aboutsummaryrefslogtreecommitdiff
path: root/SOURCES/scx-kernel.patch
blob: 7ff03ff5c098e55d71fa247ac66d37320b542f4e (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
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
7753
7754
7755
7756
7757
7758
7759
7760
7761
7762
7763
7764
7765
7766
7767
7768
7769
7770
7771
7772
7773
7774
7775
7776
7777
7778
7779
7780
7781
7782
7783
7784
7785
7786
7787
7788
7789
7790
7791
7792
7793
7794
7795
7796
7797
7798
7799
7800
7801
7802
7803
7804
7805
7806
7807
7808
7809
7810
7811
7812
7813
7814
7815
7816
7817
7818
7819
7820
7821
7822
7823
7824
7825
7826
7827
7828
7829
7830
7831
7832
7833
7834
7835
7836
7837
7838
7839
7840
7841
7842
7843
7844
7845
7846
7847
7848
7849
7850
7851
7852
7853
7854
7855
7856
7857
7858
7859
7860
7861
7862
7863
7864
7865
7866
7867
7868
7869
7870
7871
7872
7873
7874
7875
7876
7877
7878
7879
7880
7881
7882
7883
7884
7885
7886
7887
7888
7889
7890
7891
7892
7893
7894
7895
7896
7897
7898
7899
7900
7901
7902
7903
7904
7905
7906
7907
7908
7909
7910
7911
7912
7913
7914
7915
7916
7917
7918
7919
7920
7921
7922
7923
7924
7925
7926
7927
7928
7929
7930
7931
7932
7933
7934
7935
7936
7937
7938
7939
7940
7941
7942
7943
7944
7945
7946
7947
7948
7949
7950
7951
7952
7953
7954
7955
7956
7957
7958
7959
7960
7961
7962
7963
7964
7965
7966
7967
7968
7969
7970
7971
7972
7973
7974
7975
7976
7977
7978
7979
7980
7981
7982
7983
7984
7985
7986
7987
7988
7989
7990
7991
7992
7993
7994
7995
7996
7997
7998
7999
8000
8001
8002
8003
8004
8005
8006
8007
8008
8009
8010
8011
8012
8013
8014
8015
8016
8017
8018
8019
8020
8021
8022
8023
8024
8025
8026
8027
8028
8029
8030
8031
8032
8033
8034
8035
8036
8037
8038
8039
8040
8041
8042
8043
8044
8045
8046
8047
8048
8049
8050
8051
8052
8053
8054
8055
8056
8057
8058
8059
8060
8061
8062
8063
8064
8065
8066
8067
8068
8069
8070
8071
8072
8073
8074
8075
8076
8077
8078
8079
8080
8081
8082
8083
8084
8085
8086
8087
8088
8089
8090
8091
8092
8093
8094
8095
8096
8097
8098
8099
8100
8101
8102
8103
8104
8105
8106
8107
8108
8109
8110
8111
8112
8113
8114
8115
8116
8117
8118
8119
8120
8121
8122
8123
8124
8125
8126
8127
8128
8129
8130
8131
8132
8133
8134
8135
8136
8137
8138
8139
8140
8141
8142
8143
8144
8145
8146
8147
8148
8149
8150
8151
8152
8153
8154
8155
8156
8157
8158
8159
8160
8161
8162
8163
8164
8165
8166
8167
8168
8169
8170
8171
8172
8173
8174
8175
8176
8177
8178
8179
8180
8181
8182
8183
8184
8185
8186
8187
8188
8189
8190
8191
8192
8193
8194
8195
8196
8197
8198
8199
8200
8201
8202
8203
8204
8205
8206
8207
8208
8209
8210
8211
8212
8213
8214
8215
8216
8217
8218
8219
8220
8221
8222
8223
8224
8225
8226
8227
8228
8229
8230
8231
8232
8233
8234
8235
8236
8237
8238
8239
8240
8241
8242
8243
8244
8245
8246
8247
8248
8249
8250
8251
8252
8253
8254
8255
8256
8257
8258
8259
8260
8261
8262
8263
8264
8265
8266
8267
8268
8269
8270
8271
8272
8273
8274
8275
8276
8277
8278
8279
8280
8281
8282
8283
8284
8285
8286
8287
8288
8289
8290
8291
8292
8293
8294
8295
8296
8297
8298
8299
8300
8301
8302
8303
8304
8305
8306
8307
8308
8309
8310
8311
8312
8313
8314
8315
8316
8317
8318
8319
8320
8321
8322
8323
8324
8325
8326
8327
8328
8329
8330
8331
8332
8333
8334
8335
8336
8337
8338
8339
8340
8341
8342
8343
8344
8345
8346
8347
8348
8349
8350
8351
8352
8353
8354
8355
8356
8357
8358
8359
8360
8361
8362
8363
8364
8365
8366
8367
8368
8369
8370
8371
8372
8373
8374
8375
8376
8377
8378
8379
8380
8381
8382
8383
8384
8385
8386
8387
8388
8389
8390
8391
8392
8393
8394
8395
8396
8397
8398
8399
8400
8401
8402
8403
8404
8405
8406
8407
8408
8409
8410
8411
8412
8413
8414
8415
8416
8417
8418
8419
8420
8421
8422
8423
8424
8425
8426
8427
8428
8429
8430
8431
8432
8433
8434
8435
8436
8437
8438
8439
8440
8441
8442
8443
8444
8445
8446
8447
8448
8449
8450
8451
8452
8453
8454
8455
8456
8457
8458
8459
8460
8461
8462
8463
8464
8465
8466
8467
8468
8469
8470
8471
8472
8473
8474
8475
8476
8477
8478
8479
8480
8481
8482
8483
8484
8485
8486
8487
8488
8489
8490
8491
8492
8493
8494
8495
8496
8497
8498
8499
8500
8501
8502
8503
8504
8505
8506
8507
8508
8509
8510
8511
8512
8513
8514
8515
8516
8517
8518
8519
8520
8521
8522
8523
8524
8525
8526
8527
8528
8529
8530
8531
8532
8533
8534
8535
8536
8537
8538
8539
8540
8541
8542
8543
8544
8545
8546
8547
8548
8549
8550
8551
8552
8553
8554
8555
8556
8557
8558
8559
8560
8561
8562
8563
8564
8565
8566
8567
8568
8569
8570
8571
8572
8573
8574
8575
8576
8577
8578
8579
8580
8581
8582
8583
8584
8585
8586
8587
8588
8589
8590
8591
8592
8593
8594
8595
8596
8597
8598
8599
8600
8601
8602
8603
8604
8605
8606
8607
8608
8609
8610
8611
8612
8613
8614
8615
8616
8617
8618
8619
8620
8621
8622
8623
8624
8625
8626
8627
8628
8629
8630
8631
8632
8633
8634
8635
8636
8637
8638
8639
8640
8641
8642
8643
8644
8645
8646
8647
8648
8649
8650
8651
8652
8653
8654
8655
8656
8657
8658
8659
8660
8661
8662
8663
8664
8665
8666
8667
8668
8669
8670
8671
8672
8673
8674
8675
8676
8677
8678
8679
8680
8681
8682
8683
8684
8685
8686
8687
8688
8689
8690
8691
8692
8693
8694
8695
8696
8697
8698
8699
8700
8701
8702
8703
8704
8705
8706
8707
8708
8709
8710
8711
8712
8713
8714
8715
8716
8717
8718
8719
8720
8721
8722
8723
8724
8725
8726
8727
8728
8729
8730
8731
8732
8733
8734
8735
8736
8737
8738
8739
8740
8741
8742
8743
8744
8745
8746
8747
8748
8749
8750
8751
8752
8753
8754
8755
8756
8757
8758
8759
8760
8761
8762
8763
8764
8765
8766
8767
8768
8769
8770
8771
8772
8773
8774
8775
8776
8777
8778
8779
8780
8781
8782
8783
8784
8785
8786
8787
8788
8789
8790
8791
8792
8793
8794
8795
8796
8797
8798
8799
8800
8801
8802
8803
8804
8805
8806
8807
8808
8809
8810
8811
8812
8813
8814
8815
8816
8817
8818
8819
8820
8821
8822
8823
8824
8825
8826
8827
8828
8829
8830
8831
8832
8833
8834
8835
8836
8837
8838
8839
8840
8841
8842
8843
8844
8845
8846
8847
8848
8849
8850
8851
8852
8853
8854
8855
8856
8857
8858
8859
8860
8861
8862
8863
8864
8865
8866
8867
8868
8869
8870
8871
8872
8873
8874
8875
8876
8877
8878
8879
8880
8881
8882
8883
8884
8885
8886
8887
8888
8889
8890
8891
8892
8893
8894
8895
8896
8897
8898
8899
8900
8901
8902
8903
8904
8905
8906
8907
8908
8909
8910
8911
8912
8913
8914
8915
8916
8917
8918
8919
8920
8921
8922
8923
8924
8925
8926
8927
8928
8929
8930
8931
8932
8933
8934
8935
8936
8937
8938
8939
8940
8941
8942
8943
8944
8945
8946
8947
8948
8949
8950
8951
8952
8953
8954
8955
8956
8957
8958
8959
8960
8961
8962
8963
8964
8965
8966
8967
8968
8969
8970
8971
8972
8973
8974
8975
8976
8977
8978
8979
8980
8981
8982
8983
8984
8985
8986
8987
8988
8989
8990
8991
8992
8993
8994
8995
8996
8997
8998
8999
9000
9001
9002
9003
9004
9005
9006
9007
9008
9009
9010
9011
9012
9013
9014
9015
9016
9017
9018
9019
9020
9021
9022
9023
9024
9025
9026
9027
9028
9029
9030
9031
9032
9033
9034
9035
9036
9037
9038
9039
9040
9041
9042
9043
9044
9045
9046
9047
9048
9049
9050
9051
9052
9053
9054
9055
9056
9057
9058
9059
9060
9061
9062
9063
9064
9065
9066
9067
9068
9069
9070
9071
9072
9073
9074
9075
9076
9077
9078
9079
9080
9081
9082
9083
9084
9085
9086
9087
9088
9089
9090
9091
9092
9093
9094
9095
9096
9097
9098
9099
9100
9101
9102
9103
9104
9105
9106
9107
9108
9109
9110
9111
9112
9113
9114
9115
9116
9117
9118
9119
9120
9121
9122
9123
9124
9125
9126
9127
9128
9129
9130
9131
9132
9133
9134
9135
9136
9137
9138
9139
9140
9141
9142
9143
9144
9145
9146
9147
9148
9149
9150
9151
9152
9153
9154
9155
9156
9157
9158
9159
9160
9161
9162
9163
9164
9165
9166
9167
9168
9169
9170
9171
9172
9173
9174
9175
9176
9177
9178
9179
9180
9181
9182
9183
9184
9185
9186
9187
9188
9189
9190
9191
9192
9193
9194
9195
9196
9197
9198
9199
9200
9201
9202
9203
9204
9205
9206
9207
9208
9209
9210
9211
9212
9213
9214
9215
9216
9217
9218
9219
9220
9221
9222
9223
9224
9225
9226
9227
9228
9229
9230
9231
9232
9233
9234
9235
9236
9237
9238
9239
9240
9241
9242
9243
9244
9245
9246
9247
9248
9249
9250
9251
9252
9253
9254
9255
9256
9257
9258
9259
9260
9261
9262
9263
9264
9265
9266
9267
9268
9269
9270
9271
9272
9273
9274
9275
9276
9277
9278
9279
9280
9281
9282
9283
9284
9285
9286
9287
9288
9289
9290
9291
9292
9293
9294
9295
9296
9297
9298
9299
9300
9301
9302
9303
9304
9305
9306
9307
9308
9309
9310
9311
9312
9313
9314
9315
9316
9317
9318
9319
9320
9321
9322
9323
9324
9325
9326
9327
9328
9329
9330
9331
9332
9333
9334
9335
9336
9337
9338
9339
9340
9341
9342
9343
9344
9345
9346
9347
9348
9349
9350
9351
9352
9353
9354
9355
9356
9357
9358
9359
9360
9361
9362
9363
9364
9365
9366
9367
9368
9369
9370
9371
9372
9373
9374
9375
9376
9377
9378
9379
9380
9381
9382
9383
9384
9385
9386
9387
9388
9389
9390
9391
9392
9393
9394
9395
9396
9397
9398
9399
9400
9401
9402
9403
9404
9405
9406
9407
9408
9409
9410
9411
9412
9413
9414
9415
9416
9417
9418
9419
9420
9421
9422
9423
9424
9425
9426
9427
9428
9429
9430
9431
9432
9433
9434
9435
9436
9437
9438
9439
9440
9441
9442
9443
9444
9445
9446
9447
9448
9449
9450
9451
9452
9453
9454
9455
9456
9457
9458
9459
9460
9461
9462
9463
9464
9465
9466
9467
9468
9469
9470
9471
9472
9473
9474
9475
9476
9477
9478
9479
9480
9481
9482
9483
9484
9485
9486
9487
9488
9489
9490
9491
9492
9493
9494
9495
9496
9497
9498
9499
9500
9501
9502
9503
9504
9505
9506
9507
9508
9509
9510
9511
9512
9513
9514
9515
9516
9517
9518
9519
9520
9521
9522
9523
9524
9525
9526
9527
9528
9529
9530
9531
9532
9533
9534
9535
9536
9537
9538
9539
9540
9541
9542
9543
9544
9545
9546
9547
9548
9549
9550
9551
9552
9553
9554
9555
9556
9557
9558
9559
9560
9561
9562
9563
9564
9565
9566
9567
9568
9569
9570
9571
9572
9573
9574
9575
9576
9577
9578
9579
9580
9581
9582
9583
9584
9585
9586
9587
9588
9589
9590
9591
9592
9593
9594
9595
9596
9597
9598
9599
9600
9601
9602
9603
9604
9605
9606
9607
9608
9609
9610
9611
9612
9613
9614
9615
9616
9617
9618
9619
9620
9621
9622
9623
9624
9625
9626
9627
9628
9629
9630
9631
9632
9633
9634
9635
9636
9637
9638
9639
9640
9641
9642
9643
9644
9645
9646
9647
9648
9649
9650
9651
9652
9653
9654
9655
9656
9657
9658
9659
9660
9661
9662
9663
9664
9665
9666
9667
9668
9669
9670
9671
9672
9673
9674
9675
9676
9677
9678
9679
9680
9681
9682
9683
9684
9685
9686
9687
9688
9689
9690
9691
9692
9693
9694
9695
9696
9697
9698
9699
9700
9701
9702
9703
9704
9705
9706
9707
9708
9709
9710
9711
9712
9713
9714
9715
9716
9717
9718
9719
9720
9721
9722
9723
9724
9725
9726
9727
9728
9729
9730
9731
9732
9733
9734
9735
9736
9737
9738
9739
9740
9741
9742
9743
9744
9745
9746
9747
9748
9749
9750
9751
9752
9753
9754
9755
9756
9757
9758
9759
9760
9761
9762
9763
9764
9765
9766
9767
9768
9769
9770
9771
9772
9773
9774
9775
9776
9777
9778
9779
9780
9781
9782
9783
9784
9785
9786
9787
9788
9789
9790
9791
9792
9793
9794
9795
9796
9797
9798
9799
9800
9801
9802
9803
9804
9805
9806
9807
9808
9809
9810
9811
9812
9813
9814
9815
9816
9817
9818
9819
9820
9821
9822
9823
9824
9825
9826
9827
9828
9829
9830
9831
9832
9833
9834
9835
9836
9837
9838
9839
9840
9841
9842
9843
9844
9845
9846
9847
9848
9849
9850
9851
9852
9853
9854
9855
9856
9857
9858
9859
9860
9861
9862
9863
9864
9865
9866
9867
9868
9869
9870
9871
9872
9873
9874
9875
9876
9877
9878
9879
9880
9881
9882
9883
9884
9885
9886
9887
9888
9889
9890
9891
9892
9893
9894
9895
9896
9897
9898
9899
9900
9901
9902
9903
9904
9905
9906
9907
9908
9909
9910
9911
9912
9913
9914
9915
9916
9917
9918
9919
9920
9921
9922
9923
9924
9925
9926
9927
9928
9929
9930
9931
9932
9933
9934
9935
9936
9937
9938
9939
9940
9941
9942
9943
9944
9945
9946
9947
9948
9949
9950
9951
9952
9953
9954
9955
9956
9957
9958
9959
9960
9961
9962
9963
9964
9965
9966
9967
9968
9969
9970
9971
9972
9973
9974
9975
9976
9977
9978
9979
9980
9981
9982
9983
9984
9985
9986
9987
9988
9989
9990
9991
9992
9993
9994
9995
9996
9997
9998
9999
10000
10001
10002
10003
10004
10005
10006
10007
10008
10009
10010
10011
10012
10013
10014
10015
10016
10017
10018
10019
10020
10021
10022
10023
10024
10025
10026
10027
10028
10029
10030
10031
10032
10033
10034
10035
10036
10037
10038
10039
10040
10041
10042
10043
10044
10045
10046
10047
10048
10049
10050
10051
10052
10053
10054
10055
10056
10057
10058
10059
10060
10061
10062
10063
10064
10065
10066
10067
10068
10069
10070
10071
10072
10073
10074
10075
10076
10077
10078
10079
10080
10081
10082
10083
10084
10085
10086
10087
10088
10089
10090
10091
10092
10093
10094
10095
10096
10097
10098
10099
10100
10101
10102
10103
10104
10105
10106
10107
10108
10109
10110
10111
10112
10113
10114
10115
10116
10117
10118
10119
10120
10121
10122
10123
10124
10125
10126
10127
10128
10129
10130
10131
10132
10133
10134
10135
10136
10137
10138
10139
10140
10141
10142
10143
10144
10145
10146
10147
10148
10149
10150
10151
10152
10153
10154
10155
10156
10157
10158
10159
10160
10161
10162
10163
10164
10165
10166
10167
10168
10169
10170
10171
10172
10173
10174
10175
10176
10177
10178
10179
10180
10181
10182
10183
10184
10185
10186
10187
10188
10189
10190
10191
10192
10193
10194
10195
10196
10197
10198
10199
10200
10201
10202
10203
10204
10205
10206
10207
10208
10209
10210
10211
10212
10213
10214
10215
10216
10217
10218
10219
10220
10221
10222
10223
10224
10225
10226
10227
10228
10229
10230
10231
10232
10233
10234
10235
10236
10237
10238
10239
10240
10241
10242
10243
10244
10245
10246
10247
10248
10249
10250
10251
10252
10253
10254
10255
10256
10257
10258
10259
10260
10261
10262
10263
10264
10265
10266
10267
10268
10269
10270
10271
10272
10273
10274
10275
10276
10277
10278
10279
10280
10281
10282
10283
10284
10285
10286
10287
10288
10289
10290
10291
10292
10293
10294
10295
10296
10297
10298
10299
10300
10301
10302
10303
10304
10305
10306
10307
10308
10309
10310
10311
10312
10313
10314
10315
10316
10317
10318
10319
10320
10321
10322
10323
10324
10325
10326
10327
10328
10329
10330
10331
10332
10333
10334
10335
10336
10337
10338
10339
10340
10341
10342
10343
10344
10345
10346
10347
10348
10349
10350
10351
10352
10353
10354
10355
10356
10357
10358
10359
10360
10361
10362
10363
10364
10365
10366
10367
10368
10369
10370
10371
10372
10373
10374
10375
10376
10377
10378
10379
10380
10381
10382
10383
10384
10385
10386
10387
10388
10389
10390
10391
10392
10393
10394
10395
10396
10397
10398
10399
10400
10401
10402
10403
10404
10405
10406
10407
10408
10409
10410
10411
10412
10413
10414
10415
10416
10417
10418
10419
10420
10421
10422
10423
10424
10425
10426
10427
10428
10429
10430
10431
10432
10433
10434
10435
10436
10437
10438
10439
10440
10441
10442
10443
10444
10445
10446
10447
10448
10449
10450
10451
10452
10453
10454
10455
10456
10457
10458
10459
10460
10461
10462
10463
10464
10465
10466
10467
10468
10469
10470
10471
10472
10473
10474
10475
10476
10477
10478
10479
10480
10481
10482
10483
10484
10485
10486
10487
10488
10489
10490
10491
10492
10493
10494
10495
10496
10497
10498
10499
10500
10501
10502
10503
10504
10505
10506
10507
10508
10509
10510
10511
10512
10513
10514
10515
10516
10517
10518
10519
10520
10521
10522
10523
10524
10525
10526
10527
10528
10529
10530
10531
10532
10533
10534
10535
10536
10537
10538
10539
10540
10541
10542
10543
10544
10545
10546
10547
10548
10549
10550
10551
10552
10553
10554
10555
10556
10557
10558
10559
10560
10561
10562
10563
10564
10565
10566
10567
10568
10569
10570
10571
10572
10573
10574
10575
10576
10577
10578
10579
10580
10581
10582
10583
10584
10585
10586
10587
10588
10589
10590
10591
10592
10593
10594
10595
10596
10597
10598
10599
10600
10601
10602
10603
10604
10605
10606
10607
10608
10609
10610
10611
10612
10613
10614
10615
10616
10617
10618
10619
10620
10621
10622
10623
10624
10625
10626
10627
10628
10629
10630
10631
10632
10633
10634
10635
10636
10637
10638
10639
10640
10641
10642
10643
10644
10645
10646
10647
10648
10649
10650
10651
10652
10653
10654
10655
10656
10657
10658
10659
10660
10661
10662
10663
10664
10665
10666
10667
10668
10669
10670
10671
10672
10673
10674
10675
10676
10677
10678
10679
10680
10681
10682
10683
10684
10685
10686
10687
10688
10689
10690
10691
10692
10693
10694
10695
10696
10697
10698
10699
10700
10701
10702
10703
10704
10705
10706
10707
10708
10709
10710
10711
10712
10713
10714
10715
10716
10717
10718
10719
10720
10721
10722
10723
10724
10725
10726
10727
10728
10729
10730
10731
10732
10733
10734
10735
10736
10737
10738
10739
10740
10741
10742
10743
10744
10745
10746
10747
10748
10749
10750
10751
10752
10753
10754
10755
10756
10757
10758
10759
10760
10761
10762
10763
10764
10765
10766
10767
10768
10769
10770
10771
10772
10773
10774
10775
10776
10777
10778
10779
10780
10781
10782
10783
10784
10785
10786
10787
10788
10789
10790
10791
10792
10793
10794
10795
10796
10797
10798
10799
10800
10801
10802
10803
10804
10805
10806
10807
10808
10809
10810
10811
10812
10813
10814
10815
10816
10817
10818
10819
10820
10821
10822
10823
10824
10825
10826
10827
10828
10829
10830
10831
10832
10833
10834
10835
10836
10837
10838
10839
10840
10841
10842
10843
10844
10845
10846
10847
10848
10849
10850
10851
10852
10853
10854
10855
10856
10857
10858
10859
10860
10861
10862
10863
10864
10865
10866
10867
10868
10869
10870
10871
10872
10873
10874
10875
10876
10877
10878
10879
10880
10881
10882
10883
10884
10885
10886
10887
10888
10889
10890
10891
10892
10893
10894
10895
10896
10897
10898
10899
10900
10901
10902
10903
10904
10905
10906
10907
10908
10909
10910
10911
10912
10913
10914
10915
10916
10917
10918
10919
10920
10921
10922
10923
10924
10925
10926
10927
10928
10929
10930
10931
10932
10933
10934
10935
10936
10937
10938
10939
10940
10941
10942
10943
10944
10945
10946
10947
10948
10949
10950
10951
10952
10953
10954
10955
10956
10957
10958
10959
10960
10961
10962
10963
10964
10965
10966
10967
10968
10969
10970
10971
10972
10973
10974
10975
10976
10977
10978
10979
10980
10981
10982
10983
10984
10985
10986
10987
10988
10989
10990
10991
10992
10993
10994
10995
10996
10997
10998
10999
11000
11001
11002
11003
11004
11005
11006
11007
11008
11009
11010
11011
11012
11013
11014
11015
11016
11017
11018
11019
11020
11021
11022
11023
11024
11025
11026
11027
11028
11029
11030
11031
11032
11033
11034
11035
11036
11037
11038
11039
11040
11041
11042
11043
11044
11045
11046
11047
11048
11049
11050
11051
11052
11053
11054
11055
11056
11057
11058
11059
11060
11061
11062
11063
11064
11065
11066
11067
11068
11069
11070
11071
11072
11073
11074
11075
11076
11077
11078
11079
11080
11081
11082
11083
11084
11085
11086
11087
11088
11089
11090
11091
11092
11093
11094
11095
11096
11097
11098
11099
11100
11101
11102
11103
11104
11105
11106
11107
11108
11109
11110
11111
11112
11113
11114
11115
11116
11117
11118
11119
11120
11121
11122
11123
11124
11125
11126
11127
11128
11129
11130
11131
11132
11133
11134
11135
11136
11137
11138
11139
11140
11141
11142
11143
11144
11145
11146
11147
11148
11149
11150
11151
11152
11153
11154
11155
11156
11157
11158
11159
11160
11161
11162
11163
11164
11165
11166
11167
11168
11169
11170
11171
11172
11173
11174
11175
11176
11177
11178
11179
11180
11181
11182
11183
11184
11185
11186
11187
11188
11189
11190
11191
11192
11193
11194
11195
11196
11197
11198
11199
11200
11201
11202
11203
11204
11205
11206
11207
11208
11209
11210
11211
11212
11213
11214
11215
11216
11217
11218
11219
11220
11221
11222
11223
11224
11225
11226
11227
11228
11229
11230
11231
11232
11233
11234
11235
11236
11237
11238
11239
11240
11241
11242
11243
11244
11245
11246
11247
11248
11249
11250
11251
11252
11253
11254
11255
11256
11257
11258
11259
11260
11261
11262
11263
11264
11265
11266
11267
11268
11269
11270
11271
11272
11273
11274
11275
11276
11277
11278
11279
11280
11281
11282
11283
11284
11285
11286
11287
11288
11289
11290
11291
11292
11293
11294
11295
11296
11297
11298
11299
11300
11301
11302
11303
11304
11305
11306
11307
11308
11309
11310
11311
11312
11313
11314
11315
11316
11317
11318
11319
11320
11321
11322
11323
11324
11325
11326
11327
11328
11329
11330
11331
11332
11333
11334
11335
11336
11337
11338
11339
11340
11341
11342
11343
11344
11345
11346
11347
11348
11349
11350
11351
11352
11353
11354
11355
11356
11357
11358
11359
11360
11361
11362
11363
11364
11365
11366
11367
11368
11369
11370
11371
11372
11373
11374
11375
11376
11377
11378
11379
11380
11381
11382
11383
11384
11385
11386
11387
11388
11389
11390
11391
11392
11393
11394
11395
11396
11397
11398
11399
11400
11401
11402
11403
11404
11405
11406
11407
11408
11409
11410
11411
11412
11413
11414
11415
11416
11417
11418
11419
11420
11421
11422
11423
11424
11425
11426
11427
11428
11429
11430
11431
11432
11433
11434
11435
11436
11437
11438
11439
11440
11441
11442
11443
11444
11445
11446
11447
11448
11449
11450
11451
11452
11453
11454
11455
11456
11457
11458
11459
11460
11461
11462
11463
11464
11465
11466
11467
11468
11469
11470
11471
11472
11473
11474
11475
11476
11477
11478
11479
11480
11481
11482
11483
11484
11485
11486
11487
11488
11489
11490
11491
11492
11493
11494
11495
11496
11497
11498
11499
11500
11501
11502
11503
11504
11505
11506
11507
11508
11509
11510
11511
11512
11513
11514
11515
11516
11517
11518
11519
11520
11521
11522
11523
11524
11525
11526
11527
11528
11529
11530
11531
11532
11533
11534
11535
11536
11537
11538
11539
11540
11541
11542
11543
11544
11545
11546
11547
11548
11549
11550
11551
11552
11553
11554
11555
11556
11557
11558
11559
11560
11561
11562
11563
11564
11565
11566
11567
11568
11569
11570
11571
11572
11573
11574
11575
11576
11577
11578
11579
11580
11581
11582
11583
11584
11585
11586
11587
11588
11589
11590
11591
11592
11593
11594
11595
11596
11597
11598
11599
11600
11601
11602
11603
11604
11605
11606
11607
11608
11609
11610
11611
11612
11613
11614
11615
11616
11617
11618
11619
11620
11621
11622
11623
11624
11625
11626
11627
11628
11629
11630
11631
11632
11633
11634
11635
11636
11637
11638
11639
11640
11641
11642
11643
11644
11645
11646
11647
11648
11649
11650
11651
11652
11653
11654
11655
11656
11657
11658
11659
11660
11661
11662
11663
11664
11665
11666
11667
11668
11669
11670
11671
11672
11673
11674
11675
11676
11677
11678
11679
11680
11681
11682
11683
11684
11685
11686
11687
11688
11689
11690
11691
11692
11693
11694
11695
11696
11697
11698
11699
11700
11701
11702
11703
11704
11705
11706
11707
11708
11709
11710
11711
11712
11713
11714
11715
11716
11717
11718
11719
11720
11721
11722
11723
11724
11725
11726
11727
11728
11729
11730
11731
11732
11733
11734
11735
11736
11737
11738
11739
11740
11741
11742
11743
11744
11745
11746
11747
11748
11749
11750
11751
11752
11753
11754
11755
11756
11757
11758
11759
11760
11761
11762
11763
11764
11765
11766
11767
11768
11769
11770
11771
11772
11773
11774
11775
11776
11777
11778
11779
11780
11781
11782
11783
11784
11785
11786
11787
11788
11789
11790
11791
11792
11793
11794
11795
11796
11797
11798
11799
11800
11801
11802
11803
11804
11805
11806
11807
11808
11809
11810
11811
11812
11813
11814
11815
11816
11817
11818
11819
11820
11821
11822
11823
11824
11825
11826
11827
11828
11829
11830
11831
11832
11833
11834
11835
11836
11837
11838
11839
11840
11841
11842
11843
11844
11845
11846
11847
11848
11849
11850
11851
11852
11853
11854
11855
11856
11857
11858
11859
11860
11861
11862
11863
11864
11865
11866
11867
11868
11869
11870
11871
11872
11873
11874
11875
11876
11877
11878
11879
11880
11881
11882
11883
11884
11885
11886
11887
11888
11889
11890
11891
11892
11893
11894
11895
11896
11897
11898
11899
11900
11901
11902
11903
11904
11905
11906
11907
11908
11909
11910
11911
11912
11913
11914
11915
11916
11917
11918
11919
11920
11921
11922
11923
11924
11925
11926
11927
11928
11929
11930
11931
11932
11933
11934
11935
11936
11937
11938
11939
11940
11941
11942
11943
11944
11945
11946
11947
11948
11949
11950
11951
11952
11953
11954
11955
11956
11957
11958
11959
11960
11961
11962
11963
11964
11965
11966
11967
11968
11969
11970
11971
11972
11973
11974
11975
11976
11977
11978
11979
11980
11981
11982
11983
11984
11985
11986
11987
11988
11989
11990
11991
11992
11993
11994
11995
11996
11997
11998
11999
12000
12001
12002
12003
12004
12005
12006
12007
12008
12009
12010
12011
12012
12013
12014
12015
12016
12017
12018
12019
12020
12021
12022
12023
12024
12025
12026
12027
12028
12029
12030
12031
12032
12033
12034
12035
12036
12037
12038
12039
12040
12041
12042
12043
12044
12045
12046
12047
12048
12049
12050
12051
12052
12053
12054
12055
12056
12057
12058
12059
12060
12061
12062
12063
12064
12065
12066
12067
12068
12069
12070
12071
12072
12073
12074
12075
12076
12077
12078
12079
12080
12081
12082
12083
12084
12085
12086
12087
12088
12089
12090
12091
12092
12093
12094
12095
12096
12097
12098
12099
12100
12101
12102
12103
12104
12105
12106
12107
12108
12109
12110
12111
12112
12113
12114
12115
12116
12117
12118
12119
12120
12121
12122
12123
12124
12125
12126
12127
12128
12129
12130
12131
12132
12133
12134
12135
12136
12137
12138
12139
12140
12141
12142
12143
12144
12145
12146
12147
12148
12149
12150
12151
12152
12153
12154
12155
12156
12157
12158
12159
12160
12161
12162
12163
12164
12165
12166
12167
12168
12169
12170
12171
12172
12173
12174
12175
12176
12177
12178
12179
12180
12181
12182
12183
12184
12185
12186
12187
12188
12189
12190
12191
12192
12193
12194
12195
12196
12197
12198
12199
12200
12201
12202
12203
12204
12205
12206
12207
12208
12209
12210
12211
12212
12213
12214
12215
12216
12217
12218
12219
12220
12221
12222
12223
12224
12225
12226
12227
12228
12229
12230
12231
12232
12233
12234
12235
12236
12237
12238
12239
12240
12241
12242
12243
12244
12245
12246
12247
12248
12249
12250
12251
12252
12253
12254
12255
12256
12257
12258
12259
12260
12261
12262
12263
12264
12265
12266
12267
12268
12269
12270
12271
12272
12273
12274
12275
12276
12277
12278
12279
12280
12281
12282
12283
12284
12285
12286
12287
12288
12289
12290
12291
12292
12293
12294
12295
12296
12297
12298
12299
12300
12301
12302
12303
12304
12305
12306
12307
12308
12309
12310
12311
12312
12313
12314
12315
12316
12317
12318
12319
12320
12321
12322
12323
12324
12325
12326
12327
12328
12329
12330
12331
12332
12333
12334
12335
12336
12337
12338
12339
12340
12341
12342
12343
12344
12345
12346
12347
12348
12349
12350
12351
12352
12353
12354
12355
12356
12357
12358
12359
12360
12361
12362
12363
12364
12365
12366
12367
12368
12369
12370
12371
12372
12373
12374
12375
12376
12377
12378
12379
12380
12381
12382
12383
12384
12385
12386
12387
12388
12389
12390
12391
12392
12393
12394
12395
12396
12397
12398
12399
12400
12401
12402
12403
12404
12405
12406
12407
12408
12409
12410
12411
12412
12413
12414
12415
12416
12417
12418
12419
12420
12421
12422
12423
12424
12425
12426
12427
12428
12429
12430
12431
12432
12433
12434
12435
12436
12437
12438
12439
12440
12441
12442
12443
12444
12445
12446
12447
12448
12449
12450
12451
12452
12453
12454
12455
12456
12457
12458
12459
12460
12461
12462
12463
12464
12465
12466
12467
12468
12469
12470
12471
12472
12473
12474
12475
12476
12477
12478
12479
12480
12481
12482
12483
12484
12485
12486
12487
12488
12489
12490
12491
12492
12493
12494
12495
12496
12497
12498
12499
12500
12501
12502
12503
12504
12505
12506
12507
12508
12509
12510
12511
12512
12513
12514
12515
12516
12517
12518
12519
12520
12521
12522
12523
12524
12525
12526
12527
12528
12529
12530
12531
12532
12533
12534
12535
12536
12537
12538
12539
12540
12541
12542
12543
12544
12545
12546
12547
12548
12549
12550
12551
12552
12553
12554
12555
12556
12557
12558
12559
12560
12561
12562
12563
12564
12565
12566
12567
12568
12569
12570
12571
12572
12573
12574
12575
12576
12577
12578
12579
12580
12581
12582
12583
12584
12585
12586
12587
12588
12589
12590
12591
12592
12593
12594
12595
12596
12597
12598
12599
12600
12601
12602
12603
12604
12605
12606
12607
12608
12609
12610
12611
12612
12613
12614
12615
12616
12617
12618
12619
12620
12621
12622
12623
12624
12625
12626
12627
12628
12629
12630
12631
12632
12633
12634
12635
12636
12637
12638
12639
12640
12641
12642
12643
12644
12645
12646
12647
12648
12649
12650
12651
12652
12653
12654
12655
12656
12657
12658
12659
12660
12661
12662
12663
12664
12665
12666
12667
12668
12669
12670
12671
12672
12673
12674
12675
12676
12677
12678
12679
12680
12681
12682
12683
12684
12685
12686
12687
12688
12689
12690
12691
12692
12693
12694
12695
12696
12697
12698
12699
12700
12701
12702
12703
12704
12705
12706
12707
12708
12709
12710
12711
12712
12713
12714
12715
12716
12717
12718
12719
12720
12721
12722
12723
12724
12725
12726
12727
12728
12729
12730
12731
12732
12733
12734
12735
12736
12737
12738
12739
12740
12741
12742
12743
12744
12745
12746
12747
12748
12749
12750
12751
12752
12753
12754
12755
12756
12757
12758
12759
12760
12761
12762
12763
12764
12765
12766
12767
12768
12769
12770
12771
12772
12773
12774
12775
12776
12777
12778
12779
12780
12781
12782
12783
12784
12785
12786
12787
12788
12789
12790
12791
12792
12793
12794
12795
12796
12797
12798
12799
12800
12801
12802
12803
12804
12805
12806
12807
12808
12809
12810
12811
12812
12813
12814
12815
12816
12817
12818
12819
12820
12821
12822
12823
12824
12825
12826
12827
12828
12829
12830
12831
12832
12833
12834
12835
12836
12837
12838
12839
12840
12841
12842
12843
12844
12845
12846
12847
12848
12849
12850
12851
12852
12853
12854
12855
12856
12857
12858
12859
12860
12861
12862
12863
12864
12865
12866
12867
12868
12869
12870
12871
12872
12873
12874
12875
12876
12877
12878
12879
12880
12881
12882
12883
12884
12885
12886
12887
12888
12889
12890
12891
12892
12893
12894
12895
12896
12897
12898
12899
12900
12901
12902
12903
12904
12905
12906
12907
12908
12909
12910
12911
12912
12913
12914
12915
12916
12917
12918
12919
12920
12921
12922
12923
12924
12925
12926
12927
12928
12929
12930
12931
12932
12933
12934
12935
12936
12937
12938
12939
12940
12941
12942
12943
12944
12945
12946
12947
12948
12949
12950
12951
12952
12953
12954
12955
12956
12957
12958
12959
12960
12961
12962
12963
12964
12965
12966
12967
12968
12969
12970
12971
12972
12973
12974
12975
12976
12977
12978
12979
12980
12981
12982
12983
12984
12985
12986
12987
12988
12989
12990
12991
12992
12993
12994
12995
12996
12997
12998
12999
13000
13001
13002
13003
13004
13005
13006
13007
13008
13009
13010
13011
13012
13013
13014
13015
13016
13017
13018
13019
13020
13021
13022
13023
13024
13025
13026
13027
13028
13029
13030
13031
13032
13033
13034
13035
13036
13037
13038
13039
13040
13041
13042
13043
13044
13045
13046
13047
13048
13049
13050
13051
13052
13053
13054
13055
13056
13057
13058
13059
13060
13061
13062
13063
13064
13065
13066
13067
13068
13069
13070
13071
13072
13073
13074
13075
13076
13077
13078
13079
13080
13081
13082
13083
13084
13085
13086
13087
13088
13089
13090
13091
13092
13093
13094
13095
13096
13097
13098
13099
13100
13101
13102
13103
13104
13105
13106
13107
13108
13109
13110
13111
13112
13113
13114
13115
13116
13117
13118
13119
13120
13121
13122
13123
13124
13125
13126
13127
13128
13129
13130
13131
13132
13133
13134
13135
13136
13137
13138
13139
13140
13141
13142
13143
13144
13145
13146
13147
13148
13149
13150
13151
13152
13153
13154
13155
13156
13157
13158
13159
13160
13161
13162
13163
13164
13165
13166
13167
13168
13169
13170
13171
13172
13173
13174
13175
13176
13177
13178
13179
13180
13181
13182
13183
13184
13185
13186
13187
13188
13189
13190
13191
13192
13193
13194
13195
13196
13197
13198
13199
13200
13201
13202
13203
13204
13205
13206
13207
13208
13209
13210
13211
13212
13213
13214
13215
13216
13217
13218
13219
13220
13221
13222
13223
13224
13225
13226
13227
13228
13229
13230
13231
13232
13233
13234
13235
13236
13237
13238
13239
13240
13241
13242
13243
13244
13245
13246
13247
13248
13249
13250
13251
13252
13253
13254
13255
13256
13257
13258
13259
13260
13261
13262
13263
13264
13265
13266
13267
13268
13269
13270
13271
13272
13273
13274
13275
13276
13277
13278
13279
13280
13281
13282
13283
13284
13285
13286
13287
13288
13289
13290
13291
13292
13293
13294
13295
13296
13297
13298
13299
13300
13301
13302
13303
13304
13305
13306
13307
13308
13309
13310
13311
13312
13313
13314
13315
13316
13317
13318
13319
13320
13321
13322
13323
13324
13325
13326
13327
13328
13329
13330
13331
13332
13333
13334
13335
13336
13337
13338
13339
13340
13341
13342
13343
13344
13345
13346
13347
13348
13349
13350
13351
13352
13353
13354
13355
13356
13357
13358
13359
13360
13361
13362
13363
13364
13365
13366
13367
13368
13369
13370
13371
13372
13373
13374
13375
13376
13377
13378
13379
13380
13381
13382
13383
13384
13385
13386
13387
13388
13389
13390
13391
13392
13393
13394
13395
13396
13397
13398
13399
13400
13401
13402
13403
13404
13405
13406
13407
13408
13409
13410
13411
13412
13413
13414
13415
13416
13417
13418
13419
13420
13421
13422
13423
13424
13425
13426
13427
13428
13429
13430
13431
13432
13433
13434
13435
13436
13437
13438
13439
13440
13441
13442
13443
13444
13445
13446
13447
13448
13449
13450
13451
13452
13453
13454
13455
13456
13457
13458
13459
13460
13461
13462
13463
13464
13465
13466
13467
13468
13469
13470
13471
13472
13473
13474
13475
13476
13477
13478
13479
13480
13481
13482
13483
13484
13485
13486
13487
13488
13489
13490
13491
13492
13493
13494
13495
13496
13497
13498
13499
13500
13501
13502
13503
13504
13505
13506
13507
13508
13509
13510
13511
13512
13513
13514
13515
13516
13517
13518
13519
13520
13521
13522
13523
13524
13525
13526
13527
13528
13529
13530
13531
13532
13533
13534
13535
13536
13537
13538
13539
13540
13541
13542
13543
13544
13545
13546
13547
13548
13549
13550
13551
13552
13553
13554
13555
13556
13557
13558
13559
13560
13561
13562
13563
13564
13565
13566
13567
13568
13569
13570
13571
13572
13573
13574
13575
13576
13577
13578
13579
13580
13581
13582
13583
13584
13585
13586
13587
13588
13589
13590
13591
13592
13593
13594
13595
13596
13597
13598
13599
13600
13601
13602
13603
13604
13605
13606
13607
13608
13609
13610
13611
13612
13613
13614
13615
13616
13617
13618
13619
13620
13621
13622
13623
13624
13625
13626
13627
13628
13629
13630
13631
13632
13633
13634
13635
13636
13637
13638
13639
13640
13641
13642
13643
13644
13645
13646
13647
13648
13649
13650
13651
13652
13653
13654
13655
13656
13657
13658
13659
13660
13661
13662
13663
13664
13665
13666
13667
13668
13669
13670
13671
13672
13673
13674
13675
13676
13677
13678
13679
13680
13681
13682
13683
13684
13685
13686
13687
13688
13689
13690
13691
13692
13693
13694
13695
13696
13697
13698
13699
13700
13701
13702
13703
13704
13705
13706
13707
13708
13709
13710
13711
13712
13713
13714
13715
13716
13717
13718
13719
13720
13721
13722
13723
13724
13725
13726
13727
13728
13729
13730
13731
13732
13733
13734
13735
13736
13737
13738
13739
13740
13741
13742
13743
13744
13745
13746
13747
13748
13749
13750
13751
13752
13753
13754
13755
13756
13757
13758
13759
13760
13761
13762
13763
13764
13765
13766
13767
13768
13769
13770
13771
13772
13773
13774
13775
13776
13777
13778
13779
13780
13781
13782
13783
13784
13785
13786
13787
13788
13789
13790
13791
13792
13793
13794
13795
13796
13797
13798
13799
13800
13801
13802
13803
13804
13805
13806
13807
13808
13809
13810
13811
13812
13813
13814
13815
13816
13817
13818
13819
13820
13821
13822
13823
13824
13825
13826
13827
13828
13829
13830
13831
13832
13833
13834
13835
13836
13837
13838
13839
13840
13841
13842
13843
13844
13845
13846
13847
13848
13849
13850
13851
13852
13853
13854
13855
13856
13857
13858
13859
13860
13861
13862
13863
13864
13865
13866
13867
13868
13869
13870
13871
13872
13873
13874
13875
13876
13877
13878
13879
13880
13881
13882
13883
13884
13885
13886
13887
13888
13889
13890
13891
13892
13893
13894
13895
13896
13897
13898
13899
13900
13901
13902
13903
13904
13905
13906
13907
13908
13909
13910
13911
13912
13913
13914
13915
13916
13917
13918
13919
13920
13921
13922
13923
13924
13925
13926
13927
13928
13929
13930
13931
13932
13933
13934
13935
13936
13937
13938
13939
13940
13941
13942
13943
13944
13945
13946
13947
13948
13949
13950
13951
13952
13953
13954
13955
13956
13957
13958
13959
13960
13961
13962
13963
13964
13965
13966
13967
13968
13969
13970
13971
13972
13973
13974
13975
13976
13977
13978
13979
13980
13981
13982
13983
13984
13985
13986
13987
13988
13989
13990
13991
13992
13993
13994
13995
13996
13997
13998
13999
14000
14001
14002
14003
14004
14005
14006
14007
14008
14009
14010
14011
14012
14013
14014
14015
14016
14017
14018
14019
14020
14021
14022
14023
14024
14025
14026
14027
14028
14029
14030
14031
14032
14033
14034
14035
14036
14037
14038
14039
14040
14041
14042
14043
14044
14045
14046
14047
14048
14049
14050
14051
14052
14053
14054
14055
14056
14057
14058
14059
14060
14061
14062
14063
14064
14065
14066
14067
14068
14069
14070
14071
14072
14073
14074
14075
14076
14077
14078
14079
14080
14081
14082
14083
14084
14085
14086
14087
14088
14089
14090
14091
14092
14093
14094
14095
14096
14097
14098
14099
14100
14101
14102
14103
14104
14105
14106
14107
14108
14109
14110
14111
14112
14113
14114
14115
14116
14117
14118
14119
14120
14121
14122
14123
14124
14125
14126
14127
14128
14129
14130
14131
14132
14133
14134
14135
14136
14137
14138
14139
14140
14141
14142
14143
14144
14145
14146
14147
14148
14149
14150
14151
14152
14153
14154
14155
14156
14157
14158
14159
14160
14161
14162
14163
14164
14165
14166
14167
14168
14169
14170
14171
14172
14173
14174
14175
14176
14177
14178
14179
14180
14181
14182
14183
14184
14185
14186
14187
14188
14189
14190
14191
14192
14193
14194
14195
14196
14197
14198
14199
14200
14201
14202
14203
14204
14205
14206
14207
14208
14209
14210
14211
14212
14213
14214
14215
14216
14217
14218
14219
14220
14221
14222
14223
14224
14225
14226
14227
14228
14229
14230
14231
14232
14233
14234
14235
14236
14237
14238
14239
14240
14241
14242
14243
14244
14245
14246
14247
14248
14249
14250
14251
14252
14253
14254
14255
14256
14257
14258
14259
14260
14261
14262
14263
14264
14265
14266
14267
14268
14269
14270
14271
14272
14273
14274
14275
14276
14277
14278
14279
14280
14281
14282
14283
14284
14285
14286
14287
14288
14289
14290
14291
14292
14293
14294
14295
14296
14297
14298
14299
14300
14301
14302
14303
14304
14305
14306
14307
14308
14309
14310
14311
14312
14313
14314
14315
14316
14317
14318
14319
14320
14321
14322
14323
14324
14325
14326
14327
14328
14329
14330
14331
14332
14333
14334
14335
14336
14337
14338
14339
14340
14341
14342
14343
14344
14345
14346
14347
14348
14349
14350
14351
14352
14353
14354
14355
14356
14357
14358
14359
14360
14361
14362
14363
14364
14365
14366
14367
14368
14369
14370
14371
14372
14373
14374
14375
14376
14377
14378
14379
14380
14381
14382
14383
14384
14385
14386
14387
14388
14389
14390
14391
14392
14393
14394
14395
14396
14397
14398
14399
14400
14401
14402
14403
14404
14405
14406
14407
14408
14409
14410
14411
14412
14413
14414
14415
14416
14417
14418
14419
14420
14421
14422
14423
14424
14425
14426
14427
14428
14429
14430
14431
14432
14433
14434
14435
14436
14437
14438
14439
14440
14441
14442
14443
14444
14445
14446
14447
14448
14449
14450
14451
14452
14453
14454
14455
14456
14457
14458
14459
14460
14461
14462
14463
14464
14465
14466
14467
14468
14469
14470
14471
14472
14473
14474
14475
14476
14477
14478
14479
14480
14481
14482
14483
14484
14485
14486
14487
14488
14489
14490
14491
14492
14493
14494
14495
14496
14497
14498
14499
14500
14501
14502
14503
14504
14505
14506
14507
14508
14509
14510
14511
14512
14513
14514
14515
14516
14517
14518
14519
14520
14521
14522
14523
14524
14525
14526
14527
14528
14529
14530
14531
14532
14533
14534
14535
14536
14537
14538
14539
14540
14541
14542
14543
14544
14545
14546
14547
14548
14549
14550
14551
14552
14553
14554
14555
14556
14557
14558
14559
14560
14561
14562
14563
14564
14565
14566
14567
14568
14569
14570
14571
14572
14573
14574
14575
14576
14577
14578
14579
14580
14581
14582
14583
14584
14585
14586
14587
14588
14589
14590
14591
14592
14593
14594
14595
14596
14597
14598
14599
14600
14601
14602
14603
14604
14605
14606
14607
14608
14609
14610
14611
14612
14613
14614
14615
14616
14617
14618
14619
14620
14621
14622
14623
14624
14625
14626
14627
14628
14629
14630
14631
14632
14633
14634
14635
14636
14637
14638
14639
14640
14641
14642
14643
14644
14645
14646
14647
14648
14649
14650
14651
14652
14653
14654
14655
14656
14657
14658
14659
14660
14661
14662
14663
14664
14665
14666
14667
14668
14669
14670
14671
14672
14673
14674
14675
14676
14677
14678
14679
14680
14681
14682
14683
14684
14685
14686
14687
14688
14689
14690
14691
14692
14693
14694
14695
14696
14697
14698
14699
14700
14701
14702
14703
14704
14705
14706
14707
14708
14709
14710
14711
14712
14713
14714
14715
14716
14717
14718
14719
14720
14721
14722
14723
14724
14725
14726
14727
14728
14729
14730
14731
14732
14733
14734
14735
14736
14737
14738
14739
14740
14741
14742
14743
14744
14745
14746
14747
14748
14749
14750
14751
14752
14753
14754
14755
14756
14757
14758
14759
14760
14761
14762
14763
14764
14765
14766
14767
14768
14769
14770
14771
14772
14773
14774
14775
14776
14777
14778
14779
14780
14781
14782
14783
14784
14785
14786
14787
14788
14789
14790
14791
14792
14793
14794
14795
14796
14797
14798
14799
14800
14801
14802
14803
14804
14805
14806
14807
14808
14809
14810
14811
14812
14813
14814
14815
14816
14817
14818
14819
14820
14821
14822
14823
14824
14825
14826
14827
14828
14829
14830
14831
14832
14833
14834
14835
14836
14837
14838
14839
14840
14841
14842
14843
14844
14845
14846
14847
14848
14849
14850
14851
14852
14853
14854
14855
14856
14857
14858
14859
14860
14861
14862
14863
14864
14865
14866
14867
14868
14869
14870
14871
14872
14873
14874
14875
14876
14877
14878
14879
14880
14881
14882
14883
14884
14885
14886
14887
14888
14889
14890
14891
14892
14893
14894
14895
14896
14897
14898
14899
14900
14901
14902
14903
14904
14905
14906
14907
14908
14909
14910
14911
14912
14913
14914
14915
14916
14917
14918
14919
14920
14921
14922
14923
14924
14925
14926
14927
14928
14929
14930
14931
14932
14933
14934
14935
14936
14937
14938
14939
14940
14941
14942
14943
14944
14945
14946
14947
14948
14949
14950
14951
14952
14953
14954
14955
14956
14957
14958
14959
14960
14961
14962
14963
14964
14965
14966
14967
14968
14969
14970
14971
14972
14973
14974
14975
14976
14977
14978
14979
14980
14981
14982
14983
14984
14985
14986
14987
14988
14989
14990
14991
14992
14993
14994
14995
14996
14997
14998
14999
15000
15001
15002
15003
15004
15005
15006
15007
15008
15009
15010
15011
15012
15013
15014
15015
15016
15017
15018
15019
15020
15021
15022
15023
15024
15025
15026
15027
15028
15029
15030
15031
15032
15033
15034
15035
15036
15037
15038
15039
15040
15041
15042
15043
15044
15045
15046
15047
15048
15049
15050
15051
15052
15053
15054
15055
15056
15057
15058
15059
15060
15061
15062
15063
15064
15065
15066
15067
15068
15069
15070
15071
15072
15073
15074
15075
15076
15077
15078
15079
15080
15081
15082
15083
15084
15085
15086
15087
15088
15089
15090
15091
15092
15093
15094
15095
15096
15097
15098
15099
15100
15101
15102
15103
15104
15105
15106
15107
15108
15109
15110
15111
15112
15113
15114
15115
15116
15117
15118
15119
15120
15121
15122
15123
15124
15125
15126
15127
15128
15129
15130
15131
15132
15133
15134
15135
15136
15137
15138
15139
15140
15141
15142
15143
15144
15145
15146
15147
15148
15149
15150
15151
15152
15153
15154
15155
15156
15157
15158
15159
15160
15161
15162
15163
15164
15165
15166
15167
15168
15169
15170
15171
15172
15173
15174
15175
15176
15177
15178
15179
15180
15181
15182
15183
15184
15185
15186
15187
15188
15189
15190
15191
15192
15193
15194
15195
15196
15197
15198
15199
15200
15201
15202
15203
15204
15205
15206
15207
15208
15209
15210
15211
15212
15213
15214
15215
15216
15217
15218
15219
15220
15221
15222
15223
15224
15225
15226
15227
15228
15229
15230
15231
15232
15233
15234
15235
15236
15237
15238
15239
15240
15241
15242
15243
15244
15245
15246
15247
15248
15249
15250
15251
15252
15253
15254
15255
15256
15257
15258
15259
15260
15261
15262
15263
15264
15265
15266
15267
15268
15269
15270
15271
15272
15273
15274
15275
15276
15277
15278
15279
15280
15281
15282
15283
15284
15285
15286
15287
15288
15289
15290
15291
15292
15293
15294
15295
15296
15297
15298
15299
15300
15301
15302
15303
15304
15305
15306
15307
15308
15309
15310
15311
15312
15313
15314
15315
15316
15317
15318
15319
15320
15321
15322
15323
15324
15325
15326
15327
15328
15329
15330
15331
15332
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Jan200101 <sentrycraft123@gmail.com>
Date: Wed, 17 Jul 2024 14:30:16 +0200
Subject: [PATCH] scx

