
	if (!static_branch_unlikely(&scx_ops_enq_exiting) &&
	    unlikely(p->flags & PF_EXITING))
		goto local;

	if (!SCX_HAS_OP(enqueue))
		goto global;

	/* DSQ bypass didn't trigger, enqueue on the BPF scheduler */
	qseq = rq->scx.ops_qseq++ << SCX_OPSS_QSEQ_SHIFT;

	WARN_ON_ONCE(atomic_long_read(&p->scx.ops_state) != SCX_OPSS_NONE);
	atomic_long_set(&p->scx.ops_state, SCX_OPSS_QUEUEING | qseq);

	ddsp_taskp = this_cpu_ptr(&direct_dispatch_task);
	WARN_ON_ONCE(*ddsp_taskp);
	*ddsp_taskp = p;

	SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, p, enq_flags);

	*ddsp_taskp = NULL;
	if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID)
		goto direct;

	/*
	 * If not directly dispatched, QUEUEING isn't clear yet and dispatch or
	 * dequeue may be waiting. The store_release matches their load_acquire.
	 */
	atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_QUEUED | qseq);
	return;

direct:
	direct_dispatch(p, enq_flags);
	return;

local:
	/*
	 * For task-ordering, slice refill must be treated as implying the end
	 * of the current slice. Otherwise, the longer @p stays on the CPU, the
	 * higher priority it becomes from scx_prio_less()'s POV.
	 */
	touch_core_sched(rq, p);
	p->scx.slice = SCX_SLICE_DFL;
local_norefill:
	dispatch_enqueue(&rq->scx.local_dsq, p, enq_flags);
	return;

global:
	touch_core_sched(rq, p);	/* see the comment in local: */
	p->scx.slice = SCX_SLICE_DFL;
	dispatch_enqueue(find_global_dsq(p), p, enq_flags);
}

static bool task_runnable(const struct task_struct *p)
{
	return !list_empty(&p->scx.runnable_node);
}

static void set_task_runnable(struct rq *rq, struct task_struct *p)
{
	lockdep_assert_rq_held(rq);

	if (p->scx.flags & SCX_TASK_RESET_RUNNABLE_AT) {
		p->scx.runnable_at = jiffies;
		p->scx.flags &= ~SCX_TASK_RESET_RUNNABLE_AT;
	}

	/*
	 * list_add_tail() must be used. scx_ops_bypass() depends on tasks being
	 * appened to the runnable_list.
	 */
	list_add_tail(&p->scx.runnable_node, &rq->scx.runnable_list);
}

static void clr_task_runnable(struct task_struct *p, bool reset_runnable_at)
{
	list_del_init(&p->scx.runnable_node);
	if (reset_runnable_at)
		p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT;
}

static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags)
{
	int sticky_cpu = p->scx.sticky_cpu;

	if (enq_flags & ENQUEUE_WAKEUP)
		rq->scx.flags |= SCX_RQ_IN_WAKEUP;

	enq_flags |= rq->scx.extra_enq_flags;

	if (sticky_cpu >= 0)
		p->scx.sticky_cpu = -1;

	/*
	 * Restoring a running task will be immediately followed by
	 * set_next_task_scx() which expects the task to not be on the BPF
	 * scheduler as tasks can only start running through local DSQs. Force
	 * direct-dispatch into the local DSQ by setting the sticky_cpu.
	 */
	if (unlikely(enq_flags & ENQUEUE_RESTORE) && task_current(rq, p))
		sticky_cpu = cpu_of(rq);

	if (p->scx.flags & SCX_TASK_QUEUED) {
		WARN_ON_ONCE(!task_runnable(p));
		goto out;
	}

	set_task_runnable(rq, p);
	p->scx.flags |= SCX_TASK_QUEUED;
	rq->scx.nr_running++;
	add_nr_running(rq, 1);

	if (SCX_HAS_OP(runnable) && !task_on_rq_migrating(p))
		SCX_CALL_OP_TASK(SCX_KF_REST, runnable, p, enq_flags);

	if (enq_flags & SCX_ENQ_WAKEUP)
		touch_core_sched(rq, p);

	do_enqueue_task(rq, p, enq_flags, sticky_cpu);
out:
	rq->scx.flags &= ~SCX_RQ_IN_WAKEUP;
}

static void ops_dequeue(struct task_struct *p, u64 deq_flags)
{
	unsigned long opss;

	/* dequeue is always temporary, don't reset runnable_at */
	clr_task_runnable(p, false);

	/* acquire ensures that we see the preceding updates on QUEUED */
	opss = atomic_long_read_acquire(&p->scx.ops_state);

	switch (opss & SCX_OPSS_STATE_MASK) {
	case SCX_OPSS_NONE:
		break;
	case SCX_OPSS_QUEUEING:
		/*
		 * QUEUEING is started and finished while holding @p's rq lock.
		 * As we're holding the rq lock now, we shouldn't see QUEUEING.
		 */
		BUG();
	case SCX_OPSS_QUEUED:
		if (SCX_HAS_OP(dequeue))
			SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, p, deq_flags);

		if (atomic_long_try_cmpxchg(&p->scx.ops_state, &opss,
					    SCX_OPSS_NONE))
			break;
		fallthrough;
	case SCX_OPSS_DISPATCHING:
		/*
		 * If @p is being dispatched from the BPF scheduler to a DSQ,
		 * wait for the transfer to complete so that @p doesn't get
		 * added to its DSQ after dequeueing is complete.
		 *
		 * As we're waiting on DISPATCHING with the rq locked, the
		 * dispatching side shouldn't try to lock the rq while
		 * DISPATCHING is set. See dispatch_to_local_dsq().
		 *
		 * DISPATCHING shouldn't have qseq set and control can reach
		 * here with NONE @opss from the above QUEUED case block.
		 * Explicitly wait on %SCX_OPSS_DISPATCHING instead of @opss.
		 */
		wait_ops_state(p, SCX_OPSS_DISPATCHING);
		BUG_ON(atomic_long_read(&p->scx.ops_state) != SCX_OPSS_NONE);
		break;
	}
}

static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags)
{
	if (!(p->scx.flags & SCX_TASK_QUEUED)) {
		WARN_ON_ONCE(task_runnable(p));
		return true;
	}

	ops_dequeue(p, deq_flags);

	/*
	 * A currently running task which is going off @rq first gets dequeued
	 * and then stops running. As we want running <-> stopping transitions
	 * to be contained within runnable <-> quiescent transitions, trigger
	 * ->stopping() early here instead of in put_prev_task_scx().
	 *
	 * @p may go through multiple stopping <-> running transitions between
	 * here and put_prev_task_scx() if task attribute changes occur while
	 * balance_scx() leaves @rq unlocked. However, they don't contain any
	 * information meaningful to the BPF scheduler and can be suppressed by
	 * skipping the callbacks if the task is !QUEUED.
	 */
	if (SCX_HAS_OP(stopping) && task_current(rq, p)) {
		update_curr_scx(rq);
		SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, false);
	}

	if (SCX_HAS_OP(quiescent) && !task_on_rq_migrating(p))
		SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, p, deq_flags);

	if (deq_flags & SCX_DEQ_SLEEP)
		p->scx.flags |= SCX_TASK_DEQD_FOR_SLEEP;
	else
		p->scx.flags &= ~SCX_TASK_DEQD_FOR_SLEEP;

	p->scx.flags &= ~SCX_TASK_QUEUED;
	rq->scx.nr_running--;
	sub_nr_running(rq, 1);

	dispatch_dequeue(rq, p);
	return true;
}

static void yield_task_scx(struct rq *rq)
{
	struct task_struct *p = rq->curr;

	if (SCX_HAS_OP(yield))
		SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, p, NULL);
	else
		p->scx.slice = 0;
}

static bool yield_to_task_scx(struct rq *rq, struct task_struct *to)
{
	struct task_struct *from = rq->curr;

	if (SCX_HAS_OP(yield))
		return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, from, to);
	else
		return false;
}

static void move_local_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
					 struct scx_dispatch_q *src_dsq,
					 struct rq *dst_rq)
{
	struct scx_dispatch_q *dst_dsq = &dst_rq->scx.local_dsq;

	/* @dsq is locked and @p is on @dst_rq */
	lockdep_assert_held(&src_dsq->lock);
	lockdep_assert_rq_held(dst_rq);

	WARN_ON_ONCE(p->scx.holding_cpu >= 0);

	if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT))
		list_add(&p->scx.dsq_list.node, &dst_dsq->list);
	else
		list_add_tail(&p->scx.dsq_list.node, &dst_dsq->list);

	dsq_mod_nr(dst_dsq, 1);
	p->scx.dsq = dst_dsq;
}

#ifdef CONFIG_SMP
/**
 * move_remote_task_to_local_dsq - Move a task from a foreign rq to a local DSQ
 * @p: task to move
 * @enq_flags: %SCX_ENQ_*
 * @src_rq: rq to move the task from, locked on entry, released on return
 * @dst_rq: rq to move the task into, locked on return
 *
 * Move @p which is currently on @src_rq to @dst_rq's local DSQ.
 */
static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
					  struct rq *src_rq, struct rq *dst_rq)
{
	lockdep_assert_rq_held(src_rq);

	/* the following marks @p MIGRATING which excludes dequeue */
	deactivate_task(src_rq, p, 0);
	set_task_cpu(p, cpu_of(dst_rq));
	p->scx.sticky_cpu = cpu_of(dst_rq);

	raw_spin_rq_unlock(src_rq);
	raw_spin_rq_lock(dst_rq);

	/*
	 * We want to pass scx-specific enq_flags but activate_task() will
	 * truncate the upper 32 bit. As we own @rq, we can pass them through
	 * @rq->scx.extra_enq_flags instead.
	 */
	WARN_ON_ONCE(!cpumask_test_cpu(cpu_of(dst_rq), p->cpus_ptr));
	WARN_ON_ONCE(dst_rq->scx.extra_enq_flags);
	dst_rq->scx.extra_enq_flags = enq_flags;
	activate_task(dst_rq, p, 0);
	dst_rq->scx.extra_enq_flags = 0;
}

/*
 * Similar to kernel/sched/core.c::is_cpu_allowed(). However, there are two
 * differences:
 *
 * - is_cpu_allowed() asks "Can this task run on this CPU?" while
 *   task_can_run_on_remote_rq() asks "Can the BPF scheduler migrate the task to
 *   this CPU?".
 *
 *   While migration is disabled, is_cpu_allowed() has to say "yes" as the task
 *   must be allowed to finish on the CPU that it's currently on regardless of
 *   the CPU state. However, task_can_run_on_remote_rq() must say "no" as the
 *   BPF scheduler shouldn't attempt to migrate a task which has migration
 *   disabled.
 *
 * - The BPF scheduler is bypassed while the rq is offline and we can always say
 *   no to the BPF scheduler initiated migrations while offline.
 */
static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq,
				      bool trigger_error)
{
	int cpu = cpu_of(rq);

	/*
	 * We don't require the BPF scheduler to avoid dispatching to offline
	 * CPUs mostly for convenience but also because CPUs can go offline
	 * between scx_bpf_dispatch() calls and here. Trigger error iff the
	 * picked CPU is outside the allowed mask.
	 */
	if (!task_allowed_on_cpu(p, cpu)) {
		if (trigger_error)
			scx_ops_error("SCX_DSQ_LOCAL[_ON] verdict target cpu %d not allowed for %s[%d]",
				      cpu_of(rq), p->comm, p->pid);
		return false;
	}

	if (unlikely(is_migration_disabled(p)))
		return false;

	if (!scx_rq_online(rq))
		return false;

	return true;
}

/**
 * unlink_dsq_and_lock_src_rq() - Unlink task from its DSQ and lock its task_rq
 * @p: target task
 * @dsq: locked DSQ @p is currently on
 * @src_rq: rq @p is currently on, stable with @dsq locked
 *
 * Called with @dsq locked but no rq's locked. We want to move @p to a different
 * DSQ, including any local DSQ, but are not locking @src_rq. Locking @src_rq is
 * required when transferring into a local DSQ. Even when transferring into a
 * non-local DSQ, it's better to use the same mechanism to protect against
 * dequeues and maintain the invariant that @p->scx.dsq can only change while
 * @src_rq is locked, which e.g. scx_dump_task() depends on.
 *
 * We want to grab @src_rq but that can deadlock if we try while locking @dsq,
 * so we want to unlink @p from @dsq, drop its lock and then lock @src_rq. As
 * this may race with dequeue, which can't drop the rq lock or fail, do a little
 * dancing from our side.
 *
 * @p->scx.holding_cpu is set to this CPU before @dsq is unlocked. If @p gets
 * dequeued after we unlock @dsq but before locking @src_rq, the holding_cpu
 * would be cleared to -1. While other cpus may have updated it to different
 * values afterwards, as this operation can't be preempted or recurse, the
 * holding_cpu can never become this CPU again before we're done. Thus, we can
 * tell whether we lost to dequeue by testing whether the holding_cpu still
 * points to this CPU. See dispatch_dequeue() for the counterpart.
 *
 * On return, @dsq is unlocked and @src_rq is locked. Returns %true if @p is
 * still valid. %false if lost to dequeue.
 */
static bool unlink_dsq_and_lock_src_rq(struct task_struct *p,
				       struct scx_dispatch_q *dsq,
				       struct rq *src_rq)
{
	s32 cpu = raw_smp_processor_id();

	lockdep_assert_held(&dsq->lock);

	WARN_ON_ONCE(p->scx.holding_cpu >= 0);
	task_unlink_from_dsq(p, dsq);
	p->scx.holding_cpu = cpu;

	raw_spin_unlock(&dsq->lock);
	raw_spin_rq_lock(src_rq);

	/* task_rq couldn't have changed if we're still the holding cpu */
	return likely(p->scx.holding_cpu == cpu) &&
		!WARN_ON_ONCE(src_rq != task_rq(p));
}

static bool consume_remote_task(struct rq *this_rq, struct task_struct *p,
				struct scx_dispatch_q *dsq, struct rq *src_rq)
{
	raw_spin_rq_unlock(this_rq);

	if (unlink_dsq_and_lock_src_rq(p, dsq, src_rq)) {
		move_remote_task_to_local_dsq(p, 0, src_rq, this_rq);
		return true;
	} else {
		raw_spin_rq_unlock(src_rq);
		raw_spin_rq_lock(this_rq);
		return false;
	}
}
#else	/* CONFIG_SMP */
static inline void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags, struct rq *src_rq, struct rq *dst_rq) { WARN_ON_ONCE(1); }
static inline bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq, bool trigger_error) { return false; }
static inline bool consume_remote_task(struct rq *this_rq, struct task_struct *p, struct scx_dispatch_q *dsq, struct rq *task_rq) { return false; }
#endif	/* CONFIG_SMP */

static bool consume_dispatch_q(struct rq *rq, struct scx_dispatch_q *dsq)
{
	struct task_struct *p;
retry:
	/*
	 * The caller can't expect to successfully consume a task if the task's
	 * addition to @dsq isn't guaranteed to be visible somehow. Test
	 * @dsq->list without locking and skip if it seems empty.
	 */
	if (list_empty(&dsq->list))
		return false;

	raw_spin_lock(&dsq->lock);

	nldsq_for_each_task(p, dsq) {
		struct rq *task_rq = task_rq(p);

		if (rq == task_rq) {
			task_unlink_from_dsq(p, dsq);
			move_local_task_to_local_dsq(p, 0, dsq, rq);
			raw_spin_unlock(&dsq->lock);
			return true;
		}

		if (task_can_run_on_remote_rq(p, rq, false)) {
			if (likely(consume_remote_task(rq, p, dsq, task_rq)))
				return true;
			goto retry;
		}
	}

	raw_spin_unlock(&dsq->lock);
	return false;
}

static bool consume_global_dsq(struct rq *rq)
{
	int node = cpu_to_node(cpu_of(rq));

	return consume_dispatch_q(rq, global_dsqs[node]);
}

/**
 * dispatch_to_local_dsq - Dispatch a task to a local dsq
 * @rq: current rq which is locked
 * @dst_dsq: destination DSQ
 * @p: task to dispatch
 * @enq_flags: %SCX_ENQ_*
 *
 * We're holding @rq lock and want to dispatch @p to @dst_dsq which is a local
 * DSQ. This function performs all the synchronization dancing needed because
 * local DSQs are protected with rq locks.
 *
 * The caller must have exclusive ownership of @p (e.g. through
 * %SCX_OPSS_DISPATCHING).
 */
static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
				  struct task_struct *p, u64 enq_flags)
{
	struct rq *src_rq = task_rq(p);
	struct rq *dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq);

	/*
	 * We're synchronized against dequeue through DISPATCHING. As @p can't
	 * be dequeued, its task_rq and cpus_allowed are stable too.
	 *
	 * If dispatching to @rq that @p is already on, no lock dancing needed.
	 */
	if (rq == src_rq && rq == dst_rq) {
		dispatch_enqueue(dst_dsq, p, enq_flags | SCX_ENQ_CLEAR_OPSS);
		return;
	}

#ifdef CONFIG_SMP
	if (unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) {
		dispatch_enqueue(find_global_dsq(p), p,
				 enq_flags | SCX_ENQ_CLEAR_OPSS);
		return;
	}

	/*
	 * @p is on a possibly remote @src_rq which we need to lock to move the
	 * task. If dequeue is in progress, it'd be locking @src_rq and waiting
	 * on DISPATCHING, so we can't grab @src_rq lock while holding
	 * DISPATCHING.
	 *
	 * As DISPATCHING guarantees that @p is wholly ours, we can pretend that
	 * we're moving from a DSQ and use the same mechanism - mark the task
	 * under transfer with holding_cpu, release DISPATCHING and then follow
	 * the same protocol. See unlink_dsq_and_lock_src_rq().
	 */
	p->scx.holding_cpu = raw_smp_processor_id();

	/* store_release ensures that dequeue sees the above */
	atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE);

	/* switch to @src_rq lock */
	if (rq != src_rq) {
		raw_spin_rq_unlock(rq);
		raw_spin_rq_lock(src_rq);
	}

	/* task_rq couldn't have changed if we're still the holding cpu */
	if (likely(p->scx.holding_cpu == raw_smp_processor_id()) &&
	    !WARN_ON_ONCE(src_rq != task_rq(p))) {
		/*
		 * If @p is staying on the same rq, there's no need to go
		 * through the full deactivate/activate cycle. Optimize by
		 * abbreviating move_remote_task_to_local_dsq().
		 */
		if (src_rq == dst_rq) {
			p->scx.holding_cpu = -1;
			dispatch_enqueue(&dst_rq->scx.local_dsq, p, enq_flags);
		} else {
			move_remote_task_to_local_dsq(p, enq_flags,
						      src_rq, dst_rq);
		}

		/* if the destination CPU is idle, wake it up */
		if (sched_class_above(p->sched_class, dst_rq->curr->sched_class))
			resched_curr(dst_rq);
	}

	/* switch back to @rq lock */
	if (rq != dst_rq) {
		raw_spin_rq_unlock(dst_rq);
		raw_spin_rq_lock(rq);
	}
#else	/* CONFIG_SMP */
	BUG();	/* control can not reach here on UP */
#endif	/* CONFIG_SMP */
}

/**
 * finish_dispatch - Asynchronously finish dispatching a task
 * @rq: current rq which is locked
 * @p: task to finish dispatching
 * @qseq_at_dispatch: qseq when @p started getting dispatched
 * @dsq_id: destination DSQ ID
 * @enq_flags: %SCX_ENQ_*
 *
 * Dispatching to local DSQs may need to wait for queueing to complete or
 * require rq lock dancing. As we don't wanna do either while inside
 * ops.dispatch() to avoid locking order inversion, we split dispatching into
 * two parts. scx_bpf_dispatch() which is called by ops.dispatch() records the
 * task and its qseq. Once ops.dispatch() returns, this function is called to
 * finish up.
 *
 * There is no guarantee that @p is still valid for dispatching or even that it
 * was valid in the first place. Make sure that the task is still owned by the
 * BPF scheduler and claim the ownership before dispatching.
 */
static void finish_dispatch(struct rq *rq, struct task_struct *p,
			    unsigned long qseq_at_dispatch,
			    u64 dsq_id, u64 enq_flags)
{
	struct scx_dispatch_q *dsq;
	unsigned long opss;

	touch_core_sched_dispatch(rq, p);
retry:
	/*
	 * No need for _acquire here. @p is accessed only after a successful
	 * try_cmpxchg to DISPATCHING.
	 */
	opss = atomic_long_read(&p->scx.ops_state);

	switch (opss & SCX_OPSS_STATE_MASK) {
	case SCX_OPSS_DISPATCHING:
	case SCX_OPSS_NONE:
		/* someone else already got to it */
		return;
	case SCX_OPSS_QUEUED:
		/*
		 * If qseq doesn't match, @p has gone through at least one
		 * dispatch/dequeue and re-enqueue cycle between
		 * scx_bpf_dispatch() and here and we have no claim on it.
		 */
		if ((opss & SCX_OPSS_QSEQ_MASK) != qseq_at_dispatch)
			return;

		/*
		 * While we know @p is accessible, we don't yet have a claim on
		 * it - the BPF scheduler is allowed to dispatch tasks
		 * spuriously and there can be a racing dequeue attempt. Let's
		 * claim @p by atomically transitioning it from QUEUED to
		 * DISPATCHING.
		 */
		if (likely(atomic_long_try_cmpxchg(&p->scx.ops_state, &opss,
						   SCX_OPSS_DISPATCHING)))
			break;
		goto retry;
	case SCX_OPSS_QUEUEING:
		/*
		 * do_enqueue_task() is in the process of transferring the task
		 * to the BPF scheduler while holding @p's rq lock. As we aren't
		 * holding any kernel or BPF resource that the enqueue path may
		 * depend upon, it's safe to wait.
		 */
		wait_ops_state(p, opss);
		goto retry;
	}