Signed-off-by: Jan200101 <sentrycraft123@gmail.com>
---
 Documentation/scheduler/index.rst             |    1 +
 Documentation/scheduler/sched-ext.rst         |  316 +
 MAINTAINERS                                   |   13 +
 include/asm-generic/vmlinux.lds.h             |    1 +
 include/linux/cgroup.h                        |    4 +-
 include/linux/sched.h                         |    5 +
 include/linux/sched/ext.h                     |  206 +
 include/linux/sched/task.h                    |    3 +-
 include/trace/events/sched_ext.h              |   32 +
 include/uapi/linux/sched.h                    |    1 +
 init/init_task.c                              |   12 +
 kernel/Kconfig.preempt                        |   26 +-
 kernel/fork.c                                 |   17 +-
 kernel/sched/build_policy.c                   |   10 +
 kernel/sched/core.c                           |  250 +-
 kernel/sched/cpufreq_schedutil.c              |   50 +-
 kernel/sched/debug.c                          |    3 +
 kernel/sched/ext.c                            | 6537 +++++++++++++++++
 kernel/sched/ext.h                            |   69 +
 kernel/sched/fair.c                           |   27 +-
 kernel/sched/idle.c                           |    2 +
 kernel/sched/sched.h                          |  171 +-
 lib/dump_stack.c                              |    1 +
 tools/Makefile                                |   10 +-
 tools/sched_ext/.gitignore                    |    2 +
 tools/sched_ext/Makefile                      |  246 +
 tools/sched_ext/README.md                     |  258 +
 .../sched_ext/include/bpf-compat/gnu/stubs.h  |   11 +
 tools/sched_ext/include/scx/common.bpf.h      |  401 +
 tools/sched_ext/include/scx/common.h          |   75 +
 tools/sched_ext/include/scx/compat.bpf.h      |   28 +
 tools/sched_ext/include/scx/compat.h          |  187 +
 tools/sched_ext/include/scx/user_exit_info.h  |  111 +
 tools/sched_ext/scx_central.bpf.c             |  361 +
 tools/sched_ext/scx_central.c                 |  135 +
 tools/sched_ext/scx_qmap.bpf.c                |  706 ++
 tools/sched_ext/scx_qmap.c                    |  144 +
 tools/sched_ext/scx_show_state.py             |   39 +
 tools/sched_ext/scx_simple.bpf.c              |  156 +
 tools/sched_ext/scx_simple.c                  |  107 +
 tools/testing/selftests/sched_ext/.gitignore  |    6 +
 tools/testing/selftests/sched_ext/Makefile    |  218 +
 tools/testing/selftests/sched_ext/config      |    9 +
 .../selftests/sched_ext/create_dsq.bpf.c      |   58 +
 .../testing/selftests/sched_ext/create_dsq.c  |   57 +
 .../sched_ext/ddsp_bogus_dsq_fail.bpf.c       |   42 +
 .../selftests/sched_ext/ddsp_bogus_dsq_fail.c |   57 +
 .../sched_ext/ddsp_vtimelocal_fail.bpf.c      |   39 +
 .../sched_ext/ddsp_vtimelocal_fail.c          |   56 +
 .../selftests/sched_ext/dsp_local_on.bpf.c    |   65 +
 .../selftests/sched_ext/dsp_local_on.c        |   58 +
 .../sched_ext/enq_last_no_enq_fails.bpf.c     |   21 +
 .../sched_ext/enq_last_no_enq_fails.c         |   60 +
 .../sched_ext/enq_select_cpu_fails.bpf.c      |   43 +
 .../sched_ext/enq_select_cpu_fails.c          |   61 +
 tools/testing/selftests/sched_ext/exit.bpf.c  |   84 +
 tools/testing/selftests/sched_ext/exit.c      |   55 +
 tools/testing/selftests/sched_ext/exit_test.h |   20 +
 .../testing/selftests/sched_ext/hotplug.bpf.c |   61 +
 tools/testing/selftests/sched_ext/hotplug.c   |  168 +
 .../selftests/sched_ext/hotplug_test.h        |   15 +
 .../sched_ext/init_enable_count.bpf.c         |   53 +
 .../selftests/sched_ext/init_enable_count.c   |  166 +
 .../testing/selftests/sched_ext/maximal.bpf.c |  132 +
 tools/testing/selftests/sched_ext/maximal.c   |   51 +
 .../selftests/sched_ext/maybe_null.bpf.c      |   36 +
 .../testing/selftests/sched_ext/maybe_null.c  |   49 +
 .../sched_ext/maybe_null_fail_dsp.bpf.c       |   25 +
 .../sched_ext/maybe_null_fail_yld.bpf.c       |   28 +
 .../testing/selftests/sched_ext/minimal.bpf.c |   21 +
 tools/testing/selftests/sched_ext/minimal.c   |   58 +
 .../selftests/sched_ext/prog_run.bpf.c        |   32 +
 tools/testing/selftests/sched_ext/prog_run.c  |   78 +
 .../testing/selftests/sched_ext/reload_loop.c |   75 +
 tools/testing/selftests/sched_ext/runner.c    |  201 +
 tools/testing/selftests/sched_ext/scx_test.h  |  131 +
 .../selftests/sched_ext/select_cpu_dfl.bpf.c  |   40 +
 .../selftests/sched_ext/select_cpu_dfl.c      |   72 +
 .../sched_ext/select_cpu_dfl_nodispatch.bpf.c |   89 +
 .../sched_ext/select_cpu_dfl_nodispatch.c     |   72 +
 .../sched_ext/select_cpu_dispatch.bpf.c       |   41 +
 .../selftests/sched_ext/select_cpu_dispatch.c |   70 +
 .../select_cpu_dispatch_bad_dsq.bpf.c         |   37 +
 .../sched_ext/select_cpu_dispatch_bad_dsq.c   |   56 +
 .../select_cpu_dispatch_dbl_dsp.bpf.c         |   38 +
 .../sched_ext/select_cpu_dispatch_dbl_dsp.c   |   56 +
 .../sched_ext/select_cpu_vtime.bpf.c          |   92 +
 .../selftests/sched_ext/select_cpu_vtime.c    |   59 +
 .../selftests/sched_ext/test_example.c        |   49 +
 tools/testing/selftests/sched_ext/util.c      |   71 +
 tools/testing/selftests/sched_ext/util.h      |   13 +
 91 files changed, 13860 insertions(+), 118 deletions(-)
 create mode 100644 Documentation/scheduler/sched-ext.rst
 create mode 100644 include/linux/sched/ext.h
 create mode 100644 include/trace/events/sched_ext.h
 create mode 100644 kernel/sched/ext.c
 create mode 100644 kernel/sched/ext.h
 create mode 100644 tools/sched_ext/.gitignore
 create mode 100644 tools/sched_ext/Makefile
 create mode 100644 tools/sched_ext/README.md
 create mode 100644 tools/sched_ext/include/bpf-compat/gnu/stubs.h
 create mode 100644 tools/sched_ext/include/scx/common.bpf.h
 create mode 100644 tools/sched_ext/include/scx/common.h
 create mode 100644 tools/sched_ext/include/scx/compat.bpf.h
 create mode 100644 tools/sched_ext/include/scx/compat.h
 create mode 100644 tools/sched_ext/include/scx/user_exit_info.h
 create mode 100644 tools/sched_ext/scx_central.bpf.c
 create mode 100644 tools/sched_ext/scx_central.c
 create mode 100644 tools/sched_ext/scx_qmap.bpf.c
 create mode 100644 tools/sched_ext/scx_qmap.c
 create mode 100644 tools/sched_ext/scx_show_state.py
 create mode 100644 tools/sched_ext/scx_simple.bpf.c
 create mode 100644 tools/sched_ext/scx_simple.c
 create mode 100644 tools/testing/selftests/sched_ext/.gitignore
 create mode 100644 tools/testing/selftests/sched_ext/Makefile
 create mode 100644 tools/testing/selftests/sched_ext/config
 create mode 100644 tools/testing/selftests/sched_ext/create_dsq.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/create_dsq.c
 create mode 100644 tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c
 create mode 100644 tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c
 create mode 100644 tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/dsp_local_on.c
 create mode 100644 tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c
 create mode 100644 tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/enq_select_cpu_fails.c
 create mode 100644 tools/testing/selftests/sched_ext/exit.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/exit.c
 create mode 100644 tools/testing/selftests/sched_ext/exit_test.h
 create mode 100644 tools/testing/selftests/sched_ext/hotplug.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/hotplug.c
 create mode 100644 tools/testing/selftests/sched_ext/hotplug_test.h
 create mode 100644 tools/testing/selftests/sched_ext/init_enable_count.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/init_enable_count.c
 create mode 100644 tools/testing/selftests/sched_ext/maximal.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/maximal.c
 create mode 100644 tools/testing/selftests/sched_ext/maybe_null.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/maybe_null.c
 create mode 100644 tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/minimal.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/minimal.c
 create mode 100644 tools/testing/selftests/sched_ext/prog_run.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/prog_run.c
 create mode 100644 tools/testing/selftests/sched_ext/reload_loop.c
 create mode 100644 tools/testing/selftests/sched_ext/runner.c
 create mode 100644 tools/testing/selftests/sched_ext/scx_test.h
 create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dfl.c
 create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c
 create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dispatch.c
 create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c
 create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c
 create mode 100644 tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/select_cpu_vtime.c
 create mode 100644 tools/testing/selftests/sched_ext/test_example.c
 create mode 100644 tools/testing/selftests/sched_ext/util.c
 create mode 100644 tools/testing/selftests/sched_ext/util.h

diff --git a/Documentation/scheduler/index.rst b/Documentation/scheduler/index.rst
index 43bd8a145b7a..0611dc3dda8e 100644
--- a/Documentation/scheduler/index.rst
+++ b/Documentation/scheduler/index.rst
@@ -20,6 +20,7 @@ Scheduler
     sched-nice-design
     sched-rt-group
     sched-stats
+    sched-ext
     sched-debug
 