	BUG_ON(!(p->scx.flags & SCX_TASK_QUEUED));

	dsq = find_dsq_for_dispatch(this_rq(), dsq_id, p);

	if (dsq->id == SCX_DSQ_LOCAL)
		dispatch_to_local_dsq(rq, dsq, p, enq_flags);
	else
		dispatch_enqueue(dsq, p, enq_flags | SCX_ENQ_CLEAR_OPSS);
}

static void flush_dispatch_buf(struct rq *rq)
{
	struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);
	u32 u;

	for (u = 0; u < dspc->cursor; u++) {
		struct scx_dsp_buf_ent *ent = &dspc->buf[u];

		finish_dispatch(rq, ent->task, ent->qseq, ent->dsq_id,
				ent->enq_flags);
	}

	dspc->nr_tasks += dspc->cursor;
	dspc->cursor = 0;
}

static int balance_one(struct rq *rq, struct task_struct *prev)
{
	struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);
	bool prev_on_scx = prev->sched_class == &ext_sched_class;
	int nr_loops = SCX_DSP_MAX_LOOPS;

	lockdep_assert_rq_held(rq);
	rq->scx.flags |= SCX_RQ_IN_BALANCE;
	rq->scx.flags &= ~SCX_RQ_BAL_KEEP;

	if (static_branch_unlikely(&scx_ops_cpu_preempt) &&
	    unlikely(rq->scx.cpu_released)) {
		/*
		 * If the previous sched_class for the current CPU was not SCX,
		 * notify the BPF scheduler that it again has control of the
		 * core. This callback complements ->cpu_release(), which is
		 * emitted in scx_next_task_picked().
		 */
		if (SCX_HAS_OP(cpu_acquire))
			SCX_CALL_OP(0, cpu_acquire, cpu_of(rq), NULL);
		rq->scx.cpu_released = false;
	}

	if (prev_on_scx) {
		update_curr_scx(rq);

		/*
		 * If @prev is runnable & has slice left, it has priority and
		 * fetching more just increases latency for the fetched tasks.
		 * Tell pick_task_scx() to keep running @prev. If the BPF
		 * scheduler wants to handle this explicitly, it should
		 * implement ->cpu_release().
		 *
		 * See scx_ops_disable_workfn() for the explanation on the
		 * bypassing test.
		 */
		if ((prev->scx.flags & SCX_TASK_QUEUED) &&
		    prev->scx.slice && !scx_rq_bypassing(rq)) {
			rq->scx.flags |= SCX_RQ_BAL_KEEP;
			goto has_tasks;
		}
	}

	/* if there already are tasks to run, nothing to do */
	if (rq->scx.local_dsq.nr)
		goto has_tasks;

	if (consume_global_dsq(rq))
		goto has_tasks;

	if (!SCX_HAS_OP(dispatch) || scx_rq_bypassing(rq) || !scx_rq_online(rq))
		goto no_tasks;

	dspc->rq = rq;

	/*
	 * The dispatch loop. Because flush_dispatch_buf() may drop the rq lock,
	 * the local DSQ might still end up empty after a successful
	 * ops.dispatch(). If the local DSQ is empty even after ops.dispatch()
	 * produced some tasks, retry. The BPF scheduler may depend on this
	 * looping behavior to simplify its implementation.
	 */
	do {
		dspc->nr_tasks = 0;

		SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, cpu_of(rq),
			    prev_on_scx ? prev : NULL);

		flush_dispatch_buf(rq);

		if (rq->scx.local_dsq.nr)
			goto has_tasks;
		if (consume_global_dsq(rq))
			goto has_tasks;

		/*
		 * ops.dispatch() can trap us in this loop by repeatedly
		 * dispatching ineligible tasks. Break out once in a while to
		 * allow the watchdog to run. As IRQ can't be enabled in
		 * balance(), we want to complete this scheduling cycle and then
		 * start a new one. IOW, we want to call resched_curr() on the
		 * next, most likely idle, task, not the current one. Use
		 * scx_bpf_kick_cpu() for deferred kicking.
		 */
		if (unlikely(!--nr_loops)) {
			scx_bpf_kick_cpu(cpu_of(rq), 0);
			break;
		}
	} while (dspc->nr_tasks);

no_tasks:
	/*
	 * Didn't find another task to run. Keep running @prev unless
	 * %SCX_OPS_ENQ_LAST is in effect.
	 */
	if ((prev->scx.flags & SCX_TASK_QUEUED) &&
	    (!static_branch_unlikely(&scx_ops_enq_last) ||
	     scx_rq_bypassing(rq))) {
		rq->scx.flags |= SCX_RQ_BAL_KEEP;
		goto has_tasks;
	}
	rq->scx.flags &= ~SCX_RQ_IN_BALANCE;
	return false;

has_tasks:
	rq->scx.flags &= ~SCX_RQ_IN_BALANCE;
	return true;
}

static int balance_scx(struct rq *rq, struct task_struct *prev,
		       struct rq_flags *rf)
{
	int ret;

	rq_unpin_lock(rq, rf);

	ret = balance_one(rq, prev);

#ifdef CONFIG_SCHED_SMT
	/*
	 * When core-sched is enabled, this ops.balance() call will be followed
	 * by pick_task_scx() on this CPU and the SMT siblings. Balance the
	 * siblings too.
	 */
	if (sched_core_enabled(rq)) {
		const struct cpumask *smt_mask = cpu_smt_mask(cpu_of(rq));
		int scpu;

		for_each_cpu_andnot(scpu, smt_mask, cpumask_of(cpu_of(rq))) {
			struct rq *srq = cpu_rq(scpu);
			struct task_struct *sprev = srq->curr;

			WARN_ON_ONCE(__rq_lockp(rq) != __rq_lockp(srq));
			update_rq_clock(srq);
			balance_one(srq, sprev);
		}
	}
#endif
	rq_repin_lock(rq, rf);

	return ret;
}

static void process_ddsp_deferred_locals(struct rq *rq)
{
	struct task_struct *p;

	lockdep_assert_rq_held(rq);

	/*
	 * Now that @rq can be unlocked, execute the deferred enqueueing of
	 * tasks directly dispatched to the local DSQs of other CPUs. See
	 * direct_dispatch(). Keep popping from the head instead of using
	 * list_for_each_entry_safe() as dispatch_local_dsq() may unlock @rq
	 * temporarily.
	 */
	while ((p = list_first_entry_or_null(&rq->scx.ddsp_deferred_locals,
				struct task_struct, scx.dsq_list.node))) {
		struct scx_dispatch_q *dsq;

		list_del_init(&p->scx.dsq_list.node);

		dsq = find_dsq_for_dispatch(rq, p->scx.ddsp_dsq_id, p);
		if (!WARN_ON_ONCE(dsq->id != SCX_DSQ_LOCAL))
			dispatch_to_local_dsq(rq, dsq, p, p->scx.ddsp_enq_flags);
	}
}

static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
{
	if (p->scx.flags & SCX_TASK_QUEUED) {
		/*
		 * Core-sched might decide to execute @p before it is
		 * dispatched. Call ops_dequeue() to notify the BPF scheduler.
		 */
		ops_dequeue(p, SCX_DEQ_CORE_SCHED_EXEC);
		dispatch_dequeue(rq, p);
	}

	p->se.exec_start = rq_clock_task(rq);

	/* see dequeue_task_scx() on why we skip when !QUEUED */
	if (SCX_HAS_OP(running) && (p->scx.flags & SCX_TASK_QUEUED))
		SCX_CALL_OP_TASK(SCX_KF_REST, running, p);

	clr_task_runnable(p, true);

	/*
	 * @p is getting newly scheduled or got kicked after someone updated its
	 * slice. Refresh whether tick can be stopped. See scx_can_stop_tick().
	 */
	if ((p->scx.slice == SCX_SLICE_INF) !=
	    (bool)(rq->scx.flags & SCX_RQ_CAN_STOP_TICK)) {
		if (p->scx.slice == SCX_SLICE_INF)
			rq->scx.flags |= SCX_RQ_CAN_STOP_TICK;
		else
			rq->scx.flags &= ~SCX_RQ_CAN_STOP_TICK;

		sched_update_tick_dependency(rq);

		/*
		 * For now, let's refresh the load_avgs just when transitioning
		 * in and out of nohz. In the future, we might want to add a
		 * mechanism which calls the following periodically on
		 * tick-stopped CPUs.
		 */
		update_other_load_avgs(rq);
	}
}

static enum scx_cpu_preempt_reason
preempt_reason_from_class(const struct sched_class *class)
{
#ifdef CONFIG_SMP
	if (class == &stop_sched_class)
		return SCX_CPU_PREEMPT_STOP;
#endif
	if (class == &dl_sched_class)
		return SCX_CPU_PREEMPT_DL;
	if (class == &rt_sched_class)
		return SCX_CPU_PREEMPT_RT;
	return SCX_CPU_PREEMPT_UNKNOWN;
}

static void switch_class(struct rq *rq, struct task_struct *next)
{
	const struct sched_class *next_class = next->sched_class;

#ifdef CONFIG_SMP
	/*
	 * Pairs with the smp_load_acquire() issued by a CPU in
	 * kick_cpus_irq_workfn() who is waiting for this CPU to perform a
	 * resched.
	 */
	smp_store_release(&rq->scx.pnt_seq, rq->scx.pnt_seq + 1);
#endif
	if (!static_branch_unlikely(&scx_ops_cpu_preempt))
		return;

	/*
	 * The callback is conceptually meant to convey that the CPU is no
	 * longer under the control of SCX. Therefore, don't invoke the callback
	 * if the next class is below SCX (in which case the BPF scheduler has
	 * actively decided not to schedule any tasks on the CPU).
	 */
	if (sched_class_above(&ext_sched_class, next_class))
		return;

	/*
	 * At this point we know that SCX was preempted by a higher priority
	 * sched_class, so invoke the ->cpu_release() callback if we have not
	 * done so already. We only send the callback once between SCX being
	 * preempted, and it regaining control of the CPU.
	 *
	 * ->cpu_release() complements ->cpu_acquire(), which is emitted the
	 *  next time that balance_scx() is invoked.
	 */
	if (!rq->scx.cpu_released) {
		if (SCX_HAS_OP(cpu_release)) {
			struct scx_cpu_release_args args = {
				.reason = preempt_reason_from_class(next_class),
				.task = next,
			};

			SCX_CALL_OP(SCX_KF_CPU_RELEASE,
				    cpu_release, cpu_of(rq), &args);
		}
		rq->scx.cpu_released = true;
	}
}

static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
			      struct task_struct *next)
{
	update_curr_scx(rq);

	/* see dequeue_task_scx() on why we skip when !QUEUED */
	if (SCX_HAS_OP(stopping) && (p->scx.flags & SCX_TASK_QUEUED))
		SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, true);

	if (p->scx.flags & SCX_TASK_QUEUED) {
		set_task_runnable(rq, p);

		/*
		 * If @p has slice left and is being put, @p is getting
		 * preempted by a higher priority scheduler class or core-sched
		 * forcing a different task. Leave it at the head of the local
		 * DSQ.
		 */
		if (p->scx.slice && !scx_rq_bypassing(rq)) {
			dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD);
			return;
		}

		/*
		 * If @p is runnable but we're about to enter a lower
		 * sched_class, %SCX_OPS_ENQ_LAST must be set. Tell
		 * ops.enqueue() that @p is the only one available for this cpu,
		 * which should trigger an explicit follow-up scheduling event.
		 */
		if (sched_class_above(&ext_sched_class, next->sched_class)) {
			WARN_ON_ONCE(!static_branch_unlikely(&scx_ops_enq_last));
			do_enqueue_task(rq, p, SCX_ENQ_LAST, -1);
		} else {
			do_enqueue_task(rq, p, 0, -1);
		}
	}

	if (next && next->sched_class != &ext_sched_class)
		switch_class(rq, next);
}

static struct task_struct *first_local_task(struct rq *rq)
{
	return list_first_entry_or_null(&rq->scx.local_dsq.list,
					struct task_struct, scx.dsq_list.node);
}

static struct task_struct *pick_task_scx(struct rq *rq)
{
	struct task_struct *prev = rq->curr;
	struct task_struct *p;

	/*
	 * If balance_scx() is telling us to keep running @prev, replenish slice
	 * if necessary and keep running @prev. Otherwise, pop the first one
	 * from the local DSQ.
	 *
	 * WORKAROUND:
	 *
	 * %SCX_RQ_BAL_KEEP should be set iff $prev is on SCX as it must just
	 * have gone through balance_scx(). Unfortunately, there currently is a
	 * bug where fair could say yes on balance() but no on pick_task(),
	 * which then ends up calling pick_task_scx() without preceding
	 * balance_scx().
	 *
	 * For now, ignore cases where $prev is not on SCX. This isn't great and
	 * can theoretically lead to stalls. However, for switch_all cases, this
	 * happens only while a BPF scheduler is being loaded or unloaded, and,
	 * for partial cases, fair will likely keep triggering this CPU.
	 *
	 * Once fair is fixed, restore WARN_ON_ONCE().
	 */
	if ((rq->scx.flags & SCX_RQ_BAL_KEEP) &&
	    prev->sched_class == &ext_sched_class) {
		p = prev;
		if (!p->scx.slice)
			p->scx.slice = SCX_SLICE_DFL;
	} else {
		p = first_local_task(rq);
		if (!p)
			return NULL;

		if (unlikely(!p->scx.slice)) {
			if (!scx_rq_bypassing(rq) && !scx_warned_zero_slice) {
				printk_deferred(KERN_WARNING "sched_ext: %s[%d] has zero slice in %s()\n",
						p->comm, p->pid, __func__);
				scx_warned_zero_slice = true;
			}
			p->scx.slice = SCX_SLICE_DFL;
		}
	}

	return p;
}

#ifdef CONFIG_SCHED_CORE
/**
 * scx_prio_less - Task ordering for core-sched
 * @a: task A
 * @b: task B
 *
 * Core-sched is implemented as an additional scheduling layer on top of the
 * usual sched_class'es and needs to find out the expected task ordering. For
 * SCX, core-sched calls this function to interrogate the task ordering.
 *
 * Unless overridden by ops.core_sched_before(), @p->scx.core_sched_at is used
 * to implement the default task ordering. The older the timestamp, the higher
 * prority the task - the global FIFO ordering matching the default scheduling
 * behavior.
 *
 * When ops.core_sched_before() is enabled, @p->scx.core_sched_at is used to
 * implement FIFO ordering within each local DSQ. See pick_task_scx().
 */
bool scx_prio_less(const struct task_struct *a, const struct task_struct *b,
		   bool in_fi)
{
	/*
	 * The const qualifiers are dropped from task_struct pointers when
	 * calling ops.core_sched_before(). Accesses are controlled by the
	 * verifier.
	 */
	if (SCX_HAS_OP(core_sched_before) && !scx_rq_bypassing(task_rq(a)))
		return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before,
					      (struct task_struct *)a,
					      (struct task_struct *)b);
	else
		return time_after64(a->scx.core_sched_at, b->scx.core_sched_at);
}
#endif	/* CONFIG_SCHED_CORE */

#ifdef CONFIG_SMP

static bool test_and_clear_cpu_idle(int cpu)
{
#ifdef CONFIG_SCHED_SMT
	/*
	 * SMT mask should be cleared whether we can claim @cpu or not. The SMT
	 * cluster is not wholly idle either way. This also prevents
	 * scx_pick_idle_cpu() from getting caught in an infinite loop.
	 */
	if (sched_smt_active()) {
		const struct cpumask *smt = cpu_smt_mask(cpu);

		/*
		 * If offline, @cpu is not its own sibling and
		 * scx_pick_idle_cpu() can get caught in an infinite loop as
		 * @cpu is never cleared from idle_masks.smt. Ensure that @cpu
		 * is eventually cleared.
		 */
		if (cpumask_intersects(smt, idle_masks.smt))
			cpumask_andnot(idle_masks.smt, idle_masks.smt, smt);
		else if (cpumask_test_cpu(cpu, idle_masks.smt))
			__cpumask_clear_cpu(cpu, idle_masks.smt);
	}
#endif
	return cpumask_test_and_clear_cpu(cpu, idle_masks.cpu);
}

static s32 scx_pick_idle_cpu(const struct cpumask *cpus_allowed, u64 flags)
{
	int cpu;

retry:
	if (sched_smt_active()) {
		cpu = cpumask_any_and_distribute(idle_masks.smt, cpus_allowed);
		if (cpu < nr_cpu_ids)
			goto found;

		if (flags & SCX_PICK_IDLE_CORE)
			return -EBUSY;
	}

	cpu = cpumask_any_and_distribute(idle_masks.cpu, cpus_allowed);
	if (cpu >= nr_cpu_ids)
		return -EBUSY;

found:
	if (test_and_clear_cpu_idle(cpu))
		return cpu;
	else
		goto retry;
}

static s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu,
			      u64 wake_flags, bool *found)
{
	s32 cpu;

	*found = false;

	/*
	 * If WAKE_SYNC, the waker's local DSQ is empty, and the system is
	 * under utilized, wake up @p to the local DSQ of the waker. Checking
	 * only for an empty local DSQ is insufficient as it could give the
	 * wakee an unfair advantage when the system is oversaturated.
	 * Checking only for the presence of idle CPUs is also insufficient as
	 * the local DSQ of the waker could have tasks piled up on it even if
	 * there is an idle core elsewhere on the system.
	 */
	cpu = smp_processor_id();
	if ((wake_flags & SCX_WAKE_SYNC) &&
	    !cpumask_empty(idle_masks.cpu) && !(current->flags & PF_EXITING) &&
	    cpu_rq(cpu)->scx.local_dsq.nr == 0) {
		if (cpumask_test_cpu(cpu, p->cpus_ptr))
			goto cpu_found;
	}

	/*
	 * If CPU has SMT, any wholly idle CPU is likely a better pick than
	 * partially idle @prev_cpu.
	 */
	if (sched_smt_active()) {
		if (cpumask_test_cpu(prev_cpu, idle_masks.smt) &&
		    test_and_clear_cpu_idle(prev_cpu)) {
			cpu = prev_cpu;
			goto cpu_found;
		}

		cpu = scx_pick_idle_cpu(p->cpus_ptr, SCX_PICK_IDLE_CORE);
		if (cpu >= 0)
			goto cpu_found;
	}

	if (test_and_clear_cpu_idle(prev_cpu)) {
		cpu = prev_cpu;
		goto cpu_found;
	}

	cpu = scx_pick_idle_cpu(p->cpus_ptr, 0);
	if (cpu >= 0)
		goto cpu_found;

	return prev_cpu;

cpu_found:
	*found = true;
	return cpu;
}

static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flags)
{
	/*
	 * sched_exec() calls with %WF_EXEC when @p is about to exec(2) as it
	 * can be a good migration opportunity with low cache and memory
	 * footprint. Returning a CPU different than @prev_cpu triggers
	 * immediate rq migration. However, for SCX, as the current rq
	 * association doesn't dictate where the task is going to run, this
	 * doesn't fit well. If necessary, we can later add a dedicated method
	 * which can decide to preempt self to force it through the regular
	 * scheduling path.
	 */
	if (unlikely(wake_flags & WF_EXEC))
		return prev_cpu;

	if (SCX_HAS_OP(select_cpu) && !scx_rq_bypassing(task_rq(p))) {
		s32 cpu;
		struct task_struct **ddsp_taskp;

		ddsp_taskp = this_cpu_ptr(&direct_dispatch_task);
		WARN_ON_ONCE(*ddsp_taskp);
		*ddsp_taskp = p;

		cpu = SCX_CALL_OP_TASK_RET(SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU,
					   select_cpu, p, prev_cpu, wake_flags);
		*ddsp_taskp = NULL;
		if (ops_cpu_valid(cpu, "from ops.select_cpu()"))
			return cpu;
		else
			return prev_cpu;
	} else {
		bool found;
		s32 cpu;

		cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, &found);
		if (found) {
			p->scx.slice = SCX_SLICE_DFL;
			p->scx.ddsp_dsq_id = SCX_DSQ_LOCAL;
		}
		return cpu;
	}
}

static void task_woken_scx(struct rq *rq, struct task_struct *p)
{
	run_deferred(rq);
}

static void set_cpus_allowed_scx(struct task_struct *p,
				 struct affinity_context *ac)
{
	set_cpus_allowed_common(p, ac);

	/*
	 * The effective cpumask is stored in @p->cpus_ptr which may temporarily
	 * differ from the configured one in @p->cpus_mask. Always tell the bpf
	 * scheduler the effective one.
	 *
	 * Fine-grained memory write control is enforced by BPF making the const
	 * designation pointless. Cast it away when calling the operation.
	 */
	if (SCX_HAS_OP(set_cpumask))
		SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p,
				 (struct cpumask *)p->cpus_ptr);
}

static void reset_idle_masks(void)
{
	/*
	 * Consider all online cpus idle. Should converge to the actual state
	 * quickly.
	 */
	cpumask_copy(idle_masks.cpu, cpu_online_mask);
	cpumask_copy(idle_masks.smt, cpu_online_mask);
}

void __scx_update_idle(struct rq *rq, bool idle)
{
	int cpu = cpu_of(rq);

	if (SCX_HAS_OP(update_idle) && !scx_rq_bypassing(rq)) {
		SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle);
		if (!static_branch_unlikely(&scx_builtin_idle_enabled))
			return;
	}

	if (idle)
		cpumask_set_cpu(cpu, idle_masks.cpu);
	else
		cpumask_clear_cpu(cpu, idle_masks.cpu);

#ifdef CONFIG_SCHED_SMT
	if (sched_smt_active()) {
		const struct cpumask *smt = cpu_smt_mask(cpu);

		if (idle) {
			/*
			 * idle_masks.smt handling is racy but that's fine as
			 * it's only for optimization and self-correcting.
			 */
			for_each_cpu(cpu, smt) {
				if (!cpumask_test_cpu(cpu, idle_masks.cpu))
					return;
			}
			cpumask_or(idle_masks.smt, idle_masks.smt, smt);
		} else {
			cpumask_andnot(idle_masks.smt, idle_masks.smt, smt);
		}
	}
#endif
}

static void handle_hotplug(struct rq *rq, bool online)
{
	int cpu = cpu_of(rq);

	atomic_long_inc(&scx_hotplug_seq);

	if (online && SCX_HAS_OP(cpu_online))
		SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, cpu);
	else if (!online && SCX_HAS_OP(cpu_offline))
		SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, cpu);
	else
		scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG,
			     "cpu %d going %s, exiting scheduler", cpu,
			     online ? "online" : "offline");
}

void scx_rq_activate(struct rq *rq)
{
	handle_hotplug(rq, true);
}

void scx_rq_deactivate(struct rq *rq)
{
	handle_hotplug(rq, false);
}

static void rq_online_scx(struct rq *rq)
{
	rq->scx.flags |= SCX_RQ_ONLINE;
}

static void rq_offline_scx(struct rq *rq)
{
	rq->scx.flags &= ~SCX_RQ_ONLINE;
}

#else	/* CONFIG_SMP */

static bool test_and_clear_cpu_idle(int cpu) { return false; }
static s32 scx_pick_idle_cpu(const struct cpumask *cpus_allowed, u64 flags) { return -EBUSY; }
static void reset_idle_masks(void) {}

#endif	/* CONFIG_SMP */

static bool check_rq_for_timeouts(struct rq *rq)
{
	struct task_struct *p;
	struct rq_flags rf;
	bool timed_out = false;

	rq_lock_irqsave(rq, &rf);
	list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node) {
		unsigned long last_runnable = p->scx.runnable_at;

		if (unlikely(time_after(jiffies,
					last_runnable + scx_watchdog_timeout))) {
			u32 dur_ms = jiffies_to_msecs(jiffies - last_runnable);

			scx_ops_error_kind(SCX_EXIT_ERROR_STALL,
					   "%s[%d] failed to run for %u.%03us",
					   p->comm, p->pid,
					   dur_ms / 1000, dur_ms % 1000);
			timed_out = true;
			break;
		}
	}
	rq_unlock_irqrestore(rq, &rf);

	return timed_out;
}

static void scx_watchdog_workfn(struct work_struct *work)
{
	int cpu;

	WRITE_ONCE(scx_watchdog_timestamp, jiffies);

	for_each_online_cpu(cpu) {
		if (unlikely(check_rq_for_timeouts(cpu_rq(cpu))))
			break;

		cond_resched();
	}
	queue_delayed_work(system_unbound_wq, to_delayed_work(work),
			   scx_watchdog_timeout / 2);
}

void scx_tick(struct rq *rq)
{
	unsigned long last_check;

	if (!scx_enabled())
		return;

	last_check = READ_ONCE(scx_watchdog_timestamp);
	if (unlikely(time_after(jiffies,
				last_check + READ_ONCE(scx_watchdog_timeout)))) {
		u32 dur_ms = jiffies_to_msecs(jiffies - last_check);

		scx_ops_error_kind(SCX_EXIT_ERROR_STALL,
				   "watchdog failed to check in for %u.%03us",
				   dur_ms / 1000, dur_ms % 1000);
	}

	update_other_load_avgs(rq);
}

static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued)
{
	update_curr_scx(rq);

	/*
	 * While disabling, always resched and refresh core-sched timestamp as
	 * we can't trust the slice management or ops.core_sched_before().
	 */
	if (scx_rq_bypassing(rq)) {
		curr->scx.slice = 0;
		touch_core_sched(rq, curr);
	} else if (SCX_HAS_OP(tick)) {
		SCX_CALL_OP(SCX_KF_REST, tick, curr);
	}

	if (!curr->scx.slice)
		resched_curr(rq);
}

#ifdef CONFIG_EXT_GROUP_SCHED
static struct cgroup *tg_cgrp(struct task_group *tg)
{
	/*
	 * If CGROUP_SCHED is disabled, @tg is NULL. If @tg is an autogroup,
	 * @tg->css.cgroup is NULL. In both cases, @tg can be treated as the
	 * root cgroup.
	 */
	if (tg && tg->css.cgroup)
		return tg->css.cgroup;
	else
		return &cgrp_dfl_root.cgrp;
}

#define SCX_INIT_TASK_ARGS_CGROUP(tg)		.cgroup = tg_cgrp(tg),

#else	/* CONFIG_EXT_GROUP_SCHED */

#define SCX_INIT_TASK_ARGS_CGROUP(tg)

#endif	/* CONFIG_EXT_GROUP_SCHED */

static enum scx_task_state scx_get_task_state(const struct task_struct *p)
{
	return (p->scx.flags & SCX_TASK_STATE_MASK) >> SCX_TASK_STATE_SHIFT;
}

static void scx_set_task_state(struct task_struct *p, enum scx_task_state state)
{
	enum scx_task_state prev_state = scx_get_task_state(p);
	bool warn = false;

	BUILD_BUG_ON(SCX_TASK_NR_STATES > (1 << SCX_TASK_STATE_BITS));

	switch (state) {
	case SCX_TASK_NONE:
		break;
	case SCX_TASK_INIT:
		warn = prev_state != SCX_TASK_NONE;
		break;
	case SCX_TASK_READY:
		warn = prev_state == SCX_TASK_NONE;
		break;
	case SCX_TASK_ENABLED:
		warn = prev_state != SCX_TASK_READY;
		break;
	default:
		warn = true;
		return;
	}

	WARN_ONCE(warn, "sched_ext: Invalid task state transition %d -> %d for %s[%d]",
		  prev_state, state, p->comm, p->pid);

	p->scx.flags &= ~SCX_TASK_STATE_MASK;
	p->scx.flags |= state << SCX_TASK_STATE_SHIFT;
}

static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool fork)
{
	int ret;

	p->scx.disallow = false;

	if (SCX_HAS_OP(init_task)) {
		struct scx_init_task_args args = {
			SCX_INIT_TASK_ARGS_CGROUP(tg)
			.fork = fork,
		};

		ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, p, &args);
		if (unlikely(ret)) {
			ret = ops_sanitize_err("init_task", ret);
			return ret;
		}
	}

	scx_set_task_state(p, SCX_TASK_INIT);

	if (p->scx.disallow) {
		if (!fork) {
			struct rq *rq;
			struct rq_flags rf;

			rq = task_rq_lock(p, &rf);

			/*
			 * We're in the load path and @p->policy will be applied
			 * right after. Reverting @p->policy here and rejecting
			 * %SCHED_EXT transitions from scx_check_setscheduler()
			 * guarantees that if ops.init_task() sets @p->disallow,
			 * @p can never be in SCX.
			 */
			if (p->policy == SCHED_EXT) {
				p->policy = SCHED_NORMAL;
				atomic_long_inc(&scx_nr_rejected);
			}

			task_rq_unlock(rq, p, &rf);
		} else if (p->policy == SCHED_EXT) {
			scx_ops_error("ops.init_task() set task->scx.disallow for %s[%d] during fork",
				      p->comm, p->pid);
		}
	}

	p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT;
	return 0;
}

static void scx_ops_enable_task(struct task_struct *p)
{
	u32 weight;

	lockdep_assert_rq_held(task_rq(p));

	/*
	 * Set the weight before calling ops.enable() so that the scheduler
	 * doesn't see a stale value if they inspect the task struct.
	 */
	if (task_has_idle_policy(p))
		weight = WEIGHT_IDLEPRIO;
	else
		weight = sched_prio_to_weight[p->static_prio - MAX_RT_PRIO];

	p->scx.weight = sched_weight_to_cgroup(weight);

	if (SCX_HAS_OP(enable))
		SCX_CALL_OP_TASK(SCX_KF_REST, enable, p);
	scx_set_task_state(p, SCX_TASK_ENABLED);

	if (SCX_HAS_OP(set_weight))
		SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight);
}

static void scx_ops_disable_task(struct task_struct *p)
{
	lockdep_assert_rq_held(task_rq(p));
	WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED);

	if (SCX_HAS_OP(disable))
		SCX_CALL_OP(SCX_KF_REST, disable, p);
	scx_set_task_state(p, SCX_TASK_READY);
}

static void scx_ops_exit_task(struct task_struct *p)
{
	struct scx_exit_task_args args = {
		.cancelled = false,
	};

	lockdep_assert_rq_held(task_rq(p));

	switch (scx_get_task_state(p)) {
	case SCX_TASK_NONE:
		return;
	case SCX_TASK_INIT:
		args.cancelled = true;
		break;
	case SCX_TASK_READY:
		break;
	case SCX_TASK_ENABLED:
		scx_ops_disable_task(p);
		break;
	default:
		WARN_ON_ONCE(true);
		return;
	}

	if (SCX_HAS_OP(exit_task))
		SCX_CALL_OP(SCX_KF_REST, exit_task, p, &args);
	scx_set_task_state(p, SCX_TASK_NONE);
}

void init_scx_entity(struct sched_ext_entity *scx)
{
	/*
	 * init_idle() calls this function again after fork sequence is
	 * complete. Don't touch ->tasks_node as it's already linked.
	 */
	memset(scx, 0, offsetof(struct sched_ext_entity, tasks_node));

	INIT_LIST_HEAD(&scx->dsq_list.node);
	RB_CLEAR_NODE(&scx->dsq_priq);
	scx->sticky_cpu = -1;
	scx->holding_cpu = -1;
	INIT_LIST_HEAD(&scx->runnable_node);
	scx->runnable_at = jiffies;
	scx->ddsp_dsq_id = SCX_DSQ_INVALID;
	scx->slice = SCX_SLICE_DFL;
}

void scx_pre_fork(struct task_struct *p)
{
	/*
	 * BPF scheduler enable/disable paths want to be able to iterate and
	 * update all tasks which can become complex when racing forks. As
	 * enable/disable are very cold paths, let's use a percpu_rwsem to
	 * exclude forks.
	 */
	percpu_down_read(&scx_fork_rwsem);
}

int scx_fork(struct task_struct *p)
{
	percpu_rwsem_assert_held(&scx_fork_rwsem);

	if (scx_ops_init_task_enabled)
		return scx_ops_init_task(p, task_group(p), true);
	else
		return 0;
}

void scx_post_fork(struct task_struct *p)
{
	if (scx_ops_init_task_enabled) {
		scx_set_task_state(p, SCX_TASK_READY);

		/*
		 * Enable the task immediately if it's running on sched_ext.
		 * Otherwise, it'll be enabled in switching_to_scx() if and
		 * when it's ever configured to run with a SCHED_EXT policy.
		 */
		if (p->sched_class == &ext_sched_class) {
			struct rq_flags rf;
			struct rq *rq;

			rq = task_rq_lock(p, &rf);
			scx_ops_enable_task(p);
			task_rq_unlock(rq, p, &rf);
		}
	}

	spin_lock_irq(&scx_tasks_lock);
	list_add_tail(&p->scx.tasks_node, &scx_tasks);
	spin_unlock_irq(&scx_tasks_lock);

	percpu_up_read(&scx_fork_rwsem);
}

void scx_cancel_fork(struct task_struct *p)
{
	if (scx_enabled()) {
		struct rq *rq;
		struct rq_flags rf;

		rq = task_rq_lock(p, &rf);
		WARN_ON_ONCE(scx_get_task_state(p) >= SCX_TASK_READY);
		scx_ops_exit_task(p);
		task_rq_unlock(rq, p, &rf);
	}

	percpu_up_read(&scx_fork_rwsem);
}

void sched_ext_free(struct task_struct *p)
{
	unsigned long flags;

	spin_lock_irqsave(&scx_tasks_lock, flags);
	list_del_init(&p->scx.tasks_node);
	spin_unlock_irqrestore(&scx_tasks_lock, flags);

	/*
	 * @p is off scx_tasks and wholly ours. scx_ops_enable()'s READY ->
	 * ENABLED transitions can't race us. Disable ops for @p.
	 */
	if (scx_get_task_state(p) != SCX_TASK_NONE) {
		struct rq_flags rf;
		struct rq *rq;

		rq = task_rq_lock(p, &rf);
		scx_ops_exit_task(p);
		task_rq_unlock(rq, p, &rf);
	}
}

static void reweight_task_scx(struct rq *rq, struct task_struct *p,
			      const struct load_weight *lw)
{
	lockdep_assert_rq_held(task_rq(p));

	p->scx.weight = sched_weight_to_cgroup(scale_load_down(lw->weight));
	if (SCX_HAS_OP(set_weight))
		SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight);
}

static void prio_changed_scx(struct rq *rq, struct task_struct *p, int oldprio)
{
}

static void switching_to_scx(struct rq *rq, struct task_struct *p)
{
	scx_ops_enable_task(p);

	/*
	 * set_cpus_allowed_scx() is not called while @p is associated with a
	 * different scheduler class. Keep the BPF scheduler up-to-date.
	 */
	if (SCX_HAS_OP(set_cpumask))
		SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p,
				 (struct cpumask *)p->cpus_ptr);
}

static void switched_from_scx(struct rq *rq, struct task_struct *p)
{
	scx_ops_disable_task(p);
}

static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p,int wake_flags) {}
static void switched_to_scx(struct rq *rq, struct task_struct *p) {}

int scx_check_setscheduler(struct task_struct *p, int policy)
{
	lockdep_assert_rq_held(task_rq(p));

	/* if disallow, reject transitioning into SCX */
	if (scx_enabled() && READ_ONCE(p->scx.disallow) &&
	    p->policy != policy && policy == SCHED_EXT)
		return -EACCES;

	return 0;
}

#ifdef CONFIG_NO_HZ_FULL
bool scx_can_stop_tick(struct rq *rq)
{
	struct task_struct *p = rq->curr;

	if (scx_rq_bypassing(rq))
		return false;

	if (p->sched_class != &ext_sched_class)
		return true;

	/*
	 * @rq can dispatch from different DSQs, so we can't tell whether it
	 * needs the tick or not by looking at nr_running. Allow stopping ticks
	 * iff the BPF scheduler indicated so. See set_next_task_scx().
	 */
	return rq->scx.flags & SCX_RQ_CAN_STOP_TICK;
}
#endif

#ifdef CONFIG_EXT_GROUP_SCHED

DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
static bool scx_cgroup_enabled;
static bool cgroup_warned_missing_weight;
static bool cgroup_warned_missing_idle;

static void scx_cgroup_warn_missing_weight(struct task_group *tg)
{
	if (scx_ops_enable_state() == SCX_OPS_DISABLED ||
	    cgroup_warned_missing_weight)
		return;

	if ((scx_ops.flags & SCX_OPS_HAS_CGROUP_WEIGHT) || !tg->css.parent)
		return;

	pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.weight\n",
		scx_ops.name);
	cgroup_warned_missing_weight = true;
}

static void scx_cgroup_warn_missing_idle(struct task_group *tg)
{
	if (!scx_cgroup_enabled || cgroup_warned_missing_idle)
		return;

	if (!tg->idle)
		return;

	pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.idle\n",
		scx_ops.name);
	cgroup_warned_missing_idle = true;
}

int scx_tg_online(struct task_group *tg)
{
	int ret = 0;

	WARN_ON_ONCE(tg->scx_flags & (SCX_TG_ONLINE | SCX_TG_INITED));

	percpu_down_read(&scx_cgroup_rwsem);

	scx_cgroup_warn_missing_weight(tg);

	if (scx_cgroup_enabled) {
		if (SCX_HAS_OP(cgroup_init)) {
			struct scx_cgroup_init_args args =
				{ .weight = tg->scx_weight };

			ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init,
					      tg->css.cgroup, &args);
			if (ret)
				ret = ops_sanitize_err("cgroup_init", ret);
		}
		if (ret == 0)
			tg->scx_flags |= SCX_TG_ONLINE | SCX_TG_INITED;
	} else {
		tg->scx_flags |= SCX_TG_ONLINE;
	}

	percpu_up_read(&scx_cgroup_rwsem);
	return ret;
}

void scx_tg_offline(struct task_group *tg)
{
	WARN_ON_ONCE(!(tg->scx_flags & SCX_TG_ONLINE));

	percpu_down_read(&scx_cgroup_rwsem);

	if (SCX_HAS_OP(cgroup_exit) && (tg->scx_flags & SCX_TG_INITED))
		SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, tg->css.cgroup);
	tg->scx_flags &= ~(SCX_TG_ONLINE | SCX_TG_INITED);

	percpu_up_read(&scx_cgroup_rwsem);
}

int scx_cgroup_can_attach(struct cgroup_taskset *tset)
{
	struct cgroup_subsys_state *css;
	struct task_struct *p;
	int ret;

	/* released in scx_finish/cancel_attach() */
	percpu_down_read(&scx_cgroup_rwsem);

	if (!scx_cgroup_enabled)
		return 0;

	cgroup_taskset_for_each(p, css, tset) {
		struct cgroup *from = tg_cgrp(task_group(p));
		struct cgroup *to = tg_cgrp(css_tg(css));

		WARN_ON_ONCE(p->scx.cgrp_moving_from);

		/*
		 * sched_move_task() omits identity migrations. Let's match the
		 * behavior so that ops.cgroup_prep_move() and ops.cgroup_move()
		 * always match one-to-one.
		 */
		if (from == to)
			continue;

		if (SCX_HAS_OP(cgroup_prep_move)) {
			ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move,
					      p, from, css->cgroup);
			if (ret)
				goto err;
		}

		p->scx.cgrp_moving_from = from;
	}

	return 0;

err:
	cgroup_taskset_for_each(p, css, tset) {
		if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from)
			SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p,
				    p->scx.cgrp_moving_from, css->cgroup);
		p->scx.cgrp_moving_from = NULL;
	}

	percpu_up_read(&scx_cgroup_rwsem);
	return ops_sanitize_err("cgroup_prep_move", ret);
}

void scx_move_task(struct task_struct *p)
{
	if (!scx_cgroup_enabled)
		return;

	/*
	 * We're called from sched_move_task() which handles both cgroup and
	 * autogroup moves. Ignore the latter.
	 *
	 * Also ignore exiting tasks, because in the exit path tasks transition
	 * from the autogroup to the root group, so task_group_is_autogroup()
	 * alone isn't able to catch exiting autogroup tasks. This is safe for
	 * cgroup_move(), because cgroup migrations never happen for PF_EXITING
	 * tasks.
	 */
	if (task_group_is_autogroup(task_group(p)) || (p->flags & PF_EXITING))
		return;

	/*
	 * @p must have ops.cgroup_prep_move() called on it and thus
	 * cgrp_moving_from set.
	 */
	if (SCX_HAS_OP(cgroup_move) && !WARN_ON_ONCE(!p->scx.cgrp_moving_from))
		SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, p,
			p->scx.cgrp_moving_from, tg_cgrp(task_group(p)));
	p->scx.cgrp_moving_from = NULL;
}

void scx_cgroup_finish_attach(void)
{
	percpu_up_read(&scx_cgroup_rwsem);
}

void scx_cgroup_cancel_attach(struct cgroup_taskset *tset)
{
	struct cgroup_subsys_state *css;
	struct task_struct *p;

	if (!scx_cgroup_enabled)
		goto out_unlock;

	cgroup_taskset_for_each(p, css, tset) {
		if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from)
			SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p,
				    p->scx.cgrp_moving_from, css->cgroup);
		p->scx.cgrp_moving_from = NULL;
	}
out_unlock:
	percpu_up_read(&scx_cgroup_rwsem);
}

void scx_group_set_weight(struct task_group *tg, unsigned long weight)
{
	percpu_down_read(&scx_cgroup_rwsem);

	if (scx_cgroup_enabled && tg->scx_weight != weight) {
		if (SCX_HAS_OP(cgroup_set_weight))
			SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight,
				    tg_cgrp(tg), weight);
		tg->scx_weight = weight;
	}

	percpu_up_read(&scx_cgroup_rwsem);
}

void scx_group_set_idle(struct task_group *tg, bool idle)
{
	percpu_down_read(&scx_cgroup_rwsem);
	scx_cgroup_warn_missing_idle(tg);
	percpu_up_read(&scx_cgroup_rwsem);
}

static void scx_cgroup_lock(void)
{
	percpu_down_write(&scx_cgroup_rwsem);
}

static void scx_cgroup_unlock(void)
{
	percpu_up_write(&scx_cgroup_rwsem);
}

#else	/* CONFIG_EXT_GROUP_SCHED */

static inline void scx_cgroup_lock(void) {}
static inline void scx_cgroup_unlock(void) {}

#endif	/* CONFIG_EXT_GROUP_SCHED */

/*
 * Omitted operations:
 *
 * - wakeup_preempt: NOOP as it isn't useful in the wakeup path because the task
 *   isn't tied to the CPU at that point. Preemption is implemented by resetting
 *   the victim task's slice to 0 and triggering reschedule on the target CPU.
 *
 * - migrate_task_rq: Unnecessary as task to cpu mapping is transient.
 *
 * - task_fork/dead: We need fork/dead notifications for all tasks regardless of
 *   their current sched_class. Call them directly from sched core instead.
 */
DEFINE_SCHED_CLASS(ext) = {
	.enqueue_task		= enqueue_task_scx,
	.dequeue_task		= dequeue_task_scx,
	.yield_task		= yield_task_scx,
	.yield_to_task		= yield_to_task_scx,

	.wakeup_preempt		= wakeup_preempt_scx,

	.balance		= balance_scx,
	.pick_task		= pick_task_scx,

	.put_prev_task		= put_prev_task_scx,
	.set_next_task		= set_next_task_scx,

#ifdef CONFIG_SMP
	.select_task_rq		= select_task_rq_scx,
	.task_woken		= task_woken_scx,
	.set_cpus_allowed	= set_cpus_allowed_scx,

	.rq_online		= rq_online_scx,
	.rq_offline		= rq_offline_scx,
#endif

	.task_tick		= task_tick_scx,

	.switching_to		= switching_to_scx,
	.switched_from		= switched_from_scx,
	.switched_to		= switched_to_scx,
	.reweight_task		= reweight_task_scx,
	.prio_changed		= prio_changed_scx,

	.update_curr		= update_curr_scx,

#ifdef CONFIG_UCLAMP_TASK
	.uclamp_enabled		= 1,
#endif
};

static void init_dsq(struct scx_dispatch_q *dsq, u64 dsq_id)
{
	memset(dsq, 0, sizeof(*dsq));

	raw_spin_lock_init(&dsq->lock);
	INIT_LIST_HEAD(&dsq->list);
	dsq->id = dsq_id;
}

static struct scx_dispatch_q *create_dsq(u64 dsq_id, int node)
{
	struct scx_dispatch_q *dsq;
	int ret;

	if (dsq_id & SCX_DSQ_FLAG_BUILTIN)
		return ERR_PTR(-EINVAL);

	dsq = kmalloc_node(sizeof(*dsq), GFP_KERNEL, node);
	if (!dsq)
		return ERR_PTR(-ENOMEM);

	init_dsq(dsq, dsq_id);

	ret = rhashtable_insert_fast(&dsq_hash, &dsq->hash_node,
				     dsq_hash_params);
	if (ret) {
		kfree(dsq);
		return ERR_PTR(ret);
	}
	return dsq;
}

static void free_dsq_irq_workfn(struct irq_work *irq_work)
{
	struct llist_node *to_free = llist_del_all(&dsqs_to_free);
	struct scx_dispatch_q *dsq, *tmp_dsq;

	llist_for_each_entry_safe(dsq, tmp_dsq, to_free, free_node)
		kfree_rcu(dsq, rcu);
}

static DEFINE_IRQ_WORK(free_dsq_irq_work, free_dsq_irq_workfn);

static void destroy_dsq(u64 dsq_id)
{
	struct scx_dispatch_q *dsq;
	unsigned long flags;

	rcu_read_lock();

	dsq = find_user_dsq(dsq_id);
	if (!dsq)
		goto out_unlock_rcu;

	raw_spin_lock_irqsave(&dsq->lock, flags);

	if (dsq->nr) {
		scx_ops_error("attempting to destroy in-use dsq 0x%016llx (nr=%u)",
			      dsq->id, dsq->nr);
		goto out_unlock_dsq;
	}

	if (rhashtable_remove_fast(&dsq_hash, &dsq->hash_node, dsq_hash_params))
		goto out_unlock_dsq;