     text_files
diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst
new file mode 100644
index 000000000000..a707d2181a77
--- /dev/null
+++ b/Documentation/scheduler/sched-ext.rst
@@ -0,0 +1,316 @@
+==========================
+Extensible Scheduler Class
+==========================
+
+sched_ext is a scheduler class whose behavior can be defined by a set of BPF
+programs - the BPF scheduler.
+
+* sched_ext exports a full scheduling interface so that any scheduling
+  algorithm can be implemented on top.
+
+* The BPF scheduler can group CPUs however it sees fit and schedule them
+  together, as tasks aren't tied to specific CPUs at the time of wakeup.
+
+* The BPF scheduler can be turned on and off dynamically anytime.
+
+* The system integrity is maintained no matter what the BPF scheduler does.
+  The default scheduling behavior is restored anytime an error is detected,
+  a runnable task stalls, or on invoking the SysRq key sequence
+  :kbd:`SysRq-S`.
+
+* When the BPF scheduler triggers an error, debug information is dumped to
+  aid debugging. The debug dump is passed to and printed out by the
+  scheduler binary. The debug dump can also be accessed through the
+  `sched_ext_dump` tracepoint. The SysRq key sequence :kbd:`SysRq-D`
+  triggers a debug dump. This doesn't terminate the BPF scheduler and can
+  only be read through the tracepoint.
+
+Switching to and from sched_ext
+===============================
+
+``CONFIG_SCHED_CLASS_EXT`` is the config option to enable sched_ext and
+``tools/sched_ext`` contains the example schedulers. The following config
+options should be enabled to use sched_ext:
+
+.. code-block:: none
+
+    CONFIG_BPF=y
+    CONFIG_SCHED_CLASS_EXT=y
+    CONFIG_BPF_SYSCALL=y
+    CONFIG_BPF_JIT=y
+    CONFIG_DEBUG_INFO_BTF=y
+    CONFIG_BPF_JIT_ALWAYS_ON=y
+    CONFIG_BPF_JIT_DEFAULT_ON=y
+    CONFIG_PAHOLE_HAS_SPLIT_BTF=y
+    CONFIG_PAHOLE_HAS_BTF_TAG=y
+
+sched_ext is used only when the BPF scheduler is loaded and running.
+
+If a task explicitly sets its scheduling policy to ``SCHED_EXT``, it will be
+treated as ``SCHED_NORMAL`` and scheduled by CFS until the BPF scheduler is
+loaded.
+
+When the BPF scheduler is loaded and ``SCX_OPS_SWITCH_PARTIAL`` is not set
+in ``ops->flags``, all ``SCHED_NORMAL``, ``SCHED_BATCH``, ``SCHED_IDLE``, and
+``SCHED_EXT`` tasks are scheduled by sched_ext.
+
+However, when the BPF scheduler is loaded and ``SCX_OPS_SWITCH_PARTIAL`` is
+set in ``ops->flags``, only tasks with the ``SCHED_EXT`` policy are scheduled
+by sched_ext, while tasks with ``SCHED_NORMAL``, ``SCHED_BATCH`` and
+``SCHED_IDLE`` policies are scheduled by CFS.
+
+Terminating the sched_ext scheduler program, triggering :kbd:`SysRq-S`, or
+detection of any internal error including stalled runnable tasks aborts the
+BPF scheduler and reverts all tasks back to CFS.
+
+.. code-block:: none
+
+    # make -j16 -C tools/sched_ext
+    # tools/sched_ext/scx_simple
+    local=0 global=3
+    local=5 global=24
+    local=9 global=44
+    local=13 global=56
+    local=17 global=72
+    ^CEXIT: BPF scheduler unregistered
+
+The current status of the BPF scheduler can be determined as follows:
+
+.. code-block:: none
+
+    # cat /sys/kernel/sched_ext/state
+    enabled
+    # cat /sys/kernel/sched_ext/root/ops
+    simple
+
+``tools/sched_ext/scx_show_state.py`` is a drgn script which shows more
+detailed information:
+
+.. code-block:: none
+
+    # tools/sched_ext/scx_show_state.py
+    ops           : simple
+    enabled       : 1
+    switching_all : 1
+    switched_all  : 1
+    enable_state  : enabled (2)
+    bypass_depth  : 0
+    nr_rejected   : 0
+
+If ``CONFIG_SCHED_DEBUG`` is set, whether a given task is on sched_ext can
+be determined as follows:
+
+.. code-block:: none
+
+    # grep ext /proc/self/sched
+    ext.enabled                                  :                    1
+
+The Basics
+==========
+
+Userspace can implement an arbitrary BPF scheduler by loading a set of BPF
+programs that implement ``struct sched_ext_ops``. The only mandatory field
+is ``ops.name`` which must be a valid BPF object name. All operations are
+optional. The following modified excerpt is from
+``tools/sched_ext/scx_simple.bpf.c`` showing a minimal global FIFO scheduler.
+
+.. code-block:: c
+
+    /*
+     * Decide which CPU a task should be migrated to before being
+     * enqueued (either at wakeup, fork time, or exec time). If an
+     * idle core is found by the default ops.select_cpu() implementation,
+     * then dispatch the task directly to SCX_DSQ_LOCAL and skip the
+     * ops.enqueue() callback.
+     *
+     * Note that this implementation has exactly the same behavior as the
+     * default ops.select_cpu implementation. The behavior of the scheduler
+     * would be exactly same if the implementation just didn't define the
+     * simple_select_cpu() struct_ops prog.
+     */
+    s32 BPF_STRUCT_OPS(simple_select_cpu, struct task_struct *p,
+                       s32 prev_cpu, u64 wake_flags)
+    {
+            s32 cpu;
+            /* Need to initialize or the BPF verifier will reject the program */
+            bool direct = false;
+
+            cpu = scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags, &direct);
+
+            if (direct)
+                    scx_bpf_dispatch(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0);
+
+            return cpu;
+    }
+
+    /*
+     * Do a direct dispatch of a task to the global DSQ. This ops.enqueue()
+     * callback will only be invoked if we failed to find a core to dispatch
+     * to in ops.select_cpu() above.
+     *
+     * Note that this implementation has exactly the same behavior as the
+     * default ops.enqueue implementation, which just dispatches the task
+     * to SCX_DSQ_GLOBAL. The behavior of the scheduler would be exactly same
+     * if the implementation just didn't define the simple_enqueue struct_ops
+     * prog.
+     */
+    void BPF_STRUCT_OPS(simple_enqueue, struct task_struct *p, u64 enq_flags)
+    {
+            scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+    }
+
+    s32 BPF_STRUCT_OPS_SLEEPABLE(simple_init)
+    {
+            /*
+             * By default, all SCHED_EXT, SCHED_OTHER, SCHED_IDLE, and
+             * SCHED_BATCH tasks should use sched_ext.
+             */
+            return 0;
+    }
+
+    void BPF_STRUCT_OPS(simple_exit, struct scx_exit_info *ei)
+    {
+            exit_type = ei->type;
+    }
+
+    SEC(".struct_ops")
+    struct sched_ext_ops simple_ops = {
+            .select_cpu             = (void *)simple_select_cpu,
+            .enqueue                = (void *)simple_enqueue,
+            .init                   = (void *)simple_init,
+            .exit                   = (void *)simple_exit,
+            .name                   = "simple",
+    };
+
+Dispatch Queues
+---------------
+
+To match the impedance between the scheduler core and the BPF scheduler,
+sched_ext uses DSQs (dispatch queues) which can operate as both a FIFO and a
+priority queue. By default, there is one global FIFO (``SCX_DSQ_GLOBAL``),
+and one local dsq per CPU (``SCX_DSQ_LOCAL``). The BPF scheduler can manage
+an arbitrary number of dsq's using ``scx_bpf_create_dsq()`` and
+``scx_bpf_destroy_dsq()``.
+
+A CPU always executes a task from its local DSQ. A task is "dispatched" to a
+DSQ. A non-local DSQ is "consumed" to transfer a task to the consuming CPU's
+local DSQ.
+
+When a CPU is looking for the next task to run, if the local DSQ is not
+empty, the first task is picked. Otherwise, the CPU tries to consume the
+global DSQ. If that doesn't yield a runnable task either, ``ops.dispatch()``
+is invoked.
+
+Scheduling Cycle
+----------------
+
+The following briefly shows how a waking task is scheduled and executed.
+
+1. When a task is waking up, ``ops.select_cpu()`` is the first operation
+   invoked. This serves two purposes. First, CPU selection optimization
+   hint. Second, waking up the selected CPU if idle.
+
+   The CPU selected by ``ops.select_cpu()`` is an optimization hint and not
+   binding. The actual decision is made at the last step of scheduling.
+   However, there is a small performance gain if the CPU
+   ``ops.select_cpu()`` returns matches the CPU the task eventually runs on.
+
+   A side-effect of selecting a CPU is waking it up from idle. While a BPF
+   scheduler can wake up any cpu using the ``scx_bpf_kick_cpu()`` helper,
+   using ``ops.select_cpu()`` judiciously can be simpler and more efficient.
+
+   A task can be immediately dispatched to a DSQ from ``ops.select_cpu()`` by
+   calling ``scx_bpf_dispatch()``. If the task is dispatched to
+   ``SCX_DSQ_LOCAL`` from ``ops.select_cpu()``, it will be dispatched to the
+   local DSQ of whichever CPU is returned from ``ops.select_cpu()``.
+   Additionally, dispatching directly from ``ops.select_cpu()`` will cause the
+   ``ops.enqueue()`` callback to be skipped.
+
+   Note that the scheduler core will ignore an invalid CPU selection, for
+   example, if it's outside the allowed cpumask of the task.
+
+2. Once the target CPU is selected, ``ops.enqueue()`` is invoked (unless the
+   task was dispatched directly from ``ops.select_cpu()``). ``ops.enqueue()``
+   can make one of the following decisions:
+
+   * Immediately dispatch the task to either the global or local DSQ by
+     calling ``scx_bpf_dispatch()`` with ``SCX_DSQ_GLOBAL`` or
+     ``SCX_DSQ_LOCAL``, respectively.
+
+   * Immediately dispatch the task to a custom DSQ by calling
+     ``scx_bpf_dispatch()`` with a DSQ ID which is smaller than 2^63.
+
+   * Queue the task on the BPF side.
+
+3. When a CPU is ready to schedule, it first looks at its local DSQ. If
+   empty, it then looks at the global DSQ. If there still isn't a task to
+   run, ``ops.dispatch()`` is invoked which can use the following two
+   functions to populate the local DSQ.
+
+   * ``scx_bpf_dispatch()`` dispatches a task to a DSQ. Any target DSQ can
+     be used - ``SCX_DSQ_LOCAL``, ``SCX_DSQ_LOCAL_ON | cpu``,
+     ``SCX_DSQ_GLOBAL`` or a custom DSQ. While ``scx_bpf_dispatch()``
+     currently can't be called with BPF locks held, this is being worked on
+     and will be supported. ``scx_bpf_dispatch()`` schedules dispatching
+     rather than performing them immediately. There can be up to
+     ``ops.dispatch_max_batch`` pending tasks.
+
+   * ``scx_bpf_consume()`` tranfers a task from the specified non-local DSQ
+     to the dispatching DSQ. This function cannot be called with any BPF
+     locks held. ``scx_bpf_consume()`` flushes the pending dispatched tasks
+     before trying to consume the specified DSQ.
+
+4. After ``ops.dispatch()`` returns, if there are tasks in the local DSQ,
+   the CPU runs the first one. If empty, the following steps are taken:
+
+   * Try to consume the global DSQ. If successful, run the task.
+
+   * If ``ops.dispatch()`` has dispatched any tasks, retry #3.
+
+   * If the previous task is an SCX task and still runnable, keep executing
+     it (see ``SCX_OPS_ENQ_LAST``).
+
+   * Go idle.
+
+Note that the BPF scheduler can always choose to dispatch tasks immediately
+in ``ops.enqueue()`` as illustrated in the above simple example. If only the
+built-in DSQs are used, there is no need to implement ``ops.dispatch()`` as
+a task is never queued on the BPF scheduler and both the local and global
+DSQs are consumed automatically.
+
+``scx_bpf_dispatch()`` queues the task on the FIFO of the target DSQ. Use
+``scx_bpf_dispatch_vtime()`` for the priority queue. Internal DSQs such as
+``SCX_DSQ_LOCAL`` and ``SCX_DSQ_GLOBAL`` do not support priority-queue
+dispatching, and must be dispatched to with ``scx_bpf_dispatch()``.  See the
+function documentation and usage in ``tools/sched_ext/scx_simple.bpf.c`` for
+more information.
+
+Where to Look
+=============
+
+* ``include/linux/sched/ext.h`` defines the core data structures, ops table
+  and constants.
+
+* ``kernel/sched/ext.c`` contains sched_ext core implementation and helpers.
+  The functions prefixed with ``scx_bpf_`` can be called from the BPF
+  scheduler.
+
+* ``tools/sched_ext/`` hosts example BPF scheduler implementations.
+
+  * ``scx_simple[.bpf].c``: Minimal global FIFO scheduler example using a
+    custom DSQ.
+
+  * ``scx_qmap[.bpf].c``: A multi-level FIFO scheduler supporting five
+    levels of priority implemented with ``BPF_MAP_TYPE_QUEUE``.
+
+ABI Instability
+===============
+
+The APIs provided by sched_ext to BPF schedulers programs have no stability
+guarantees. This includes the ops table callbacks and constants defined in
+``include/linux/sched/ext.h``, as well as the ``scx_bpf_`` kfuncs defined in
+``kernel/sched/ext.c``.
+
+While we will attempt to provide a relatively stable API surface when
+possible, they are subject to change without warning between kernel
+versions.
diff --git a/MAINTAINERS b/MAINTAINERS
index 3121709d99e3..bf3b77e96dc4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19623,6 +19623,19 @@ F:	include/linux/wait.h
 F:	include/uapi/linux/sched.h
 F:	kernel/sched/
 
+SCHEDULER - SCHED_EXT
+R:	Tejun Heo <tj@kernel.org>
+R:	David Vernet <void@manifault.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+W:	https://github.com/sched-ext/scx
+T:	git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git
+F:	include/linux/sched/ext.h
+F:	kernel/sched/ext.h
+F:	kernel/sched/ext.c
+F:	tools/sched_ext/
+F:	tools/testing/selftests/sched_ext
+
 SCSI LIBSAS SUBSYSTEM
 R:	John Garry <john.g.garry@oracle.com>
 R:	Jason Yan <yanaijie@huawei.com>
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index f7749d0f2562..05bfe4acba1d 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -131,6 +131,7 @@
 	*(__dl_sched_class)			\
 	*(__rt_sched_class)			\
 	*(__fair_sched_class)			\
+	*(__ext_sched_class)			\
 	*(__idle_sched_class)			\
 	__sched_class_lowest = .;
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 34aaf0e87def..bcebf8096e91 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -29,8 +29,6 @@
 
 struct kernel_clone_args;
 
-#ifdef CONFIG_CGROUPS
-
 /*
  * All weight knobs on the default hierarchy should use the following min,
  * default and max values.  The default value is the logarithmic center of
@@ -40,6 +38,8 @@ struct kernel_clone_args;
 #define CGROUP_WEIGHT_DFL		100
 #define CGROUP_WEIGHT_MAX		10000
 
+#ifdef CONFIG_CGROUPS
+
 enum {
 	CSS_TASK_ITER_PROCS    = (1U << 0),  /* walk only threadgroup leaders */
 	CSS_TASK_ITER_THREADED = (1U << 1),  /* walk all threaded css_sets in the domain */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3c2abbc587b4..dc07eb0d3290 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -80,6 +80,8 @@ struct task_group;
 struct task_struct;
 struct user_event_mm;
 
+#include <linux/sched/ext.h>
+
 /*
  * Task state bitmask. NOTE! These bits are also
  * encoded in fs/proc/array.c: get_task_state().
@@ -798,6 +800,9 @@ struct task_struct {
 	struct sched_rt_entity		rt;
 	struct sched_dl_entity		dl;
 	struct sched_dl_entity		*dl_server;
+#ifdef CONFIG_SCHED_CLASS_EXT
+	struct sched_ext_entity		scx;
+#endif
 	const struct sched_class	*sched_class;
 
 #ifdef CONFIG_SCHED_CORE
diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
new file mode 100644
index 000000000000..593d2f4909dd
--- /dev/null
+++ b/include/linux/sched/ext.h
@@ -0,0 +1,206 @@
+/* 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>
+ */
+#ifndef _LINUX_SCHED_EXT_H
+#define _LINUX_SCHED_EXT_H
+
+#ifdef CONFIG_SCHED_CLASS_EXT
+
+#include <linux/llist.h>
+#include <linux/rhashtable-types.h>
+
+enum scx_public_consts {
+	SCX_OPS_NAME_LEN	= 128,
+
+	SCX_SLICE_DFL		= 20 * 1000000,	/* 20ms */
+	SCX_SLICE_INF		= U64_MAX,	/* infinite, implies nohz */
+};
+
+/*
+ * DSQ (dispatch queue) IDs are 64bit of the format:
+ *
+ *   Bits: [63] [62 ..  0]
+ *         [ B] [   ID   ]
+ *
+ *    B: 1 for IDs for built-in DSQs, 0 for ops-created user DSQs
+ *   ID: 63 bit ID
+ *
+ * Built-in IDs:
+ *
+ *   Bits: [63] [62] [61..32] [31 ..  0]
+ *         [ 1] [ L] [   R  ] [    V   ]
+ *
+ *    1: 1 for built-in DSQs.
+ *    L: 1 for LOCAL_ON DSQ IDs, 0 for others
+ *    V: For LOCAL_ON DSQ IDs, a CPU number. For others, a pre-defined value.
+ */
+enum scx_dsq_id_flags {
+	SCX_DSQ_FLAG_BUILTIN	= 1LLU << 63,
+	SCX_DSQ_FLAG_LOCAL_ON	= 1LLU << 62,
+
+	SCX_DSQ_INVALID		= SCX_DSQ_FLAG_BUILTIN | 0,
+	SCX_DSQ_GLOBAL		= SCX_DSQ_FLAG_BUILTIN | 1,
+	SCX_DSQ_LOCAL		= SCX_DSQ_FLAG_BUILTIN | 2,
+	SCX_DSQ_LOCAL_ON	= SCX_DSQ_FLAG_BUILTIN | SCX_DSQ_FLAG_LOCAL_ON,
+	SCX_DSQ_LOCAL_CPU_MASK	= 0xffffffffLLU,
+};
+
+/*
+ * A dispatch queue (DSQ) can be either a FIFO or p->scx.dsq_vtime ordered
+ * queue. A built-in DSQ is always a FIFO. The built-in local DSQs are used to
+ * buffer between the scheduler core and the BPF scheduler. See the
+ * documentation for more details.
+ */
+struct scx_dispatch_q {
+	raw_spinlock_t		lock;
+	struct list_head	list;	/* tasks in dispatch order */
+	struct rb_root		priq;	/* used to order by p->scx.dsq_vtime */
+	u32			nr;
+	u32			seq;	/* used by BPF iter */
+	u64			id;
+	struct rhash_head	hash_node;
+	struct llist_node	free_node;
+	struct rcu_head		rcu;
+};
+
+/* scx_entity.flags */
+enum scx_ent_flags {
+	SCX_TASK_QUEUED		= 1 << 0, /* on ext runqueue */
+	SCX_TASK_BAL_KEEP	= 1 << 1, /* balance decided to keep current */
+	SCX_TASK_RESET_RUNNABLE_AT = 1 << 2, /* runnable_at should be reset */
+	SCX_TASK_DEQD_FOR_SLEEP	= 1 << 3, /* last dequeue was for SLEEP */
+
+	SCX_TASK_STATE_SHIFT	= 8,	  /* bit 8 and 9 are used to carry scx_task_state */
+	SCX_TASK_STATE_BITS	= 2,
+	SCX_TASK_STATE_MASK	= ((1 << SCX_TASK_STATE_BITS) - 1) << SCX_TASK_STATE_SHIFT,
+
+	SCX_TASK_CURSOR		= 1 << 31, /* iteration cursor, not a task */
+};
+
+/* scx_entity.flags & SCX_TASK_STATE_MASK */
+enum scx_task_state {
+	SCX_TASK_NONE,		/* ops.init_task() not called yet */
+	SCX_TASK_INIT,		/* ops.init_task() succeeded, but task can be cancelled */
+	SCX_TASK_READY,		/* fully initialized, but not in sched_ext */
+	SCX_TASK_ENABLED,	/* fully initialized and in sched_ext */
+
+	SCX_TASK_NR_STATES,
+};
+
+/* scx_entity.dsq_flags */
+enum scx_ent_dsq_flags {
+	SCX_TASK_DSQ_ON_PRIQ	= 1 << 0, /* task is queued on the priority queue of a dsq */
+};
+
+/*
+ * Mask bits for scx_entity.kf_mask. Not all kfuncs can be called from
+ * everywhere and the following bits track which kfunc sets are currently
+ * allowed for %current. This simple per-task tracking works because SCX ops
+ * nest in a limited way. BPF will likely implement a way to allow and disallow
+ * kfuncs depending on the calling context which will replace this manual
+ * mechanism. See scx_kf_allow().
+ */
+enum scx_kf_mask {
+	SCX_KF_UNLOCKED		= 0,	  /* not sleepable, not rq locked */
+	/* all non-sleepables may be nested inside SLEEPABLE */
+	SCX_KF_SLEEPABLE	= 1 << 0, /* sleepable init operations */
+	/* ENQUEUE and DISPATCH may be nested inside CPU_RELEASE */
+	SCX_KF_CPU_RELEASE	= 1 << 1, /* ops.cpu_release() */
+	/* ops.dequeue (in REST) may be nested inside DISPATCH */
+	SCX_KF_DISPATCH		= 1 << 2, /* ops.dispatch() */
+	SCX_KF_ENQUEUE		= 1 << 3, /* ops.enqueue() and ops.select_cpu() */
+	SCX_KF_SELECT_CPU	= 1 << 4, /* ops.select_cpu() */
+	SCX_KF_REST		= 1 << 5, /* other rq-locked operations */
+
+	__SCX_KF_RQ_LOCKED	= SCX_KF_CPU_RELEASE | SCX_KF_DISPATCH |
+				  SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST,
+	__SCX_KF_TERMINAL	= SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST,
+};
+
+struct scx_dsq_list_node {
+	struct list_head	node;
+	bool			is_bpf_iter_cursor;
+};
+
+/*
+ * The following is embedded in task_struct and contains all fields necessary
+ * for a task to be scheduled by SCX.
+ */
+struct sched_ext_entity {
+	struct scx_dispatch_q	*dsq;
+	struct scx_dsq_list_node dsq_list;	/* dispatch order */
+	struct rb_node		dsq_priq;	/* p->scx.dsq_vtime order */
+	u32			dsq_seq;
+	u32			dsq_flags;	/* protected by DSQ lock */
+	u32			flags;		/* protected by rq lock */
+	u32			weight;
+	s32			sticky_cpu;
+	s32			holding_cpu;
+	u32			kf_mask;	/* see scx_kf_mask above */
+	struct task_struct	*kf_tasks[2];	/* see SCX_CALL_OP_TASK() */
+	atomic_long_t		ops_state;
+
+	struct list_head	runnable_node;	/* rq->scx.runnable_list */
+	unsigned long		runnable_at;
+
+#ifdef CONFIG_SCHED_CORE
+	u64			core_sched_at;	/* see scx_prio_less() */
+#endif
+	u64			ddsp_dsq_id;
+	u64			ddsp_enq_flags;
+
+	/* BPF scheduler modifiable fields */
+
+	/*
+	 * Runtime budget in nsecs. This is usually set through
+	 * scx_bpf_dispatch() but can also be modified directly by the BPF
+	 * scheduler. Automatically decreased by SCX as the task executes. On
+	 * depletion, a scheduling event is triggered.
+	 *
+	 * This value is cleared to zero if the task is preempted by
+	 * %SCX_KICK_PREEMPT and shouldn't be used to determine how long the
+	 * task ran. Use p->se.sum_exec_runtime instead.
+	 */
+	u64			slice;
+
+	/*
+	 * Used to order tasks when dispatching to the vtime-ordered priority
+	 * queue of a dsq. This is usually set through scx_bpf_dispatch_vtime()
+	 * but can also be modified directly by the BPF scheduler. Modifying it
+	 * while a task is queued on a dsq may mangle the ordering and is not
+	 * recommended.
+	 */
+	u64			dsq_vtime;
+
+	/*
+	 * If set, reject future sched_setscheduler(2) calls updating the policy
+	 * to %SCHED_EXT with -%EACCES.
+	 *
+	 * If set from ops.init_task() and the task's policy is already
+	 * %SCHED_EXT, which can happen while the BPF scheduler is being loaded
+	 * or by inhering the parent's policy during fork, the task's policy is
+	 * rejected and forcefully reverted to %SCHED_NORMAL. The number of
+	 * such events are reported through /sys/kernel/debug/sched_ext::nr_rejected.
+	 */
+	bool			disallow;	/* reject switching into SCX */
+
+	/* cold fields */
+	/* must be the last field, see init_scx_entity() */
+	struct list_head	tasks_node;
+};
+
+void sched_ext_free(struct task_struct *p);
+void print_scx_info(const char *log_lvl, struct task_struct *p);
+
+#else	/* !CONFIG_SCHED_CLASS_EXT */
+
+static inline void sched_ext_free(struct task_struct *p) {}
+static inline void print_scx_info(const char *log_lvl, struct task_struct *p) {}
+
+#endif	/* CONFIG_SCHED_CLASS_EXT */
+#endif	/* _LINUX_SCHED_EXT_H */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index d362aacf9f89..4df2f9055587 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -63,7 +63,8 @@ extern asmlinkage void schedule_tail(struct task_struct *prev);
 extern void init_idle(struct task_struct *idle, int cpu);
 
 extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
-extern void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs);
+extern int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs);
+extern void sched_cancel_fork(struct task_struct *p);
 extern void sched_post_fork(struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 
diff --git a/include/trace/events/sched_ext.h b/include/trace/events/sched_ext.h
new file mode 100644
index 000000000000..fe19da7315a9
--- /dev/null
+++ b/include/trace/events/sched_ext.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM sched_ext
+
+#if !defined(_TRACE_SCHED_EXT_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SCHED_EXT_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(sched_ext_dump,
+
+	TP_PROTO(const char *line),
+
+	TP_ARGS(line),
+
+	TP_STRUCT__entry(
+		__string(line, line)
+	),
+
+	TP_fast_assign(
+		__assign_str(line, line);
+	),
+
+	TP_printk("%s",
+		__get_str(line)
+	)
+);
+
+#endif /* _TRACE_SCHED_EXT_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 3bac0a8ceab2..359a14cc76a4 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -118,6 +118,7 @@ struct clone_args {
 /* SCHED_ISO: reserved but not implemented yet */
 #define SCHED_IDLE		5
 #define SCHED_DEADLINE		6
+#define SCHED_EXT		7
 
 /* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
 #define SCHED_RESET_ON_FORK     0x40000000
diff --git a/init/init_task.c b/init/init_task.c
index 4daee6d761c8..ce882dbd2635 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -6,6 +6,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/task.h>
+#include <linux/sched/ext.h>
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
@@ -97,6 +98,17 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
 #endif
 #ifdef CONFIG_CGROUP_SCHED
 	.sched_task_group = &root_task_group,
+#endif
+#ifdef CONFIG_SCHED_CLASS_EXT
+	.scx		= {
+		.dsq_list.node	= LIST_HEAD_INIT(init_task.scx.dsq_list.node),
+		.sticky_cpu	= -1,
+		.holding_cpu	= -1,
+		.runnable_node	= LIST_HEAD_INIT(init_task.scx.runnable_node),
+		.runnable_at	= INITIAL_JIFFIES,
+		.ddsp_dsq_id	= SCX_DSQ_INVALID,
+		.slice		= SCX_SLICE_DFL,
+	},
 #endif
 	.ptraced	= LIST_HEAD_INIT(init_task.ptraced),
 	.ptrace_entry	= LIST_HEAD_INIT(init_task.ptrace_entry),
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index c2f1fd95a821..f3d140c3acc1 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -133,4 +133,28 @@ config SCHED_CORE
 	  which is the likely usage by Linux distributions, there should
 	  be no measurable impact on performance.
 
-
+config SCHED_CLASS_EXT
+	bool "Extensible Scheduling Class"
+	depends on BPF_SYSCALL && BPF_JIT && DEBUG_INFO_BTF
+	help
+	  This option enables a new scheduler class sched_ext (SCX), which
+	  allows scheduling policies to be implemented as BPF programs to
+	  achieve the following:
+
+	  - Ease of experimentation and exploration: Enabling rapid
+	    iteration of new scheduling policies.
+	  - Customization: Building application-specific schedulers which
+	    implement policies that are not applicable to general-purpose
+	    schedulers.
+	  - Rapid scheduler deployments: Non-disruptive swap outs of
+	    scheduling policies in production environments.
+
+	  sched_ext leverages BPF struct_ops feature to define a structure
+	  which exports function callbacks and flags to BPF programs that
+	  wish to implement scheduling policies. The struct_ops structure
+	  exported by sched_ext is struct sched_ext_ops, and is conceptually
+	  similar to struct sched_class.
+
+	  For more information:
+	    Documentation/scheduler/sched-ext.rst
+	    https://github.com/sched-ext/scx
diff --git a/kernel/fork.c b/kernel/fork.c
index aebb3e6c96dc..5d1f9de254d6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -23,6 +23,7 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/ext.h>
 #include <linux/seq_file.h>
 #include <linux/rtmutex.h>
 #include <linux/init.h>
@@ -971,6 +972,7 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(refcount_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
+	sched_ext_free(tsk);
 	io_uring_free(tsk);
 	cgroup_free(tsk);
 	task_numa_free(tsk, true);
@@ -2363,7 +2365,7 @@ __latent_entropy struct task_struct *copy_process(
 
 	retval = perf_event_init_task(p, clone_flags);
 	if (retval)
-		goto bad_fork_cleanup_policy;
+		goto bad_fork_sched_cancel_fork;
 	retval = audit_alloc(p);
 	if (retval)
 		goto bad_fork_cleanup_perf;
@@ -2496,7 +2498,9 @@ __latent_entropy struct task_struct *copy_process(
 	 * cgroup specific, it unconditionally needs to place the task on a
 	 * runqueue.
 	 */
-	sched_cgroup_fork(p, args);
+	retval = sched_cgroup_fork(p, args);
+	if (retval)
+		goto bad_fork_cancel_cgroup;
 
 	/*
 	 * From this point on we must avoid any synchronous user-space
@@ -2542,13 +2546,13 @@ __latent_entropy struct task_struct *copy_process(
 	/* Don't start children in a dying pid namespace */
 	if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) {
 		retval = -ENOMEM;
-		goto bad_fork_cancel_cgroup;
+		goto bad_fork_core_free;
 	}
 
 	/* Let kill terminate clone/fork in the middle */
 	if (fatal_signal_pending(current)) {
 		retval = -EINTR;
-		goto bad_fork_cancel_cgroup;
+		goto bad_fork_core_free;
 	}
 
 	/* No more failure paths after this point. */
@@ -2622,10 +2626,11 @@ __latent_entropy struct task_struct *copy_process(
 
 	return p;
 
-bad_fork_cancel_cgroup:
+bad_fork_core_free:
 	sched_core_free(p);
 	spin_unlock(&current->sighand->siglock);
 	write_unlock_irq(&tasklist_lock);
+bad_fork_cancel_cgroup:
 	cgroup_cancel_fork(p, args);
 bad_fork_put_pidfd:
 	if (clone_flags & CLONE_PIDFD) {
@@ -2664,6 +2669,8 @@ __latent_entropy struct task_struct *copy_process(
 	audit_free(p);
 bad_fork_cleanup_perf:
 	perf_event_free_task(p);
+bad_fork_sched_cancel_fork:
+	sched_cancel_fork(p);
 bad_fork_cleanup_policy:
 	lockdep_free_task(p);
 #ifdef CONFIG_NUMA
diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c
index d9dc9ab3773f..e7d539bb721e 100644
--- a/kernel/sched/build_policy.c
+++ b/kernel/sched/build_policy.c
@@ -16,18 +16,25 @@
 #include <linux/sched/clock.h>
 #include <linux/sched/cputime.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/isolation.h>
 #include <linux/sched/posix-timers.h>
 #include <linux/sched/rt.h>
 
 #include <linux/cpuidle.h>
 #include <linux/jiffies.h>
+#include <linux/kobject.h>
 #include <linux/livepatch.h>
+#include <linux/pm.h>
 #include <linux/psi.h>
+#include <linux/rhashtable.h>
+#include <linux/seq_buf.h>
 #include <linux/seqlock_api.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
 #include <linux/tsacct_kern.h>
 #include <linux/vtime.h>
+#include <linux/sysrq.h>
+#include <linux/percpu-rwsem.h>
 
 #include <uapi/linux/sched/types.h>
 
@@ -52,3 +59,6 @@
 #include "cputime.c"
 #include "deadline.c"
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+# include "ext.c"
+#endif
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d211d40a2edc..e5a6766b3a45 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -168,7 +168,10 @@ static inline int __task_prio(const struct task_struct *p)
 	if (p->sched_class == &idle_sched_class)
 		return MAX_RT_PRIO + NICE_WIDTH; /* 140 */
 
-	return MAX_RT_PRIO + MAX_NICE; /* 120, squash fair */
+	if (task_on_scx(p))
+		return MAX_RT_PRIO + MAX_NICE + 1; /* 120, squash ext */
+
+	return MAX_RT_PRIO + MAX_NICE; /* 119, squash fair */
 }
 
 /*
@@ -197,6 +200,11 @@ static inline bool prio_less(const struct task_struct *a,
 	if (pa == MAX_RT_PRIO + MAX_NICE)	/* fair */
 		return cfs_prio_less(a, b, in_fi);
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+	if (pa == MAX_RT_PRIO + MAX_NICE + 1)	/* ext */
+		return scx_prio_less(a, b, in_fi);
+#endif
+
 	return false;
 }
 
@@ -1255,11 +1263,14 @@ bool sched_can_stop_tick(struct rq *rq)
 		return true;
 
 	/*
-	 * If there are no DL,RR/FIFO tasks, there must only be CFS tasks left;
-	 * if there's more than one we need the tick for involuntary
-	 * preemption.
+	 * If there are no DL,RR/FIFO tasks, there must only be CFS or SCX tasks
+	 * left. For CFS, if there's more than one we need the tick for
+	 * involuntary preemption. For SCX, ask.
 	 */
-	if (rq->nr_running > 1)
+	if (!scx_switched_all() && rq->nr_running > 1)
+		return false;
+
+	if (scx_enabled() && !scx_can_stop_tick(rq))
 		return false;
 
 	/*
@@ -1327,27 +1338,24 @@ int tg_nop(struct task_group *tg, void *data)
 static void set_load_weight(struct task_struct *p, bool update_load)
 {
 	int prio = p->static_prio - MAX_RT_PRIO;
-	struct load_weight *load = &p->se.load;
+	struct load_weight lw;
 
-	/*
-	 * SCHED_IDLE tasks get minimal weight:
-	 */
 	if (task_has_idle_policy(p)) {
-		load->weight = scale_load(WEIGHT_IDLEPRIO);
-		load->inv_weight = WMULT_IDLEPRIO;
-		return;
+		lw.weight = scale_load(WEIGHT_IDLEPRIO);
+		lw.inv_weight = WMULT_IDLEPRIO;
+	} else {
+		lw.weight = scale_load(sched_prio_to_weight[prio]);
+		lw.inv_weight = sched_prio_to_wmult[prio];
 	}
 
 	/*
 	 * SCHED_OTHER tasks have to update their load when changing their
 	 * weight
 	 */
-	if (update_load && p->sched_class == &fair_sched_class) {
-		reweight_task(p, prio);
-	} else {
-		load->weight = scale_load(sched_prio_to_weight[prio]);
-		load->inv_weight = sched_prio_to_wmult[prio];
-	}
+	if (update_load && p->sched_class->reweight_task)
+		p->sched_class->reweight_task(task_rq(p), p, &lw);
+	else
+		p->se.load = lw;
 }
 
 #ifdef CONFIG_UCLAMP_TASK
@@ -2214,6 +2222,17 @@ inline int task_curr(const struct task_struct *p)
 	return cpu_curr(task_cpu(p)) == p;
 }
 
+/*
+ * ->switching_to() is called with the pi_lock and rq_lock held and must not
+ * mess with locking.
+ */
+void check_class_changing(struct rq *rq, struct task_struct *p,
+			  const struct sched_class *prev_class)
+{
+	if (prev_class != p->sched_class && p->sched_class->switching_to)
+		p->sched_class->switching_to(rq, p);
+}
+
 /*
  * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock,
  * use the balance_callback list if you want balancing.
@@ -2221,9 +2240,9 @@ inline int task_curr(const struct task_struct *p)
  * this means any call to check_class_changed() must be followed by a call to
  * balance_callback().
  */
-static inline void check_class_changed(struct rq *rq, struct task_struct *p,
-				       const struct sched_class *prev_class,
-				       int oldprio)
+void check_class_changed(struct rq *rq, struct task_struct *p,
+			 const struct sched_class *prev_class,
+			 int oldprio)
 {
 	if (prev_class != p->sched_class) {
 		if (prev_class->switched_from)
@@ -3986,6 +4005,15 @@ bool cpus_share_resources(int this_cpu, int that_cpu)
 
 static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
 {
+	/*
+	 * The BPF scheduler may depend on select_task_rq() being invoked during
+	 * wakeups. In addition, @p may end up executing on a different CPU
+	 * regardless of what happens in the wakeup path making the ttwu_queue
+	 * optimization less meaningful. Skip if on SCX.
+	 */
+	if (task_on_scx(p))
+		return false;
+
 	/*
 	 * Do not complicate things with the async wake_list while the CPU is
 	 * in hotplug state.
@@ -4553,6 +4581,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->rt.on_rq		= 0;
 	p->rt.on_list		= 0;
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+	init_scx_entity(&p->scx);
+#endif
+
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
 #endif
@@ -4794,10 +4826,18 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 	if (dl_prio(p->prio))
 		return -EAGAIN;
-	else if (rt_prio(p->prio))
+
+	scx_pre_fork(p);
+
+	if (rt_prio(p->prio)) {
 		p->sched_class = &rt_sched_class;
-	else
+#ifdef CONFIG_SCHED_CLASS_EXT
+	} else if (task_should_scx(p)) {
+		p->sched_class = &ext_sched_class;
+#endif
+	} else {
 		p->sched_class = &fair_sched_class;
+	}
 
 	init_entity_runnable_average(&p->se);
 
@@ -4817,7 +4857,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	return 0;
 }
 
-void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
+int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
 {
 	unsigned long flags;
 
@@ -4979,6 +4979,13 @@
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
+	return scx_fork(p);
+}
+
+void sched_cancel_fork(struct task_struct *p)
+{
+	scx_cancel_fork(p);
 }
 
 void sched_post_fork(struct task_struct *p)
@@ -4987,6 +4994,7 @@
 	sched_post_fork_bore(p);
 #endif // CONFIG_SCHED_BORE
 	uclamp_post_fork(p);
+	scx_post_fork(p);
 }
 
 unsigned long to_ratio(u64 period, u64 runtime)
@@ -5687,6 +5735,7 @@ void scheduler_tick(void)
 	calc_global_load_tick(rq);
 	sched_core_tick(rq);
 	task_tick_mm_cid(rq, curr);
+	scx_tick(rq);
 
 	rq_unlock(rq, &rf);
 
@@ -5699,8 +5748,10 @@ void scheduler_tick(void)
 		wq_worker_tick(curr);
 
 #ifdef CONFIG_SMP
-	rq->idle_balance = idle_cpu(cpu);
-	trigger_load_balance(rq);
+	if (!scx_switched_all()) {
+		rq->idle_balance = idle_cpu(cpu);
+		trigger_load_balance(rq);
+	}
 #endif
 }
 
@@ -5991,7 +6042,19 @@ static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
 				  struct rq_flags *rf)
 {
 #ifdef CONFIG_SMP
+	const struct sched_class *start_class = prev->sched_class;
 	const struct sched_class *class;
+
+#ifdef CONFIG_SCHED_CLASS_EXT
+	/*
+	 * SCX requires a balance() call before every pick_next_task() including
+	 * when waking up from SCHED_IDLE. If @start_class is below SCX, start
+	 * from SCX instead.
+	 */
+	if (sched_class_above(&ext_sched_class, start_class))
+		start_class = &ext_sched_class;
+#endif
+
 	/*
 	 * We must do the balancing pass before put_prev_task(), such
 	 * that when we release the rq->lock the task is in the same
@@ -6000,7 +6063,7 @@ static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
 	 * We can terminate the balance pass as soon as we know there is
 	 * a runnable task of @class priority or higher.
 	 */
-	for_class_range(class, prev->sched_class, &idle_sched_class) {
+	for_active_class_range(class, start_class, &idle_sched_class) {
 		if (class->balance(rq, prev, rf))
 			break;
 	}
@@ -6018,6 +6081,9 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	const struct sched_class *class;
 	struct task_struct *p;
 
+	if (scx_enabled())
+		goto restart;
+
 	/*
 	 * Optimization: we know that if all tasks are in the fair class we can
 	 * call that function directly, but only if the @prev task wasn't of a
@@ -6058,10 +6124,15 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	if (prev->dl_server)
 		prev->dl_server = NULL;
 
-	for_each_class(class) {
+	for_each_active_class(class) {
 		p = class->pick_next_task(rq);
-		if (p)
+		if (p) {
+			const struct sched_class *prev_class = prev->sched_class;
+
+			if (class != prev_class && prev_class->switch_class)
+				prev_class->switch_class(rq, p);
 			return p;
+		}
 	}
 
 	BUG(); /* The idle class should always have a runnable task. */
@@ -6091,7 +6162,7 @@ static inline struct task_struct *pick_task(struct rq *rq)
 	const struct sched_class *class;
 	struct task_struct *p;
 
-	for_each_class(class) {
+	for_each_active_class(class) {
 		p = class->pick_task(rq);
 		if (p)
 			return p;
@@ -7081,12 +7152,16 @@ int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flag
 }
 EXPORT_SYMBOL(default_wake_function);
 
-static void __setscheduler_prio(struct task_struct *p, int prio)
+void __setscheduler_prio(struct task_struct *p, int prio)
 {
 	if (dl_prio(prio))
 		p->sched_class = &dl_sched_class;
 	else if (rt_prio(prio))
 		p->sched_class = &rt_sched_class;
+#ifdef CONFIG_SCHED_CLASS_EXT
+	else if (task_should_scx(p))
+		p->sched_class = &ext_sched_class;
+#endif
 	else
 		p->sched_class = &fair_sched_class;
 
@@ -7247,6 +7322,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	}
 
 	__setscheduler_prio(p, prio);
+	check_class_changing(rq, p, prev_class);
 
 	if (queued)
 		enqueue_task(rq, p, queue_flag);
@@ -7468,6 +7544,25 @@ int sched_core_idle_cpu(int cpu)
 #endif
 
 #ifdef CONFIG_SMP
+/*
+ * Load avg and utiliztion metrics need to be updated periodically and before
+ * consumption. This function updates the metrics for all subsystems except for
+ * the fair class. @rq must be locked and have its clock updated.
+ */
+bool update_other_load_avgs(struct rq *rq)
+{
+	u64 now = rq_clock_pelt(rq);
+	const struct sched_class *curr_class = rq->curr->sched_class;
+	unsigned long hw_pressure = arch_scale_thermal_pressure(cpu_of(rq));
+
+	lockdep_assert_rq_held(rq);
+
+	return update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
+		update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
+		update_thermal_load_avg(now, rq, hw_pressure) |
+		update_irq_load_avg(rq, 0);
+}
+
 /*
  * This function computes an effective utilization for the given CPU, to be
  * used for frequency selection given the linear relation: f = u * f_max.
@@ -7790,6 +7885,10 @@ static int __sched_setscheduler(struct task_struct *p,
 		goto unlock;
 	}
 
+	retval = scx_check_setscheduler(p, policy);
+	if (retval)
+		goto unlock;
+
 	/*
 	 * If not changing anything there's no need to proceed further,
 	 * but store a possible modification of reset_on_fork.
@@ -7892,6 +7991,7 @@ static int __sched_setscheduler(struct task_struct *p,
 		__setscheduler_prio(p, newprio);
 	}
 	__setscheduler_uclamp(p, attr);
+	check_class_changing(rq, p, prev_class);
 
 	if (queued) {
 		/*
@@ -9067,6 +9167,7 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
 	case SCHED_NORMAL:
 	case SCHED_BATCH:
 	case SCHED_IDLE:
+	case SCHED_EXT:
 		ret = 0;
 		break;
 	}
@@ -9094,6 +9195,7 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
 	case SCHED_NORMAL:
 	case SCHED_BATCH:
 	case SCHED_IDLE:
+	case SCHED_EXT:
 		ret = 0;
 	}
 	return ret;
@@ -9189,6 +9291,7 @@ void sched_show_task(struct task_struct *p)
 
 	print_worker_info(KERN_INFO, p);
 	print_stop_info(KERN_INFO, p);
+	print_scx_info(KERN_INFO, p);
 	show_stack(p, NULL, KERN_INFO);
 	put_task_stack(p);
 }
@@ -9681,6 +9784,8 @@ int sched_cpu_activate(unsigned int cpu)
 		cpuset_cpu_active();
 	}
 
+	scx_rq_activate(rq);
+
 	/*
 	 * Put the rq online, if not already. This happens:
 	 *
@@ -9741,6 +9846,8 @@ int sched_cpu_deactivate(unsigned int cpu)
 	}
 	rq_unlock_irqrestore(rq, &rf);
 
+	scx_rq_deactivate(rq);
+
 #ifdef CONFIG_SCHED_SMT
 	/*
 	 * When going down, decrement the number of cores with SMT present.
@@ -10062,11 +10062,15 @@
 	int i;
 
 	/* Make sure the linker didn't screw up */
-	BUG_ON(&idle_sched_class != &fair_sched_class + 1 ||
-	       &fair_sched_class != &rt_sched_class + 1 ||
-	       &rt_sched_class   != &dl_sched_class + 1);
 #ifdef CONFIG_SMP
-	BUG_ON(&dl_sched_class != &stop_sched_class + 1);
+	BUG_ON(!sched_class_above(&stop_sched_class, &dl_sched_class));
+#endif
+	BUG_ON(!sched_class_above(&dl_sched_class, &rt_sched_class));
+	BUG_ON(!sched_class_above(&rt_sched_class, &fair_sched_class));
+	BUG_ON(!sched_class_above(&fair_sched_class, &idle_sched_class));
+#ifdef CONFIG_SCHED_CLASS_EXT
+	BUG_ON(!sched_class_above(&fair_sched_class, &ext_sched_class));
+	BUG_ON(!sched_class_above(&ext_sched_class, &idle_sched_class));
 #endif
 
 #ifdef CONFIG_SCHED_BORE
@@ -10097,6 +10208,7 @@ void __init sched_init(void)
 	balance_push_set(smp_processor_id(), false);
 #endif
 	init_sched_fair_class();
+	init_sched_ext_class();
 
 	psi_init();
 
@@ -10523,11 +10635,6 @@ void sched_move_task(struct task_struct *tsk)
 	}
 }
 
-static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
-{
-	return css ? container_of(css, struct task_group, css) : NULL;
-}
-
 static struct cgroup_subsys_state *
 cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 {
@@ -11294,29 +11401,27 @@ static int cpu_local_stat_show(struct seq_file *sf,
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+
+static unsigned long tg_weight(struct task_group *tg)
+{
+	return scale_load_down(tg->shares);
+}
+
 static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
 			       struct cftype *cft)
 {
-	struct task_group *tg = css_tg(css);
-	u64 weight = scale_load_down(tg->shares);
-
-	return DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024);
+	return sched_weight_to_cgroup(tg_weight(css_tg(css)));
 }
 
 static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
-				struct cftype *cft, u64 weight)
+				struct cftype *cft, u64 cgrp_weight)
 {
-	/*
-	 * cgroup weight knobs should use the common MIN, DFL and MAX
-	 * values which are 1, 100 and 10000 respectively.  While it loses
-	 * a bit of range on both ends, it maps pretty well onto the shares
-	 * value used by scheduler and the round-trip conversions preserve
-	 * the original value over the entire range.
-	 */
-	if (weight < CGROUP_WEIGHT_MIN || weight > CGROUP_WEIGHT_MAX)
+	unsigned long weight;
+
+	if (cgrp_weight < CGROUP_WEIGHT_MIN || cgrp_weight > CGROUP_WEIGHT_MAX)
 		return -ERANGE;
 
-	weight = DIV_ROUND_CLOSEST_ULL(weight * 1024, CGROUP_WEIGHT_DFL);
+	weight = sched_weight_from_cgroup(cgrp_weight);
 
 	return sched_group_set_shares(css_tg(css), scale_load(weight));
 }
@@ -11324,7 +11429,7 @@ static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
 static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
 				    struct cftype *cft)
 {
-	unsigned long weight = scale_load_down(css_tg(css)->shares);
+	unsigned long weight = tg_weight(css_tg(css));
 	int last_delta = INT_MAX;
 	int prio, delta;
 
@@ -12065,3 +12170,38 @@ void sched_mm_cid_fork(struct task_struct *t)
 	t->mm_cid_active = 1;
 }
 #endif
+
+#ifdef CONFIG_SCHED_CLASS_EXT
+void sched_deq_and_put_task(struct task_struct *p, int queue_flags,
+			    struct sched_enq_and_set_ctx *ctx)
+{
+	struct rq *rq = task_rq(p);
+
+	lockdep_assert_rq_held(rq);
+
+	*ctx = (struct sched_enq_and_set_ctx){
+		.p = p,
+		.queue_flags = queue_flags,
+		.queued = task_on_rq_queued(p),
+		.running = task_current(rq, p),
+	};
+
+	update_rq_clock(rq);
+	if (ctx->queued)
+		dequeue_task(rq, p, queue_flags | DEQUEUE_NOCLOCK);
+	if (ctx->running)
+		put_prev_task(rq, p);
+}
+
+void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx)
+{
+	struct rq *rq = task_rq(ctx->p);
+
+	lockdep_assert_rq_held(rq);
+
+	if (ctx->queued)
+		enqueue_task(rq, ctx->p, ctx->queue_flags | ENQUEUE_NOCLOCK);
+	if (ctx->running)
+		set_next_task(rq, ctx->p);
+}
+#endif	/* CONFIG_SCHED_CLASS_EXT */
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index eece6244f9d2..e683e5d08daa 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -197,8 +197,10 @@ unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
 
 static void sugov_get_util(struct sugov_cpu *sg_cpu, unsigned long boost)
 {
-	unsigned long min, max, util = cpu_util_cfs_boost(sg_cpu->cpu);
+	unsigned long min, max, util = scx_cpuperf_target(sg_cpu->cpu);
 
+	if (!scx_switched_all())
+		util += cpu_util_cfs_boost(sg_cpu->cpu);
 	util = effective_cpu_util(sg_cpu->cpu, util, &min, &max);
 	util = max(util, boost);
 	sg_cpu->bw_min = min;
@@ -325,16 +327,35 @@ static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
-static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
+static bool sugov_hold_freq(struct sugov_cpu *sg_cpu)
 {
-	unsigned long idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu);
-	bool ret = idle_calls == sg_cpu->saved_idle_calls;
+	unsigned long idle_calls;
+	bool ret;
+
+	/*
+	 * The heuristics in this function is for the fair class. For SCX, the
+	 * performance target comes directly from the BPF scheduler. Let's just
+	 * follow it.
+	 */
+	if (scx_switched_all())
+		return false;
+
+	/* if capped by uclamp_max, always update to be in compliance */
+	if (uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)))
+		return false;
+
+	/*
+	 * Maintain the frequency if the CPU has not been idle recently, as
+	 * reduction is likely to be premature.
+	 */
+	idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu);
+	ret = idle_calls == sg_cpu->saved_idle_calls;
 
 	sg_cpu->saved_idle_calls = idle_calls;
 	return ret;
 }
 #else
-static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
+static inline bool sugov_hold_freq(struct sugov_cpu *sg_cpu) { return false; }
 #endif /* CONFIG_NO_HZ_COMMON */
 
 /*
@@ -382,14 +403,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
 		return;
 
 	next_f = get_next_freq(sg_policy, sg_cpu->util, max_cap);
-	/*
-	 * Do not reduce the frequency if the CPU has not been idle
-	 * recently, as the reduction is likely to be premature then.
-	 *
-	 * Except when the rq is capped by uclamp_max.
-	 */
-	if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
-	    sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
+
+	if (sugov_hold_freq(sg_cpu) && next_f < sg_policy->next_freq &&
 	    !sg_policy->need_freq_update) {
 		next_f = sg_policy->next_freq;
 
@@ -436,14 +451,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 	if (!sugov_update_single_common(sg_cpu, time, max_cap, flags))
 		return;
 
-	/*
-	 * Do not reduce the target performance level if the CPU has not been
-	 * idle recently, as the reduction is likely to be premature then.
-	 *
-	 * Except when the rq is capped by uclamp_max.
-	 */
-	if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
-	    sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
+	if (sugov_hold_freq(sg_cpu) && sg_cpu->util < prev_util)
 		sg_cpu->util = prev_util;
 
 	cpufreq_driver_adjust_perf(sg_cpu->cpu, sg_cpu->bw_min,
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 8d5d98a5834d..6f306e1c9c3e 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1089,6 +1089,9 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		P(dl.runtime);
 		P(dl.deadline);
 	}
+#ifdef CONFIG_SCHED_CLASS_EXT
+	__PS("ext.enabled", task_on_scx(p));
+#endif
 #undef PN_SCHEDSTAT
 #undef P_SCHEDSTAT
 