	/*
	 * Mark dead by invalidating ->id to prevent dispatch_enqueue() from
	 * queueing more tasks. As this function can be called from anywhere,
	 * freeing is bounced through an irq work to avoid nesting RCU
	 * operations inside scheduler locks.
	 */
	dsq->id = SCX_DSQ_INVALID;
	llist_add(&dsq->free_node, &dsqs_to_free);
	irq_work_queue(&free_dsq_irq_work);

out_unlock_dsq:
	raw_spin_unlock_irqrestore(&dsq->lock, flags);
out_unlock_rcu:
	rcu_read_unlock();
}

#ifdef CONFIG_EXT_GROUP_SCHED
static void scx_cgroup_exit(void)
{
	struct cgroup_subsys_state *css;

	percpu_rwsem_assert_held(&scx_cgroup_rwsem);

	scx_cgroup_enabled = false;

	/*
	 * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk
	 * cgroups and exit all the inited ones, all online cgroups are exited.
	 */
	rcu_read_lock();
	css_for_each_descendant_post(css, &root_task_group.css) {
		struct task_group *tg = css_tg(css);

		if (!(tg->scx_flags & SCX_TG_INITED))
			continue;
		tg->scx_flags &= ~SCX_TG_INITED;

		if (!scx_ops.cgroup_exit)
			continue;

		if (WARN_ON_ONCE(!css_tryget(css)))
			continue;
		rcu_read_unlock();

		SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, css->cgroup);

		rcu_read_lock();
		css_put(css);
	}
	rcu_read_unlock();
}

static int scx_cgroup_init(void)
{
	struct cgroup_subsys_state *css;
	int ret;

	percpu_rwsem_assert_held(&scx_cgroup_rwsem);

	cgroup_warned_missing_weight = false;
	cgroup_warned_missing_idle = false;

	/*
	 * scx_tg_on/offline() are excluded thorugh scx_cgroup_rwsem. If we walk
	 * cgroups and init, all online cgroups are initialized.
	 */
	rcu_read_lock();
	css_for_each_descendant_pre(css, &root_task_group.css) {
		struct task_group *tg = css_tg(css);
		struct scx_cgroup_init_args args = { .weight = tg->scx_weight };

		scx_cgroup_warn_missing_weight(tg);
		scx_cgroup_warn_missing_idle(tg);

		if ((tg->scx_flags &
		     (SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE)
			continue;

		if (!scx_ops.cgroup_init) {
			tg->scx_flags |= SCX_TG_INITED;
			continue;
		}

		if (WARN_ON_ONCE(!css_tryget(css)))
			continue;
		rcu_read_unlock();

		ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init,
				      css->cgroup, &args);
		if (ret) {
			css_put(css);
			scx_ops_error("ops.cgroup_init() failed (%d)", ret);
			return ret;
		}
		tg->scx_flags |= SCX_TG_INITED;

		rcu_read_lock();
		css_put(css);
	}
	rcu_read_unlock();

	WARN_ON_ONCE(scx_cgroup_enabled);
	scx_cgroup_enabled = true;

	return 0;
}

#else
static void scx_cgroup_exit(void) {}
static int scx_cgroup_init(void) { return 0; }
#endif


/********************************************************************************
 * Sysfs interface and ops enable/disable.
 */

#define SCX_ATTR(_name)								\
	static struct kobj_attribute scx_attr_##_name = {			\
		.attr = { .name = __stringify(_name), .mode = 0444 },		\
		.show = scx_attr_##_name##_show,				\
	}

static ssize_t scx_attr_state_show(struct kobject *kobj,
				   struct kobj_attribute *ka, char *buf)
{
	return sysfs_emit(buf, "%s\n",
			  scx_ops_enable_state_str[scx_ops_enable_state()]);
}
SCX_ATTR(state);

static ssize_t scx_attr_switch_all_show(struct kobject *kobj,
					struct kobj_attribute *ka, char *buf)
{
	return sysfs_emit(buf, "%d\n", READ_ONCE(scx_switching_all));
}
SCX_ATTR(switch_all);

static ssize_t scx_attr_nr_rejected_show(struct kobject *kobj,
					 struct kobj_attribute *ka, char *buf)
{
	return sysfs_emit(buf, "%ld\n", atomic_long_read(&scx_nr_rejected));
}
SCX_ATTR(nr_rejected);

static ssize_t scx_attr_hotplug_seq_show(struct kobject *kobj,
					 struct kobj_attribute *ka, char *buf)
{
	return sysfs_emit(buf, "%ld\n", atomic_long_read(&scx_hotplug_seq));
}
SCX_ATTR(hotplug_seq);

static ssize_t scx_attr_enable_seq_show(struct kobject *kobj,
					struct kobj_attribute *ka, char *buf)
{
	return sysfs_emit(buf, "%ld\n", atomic_long_read(&scx_enable_seq));
}
SCX_ATTR(enable_seq);

static struct attribute *scx_global_attrs[] = {
	&scx_attr_state.attr,
	&scx_attr_switch_all.attr,
	&scx_attr_nr_rejected.attr,
	&scx_attr_hotplug_seq.attr,
	&scx_attr_enable_seq.attr,
	NULL,
};

static const struct attribute_group scx_global_attr_group = {
	.attrs = scx_global_attrs,
};

static void scx_kobj_release(struct kobject *kobj)
{
	kfree(kobj);
}

static ssize_t scx_attr_ops_show(struct kobject *kobj,
				 struct kobj_attribute *ka, char *buf)
{
	return sysfs_emit(buf, "%s\n", scx_ops.name);
}
SCX_ATTR(ops);

static struct attribute *scx_sched_attrs[] = {
	&scx_attr_ops.attr,
	NULL,
};
ATTRIBUTE_GROUPS(scx_sched);

static const struct kobj_type scx_ktype = {
	.release = scx_kobj_release,
	.sysfs_ops = &kobj_sysfs_ops,
	.default_groups = scx_sched_groups,
};

static int scx_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
{
	return add_uevent_var(env, "SCXOPS=%s", scx_ops.name);
}

static const struct kset_uevent_ops scx_uevent_ops = {
	.uevent = scx_uevent,
};

/*
 * Used by sched_fork() and __setscheduler_prio() to pick the matching
 * sched_class. dl/rt are already handled.
 */
bool task_should_scx(struct task_struct *p)
{
	if (!scx_enabled() ||
	    unlikely(scx_ops_enable_state() == SCX_OPS_DISABLING))
		return false;
	if (READ_ONCE(scx_switching_all))
		return true;
	return p->policy == SCHED_EXT;
}

/**
 * scx_ops_bypass - [Un]bypass scx_ops and guarantee forward progress
 *
 * Bypassing guarantees that all runnable tasks make forward progress without
 * trusting the BPF scheduler. We can't grab any mutexes or rwsems as they might
 * be held by tasks that the BPF scheduler is forgetting to run, which
 * unfortunately also excludes toggling the static branches.
 *
 * Let's work around by overriding a couple ops and modifying behaviors based on
 * the DISABLING state and then cycling the queued tasks through dequeue/enqueue
 * to force global FIFO scheduling.
 *
 * - ops.select_cpu() is ignored and the default select_cpu() is used.
 *
 * - ops.enqueue() is ignored and tasks are queued in simple global FIFO order.
 *   %SCX_OPS_ENQ_LAST is also ignored.
 *
 * - ops.dispatch() is ignored.
 *
 * - balance_scx() does not set %SCX_RQ_BAL_KEEP on non-zero slice as slice
 *   can't be trusted. Whenever a tick triggers, the running task is rotated to
 *   the tail of the queue with core_sched_at touched.
 *
 * - pick_next_task() suppresses zero slice warning.
 *
 * - scx_bpf_kick_cpu() is disabled to avoid irq_work malfunction during PM
 *   operations.
 *
 * - scx_prio_less() reverts to the default core_sched_at order.
 */
static void scx_ops_bypass(bool bypass)
{
	int depth, cpu;

	if (bypass) {
		depth = atomic_inc_return(&scx_ops_bypass_depth);
		WARN_ON_ONCE(depth <= 0);
		if (depth != 1)
			return;
	} else {
		depth = atomic_dec_return(&scx_ops_bypass_depth);
		WARN_ON_ONCE(depth < 0);
		if (depth != 0)
			return;
	}

	/*
	 * No task property is changing. We just need to make sure all currently
	 * queued tasks are re-queued according to the new scx_rq_bypassing()
	 * state. As an optimization, walk each rq's runnable_list instead of
	 * the scx_tasks list.
	 *
	 * This function can't trust the scheduler and thus can't use
	 * cpus_read_lock(). Walk all possible CPUs instead of online.
	 */
	for_each_possible_cpu(cpu) {
		struct rq *rq = cpu_rq(cpu);
		struct rq_flags rf;
		struct task_struct *p, *n;

		rq_lock_irqsave(rq, &rf);

		if (bypass) {
			WARN_ON_ONCE(rq->scx.flags & SCX_RQ_BYPASSING);
			rq->scx.flags |= SCX_RQ_BYPASSING;
		} else {
			WARN_ON_ONCE(!(rq->scx.flags & SCX_RQ_BYPASSING));
			rq->scx.flags &= ~SCX_RQ_BYPASSING;
		}

		/*
		 * We need to guarantee that no tasks are on the BPF scheduler
		 * while bypassing. Either we see enabled or the enable path
		 * sees scx_rq_bypassing() before moving tasks to SCX.
		 */
		if (!scx_enabled()) {
			rq_unlock_irqrestore(rq, &rf);
			continue;
		}

		/*
		 * The use of list_for_each_entry_safe_reverse() is required
		 * because each task is going to be removed from and added back
		 * to the runnable_list during iteration. Because they're added
		 * to the tail of the list, safe reverse iteration can still
		 * visit all nodes.
		 */
		list_for_each_entry_safe_reverse(p, n, &rq->scx.runnable_list,
						 scx.runnable_node) {
			struct sched_enq_and_set_ctx ctx;

			/* cycling deq/enq is enough, see the function comment */
			sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);
			sched_enq_and_set_task(&ctx);
		}

		rq_unlock_irqrestore(rq, &rf);

		/* resched to restore ticks and idle state */
		resched_cpu(cpu);
	}
}

static void free_exit_info(struct scx_exit_info *ei)
{
	kfree(ei->dump);
	kfree(ei->msg);
	kfree(ei->bt);
	kfree(ei);
}

static struct scx_exit_info *alloc_exit_info(size_t exit_dump_len)
{
	struct scx_exit_info *ei;

	ei = kzalloc(sizeof(*ei), GFP_KERNEL);
	if (!ei)
		return NULL;

	ei->bt = kcalloc(SCX_EXIT_BT_LEN, sizeof(ei->bt[0]), GFP_KERNEL);
	ei->msg = kzalloc(SCX_EXIT_MSG_LEN, GFP_KERNEL);
	ei->dump = kzalloc(exit_dump_len, GFP_KERNEL);

	if (!ei->bt || !ei->msg || !ei->dump) {
		free_exit_info(ei);
		return NULL;
	}

	return ei;
}

static const char *scx_exit_reason(enum scx_exit_kind kind)
{
	switch (kind) {
	case SCX_EXIT_UNREG:
		return "unregistered from user space";
	case SCX_EXIT_UNREG_BPF:
		return "unregistered from BPF";
	case SCX_EXIT_UNREG_KERN:
		return "unregistered from the main kernel";
	case SCX_EXIT_SYSRQ:
		return "disabled by sysrq-S";
	case SCX_EXIT_ERROR:
		return "runtime error";
	case SCX_EXIT_ERROR_BPF:
		return "scx_bpf_error";
	case SCX_EXIT_ERROR_STALL:
		return "runnable task stall";
	default:
		return "<UNKNOWN>";
	}
}

static void scx_ops_disable_workfn(struct kthread_work *work)
{
	struct scx_exit_info *ei = scx_exit_info;
	struct scx_task_iter sti;
	struct task_struct *p;
	struct rhashtable_iter rht_iter;
	struct scx_dispatch_q *dsq;
	int i, kind;

	kind = atomic_read(&scx_exit_kind);
	while (true) {
		/*
		 * NONE indicates that a new scx_ops has been registered since
		 * disable was scheduled - don't kill the new ops. DONE
		 * indicates that the ops has already been disabled.
		 */
		if (kind == SCX_EXIT_NONE || kind == SCX_EXIT_DONE)
			return;
		if (atomic_try_cmpxchg(&scx_exit_kind, &kind, SCX_EXIT_DONE))
			break;
	}
	ei->kind = kind;
	ei->reason = scx_exit_reason(ei->kind);

	/* guarantee forward progress by bypassing scx_ops */
	scx_ops_bypass(true);

	switch (scx_ops_set_enable_state(SCX_OPS_DISABLING)) {
	case SCX_OPS_DISABLING:
		WARN_ONCE(true, "sched_ext: duplicate disabling instance?");
		break;
	case SCX_OPS_DISABLED:
		pr_warn("sched_ext: ops error detected without ops (%s)\n",
			scx_exit_info->msg);
		WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_DISABLED) !=
			     SCX_OPS_DISABLING);
		goto done;
	default:
		break;
	}

	/*
	 * Here, every runnable task is guaranteed to make forward progress and
	 * we can safely use blocking synchronization constructs. Actually
	 * disable ops.
	 */
	mutex_lock(&scx_ops_enable_mutex);

	static_branch_disable(&__scx_switched_all);
	WRITE_ONCE(scx_switching_all, false);

	/*
	 * Shut down cgroup support before tasks so that the cgroup attach path
	 * doesn't race against scx_ops_exit_task().
	 */
	scx_cgroup_lock();
	scx_cgroup_exit();
	scx_cgroup_unlock();

	/*
	 * The BPF scheduler is going away. All tasks including %TASK_DEAD ones
	 * must be switched out and exited synchronously.
	 */
	percpu_down_write(&scx_fork_rwsem);

	scx_ops_init_task_enabled = false;

	scx_task_iter_start(&sti);
	while ((p = scx_task_iter_next_locked(&sti))) {
		const struct sched_class *old_class = p->sched_class;
		struct sched_enq_and_set_ctx ctx;

		sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);

		p->sched_class = __setscheduler_class(p, p->prio);
		check_class_changing(task_rq(p), p, old_class);

		sched_enq_and_set_task(&ctx);

		check_class_changed(task_rq(p), p, old_class, p->prio);
		scx_ops_exit_task(p);
	}
	scx_task_iter_stop(&sti);
	percpu_up_write(&scx_fork_rwsem);

	/* no task is on scx, turn off all the switches and flush in-progress calls */
	static_branch_disable(&__scx_ops_enabled);
	for (i = SCX_OPI_BEGIN; i < SCX_OPI_END; i++)
		static_branch_disable(&scx_has_op[i]);
	static_branch_disable(&scx_ops_enq_last);
	static_branch_disable(&scx_ops_enq_exiting);
	static_branch_disable(&scx_ops_cpu_preempt);
	static_branch_disable(&scx_builtin_idle_enabled);
	synchronize_rcu();

	if (ei->kind >= SCX_EXIT_ERROR) {
		pr_err("sched_ext: BPF scheduler \"%s\" disabled (%s)\n",
		       scx_ops.name, ei->reason);

		if (ei->msg[0] != '\0')
			pr_err("sched_ext: %s: %s\n", scx_ops.name, ei->msg);
#ifdef CONFIG_STACKTRACE
		stack_trace_print(ei->bt, ei->bt_len, 2);
#endif
	} else {
		pr_info("sched_ext: BPF scheduler \"%s\" disabled (%s)\n",
			scx_ops.name, ei->reason);
	}

	if (scx_ops.exit)
		SCX_CALL_OP(SCX_KF_UNLOCKED, exit, ei);

	cancel_delayed_work_sync(&scx_watchdog_work);

	/*
	 * Delete the kobject from the hierarchy eagerly in addition to just
	 * dropping a reference. Otherwise, if the object is deleted
	 * asynchronously, sysfs could observe an object of the same name still
	 * in the hierarchy when another scheduler is loaded.
	 */
	kobject_del(scx_root_kobj);
	kobject_put(scx_root_kobj);
	scx_root_kobj = NULL;

	memset(&scx_ops, 0, sizeof(scx_ops));

	rhashtable_walk_enter(&dsq_hash, &rht_iter);
	do {
		rhashtable_walk_start(&rht_iter);

		while ((dsq = rhashtable_walk_next(&rht_iter)) && !IS_ERR(dsq))
			destroy_dsq(dsq->id);

		rhashtable_walk_stop(&rht_iter);
	} while (dsq == ERR_PTR(-EAGAIN));
	rhashtable_walk_exit(&rht_iter);

	free_percpu(scx_dsp_ctx);
	scx_dsp_ctx = NULL;
	scx_dsp_max_batch = 0;

	free_exit_info(scx_exit_info);
	scx_exit_info = NULL;

	mutex_unlock(&scx_ops_enable_mutex);

	WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_DISABLED) !=
		     SCX_OPS_DISABLING);
done:
	scx_ops_bypass(false);
}

static DEFINE_KTHREAD_WORK(scx_ops_disable_work, scx_ops_disable_workfn);

static void schedule_scx_ops_disable_work(void)
{
	struct kthread_worker *helper = READ_ONCE(scx_ops_helper);

	/*
	 * We may be called spuriously before the first bpf_sched_ext_reg(). If
	 * scx_ops_helper isn't set up yet, there's nothing to do.
	 */
	if (helper)
		kthread_queue_work(helper, &scx_ops_disable_work);
}

static void scx_ops_disable(enum scx_exit_kind kind)
{
	int none = SCX_EXIT_NONE;

	if (WARN_ON_ONCE(kind == SCX_EXIT_NONE || kind == SCX_EXIT_DONE))
		kind = SCX_EXIT_ERROR;

	atomic_try_cmpxchg(&scx_exit_kind, &none, kind);

	schedule_scx_ops_disable_work();
}

static void dump_newline(struct seq_buf *s)
{
	trace_sched_ext_dump("");

	/* @s may be zero sized and seq_buf triggers WARN if so */
	if (s->size)
		seq_buf_putc(s, '\n');
}

static __printf(2, 3) void dump_line(struct seq_buf *s, const char *fmt, ...)
{
	va_list args;

#ifdef CONFIG_TRACEPOINTS
	if (trace_sched_ext_dump_enabled()) {
		/* protected by scx_dump_state()::dump_lock */
		static char line_buf[SCX_EXIT_MSG_LEN];

		va_start(args, fmt);
		vscnprintf(line_buf, sizeof(line_buf), fmt, args);
		va_end(args);

		trace_sched_ext_dump(line_buf);
	}
#endif
	/* @s may be zero sized and seq_buf triggers WARN if so */
	if (s->size) {
		va_start(args, fmt);
		seq_buf_vprintf(s, fmt, args);
		va_end(args);

		seq_buf_putc(s, '\n');
	}
}

static void dump_stack_trace(struct seq_buf *s, const char *prefix,
			     const unsigned long *bt, unsigned int len)
{
	unsigned int i;

	for (i = 0; i < len; i++)
		dump_line(s, "%s%pS", prefix, (void *)bt[i]);
}

static void ops_dump_init(struct seq_buf *s, const char *prefix)
{
	struct scx_dump_data *dd = &scx_dump_data;

	lockdep_assert_irqs_disabled();

	dd->cpu = smp_processor_id();		/* allow scx_bpf_dump() */
	dd->first = true;
	dd->cursor = 0;
	dd->s = s;
	dd->prefix = prefix;
}

static void ops_dump_flush(void)
{
	struct scx_dump_data *dd = &scx_dump_data;
	char *line = dd->buf.line;

	if (!dd->cursor)
		return;

	/*
	 * There's something to flush and this is the first line. Insert a blank
	 * line to distinguish ops dump.
	 */
	if (dd->first) {
		dump_newline(dd->s);
		dd->first = false;
	}

	/*
	 * There may be multiple lines in $line. Scan and emit each line
	 * separately.
	 */
	while (true) {
		char *end = line;
		char c;

		while (*end != '\n' && *end != '\0')
			end++;

		/*
		 * If $line overflowed, it may not have newline at the end.
		 * Always emit with a newline.
		 */
		c = *end;
		*end = '\0';
		dump_line(dd->s, "%s%s", dd->prefix, line);
		if (c == '\0')
			break;

		/* move to the next line */
		end++;
		if (*end == '\0')
			break;
		line = end;
	}

	dd->cursor = 0;
}

static void ops_dump_exit(void)
{
	ops_dump_flush();
	scx_dump_data.cpu = -1;
}

static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx,
			  struct task_struct *p, char marker)
{
	static unsigned long bt[SCX_EXIT_BT_LEN];
	char dsq_id_buf[19] = "(n/a)";
	unsigned long ops_state = atomic_long_read(&p->scx.ops_state);
	unsigned int bt_len = 0;

	if (p->scx.dsq)
		scnprintf(dsq_id_buf, sizeof(dsq_id_buf), "0x%llx",
			  (unsigned long long)p->scx.dsq->id);

	dump_newline(s);
	dump_line(s, " %c%c %s[%d] %+ldms",
		  marker, task_state_to_char(p), p->comm, p->pid,
		  jiffies_delta_msecs(p->scx.runnable_at, dctx->at_jiffies));
	dump_line(s, "      scx_state/flags=%u/0x%x dsq_flags=0x%x ops_state/qseq=%lu/%lu",
		  scx_get_task_state(p), p->scx.flags & ~SCX_TASK_STATE_MASK,
		  p->scx.dsq_flags, ops_state & SCX_OPSS_STATE_MASK,
		  ops_state >> SCX_OPSS_QSEQ_SHIFT);
	dump_line(s, "      sticky/holding_cpu=%d/%d dsq_id=%s dsq_vtime=%llu",
		  p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf,
		  p->scx.dsq_vtime);
	dump_line(s, "      cpus=%*pb", cpumask_pr_args(p->cpus_ptr));

	if (SCX_HAS_OP(dump_task)) {
		ops_dump_init(s, "    ");
		SCX_CALL_OP(SCX_KF_REST, dump_task, dctx, p);
		ops_dump_exit();
	}