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
new file mode 100644
index 000000000000..b9fd7b7d4a86
--- /dev/null
+++ b/kernel/sched/ext.c
@@ -0,0 +1,6537 @@
+/* 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,
+};
+
+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,
+
+	SCX_OPS_ALL_FLAGS	= SCX_OPS_KEEP_BUILTIN_IDLE |
+				  SCX_OPS_ENQ_LAST |
+				  SCX_OPS_ENQ_EXITING |
+				  SCX_OPS_SWITCH_PARTIAL,
+};
+
+/* 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;
+};
+
+/* argument container for ops.exit_task() */
+struct scx_exit_task_args {
+	/* Whether the task exited before running on sched_ext. */
+	bool cancelled;
+};
+
+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);
+
+	/*
+	 * 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
+	 */
+	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,
+
+	/* 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.
+	 *
+	 * If the BPF scheduler wants to continue executing the task,
+	 * ops.enqueue() should dispatch the task to %SCX_DSQ_LOCAL immediately.
+	 * If the task gets queued on a different dsq or the BPF side, 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_ops_enable_state {
+	SCX_OPS_PREPPING,
+	SCX_OPS_ENABLING,
+	SCX_OPS_ENABLED,
+	SCX_OPS_DISABLING,
+	SCX_OPS_DISABLED,
+};
+
+static const char *scx_ops_enable_state_str[] = {
+	[SCX_OPS_PREPPING]	= "prepping",
+	[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_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);
+
+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);
+
+/*
+ * 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 */
+static struct scx_dispatch_q __cacheline_aligned_in_smp scx_dsq_global;
+
+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;
+};
+
+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;
+}
+
+/*
+ * 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;
+	}
+
+	if (unlikely((mask & SCX_KF_SLEEPABLE) && in_interrupt())) {
+		scx_ops_error("sleepable kfunc called from non-sleepable context");
+		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 the SCX_KF_SLEEPABLE
+	 * boundary thanks to the above in_interrupt() check.
+	 */
+	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;
+}
+
+/**
+ * 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->is_bpf_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 << 0,
+
+	__SCX_DSQ_ITER_ALL_FLAGS	= SCX_DSQ_ITER_REV,
+};
+
+struct bpf_iter_scx_dsq_kern {
+	struct scx_dsq_list_node	cursor;
+	struct scx_dispatch_q		*dsq;
+	u32				dsq_seq;
+	u32				flags;
+} __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;
+};
+
+/**
+ * scx_task_iter_init - Initialize a task iterator
+ * @iter: iterator to init
+ *
+ * Initialize @iter. Must be called with scx_tasks_lock held. Once initialized,
+ * @iter must eventually be exited with scx_task_iter_exit().
+ *
+ * scx_tasks_lock may be released between this and the first next() call or
+ * between any two next() calls. If scx_tasks_lock is 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_init(struct scx_task_iter *iter)
+{
+	lockdep_assert_held(&scx_tasks_lock);
+
+	iter->cursor = (struct sched_ext_entity){ .flags = SCX_TASK_CURSOR };
+	list_add(&iter->cursor.tasks_node, &scx_tasks);
+	iter->locked = NULL;
+}
+
+/**
+ * scx_task_iter_rq_unlock - Unlock rq locked by a task iterator
+ * @iter: iterator to unlock rq for
+ *
+ * If @iter is in the middle of a locked iteration, it may be locking the rq of
+ * the task currently being visited. Unlock the rq if so. This function can be
+ * safely called anytime during an iteration.
+ *
+ * Returns %true if the rq @iter was locking is unlocked. %false if @iter was
+ * not locking an rq.
+ */
+static bool 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;
+		return true;
+	} else {
+		return false;
+	}
+}
+
+/**
+ * scx_task_iter_exit - Exit a task iterator
+ * @iter: iterator to exit
+ *
+ * Exit a previously initialized @iter. Must be called with scx_tasks_lock held.
+ * If the iterator holds a task's rq lock, that rq lock is released. See
+ * scx_task_iter_init() for details.
+ */
+static void scx_task_iter_exit(struct scx_task_iter *iter)
+{
+	lockdep_assert_held(&scx_tasks_lock);
+
+	scx_task_iter_rq_unlock(iter);
+	list_del_init(&iter->cursor.tasks_node);
+}
+
+/**
+ * scx_task_iter_next - Next task
+ * @iter: iterator to walk
+ *
+ * Visit the next task. See scx_task_iter_init() for details.
+ */
+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;
+
+	lockdep_assert_held(&scx_tasks_lock);
+
+	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_init()
+ * for details.
+ */
+static struct task_struct *
+scx_task_iter_next_locked(struct scx_task_iter *iter, bool include_dead)
+{
+	struct task_struct *p;
+retry:
+	scx_task_iter_rq_unlock(iter);
+
+	while ((p = scx_task_iter_next(iter))) {
+		/*
+		 * is_idle_task() tests %PF_IDLE which may not be set for CPUs
+		 * which haven't yet been onlined. Test sched_class directly.
+		 */
+		if (p->sched_class != &idle_sched_class)
+			break;
+	}
+	if (!p)
+		return NULL;
+
+	iter->rq = task_rq_lock(p, &iter->rf);
+	iter->locked = p;
+
+	/*
+	 * If we see %TASK_DEAD, @p already disabled preemption, is about to do
+	 * the final __schedule(), won't ever need to be scheduled again and can
+	 * thus be safely ignored. If we don't see %TASK_DEAD, @p can't enter
+	 * the final __schedle() while we're locking its rq and thus will stay
+	 * alive until the rq is unlocked.
+	 */
+	if (!include_dead && READ_ONCE(p->__state) == TASK_DEAD)
+		goto retry;
+
+	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_ops_bypassing(void)
+{
+	return unlikely(atomic_read(&scx_ops_bypass_depth));
+}
+
+/**
+ * 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)
+{
+#ifdef CONFIG_SCHED_CORE
+	/*
+	 * It's okay to update the timestamp spuriously. Use
+	 * sched_core_disabled() which is cheaper than enabled().
+	 */
+	if (!sched_core_disabled())
+		p->scx.core_sched_at = rq_clock_task(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);
+	assert_clock_updated(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;
+	u64 now = rq_clock_task(rq);
+	u64 delta_exec;
+
+	if (time_before_eq64(now, curr->se.exec_start))
+		return;
+
+	delta_exec = now - curr->se.exec_start;
+	curr->se.exec_start = now;
+	curr->se.sum_exec_runtime += delta_exec;
+	account_group_exec_runtime(curr, delta_exec);
+	cgroup_account_cputime(curr, delta_exec);
+
+	if (curr->scx.slice != SCX_SLICE_INF) {
+		curr->scx.slice -= min(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 = &scx_dsq_global;
+			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)
+{
+	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);
+}
+
+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 */
+		WARN_ON_ONCE(list_empty(&p->scx.dsq_list.node));
+		task_unlink_from_dsq(p, dsq);
+		dsq_mod_nr(dsq, -1);
+	} 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_user_dsq(u64 dsq_id)
+{
+	return rhashtable_lookup_fast(&dsq_hash, &dsq_id, dsq_hash_params);
+}
+
+static struct scx_dispatch_q *find_non_local_dsq(u64 dsq_id)
+{
+	lockdep_assert(rcu_read_lock_any_held());
+
+	if (dsq_id == SCX_DSQ_GLOBAL)
+		return &scx_dsq_global;
+	else
+		return find_user_dsq(dsq_id);
+}
+
+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;
+
+	dsq = find_non_local_dsq(dsq_id);
+	if (unlikely(!dsq)) {
+		scx_ops_error("non-existent DSQ 0x%llx for %s[%d]",
+			      dsq_id, p->comm, p->pid);
+		return &scx_dsq_global;
+	}
+
+	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;
+	u64 dsq_id = p->scx.ddsp_dsq_id;
+
+	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_ON) == SCX_DSQ_LOCAL_ON) {
+		s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK;
+		unsigned long opss;
+
+		if (cpu == cpu_of(rq)) {
+			dsq_id = SCX_DSQ_LOCAL;
+			goto dispatch;
+		}
+
+		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:
+	dsq = find_dsq_for_dispatch(rq, dsq_id, p);
+	dispatch_enqueue(dsq, p, p->scx.ddsp_enq_flags | SCX_ENQ_CLEAR_OPSS);
+}
+
+static bool scx_rq_online(struct rq *rq)
+{
+	return likely(rq->scx.flags & SCX_RQ_ONLINE);
+}
+
+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_ops_bypassing()) {
+		if (enq_flags & SCX_ENQ_LAST)
+			goto local;
+		else
+			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;
+
+	/* see %SCX_OPS_ENQ_LAST */
+	if (!static_branch_unlikely(&scx_ops_enq_last) &&
+	    (enq_flags & SCX_ENQ_LAST))
+		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(&scx_dsq_global, 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))
+		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 void 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;
+	}
+
+	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))
+		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);
+}
+
+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;
+}
+
+#ifdef CONFIG_SMP
+/**
+ * move_task_to_local_dsq - Move a task from a different rq to a local DSQ
+ * @rq: rq to move the task into, currently locked
+ * @p: task to move
+ * @enq_flags: %SCX_ENQ_*
+ *
+ * Move @p which is currently on a different rq to @rq's local DSQ. The caller
+ * must:
+ *
+ * 1. Start with exclusive access to @p either through its DSQ lock or
+ *    %SCX_OPSS_DISPATCHING flag.
+ *
+ * 2. Set @p->scx.holding_cpu to raw_smp_processor_id().
+ *
+ * 3. Remember task_rq(@p). Release the exclusive access so that we don't
+ *    deadlock with dequeue.
+ *
+ * 4. Lock @rq and the task_rq from #3.
+ *
+ * 5. Call this function.
+ *
+ * Returns %true if @p was successfully moved. %false after racing dequeue and
+ * losing.
+ */
+static bool move_task_to_local_dsq(struct rq *rq, struct task_struct *p,
+				   u64 enq_flags)
+{
+	struct rq *task_rq;
+
+	lockdep_assert_rq_held(rq);
+
+	/*
+	 * If dequeue got to @p while we were trying to lock both rq's, it'd
+	 * have cleared @p->scx.holding_cpu to -1. While other cpus may have
+	 * updated it to different values afterwards, as this operation can't be
+	 * preempted or recurse, @p->scx.holding_cpu can never become
+	 * raw_smp_processor_id() again before we're done. Thus, we can tell
+	 * whether we lost to dequeue by testing whether @p->scx.holding_cpu is
+	 * still raw_smp_processor_id().
+	 *
+	 * See dispatch_dequeue() for the counterpart.
+	 */
+	if (unlikely(p->scx.holding_cpu != raw_smp_processor_id()))
+		return false;
+
+	/* @p->rq couldn't have changed if we're still the holding cpu */
+	task_rq = task_rq(p);
+	lockdep_assert_rq_held(task_rq);
+
+	WARN_ON_ONCE(!cpumask_test_cpu(cpu_of(rq), p->cpus_ptr));
+	deactivate_task(task_rq, p, 0);
+	set_task_cpu(p, cpu_of(rq));
+	p->scx.sticky_cpu = cpu_of(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(rq->scx.extra_enq_flags);
+	rq->scx.extra_enq_flags = enq_flags;
+	activate_task(rq, p, 0);
+	rq->scx.extra_enq_flags = 0;
+
+	return true;
+}
+
+/**
+ * dispatch_to_local_dsq_lock - Ensure source and destination rq's are locked
+ * @rq: current rq which is locked
+ * @src_rq: rq to move task from
+ * @dst_rq: rq to move task to
+ *
+ * We're holding @rq lock and trying to dispatch a task from @src_rq to
+ * @dst_rq's local DSQ and thus need to lock both @src_rq and @dst_rq. Whether
+ * @rq stays locked isn't important as long as the state is restored after
+ * dispatch_to_local_dsq_unlock().
+ */
+static void dispatch_to_local_dsq_lock(struct rq *rq, struct rq *src_rq,
+				       struct rq *dst_rq)
+{
+	if (src_rq == dst_rq) {
+		raw_spin_rq_unlock(rq);
+		raw_spin_rq_lock(dst_rq);
+	} else if (rq == src_rq) {
+		double_lock_balance(rq, dst_rq);
+	} else if (rq == dst_rq) {
+		double_lock_balance(rq, src_rq);
+	} else {
+		raw_spin_rq_unlock(rq);
+		double_rq_lock(src_rq, dst_rq);
+	}
+}
+
+/**
+ * dispatch_to_local_dsq_unlock - Undo dispatch_to_local_dsq_lock()
+ * @rq: current rq which is locked
+ * @src_rq: rq to move task from
+ * @dst_rq: rq to move task to
+ *
+ * Unlock @src_rq and @dst_rq and ensure that @rq is locked on return.
+ */
+static void dispatch_to_local_dsq_unlock(struct rq *rq, struct rq *src_rq,
+					 struct rq *dst_rq)
+{
+	if (src_rq == dst_rq) {
+		raw_spin_rq_unlock(dst_rq);
+		raw_spin_rq_lock(rq);
+	} else if (rq == src_rq) {
+		double_unlock_balance(rq, dst_rq);
+	} else if (rq == dst_rq) {
+		double_unlock_balance(rq, src_rq);
+	} else {
+		double_rq_unlock(src_rq, dst_rq);
+		raw_spin_rq_lock(rq);
+	}
+}
+#endif	/* CONFIG_SMP */
+
+static void consume_local_task(struct rq *rq, struct scx_dispatch_q *dsq,
+			       struct task_struct *p)
+{
+	lockdep_assert_held(&dsq->lock);	/* released on return */
+
+	/* @dsq is locked and @p is on this rq */
+	WARN_ON_ONCE(p->scx.holding_cpu >= 0);
+	task_unlink_from_dsq(p, dsq);
+	list_add_tail(&p->scx.dsq_list.node, &rq->scx.local_dsq.list);
+	dsq_mod_nr(dsq, -1);
+	dsq_mod_nr(&rq->scx.local_dsq, 1);
+	p->scx.dsq = &rq->scx.local_dsq;
+	raw_spin_unlock(&dsq->lock);
+}
+
+#ifdef CONFIG_SMP
+/*
+ * Similar to kernel/sched/core.c::is_cpu_allowed() but we're testing whether @p
+ * can be pulled to @rq.
+ */
+static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq)
+{
+	int cpu = cpu_of(rq);
+
+	if (!cpumask_test_cpu(cpu, p->cpus_ptr))
+		return false;
+	if (unlikely(is_migration_disabled(p)))
+		return false;
+	if (!(p->flags & PF_KTHREAD) && unlikely(!task_cpu_possible(cpu, p)))
+		return false;
+	if (!scx_rq_online(rq))
+		return false;
+	return true;
+}
+
+static bool consume_remote_task(struct rq *rq, struct scx_dispatch_q *dsq,
+				struct task_struct *p, struct rq *task_rq)
+{
+	bool moved = false;
+
+	lockdep_assert_held(&dsq->lock);	/* released on return */
+
+	/*
+	 * @dsq is locked and @p is on a remote rq. @p is currently protected by
+	 * @dsq->lock. We want to pull @p to @rq but may deadlock if we grab
+	 * @task_rq while holding @dsq and @rq locks. As dequeue can't drop the
+	 * rq lock or fail, do a little dancing from our side. See
+	 * move_task_to_local_dsq().
+	 */
+	WARN_ON_ONCE(p->scx.holding_cpu >= 0);
+	task_unlink_from_dsq(p, dsq);
+	dsq_mod_nr(dsq, -1);
+	p->scx.holding_cpu = raw_smp_processor_id();
+	raw_spin_unlock(&dsq->lock);
+
+	double_lock_balance(rq, task_rq);
+
+	moved = move_task_to_local_dsq(rq, p, 0);
+
+	double_unlock_balance(rq, task_rq);
+
+	return moved;
+}
+#else	/* CONFIG_SMP */
+static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq) { return false; }
+static bool consume_remote_task(struct rq *rq, struct scx_dispatch_q *dsq,
+				struct task_struct *p, 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) {
+			consume_local_task(rq, dsq, p);
+			return true;
+		}
+
+		if (task_can_run_on_remote_rq(p, rq)) {
+			if (likely(consume_remote_task(rq, dsq, p, task_rq)))
+				return true;
+			goto retry;
+		}
+	}
+
+	raw_spin_unlock(&dsq->lock);
+	return false;
+}
+
+enum dispatch_to_local_dsq_ret {
+	DTL_DISPATCHED,		/* successfully dispatched */
+	DTL_LOST,		/* lost race to dequeue */
+	DTL_NOT_LOCAL,		/* destination is not a local DSQ */
+	DTL_INVALID,		/* invalid local dsq_id */
+};
+
+/**
+ * dispatch_to_local_dsq - Dispatch a task to a local dsq
+ * @rq: current rq which is locked
+ * @dsq_id: destination dsq ID
+ * @p: task to dispatch
+ * @enq_flags: %SCX_ENQ_*
+ *
+ * We're holding @rq lock and want to dispatch @p to the local DSQ identified by
+ * @dsq_id. 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 enum dispatch_to_local_dsq_ret
+dispatch_to_local_dsq(struct rq *rq, u64 dsq_id, struct task_struct *p,
+		      u64 enq_flags)
+{
+	struct rq *src_rq = task_rq(p);
+	struct rq *dst_rq;
+
+	/*
+	 * We're synchronized against dequeue through DISPATCHING. As @p can't
+	 * be dequeued, its task_rq and cpus_allowed are stable too.
+	 */
+	if (dsq_id == SCX_DSQ_LOCAL) {
+		dst_rq = rq;
+	} 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, "in SCX_DSQ_LOCAL_ON dispatch verdict"))
+			return DTL_INVALID;
+		dst_rq = cpu_rq(cpu);
+	} else {
+		return DTL_NOT_LOCAL;
+	}
+
+	/* if dispatching to @rq that @p is already on, no lock dancing needed */
+	if (rq == src_rq && rq == dst_rq) {
+		dispatch_enqueue(&dst_rq->scx.local_dsq, p,
+				 enq_flags | SCX_ENQ_CLEAR_OPSS);
+		return DTL_DISPATCHED;
+	}
+
+#ifdef CONFIG_SMP
+	if (cpumask_test_cpu(cpu_of(dst_rq), p->cpus_ptr)) {
+		struct rq *locked_dst_rq = dst_rq;
+		bool dsp;
+
+		/*
+		 * @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.
+		 */
+		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);
+
+		dispatch_to_local_dsq_lock(rq, src_rq, locked_dst_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. If @p
+		 * is destined to an offline CPU, queue it on its current CPU
+		 * instead, which should always be safe. As this is an allowed
+		 * behavior, don't trigger an ops error.
+		 */
+		if (!scx_rq_online(dst_rq))
+			dst_rq = src_rq;
+
+		if (src_rq == dst_rq) {
+			/*
+			 * As @p is staying on the same rq, there's no need to
+			 * go through the full deactivate/activate cycle.
+			 * Optimize by abbreviating the operations in
+			 * move_task_to_local_dsq().
+			 */
+			dsp = p->scx.holding_cpu == raw_smp_processor_id();
+			if (likely(dsp)) {
+				p->scx.holding_cpu = -1;
+				dispatch_enqueue(&dst_rq->scx.local_dsq, p,
+						 enq_flags);
+			}
+		} else {
+			dsp = move_task_to_local_dsq(dst_rq, p, enq_flags);
+		}
+
+		/* if the destination CPU is idle, wake it up */
+		if (dsp && sched_class_above(p->sched_class,
+					     dst_rq->curr->sched_class))
+			resched_curr(dst_rq);
+
+		dispatch_to_local_dsq_unlock(rq, src_rq, locked_dst_rq);
+
+		return dsp ? DTL_DISPATCHED : DTL_LOST;
+	}
+#endif	/* CONFIG_SMP */
+
+	scx_ops_error("SCX_DSQ_LOCAL[_ON] verdict target cpu %d not allowed for %s[%d]",
+		      cpu_of(dst_rq), p->comm, p->pid);
+	return DTL_INVALID;
+}
+
+/**
+ * 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));
+
+	switch (dispatch_to_local_dsq(rq, dsq_id, p, enq_flags)) {
+	case DTL_DISPATCHED:
+		break;
+	case DTL_LOST:
+		break;
+	case DTL_INVALID:
+		dsq_id = SCX_DSQ_GLOBAL;
+		fallthrough;
+	case DTL_NOT_LOCAL:
+		dsq = find_dsq_for_dispatch(cpu_rq(raw_smp_processor_id()),
+					    dsq_id, p);
+		dispatch_enqueue(dsq, p, enq_flags | SCX_ENQ_CLEAR_OPSS);
+		break;
+	}
+}
+
+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, bool local)
+{
+	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;
+	bool has_tasks = false;
+
+	lockdep_assert_rq_held(rq);
+	rq->scx.flags |= SCX_RQ_IN_BALANCE;
+
+	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) {
+		WARN_ON_ONCE(local && (prev->scx.flags & SCX_TASK_BAL_KEEP));
+		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 put_prev_task_scx() to put @prev on local_dsq. If the
+		 * BPF scheduler wants to handle this explicitly, it should
+		 * implement ->cpu_released().
+		 *
+		 * See scx_ops_disable_workfn() for the explanation on the
+		 * bypassing test.
+		 *
+		 * When balancing a remote CPU for core-sched, there won't be a
+		 * following put_prev_task_scx() call and we don't own
+		 * %SCX_TASK_BAL_KEEP. Instead, pick_task_scx() will test the
+		 * same conditions later and pick @rq->curr accordingly.
+		 */
+		if ((prev->scx.flags & SCX_TASK_QUEUED) &&
+		    prev->scx.slice && !scx_ops_bypassing()) {
+			if (local)
+				prev->scx.flags |= SCX_TASK_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_dispatch_q(rq, &scx_dsq_global))
+		goto has_tasks;
+
+	if (!SCX_HAS_OP(dispatch) || scx_ops_bypassing() || !scx_rq_online(rq))
+		goto out;
+
+	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_dispatch_q(rq, &scx_dsq_global))
+			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);
+
+	goto out;
+
+has_tasks:
+	has_tasks = true;
+out:
+	rq->scx.flags &= ~SCX_RQ_IN_BALANCE;
+	return has_tasks;
+}
+
+#ifdef CONFIG_SMP
+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, true);
+
+#ifdef CONFIG_SCHED_SMT
+	/*
+	 * When core-sched is enabled, this ops.balance() call will be followed
+	 * by put_prev_scx() and pick_task_scx() on this CPU and pick_task_scx()
+	 * on 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, false);
+		}
+	}
+#endif
+	rq_repin_lock(rq, rf);
+
+	return ret;
+}
+#endif
+
+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 void process_ddsp_deferred_locals(struct rq *rq)
+{
+	struct task_struct *p, *tmp;
+
+	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().
+	 */
+	list_for_each_entry_safe(p, tmp, &rq->scx.ddsp_deferred_locals,
+				 scx.dsq_list.node) {
+		s32 ret;
+
+		list_del_init(&p->scx.dsq_list.node);
+
+		ret = dispatch_to_local_dsq(rq, p->scx.ddsp_dsq_id, p,
+					    p->scx.ddsp_enq_flags);
+		WARN_ON_ONCE(ret == DTL_NOT_LOCAL);
+	}
+}
+
+static void put_prev_task_scx(struct rq *rq, struct task_struct *p)
+{
+#ifndef CONFIG_SMP
+	/*
+	 * UP workaround.
+	 *
+	 * Because SCX may transfer tasks across CPUs during dispatch, dispatch
+	 * is performed from its balance operation which isn't called in UP.
+	 * Let's work around by calling it from the operations which come right
+	 * after.
+	 *
+	 * 1. If the prev task is on SCX, pick_next_task() calls
+	 *    .put_prev_task() right after. As .put_prev_task() is also called
+	 *    from other places, we need to distinguish the calls which can be
+	 *    done by looking at the previous task's state - if still queued or
+	 *    dequeued with %SCX_DEQ_SLEEP, the caller must be pick_next_task().
+	 *    This case is handled here.
+	 *
+	 * 2. If the prev task is not on SCX, the first following call into SCX
+	 *    will be .pick_next_task(), which is covered by calling
+	 *    balance_scx() from pick_next_task_scx().
+	 *
+	 * Note that we can't merge the first case into the second as
+	 * balance_scx() must be called before the previous SCX task goes
+	 * through put_prev_task_scx().
+	 *
+         * @rq is pinned and can't be unlocked. As UP doesn't transfer tasks
+         * around, balance_one() doesn't need to.
+	 */
+	if (p->scx.flags & (SCX_TASK_QUEUED | SCX_TASK_DEQD_FOR_SLEEP))
+		balance_one(rq, p, true);
+#endif
+
+	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 we're being called from put_prev_task_balance(), balance_scx() may
+	 * have decided that @p should keep running.
+	 */
+	if (p->scx.flags & SCX_TASK_BAL_KEEP) {
+		p->scx.flags &= ~SCX_TASK_BAL_KEEP;
+		set_task_runnable(rq, p);
+		dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD);
+		return;
+	}
+
+	if (p->scx.flags & SCX_TASK_QUEUED) {
+		set_task_runnable(rq, p);
+
+		/*
+		 * If @p has slice left and balance_scx() didn't tag it for
+		 * keeping, @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_ops_bypassing()) {
+			dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD);
+			return;
+		}
+
+		/*
+		 * If we're in the pick_next_task path, balance_scx() should
+		 * have already populated the local DSQ if there are any other
+		 * available tasks. If empty, tell ops.enqueue() that @p is the
+		 * only one available for this cpu. ops.enqueue() should put it
+		 * on the local DSQ so that the subsequent pick_next_task_scx()
+		 * can find the task unless it wants to trigger a separate
+		 * follow-up scheduling event.
+		 */
+		if (list_empty(&rq->scx.local_dsq.list))
+			do_enqueue_task(rq, p, SCX_ENQ_LAST, -1);
+		else
+			do_enqueue_task(rq, p, 0, -1);
+	}
+}
+
+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_next_task_scx(struct rq *rq)
+{
+	struct task_struct *p;
+
+#ifndef CONFIG_SMP
+	/* UP workaround - see the comment at the head of put_prev_task_scx() */
+	if (unlikely(rq->curr->sched_class != &ext_sched_class))
+		balance_one(rq, rq->curr, true);
+#endif
+
+	p = first_local_task(rq);
+	if (!p)
+		return NULL;
+
+	set_next_task_scx(rq, p, true);
+
+	if (unlikely(!p->scx.slice)) {
+		if (!scx_ops_bypassing() && !scx_warned_zero_slice) {
+			printk_deferred(KERN_WARNING "sched_ext: %s[%d] has zero slice in pick_next_task_scx()\n",
+					p->comm, p->pid);
+			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_ops_bypassing())
+		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);
+}
+
+/**
+ * pick_task_scx - Pick a candidate task for core-sched
+ * @rq: rq to pick the candidate task from
+ *
+ * Core-sched calls this function on each SMT sibling to determine the next
+ * tasks to run on the SMT siblings. balance_one() has been called on all
+ * siblings and put_prev_task_scx() has been called only for the current CPU.
+ *
+ * As put_prev_task_scx() hasn't been called on remote CPUs, we can't just look
+ * at the first task in the local dsq. @rq->curr has to be considered explicitly
+ * to mimic %SCX_TASK_BAL_KEEP.
+ */
+static struct task_struct *pick_task_scx(struct rq *rq)
+{
+	struct task_struct *curr = rq->curr;
+	struct task_struct *first = first_local_task(rq);
+
+	if (curr->scx.flags & SCX_TASK_QUEUED) {
+		/* is curr the only runnable task? */
+		if (!first)
+			return curr;
+
+		/*
+		 * Does curr trump first? We can always go by core_sched_at for
+		 * this comparison as it represents global FIFO ordering when
+		 * the default core-sched ordering is used and local-DSQ FIFO
+		 * ordering otherwise.
+		 *
+		 * We can have a task with an earlier timestamp on the DSQ. For
+		 * example, when a current task is preempted by a sibling
+		 * picking a different cookie, the task would be requeued at the
+		 * head of the local DSQ with an earlier timestamp than the
+		 * core-sched picked next task. Besides, the BPF scheduler may
+		 * dispatch any tasks to the local DSQ anytime.
+		 */
+		if (curr->scx.slice && time_before64(curr->scx.core_sched_at,
+						     first->scx.core_sched_at))
+			return curr;
+	}
+
+	return first;	/* this may be %NULL */
+}
+#endif	/* CONFIG_SCHED_CORE */
+
+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_scx(struct rq *rq, struct task_struct *next)
+{
+	const struct sched_class *next_class = next->sched_class;
+
+	if (!scx_enabled())
+		return;
+#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;
+	}
+}
+
+#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 (!static_branch_likely(&scx_builtin_idle_enabled)) {
+		scx_ops_error("built-in idle tracking is disabled");
+		return prev_cpu;
+	}
+
+	/*
+	 * 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) && p->nr_cpus_allowed > 1 &&
+	    !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 (p->nr_cpus_allowed == 1) {
+		if (test_and_clear_cpu_idle(prev_cpu)) {
+			cpu = prev_cpu;
+			goto cpu_found;
+		} else {
+			return prev_cpu;
+		}
+	}
+
+	/*
+	 * 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)) {
+		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_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_SLEEPABLE, cpu_online, cpu);
+	else if (!online && SCX_HAS_OP(cpu_offline))
+		SCX_CALL_OP(SCX_KF_SLEEPABLE, 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_ops_bypassing()) {
+		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);
+}
+
+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 = {
+			.fork = fork,
+		};
+
+		ret = SCX_CALL_OP_RET(SCX_KF_SLEEPABLE, 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) {
+		struct rq *rq;
+		struct rq_flags rf;
+
+		rq = task_rq_lock(p, &rf);
+
+		/*
+		 * We're either in fork or 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);
+	}
+
+	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(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_enabled())
+		return scx_ops_init_task(p, task_group(p), true);
+	else
+		return 0;
+}
+
+void scx_post_fork(struct task_struct *p)
+{
+	if (scx_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_ops_bypassing())
+		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
+
+/*
+ * 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,
+
+	.pick_next_task		= pick_next_task_scx,
+
+	.put_prev_task		= put_prev_task_scx,
+	.set_next_task		= set_next_task_scx,
+
+	.switch_class		= switch_class_scx,
+
+#ifdef CONFIG_SMP
+	.balance		= balance_scx,
+	.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
+
+#ifdef CONFIG_SCHED_CORE
+	.pick_task		= pick_task_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();
+}
+
+
+/********************************************************************************
+ * 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 struct attribute *scx_global_attrs[] = {
+	&scx_attr_state.attr,
+	&scx_attr_switch_all.attr,
+	&scx_attr_nr_rejected.attr,
+	&scx_attr_hotplug_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.
+ *
+ * a. ops.enqueue() is ignored and tasks are queued in simple global FIFO order.
+ *
+ * b. ops.dispatch() is ignored.
+ *
+ * c. balance_scx() never sets %SCX_TASK_BAL_KEEP as the slice value can't be
+ *    trusted. Whenever a tick triggers, the running task is rotated to the tail
+ *    of the queue with core_sched_at touched.
+ *
+ * d. pick_next_task() suppresses zero slice warning.
+ *
+ * e. scx_bpf_kick_cpu() is disabled to avoid irq_work malfunction during PM
+ *    operations.
+ *
+ * f. 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;
+	}
+
+	/*
+	 * We need to guarantee that no tasks are on the BPF scheduler while
+	 * bypassing. Either we see enabled or the enable path sees the
+	 * increased bypass_depth before moving tasks to SCX.
+	 */
+	if (!scx_enabled())
+		return;
+
+	/*
+	 * No task property is changing. We just need to make sure all currently
+	 * queued tasks are re-queued according to the new scx_ops_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);
+
+		/*
+		 * 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);
+
+		/* kick to restore ticks */
+		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 "Scheduler unregistered from user space";
+	case SCX_EXIT_UNREG_BPF:
+		return "Scheduler unregistered from BPF";
+	case SCX_EXIT_UNREG_KERN:
+		return "Scheduler 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);
+
+	/*
+	 * Avoid racing against fork. See scx_ops_enable() for explanation on
+	 * the locking order.
+	 */
+	percpu_down_write(&scx_fork_rwsem);
+	cpus_read_lock();
+
+	spin_lock_irq(&scx_tasks_lock);
+	scx_task_iter_init(&sti);
+	/*
+	 * Invoke scx_ops_exit_task() on all non-idle tasks, including
+	 * TASK_DEAD tasks. Because dead tasks may have a nonzero refcount,
+	 * we may not have invoked sched_ext_free() on them by the time a
+	 * scheduler is disabled. We must therefore exit the task here, or we'd
+	 * fail to invoke ops.exit_task(), as the scheduler will have been
+	 * unloaded by the time the task is subsequently exited on the
+	 * sched_ext_free() path.
+	 */
+	while ((p = scx_task_iter_next_locked(&sti, true))) {
+		const struct sched_class *old_class = p->sched_class;
+		struct sched_enq_and_set_ctx ctx;
+
+		if (READ_ONCE(p->__state) != TASK_DEAD) {
+			sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE,
+					       &ctx);
+
+			p->scx.slice = min_t(u64, p->scx.slice, SCX_SLICE_DFL);
+			__setscheduler_prio(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_exit(&sti);
+	spin_unlock_irq(&scx_tasks_lock);
+
+	/* no task is on scx, turn off all the switches and flush in-progress calls */
+	static_branch_disable_cpuslocked(&__scx_ops_enabled);
+	for (i = SCX_OPI_BEGIN; i < SCX_OPI_END; i++)
+		static_branch_disable_cpuslocked(&scx_has_op[i]);
+	static_branch_disable_cpuslocked(&scx_ops_enq_last);
+	static_branch_disable_cpuslocked(&scx_ops_enq_exiting);
+	static_branch_disable_cpuslocked(&scx_ops_cpu_preempt);
+	static_branch_disable_cpuslocked(&scx_builtin_idle_enabled);
+	synchronize_rcu();
+
+	cpus_read_unlock();
+	percpu_up_write(&scx_fork_rwsem);
+
+	if (ei->kind >= SCX_EXIT_ERROR) {
+		printk(KERN_ERR "sched_ext: BPF scheduler \"%s\" errored, disabling\n", scx_ops.name);
+
+		if (ei->msg[0] == '\0')
+			printk(KERN_ERR "sched_ext: %s\n", ei->reason);
+		else
+			printk(KERN_ERR "sched_ext: %s (%s)\n", ei->reason, ei->msg);
+
+		stack_trace_print(ei->bt, ei->bt_len, 2);
+	}
+
+	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;
+
+	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();
+	}
+
+	bt_len = stack_trace_save_tsk(p, bt, SCX_EXIT_BT_LEN, 1);
+	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;
+
+	if (kind >= SCX_EXIT_ERROR)
+		ei->bt_len = stack_trace_save(ei->bt, SCX_EXIT_BT_LEN, 1);
+
+	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 scx_task_iter sti;
+	struct task_struct *p;
+	unsigned long timeout;
+	int i, cpu, 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 (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 PREPPING 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_PREPPING) !=
+		     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_SLEEPABLE, init);
+		if (ret) {
+			ret = ops_sanitize_err("init", ret);
+			goto err_disable_unlock_cpus;
+		}
+	}
+
+	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]);
+
+	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);
+
+	/*
+	 * Lock out forks before opening the floodgate so that they don't wander
+	 * into the operations prematurely.
+	 *
+	 * We don't need to keep the CPUs stable but grab cpus_read_lock() to
+	 * ease future locking changes for cgroup suport.
+	 *
+	 * Note that cpu_hotplug_lock must nest inside scx_fork_rwsem due to the
+	 * following dependency chain:
+	 *
+	 *   scx_fork_rwsem --> pernet_ops_rwsem --> cpu_hotplug_lock
+	 */
+	percpu_down_write(&scx_fork_rwsem);
+	cpus_read_lock();
+
+	check_hotplug_seq(ops);
+
+	for (i = SCX_OPI_NORMAL_BEGIN; i < SCX_OPI_NORMAL_END; i++)
+		if (((void (**)(void))ops)[i])
+			static_branch_enable_cpuslocked(&scx_has_op[i]);
+
+	if (ops->flags & SCX_OPS_ENQ_LAST)
+		static_branch_enable_cpuslocked(&scx_ops_enq_last);
+
+	if (ops->flags & SCX_OPS_ENQ_EXITING)
+		static_branch_enable_cpuslocked(&scx_ops_enq_exiting);
+	if (scx_ops.cpu_acquire || scx_ops.cpu_release)
+		static_branch_enable_cpuslocked(&scx_ops_cpu_preempt);
+
+	if (!ops->update_idle || (ops->flags & SCX_OPS_KEEP_BUILTIN_IDLE)) {
+		reset_idle_masks();
+		static_branch_enable_cpuslocked(&scx_builtin_idle_enabled);
+	} else {
+		static_branch_disable_cpuslocked(&scx_builtin_idle_enabled);
+	}
+
+	static_branch_enable_cpuslocked(&__scx_ops_enabled);
+
+	/*
+	 * 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.
+	 */
+	spin_lock_irq(&scx_tasks_lock);
+
+	scx_task_iter_init(&sti);
+	while ((p = scx_task_iter_next_locked(&sti, false))) {
+		get_task_struct(p);
+		scx_task_iter_rq_unlock(&sti);
+		spin_unlock_irq(&scx_tasks_lock);
+
+		ret = scx_ops_init_task(p, task_group(p), false);
+		if (ret) {
+			put_task_struct(p);
+			spin_lock_irq(&scx_tasks_lock);
+			scx_task_iter_exit(&sti);
+			spin_unlock_irq(&scx_tasks_lock);
+			pr_err("sched_ext: ops.init_task() failed (%d) for %s[%d] while loading\n",
+			       ret, p->comm, p->pid);
+			goto err_disable_unlock_all;
+		}
+
+		put_task_struct(p);
+		spin_lock_irq(&scx_tasks_lock);
+	}
+	scx_task_iter_exit(&sti);
+
+	/*
+	 * All tasks are prepped but are still ops-disabled. Ensure that
+	 * %current can't be scheduled out and switch everyone.
+	 * preempt_disable() is necessary because we can't guarantee that
+	 * %current won't be starved if scheduled out while switching.
+	 */
+	preempt_disable();
+
+	/*
+	 * From here on, the disable path must assume that tasks have ops
+	 * enabled and need to be recovered.
+	 *
+	 * Transition to ENABLING fails iff the BPF scheduler has already
+	 * triggered scx_bpf_error(). Returning an error code here would lose
+	 * the recorded error information. Exit indicating success so that the
+	 * error is notified through ops.exit() with all the details.
+	 */
+	if (!scx_ops_tryset_enable_state(SCX_OPS_ENABLING, SCX_OPS_PREPPING)) {
+		preempt_enable();
+		spin_unlock_irq(&scx_tasks_lock);
+		WARN_ON_ONCE(atomic_read(&scx_exit_kind) == SCX_EXIT_NONE);
+		ret = 0;
+		goto err_disable_unlock_all;
+	}
+
+	/*
+	 * We're fully committed and can't fail. The PREPPED -> ENABLED
+	 * transitions here are synchronized against sched_ext_free() through
+	 * scx_tasks_lock.
+	 */
+	WRITE_ONCE(scx_switching_all, !(ops->flags & SCX_OPS_SWITCH_PARTIAL));
+
+	scx_task_iter_init(&sti);
+	while ((p = scx_task_iter_next_locked(&sti, false))) {
+		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);
+
+		scx_set_task_state(p, SCX_TASK_READY);
+		__setscheduler_prio(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_exit(&sti);
+
+	spin_unlock_irq(&scx_tasks_lock);
+	preempt_enable();
+	cpus_read_unlock();
+	percpu_up_write(&scx_fork_rwsem);
+
+	/* see above ENABLING transition for the explanation on exiting with 0 */
+	if (!scx_ops_tryset_enable_state(SCX_OPS_ENABLED, SCX_OPS_ENABLING)) {
+		WARN_ON_ONCE(atomic_read(&scx_exit_kind) == SCX_EXIT_NONE);
+		ret = 0;
+		goto err_disable;
+	}
+
+	if (!(ops->flags & SCX_OPS_SWITCH_PARTIAL))
+		static_branch_enable(&__scx_switched_all);
+
+	kobject_uevent(scx_root_kobj, KOBJ_ADD);
+	mutex_unlock(&scx_ops_enable_mutex);
+
+	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:
+	percpu_up_write(&scx_fork_rwsem);
+err_disable_unlock_cpus:
+	cpus_read_unlock();
+err_disable:
+	mutex_unlock(&scx_ops_enable_mutex);
+	/* must be fully disabled before returning */
+	scx_ops_disable(SCX_EXIT_ERROR);
+	kthread_flush_work(&scx_ops_disable_work);
+	return ret;
+}
+
+
+/********************************************************************************
+ * 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):
+	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)
+{
+	return scx_ops_enable(kdata);
+}
+
+static void bpf_scx_unreg(void *kdata)
+{
+	scx_ops_disable(SCX_EXIT_UNREG);
+	kthread_flush_work(&scx_ops_disable_work);
+}
+
+static int bpf_scx_init(struct btf *btf)
+{
+	u32 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)
+{
+	/*
+	 * 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 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) {}
+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 struct sched_ext_ops __bpf_ops_sched_ext_ops = {
+	.select_cpu = select_cpu_stub,
+	.enqueue = enqueue_stub,
+	.dequeue = dequeue_stub,
+	.dispatch = dispatch_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,
+	.cpu_online = cpu_online_stub,
+	.cpu_offline = cpu_offline_stub,
+	.init = init_stub,
+	.exit = exit_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);
+
+	BUG_ON(rhashtable_init(&dsq_hash, &dsq_hash_params));
+	init_dsq(&scx_dsq_global, SCX_DSQ_GLOBAL);
+#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_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 ops.init() and
+ * ops.init_task().
+ */
+__bpf_kfunc s32 scx_bpf_create_dsq(u64 dsq_id, s32 node)
+{
+	if (!scx_kf_allowed(SCX_KF_SLEEPABLE))
+		return -EINVAL;
+
+	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_sleepable)
+BTF_ID_FLAGS(func, scx_bpf_create_dsq, KF_SLEEPABLE)
+BTF_KFUNCS_END(scx_kfunc_ids_sleepable)
+
+static const struct btf_kfunc_id_set scx_kfunc_set_sleepable = {
+	.owner			= THIS_MODULE,
+	.set			= &scx_kfunc_ids_sleepable,
+};
+
+__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 (!scx_kf_allowed(SCX_KF_SELECT_CPU)) {
+		*is_idle = false;
+		return prev_cpu;
+	}
+#ifdef CONFIG_SMP
+	return scx_select_cpu_dfl(p, prev_cpu, wake_flags, is_idle);
+#else
+	*is_idle = false;
+	return prev_cpu;
+#endif
+}
+
+__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
+ * @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
+ * @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,
+};
+
+__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_non_local_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;
+	}
+}
+
+__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_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_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;
+
+	/*
+	 * 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_ops_bypassing())
+		return;
+
+	local_irq_save(irq_flags);
+
+	this_rq = this_rq();
+
+	/*
+	 * 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_non_local_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_ALL_FLAGS)
+		return -EINVAL;
+
+	kit->dsq = find_non_local_dsq(dsq_id);
+	if (!kit->dsq)
+		return -ENOENT;
+
+	INIT_LIST_HEAD(&kit->cursor.node);
+	kit->cursor.is_bpf_iter_cursor = true;
+	kit->dsq_seq = READ_ONCE(kit->dsq->seq);
+	kit->flags = flags;
+
+	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->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->dsq_seq, 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);
+}
+
+__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)
+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_sleepable)) ||
+	    (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_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);
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
new file mode 100644
index 000000000000..32d3a51f591a
--- /dev/null
+++ b/kernel/sched/ext.h
@@ -0,0 +1,69 @@
+/* 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>
+ */
+#ifdef CONFIG_SCHED_CLASS_EXT
+
+void scx_tick(struct rq *rq);
+void init_scx_entity(struct sched_ext_entity *scx);
+void scx_pre_fork(struct task_struct *p);
+int scx_fork(struct task_struct *p);
+void scx_post_fork(struct task_struct *p);
+void scx_cancel_fork(struct task_struct *p);
+bool scx_can_stop_tick(struct rq *rq);
+void scx_rq_activate(struct rq *rq);
+void scx_rq_deactivate(struct rq *rq);
+int scx_check_setscheduler(struct task_struct *p, int policy);
+bool task_should_scx(struct task_struct *p);
+void init_sched_ext_class(void);
+
+static inline u32 scx_cpuperf_target(s32 cpu)
+{
+	if (scx_enabled())
+		return cpu_rq(cpu)->scx.cpuperf_target;
+	else
+		return 0;
+}
+
+static inline bool task_on_scx(const struct task_struct *p)
+{
+	return scx_enabled() && p->sched_class == &ext_sched_class;
+}
+
+#ifdef CONFIG_SCHED_CORE
+bool scx_prio_less(const struct task_struct *a, const struct task_struct *b,
+		   bool in_fi);
+#endif
+
+#else	/* CONFIG_SCHED_CLASS_EXT */
+
+static inline void scx_tick(struct rq *rq) {}
+static inline void scx_pre_fork(struct task_struct *p) {}
+static inline int scx_fork(struct task_struct *p) { return 0; }
+static inline void scx_post_fork(struct task_struct *p) {}
+static inline void scx_cancel_fork(struct task_struct *p) {}
+static inline u32 scx_cpuperf_target(s32 cpu) { return 0; }
+static inline bool scx_can_stop_tick(struct rq *rq) { return true; }
+static inline void scx_rq_activate(struct rq *rq) {}
+static inline void scx_rq_deactivate(struct rq *rq) {}
+static inline int scx_check_setscheduler(struct task_struct *p, int policy) { return 0; }
+static inline bool task_on_scx(const struct task_struct *p) { return false; }
+static inline void init_sched_ext_class(void) {}
+
+#endif	/* CONFIG_SCHED_CLASS_EXT */
+
+#if defined(CONFIG_SCHED_CLASS_EXT) && defined(CONFIG_SMP)
+void __scx_update_idle(struct rq *rq, bool idle);
+
+static inline void scx_update_idle(struct rq *rq, bool idle)
+{
+	if (scx_enabled())
+		__scx_update_idle(rq, idle);
+}
+#else
+static inline void scx_update_idle(struct rq *rq, bool idle) {}
+#endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 213c94d027a4..ee4fe81ba456 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4074,6 +4074,17 @@
 	load->inv_weight = sched_prio_to_wmult[prio];
 }
 
+static void reweight_task_fair(struct rq *rq, struct task_struct *p,
+			       const struct load_weight *lw)
+{
+	struct sched_entity *se = &p->se;
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	struct load_weight *load = &se->load;
+
+	reweight_entity(cfs_rq, se, lw->weight);
+	load->inv_weight = lw->inv_weight;
+}
+
 static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -8348,7 +8348,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	 * Batch and idle tasks do not preempt non-idle tasks (their preemption
 	 * is driven by the tick):
 	 */
-	if (unlikely(p->policy != SCHED_NORMAL) || !sched_feat(WAKEUP_PREEMPTION))
+	if (unlikely(!normal_policy(p->policy)) || !sched_feat(WAKEUP_PREEMPTION))
 		return;
 
 	find_matching_se(&se, &pse);
@@ -9309,28 +9309,18 @@ static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) {
 
 static bool __update_blocked_others(struct rq *rq, bool *done)
 {
-	const struct sched_class *curr_class;
-	u64 now = rq_clock_pelt(rq);
-	unsigned long thermal_pressure;
-	bool decayed;
+	bool updated;
 
 	/*
 	 * update_load_avg() can call cpufreq_update_util(). Make sure that RT,
 	 * DL and IRQ signals have been updated before updating CFS.
 	 */
-	curr_class = rq->curr->sched_class;
-
-	thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
-
-	decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
-		  update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
-		  update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure) |
-		  update_irq_load_avg(rq, 0);
+	updated = update_other_load_avgs(rq);
 
 	if (others_have_blocked(rq))
 		*done = false;
 
-	return decayed;
+	return updated;
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -13156,6 +13146,7 @@ DEFINE_SCHED_CLASS(fair) = {
 	.task_tick		= task_tick_fair,
 	.task_fork		= task_fork_fair,
 
+	.reweight_task		= reweight_task_fair,
 	.prio_changed		= prio_changed_fair,
 	.switched_from		= switched_from_fair,
 	.switched_to		= switched_to_fair,
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 6135fbe83d68..3b6540cc436a 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -458,11 +458,13 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags)
 
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
+	scx_update_idle(rq, false);
 }
 
 static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
 {
 	update_idle_core(rq);
+	scx_update_idle(rq, true);
 	schedstat_inc(rq->sched_goidle);
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ae50f212775e..9ce5074e8a8d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -173,9 +173,19 @@ static inline int idle_policy(int policy)
 {
 	return policy == SCHED_IDLE;
 }
+
+static inline int normal_policy(int policy)
+{
+#ifdef CONFIG_SCHED_CLASS_EXT
+	if (policy == SCHED_EXT)
+		return true;
+#endif
+	return policy == SCHED_NORMAL;
+}
+
 static inline int fair_policy(int policy)
 {
-	return policy == SCHED_NORMAL || policy == SCHED_BATCH;
+	return normal_policy(policy) || policy == SCHED_BATCH;
 }
 
 static inline int rt_policy(int policy)
@@ -223,6 +233,24 @@ static inline void update_avg(u64 *avg, u64 sample)
 #define shr_bound(val, shift)							\
 	(val >> min_t(typeof(shift), shift, BITS_PER_TYPE(typeof(val)) - 1))
 
+/*
+ * cgroup weight knobs should use the common MIN, DFL and MAX values which are
+ * 1, 100 and 10000 respectively. While it loses a bit of range on both ends, it
+ * maps pretty well onto the shares value used by scheduler and the round-trip
+ * conversions preserve the original value over the entire range.
+ */
+static inline unsigned long sched_weight_from_cgroup(unsigned long cgrp_weight)
+{
+	return DIV_ROUND_CLOSEST_ULL(cgrp_weight * 1024, CGROUP_WEIGHT_DFL);
+}
+
+static inline unsigned long sched_weight_to_cgroup(unsigned long weight)
+{
+	return clamp_t(unsigned long,
+		       DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024),
+		       CGROUP_WEIGHT_MIN, CGROUP_WEIGHT_MAX);
+}
+
 /*
  * !! For sched_setattr_nocheck() (kernel) only !!
  *
@@ -461,6 +489,11 @@ static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
 	return walk_tg_tree_from(&root_task_group, down, up, data);
 }
 
+static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
+{
+	return css ? container_of(css, struct task_group, css) : NULL;
+}
+
 extern int tg_nop(struct task_group *tg, void *data);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -569,6 +602,12 @@ do {									\
 # define u64_u32_load(var)      u64_u32_load_copy(var, var##_copy)
 # define u64_u32_store(var, val) u64_u32_store_copy(var, var##_copy, val)
 
+struct rq;
+struct balance_callback {
+	struct balance_callback *next;
+	void (*func)(struct rq *rq);
+};
+
 /* CFS-related fields in a runqueue */
 struct cfs_rq {
 	struct load_weight	load;
@@ -677,6 +716,42 @@ struct cfs_rq {
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 };
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+/* scx_rq->flags, protected by the rq lock */
+enum scx_rq_flags {
+	/*
+	 * A hotplugged CPU starts scheduling before rq_online_scx(). Track
+	 * ops.cpu_on/offline() state so that ops.enqueue/dispatch() are called
+	 * only while the BPF scheduler considers the CPU to be online.
+	 */
+	SCX_RQ_ONLINE		= 1 << 0,
+	SCX_RQ_CAN_STOP_TICK	= 1 << 1,
+
+	SCX_RQ_IN_WAKEUP	= 1 << 16,
+	SCX_RQ_IN_BALANCE	= 1 << 17,
+};
+
+struct scx_rq {
+	struct scx_dispatch_q	local_dsq;
+	struct list_head	runnable_list;		/* runnable tasks on this rq */
+	struct list_head	ddsp_deferred_locals;	/* deferred ddsps from enq */
+	unsigned long		ops_qseq;
+	u64			extra_enq_flags;	/* see move_task_to_local_dsq() */
+	u32			nr_running;
+	u32			flags;
+	u32			cpuperf_target;		/* [0, SCHED_CAPACITY_SCALE] */
+	bool			cpu_released;
+	cpumask_var_t		cpus_to_kick;
+	cpumask_var_t		cpus_to_kick_if_idle;
+	cpumask_var_t		cpus_to_preempt;
+	cpumask_var_t		cpus_to_wait;
+	unsigned long		pnt_seq;
+	struct balance_callback	deferred_bal_cb;
+	struct irq_work		deferred_irq_work;
+	struct irq_work		kick_cpus_irq_work;
+};
+#endif /* CONFIG_SCHED_CLASS_EXT */
+
 static inline int rt_bandwidth_enabled(void)
 {
 	return sysctl_sched_rt_runtime >= 0;
@@ -969,12 +1044,6 @@ struct uclamp_rq {
 DECLARE_STATIC_KEY_FALSE(sched_uclamp_used);
 #endif /* CONFIG_UCLAMP_TASK */
 
-struct rq;
-struct balance_callback {
-	struct balance_callback *next;
-	void (*func)(struct rq *rq);
-};
-
 /*
  * This is the main, per-CPU runqueue data structure.
  *
@@ -1017,6 +1086,9 @@ struct rq {
 	struct cfs_rq		cfs;
 	struct rt_rq		rt;
 	struct dl_rq		dl;
+#ifdef CONFIG_SCHED_CLASS_EXT
+	struct scx_rq		scx;
+#endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this CPU: */
@@ -2276,6 +2348,8 @@ struct sched_class {
 	void (*put_prev_task)(struct rq *rq, struct task_struct *p);
 	void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
 
+	void (*switch_class)(struct rq *rq, struct task_struct *next);
+
 #ifdef CONFIG_SMP
 	int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int flags);
@@ -2303,8 +2377,11 @@ struct sched_class {
 	 * cannot assume the switched_from/switched_to pair is serialized by
 	 * rq->lock. They are however serialized by p->pi_lock.
 	 */
+	void (*switching_to) (struct rq *this_rq, struct task_struct *task);
 	void (*switched_from)(struct rq *this_rq, struct task_struct *task);
 	void (*switched_to)  (struct rq *this_rq, struct task_struct *task);
+	void (*reweight_task)(struct rq *this_rq, struct task_struct *task,
+			      const struct load_weight *lw);
 	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
 			      int oldprio);
 
@@ -2353,19 +2430,54 @@ const struct sched_class name##_sched_class \
 extern struct sched_class __sched_class_highest[];
 extern struct sched_class __sched_class_lowest[];
 
+extern const struct sched_class stop_sched_class;
+extern const struct sched_class dl_sched_class;
+extern const struct sched_class rt_sched_class;
+extern const struct sched_class fair_sched_class;
+extern const struct sched_class idle_sched_class;
+
+#ifdef CONFIG_SCHED_CLASS_EXT
+extern const struct sched_class ext_sched_class;
+
+DECLARE_STATIC_KEY_FALSE(__scx_ops_enabled);	/* SCX BPF scheduler loaded */
+DECLARE_STATIC_KEY_FALSE(__scx_switched_all);	/* all fair class tasks on SCX */
+
+#define scx_enabled()		static_branch_unlikely(&__scx_ops_enabled)
+#define scx_switched_all()	static_branch_unlikely(&__scx_switched_all)
+#else /* !CONFIG_SCHED_CLASS_EXT */
+#define scx_enabled()		false
+#define scx_switched_all()	false
+#endif /* !CONFIG_SCHED_CLASS_EXT */
+
+/*
+ * Iterate only active classes. SCX can take over all fair tasks or be
+ * completely disabled. If the former, skip fair. If the latter, skip SCX.
+ */
+static inline const struct sched_class *next_active_class(const struct sched_class *class)
+{
+	class++;
+#ifdef CONFIG_SCHED_CLASS_EXT
+	if (scx_switched_all() && class == &fair_sched_class)
+		class++;
+	if (!scx_enabled() && class == &ext_sched_class)
+		class++;
+#endif
+	return class;
+}
+
 #define for_class_range(class, _from, _to) \
 	for (class = (_from); class < (_to); class++)
 
 #define for_each_class(class) \
 	for_class_range(class, __sched_class_highest, __sched_class_lowest)
 
-#define sched_class_above(_a, _b)	((_a) < (_b))
+#define for_active_class_range(class, _from, _to)				\
+	for (class = (_from); class != (_to); class = next_active_class(class))
 
-extern const struct sched_class stop_sched_class;
-extern const struct sched_class dl_sched_class;
-extern const struct sched_class rt_sched_class;
-extern const struct sched_class fair_sched_class;
-extern const struct sched_class idle_sched_class;
+#define for_each_active_class(class)						\
+	for_active_class_range(class, __sched_class_highest, __sched_class_lowest)
+
+#define sched_class_above(_a, _b)	((_a) < (_b))
 
 static inline bool sched_stop_runnable(struct rq *rq)
 {
@@ -2462,7 +2574,7 @@ extern void init_sched_dl_class(void);
 extern void init_sched_rt_class(void);
 extern void init_sched_fair_class(void);
 
-extern void reweight_task(struct task_struct *p, int prio);
+extern void __setscheduler_prio(struct task_struct *p, int prio);
 
 extern void resched_curr(struct rq *rq);
 extern void resched_cpu(int cpu);
@@ -2542,6 +2654,12 @@ static inline void sub_nr_running(struct rq *rq, unsigned count)
 extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
 extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
 
+extern void check_class_changing(struct rq *rq, struct task_struct *p,
+				 const struct sched_class *prev_class);
+extern void check_class_changed(struct rq *rq, struct task_struct *p,
+				const struct sched_class *prev_class,
+				int oldprio);
+
 extern void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags);
 
 #ifdef CONFIG_PREEMPT_RT
@@ -3007,6 +3125,9 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif
 
 #ifdef CONFIG_SMP
+
+bool update_other_load_avgs(struct rq *rq);
+
 unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
 				 unsigned long *min,
 				 unsigned long *max);
@@ -3049,6 +3170,8 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
 {
 	return READ_ONCE(rq->avg_rt.util_avg);
 }
+#else /* !CONFIG_SMP */
+static inline bool update_other_load_avgs(struct rq *rq) { return false; }
 #endif
 
 #ifdef CONFIG_UCLAMP_TASK
@@ -3481,4 +3604,24 @@ static inline void init_sched_mm_cid(struct task_struct *t) { }
 extern u64 avg_vruntime(struct cfs_rq *cfs_rq);
 extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se);
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+/*
+ * Used by SCX in the enable/disable paths to move tasks between sched_classes
+ * and establish invariants.
+ */
+struct sched_enq_and_set_ctx {
+	struct task_struct	*p;
+	int			queue_flags;
+	bool			queued;
+	bool			running;
+};
+
+void sched_deq_and_put_task(struct task_struct *p, int queue_flags,
+			    struct sched_enq_and_set_ctx *ctx);
+void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx);
+
+#endif /* CONFIG_SCHED_CLASS_EXT */
+
+#include "ext.h"
+
 #endif /* _KERNEL_SCHED_SCHED_H */
diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index 222c6d6c8281..9581ef4efec5 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -68,6 +68,7 @@ void dump_stack_print_info(const char *log_lvl)
 
 	print_worker_info(log_lvl, current);
 	print_stop_info(log_lvl, current);
+	print_scx_info(log_lvl, current);
 }
 
 /**
diff --git a/tools/Makefile b/tools/Makefile
index 276f5d0d53a4..278d24723b74 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -28,6 +28,7 @@ help:
 	@echo '  pci                    - PCI tools'
 	@echo '  perf                   - Linux performance measurement and analysis tool'
 	@echo '  selftests              - various kernel selftests'
+	@echo '  sched_ext              - sched_ext example schedulers'
 	@echo '  bootconfig             - boot config tool'
 	@echo '  spi                    - spi tools'
 	@echo '  tmon                   - thermal monitoring and tuning tool'
@@ -91,6 +92,9 @@ perf: FORCE
 	$(Q)mkdir -p $(PERF_O) .
 	$(Q)$(MAKE) --no-print-directory -C perf O=$(PERF_O) subdir=
 
+sched_ext: FORCE
+	$(call descend,sched_ext)
+
 selftests: FORCE
 	$(call descend,testing/$@)
 
@@ -184,6 +188,9 @@ perf_clean:
 	$(Q)mkdir -p $(PERF_O) .
 	$(Q)$(MAKE) --no-print-directory -C perf O=$(PERF_O) subdir= clean
 
+sched_ext_clean:
+	$(call descend,sched_ext,clean)
+
 selftests_clean:
 	$(call descend,testing/$(@:_clean=),clean)
 
@@ -213,6 +220,7 @@ clean: acpi_clean counter_clean cpupower_clean hv_clean firewire_clean \
 		mm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
 		freefall_clean build_clean libbpf_clean libsubcmd_clean \
 		gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \
-		intel-speed-select_clean tracing_clean thermal_clean thermometer_clean thermal-engine_clean
+		intel-speed-select_clean tracing_clean thermal_clean thermometer_clean thermal-engine_clean \
+		sched_ext_clean
 