#ifdef CONFIG_STACKTRACE
	bt_len = stack_trace_save_tsk(p, bt, SCX_EXIT_BT_LEN, 1);
#endif
	if (bt_len) {
		dump_newline(s);
		dump_stack_trace(s, "    ", bt, bt_len);
	}
}

static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
{
	static DEFINE_SPINLOCK(dump_lock);
	static const char trunc_marker[] = "\n\n~~~~ TRUNCATED ~~~~\n";
	struct scx_dump_ctx dctx = {
		.kind = ei->kind,
		.exit_code = ei->exit_code,
		.reason = ei->reason,
		.at_ns = ktime_get_ns(),
		.at_jiffies = jiffies,
	};
	struct seq_buf s;
	unsigned long flags;
	char *buf;
	int cpu;

	spin_lock_irqsave(&dump_lock, flags);

	seq_buf_init(&s, ei->dump, dump_len);

	if (ei->kind == SCX_EXIT_NONE) {
		dump_line(&s, "Debug dump triggered by %s", ei->reason);
	} else {
		dump_line(&s, "%s[%d] triggered exit kind %d:",
			  current->comm, current->pid, ei->kind);
		dump_line(&s, "  %s (%s)", ei->reason, ei->msg);
		dump_newline(&s);
		dump_line(&s, "Backtrace:");
		dump_stack_trace(&s, "  ", ei->bt, ei->bt_len);
	}

	if (SCX_HAS_OP(dump)) {
		ops_dump_init(&s, "");
		SCX_CALL_OP(SCX_KF_UNLOCKED, dump, &dctx);
		ops_dump_exit();
	}

	dump_newline(&s);
	dump_line(&s, "CPU states");
	dump_line(&s, "----------");

	for_each_possible_cpu(cpu) {
		struct rq *rq = cpu_rq(cpu);
		struct rq_flags rf;
		struct task_struct *p;
		struct seq_buf ns;
		size_t avail, used;
		bool idle;

		rq_lock(rq, &rf);

		idle = list_empty(&rq->scx.runnable_list) &&
			rq->curr->sched_class == &idle_sched_class;

		if (idle && !SCX_HAS_OP(dump_cpu))
			goto next;

		/*
		 * We don't yet know whether ops.dump_cpu() will produce output
		 * and we may want to skip the default CPU dump if it doesn't.
		 * Use a nested seq_buf to generate the standard dump so that we
		 * can decide whether to commit later.
		 */
		avail = seq_buf_get_buf(&s, &buf);
		seq_buf_init(&ns, buf, avail);

		dump_newline(&ns);
		dump_line(&ns, "CPU %-4d: nr_run=%u flags=0x%x cpu_rel=%d ops_qseq=%lu pnt_seq=%lu",
			  cpu, rq->scx.nr_running, rq->scx.flags,
			  rq->scx.cpu_released, rq->scx.ops_qseq,
			  rq->scx.pnt_seq);
		dump_line(&ns, "          curr=%s[%d] class=%ps",
			  rq->curr->comm, rq->curr->pid,
			  rq->curr->sched_class);
		if (!cpumask_empty(rq->scx.cpus_to_kick))
			dump_line(&ns, "  cpus_to_kick   : %*pb",
				  cpumask_pr_args(rq->scx.cpus_to_kick));
		if (!cpumask_empty(rq->scx.cpus_to_kick_if_idle))
			dump_line(&ns, "  idle_to_kick   : %*pb",
				  cpumask_pr_args(rq->scx.cpus_to_kick_if_idle));
		if (!cpumask_empty(rq->scx.cpus_to_preempt))
			dump_line(&ns, "  cpus_to_preempt: %*pb",
				  cpumask_pr_args(rq->scx.cpus_to_preempt));
		if (!cpumask_empty(rq->scx.cpus_to_wait))
			dump_line(&ns, "  cpus_to_wait   : %*pb",
				  cpumask_pr_args(rq->scx.cpus_to_wait));

		used = seq_buf_used(&ns);
		if (SCX_HAS_OP(dump_cpu)) {
			ops_dump_init(&ns, "  ");
			SCX_CALL_OP(SCX_KF_REST, dump_cpu, &dctx, cpu, idle);
			ops_dump_exit();
		}

		/*
		 * If idle && nothing generated by ops.dump_cpu(), there's
		 * nothing interesting. Skip.
		 */
		if (idle && used == seq_buf_used(&ns))
			goto next;

		/*
		 * $s may already have overflowed when $ns was created. If so,
		 * calling commit on it will trigger BUG.
		 */
		if (avail) {
			seq_buf_commit(&s, seq_buf_used(&ns));
			if (seq_buf_has_overflowed(&ns))
				seq_buf_set_overflow(&s);
		}

		if (rq->curr->sched_class == &ext_sched_class)
			scx_dump_task(&s, &dctx, rq->curr, '*');

		list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node)
			scx_dump_task(&s, &dctx, p, ' ');
	next:
		rq_unlock(rq, &rf);
	}

	if (seq_buf_has_overflowed(&s) && dump_len >= sizeof(trunc_marker))
		memcpy(ei->dump + dump_len - sizeof(trunc_marker),
		       trunc_marker, sizeof(trunc_marker));

	spin_unlock_irqrestore(&dump_lock, flags);
}

static void scx_ops_error_irq_workfn(struct irq_work *irq_work)
{
	struct scx_exit_info *ei = scx_exit_info;

	if (ei->kind >= SCX_EXIT_ERROR)
		scx_dump_state(ei, scx_ops.exit_dump_len);

	schedule_scx_ops_disable_work();
}

static DEFINE_IRQ_WORK(scx_ops_error_irq_work, scx_ops_error_irq_workfn);

static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind,
					     s64 exit_code,
					     const char *fmt, ...)
{
	struct scx_exit_info *ei = scx_exit_info;
	int none = SCX_EXIT_NONE;
	va_list args;

	if (!atomic_try_cmpxchg(&scx_exit_kind, &none, kind))
		return;

	ei->exit_code = exit_code;
#ifdef CONFIG_STACKTRACE
	if (kind >= SCX_EXIT_ERROR)
		ei->bt_len = stack_trace_save(ei->bt, SCX_EXIT_BT_LEN, 1);
#endif
	va_start(args, fmt);
	vscnprintf(ei->msg, SCX_EXIT_MSG_LEN, fmt, args);
	va_end(args);

	/*
	 * Set ei->kind and ->reason for scx_dump_state(). They'll be set again
	 * in scx_ops_disable_workfn().
	 */
	ei->kind = kind;
	ei->reason = scx_exit_reason(ei->kind);

	irq_work_queue(&scx_ops_error_irq_work);
}

static struct kthread_worker *scx_create_rt_helper(const char *name)
{
	struct kthread_worker *helper;

	helper = kthread_create_worker(0, name);
	if (helper)
		sched_set_fifo(helper->task);
	return helper;
}

static void check_hotplug_seq(const struct sched_ext_ops *ops)
{
	unsigned long long global_hotplug_seq;

	/*
	 * If a hotplug event has occurred between when a scheduler was
	 * initialized, and when we were able to attach, exit and notify user
	 * space about it.
	 */
	if (ops->hotplug_seq) {
		global_hotplug_seq = atomic_long_read(&scx_hotplug_seq);
		if (ops->hotplug_seq != global_hotplug_seq) {
			scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG,
				     "expected hotplug seq %llu did not match actual %llu",
				     ops->hotplug_seq, global_hotplug_seq);
		}
	}
}

static int validate_ops(const struct sched_ext_ops *ops)
{
	/*
	 * It doesn't make sense to specify the SCX_OPS_ENQ_LAST flag if the
	 * ops.enqueue() callback isn't implemented.
	 */
	if ((ops->flags & SCX_OPS_ENQ_LAST) && !ops->enqueue) {
		scx_ops_error("SCX_OPS_ENQ_LAST requires ops.enqueue() to be implemented");
		return -EINVAL;
	}

	return 0;
}

static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
{
	struct scx_task_iter sti;
	struct task_struct *p;
	unsigned long timeout;
	int i, cpu, node, ret;

	if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN),
			   cpu_possible_mask)) {
		pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation");
		return -EINVAL;
	}

	mutex_lock(&scx_ops_enable_mutex);

	if (!scx_ops_helper) {
		WRITE_ONCE(scx_ops_helper,
			   scx_create_rt_helper("sched_ext_ops_helper"));
		if (!scx_ops_helper) {
			ret = -ENOMEM;
			goto err_unlock;
		}
	}

	if (!global_dsqs) {
		struct scx_dispatch_q **dsqs;

		dsqs = kcalloc(nr_node_ids, sizeof(dsqs[0]), GFP_KERNEL);
		if (!dsqs) {
			ret = -ENOMEM;
			goto err_unlock;
		}

		for_each_node_state(node, N_POSSIBLE) {
			struct scx_dispatch_q *dsq;

			dsq = kzalloc_node(sizeof(*dsq), GFP_KERNEL, node);
			if (!dsq) {
				for_each_node_state(node, N_POSSIBLE)
					kfree(dsqs[node]);
				kfree(dsqs);
				ret = -ENOMEM;
				goto err_unlock;
			}

			init_dsq(dsq, SCX_DSQ_GLOBAL);
			dsqs[node] = dsq;
		}

		global_dsqs = dsqs;
	}

	if (scx_ops_enable_state() != SCX_OPS_DISABLED) {
		ret = -EBUSY;
		goto err_unlock;
	}

	scx_root_kobj = kzalloc(sizeof(*scx_root_kobj), GFP_KERNEL);
	if (!scx_root_kobj) {
		ret = -ENOMEM;
		goto err_unlock;
	}

	scx_root_kobj->kset = scx_kset;
	ret = kobject_init_and_add(scx_root_kobj, &scx_ktype, NULL, "root");
	if (ret < 0)
		goto err;

	scx_exit_info = alloc_exit_info(ops->exit_dump_len);
	if (!scx_exit_info) {
		ret = -ENOMEM;
		goto err_del;
	}

	/*
	 * Set scx_ops, transition to ENABLING and clear exit info to arm the
	 * disable path. Failure triggers full disabling from here on.
	 */
	scx_ops = *ops;

	WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_ENABLING) !=
		     SCX_OPS_DISABLED);

	atomic_set(&scx_exit_kind, SCX_EXIT_NONE);
	scx_warned_zero_slice = false;

	atomic_long_set(&scx_nr_rejected, 0);

	for_each_possible_cpu(cpu)
		cpu_rq(cpu)->scx.cpuperf_target = SCX_CPUPERF_ONE;

	/*
	 * Keep CPUs stable during enable so that the BPF scheduler can track
	 * online CPUs by watching ->on/offline_cpu() after ->init().
	 */
	cpus_read_lock();

	if (scx_ops.init) {
		ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init);
		if (ret) {
			ret = ops_sanitize_err("init", ret);
			cpus_read_unlock();
			scx_ops_error("ops.init() failed (%d)", ret);
			goto err_disable;
		}
	}

	for (i = SCX_OPI_CPU_HOTPLUG_BEGIN; i < SCX_OPI_CPU_HOTPLUG_END; i++)
		if (((void (**)(void))ops)[i])
			static_branch_enable_cpuslocked(&scx_has_op[i]);

	check_hotplug_seq(ops);
	cpus_read_unlock();

	ret = validate_ops(ops);
	if (ret)
		goto err_disable;

	WARN_ON_ONCE(scx_dsp_ctx);
	scx_dsp_max_batch = ops->dispatch_max_batch ?: SCX_DSP_DFL_MAX_BATCH;
	scx_dsp_ctx = __alloc_percpu(struct_size_t(struct scx_dsp_ctx, buf,
						   scx_dsp_max_batch),
				     __alignof__(struct scx_dsp_ctx));
	if (!scx_dsp_ctx) {
		ret = -ENOMEM;
		goto err_disable;
	}

	if (ops->timeout_ms)
		timeout = msecs_to_jiffies(ops->timeout_ms);
	else
		timeout = SCX_WATCHDOG_MAX_TIMEOUT;

	WRITE_ONCE(scx_watchdog_timeout, timeout);
	WRITE_ONCE(scx_watchdog_timestamp, jiffies);
	queue_delayed_work(system_unbound_wq, &scx_watchdog_work,
			   scx_watchdog_timeout / 2);

	/*
	 * Once __scx_ops_enabled is set, %current can be switched to SCX
	 * anytime. This can lead to stalls as some BPF schedulers (e.g.
	 * userspace scheduling) may not function correctly before all tasks are
	 * switched. Init in bypass mode to guarantee forward progress.
	 */
	scx_ops_bypass(true);

	for (i = SCX_OPI_NORMAL_BEGIN; i < SCX_OPI_NORMAL_END; i++)
		if (((void (**)(void))ops)[i])
			static_branch_enable(&scx_has_op[i]);

	if (ops->flags & SCX_OPS_ENQ_LAST)
		static_branch_enable(&scx_ops_enq_last);

	if (ops->flags & SCX_OPS_ENQ_EXITING)
		static_branch_enable(&scx_ops_enq_exiting);
	if (scx_ops.cpu_acquire || scx_ops.cpu_release)
		static_branch_enable(&scx_ops_cpu_preempt);

	if (!ops->update_idle || (ops->flags & SCX_OPS_KEEP_BUILTIN_IDLE)) {
		reset_idle_masks();
		static_branch_enable(&scx_builtin_idle_enabled);
	} else {
		static_branch_disable(&scx_builtin_idle_enabled);
	}

	/*
	 * Lock out forks, cgroup on/offlining and moves before opening the
	 * floodgate so that they don't wander into the operations prematurely.
	 */
	percpu_down_write(&scx_fork_rwsem);

	WARN_ON_ONCE(scx_ops_init_task_enabled);
	scx_ops_init_task_enabled = true;

	/*
	 * Enable ops for every task. Fork is excluded by scx_fork_rwsem
	 * preventing new tasks from being added. No need to exclude tasks
	 * leaving as sched_ext_free() can handle both prepped and enabled
	 * tasks. Prep all tasks first and then enable them with preemption
	 * disabled.
	 *
	 * All cgroups should be initialized before scx_ops_init_task() so that
	 * the BPF scheduler can reliably track each task's cgroup membership
	 * from scx_ops_init_task(). Lock out cgroup on/offlining and task
	 * migrations while tasks are being initialized so that
	 * scx_cgroup_can_attach() never sees uninitialized tasks.
	 */
	scx_cgroup_lock();
	ret = scx_cgroup_init();
	if (ret)
		goto err_disable_unlock_all;

	scx_task_iter_start(&sti);
	while ((p = scx_task_iter_next_locked(&sti))) {
		/*
		 * @p may already be dead, have lost all its usages counts and
		 * be waiting for RCU grace period before being freed. @p can't
		 * be initialized for SCX in such cases and should be ignored.
		 */
		if (!tryget_task_struct(p))
			continue;

		scx_task_iter_unlock(&sti);

		ret = scx_ops_init_task(p, task_group(p), false);
		if (ret) {
			put_task_struct(p);
			scx_task_iter_relock(&sti);
			scx_task_iter_stop(&sti);
			scx_ops_error("ops.init_task() failed (%d) for %s[%d]",
				      ret, p->comm, p->pid);
			goto err_disable_unlock_all;
		}

		scx_set_task_state(p, SCX_TASK_READY);

		put_task_struct(p);
		scx_task_iter_relock(&sti);
	}
	scx_task_iter_stop(&sti);
	scx_cgroup_unlock();
	percpu_up_write(&scx_fork_rwsem);

	/*
	 * All tasks are READY. It's safe to turn on scx_enabled() and switch
	 * all eligible tasks.
	 */
	WRITE_ONCE(scx_switching_all, !(ops->flags & SCX_OPS_SWITCH_PARTIAL));
	static_branch_enable(&__scx_ops_enabled);

	/*
	 * We're fully committed and can't fail. The task READY -> ENABLED
	 * transitions here are synchronized against sched_ext_free() through
	 * scx_tasks_lock.
	 */
	percpu_down_write(&scx_fork_rwsem);
	scx_task_iter_start(&sti);
	while ((p = scx_task_iter_next_locked(&sti))) {
		const struct sched_class *old_class = p->sched_class;
		struct sched_enq_and_set_ctx ctx;

		sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);

		p->scx.slice = SCX_SLICE_DFL;
		p->sched_class = __setscheduler_class(p, p->prio);
		check_class_changing(task_rq(p), p, old_class);

		sched_enq_and_set_task(&ctx);

		check_class_changed(task_rq(p), p, old_class, p->prio);
	}
	scx_task_iter_stop(&sti);
	percpu_up_write(&scx_fork_rwsem);

	scx_ops_bypass(false);

	if (!scx_ops_tryset_enable_state(SCX_OPS_ENABLED, SCX_OPS_ENABLING)) {
		WARN_ON_ONCE(atomic_read(&scx_exit_kind) == SCX_EXIT_NONE);
		goto err_disable;
	}

	if (!(ops->flags & SCX_OPS_SWITCH_PARTIAL))
		static_branch_enable(&__scx_switched_all);

	pr_info("sched_ext: BPF scheduler \"%s\" enabled%s\n",
		scx_ops.name, scx_switched_all() ? "" : " (partial)");
	kobject_uevent(scx_root_kobj, KOBJ_ADD);
	mutex_unlock(&scx_ops_enable_mutex);

	atomic_long_inc(&scx_enable_seq);

	return 0;

err_del:
	kobject_del(scx_root_kobj);
err:
	kobject_put(scx_root_kobj);
	scx_root_kobj = NULL;
	if (scx_exit_info) {
		free_exit_info(scx_exit_info);
		scx_exit_info = NULL;
	}
err_unlock:
	mutex_unlock(&scx_ops_enable_mutex);
	return ret;

err_disable_unlock_all:
	scx_cgroup_unlock();
	percpu_up_write(&scx_fork_rwsem);
	scx_ops_bypass(false);
err_disable:
	mutex_unlock(&scx_ops_enable_mutex);
	/*
	 * Returning an error code here would not pass all the error information
	 * to userspace. Record errno using scx_ops_error() for cases
	 * scx_ops_error() wasn't already invoked and exit indicating success so
	 * that the error is notified through ops.exit() with all the details.
	 *
	 * Flush scx_ops_disable_work to ensure that error is reported before
	 * init completion.
	 */
	scx_ops_error("scx_ops_enable() failed (%d)", ret);
	kthread_flush_work(&scx_ops_disable_work);
	return 0;
}


/********************************************************************************
 * bpf_struct_ops plumbing.
 */
#include <linux/bpf_verifier.h>
#include <linux/bpf.h>
#include <linux/btf.h>

extern struct btf *btf_vmlinux;
static const struct btf_type *task_struct_type;
static u32 task_struct_type_id;

static bool set_arg_maybe_null(const char *op, int arg_n, int off, int size,
			       enum bpf_access_type type,
			       const struct bpf_prog *prog,
			       struct bpf_insn_access_aux *info)
{
	struct btf *btf = bpf_get_btf_vmlinux();
	const struct bpf_struct_ops_desc *st_ops_desc;
	const struct btf_member *member;
	const struct btf_type *t;
	u32 btf_id, member_idx;
	const char *mname;

	/* struct_ops op args are all sequential, 64-bit numbers */
	if (off != arg_n * sizeof(__u64))
		return false;

	/* btf_id should be the type id of struct sched_ext_ops */
	btf_id = prog->aux->attach_btf_id;
	st_ops_desc = bpf_struct_ops_find(btf, btf_id);
	if (!st_ops_desc)
		return false;

	/* BTF type of struct sched_ext_ops */
	t = st_ops_desc->type;

	member_idx = prog->expected_attach_type;
	if (member_idx >= btf_type_vlen(t))
		return false;

	/*
	 * Get the member name of this struct_ops program, which corresponds to
	 * a field in struct sched_ext_ops. For example, the member name of the
	 * dispatch struct_ops program (callback) is "dispatch".
	 */
	member = &btf_type_member(t)[member_idx];
	mname = btf_name_by_offset(btf_vmlinux, member->name_off);

	if (!strcmp(mname, op)) {
		/*
		 * The value is a pointer to a type (struct task_struct) given
		 * by a BTF ID (PTR_TO_BTF_ID). It is trusted (PTR_TRUSTED),
		 * however, can be a NULL (PTR_MAYBE_NULL). The BPF program
		 * should check the pointer to make sure it is not NULL before
		 * using it, or the verifier will reject the program.
		 *
		 * Longer term, this is something that should be addressed by
		 * BTF, and be fully contained within the verifier.
		 */
		info->reg_type = PTR_MAYBE_NULL | PTR_TO_BTF_ID | PTR_TRUSTED;
		info->btf = btf_vmlinux;
		info->btf_id = task_struct_type_id;

		return true;
	}

	return false;
}

static bool bpf_scx_is_valid_access(int off, int size,
				    enum bpf_access_type type,
				    const struct bpf_prog *prog,
				    struct bpf_insn_access_aux *info)
{
	if (type != BPF_READ)
		return false;
	if (set_arg_maybe_null("dispatch", 1, off, size, type, prog, info) ||
	    set_arg_maybe_null("yield", 1, off, size, type, prog, info))
		return true;
	if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS)
		return false;
	if (off % size != 0)
		return false;

	return btf_ctx_access(off, size, type, prog, info);
}

static int bpf_scx_btf_struct_access(struct bpf_verifier_log *log,
				     const struct bpf_reg_state *reg, int off,
				     int size)
{
	const struct btf_type *t;

	t = btf_type_by_id(reg->btf, reg->btf_id);
	if (t == task_struct_type) {
		if (off >= offsetof(struct task_struct, scx.slice) &&
		    off + size <= offsetofend(struct task_struct, scx.slice))
			return SCALAR_VALUE;
		if (off >= offsetof(struct task_struct, scx.dsq_vtime) &&
		    off + size <= offsetofend(struct task_struct, scx.dsq_vtime))
			return SCALAR_VALUE;
		if (off >= offsetof(struct task_struct, scx.disallow) &&
		    off + size <= offsetofend(struct task_struct, scx.disallow))
			return SCALAR_VALUE;
	}

	return -EACCES;
}

static const struct bpf_func_proto *
bpf_scx_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
	switch (func_id) {
	case BPF_FUNC_task_storage_get:
		return &bpf_task_storage_get_proto;
	case BPF_FUNC_task_storage_delete:
		return &bpf_task_storage_delete_proto;
	default:
		return bpf_base_func_proto(func_id, prog);
	}
}

static const struct bpf_verifier_ops bpf_scx_verifier_ops = {
	.get_func_proto = bpf_scx_get_func_proto,
	.is_valid_access = bpf_scx_is_valid_access,
	.btf_struct_access = bpf_scx_btf_struct_access,
};

static int bpf_scx_init_member(const struct btf_type *t,
			       const struct btf_member *member,
			       void *kdata, const void *udata)
{
	const struct sched_ext_ops *uops = udata;
	struct sched_ext_ops *ops = kdata;
	u32 moff = __btf_member_bit_offset(t, member) / 8;
	int ret;

	switch (moff) {
	case offsetof(struct sched_ext_ops, dispatch_max_batch):
		if (*(u32 *)(udata + moff) > INT_MAX)
			return -E2BIG;
		ops->dispatch_max_batch = *(u32 *)(udata + moff);
		return 1;
	case offsetof(struct sched_ext_ops, flags):
		if (*(u64 *)(udata + moff) & ~SCX_OPS_ALL_FLAGS)
			return -EINVAL;
		ops->flags = *(u64 *)(udata + moff);
		return 1;
	case offsetof(struct sched_ext_ops, name):
		ret = bpf_obj_name_cpy(ops->name, uops->name,
				       sizeof(ops->name));
		if (ret < 0)
			return ret;
		if (ret == 0)
			return -EINVAL;
		return 1;
	case offsetof(struct sched_ext_ops, timeout_ms):
		if (msecs_to_jiffies(*(u32 *)(udata + moff)) >
		    SCX_WATCHDOG_MAX_TIMEOUT)
			return -E2BIG;
		ops->timeout_ms = *(u32 *)(udata + moff);
		return 1;
	case offsetof(struct sched_ext_ops, exit_dump_len):
		ops->exit_dump_len =
			*(u32 *)(udata + moff) ?: SCX_EXIT_DUMP_DFL_LEN;
		return 1;
	case offsetof(struct sched_ext_ops, hotplug_seq):
		ops->hotplug_seq = *(u64 *)(udata + moff);
		return 1;
	}