 .PHONY: FORCE
diff --git a/tools/sched_ext/.gitignore b/tools/sched_ext/.gitignore
new file mode 100644
index 000000000000..d6264fe1c8cd
--- /dev/null
+++ b/tools/sched_ext/.gitignore
@@ -0,0 +1,2 @@
+tools/
+build/
diff --git a/tools/sched_ext/Makefile b/tools/sched_ext/Makefile
new file mode 100644
index 000000000000..bf7e108f5ae1
--- /dev/null
+++ b/tools/sched_ext/Makefile
@@ -0,0 +1,246 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+include ../build/Build.include
+include ../scripts/Makefile.arch
+include ../scripts/Makefile.include
+
+all: all_targets
+
+ifneq ($(LLVM),)
+ifneq ($(filter %/,$(LLVM)),)
+LLVM_PREFIX := $(LLVM)
+else ifneq ($(filter -%,$(LLVM)),)
+LLVM_SUFFIX := $(LLVM)
+endif
+
+CLANG_TARGET_FLAGS_arm          := arm-linux-gnueabi
+CLANG_TARGET_FLAGS_arm64        := aarch64-linux-gnu
+CLANG_TARGET_FLAGS_hexagon      := hexagon-linux-musl
+CLANG_TARGET_FLAGS_m68k         := m68k-linux-gnu
+CLANG_TARGET_FLAGS_mips         := mipsel-linux-gnu
+CLANG_TARGET_FLAGS_powerpc      := powerpc64le-linux-gnu
+CLANG_TARGET_FLAGS_riscv        := riscv64-linux-gnu
+CLANG_TARGET_FLAGS_s390         := s390x-linux-gnu
+CLANG_TARGET_FLAGS_x86          := x86_64-linux-gnu
+CLANG_TARGET_FLAGS              := $(CLANG_TARGET_FLAGS_$(ARCH))
+
+ifeq ($(CROSS_COMPILE),)
+ifeq ($(CLANG_TARGET_FLAGS),)
+$(error Specify CROSS_COMPILE or add '--target=' option to lib.mk)
+else
+CLANG_FLAGS     += --target=$(CLANG_TARGET_FLAGS)
+endif # CLANG_TARGET_FLAGS
+else
+CLANG_FLAGS     += --target=$(notdir $(CROSS_COMPILE:%-=%))
+endif # CROSS_COMPILE
+
+CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) $(CLANG_FLAGS) -fintegrated-as
+else
+CC := $(CROSS_COMPILE)gcc
+endif # LLVM
+
+CURDIR := $(abspath .)
+TOOLSDIR := $(abspath ..)
+LIBDIR := $(TOOLSDIR)/lib
+BPFDIR := $(LIBDIR)/bpf
+TOOLSINCDIR := $(TOOLSDIR)/include
+BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool
+APIDIR := $(TOOLSINCDIR)/uapi
+GENDIR := $(abspath ../../include/generated)
+GENHDR := $(GENDIR)/autoconf.h
+
+ifeq ($(O),)
+OUTPUT_DIR := $(CURDIR)/build
+else
+OUTPUT_DIR := $(O)/build
+endif # O
+OBJ_DIR := $(OUTPUT_DIR)/obj
+INCLUDE_DIR := $(OUTPUT_DIR)/include
+BPFOBJ_DIR := $(OBJ_DIR)/libbpf
+SCXOBJ_DIR := $(OBJ_DIR)/sched_ext
+BINDIR := $(OUTPUT_DIR)/bin
+BPFOBJ := $(BPFOBJ_DIR)/libbpf.a
+ifneq ($(CROSS_COMPILE),)
+HOST_BUILD_DIR		:= $(OBJ_DIR)/host
+HOST_OUTPUT_DIR	:= host-tools
+HOST_INCLUDE_DIR	:= $(HOST_OUTPUT_DIR)/include
+else
+HOST_BUILD_DIR		:= $(OBJ_DIR)
+HOST_OUTPUT_DIR	:= $(OUTPUT_DIR)
+HOST_INCLUDE_DIR	:= $(INCLUDE_DIR)
+endif
+HOST_BPFOBJ := $(HOST_BUILD_DIR)/libbpf/libbpf.a
+RESOLVE_BTFIDS := $(HOST_BUILD_DIR)/resolve_btfids/resolve_btfids
+DEFAULT_BPFTOOL := $(HOST_OUTPUT_DIR)/sbin/bpftool
+
+VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)					\
+		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)		\
+		     ../../vmlinux						\
+		     /sys/kernel/btf/vmlinux					\
+		     /boot/vmlinux-$(shell uname -r)
+VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+ifeq ($(VMLINUX_BTF),)
+$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)")
+endif
+
+BPFTOOL ?= $(DEFAULT_BPFTOOL)
+
+ifneq ($(wildcard $(GENHDR)),)
+  GENFLAGS := -DHAVE_GENHDR
+endif
+
+CFLAGS += -g -O2 -rdynamic -pthread -Wall -Werror $(GENFLAGS)			\
+	  -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)				\
+	  -I$(TOOLSINCDIR) -I$(APIDIR) -I$(CURDIR)/include
+
+# Silence some warnings when compiled with clang
+ifneq ($(LLVM),)
+CFLAGS += -Wno-unused-command-line-argument
+endif
+
+LDFLAGS = -lelf -lz -lpthread
+
+IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null |				\
+			grep 'define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__')
+
+# Get Clang's default includes on this system, as opposed to those seen by
+# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
+#
+# Use '-idirafter': Don't interfere with include mechanics except where the
+# build would have failed anyways.
+define get_sys_includes
+$(shell $(1) -v -E - </dev/null 2>&1 \
+	| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
+$(shell $(1) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}')
+endef
+
+BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH)					\
+	     $(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian)		\
+	     -I$(CURDIR)/include -I$(CURDIR)/include/bpf-compat			\
+	     -I$(INCLUDE_DIR) -I$(APIDIR)					\
+	     -I../../include							\
+	     $(call get_sys_includes,$(CLANG))					\
+	     -Wall -Wno-compare-distinct-pointer-types				\
+	     -O2 -mcpu=v3
+
+# sort removes libbpf duplicates when not cross-building
+MAKE_DIRS := $(sort $(OBJ_DIR)/libbpf $(HOST_BUILD_DIR)/libbpf			\
+	       $(HOST_BUILD_DIR)/bpftool $(HOST_BUILD_DIR)/resolve_btfids	\
+	       $(INCLUDE_DIR) $(SCXOBJ_DIR) $(BINDIR))
+
+$(MAKE_DIRS):
+	$(call msg,MKDIR,,$@)
+	$(Q)mkdir -p $@
+
+$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)			\
+	   $(APIDIR)/linux/bpf.h						\
+	   | $(OBJ_DIR)/libbpf
+	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(OBJ_DIR)/libbpf/	\
+		    EXTRA_CFLAGS='-g -O0 -fPIC'					\
+		    DESTDIR=$(OUTPUT_DIR) prefix= all install_headers
+
+$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)	\
+		    $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
+	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)				\
+		    ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD)		\
+		    EXTRA_CFLAGS='-g -O0'					\
+		    OUTPUT=$(HOST_BUILD_DIR)/bpftool/				\
+		    LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/			\
+		    LIBBPF_DESTDIR=$(HOST_OUTPUT_DIR)/				\
+		    prefix= DESTDIR=$(HOST_OUTPUT_DIR)/ install-bin
+
+$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR)
+ifeq ($(VMLINUX_H),)
+	$(call msg,GEN,,$@)
+	$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
+else
+	$(call msg,CP,,$@)
+	$(Q)cp "$(VMLINUX_H)" $@
+endif
+
+$(SCXOBJ_DIR)/%.bpf.o: %.bpf.c $(INCLUDE_DIR)/vmlinux.h include/scx/*.h		\
+		       | $(BPFOBJ) $(SCXOBJ_DIR)
+	$(call msg,CLNG-BPF,,$(notdir $@))
+	$(Q)$(CLANG) $(BPF_CFLAGS) -target bpf -c $< -o $@
+
+$(INCLUDE_DIR)/%.bpf.skel.h: $(SCXOBJ_DIR)/%.bpf.o $(INCLUDE_DIR)/vmlinux.h $(BPFTOOL)
+	$(eval sched=$(notdir $@))
+	$(call msg,GEN-SKEL,,$(sched))
+	$(Q)$(BPFTOOL) gen object $(<:.o=.linked1.o) $<
+	$(Q)$(BPFTOOL) gen object $(<:.o=.linked2.o) $(<:.o=.linked1.o)
+	$(Q)$(BPFTOOL) gen object $(<:.o=.linked3.o) $(<:.o=.linked2.o)
+	$(Q)diff $(<:.o=.linked2.o) $(<:.o=.linked3.o)
+	$(Q)$(BPFTOOL) gen skeleton $(<:.o=.linked3.o) name $(subst .bpf.skel.h,,$(sched)) > $@
+	$(Q)$(BPFTOOL) gen subskeleton $(<:.o=.linked3.o) name $(subst .bpf.skel.h,,$(sched)) > $(@:.skel.h=.subskel.h)
+
+SCX_COMMON_DEPS := include/scx/common.h include/scx/user_exit_info.h | $(BINDIR)
+
+c-sched-targets = scx_simple scx_qmap scx_central
+
+$(addprefix $(BINDIR)/,$(c-sched-targets)): \
+	$(BINDIR)/%: \
+		$(filter-out %.bpf.c,%.c) \
+		$(INCLUDE_DIR)/%.bpf.skel.h \
+		$(SCX_COMMON_DEPS)
+	$(eval sched=$(notdir $@))
+	$(CC) $(CFLAGS) -c $(sched).c -o $(SCXOBJ_DIR)/$(sched).o
+	$(CC) -o $@ $(SCXOBJ_DIR)/$(sched).o $(HOST_BPFOBJ) $(LDFLAGS)
+
+$(c-sched-targets): %: $(BINDIR)/%
+
+install: all
+	$(Q)mkdir -p $(DESTDIR)/usr/local/bin/
+	$(Q)cp $(BINDIR)/* $(DESTDIR)/usr/local/bin/
+
+clean:
+	rm -rf $(OUTPUT_DIR) $(HOST_OUTPUT_DIR)
+	rm -f *.o *.bpf.o *.bpf.skel.h *.bpf.subskel.h
+	rm -f $(c-sched-targets)
+
+help:
+	@echo   'Building targets'
+	@echo   '================'
+	@echo   ''
+	@echo   '  all		  - Compile all schedulers'
+	@echo   ''
+	@echo   'Alternatively, you may compile individual schedulers:'
+	@echo   ''
+	@printf '  %s\n' $(c-sched-targets)
+	@echo   ''
+	@echo   'For any scheduler build target, you may specify an alternative'
+	@echo   'build output path with the O= environment variable. For example:'
+	@echo   ''
+	@echo   '   O=/tmp/sched_ext make all'
+	@echo   ''
+	@echo   'will compile all schedulers, and emit the build artifacts to'
+	@echo   '/tmp/sched_ext/build.'
+	@echo   ''
+	@echo   ''
+	@echo   'Installing targets'
+	@echo   '=================='
+	@echo   ''
+	@echo   '  install	  - Compile and install all schedulers to /usr/bin.'
+	@echo   '		    You may specify the DESTDIR= environment variable'
+	@echo   '		    to indicate a prefix for /usr/bin. For example:'
+	@echo   ''
+	@echo   '                     DESTDIR=/tmp/sched_ext make install'
+	@echo   ''
+	@echo   '		    will build the schedulers in CWD/build, and'
+	@echo   '		    install the schedulers to /tmp/sched_ext/usr/bin.'
+	@echo   ''
+	@echo   ''
+	@echo   'Cleaning targets'
+	@echo   '================'
+	@echo   ''
+	@echo   '  clean		  - Remove all generated files'
+
+all_targets: $(c-sched-targets)
+
+.PHONY: all all_targets $(c-sched-targets) clean help
+
+# delete failed targets
+.DELETE_ON_ERROR:
+
+# keep intermediate (.bpf.skel.h, .bpf.o, etc) targets
+.SECONDARY:
diff --git a/tools/sched_ext/README.md b/tools/sched_ext/README.md
new file mode 100644
index 000000000000..8efe70cc4363
--- /dev/null
+++ b/tools/sched_ext/README.md
@@ -0,0 +1,258 @@
+SCHED_EXT EXAMPLE SCHEDULERS
+============================
+
+# Introduction
+
+This directory contains a number of example sched_ext schedulers. These
+schedulers are meant to provide examples of different types of schedulers
+that can be built using sched_ext, and illustrate how various features of
+sched_ext can be used.
+
+Some of the examples are performant, production-ready schedulers. That is, for
+the correct workload and with the correct tuning, they may be deployed in a
+production environment with acceptable or possibly even improved performance.
+Others are just examples that in practice, would not provide acceptable
+performance (though they could be improved to get there).
+
+This README will describe these example schedulers, including describing the
+types of workloads or scenarios they're designed to accommodate, and whether or
+not they're production ready. For more details on any of these schedulers,
+please see the header comment in their .bpf.c file.
+
+
+# Compiling the examples
+
+There are a few toolchain dependencies for compiling the example schedulers.
+
+## Toolchain dependencies
+
+1. clang >= 16.0.0
+
+The schedulers are BPF programs, and therefore must be compiled with clang. gcc
+is actively working on adding a BPF backend compiler as well, but are still
+missing some features such as BTF type tags which are necessary for using
+kptrs.
+
+2. pahole >= 1.25
+
+You may need pahole in order to generate BTF from DWARF.
+
+3. rust >= 1.70.0
+
+Rust schedulers uses features present in the rust toolchain >= 1.70.0. You
+should be able to use the stable build from rustup, but if that doesn't
+work, try using the rustup nightly build.
+
+There are other requirements as well, such as make, but these are the main /
+non-trivial ones.
+
+## Compiling the kernel
+
+In order to run a sched_ext scheduler, you'll have to run a kernel compiled
+with the patches in this repository, and with a minimum set of necessary
+Kconfig options:
+
+```
+CONFIG_BPF=y
+CONFIG_SCHED_CLASS_EXT=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_BPF_JIT=y
+CONFIG_DEBUG_INFO_BTF=y
+```
+
+It's also recommended that you also include the following Kconfig options:
+
+```
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_BPF_JIT_DEFAULT_ON=y
+CONFIG_PAHOLE_HAS_SPLIT_BTF=y
+CONFIG_PAHOLE_HAS_BTF_TAG=y
+```
+
+There is a `Kconfig` file in this directory whose contents you can append to
+your local `.config` file, as long as there are no conflicts with any existing
+options in the file.
+
+## Getting a vmlinux.h file
+
+You may notice that most of the example schedulers include a "vmlinux.h" file.
+This is a large, auto-generated header file that contains all of the types
+defined in some vmlinux binary that was compiled with
+[BTF](https://docs.kernel.org/bpf/btf.html) (i.e. with the BTF-related Kconfig
+options specified above).
+
+The header file is created using `bpftool`, by passing it a vmlinux binary
+compiled with BTF as follows:
+
+```bash
+$ bpftool btf dump file /path/to/vmlinux format c > vmlinux.h
+```
+
+`bpftool` analyzes all of the BTF encodings in the binary, and produces a
+header file that can be included by BPF programs to access those types.  For
+example, using vmlinux.h allows a scheduler to access fields defined directly
+in vmlinux as follows:
+
+```c
+#include "vmlinux.h"
+// vmlinux.h is also implicitly included by scx_common.bpf.h.
+#include "scx_common.bpf.h"
+
+/*
+ * vmlinux.h provides definitions for struct task_struct and
+ * struct scx_enable_args.
+ */
+void BPF_STRUCT_OPS(example_enable, struct task_struct *p,
+		    struct scx_enable_args *args)
+{
+	bpf_printk("Task %s enabled in example scheduler", p->comm);
+}
+
+// vmlinux.h provides the definition for struct sched_ext_ops.
+SEC(".struct_ops.link")
+struct sched_ext_ops example_ops {
+	.enable	= (void *)example_enable,
+	.name	= "example",
+}
+```
+
+The scheduler build system will generate this vmlinux.h file as part of the
+scheduler build pipeline. It looks for a vmlinux file in the following
+dependency order:
+
+1. If the O= environment variable is defined, at `$O/vmlinux`
+2. If the KBUILD_OUTPUT= environment variable is defined, at
+   `$KBUILD_OUTPUT/vmlinux`
+3. At `../../vmlinux` (i.e. at the root of the kernel tree where you're
+   compiling the schedulers)
+3. `/sys/kernel/btf/vmlinux`
+4. `/boot/vmlinux-$(uname -r)`
+
+In other words, if you have compiled a kernel in your local repo, its vmlinux
+file will be used to generate vmlinux.h. Otherwise, it will be the vmlinux of
+the kernel you're currently running on. This means that if you're running on a
+kernel with sched_ext support, you may not need to compile a local kernel at
+all.
+
+### Aside on CO-RE
+
+One of the cooler features of BPF is that it supports
+[CO-RE](https://nakryiko.com/posts/bpf-core-reference-guide/) (Compile Once Run
+Everywhere). This feature allows you to reference fields inside of structs with
+types defined internal to the kernel, and not have to recompile if you load the
+BPF program on a different kernel with the field at a different offset. In our
+example above, we print out a task name with `p->comm`. CO-RE would perform
+relocations for that access when the program is loaded to ensure that it's
+referencing the correct offset for the currently running kernel.
+
+## Compiling the schedulers
+
+Once you have your toolchain setup, and a vmlinux that can be used to generate
+a full vmlinux.h file, you can compile the schedulers using `make`:
+
+```bash
+$ make -j($nproc)
+```
+
+# Example schedulers
+
+This directory contains the following example schedulers. These schedulers are
+for testing and demonstrating different aspects of sched_ext. While some may be
+useful in limited scenarios, they are not intended to be practical.
+
+For more scheduler implementations, tools and documentation, visit
+https://github.com/sched-ext/scx.
+
+## scx_simple
+
+A simple scheduler that provides an example of a minimal sched_ext scheduler.
+scx_simple can be run in either global weighted vtime mode, or FIFO mode.
+
+Though very simple, in limited scenarios, this scheduler can perform reasonably
+well on single-socket systems with a unified L3 cache.
+
+## scx_qmap
+
+Another simple, yet slightly more complex scheduler that provides an example of
+a basic weighted FIFO queuing policy. It also provides examples of some common
+useful BPF features, such as sleepable per-task storage allocation in the
+`ops.prep_enable()` callback, and using the `BPF_MAP_TYPE_QUEUE` map type to
+enqueue tasks. It also illustrates how core-sched support could be implemented.
+
+## scx_central
+
+A "central" scheduler where scheduling decisions are made from a single CPU.
+This scheduler illustrates how scheduling decisions can be dispatched from a
+single CPU, allowing other cores to run with infinite slices, without timer
+ticks, and without having to incur the overhead of making scheduling decisions.
+
+The approach demonstrated by this scheduler may be useful for any workload that
+benefits from minimizing scheduling overhead and timer ticks. An example of
+where this could be particularly useful is running VMs, where running with
+infinite slices and no timer ticks allows the VM to avoid unnecessary expensive
+vmexits.
+
+
+# Troubleshooting
+
+There are a number of common issues that you may run into when building the
+schedulers. We'll go over some of the common ones here.
+
+## Build Failures
+
+### Old version of clang
+
+```
+error: static assertion failed due to requirement 'SCX_DSQ_FLAG_BUILTIN': bpftool generated vmlinux.h is missing high bits for 64bit enums, upgrade clang and pahole
+        _Static_assert(SCX_DSQ_FLAG_BUILTIN,
+                       ^~~~~~~~~~~~~~~~~~~~
+1 error generated.
+```
+
+This means you built the kernel or the schedulers with an older version of
+clang than what's supported (i.e. older than 16.0.0). To remediate this:
+
+1. `which clang` to make sure you're using a sufficiently new version of clang.
+
+2. `make fullclean` in the root path of the repository, and rebuild the kernel
+   and schedulers.
+
+3. Rebuild the kernel, and then your example schedulers.
+
+The schedulers are also cleaned if you invoke `make mrproper` in the root
+directory of the tree.
+
+### Stale kernel build / incomplete vmlinux.h file
+
+As described above, you'll need a `vmlinux.h` file that was generated from a
+vmlinux built with BTF, and with sched_ext support enabled. If you don't,
+you'll see errors such as the following which indicate that a type being
+referenced in a scheduler is unknown:
+
+```
+/path/to/sched_ext/tools/sched_ext/user_exit_info.h:25:23: note: forward declaration of 'struct scx_exit_info'
+
+const struct scx_exit_info *ei)
+
+^
+```
+
+In order to resolve this, please follow the steps above in
+[Getting a vmlinux.h file](#getting-a-vmlinuxh-file) in order to ensure your
+schedulers are using a vmlinux.h file that includes the requisite types.
+
+## Misc
+
+### llvm: [OFF]
+
+You may see the following output when building the schedulers:
+
+```
+Auto-detecting system features:
+...                         clang-bpf-co-re: [ on  ]
+...                                    llvm: [ OFF ]
+...                                  libcap: [ on  ]
+...                                  libbfd: [ on  ]
+```
+
+Seeing `llvm: [ OFF ]` here is not an issue. You can safely ignore.
diff --git a/tools/sched_ext/include/bpf-compat/gnu/stubs.h b/tools/sched_ext/include/bpf-compat/gnu/stubs.h
new file mode 100644
index 000000000000..ad7d139ce907
--- /dev/null
+++ b/tools/sched_ext/include/bpf-compat/gnu/stubs.h
@@ -0,0 +1,11 @@
+/*
+ * Dummy gnu/stubs.h. clang can end up including /usr/include/gnu/stubs.h when
+ * compiling BPF files although its content doesn't play any role. The file in
+ * turn includes stubs-64.h or stubs-32.h depending on whether __x86_64__ is
+ * defined. When compiling a BPF source, __x86_64__ isn't set and thus
+ * stubs-32.h is selected. However, the file is not there if the system doesn't
+ * have 32bit glibc devel package installed leading to a build failure.
+ *
+ * The problem is worked around by making this file available in the include
+ * search paths before the system one when building BPF.
+ */
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
new file mode 100644
index 000000000000..20280df62857
--- /dev/null
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -0,0 +1,401 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2022 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2022 David Vernet <dvernet@meta.com>
+ */
+#ifndef __SCX_COMMON_BPF_H
+#define __SCX_COMMON_BPF_H
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <asm-generic/errno.h>
+#include "user_exit_info.h"
+
+#define PF_WQ_WORKER			0x00000020	/* I'm a workqueue worker */
+#define PF_KTHREAD			0x00200000	/* I am a kernel thread */
+#define PF_EXITING			0x00000004
+#define CLOCK_MONOTONIC			1
+
+/*
+ * Earlier versions of clang/pahole lost upper 32bits in 64bit enums which can
+ * lead to really confusing misbehaviors. Let's trigger a build failure.
+ */
+static inline void ___vmlinux_h_sanity_check___(void)
+{
+	_Static_assert(SCX_DSQ_FLAG_BUILTIN,
+		       "bpftool generated vmlinux.h is missing high bits for 64bit enums, upgrade clang and pahole");
+}
+
+s32 scx_bpf_create_dsq(u64 dsq_id, s32 node) __ksym;
+s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *is_idle) __ksym;
+void scx_bpf_dispatch(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_flags) __ksym;
+void scx_bpf_dispatch_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym;
+u32 scx_bpf_dispatch_nr_slots(void) __ksym;
+void scx_bpf_dispatch_cancel(void) __ksym;
+bool scx_bpf_consume(u64 dsq_id) __ksym;
+u32 scx_bpf_reenqueue_local(void) __ksym;
+void scx_bpf_kick_cpu(s32 cpu, u64 flags) __ksym;
+s32 scx_bpf_dsq_nr_queued(u64 dsq_id) __ksym;
+void scx_bpf_destroy_dsq(u64 dsq_id) __ksym;
+int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, u64 flags) __ksym __weak;
+struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *it) __ksym __weak;
+void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it) __ksym __weak;
+void scx_bpf_exit_bstr(s64 exit_code, char *fmt, unsigned long long *data, u32 data__sz) __ksym __weak;
+void scx_bpf_error_bstr(char *fmt, unsigned long long *data, u32 data_len) __ksym;
+void scx_bpf_dump_bstr(char *fmt, unsigned long long *data, u32 data_len) __ksym __weak;
+u32 scx_bpf_cpuperf_cap(s32 cpu) __ksym __weak;
+u32 scx_bpf_cpuperf_cur(s32 cpu) __ksym __weak;
+void scx_bpf_cpuperf_set(s32 cpu, u32 perf) __ksym __weak;
+u32 scx_bpf_nr_cpu_ids(void) __ksym __weak;
+const struct cpumask *scx_bpf_get_possible_cpumask(void) __ksym __weak;
+const struct cpumask *scx_bpf_get_online_cpumask(void) __ksym __weak;
+void scx_bpf_put_cpumask(const struct cpumask *cpumask) __ksym __weak;
+const struct cpumask *scx_bpf_get_idle_cpumask(void) __ksym;
+const struct cpumask *scx_bpf_get_idle_smtmask(void) __ksym;
+void scx_bpf_put_idle_cpumask(const struct cpumask *cpumask) __ksym;
+bool scx_bpf_test_and_clear_cpu_idle(s32 cpu) __ksym;
+s32 scx_bpf_pick_idle_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym;
+s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym;
+bool scx_bpf_task_running(const struct task_struct *p) __ksym;
+s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym;
+struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym;
+
+static inline __attribute__((format(printf, 1, 2)))
+void ___scx_bpf_bstr_format_checker(const char *fmt, ...) {}
+
+/*
+ * Helper macro for initializing the fmt and variadic argument inputs to both
+ * bstr exit kfuncs. Callers to this function should use ___fmt and ___param to
+ * refer to the initialized list of inputs to the bstr kfunc.
+ */
+#define scx_bpf_bstr_preamble(fmt, args...)					\
+	static char ___fmt[] = fmt;						\
+	/*									\
+	 * Note that __param[] must have at least one				\
+	 * element to keep the verifier happy.					\
+	 */									\
+	unsigned long long ___param[___bpf_narg(args) ?: 1] = {};		\
+										\
+	_Pragma("GCC diagnostic push")						\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")			\
+	___bpf_fill(___param, args);						\
+	_Pragma("GCC diagnostic pop")						\
+
+/*
+ * scx_bpf_exit() wraps the scx_bpf_exit_bstr() kfunc with variadic arguments
+ * instead of an array of u64. Using this macro will cause the scheduler to
+ * exit cleanly with the specified exit code being passed to user space.
+ */
+#define scx_bpf_exit(code, fmt, args...)					\
+({										\
+	scx_bpf_bstr_preamble(fmt, args)					\
+	scx_bpf_exit_bstr(code, ___fmt, ___param, sizeof(___param));		\
+	___scx_bpf_bstr_format_checker(fmt, ##args);				\
+})
+
+/*
+ * scx_bpf_error() wraps the scx_bpf_error_bstr() kfunc with variadic arguments
+ * instead of an array of u64. Invoking this macro will cause the scheduler to
+ * exit in an erroneous state, with diagnostic information being passed to the
+ * user.
+ */
+#define scx_bpf_error(fmt, args...)						\
+({										\
+	scx_bpf_bstr_preamble(fmt, args)					\
+	scx_bpf_error_bstr(___fmt, ___param, sizeof(___param));			\
+	___scx_bpf_bstr_format_checker(fmt, ##args);				\
+})
+
+/*
+ * scx_bpf_dump() wraps the scx_bpf_dump_bstr() kfunc with variadic arguments
+ * instead of an array of u64. To be used from ops.dump() and friends.
+ */
+#define scx_bpf_dump(fmt, args...)						\
+({										\
+	scx_bpf_bstr_preamble(fmt, args)					\
+	scx_bpf_dump_bstr(___fmt, ___param, sizeof(___param));			\
+	___scx_bpf_bstr_format_checker(fmt, ##args);				\
+})
+
+#define BPF_STRUCT_OPS(name, args...)						\
+SEC("struct_ops/"#name)								\
+BPF_PROG(name, ##args)
+
+#define BPF_STRUCT_OPS_SLEEPABLE(name, args...)					\
+SEC("struct_ops.s/"#name)							\
+BPF_PROG(name, ##args)
+
+/**
+ * RESIZABLE_ARRAY - Generates annotations for an array that may be resized
+ * @elfsec: the data section of the BPF program in which to place the array
+ * @arr: the name of the array
+ *
+ * libbpf has an API for setting map value sizes. Since data sections (i.e.
+ * bss, data, rodata) themselves are maps, a data section can be resized. If
+ * a data section has an array as its last element, the BTF info for that
+ * array will be adjusted so that length of the array is extended to meet the
+ * new length of the data section. This macro annotates an array to have an
+ * element count of one with the assumption that this array can be resized
+ * within the userspace program. It also annotates the section specifier so
+ * this array exists in a custom sub data section which can be resized
+ * independently.
+ *
+ * See RESIZE_ARRAY() for the userspace convenience macro for resizing an
+ * array declared with RESIZABLE_ARRAY().
+ */
+#define RESIZABLE_ARRAY(elfsec, arr) arr[1] SEC("."#elfsec"."#arr)
+
+/**
+ * MEMBER_VPTR - Obtain the verified pointer to a struct or array member
+ * @base: struct or array to index
+ * @member: dereferenced member (e.g. .field, [idx0][idx1], .field[idx0] ...)
+ *
+ * The verifier often gets confused by the instruction sequence the compiler
+ * generates for indexing struct fields or arrays. This macro forces the
+ * compiler to generate a code sequence which first calculates the byte offset,
+ * checks it against the struct or array size and add that byte offset to
+ * generate the pointer to the member to help the verifier.
+ *
+ * Ideally, we want to abort if the calculated offset is out-of-bounds. However,
+ * BPF currently doesn't support abort, so evaluate to %NULL instead. The caller
+ * must check for %NULL and take appropriate action to appease the verifier. To
+ * avoid confusing the verifier, it's best to check for %NULL and dereference
+ * immediately.
+ *
+ *	vptr = MEMBER_VPTR(my_array, [i][j]);
+ *	if (!vptr)
+ *		return error;
+ *	*vptr = new_value;
+ *
+ * sizeof(@base) should encompass the memory area to be accessed and thus can't
+ * be a pointer to the area. Use `MEMBER_VPTR(*ptr, .member)` instead of
+ * `MEMBER_VPTR(ptr, ->member)`.
+ */
+#define MEMBER_VPTR(base, member) (typeof((base) member) *)			\
+({										\
+	u64 __base = (u64)&(base);						\
+	u64 __addr = (u64)&((base) member) - __base;				\
+	_Static_assert(sizeof(base) >= sizeof((base) member),			\
+		       "@base is smaller than @member, is @base a pointer?");	\
+	asm volatile (								\
+		"if %0 <= %[max] goto +2\n"					\
+		"%0 = 0\n"							\
+		"goto +1\n"							\
+		"%0 += %1\n"							\
+		: "+r"(__addr)							\
+		: "r"(__base),							\
+		  [max]"i"(sizeof(base) - sizeof((base) member)));		\
+	__addr;									\
+})
+
+/**
+ * ARRAY_ELEM_PTR - Obtain the verified pointer to an array element
+ * @arr: array to index into
+ * @i: array index
+ * @n: number of elements in array
+ *
+ * Similar to MEMBER_VPTR() but is intended for use with arrays where the
+ * element count needs to be explicit.
+ * It can be used in cases where a global array is defined with an initial
+ * size but is intended to be be resized before loading the BPF program.
+ * Without this version of the macro, MEMBER_VPTR() will use the compile time
+ * size of the array to compute the max, which will result in rejection by
+ * the verifier.
+ */
+#define ARRAY_ELEM_PTR(arr, i, n) (typeof(arr[i]) *)				\
+({										\
+	u64 __base = (u64)arr;							\
+	u64 __addr = (u64)&(arr[i]) - __base;					\
+	asm volatile (								\
+		"if %0 <= %[max] goto +2\n"					\
+		"%0 = 0\n"							\
+		"goto +1\n"							\
+		"%0 += %1\n"							\
+		: "+r"(__addr)							\
+		: "r"(__base),							\
+		  [max]"r"(sizeof(arr[0]) * ((n) - 1)));			\
+	__addr;									\
+})
+
+
+/*
+ * BPF declarations and helpers
+ */
+
+/* list and rbtree */
+#define __contains(name, node) __attribute__((btf_decl_tag("contains:" #name ":" #node)))
+#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
+
+void *bpf_obj_new_impl(__u64 local_type_id, void *meta) __ksym;
+void bpf_obj_drop_impl(void *kptr, void *meta) __ksym;
+
+#define bpf_obj_new(type) ((type *)bpf_obj_new_impl(bpf_core_type_id_local(type), NULL))
+#define bpf_obj_drop(kptr) bpf_obj_drop_impl(kptr, NULL)
+
+void bpf_list_push_front(struct bpf_list_head *head, struct bpf_list_node *node) __ksym;
+void bpf_list_push_back(struct bpf_list_head *head, struct bpf_list_node *node) __ksym;
+struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) __ksym;
+struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) __ksym;
+struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root,
+				      struct bpf_rb_node *node) __ksym;
+int bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node *node,
+			bool (less)(struct bpf_rb_node *a, const struct bpf_rb_node *b),
+			void *meta, __u64 off) __ksym;
+#define bpf_rbtree_add(head, node, less) bpf_rbtree_add_impl(head, node, less, NULL, 0)
+
+struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root) __ksym;
+
+void *bpf_refcount_acquire_impl(void *kptr, void *meta) __ksym;
+#define bpf_refcount_acquire(kptr) bpf_refcount_acquire_impl(kptr, NULL)
+
+/* task */
+struct task_struct *bpf_task_from_pid(s32 pid) __ksym;
+struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* cgroup */
+struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
+struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
+
+/* css iteration */
+struct bpf_iter_css;
+struct cgroup_subsys_state;
+extern int bpf_iter_css_new(struct bpf_iter_css *it,
+			    struct cgroup_subsys_state *start,
+			    unsigned int flags) __weak __ksym;
+extern struct cgroup_subsys_state *
+bpf_iter_css_next(struct bpf_iter_css *it) __weak __ksym;
+extern void bpf_iter_css_destroy(struct bpf_iter_css *it) __weak __ksym;
+
+/* cpumask */
+struct bpf_cpumask *bpf_cpumask_create(void) __ksym;
+struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) __ksym;
+void bpf_cpumask_release(struct bpf_cpumask *cpumask) __ksym;
+u32 bpf_cpumask_first(const struct cpumask *cpumask) __ksym;
+u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym;
+void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
+void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
+bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) __ksym;
+bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
+bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
+void bpf_cpumask_setall(struct bpf_cpumask *cpumask) __ksym;
+void bpf_cpumask_clear(struct bpf_cpumask *cpumask) __ksym;
+bool bpf_cpumask_and(struct bpf_cpumask *dst, const struct cpumask *src1,
+		     const struct cpumask *src2) __ksym;
+void bpf_cpumask_or(struct bpf_cpumask *dst, const struct cpumask *src1,
+		    const struct cpumask *src2) __ksym;
+void bpf_cpumask_xor(struct bpf_cpumask *dst, const struct cpumask *src1,
+		     const struct cpumask *src2) __ksym;
+bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2) __ksym;
+bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *src2) __ksym;
+bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) __ksym;
+bool bpf_cpumask_empty(const struct cpumask *cpumask) __ksym;
+bool bpf_cpumask_full(const struct cpumask *cpumask) __ksym;
+void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym;
+u32 bpf_cpumask_any_distribute(const struct cpumask *cpumask) __ksym;
+u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
+				   const struct cpumask *src2) __ksym;
+
+/* rcu */
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
+
+/*
+ * Other helpers
+ */
+
+/* useful compiler attributes */
+#define likely(x) __builtin_expect(!!(x), 1)
+#define unlikely(x) __builtin_expect(!!(x), 0)
+#define __maybe_unused __attribute__((__unused__))
+
+/*
+ * READ/WRITE_ONCE() are from kernel (include/asm-generic/rwonce.h). They
+ * prevent compiler from caching, redoing or reordering reads or writes.
+ */
+typedef __u8  __attribute__((__may_alias__))  __u8_alias_t;
+typedef __u16 __attribute__((__may_alias__)) __u16_alias_t;
+typedef __u32 __attribute__((__may_alias__)) __u32_alias_t;
+typedef __u64 __attribute__((__may_alias__)) __u64_alias_t;
+
+static __always_inline void __read_once_size(const volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(__u8_alias_t  *) res = *(volatile __u8_alias_t  *) p; break;
+	case 2: *(__u16_alias_t *) res = *(volatile __u16_alias_t *) p; break;
+	case 4: *(__u32_alias_t *) res = *(volatile __u32_alias_t *) p; break;
+	case 8: *(__u64_alias_t *) res = *(volatile __u64_alias_t *) p; break;
+	default:
+		barrier();
+		__builtin_memcpy((void *)res, (const void *)p, size);
+		barrier();
+	}
+}
+
+static __always_inline void __write_once_size(volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(volatile  __u8_alias_t *) p = *(__u8_alias_t  *) res; break;
+	case 2: *(volatile __u16_alias_t *) p = *(__u16_alias_t *) res; break;
+	case 4: *(volatile __u32_alias_t *) p = *(__u32_alias_t *) res; break;
+	case 8: *(volatile __u64_alias_t *) p = *(__u64_alias_t *) res; break;
+	default:
+		barrier();
+		__builtin_memcpy((void *)p, (const void *)res, size);
+		barrier();
+	}
+}
+
+#define READ_ONCE(x)					\
+({							\
+	union { typeof(x) __val; char __c[1]; } __u =	\
+		{ .__c = { 0 } };			\
+	__read_once_size(&(x), __u.__c, sizeof(x));	\
+	__u.__val;					\
+})
+
+#define WRITE_ONCE(x, val)				\
+({							\
+	union { typeof(x) __val; char __c[1]; } __u =	\
+		{ .__val = (val) }; 			\
+	__write_once_size(&(x), __u.__c, sizeof(x));	\
+	__u.__val;					\
+})
+
+/*
+ * log2_u32 - Compute the base 2 logarithm of a 32-bit exponential value.
+ * @v: The value for which we're computing the base 2 logarithm.
+ */
+static inline u32 log2_u32(u32 v)
+{
+        u32 r;
+        u32 shift;
+
+        r = (v > 0xFFFF) << 4; v >>= r;
+        shift = (v > 0xFF) << 3; v >>= shift; r |= shift;
+        shift = (v > 0xF) << 2; v >>= shift; r |= shift;
+        shift = (v > 0x3) << 1; v >>= shift; r |= shift;
+        r |= (v >> 1);
+        return r;
+}
+
+/*
+ * log2_u64 - Compute the base 2 logarithm of a 64-bit exponential value.
+ * @v: The value for which we're computing the base 2 logarithm.
+ */
+static inline u32 log2_u64(u64 v)
+{
+        u32 hi = v >> 32;
+        if (hi)
+                return log2_u32(hi) + 32 + 1;
+        else
+                return log2_u32(v) + 1;
+}
+
+#include "compat.bpf.h"