	return 0;
}

static int bpf_scx_check_member(const struct btf_type *t,
				const struct btf_member *member,
				const struct bpf_prog *prog)
{
	u32 moff = __btf_member_bit_offset(t, member) / 8;

	switch (moff) {
	case offsetof(struct sched_ext_ops, init_task):
#ifdef CONFIG_EXT_GROUP_SCHED
	case offsetof(struct sched_ext_ops, cgroup_init):
	case offsetof(struct sched_ext_ops, cgroup_exit):
	case offsetof(struct sched_ext_ops, cgroup_prep_move):
#endif
	case offsetof(struct sched_ext_ops, cpu_online):
	case offsetof(struct sched_ext_ops, cpu_offline):
	case offsetof(struct sched_ext_ops, init):
	case offsetof(struct sched_ext_ops, exit):
		break;
	default:
		if (prog->sleepable)
			return -EINVAL;
	}

	return 0;
}

static int bpf_scx_reg(void *kdata, struct bpf_link *link)
{
	return scx_ops_enable(kdata, link);
}

static void bpf_scx_unreg(void *kdata, struct bpf_link *link)
{
	scx_ops_disable(SCX_EXIT_UNREG);
	kthread_flush_work(&scx_ops_disable_work);
}

static int bpf_scx_init(struct btf *btf)
{
	s32 type_id;

	type_id = btf_find_by_name_kind(btf, "task_struct", BTF_KIND_STRUCT);
	if (type_id < 0)
		return -EINVAL;
	task_struct_type = btf_type_by_id(btf, type_id);
	task_struct_type_id = type_id;

	return 0;
}

static int bpf_scx_update(void *kdata, void *old_kdata, struct bpf_link *link)
{
	/*
	 * sched_ext does not support updating the actively-loaded BPF
	 * scheduler, as registering a BPF scheduler can always fail if the
	 * scheduler returns an error code for e.g. ops.init(), ops.init_task(),
	 * etc. Similarly, we can always race with unregistration happening
	 * elsewhere, such as with sysrq.
	 */
	return -EOPNOTSUPP;
}

static int bpf_scx_validate(void *kdata)
{
	return 0;
}

static s32 select_cpu_stub(struct task_struct *p, s32 prev_cpu, u64 wake_flags) { return -EINVAL; }
static void enqueue_stub(struct task_struct *p, u64 enq_flags) {}
static void dequeue_stub(struct task_struct *p, u64 enq_flags) {}
static void dispatch_stub(s32 prev_cpu, struct task_struct *p) {}
static void tick_stub(struct task_struct *p) {}
static void runnable_stub(struct task_struct *p, u64 enq_flags) {}
static void running_stub(struct task_struct *p) {}
static void stopping_stub(struct task_struct *p, bool runnable) {}
static void quiescent_stub(struct task_struct *p, u64 deq_flags) {}
static bool yield_stub(struct task_struct *from, struct task_struct *to) { return false; }
static bool core_sched_before_stub(struct task_struct *a, struct task_struct *b) { return false; }
static void set_weight_stub(struct task_struct *p, u32 weight) {}
static void set_cpumask_stub(struct task_struct *p, const struct cpumask *mask) {}
static void update_idle_stub(s32 cpu, bool idle) {}
static void cpu_acquire_stub(s32 cpu, struct scx_cpu_acquire_args *args) {}
static void cpu_release_stub(s32 cpu, struct scx_cpu_release_args *args) {}
static s32 init_task_stub(struct task_struct *p, struct scx_init_task_args *args) { return -EINVAL; }
static void exit_task_stub(struct task_struct *p, struct scx_exit_task_args *args) {}
static void enable_stub(struct task_struct *p) {}
static void disable_stub(struct task_struct *p) {}
#ifdef CONFIG_EXT_GROUP_SCHED
static s32 cgroup_init_stub(struct cgroup *cgrp, struct scx_cgroup_init_args *args) { return -EINVAL; }
static void cgroup_exit_stub(struct cgroup *cgrp) {}
static s32 cgroup_prep_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) { return -EINVAL; }
static void cgroup_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) {}
static void cgroup_cancel_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) {}
static void cgroup_set_weight_stub(struct cgroup *cgrp, u32 weight) {}
#endif
static void cpu_online_stub(s32 cpu) {}
static void cpu_offline_stub(s32 cpu) {}
static s32 init_stub(void) { return -EINVAL; }
static void exit_stub(struct scx_exit_info *info) {}
static void dump_stub(struct scx_dump_ctx *ctx) {}
static void dump_cpu_stub(struct scx_dump_ctx *ctx, s32 cpu, bool idle) {}
static void dump_task_stub(struct scx_dump_ctx *ctx, struct task_struct *p) {}

static struct sched_ext_ops __bpf_ops_sched_ext_ops = {
	.select_cpu = select_cpu_stub,
	.enqueue = enqueue_stub,
	.dequeue = dequeue_stub,
	.dispatch = dispatch_stub,
	.tick = tick_stub,
	.runnable = runnable_stub,
	.running = running_stub,
	.stopping = stopping_stub,
	.quiescent = quiescent_stub,
	.yield = yield_stub,
	.core_sched_before = core_sched_before_stub,
	.set_weight = set_weight_stub,
	.set_cpumask = set_cpumask_stub,
	.update_idle = update_idle_stub,
	.cpu_acquire = cpu_acquire_stub,
	.cpu_release = cpu_release_stub,
	.init_task = init_task_stub,
	.exit_task = exit_task_stub,
	.enable = enable_stub,
	.disable = disable_stub,
#ifdef CONFIG_EXT_GROUP_SCHED
	.cgroup_init = cgroup_init_stub,
	.cgroup_exit = cgroup_exit_stub,
	.cgroup_prep_move = cgroup_prep_move_stub,
	.cgroup_move = cgroup_move_stub,
	.cgroup_cancel_move = cgroup_cancel_move_stub,
	.cgroup_set_weight = cgroup_set_weight_stub,
#endif
	.cpu_online = cpu_online_stub,
	.cpu_offline = cpu_offline_stub,
	.init = init_stub,
	.exit = exit_stub,
	.dump = dump_stub,
	.dump_cpu = dump_cpu_stub,
	.dump_task = dump_task_stub,
};

static struct bpf_struct_ops bpf_sched_ext_ops = {
	.verifier_ops = &bpf_scx_verifier_ops,
	.reg = bpf_scx_reg,
	.unreg = bpf_scx_unreg,
	.check_member = bpf_scx_check_member,
	.init_member = bpf_scx_init_member,
	.init = bpf_scx_init,
	.update = bpf_scx_update,
	.validate = bpf_scx_validate,
	.name = "sched_ext_ops",
	.owner = THIS_MODULE,
	.cfi_stubs = &__bpf_ops_sched_ext_ops
};


/********************************************************************************
 * System integration and init.
 */

static void sysrq_handle_sched_ext_reset(u8 key)
{
	if (scx_ops_helper)
		scx_ops_disable(SCX_EXIT_SYSRQ);
	else
		pr_info("sched_ext: BPF scheduler not yet used\n");
}

static const struct sysrq_key_op sysrq_sched_ext_reset_op = {
	.handler	= sysrq_handle_sched_ext_reset,
	.help_msg	= "reset-sched-ext(S)",
	.action_msg	= "Disable sched_ext and revert all tasks to CFS",
	.enable_mask	= SYSRQ_ENABLE_RTNICE,
};

static void sysrq_handle_sched_ext_dump(u8 key)
{
	struct scx_exit_info ei = { .kind = SCX_EXIT_NONE, .reason = "SysRq-D" };

	if (scx_enabled())
		scx_dump_state(&ei, 0);
}

static const struct sysrq_key_op sysrq_sched_ext_dump_op = {
	.handler	= sysrq_handle_sched_ext_dump,
	.help_msg	= "dump-sched-ext(D)",
	.action_msg	= "Trigger sched_ext debug dump",
	.enable_mask	= SYSRQ_ENABLE_RTNICE,
};

static bool can_skip_idle_kick(struct rq *rq)
{
	lockdep_assert_rq_held(rq);

	/*
	 * We can skip idle kicking if @rq is going to go through at least one
	 * full SCX scheduling cycle before going idle. Just checking whether
	 * curr is not idle is insufficient because we could be racing
	 * balance_one() trying to pull the next task from a remote rq, which
	 * may fail, and @rq may become idle afterwards.
	 *
	 * The race window is small and we don't and can't guarantee that @rq is
	 * only kicked while idle anyway. Skip only when sure.
	 */
	return !is_idle_task(rq->curr) && !(rq->scx.flags & SCX_RQ_IN_BALANCE);
}

static bool kick_one_cpu(s32 cpu, struct rq *this_rq, unsigned long *pseqs)
{
	struct rq *rq = cpu_rq(cpu);
	struct scx_rq *this_scx = &this_rq->scx;
	bool should_wait = false;
	unsigned long flags;

	raw_spin_rq_lock_irqsave(rq, flags);

	/*
	 * During CPU hotplug, a CPU may depend on kicking itself to make
	 * forward progress. Allow kicking self regardless of online state.
	 */
	if (cpu_online(cpu) || cpu == cpu_of(this_rq)) {
		if (cpumask_test_cpu(cpu, this_scx->cpus_to_preempt)) {
			if (rq->curr->sched_class == &ext_sched_class)
				rq->curr->scx.slice = 0;
			cpumask_clear_cpu(cpu, this_scx->cpus_to_preempt);
		}

		if (cpumask_test_cpu(cpu, this_scx->cpus_to_wait)) {
			pseqs[cpu] = rq->scx.pnt_seq;
			should_wait = true;
		}

		resched_curr(rq);
	} else {
		cpumask_clear_cpu(cpu, this_scx->cpus_to_preempt);
		cpumask_clear_cpu(cpu, this_scx->cpus_to_wait);
	}

	raw_spin_rq_unlock_irqrestore(rq, flags);

	return should_wait;
}

static void kick_one_cpu_if_idle(s32 cpu, struct rq *this_rq)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long flags;

	raw_spin_rq_lock_irqsave(rq, flags);

	if (!can_skip_idle_kick(rq) &&
	    (cpu_online(cpu) || cpu == cpu_of(this_rq)))
		resched_curr(rq);

	raw_spin_rq_unlock_irqrestore(rq, flags);
}

static void kick_cpus_irq_workfn(struct irq_work *irq_work)
{
	struct rq *this_rq = this_rq();
	struct scx_rq *this_scx = &this_rq->scx;
	unsigned long *pseqs = this_cpu_ptr(scx_kick_cpus_pnt_seqs);
	bool should_wait = false;
	s32 cpu;

	for_each_cpu(cpu, this_scx->cpus_to_kick) {
		should_wait |= kick_one_cpu(cpu, this_rq, pseqs);
		cpumask_clear_cpu(cpu, this_scx->cpus_to_kick);
		cpumask_clear_cpu(cpu, this_scx->cpus_to_kick_if_idle);
	}

	for_each_cpu(cpu, this_scx->cpus_to_kick_if_idle) {
		kick_one_cpu_if_idle(cpu, this_rq);
		cpumask_clear_cpu(cpu, this_scx->cpus_to_kick_if_idle);
	}

	if (!should_wait)
		return;

	for_each_cpu(cpu, this_scx->cpus_to_wait) {
		unsigned long *wait_pnt_seq = &cpu_rq(cpu)->scx.pnt_seq;

		if (cpu != cpu_of(this_rq)) {
			/*
			 * Pairs with smp_store_release() issued by this CPU in
			 * scx_next_task_picked() on the resched path.
			 *
			 * We busy-wait here to guarantee that no other task can
			 * be scheduled on our core before the target CPU has
			 * entered the resched path.
			 */
			while (smp_load_acquire(wait_pnt_seq) == pseqs[cpu])
				cpu_relax();
		}

		cpumask_clear_cpu(cpu, this_scx->cpus_to_wait);
	}
}

/**
 * print_scx_info - print out sched_ext scheduler state
 * @log_lvl: the log level to use when printing
 * @p: target task
 *
 * If a sched_ext scheduler is enabled, print the name and state of the
 * scheduler. If @p is on sched_ext, print further information about the task.
 *
 * This function can be safely called on any task as long as the task_struct
 * itself is accessible. While safe, this function isn't synchronized and may
 * print out mixups or garbages of limited length.
 */
void print_scx_info(const char *log_lvl, struct task_struct *p)
{
	enum scx_ops_enable_state state = scx_ops_enable_state();
	const char *all = READ_ONCE(scx_switching_all) ? "+all" : "";
	char runnable_at_buf[22] = "?";
	struct sched_class *class;
	unsigned long runnable_at;

	if (state == SCX_OPS_DISABLED)
		return;

	/*
	 * Carefully check if the task was running on sched_ext, and then
	 * carefully copy the time it's been runnable, and its state.
	 */
	if (copy_from_kernel_nofault(&class, &p->sched_class, sizeof(class)) ||
	    class != &ext_sched_class) {
		printk("%sSched_ext: %s (%s%s)", log_lvl, scx_ops.name,
		       scx_ops_enable_state_str[state], all);
		return;
	}

	if (!copy_from_kernel_nofault(&runnable_at, &p->scx.runnable_at,
				      sizeof(runnable_at)))
		scnprintf(runnable_at_buf, sizeof(runnable_at_buf), "%+ldms",
			  jiffies_delta_msecs(runnable_at, jiffies));

	/* print everything onto one line to conserve console space */
	printk("%sSched_ext: %s (%s%s), task: runnable_at=%s",
	       log_lvl, scx_ops.name, scx_ops_enable_state_str[state], all,
	       runnable_at_buf);
}

static int scx_pm_handler(struct notifier_block *nb, unsigned long event, void *ptr)
{
	/*
	 * SCX schedulers often have userspace components which are sometimes
	 * involved in critial scheduling paths. PM operations involve freezing
	 * userspace which can lead to scheduling misbehaviors including stalls.
	 * Let's bypass while PM operations are in progress.
	 */
	switch (event) {
	case PM_HIBERNATION_PREPARE:
	case PM_SUSPEND_PREPARE:
	case PM_RESTORE_PREPARE:
		scx_ops_bypass(true);
		break;
	case PM_POST_HIBERNATION:
	case PM_POST_SUSPEND:
	case PM_POST_RESTORE:
		scx_ops_bypass(false);
		break;
	}

	return NOTIFY_OK;
}

static struct notifier_block scx_pm_notifier = {
	.notifier_call = scx_pm_handler,
};

void __init init_sched_ext_class(void)
{
	s32 cpu, v;

	/*
	 * The following is to prevent the compiler from optimizing out the enum
	 * definitions so that BPF scheduler implementations can use them
	 * through the generated vmlinux.h.
	 */
	WRITE_ONCE(v, SCX_ENQ_WAKEUP | SCX_DEQ_SLEEP | SCX_KICK_PREEMPT |
		   SCX_TG_ONLINE);

	BUG_ON(rhashtable_init(&dsq_hash, &dsq_hash_params));
#ifdef CONFIG_SMP
	BUG_ON(!alloc_cpumask_var(&idle_masks.cpu, GFP_KERNEL));
	BUG_ON(!alloc_cpumask_var(&idle_masks.smt, GFP_KERNEL));
#endif
	scx_kick_cpus_pnt_seqs =
		__alloc_percpu(sizeof(scx_kick_cpus_pnt_seqs[0]) * nr_cpu_ids,
			       __alignof__(scx_kick_cpus_pnt_seqs[0]));
	BUG_ON(!scx_kick_cpus_pnt_seqs);

	for_each_possible_cpu(cpu) {
		struct rq *rq = cpu_rq(cpu);

		init_dsq(&rq->scx.local_dsq, SCX_DSQ_LOCAL);
		INIT_LIST_HEAD(&rq->scx.runnable_list);
		INIT_LIST_HEAD(&rq->scx.ddsp_deferred_locals);

		BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_kick, GFP_KERNEL));
		BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_kick_if_idle, GFP_KERNEL));
		BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_preempt, GFP_KERNEL));
		BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_wait, GFP_KERNEL));
		init_irq_work(&rq->scx.deferred_irq_work, deferred_irq_workfn);
		init_irq_work(&rq->scx.kick_cpus_irq_work, kick_cpus_irq_workfn);

		if (cpu_online(cpu))
			cpu_rq(cpu)->scx.flags |= SCX_RQ_ONLINE;
	}

	register_sysrq_key('S', &sysrq_sched_ext_reset_op);
	register_sysrq_key('D', &sysrq_sched_ext_dump_op);
	INIT_DELAYED_WORK(&scx_watchdog_work, scx_watchdog_workfn);
}


/********************************************************************************
 * Helpers that can be called from the BPF scheduler.
 */
#include <linux/btf_ids.h>

__bpf_kfunc_start_defs();

/**
 * scx_bpf_select_cpu_dfl - The default implementation of ops.select_cpu()
 * @p: task_struct to select a CPU for
 * @prev_cpu: CPU @p was on previously
 * @wake_flags: %SCX_WAKE_* flags
 * @is_idle: out parameter indicating whether the returned CPU is idle
 *
 * Can only be called from ops.select_cpu() if the built-in CPU selection is
 * enabled - ops.update_idle() is missing or %SCX_OPS_KEEP_BUILTIN_IDLE is set.
 * @p, @prev_cpu and @wake_flags match ops.select_cpu().
 *
 * Returns the picked CPU with *@is_idle indicating whether the picked CPU is
 * currently idle and thus a good candidate for direct dispatching.
 */
__bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu,
				       u64 wake_flags, bool *is_idle)
{
	if (!static_branch_likely(&scx_builtin_idle_enabled)) {
		scx_ops_error("built-in idle tracking is disabled");
		goto prev_cpu;
	}

	if (!scx_kf_allowed(SCX_KF_SELECT_CPU))
		goto prev_cpu;

#ifdef CONFIG_SMP
	return scx_select_cpu_dfl(p, prev_cpu, wake_flags, is_idle);
#endif

prev_cpu:
	*is_idle = false;
	return prev_cpu;
}

__bpf_kfunc_end_defs();

BTF_KFUNCS_START(scx_kfunc_ids_select_cpu)
BTF_ID_FLAGS(func, scx_bpf_select_cpu_dfl, KF_RCU)
BTF_KFUNCS_END(scx_kfunc_ids_select_cpu)

static const struct btf_kfunc_id_set scx_kfunc_set_select_cpu = {
	.owner			= THIS_MODULE,
	.set			= &scx_kfunc_ids_select_cpu,
};

static bool scx_dispatch_preamble(struct task_struct *p, u64 enq_flags)
{
	if (!scx_kf_allowed(SCX_KF_ENQUEUE | SCX_KF_DISPATCH))
		return false;

	lockdep_assert_irqs_disabled();

	if (unlikely(!p)) {
		scx_ops_error("called with NULL task");
		return false;
	}

	if (unlikely(enq_flags & __SCX_ENQ_INTERNAL_MASK)) {
		scx_ops_error("invalid enq_flags 0x%llx", enq_flags);
		return false;
	}

	return true;
}

static void scx_dispatch_commit(struct task_struct *p, u64 dsq_id, u64 enq_flags)
{
	struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);
	struct task_struct *ddsp_task;

	ddsp_task = __this_cpu_read(direct_dispatch_task);
	if (ddsp_task) {
		mark_direct_dispatch(ddsp_task, p, dsq_id, enq_flags);
		return;
	}

	if (unlikely(dspc->cursor >= scx_dsp_max_batch)) {
		scx_ops_error("dispatch buffer overflow");
		return;
	}

	dspc->buf[dspc->cursor++] = (struct scx_dsp_buf_ent){
		.task = p,
		.qseq = atomic_long_read(&p->scx.ops_state) & SCX_OPSS_QSEQ_MASK,
		.dsq_id = dsq_id,
		.enq_flags = enq_flags,
	};
}

__bpf_kfunc_start_defs();

/**
 * scx_bpf_dispatch - Dispatch a task into the FIFO queue of a DSQ
 * @p: task_struct to dispatch
 * @dsq_id: DSQ to dispatch to
 * @slice: duration @p can run for in nsecs, 0 to keep the current value
 * @enq_flags: SCX_ENQ_*
 *
 * Dispatch @p into the FIFO queue of the DSQ identified by @dsq_id. It is safe
 * to call this function spuriously. Can be called from ops.enqueue(),
 * ops.select_cpu(), and ops.dispatch().
 *
 * When called from ops.select_cpu() or ops.enqueue(), it's for direct dispatch
 * and @p must match the task being enqueued. Also, %SCX_DSQ_LOCAL_ON can't be
 * used to target the local DSQ of a CPU other than the enqueueing one. Use
 * ops.select_cpu() to be on the target CPU in the first place.
 *
 * When called from ops.select_cpu(), @enq_flags and @dsp_id are stored, and @p
 * will be directly dispatched to the corresponding dispatch queue after
 * ops.select_cpu() returns. If @p is dispatched to SCX_DSQ_LOCAL, it will be
 * dispatched to the local DSQ of the CPU returned by ops.select_cpu().
 * @enq_flags are OR'd with the enqueue flags on the enqueue path before the
 * task is dispatched.
 *
 * When called from ops.dispatch(), there are no restrictions on @p or @dsq_id
 * and this function can be called upto ops.dispatch_max_batch times to dispatch
 * multiple tasks. scx_bpf_dispatch_nr_slots() returns the number of the
 * remaining slots. scx_bpf_consume() flushes the batch and resets the counter.
 *
 * This function doesn't have any locking restrictions and may be called under
 * BPF locks (in the future when BPF introduces more flexible locking).
 *
 * @p is allowed to run for @slice. The scheduling path is triggered on slice
 * exhaustion. If zero, the current residual slice is maintained. If
 * %SCX_SLICE_INF, @p never expires and the BPF scheduler must kick the CPU with
 * scx_bpf_kick_cpu() to trigger scheduling.
 */
__bpf_kfunc void scx_bpf_dispatch(struct task_struct *p, u64 dsq_id, u64 slice,
				  u64 enq_flags)
{
	if (!scx_dispatch_preamble(p, enq_flags))
		return;

	if (slice)
		p->scx.slice = slice;
	else
		p->scx.slice = p->scx.slice ?: 1;

	scx_dispatch_commit(p, dsq_id, enq_flags);
}

/**
 * scx_bpf_dispatch_vtime - Dispatch a task into the vtime priority queue of a DSQ
 * @p: task_struct to dispatch
 * @dsq_id: DSQ to dispatch to
 * @slice: duration @p can run for in nsecs, 0 to keep the current value
 * @vtime: @p's ordering inside the vtime-sorted queue of the target DSQ
 * @enq_flags: SCX_ENQ_*
 *
 * Dispatch @p into the vtime priority queue of the DSQ identified by @dsq_id.
 * Tasks queued into the priority queue are ordered by @vtime and always
 * consumed after the tasks in the FIFO queue. All other aspects are identical
 * to scx_bpf_dispatch().
 *
 * @vtime ordering is according to time_before64() which considers wrapping. A
 * numerically larger vtime may indicate an earlier position in the ordering and
 * vice-versa.
 */
__bpf_kfunc void scx_bpf_dispatch_vtime(struct task_struct *p, u64 dsq_id,
					u64 slice, u64 vtime, u64 enq_flags)
{
	if (!scx_dispatch_preamble(p, enq_flags))
		return;

	if (slice)
		p->scx.slice = slice;
	else
		p->scx.slice = p->scx.slice ?: 1;

	p->scx.dsq_vtime = vtime;

	scx_dispatch_commit(p, dsq_id, enq_flags | SCX_ENQ_DSQ_PRIQ);
}

__bpf_kfunc_end_defs();

BTF_KFUNCS_START(scx_kfunc_ids_enqueue_dispatch)
BTF_ID_FLAGS(func, scx_bpf_dispatch, KF_RCU)
BTF_ID_FLAGS(func, scx_bpf_dispatch_vtime, KF_RCU)
BTF_KFUNCS_END(scx_kfunc_ids_enqueue_dispatch)

static const struct btf_kfunc_id_set scx_kfunc_set_enqueue_dispatch = {
	.owner			= THIS_MODULE,
	.set			= &scx_kfunc_ids_enqueue_dispatch,
};

static bool scx_dispatch_from_dsq(struct bpf_iter_scx_dsq_kern *kit,
				  struct task_struct *p, u64 dsq_id,
				  u64 enq_flags)
{
	struct scx_dispatch_q *src_dsq = kit->dsq, *dst_dsq;
	struct rq *this_rq, *src_rq, *dst_rq, *locked_rq;
	bool dispatched = false;
	bool in_balance;
	unsigned long flags;

	if (!scx_kf_allowed_if_unlocked() && !scx_kf_allowed(SCX_KF_DISPATCH))
		return false;

	/*
	 * Can be called from either ops.dispatch() locking this_rq() or any
	 * context where no rq lock is held. If latter, lock @p's task_rq which
	 * we'll likely need anyway.
	 */
	src_rq = task_rq(p);

	local_irq_save(flags);
	this_rq = this_rq();
	in_balance = this_rq->scx.flags & SCX_RQ_IN_BALANCE;

	if (in_balance) {
		if (this_rq != src_rq) {
			raw_spin_rq_unlock(this_rq);
			raw_spin_rq_lock(src_rq);
		}
	} else {
		raw_spin_rq_lock(src_rq);
	}

	locked_rq = src_rq;
	raw_spin_lock(&src_dsq->lock);

	/*
	 * Did someone else get to it? @p could have already left $src_dsq, got
	 * re-enqueud, or be in the process of being consumed by someone else.
	 */
	if (unlikely(p->scx.dsq != src_dsq ||
		     u32_before(kit->cursor.priv, p->scx.dsq_seq) ||
		     p->scx.holding_cpu >= 0) ||
	    WARN_ON_ONCE(src_rq != task_rq(p))) {
		raw_spin_unlock(&src_dsq->lock);
		goto out;
	}

	/* @p is still on $src_dsq and stable, determine the destination */
	dst_dsq = find_dsq_for_dispatch(this_rq, dsq_id, p);

	if (dst_dsq->id == SCX_DSQ_LOCAL) {
		dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq);
		if (!task_can_run_on_remote_rq(p, dst_rq, true)) {
			dst_dsq = find_global_dsq(p);
			dst_rq = src_rq;
		}
	} else {
		/* no need to migrate if destination is a non-local DSQ */
		dst_rq = src_rq;
	}

	/*
	 * Move @p into $dst_dsq. If $dst_dsq is the local DSQ of a different
	 * CPU, @p will be migrated.
	 */
	if (dst_dsq->id == SCX_DSQ_LOCAL) {
		/* @p is going from a non-local DSQ to a local DSQ */
		if (src_rq == dst_rq) {
			task_unlink_from_dsq(p, src_dsq);
			move_local_task_to_local_dsq(p, enq_flags,
						     src_dsq, dst_rq);
			raw_spin_unlock(&src_dsq->lock);
		} else {
			raw_spin_unlock(&src_dsq->lock);
			move_remote_task_to_local_dsq(p, enq_flags,
						      src_rq, dst_rq);
			locked_rq = dst_rq;
		}
	} else {
		/*
		 * @p is going from a non-local DSQ to a non-local DSQ. As
		 * $src_dsq is already locked, do an abbreviated dequeue.
		 */
		task_unlink_from_dsq(p, src_dsq);
		p->scx.dsq = NULL;
		raw_spin_unlock(&src_dsq->lock);

		if (kit->cursor.flags & __SCX_DSQ_ITER_HAS_VTIME)
			p->scx.dsq_vtime = kit->vtime;
		dispatch_enqueue(dst_dsq, p, enq_flags);
	}

	if (kit->cursor.flags & __SCX_DSQ_ITER_HAS_SLICE)
		p->scx.slice = kit->slice;

	dispatched = true;
out:
	if (in_balance) {
		if (this_rq != locked_rq) {
			raw_spin_rq_unlock(locked_rq);
			raw_spin_rq_lock(this_rq);
		}
	} else {
		raw_spin_rq_unlock_irqrestore(locked_rq, flags);
	}

	kit->cursor.flags &= ~(__SCX_DSQ_ITER_HAS_SLICE |
			       __SCX_DSQ_ITER_HAS_VTIME);
	return dispatched;
}

__bpf_kfunc_start_defs();

/**
 * scx_bpf_dispatch_nr_slots - Return the number of remaining dispatch slots
 *
 * Can only be called from ops.dispatch().
 */
__bpf_kfunc u32 scx_bpf_dispatch_nr_slots(void)
{
	if (!scx_kf_allowed(SCX_KF_DISPATCH))
		return 0;

	return scx_dsp_max_batch - __this_cpu_read(scx_dsp_ctx->cursor);
}

/**
 * scx_bpf_dispatch_cancel - Cancel the latest dispatch
 *
 * Cancel the latest dispatch. Can be called multiple times to cancel further
 * dispatches. Can only be called from ops.dispatch().
 */
__bpf_kfunc void scx_bpf_dispatch_cancel(void)
{
	struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);

	if (!scx_kf_allowed(SCX_KF_DISPATCH))
		return;

	if (dspc->cursor > 0)
		dspc->cursor--;
	else
		scx_ops_error("dispatch buffer underflow");
}

/**
 * scx_bpf_consume - Transfer a task from a DSQ to the current CPU's local DSQ
 * @dsq_id: DSQ to consume
 *
 * Consume a task from the non-local DSQ identified by @dsq_id and transfer it
 * to the current CPU's local DSQ for execution. Can only be called from
 * ops.dispatch().
 *
 * This function flushes the in-flight dispatches from scx_bpf_dispatch() before
 * trying to consume the specified DSQ. It may also grab rq locks and thus can't
 * be called under any BPF locks.
 *
 * Returns %true if a task has been consumed, %false if there isn't any task to
 * consume.
 */
__bpf_kfunc bool scx_bpf_consume(u64 dsq_id)
{
	struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);
	struct scx_dispatch_q *dsq;

	if (!scx_kf_allowed(SCX_KF_DISPATCH))
		return false;

	flush_dispatch_buf(dspc->rq);

	dsq = find_user_dsq(dsq_id);
	if (unlikely(!dsq)) {
		scx_ops_error("invalid DSQ ID 0x%016llx", dsq_id);
		return false;
	}

	if (consume_dispatch_q(dspc->rq, dsq)) {
		/*
		 * A successfully consumed task can be dequeued before it starts
		 * running while the CPU is trying to migrate other dispatched
		 * tasks. Bump nr_tasks to tell balance_scx() to retry on empty
		 * local DSQ.
		 */
		dspc->nr_tasks++;
		return true;
	} else {
		return false;
	}
}

/**
 * scx_bpf_dispatch_from_dsq_set_slice - Override slice when dispatching from DSQ
 * @it__iter: DSQ iterator in progress
 * @slice: duration the dispatched task can run for in nsecs
 *
 * Override the slice of the next task that will be dispatched from @it__iter
 * using scx_bpf_dispatch_from_dsq[_vtime](). If this function is not called,
 * the previous slice duration is kept.
 */
__bpf_kfunc void scx_bpf_dispatch_from_dsq_set_slice(
				struct bpf_iter_scx_dsq *it__iter, u64 slice)
{
	struct bpf_iter_scx_dsq_kern *kit = (void *)it__iter;

	kit->slice = slice;
	kit->cursor.flags |= __SCX_DSQ_ITER_HAS_SLICE;
}

/**
 * scx_bpf_dispatch_from_dsq_set_vtime - Override vtime when dispatching from DSQ
 * @it__iter: DSQ iterator in progress
 * @vtime: task's ordering inside the vtime-sorted queue of the target DSQ
 *
 * Override the vtime of the next task that will be dispatched from @it__iter
 * using scx_bpf_dispatch_from_dsq_vtime(). If this function is not called, the
 * previous slice vtime is kept. If scx_bpf_dispatch_from_dsq() is used to
 * dispatch the next task, the override is ignored and cleared.
 */
__bpf_kfunc void scx_bpf_dispatch_from_dsq_set_vtime(
				struct bpf_iter_scx_dsq *it__iter, u64 vtime)
{
	struct bpf_iter_scx_dsq_kern *kit = (void *)it__iter;

	kit->vtime = vtime;
	kit->cursor.flags |= __SCX_DSQ_ITER_HAS_VTIME;
}

/**
 * scx_bpf_dispatch_from_dsq - Move a task from DSQ iteration to a DSQ
 * @it__iter: DSQ iterator in progress
 * @p: task to transfer
 * @dsq_id: DSQ to move @p to
 * @enq_flags: SCX_ENQ_*
 *
 * Transfer @p which is on the DSQ currently iterated by @it__iter to the DSQ
 * specified by @dsq_id. All DSQs - local DSQs, global DSQ and user DSQs - can
 * be the destination.
 *
 * For the transfer to be successful, @p must still be on the DSQ and have been
 * queued before the DSQ iteration started. This function doesn't care whether
 * @p was obtained from the DSQ iteration. @p just has to be on the DSQ and have
 * been queued before the iteration started.
 *
 * @p's slice is kept by default. Use scx_bpf_dispatch_from_dsq_set_slice() to
 * update.
 *
 * Can be called from ops.dispatch() or any BPF context which doesn't hold a rq
 * lock (e.g. BPF timers or SYSCALL programs).
 *
 * Returns %true if @p has been consumed, %false if @p had already been consumed
 * or dequeued.
 */
__bpf_kfunc bool scx_bpf_dispatch_from_dsq(struct bpf_iter_scx_dsq *it__iter,
					   struct task_struct *p, u64 dsq_id,
					   u64 enq_flags)
{
	return scx_dispatch_from_dsq((struct bpf_iter_scx_dsq_kern *)it__iter,
				     p, dsq_id, enq_flags);
}

/**
 * scx_bpf_dispatch_vtime_from_dsq - Move a task from DSQ iteration to a PRIQ DSQ
 * @it__iter: DSQ iterator in progress
 * @p: task to transfer
 * @dsq_id: DSQ to move @p to
 * @enq_flags: SCX_ENQ_*
 *
 * Transfer @p which is on the DSQ currently iterated by @it__iter to the
 * priority queue of the DSQ specified by @dsq_id. The destination must be a
 * user DSQ as only user DSQs support priority queue.
 *
 * @p's slice and vtime are kept by default. Use
 * scx_bpf_dispatch_from_dsq_set_slice() and
 * scx_bpf_dispatch_from_dsq_set_vtime() to update.
 *
 * All other aspects are identical to scx_bpf_dispatch_from_dsq(). See
 * scx_bpf_dispatch_vtime() for more information on @vtime.
 */
__bpf_kfunc bool scx_bpf_dispatch_vtime_from_dsq(struct bpf_iter_scx_dsq *it__iter,
						 struct task_struct *p, u64 dsq_id,
						 u64 enq_flags)
{
	return scx_dispatch_from_dsq((struct bpf_iter_scx_dsq_kern *)it__iter,
				     p, dsq_id, enq_flags | SCX_ENQ_DSQ_PRIQ);
}

__bpf_kfunc_end_defs();

BTF_KFUNCS_START(scx_kfunc_ids_dispatch)
BTF_ID_FLAGS(func, scx_bpf_dispatch_nr_slots)
BTF_ID_FLAGS(func, scx_bpf_dispatch_cancel)
BTF_ID_FLAGS(func, scx_bpf_consume)
BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq_set_slice)
BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq_set_vtime)
BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq, KF_RCU)
BTF_ID_FLAGS(func, scx_bpf_dispatch_vtime_from_dsq, KF_RCU)
BTF_KFUNCS_END(scx_kfunc_ids_dispatch)

static const struct btf_kfunc_id_set scx_kfunc_set_dispatch = {
	.owner			= THIS_MODULE,
	.set			= &scx_kfunc_ids_dispatch,
};

__bpf_kfunc_start_defs();

/**
 * scx_bpf_reenqueue_local - Re-enqueue tasks on a local DSQ
 *
 * Iterate over all of the tasks currently enqueued on the local DSQ of the
 * caller's CPU, and re-enqueue them in the BPF scheduler. Returns the number of
 * processed tasks. Can only be called from ops.cpu_release().
 */
__bpf_kfunc u32 scx_bpf_reenqueue_local(void)
{
	LIST_HEAD(tasks);
	u32 nr_enqueued = 0;
	struct rq *rq;
	struct task_struct *p, *n;

	if (!scx_kf_allowed(SCX_KF_CPU_RELEASE))
		return 0;

	rq = cpu_rq(smp_processor_id());
	lockdep_assert_rq_held(rq);

	/*
	 * The BPF scheduler may choose to dispatch tasks back to
	 * @rq->scx.local_dsq. Move all candidate tasks off to a private list
	 * first to avoid processing the same tasks repeatedly.
	 */
	list_for_each_entry_safe(p, n, &rq->scx.local_dsq.list,
				 scx.dsq_list.node) {
		/*
		 * If @p is being migrated, @p's current CPU may not agree with
		 * its allowed CPUs and the migration_cpu_stop is about to
		 * deactivate and re-activate @p anyway. Skip re-enqueueing.
		 *
		 * While racing sched property changes may also dequeue and
		 * re-enqueue a migrating task while its current CPU and allowed
		 * CPUs disagree, they use %ENQUEUE_RESTORE which is bypassed to
		 * the current local DSQ for running tasks and thus are not
		 * visible to the BPF scheduler.
		 */
		if (p->migration_pending)
			continue;

		dispatch_dequeue(rq, p);
		list_add_tail(&p->scx.dsq_list.node, &tasks);
	}

	list_for_each_entry_safe(p, n, &tasks, scx.dsq_list.node) {
		list_del_init(&p->scx.dsq_list.node);
		do_enqueue_task(rq, p, SCX_ENQ_REENQ, -1);
		nr_enqueued++;
	}

	return nr_enqueued;
}

__bpf_kfunc_end_defs();

BTF_KFUNCS_START(scx_kfunc_ids_cpu_release)
BTF_ID_FLAGS(func, scx_bpf_reenqueue_local)
BTF_KFUNCS_END(scx_kfunc_ids_cpu_release)

static const struct btf_kfunc_id_set scx_kfunc_set_cpu_release = {
	.owner			= THIS_MODULE,
	.set			= &scx_kfunc_ids_cpu_release,
};

__bpf_kfunc_start_defs();

/**
 * scx_bpf_create_dsq - Create a custom DSQ
 * @dsq_id: DSQ to create
 * @node: NUMA node to allocate from
 *
 * Create a custom DSQ identified by @dsq_id. Can be called from any sleepable
 * scx callback, and any BPF_PROG_TYPE_SYSCALL prog.
 */
__bpf_kfunc s32 scx_bpf_create_dsq(u64 dsq_id, s32 node)
{
	if (unlikely(node >= (int)nr_node_ids ||
		     (node < 0 && node != NUMA_NO_NODE)))
		return -EINVAL;
	return PTR_ERR_OR_ZERO(create_dsq(dsq_id, node));
}

__bpf_kfunc_end_defs();

BTF_KFUNCS_START(scx_kfunc_ids_unlocked)
BTF_ID_FLAGS(func, scx_bpf_create_dsq, KF_SLEEPABLE)
BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq, KF_RCU)
BTF_ID_FLAGS(func, scx_bpf_dispatch_vtime_from_dsq, KF_RCU)
BTF_KFUNCS_END(scx_kfunc_ids_unlocked)

static const struct btf_kfunc_id_set scx_kfunc_set_unlocked = {
	.owner			= THIS_MODULE,
	.set			= &scx_kfunc_ids_unlocked,
};

__bpf_kfunc_start_defs();

/**
 * scx_bpf_kick_cpu - Trigger reschedule on a CPU
 * @cpu: cpu to kick
 * @flags: %SCX_KICK_* flags
 *
 * Kick @cpu into rescheduling. This can be used to wake up an idle CPU or
 * trigger rescheduling on a busy CPU. This can be called from any online
 * scx_ops operation and the actual kicking is performed asynchronously through
 * an irq work.
 */
__bpf_kfunc void scx_bpf_kick_cpu(s32 cpu, u64 flags)
{
	struct rq *this_rq;
	unsigned long irq_flags;

	if (!ops_cpu_valid(cpu, NULL))
		return;

	local_irq_save(irq_flags);

	this_rq = this_rq();

	/*
	 * While bypassing for PM ops, IRQ handling may not be online which can
	 * lead to irq_work_queue() malfunction such as infinite busy wait for
	 * IRQ status update. Suppress kicking.
	 */
	if (scx_rq_bypassing(this_rq))
		goto out;

	/*
	 * Actual kicking is bounced to kick_cpus_irq_workfn() to avoid nesting
	 * rq locks. We can probably be smarter and avoid bouncing if called
	 * from ops which don't hold a rq lock.
	 */
	if (flags & SCX_KICK_IDLE) {
		struct rq *target_rq = cpu_rq(cpu);

		if (unlikely(flags & (SCX_KICK_PREEMPT | SCX_KICK_WAIT)))
			scx_ops_error("PREEMPT/WAIT cannot be used with SCX_KICK_IDLE");

		if (raw_spin_rq_trylock(target_rq)) {
			if (can_skip_idle_kick(target_rq)) {
				raw_spin_rq_unlock(target_rq);
				goto out;
			}
			raw_spin_rq_unlock(target_rq);
		}
		cpumask_set_cpu(cpu, this_rq->scx.cpus_to_kick_if_idle);
	} else {
		cpumask_set_cpu(cpu, this_rq->scx.cpus_to_kick);

		if (flags & SCX_KICK_PREEMPT)
			cpumask_set_cpu(cpu, this_rq->scx.cpus_to_preempt);
		if (flags & SCX_KICK_WAIT)
			cpumask_set_cpu(cpu, this_rq->scx.cpus_to_wait);
	}

	irq_work_queue(&this_rq->scx.kick_cpus_irq_work);
out:
	local_irq_restore(irq_flags);
}

/**
 * scx_bpf_dsq_nr_queued - Return the number of queued tasks
 * @dsq_id: id of the DSQ
 *
 * Return the number of tasks in the DSQ matching @dsq_id. If not found,
 * -%ENOENT is returned.
 */
__bpf_kfunc s32 scx_bpf_dsq_nr_queued(u64 dsq_id)
{
	struct scx_dispatch_q *dsq;
	s32 ret;

	preempt_disable();

	if (dsq_id == SCX_DSQ_LOCAL) {
		ret = READ_ONCE(this_rq()->scx.local_dsq.nr);
		goto out;
	} else if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) {
		s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK;

		if (ops_cpu_valid(cpu, NULL)) {
			ret = READ_ONCE(cpu_rq(cpu)->scx.local_dsq.nr);
			goto out;
		}
	} else {
		dsq = find_user_dsq(dsq_id);
		if (dsq) {
			ret = READ_ONCE(dsq->nr);
			goto out;
		}
	}
	ret = -ENOENT;
out:
	preempt_enable();
	return ret;
}

/**
 * scx_bpf_destroy_dsq - Destroy a custom DSQ
 * @dsq_id: DSQ to destroy
 *
 * Destroy the custom DSQ identified by @dsq_id. Only DSQs created with
 * scx_bpf_create_dsq() can be destroyed. The caller must ensure that the DSQ is
 * empty and no further tasks are dispatched to it. Ignored if called on a DSQ
 * which doesn't exist. Can be called from any online scx_ops operations.
 */
__bpf_kfunc void scx_bpf_destroy_dsq(u64 dsq_id)
{
	destroy_dsq(dsq_id);
}

/**
 * bpf_iter_scx_dsq_new - Create a DSQ iterator
 * @it: iterator to initialize
 * @dsq_id: DSQ to iterate
 * @flags: %SCX_DSQ_ITER_*
 *
 * Initialize BPF iterator @it which can be used with bpf_for_each() to walk
 * tasks in the DSQ specified by @dsq_id. Iteration using @it only includes
 * tasks which are already queued when this function is invoked.
 */
__bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id,
				     u64 flags)
{
	struct bpf_iter_scx_dsq_kern *kit = (void *)it;

	BUILD_BUG_ON(sizeof(struct bpf_iter_scx_dsq_kern) >
		     sizeof(struct bpf_iter_scx_dsq));
	BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) !=
		     __alignof__(struct bpf_iter_scx_dsq));

	if (flags & ~__SCX_DSQ_ITER_USER_FLAGS)
		return -EINVAL;

	kit->dsq = find_user_dsq(dsq_id);
	if (!kit->dsq)
		return -ENOENT;

	INIT_LIST_HEAD(&kit->cursor.node);
	kit->cursor.flags |= SCX_DSQ_LNODE_ITER_CURSOR | flags;
	kit->cursor.priv = READ_ONCE(kit->dsq->seq);

	return 0;
}

/**
 * bpf_iter_scx_dsq_next - Progress a DSQ iterator
 * @it: iterator to progress
 *
 * Return the next task. See bpf_iter_scx_dsq_new().
 */
__bpf_kfunc struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *it)
{
	struct bpf_iter_scx_dsq_kern *kit = (void *)it;
	bool rev = kit->cursor.flags & SCX_DSQ_ITER_REV;
	struct task_struct *p;
	unsigned long flags;

	if (!kit->dsq)
		return NULL;

	raw_spin_lock_irqsave(&kit->dsq->lock, flags);

	if (list_empty(&kit->cursor.node))
		p = NULL;
	else
		p = container_of(&kit->cursor, struct task_struct, scx.dsq_list);

	/*
	 * Only tasks which were queued before the iteration started are
	 * visible. This bounds BPF iterations and guarantees that vtime never
	 * jumps in the other direction while iterating.
	 */
	do {
		p = nldsq_next_task(kit->dsq, p, rev);
	} while (p && unlikely(u32_before(kit->cursor.priv, p->scx.dsq_seq)));

	if (p) {
		if (rev)
			list_move_tail(&kit->cursor.node, &p->scx.dsq_list.node);
		else
			list_move(&kit->cursor.node, &p->scx.dsq_list.node);
	} else {
		list_del_init(&kit->cursor.node);
	}

	raw_spin_unlock_irqrestore(&kit->dsq->lock, flags);

	return p;
}

/**
 * bpf_iter_scx_dsq_destroy - Destroy a DSQ iterator
 * @it: iterator to destroy
 *
 * Undo scx_iter_scx_dsq_new().
 */
__bpf_kfunc void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it)
{
	struct bpf_iter_scx_dsq_kern *kit = (void *)it;

	if (!kit->dsq)
		return;

	if (!list_empty(&kit->cursor.node)) {
		unsigned long flags;

		raw_spin_lock_irqsave(&kit->dsq->lock, flags);
		list_del_init(&kit->cursor.node);
		raw_spin_unlock_irqrestore(&kit->dsq->lock, flags);
	}
	kit->dsq = NULL;
}

__bpf_kfunc_end_defs();

static s32 __bstr_format(u64 *data_buf, char *line_buf, size_t line_size,
			 char *fmt, unsigned long long *data, u32 data__sz)
{
	struct bpf_bprintf_data bprintf_data = { .get_bin_args = true };
	s32 ret;

	if (data__sz % 8 || data__sz > MAX_BPRINTF_VARARGS * 8 ||
	    (data__sz && !data)) {
		scx_ops_error("invalid data=%p and data__sz=%u",
			      (void *)data, data__sz);
		return -EINVAL;
	}

	ret = copy_from_kernel_nofault(data_buf, data, data__sz);
	if (ret < 0) {
		scx_ops_error("failed to read data fields (%d)", ret);
		return ret;
	}

	ret = bpf_bprintf_prepare(fmt, UINT_MAX, data_buf, data__sz / 8,
				  &bprintf_data);
	if (ret < 0) {
		scx_ops_error("format preparation failed (%d)", ret);
		return ret;
	}

	ret = bstr_printf(line_buf, line_size, fmt,
			  bprintf_data.bin_args);
	bpf_bprintf_cleanup(&bprintf_data);
	if (ret < 0) {
		scx_ops_error("(\"%s\", %p, %u) failed to format",
			      fmt, data, data__sz);
		return ret;
	}

	return ret;
}

static s32 bstr_format(struct scx_bstr_buf *buf,
		       char *fmt, unsigned long long *data, u32 data__sz)
{
	return __bstr_format(buf->data, buf->line, sizeof(buf->line),
			     fmt, data, data__sz);
}

__bpf_kfunc_start_defs();

/**
 * scx_bpf_exit_bstr - Gracefully exit the BPF scheduler.
 * @exit_code: Exit value to pass to user space via struct scx_exit_info.
 * @fmt: error message format string
 * @data: format string parameters packaged using ___bpf_fill() macro
 * @data__sz: @data len, must end in '__sz' for the verifier
 *
 * Indicate that the BPF scheduler wants to exit gracefully, and initiate ops
 * disabling.
 */
__bpf_kfunc void scx_bpf_exit_bstr(s64 exit_code, char *fmt,
				   unsigned long long *data, u32 data__sz)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&scx_exit_bstr_buf_lock, flags);
	if (bstr_format(&scx_exit_bstr_buf, fmt, data, data__sz) >= 0)
		scx_ops_exit_kind(SCX_EXIT_UNREG_BPF, exit_code, "%s",
				  scx_exit_bstr_buf.line);
	raw_spin_unlock_irqrestore(&scx_exit_bstr_buf_lock, flags);
}

/**
 * scx_bpf_error_bstr - Indicate fatal error
 * @fmt: error message format string
 * @data: format string parameters packaged using ___bpf_fill() macro
 * @data__sz: @data len, must end in '__sz' for the verifier
 *
 * Indicate that the BPF scheduler encountered a fatal error and initiate ops
 * disabling.
 */
__bpf_kfunc void scx_bpf_error_bstr(char *fmt, unsigned long long *data,
				    u32 data__sz)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&scx_exit_bstr_buf_lock, flags);
	if (bstr_format(&scx_exit_bstr_buf, fmt, data, data__sz) >= 0)
		scx_ops_exit_kind(SCX_EXIT_ERROR_BPF, 0, "%s",
				  scx_exit_bstr_buf.line);
	raw_spin_unlock_irqrestore(&scx_exit_bstr_buf_lock, flags);
}

/**
 * scx_bpf_dump - Generate extra debug dump specific to the BPF scheduler
 * @fmt: format string
 * @data: format string parameters packaged using ___bpf_fill() macro
 * @data__sz: @data len, must end in '__sz' for the verifier
 *
 * To be called through scx_bpf_dump() helper from ops.dump(), dump_cpu() and
 * dump_task() to generate extra debug dump specific to the BPF scheduler.
 *
 * The extra dump may be multiple lines. A single line may be split over
 * multiple calls. The last line is automatically terminated.
 */
__bpf_kfunc void scx_bpf_dump_bstr(char *fmt, unsigned long long *data,
				   u32 data__sz)
{
	struct scx_dump_data *dd = &scx_dump_data;
	struct scx_bstr_buf *buf = &dd->buf;
	s32 ret;

	if (raw_smp_processor_id() != dd->cpu) {
		scx_ops_error("scx_bpf_dump() must only be called from ops.dump() and friends");
		return;
	}

	/* append the formatted string to the line buf */
	ret = __bstr_format(buf->data, buf->line + dd->cursor,
			    sizeof(buf->line) - dd->cursor, fmt, data, data__sz);
	if (ret < 0) {
		dump_line(dd->s, "%s[!] (\"%s\", %p, %u) failed to format (%d)",
			  dd->prefix, fmt, data, data__sz, ret);
		return;
	}

	dd->cursor += ret;
	dd->cursor = min_t(s32, dd->cursor, sizeof(buf->line));

	if (!dd->cursor)
		return;

	/*
	 * If the line buf overflowed or ends in a newline, flush it into the
	 * dump. This is to allow the caller to generate a single line over
	 * multiple calls. As ops_dump_flush() can also handle multiple lines in
	 * the line buf, the only case which can lead to an unexpected
	 * truncation is when the caller keeps generating newlines in the middle
	 * instead of the end consecutively. Don't do that.
	 */
	if (dd->cursor >= sizeof(buf->line) || buf->line[dd->cursor - 1] == '\n')
		ops_dump_flush();
}

/**
 * scx_bpf_cpuperf_cap - Query the maximum relative capacity of a CPU
 * @cpu: CPU of interest
 *
 * Return the maximum relative capacity of @cpu in relation to the most
 * performant CPU in the system. The return value is in the range [1,
 * %SCX_CPUPERF_ONE]. See scx_bpf_cpuperf_cur().
 */
__bpf_kfunc u32 scx_bpf_cpuperf_cap(s32 cpu)
{
	if (ops_cpu_valid(cpu, NULL))
		return arch_scale_cpu_capacity(cpu);
	else
		return SCX_CPUPERF_ONE;
}

/**
 * scx_bpf_cpuperf_cur - Query the current relative performance of a CPU
 * @cpu: CPU of interest
 *
 * Return the current relative performance of @cpu in relation to its maximum.
 * The return value is in the range [1, %SCX_CPUPERF_ONE].
 *
 * The current performance level of a CPU in relation to the maximum performance
 * available in the system can be calculated as follows:
 *
 *   scx_bpf_cpuperf_cap() * scx_bpf_cpuperf_cur() / %SCX_CPUPERF_ONE
 *
 * The result is in the range [1, %SCX_CPUPERF_ONE].
 */
__bpf_kfunc u32 scx_bpf_cpuperf_cur(s32 cpu)
{
	if (ops_cpu_valid(cpu, NULL))
		return arch_scale_freq_capacity(cpu);
	else
		return SCX_CPUPERF_ONE;
}

/**
 * scx_bpf_cpuperf_set - Set the relative performance target of a CPU
 * @cpu: CPU of interest
 * @perf: target performance level [0, %SCX_CPUPERF_ONE]
 * @flags: %SCX_CPUPERF_* flags
 *
 * Set the target performance level of @cpu to @perf. @perf is in linear
 * relative scale between 0 and %SCX_CPUPERF_ONE. This determines how the
 * schedutil cpufreq governor chooses the target frequency.
 *
 * The actual performance level chosen, CPU grouping, and the overhead and
 * latency of the operations are dependent on the hardware and cpufreq driver in
 * use. Consult hardware and cpufreq documentation for more information. The
 * current performance level can be monitored using scx_bpf_cpuperf_cur().
 */
__bpf_kfunc void scx_bpf_cpuperf_set(s32 cpu, u32 perf)
{
	if (unlikely(perf > SCX_CPUPERF_ONE)) {
		scx_ops_error("Invalid cpuperf target %u for CPU %d", perf, cpu);
		return;
	}

	if (ops_cpu_valid(cpu, NULL)) {
		struct rq *rq = cpu_rq(cpu);

		rq->scx.cpuperf_target = perf;

		rcu_read_lock_sched_notrace();
		cpufreq_update_util(cpu_rq(cpu), 0);
		rcu_read_unlock_sched_notrace();
	}
}

/**
 * scx_bpf_nr_cpu_ids - Return the number of possible CPU IDs
 *
 * All valid CPU IDs in the system are smaller than the returned value.
 */
__bpf_kfunc u32 scx_bpf_nr_cpu_ids(void)
{
	return nr_cpu_ids;
}

/**
 * scx_bpf_get_possible_cpumask - Get a referenced kptr to cpu_possible_mask
 */
__bpf_kfunc const struct cpumask *scx_bpf_get_possible_cpumask(void)
{
	return cpu_possible_mask;
}

/**
 * scx_bpf_get_online_cpumask - Get a referenced kptr to cpu_online_mask
 */
__bpf_kfunc const struct cpumask *scx_bpf_get_online_cpumask(void)
{
	return cpu_online_mask;
}

/**
 * scx_bpf_put_cpumask - Release a possible/online cpumask
 * @cpumask: cpumask to release
 */
__bpf_kfunc void scx_bpf_put_cpumask(const struct cpumask *cpumask)
{
	/*
	 * Empty function body because we aren't actually acquiring or releasing
	 * a reference to a global cpumask, which is read-only in the caller and
	 * is never released. The acquire / release semantics here are just used
	 * to make the cpumask is a trusted pointer in the caller.
	 */
}

/**
 * scx_bpf_get_idle_cpumask - Get a referenced kptr to the idle-tracking
 * per-CPU cpumask.
 *
 * Returns NULL if idle tracking is not enabled, or running on a UP kernel.
 */
__bpf_kfunc const struct cpumask *scx_bpf_get_idle_cpumask(void)
{
	if (!static_branch_likely(&scx_builtin_idle_enabled)) {
		scx_ops_error("built-in idle tracking is disabled");
		return cpu_none_mask;
	}

#ifdef CONFIG_SMP
	return idle_masks.cpu;
#else
	return cpu_none_mask;
#endif
}

/**
 * scx_bpf_get_idle_smtmask - Get a referenced kptr to the idle-tracking,
 * per-physical-core cpumask. Can be used to determine if an entire physical
 * core is free.
 *
 * Returns NULL if idle tracking is not enabled, or running on a UP kernel.
 */
__bpf_kfunc const struct cpumask *scx_bpf_get_idle_smtmask(void)
{
	if (!static_branch_likely(&scx_builtin_idle_enabled)) {
		scx_ops_error("built-in idle tracking is disabled");
		return cpu_none_mask;
	}

#ifdef CONFIG_SMP
	if (sched_smt_active())
		return idle_masks.smt;
	else
		return idle_masks.cpu;
#else
	return cpu_none_mask;
#endif
}

/**
 * scx_bpf_put_idle_cpumask - Release a previously acquired referenced kptr to
 * either the percpu, or SMT idle-tracking cpumask.
 */
__bpf_kfunc void scx_bpf_put_idle_cpumask(const struct cpumask *idle_mask)
{
	/*
	 * Empty function body because we aren't actually acquiring or releasing
	 * a reference to a global idle cpumask, which is read-only in the
	 * caller and is never released. The acquire / release semantics here
	 * are just used to make the cpumask a trusted pointer in the caller.
	 */
}

/**
 * scx_bpf_test_and_clear_cpu_idle - Test and clear @cpu's idle state
 * @cpu: cpu to test and clear idle for
 *
 * Returns %true if @cpu was idle and its idle state was successfully cleared.
 * %false otherwise.
 *
 * Unavailable if ops.update_idle() is implemented and
 * %SCX_OPS_KEEP_BUILTIN_IDLE is not set.
 */
__bpf_kfunc bool scx_bpf_test_and_clear_cpu_idle(s32 cpu)
{
	if (!static_branch_likely(&scx_builtin_idle_enabled)) {
		scx_ops_error("built-in idle tracking is disabled");
		return false;
	}

	if (ops_cpu_valid(cpu, NULL))
		return test_and_clear_cpu_idle(cpu);
	else
		return false;
}

/**
 * scx_bpf_pick_idle_cpu - Pick and claim an idle cpu
 * @cpus_allowed: Allowed cpumask
 * @flags: %SCX_PICK_IDLE_CPU_* flags
 *
 * Pick and claim an idle cpu in @cpus_allowed. Returns the picked idle cpu
 * number on success. -%EBUSY if no matching cpu was found.
 *
 * Idle CPU tracking may race against CPU scheduling state transitions. For
 * example, this function may return -%EBUSY as CPUs are transitioning into the
 * idle state. If the caller then assumes that there will be dispatch events on
 * the CPUs as they were all busy, the scheduler may end up stalling with CPUs
 * idling while there are pending tasks. Use scx_bpf_pick_any_cpu() and
 * scx_bpf_kick_cpu() to guarantee that there will be at least one dispatch
 * event in the near future.
 *
 * Unavailable if ops.update_idle() is implemented and
 * %SCX_OPS_KEEP_BUILTIN_IDLE is not set.
 */
__bpf_kfunc s32 scx_bpf_pick_idle_cpu(const struct cpumask *cpus_allowed,
				      u64 flags)
{
	if (!static_branch_likely(&scx_builtin_idle_enabled)) {
		scx_ops_error("built-in idle tracking is disabled");
		return -EBUSY;
	}

	return scx_pick_idle_cpu(cpus_allowed, flags);
}

/**
 * scx_bpf_pick_any_cpu - Pick and claim an idle cpu if available or pick any CPU
 * @cpus_allowed: Allowed cpumask
 * @flags: %SCX_PICK_IDLE_CPU_* flags
 *
 * Pick and claim an idle cpu in @cpus_allowed. If none is available, pick any
 * CPU in @cpus_allowed. Guaranteed to succeed and returns the picked idle cpu
 * number if @cpus_allowed is not empty. -%EBUSY is returned if @cpus_allowed is
 * empty.
 *
 * If ops.update_idle() is implemented and %SCX_OPS_KEEP_BUILTIN_IDLE is not
 * set, this function can't tell which CPUs are idle and will always pick any
 * CPU.
 */
__bpf_kfunc s32 scx_bpf_pick_any_cpu(const struct cpumask *cpus_allowed,
				     u64 flags)
{
	s32 cpu;

	if (static_branch_likely(&scx_builtin_idle_enabled)) {
		cpu = scx_pick_idle_cpu(cpus_allowed, flags);
		if (cpu >= 0)
			return cpu;
	}

	cpu = cpumask_any_distribute(cpus_allowed);
	if (cpu < nr_cpu_ids)
		return cpu;
	else
		return -EBUSY;
}

/**
 * scx_bpf_task_running - Is task currently running?
 * @p: task of interest
 */
__bpf_kfunc bool scx_bpf_task_running(const struct task_struct *p)
{
	return task_rq(p)->curr == p;
}

/**
 * scx_bpf_task_cpu - CPU a task is currently associated with
 * @p: task of interest
 */
__bpf_kfunc s32 scx_bpf_task_cpu(const struct task_struct *p)
{
	return task_cpu(p);
}

/**
 * scx_bpf_cpu_rq - Fetch the rq of a CPU
 * @cpu: CPU of the rq
 */
__bpf_kfunc struct rq *scx_bpf_cpu_rq(s32 cpu)
{
	if (!ops_cpu_valid(cpu, NULL))
		return NULL;

	return cpu_rq(cpu);
}

/**
 * scx_bpf_task_cgroup - Return the sched cgroup of a task
 * @p: task of interest
 *
 * @p->sched_task_group->css.cgroup represents the cgroup @p is associated with
 * from the scheduler's POV. SCX operations should use this function to
 * determine @p's current cgroup as, unlike following @p->cgroups,
 * @p->sched_task_group is protected by @p's rq lock and thus atomic w.r.t. all
 * rq-locked operations. Can be called on the parameter tasks of rq-locked
 * operations. The restriction guarantees that @p's rq is locked by the caller.
 */
#ifdef CONFIG_CGROUP_SCHED
__bpf_kfunc struct cgroup *scx_bpf_task_cgroup(struct task_struct *p)
{
	struct task_group *tg = p->sched_task_group;
	struct cgroup *cgrp = &cgrp_dfl_root.cgrp;

	if (!scx_kf_allowed_on_arg_tasks(__SCX_KF_RQ_LOCKED, p))
		goto out;

	/*
	 * A task_group may either be a cgroup or an autogroup. In the latter
	 * case, @tg->css.cgroup is %NULL. A task_group can't become the other
	 * kind once created.
	 */
	if (tg && tg->css.cgroup)
		cgrp = tg->css.cgroup;
	else
		cgrp = &cgrp_dfl_root.cgrp;
out:
	cgroup_get(cgrp);
	return cgrp;
}
#endif

__bpf_kfunc_end_defs();

BTF_KFUNCS_START(scx_kfunc_ids_any)
BTF_ID_FLAGS(func, scx_bpf_kick_cpu)
BTF_ID_FLAGS(func, scx_bpf_dsq_nr_queued)
BTF_ID_FLAGS(func, scx_bpf_destroy_dsq)
BTF_ID_FLAGS(func, bpf_iter_scx_dsq_new, KF_ITER_NEW | KF_RCU_PROTECTED)
BTF_ID_FLAGS(func, bpf_iter_scx_dsq_next, KF_ITER_NEXT | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_iter_scx_dsq_destroy, KF_ITER_DESTROY)
BTF_ID_FLAGS(func, scx_bpf_exit_bstr, KF_TRUSTED_ARGS)
BTF_ID_FLAGS(func, scx_bpf_error_bstr, KF_TRUSTED_ARGS)
BTF_ID_FLAGS(func, scx_bpf_dump_bstr, KF_TRUSTED_ARGS)
BTF_ID_FLAGS(func, scx_bpf_cpuperf_cap)
BTF_ID_FLAGS(func, scx_bpf_cpuperf_cur)
BTF_ID_FLAGS(func, scx_bpf_cpuperf_set)
BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids)
BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE)
BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE)
BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE)
BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask, KF_ACQUIRE)
BTF_ID_FLAGS(func, scx_bpf_get_idle_smtmask, KF_ACQUIRE)
BTF_ID_FLAGS(func, scx_bpf_put_idle_cpumask, KF_RELEASE)
BTF_ID_FLAGS(func, scx_bpf_test_and_clear_cpu_idle)
BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_RCU)
BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_RCU)
BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU)
BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU)
BTF_ID_FLAGS(func, scx_bpf_cpu_rq)
#ifdef CONFIG_CGROUP_SCHED
BTF_ID_FLAGS(func, scx_bpf_task_cgroup, KF_RCU | KF_ACQUIRE)
#endif
BTF_KFUNCS_END(scx_kfunc_ids_any)

static const struct btf_kfunc_id_set scx_kfunc_set_any = {
	.owner			= THIS_MODULE,
	.set			= &scx_kfunc_ids_any,
};

static int __init scx_init(void)
{
	int ret;

	/*
	 * kfunc registration can't be done from init_sched_ext_class() as
	 * register_btf_kfunc_id_set() needs most of the system to be up.
	 *
	 * Some kfuncs are context-sensitive and can only be called from
	 * specific SCX ops. They are grouped into BTF sets accordingly.
	 * Unfortunately, BPF currently doesn't have a way of enforcing such
	 * restrictions. Eventually, the verifier should be able to enforce
	 * them. For now, register them the same and make each kfunc explicitly
	 * check using scx_kf_allowed().
	 */
	if ((ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
					     &scx_kfunc_set_select_cpu)) ||
	    (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
					     &scx_kfunc_set_enqueue_dispatch)) ||
	    (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
					     &scx_kfunc_set_dispatch)) ||
	    (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
					     &scx_kfunc_set_cpu_release)) ||
	    (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
					     &scx_kfunc_set_unlocked)) ||
	    (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL,
					     &scx_kfunc_set_unlocked)) ||
	    (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
					     &scx_kfunc_set_any)) ||
	    (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING,
					     &scx_kfunc_set_any)) ||
	    (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL,
					     &scx_kfunc_set_any))) {
		pr_err("sched_ext: Failed to register kfunc sets (%d)\n", ret);
		return ret;
	}

	ret = register_bpf_struct_ops(&bpf_sched_ext_ops, sched_ext_ops);
	if (ret) {
		pr_err("sched_ext: Failed to register struct_ops (%d)\n", ret);
		return ret;
	}

	ret = register_pm_notifier(&scx_pm_notifier);
	if (ret) {
		pr_err("sched_ext: Failed to register PM notifier (%d)\n", ret);
		return ret;
	}

	scx_kset = kset_create_and_add("sched_ext", &scx_uevent_ops, kernel_kobj);
	if (!scx_kset) {
		pr_err("sched_ext: Failed to create /sys/kernel/sched_ext\n");
		return -ENOMEM;
	}

	ret = sysfs_create_group(&scx_kset->kobj, &scx_global_attr_group);
	if (ret < 0) {
		pr_err("sched_ext: Failed to add global attributes\n");
		return ret;
	}

	return 0;
}
__initcall(scx_init);