+
+#endif	/* __SCX_COMMON_BPF_H */
diff --git a/tools/sched_ext/include/scx/common.h b/tools/sched_ext/include/scx/common.h
new file mode 100644
index 000000000000..5b0f90152152
--- /dev/null
+++ b/tools/sched_ext/include/scx/common.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ */
+#ifndef __SCHED_EXT_COMMON_H
+#define __SCHED_EXT_COMMON_H
+
+#ifdef __KERNEL__
+#error "Should not be included by BPF programs"
+#endif
+
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <errno.h>
+
+typedef uint8_t u8;
+typedef uint16_t u16;
+typedef uint32_t u32;
+typedef uint64_t u64;
+typedef int8_t s8;
+typedef int16_t s16;
+typedef int32_t s32;
+typedef int64_t s64;
+
+#define SCX_BUG(__fmt, ...)							\
+	do {									\
+		fprintf(stderr, "[SCX_BUG] %s:%d", __FILE__, __LINE__);		\
+		if (errno)							\
+			fprintf(stderr, " (%s)\n", strerror(errno));		\
+		else								\
+			fprintf(stderr, "\n");					\
+		fprintf(stderr, __fmt __VA_OPT__(,) __VA_ARGS__);		\
+		fprintf(stderr, "\n");						\
+										\
+		exit(EXIT_FAILURE);						\
+	} while (0)
+
+#define SCX_BUG_ON(__cond, __fmt, ...)					\
+	do {								\
+		if (__cond)						\
+			SCX_BUG((__fmt) __VA_OPT__(,) __VA_ARGS__);	\
+	} while (0)
+
+/**
+ * RESIZE_ARRAY - Convenience macro for resizing a BPF array
+ * @__skel: the skeleton containing the array
+ * @elfsec: the data section of the BPF program in which the array exists
+ * @arr: the name of the array
+ * @n: the desired array element count
+ *
+ * For BPF arrays declared with RESIZABLE_ARRAY(), this macro performs two
+ * operations. It resizes the map which corresponds to the custom data
+ * section that contains the target array. As a side effect, the BTF info for
+ * the array is adjusted so that the array length is sized to cover the new
+ * data section size. The second operation is reassigning the skeleton pointer
+ * for that custom data section so that it points to the newly memory mapped
+ * region.
+ */
+#define RESIZE_ARRAY(__skel, elfsec, arr, n)						\
+	do {										\
+		size_t __sz;								\
+		bpf_map__set_value_size((__skel)->maps.elfsec##_##arr,			\
+				sizeof((__skel)->elfsec##_##arr->arr[0]) * (n));	\
+		(__skel)->elfsec##_##arr =						\
+			bpf_map__initial_value((__skel)->maps.elfsec##_##arr, &__sz);	\
+	} while (0)
+
+#include "user_exit_info.h"
+#include "compat.h"
+
+#endif	/* __SCHED_EXT_COMMON_H */
diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h
new file mode 100644
index 000000000000..3d2fe1208900
--- /dev/null
+++ b/tools/sched_ext/include/scx/compat.bpf.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#ifndef __SCX_COMPAT_BPF_H
+#define __SCX_COMPAT_BPF_H
+
+#define __COMPAT_ENUM_OR_ZERO(__type, __ent)					\
+({										\
+	__type __ret = 0;							\
+	if (bpf_core_enum_value_exists(__type, __ent))				\
+		__ret = __ent;							\
+	__ret;									\
+})
+
+/*
+ * Define sched_ext_ops. This may be expanded to define multiple variants for
+ * backward compatibility. See compat.h::SCX_OPS_LOAD/ATTACH().
+ */
+#define SCX_OPS_DEFINE(__name, ...)						\
+	SEC(".struct_ops.link")							\
+	struct sched_ext_ops __name = {						\
+		__VA_ARGS__,							\
+	};
+
+#endif	/* __SCX_COMPAT_BPF_H */
diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h
new file mode 100644
index 000000000000..1bf8eddf20c2
--- /dev/null
+++ b/tools/sched_ext/include/scx/compat.h
@@ -0,0 +1,187 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#ifndef __SCX_COMPAT_H
+#define __SCX_COMPAT_H
+
+#include <bpf/btf.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+struct btf *__COMPAT_vmlinux_btf __attribute__((weak));
+
+static inline void __COMPAT_load_vmlinux_btf(void)
+{
+	if (!__COMPAT_vmlinux_btf) {
+		__COMPAT_vmlinux_btf = btf__load_vmlinux_btf();
+		SCX_BUG_ON(!__COMPAT_vmlinux_btf, "btf__load_vmlinux_btf()");
+	}
+}
+
+static inline bool __COMPAT_read_enum(const char *type, const char *name, u64 *v)
+{
+	const struct btf_type *t;
+	const char *n;
+	s32 tid;
+	int i;
+
+	__COMPAT_load_vmlinux_btf();
+
+	tid = btf__find_by_name(__COMPAT_vmlinux_btf, type);
+	if (tid < 0)
+		return false;
+
+	t = btf__type_by_id(__COMPAT_vmlinux_btf, tid);
+	SCX_BUG_ON(!t, "btf__type_by_id(%d)", tid);
+
+	if (btf_is_enum(t)) {
+		struct btf_enum *e = btf_enum(t);
+
+		for (i = 0; i < BTF_INFO_VLEN(t->info); i++) {
+			n = btf__name_by_offset(__COMPAT_vmlinux_btf, e[i].name_off);
+			SCX_BUG_ON(!n, "btf__name_by_offset()");
+			if (!strcmp(n, name)) {
+				*v = e[i].val;
+				return true;
+			}
+		}
+	} else if (btf_is_enum64(t)) {
+		struct btf_enum64 *e = btf_enum64(t);
+
+		for (i = 0; i < BTF_INFO_VLEN(t->info); i++) {
+			n = btf__name_by_offset(__COMPAT_vmlinux_btf, e[i].name_off);
+			SCX_BUG_ON(!n, "btf__name_by_offset()");
+			if (!strcmp(n, name)) {
+				*v = btf_enum64_value(&e[i]);
+				return true;
+			}
+		}
+	}
+
+	return false;
+}
+
+#define __COMPAT_ENUM_OR_ZERO(__type, __ent)					\
+({										\
+	u64 __val = 0;								\
+	__COMPAT_read_enum(__type, __ent, &__val);				\
+	__val;									\
+})
+
+static inline bool __COMPAT_has_ksym(const char *ksym)
+{
+	__COMPAT_load_vmlinux_btf();
+	return btf__find_by_name(__COMPAT_vmlinux_btf, ksym) >= 0;
+}
+
+static inline bool __COMPAT_struct_has_field(const char *type, const char *field)
+{
+	const struct btf_type *t;
+	const struct btf_member *m;
+	const char *n;
+	s32 tid;
+	int i;
+
+	__COMPAT_load_vmlinux_btf();
+	tid = btf__find_by_name_kind(__COMPAT_vmlinux_btf, type, BTF_KIND_STRUCT);
+	if (tid < 0)
+		return false;
+
+	t = btf__type_by_id(__COMPAT_vmlinux_btf, tid);
+	SCX_BUG_ON(!t, "btf__type_by_id(%d)", tid);
+
+	m = btf_members(t);
+
+	for (i = 0; i < BTF_INFO_VLEN(t->info); i++) {
+		n = btf__name_by_offset(__COMPAT_vmlinux_btf, m[i].name_off);
+		SCX_BUG_ON(!n, "btf__name_by_offset()");
+			if (!strcmp(n, field))
+				return true;
+	}
+
+	return false;
+}
+
+#define SCX_OPS_SWITCH_PARTIAL							\
+	__COMPAT_ENUM_OR_ZERO("scx_ops_flags", "SCX_OPS_SWITCH_PARTIAL")
+
+static inline long scx_hotplug_seq(void)
+{
+	int fd;
+	char buf[32];
+	ssize_t len;
+	long val;
+
+	fd = open("/sys/kernel/sched_ext/hotplug_seq", O_RDONLY);
+	if (fd < 0)
+		return -ENOENT;
+
+	len = read(fd, buf, sizeof(buf) - 1);
+	SCX_BUG_ON(len <= 0, "read failed (%ld)", len);
+	buf[len] = 0;
+	close(fd);
+
+	val = strtoul(buf, NULL, 10);
+	SCX_BUG_ON(val < 0, "invalid num hotplug events: %lu", val);
+
+	return val;
+}
+
+/*
+ * struct sched_ext_ops can change over time. If compat.bpf.h::SCX_OPS_DEFINE()
+ * is used to define ops and compat.h::SCX_OPS_LOAD/ATTACH() are used to load
+ * and attach it, backward compatibility is automatically maintained where
+ * reasonable.
+ *
+ * ec7e3b0463e1 ("implement-ops") in https://github.com/sched-ext/sched_ext is
+ * the current minimum required kernel version.
+ */
+#define SCX_OPS_OPEN(__ops_name, __scx_name) ({					\
+	struct __scx_name *__skel;						\
+										\
+	SCX_BUG_ON(!__COMPAT_struct_has_field("sched_ext_ops", "dump"),		\
+		   "sched_ext_ops.dump() missing, kernel too old?");		\
+										\
+	__skel = __scx_name##__open();						\
+	SCX_BUG_ON(!__skel, "Could not open " #__scx_name);			\
+	__skel->struct_ops.__ops_name->hotplug_seq = scx_hotplug_seq();		\
+	__skel; 								\
+})
+
+#define SCX_OPS_LOAD(__skel, __ops_name, __scx_name, __uei_name) ({		\
+	UEI_SET_SIZE(__skel, __ops_name, __uei_name);				\
+	SCX_BUG_ON(__scx_name##__load((__skel)), "Failed to load skel");	\
+})
+
+/*
+ * New versions of bpftool now emit additional link placeholders for BPF maps,
+ * and set up BPF skeleton in such a way that libbpf will auto-attach BPF maps
+ * automatically, assumming libbpf is recent enough (v1.5+). Old libbpf will do
+ * nothing with those links and won't attempt to auto-attach maps.
+ *
+ * To maintain compatibility with older libbpf while avoiding trying to attach
+ * twice, disable the autoattach feature on newer libbpf.
+ */
+/* BACKPORT - bpf_mpa__set_autoattach() not available yet, commented out */
+/*#if LIBBPF_MAJOR_VERSION > 1 ||					\
+	(LIBBPF_MAJOR_VERSION == 1 && LIBBPF_MINOR_VERSION >= 5)
+#define __SCX_OPS_DISABLE_AUTOATTACH(__skel, __ops_name)			\
+	bpf_map__set_autoattach((__skel)->maps.__ops_name, false)
+#else*/
+#define __SCX_OPS_DISABLE_AUTOATTACH(__skel, __ops_name) do {} while (0)
+/*#endif*/
+
+#define SCX_OPS_ATTACH(__skel, __ops_name, __scx_name) ({			\
+	struct bpf_link *__link;						\
+	__SCX_OPS_DISABLE_AUTOATTACH(__skel, __ops_name);			\
+	SCX_BUG_ON(__scx_name##__attach((__skel)), "Failed to attach skel");	\
+	__link = bpf_map__attach_struct_ops((__skel)->maps.__ops_name);		\
+	SCX_BUG_ON(!__link, "Failed to attach struct_ops");			\
+	__link;									\
+})
+
+#endif	/* __SCX_COMPAT_H */
diff --git a/tools/sched_ext/include/scx/user_exit_info.h b/tools/sched_ext/include/scx/user_exit_info.h
new file mode 100644
index 000000000000..891693ee604e
--- /dev/null
+++ b/tools/sched_ext/include/scx/user_exit_info.h
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Define struct user_exit_info which is shared between BPF and userspace parts
+ * to communicate exit status and other information.
+ *
+ * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2022 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2022 David Vernet <dvernet@meta.com>
+ */
+#ifndef __USER_EXIT_INFO_H
+#define __USER_EXIT_INFO_H
+
+enum uei_sizes {
+	UEI_REASON_LEN		= 128,
+	UEI_MSG_LEN		= 1024,
+	UEI_DUMP_DFL_LEN	= 32768,
+};
+
+struct user_exit_info {
+	int		kind;
+	s64		exit_code;
+	char		reason[UEI_REASON_LEN];
+	char		msg[UEI_MSG_LEN];
+};
+
+#ifdef __bpf__
+
+#include "vmlinux.h"
+#include <bpf/bpf_core_read.h>
+
+#define UEI_DEFINE(__name)							\
+	char RESIZABLE_ARRAY(data, __name##_dump);				\
+	const volatile u32 __name##_dump_len;					\
+	struct user_exit_info __name SEC(".data")
+
+#define UEI_RECORD(__uei_name, __ei) ({						\
+	bpf_probe_read_kernel_str(__uei_name.reason,				\
+				  sizeof(__uei_name.reason), (__ei)->reason);	\
+	bpf_probe_read_kernel_str(__uei_name.msg,				\
+				  sizeof(__uei_name.msg), (__ei)->msg);		\
+	bpf_probe_read_kernel_str(__uei_name##_dump,				\
+				  __uei_name##_dump_len, (__ei)->dump);		\
+	if (bpf_core_field_exists((__ei)->exit_code))				\
+		__uei_name.exit_code = (__ei)->exit_code;			\
+	/* use __sync to force memory barrier */				\
+	__sync_val_compare_and_swap(&__uei_name.kind, __uei_name.kind,		\
+				    (__ei)->kind);				\
+})
+
+#else	/* !__bpf__ */
+
+#include <stdio.h>
+#include <stdbool.h>
+
+/* no need to call the following explicitly if SCX_OPS_LOAD() is used */
+#define UEI_SET_SIZE(__skel, __ops_name, __uei_name) ({					\
+	u32 __len = (__skel)->struct_ops.__ops_name->exit_dump_len ?: UEI_DUMP_DFL_LEN;	\
+	(__skel)->rodata->__uei_name##_dump_len = __len;				\
+	RESIZE_ARRAY((__skel), data, __uei_name##_dump, __len);				\
+})
+
+#define UEI_EXITED(__skel, __uei_name) ({					\
+	/* use __sync to force memory barrier */				\
+	__sync_val_compare_and_swap(&(__skel)->data->__uei_name.kind, -1, -1);	\
+})
+
+#define UEI_REPORT(__skel, __uei_name) ({					\
+	struct user_exit_info *__uei = &(__skel)->data->__uei_name;		\
+	char *__uei_dump = (__skel)->data_##__uei_name##_dump->__uei_name##_dump; \
+	if (__uei_dump[0] != '\0') {						\
+		fputs("\nDEBUG DUMP\n", stderr);				\
+		fputs("================================================================================\n\n", stderr); \
+		fputs(__uei_dump, stderr);					\
+		fputs("\n================================================================================\n\n", stderr); \
+	}									\
+	fprintf(stderr, "EXIT: %s", __uei->reason);				\
+	if (__uei->msg[0] != '\0')						\
+		fprintf(stderr, " (%s)", __uei->msg);				\
+	fputs("\n", stderr);							\
+	__uei->exit_code;							\
+})
+
+/*
+ * We can't import vmlinux.h while compiling user C code. Let's duplicate
+ * scx_exit_code definition.
+ */
+enum scx_exit_code {
+	/* Reasons */
+	SCX_ECODE_RSN_HOTPLUG		= 1LLU << 32,
+
+	/* Actions */
+	SCX_ECODE_ACT_RESTART		= 1LLU << 48,
+};
+
+enum uei_ecode_mask {
+	UEI_ECODE_USER_MASK		= ((1LLU << 32) - 1),
+	UEI_ECODE_SYS_RSN_MASK		= ((1LLU << 16) - 1) << 32,
+	UEI_ECODE_SYS_ACT_MASK		= ((1LLU << 16) - 1) << 48,
+};
+
+/*
+ * These macro interpret the ecode returned from UEI_REPORT().
+ */
+#define UEI_ECODE_USER(__ecode)		((__ecode) & UEI_ECODE_USER_MASK)
+#define UEI_ECODE_SYS_RSN(__ecode)	((__ecode) & UEI_ECODE_SYS_RSN_MASK)
+#define UEI_ECODE_SYS_ACT(__ecode)	((__ecode) & UEI_ECODE_SYS_ACT_MASK)
+
+#define UEI_ECODE_RESTART(__ecode)	(UEI_ECODE_SYS_ACT((__ecode)) == SCX_ECODE_ACT_RESTART)
+
+#endif	/* __bpf__ */
+#endif	/* __USER_EXIT_INFO_H */
diff --git a/tools/sched_ext/scx_central.bpf.c b/tools/sched_ext/scx_central.bpf.c
new file mode 100644
index 000000000000..1d8fd570eaa7
--- /dev/null
+++ b/tools/sched_ext/scx_central.bpf.c
@@ -0,0 +1,361 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A central FIFO sched_ext scheduler which demonstrates the followings:
+ *
+ * a. Making all scheduling decisions from one CPU:
+ *
+ *    The central CPU is the only one making scheduling decisions. All other
+ *    CPUs kick the central CPU when they run out of tasks to run.
+ *
+ *    There is one global BPF queue and the central CPU schedules all CPUs by
+ *    dispatching from the global queue to each CPU's local dsq from dispatch().
+ *    This isn't the most straightforward. e.g. It'd be easier to bounce
+ *    through per-CPU BPF queues. The current design is chosen to maximally
+ *    utilize and verify various SCX mechanisms such as LOCAL_ON dispatching.
+ *
+ * b. Tickless operation
+ *
+ *    All tasks are dispatched with the infinite slice which allows stopping the
+ *    ticks on CONFIG_NO_HZ_FULL kernels running with the proper nohz_full
+ *    parameter. The tickless operation can be observed through
+ *    /proc/interrupts.
+ *
+ *    Periodic switching is enforced by a periodic timer checking all CPUs and
+ *    preempting them as necessary. Unfortunately, BPF timer currently doesn't
+ *    have a way to pin to a specific CPU, so the periodic timer isn't pinned to
+ *    the central CPU.
+ *
+ * c. Preemption
+ *
+ *    Kthreads are unconditionally queued to the head of a matching local dsq
+ *    and dispatched with SCX_DSQ_PREEMPT. This ensures that a kthread is always
+ *    prioritized over user threads, which is required for ensuring forward
+ *    progress as e.g. the periodic timer may run on a ksoftirqd and if the
+ *    ksoftirqd gets starved by a user thread, there may not be anything else to
+ *    vacate that user thread.
+ *
+ *    SCX_KICK_PREEMPT is used to trigger scheduling and CPUs to move to the
+ *    next tasks.
+ *
+ * This scheduler is designed to maximize usage of various SCX mechanisms. A
+ * more practical implementation would likely put the scheduling loop outside
+ * the central CPU's dispatch() path and add some form of priority mechanism.
+ *
+ * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2022 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2022 David Vernet <dvernet@meta.com>
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+enum {
+	FALLBACK_DSQ_ID		= 0,
+	MS_TO_NS		= 1000LLU * 1000,
+	TIMER_INTERVAL_NS	= 1 * MS_TO_NS,
+};
+
+const volatile s32 central_cpu;
+const volatile u32 nr_cpu_ids = 1;	/* !0 for veristat, set during init */
+const volatile u64 slice_ns = SCX_SLICE_DFL;
+
+bool timer_pinned = true;
+u64 nr_total, nr_locals, nr_queued, nr_lost_pids;
+u64 nr_timers, nr_dispatches, nr_mismatches, nr_retries;
+u64 nr_overflows;
+
+UEI_DEFINE(uei);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_QUEUE);
+	__uint(max_entries, 4096);
+	__type(value, s32);
+} central_q SEC(".maps");
+
+/* can't use percpu map due to bad lookups */
+bool RESIZABLE_ARRAY(data, cpu_gimme_task);
+u64 RESIZABLE_ARRAY(data, cpu_started_at);
+
+struct central_timer {
+	struct bpf_timer timer;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, u32);
+	__type(value, struct central_timer);
+} central_timer SEC(".maps");
+
+static bool vtime_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}
+
+s32 BPF_STRUCT_OPS(central_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	/*
+	 * Steer wakeups to the central CPU as much as possible to avoid
+	 * disturbing other CPUs. It's safe to blindly return the central cpu as
+	 * select_cpu() is a hint and if @p can't be on it, the kernel will
+	 * automatically pick a fallback CPU.
+	 */
+	return central_cpu;
+}
+
+void BPF_STRUCT_OPS(central_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	s32 pid = p->pid;
+
+	__sync_fetch_and_add(&nr_total, 1);
+
+	/*
+	 * Push per-cpu kthreads at the head of local dsq's and preempt the
+	 * corresponding CPU. This ensures that e.g. ksoftirqd isn't blocked
+	 * behind other threads which is necessary for forward progress
+	 * guarantee as we depend on the BPF timer which may run from ksoftirqd.
+	 */
+	if ((p->flags & PF_KTHREAD) && p->nr_cpus_allowed == 1) {
+		__sync_fetch_and_add(&nr_locals, 1);
+		scx_bpf_dispatch(p, SCX_DSQ_LOCAL, SCX_SLICE_INF,
+				 enq_flags | SCX_ENQ_PREEMPT);
+		return;
+	}
+
+	if (bpf_map_push_elem(&central_q, &pid, 0)) {
+		__sync_fetch_and_add(&nr_overflows, 1);
+		scx_bpf_dispatch(p, FALLBACK_DSQ_ID, SCX_SLICE_INF, enq_flags);
+		return;
+	}
+
+	__sync_fetch_and_add(&nr_queued, 1);
+
+	if (!scx_bpf_task_running(p))
+		scx_bpf_kick_cpu(central_cpu, SCX_KICK_PREEMPT);
+}
+
+static bool dispatch_to_cpu(s32 cpu)
+{
+	struct task_struct *p;
+	s32 pid;
+
+	bpf_repeat(BPF_MAX_LOOPS) {
+		if (bpf_map_pop_elem(&central_q, &pid))
+			break;
+
+		__sync_fetch_and_sub(&nr_queued, 1);
+
+		p = bpf_task_from_pid(pid);
+		if (!p) {
+			__sync_fetch_and_add(&nr_lost_pids, 1);
+			continue;
+		}
+
+		/*
+		 * If we can't run the task at the top, do the dumb thing and
+		 * bounce it to the fallback dsq.
+		 */
+		if (!bpf_cpumask_test_cpu(cpu, p->cpus_ptr)) {
+			__sync_fetch_and_add(&nr_mismatches, 1);
+			scx_bpf_dispatch(p, FALLBACK_DSQ_ID, SCX_SLICE_INF, 0);
+			bpf_task_release(p);
+			/*
+			 * We might run out of dispatch buffer slots if we continue dispatching
+			 * to the fallback DSQ, without dispatching to the local DSQ of the
+			 * target CPU. In such a case, break the loop now as will fail the
+			 * next dispatch operation.
+			 */
+			if (!scx_bpf_dispatch_nr_slots())
+				break;
+			continue;
+		}
+
+		/* dispatch to local and mark that @cpu doesn't need more */
+		scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | cpu, SCX_SLICE_INF, 0);
+
+		if (cpu != central_cpu)
+			scx_bpf_kick_cpu(cpu, SCX_KICK_IDLE);
+
+		bpf_task_release(p);
+		return true;
+	}
+
+	return false;
+}
+
+void BPF_STRUCT_OPS(central_dispatch, s32 cpu, struct task_struct *prev)
+{
+	if (cpu == central_cpu) {
+		/* dispatch for all other CPUs first */
+		__sync_fetch_and_add(&nr_dispatches, 1);
+
+		bpf_for(cpu, 0, nr_cpu_ids) {
+			bool *gimme;
+
+			if (!scx_bpf_dispatch_nr_slots())
+				break;
+
+			/* central's gimme is never set */
+			gimme = ARRAY_ELEM_PTR(cpu_gimme_task, cpu, nr_cpu_ids);
+			if (gimme && !*gimme)
+				continue;
+
+			if (dispatch_to_cpu(cpu))
+				*gimme = false;
+		}
+
+		/*
+		 * Retry if we ran out of dispatch buffer slots as we might have
+		 * skipped some CPUs and also need to dispatch for self. The ext
+		 * core automatically retries if the local dsq is empty but we
+		 * can't rely on that as we're dispatching for other CPUs too.
+		 * Kick self explicitly to retry.
+		 */
+		if (!scx_bpf_dispatch_nr_slots()) {
+			__sync_fetch_and_add(&nr_retries, 1);
+			scx_bpf_kick_cpu(central_cpu, SCX_KICK_PREEMPT);
+			return;
+		}
+
+		/* look for a task to run on the central CPU */
+		if (scx_bpf_consume(FALLBACK_DSQ_ID))
+			return;
+		dispatch_to_cpu(central_cpu);
+	} else {
+		bool *gimme;
+
+		if (scx_bpf_consume(FALLBACK_DSQ_ID))
+			return;
+
+		gimme = ARRAY_ELEM_PTR(cpu_gimme_task, cpu, nr_cpu_ids);
+		if (gimme)
+			*gimme = true;
+
+		/*
+		 * Force dispatch on the scheduling CPU so that it finds a task
+		 * to run for us.
+		 */
+		scx_bpf_kick_cpu(central_cpu, SCX_KICK_PREEMPT);
+	}
+}
+
+void BPF_STRUCT_OPS(central_running, struct task_struct *p)
+{
+	s32 cpu = scx_bpf_task_cpu(p);
+	u64 *started_at = ARRAY_ELEM_PTR(cpu_started_at, cpu, nr_cpu_ids);
+	if (started_at)
+		*started_at = bpf_ktime_get_ns() ?: 1;	/* 0 indicates idle */
+}
+
+void BPF_STRUCT_OPS(central_stopping, struct task_struct *p, bool runnable)
+{
+	s32 cpu = scx_bpf_task_cpu(p);
+	u64 *started_at = ARRAY_ELEM_PTR(cpu_started_at, cpu, nr_cpu_ids);
+	if (started_at)
+		*started_at = 0;
+}
+
+static int central_timerfn(void *map, int *key, struct bpf_timer *timer)
+{
+	u64 now = bpf_ktime_get_ns();
+	u64 nr_to_kick = nr_queued;
+	s32 i, curr_cpu;
+
+	curr_cpu = bpf_get_smp_processor_id();
+	if (timer_pinned && (curr_cpu != central_cpu)) {
+		scx_bpf_error("Central timer ran on CPU %d, not central CPU %d",
+			      curr_cpu, central_cpu);
+		return 0;
+	}
+
+	bpf_for(i, 0, nr_cpu_ids) {
+		s32 cpu = (nr_timers + i) % nr_cpu_ids;
+		u64 *started_at;
+
+		if (cpu == central_cpu)
+			continue;
+
+		/* kick iff the current one exhausted its slice */
+		started_at = ARRAY_ELEM_PTR(cpu_started_at, cpu, nr_cpu_ids);
+		if (started_at && *started_at &&
+		    vtime_before(now, *started_at + slice_ns))
+			continue;
+
+		/* and there's something pending */
+		if (scx_bpf_dsq_nr_queued(FALLBACK_DSQ_ID) ||
+		    scx_bpf_dsq_nr_queued(SCX_DSQ_LOCAL_ON | cpu))
+			;
+		else if (nr_to_kick)
+			nr_to_kick--;
+		else
+			continue;
+
+		scx_bpf_kick_cpu(cpu, SCX_KICK_PREEMPT);
+	}
+
+	bpf_timer_start(timer, TIMER_INTERVAL_NS, BPF_F_TIMER_CPU_PIN);
+	__sync_fetch_and_add(&nr_timers, 1);
+	return 0;
+}
+
+int BPF_STRUCT_OPS_SLEEPABLE(central_init)
+{
+	u32 key = 0;
+	struct bpf_timer *timer;
+	int ret;
+
+	ret = scx_bpf_create_dsq(FALLBACK_DSQ_ID, -1);
+	if (ret)
+		return ret;
+
+	timer = bpf_map_lookup_elem(&central_timer, &key);
+	if (!timer)
+		return -ESRCH;
+
+	if (bpf_get_smp_processor_id() != central_cpu) {
+		scx_bpf_error("init from non-central CPU");
+		return -EINVAL;
+	}
+
+	bpf_timer_init(timer, &central_timer, CLOCK_MONOTONIC);
+	bpf_timer_set_callback(timer, central_timerfn);
+
+	ret = bpf_timer_start(timer, TIMER_INTERVAL_NS, BPF_F_TIMER_CPU_PIN);
+	/*
+	 * BPF_F_TIMER_CPU_PIN is pretty new (>=6.7). If we're running in a
+	 * kernel which doesn't have it, bpf_timer_start() will return -EINVAL.
+	 * Retry without the PIN. This would be the perfect use case for
+	 * bpf_core_enum_value_exists() but the enum type doesn't have a name
+	 * and can't be used with bpf_core_enum_value_exists(). Oh well...
+	 */
+	if (ret == -EINVAL) {
+		timer_pinned = false;
+		ret = bpf_timer_start(timer, TIMER_INTERVAL_NS, 0);
+	}
+	if (ret)
+		scx_bpf_error("bpf_timer_start failed (%d)", ret);
+	return ret;
+}
+
+void BPF_STRUCT_OPS(central_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SCX_OPS_DEFINE(central_ops,
+	       /*
+		* We are offloading all scheduling decisions to the central CPU
+		* and thus being the last task on a given CPU doesn't mean
+		* anything special. Enqueue the last tasks like any other tasks.
+		*/
+	       .flags			= SCX_OPS_ENQ_LAST,
+
+	       .select_cpu		= (void *)central_select_cpu,
+	       .enqueue			= (void *)central_enqueue,
+	       .dispatch		= (void *)central_dispatch,
+	       .running			= (void *)central_running,
+	       .stopping		= (void *)central_stopping,
+	       .init			= (void *)central_init,
+	       .exit			= (void *)central_exit,
+	       .name			= "central");
diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c
new file mode 100644
index 000000000000..21deea320bd7
--- /dev/null
+++ b/tools/sched_ext/scx_central.c
@@ -0,0 +1,135 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * 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 _GNU_SOURCE
+#include <sched.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <signal.h>
+#include <libgen.h>
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include "scx_central.bpf.skel.h"
+
+const char help_fmt[] =
+"A central FIFO sched_ext scheduler.\n"
+"\n"
+"See the top-level comment in .bpf.c for more details.\n"
+"\n"
+"Usage: %s [-s SLICE_US] [-c CPU]\n"
+"\n"
+"  -s SLICE_US   Override slice duration\n"
+"  -c CPU        Override the central CPU (default: 0)\n"
+"  -v            Print libbpf debug messages\n"
+"  -h            Display this help and exit\n";
+
+static bool verbose;
+static volatile int exit_req;
+
+static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args)
+{
+	if (level == LIBBPF_DEBUG && !verbose)
+		return 0;
+	return vfprintf(stderr, format, args);
+}
+
+static void sigint_handler(int dummy)
+{
+	exit_req = 1;
+}
+
+int main(int argc, char **argv)
+{
+	struct scx_central *skel;
+	struct bpf_link *link;
+	__u64 seq = 0, ecode;
+	__s32 opt;
+	cpu_set_t *cpuset;
+
+	libbpf_set_print(libbpf_print_fn);
+	signal(SIGINT, sigint_handler);
+	signal(SIGTERM, sigint_handler);
+restart:
+	skel = SCX_OPS_OPEN(central_ops, scx_central);
+
+	skel->rodata->central_cpu = 0;
+	skel->rodata->nr_cpu_ids = libbpf_num_possible_cpus();
+
+	while ((opt = getopt(argc, argv, "s:c:pvh")) != -1) {
+		switch (opt) {
+		case 's':
+			skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
+			break;
+		case 'c':
+			skel->rodata->central_cpu = strtoul(optarg, NULL, 0);
+			break;
+		case 'v':
+			verbose = true;
+			break;
+		default:
+			fprintf(stderr, help_fmt, basename(argv[0]));
+			return opt != 'h';
+		}
+	}
+
+	/* Resize arrays so their element count is equal to cpu count. */
+	RESIZE_ARRAY(skel, data, cpu_gimme_task, skel->rodata->nr_cpu_ids);
+	RESIZE_ARRAY(skel, data, cpu_started_at, skel->rodata->nr_cpu_ids);
+
+	SCX_OPS_LOAD(skel, central_ops, scx_central, uei);
+
+	/*
+	 * Affinitize the loading thread to the central CPU, as:
+	 * - That's where the BPF timer is first invoked in the BPF program.
+	 * - We probably don't want this user space component to take up a core
+	 *   from a task that would benefit from avoiding preemption on one of
+	 *   the tickless cores.
+	 *
+	 * Until BPF supports pinning the timer, it's not guaranteed that it
+	 * will always be invoked on the central CPU. In practice, this
+	 * suffices the majority of the time.
+	 */
+	cpuset = CPU_ALLOC(skel->rodata->nr_cpu_ids);
+	SCX_BUG_ON(!cpuset, "Failed to allocate cpuset");
+	CPU_ZERO(cpuset);
+	CPU_SET(skel->rodata->central_cpu, cpuset);
+	SCX_BUG_ON(sched_setaffinity(0, sizeof(cpuset), cpuset),
+		   "Failed to affinitize to central CPU %d (max %d)",
+		   skel->rodata->central_cpu, skel->rodata->nr_cpu_ids - 1);
+	CPU_FREE(cpuset);
+
+	link = SCX_OPS_ATTACH(skel, central_ops, scx_central);
+
+	if (!skel->data->timer_pinned)
+		printf("WARNING : BPF_F_TIMER_CPU_PIN not available, timer not pinned to central\n");
+
+	while (!exit_req && !UEI_EXITED(skel, uei)) {
+		printf("[SEQ %llu]\n", seq++);
+		printf("total   :%10" PRIu64 "    local:%10" PRIu64 "   queued:%10" PRIu64 "  lost:%10" PRIu64 "\n",
+		       skel->bss->nr_total,
+		       skel->bss->nr_locals,
+		       skel->bss->nr_queued,
+		       skel->bss->nr_lost_pids);
+		printf("timer   :%10" PRIu64 " dispatch:%10" PRIu64 " mismatch:%10" PRIu64 " retry:%10" PRIu64 "\n",
+		       skel->bss->nr_timers,
+		       skel->bss->nr_dispatches,
+		       skel->bss->nr_mismatches,
+		       skel->bss->nr_retries);
+		printf("overflow:%10" PRIu64 "\n",
+		       skel->bss->nr_overflows);
+		fflush(stdout);
+		sleep(1);
+	}
+
+	bpf_link__destroy(link);
+	ecode = UEI_REPORT(skel, uei);
+	scx_central__destroy(skel);
+
+	if (UEI_ECODE_RESTART(ecode))
+		goto restart;
+	return 0;
+}
diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
new file mode 100644
index 000000000000..892278f12dce
--- /dev/null
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -0,0 +1,706 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A simple five-level FIFO queue scheduler.
+ *
+ * There are five FIFOs implemented using BPF_MAP_TYPE_QUEUE. A task gets
+ * assigned to one depending on its compound weight. Each CPU round robins
+ * through the FIFOs and dispatches more from FIFOs with higher indices - 1 from
+ * queue0, 2 from queue1, 4 from queue2 and so on.
+ *
+ * This scheduler demonstrates:
+ *
+ * - BPF-side queueing using PIDs.
+ * - Sleepable per-task storage allocation using ops.prep_enable().
+ * - Using ops.cpu_release() to handle a higher priority scheduling class taking
+ *   the CPU away.
+ * - Core-sched support.
+ *
+ * This scheduler is primarily for demonstration and testing of sched_ext
+ * features and unlikely to be useful for actual workloads.
+ *
+ * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2022 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2022 David Vernet <dvernet@meta.com>
+ */
+#include <scx/common.bpf.h>
+
+enum consts {
+	ONE_SEC_IN_NS		= 1000000000,
+	SHARED_DSQ		= 0,
+};
+
+char _license[] SEC("license") = "GPL";
+
+const volatile u64 slice_ns = SCX_SLICE_DFL;
+const volatile u32 stall_user_nth;
+const volatile u32 stall_kernel_nth;
+const volatile u32 dsp_inf_loop_after;
+const volatile u32 dsp_batch;
+const volatile bool print_shared_dsq;
+const volatile s32 disallow_tgid;
+const volatile bool suppress_dump;
+
+u32 test_error_cnt;
+
+UEI_DEFINE(uei);
+
+struct qmap {
+	__uint(type, BPF_MAP_TYPE_QUEUE);
+	__uint(max_entries, 4096);
+	__type(value, u32);
+} queue0 SEC(".maps"),
+  queue1 SEC(".maps"),
+  queue2 SEC(".maps"),
+  queue3 SEC(".maps"),
+  queue4 SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, 5);
+	__type(key, int);
+	__array(values, struct qmap);
+} queue_arr SEC(".maps") = {
+	.values = {
+		[0] = &queue0,
+		[1] = &queue1,
+		[2] = &queue2,
+		[3] = &queue3,
+		[4] = &queue4,
+	},
+};
+
+/*
+ * If enabled, CPU performance target is set according to the queue index
+ * according to the following table.
+ */
+static const u32 qidx_to_cpuperf_target[] = {
+	[0] = SCX_CPUPERF_ONE * 0 / 4,
+	[1] = SCX_CPUPERF_ONE * 1 / 4,
+	[2] = SCX_CPUPERF_ONE * 2 / 4,
+	[3] = SCX_CPUPERF_ONE * 3 / 4,
+	[4] = SCX_CPUPERF_ONE * 4 / 4,
+};
+
+/*
+ * Per-queue sequence numbers to implement core-sched ordering.
+ *
+ * Tail seq is assigned to each queued task and incremented. Head seq tracks the
+ * sequence number of the latest dispatched task. The distance between the a
+ * task's seq and the associated queue's head seq is called the queue distance
+ * and used when comparing two tasks for ordering. See qmap_core_sched_before().
+ */
+static u64 core_sched_head_seqs[5];
+static u64 core_sched_tail_seqs[5];
+
+/* Per-task scheduling context */
+struct task_ctx {
+	bool	force_local;	/* Dispatch directly to local_dsq */
+	u64	core_sched_seq;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct task_ctx);
+} task_ctx_stor SEC(".maps");
+
+struct cpu_ctx {
+	u64	dsp_idx;	/* dispatch index */
+	u64	dsp_cnt;	/* remaining count */
+	u32	avg_weight;
+	u32	cpuperf_target;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, u32);
+	__type(value, struct cpu_ctx);
+} cpu_ctx_stor SEC(".maps");
+
+/* Statistics */
+u64 nr_enqueued, nr_dispatched, nr_reenqueued, nr_dequeued, nr_ddsp_from_enq;
+u64 nr_core_sched_execed;
+u32 cpuperf_min, cpuperf_avg, cpuperf_max;
+u32 cpuperf_target_min, cpuperf_target_avg, cpuperf_target_max;
+
+static s32 pick_direct_dispatch_cpu(struct task_struct *p, s32 prev_cpu)
+{
+	s32 cpu;
+
+	if (p->nr_cpus_allowed == 1 ||
+	    scx_bpf_test_and_clear_cpu_idle(prev_cpu))
+		return prev_cpu;
+
+	cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
+	if (cpu >= 0)
+		return cpu;
+
+	return -1;
+}
+
+s32 BPF_STRUCT_OPS(qmap_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	struct task_ctx *tctx;
+	s32 cpu;
+
+	tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0);
+	if (!tctx) {
+		scx_bpf_error("task_ctx lookup failed");
+		return -ESRCH;
+	}
+
+	cpu = pick_direct_dispatch_cpu(p, prev_cpu);
+
+	if (cpu >= 0) {
+		tctx->force_local = true;
+		return cpu;
+	} else {
+		return prev_cpu;
+	}
+}
+
+static int weight_to_idx(u32 weight)
+{
+	/* Coarsely map the compound weight to a FIFO. */
+	if (weight <= 25)
+		return 0;
+	else if (weight <= 50)
+		return 1;
+	else if (weight < 200)
+		return 2;
+	else if (weight < 400)
+		return 3;
+	else
+		return 4;
+}
+
+void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	static u32 user_cnt, kernel_cnt;
+	struct task_ctx *tctx;
+	u32 pid = p->pid;
+	int idx = weight_to_idx(p->scx.weight);
+	void *ring;
+	s32 cpu;
+
+	if (p->flags & PF_KTHREAD) {
+		if (stall_kernel_nth && !(++kernel_cnt % stall_kernel_nth))
+			return;
+	} else {
+		if (stall_user_nth && !(++user_cnt % stall_user_nth))
+			return;
+	}
+
+	if (test_error_cnt && !--test_error_cnt)
+		scx_bpf_error("test triggering error");
+
+	tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0);
+	if (!tctx) {
+		scx_bpf_error("task_ctx lookup failed");
+		return;
+	}
+
+	/*
+	 * All enqueued tasks must have their core_sched_seq updated for correct
+	 * core-sched ordering, which is why %SCX_OPS_ENQ_LAST is specified in
+	 * qmap_ops.flags.
+	 */
+	tctx->core_sched_seq = core_sched_tail_seqs[idx]++;
+
+	/*
+	 * If qmap_select_cpu() is telling us to or this is the last runnable
+	 * task on the CPU, enqueue locally.
+	 */
+	if (tctx->force_local || (enq_flags & SCX_ENQ_LAST)) {
+		tctx->force_local = false;
+		scx_bpf_dispatch(p, SCX_DSQ_LOCAL, slice_ns, enq_flags);
+		return;
+	}
+
+	/* if !WAKEUP, select_cpu() wasn't called, try direct dispatch */
+	if (!(enq_flags & SCX_ENQ_WAKEUP) &&
+	    (cpu = pick_direct_dispatch_cpu(p, scx_bpf_task_cpu(p))) >= 0) {
+		__sync_fetch_and_add(&nr_ddsp_from_enq, 1);
+		scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | cpu, slice_ns, enq_flags);
+		return;
+	}
+
+	/*
+	 * If the task was re-enqueued due to the CPU being preempted by a
+	 * higher priority scheduling class, just re-enqueue the task directly
+	 * on the global DSQ. As we want another CPU to pick it up, find and
+	 * kick an idle CPU.
+	 */
+	if (enq_flags & SCX_ENQ_REENQ) {
+		s32 cpu;
+
+		scx_bpf_dispatch(p, SHARED_DSQ, 0, enq_flags);
+		cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
+		if (cpu >= 0)
+			scx_bpf_kick_cpu(cpu, SCX_KICK_IDLE);
+		return;
+	}
+
+	ring = bpf_map_lookup_elem(&queue_arr, &idx);
+	if (!ring) {
+		scx_bpf_error("failed to find ring %d", idx);
+		return;
+	}
+
+	/* Queue on the selected FIFO. If the FIFO overflows, punt to global. */
+	if (bpf_map_push_elem(ring, &pid, 0)) {
+		scx_bpf_dispatch(p, SHARED_DSQ, slice_ns, enq_flags);
+		return;
+	}
+
+	__sync_fetch_and_add(&nr_enqueued, 1);
+}
+
+/*
+ * The BPF queue map doesn't support removal and sched_ext can handle spurious
+ * dispatches. qmap_dequeue() is only used to collect statistics.
+ */
+void BPF_STRUCT_OPS(qmap_dequeue, struct task_struct *p, u64 deq_flags)
+{
+	__sync_fetch_and_add(&nr_dequeued, 1);
+	if (deq_flags & SCX_DEQ_CORE_SCHED_EXEC)
+		__sync_fetch_and_add(&nr_core_sched_execed, 1);
+}
+
+static void update_core_sched_head_seq(struct task_struct *p)
+{
+	struct task_ctx *tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0);
+	int idx = weight_to_idx(p->scx.weight);
+
+	if (tctx)
+		core_sched_head_seqs[idx] = tctx->core_sched_seq;
+	else
+		scx_bpf_error("task_ctx lookup failed");
+}
+
+void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev)
+{
+	struct task_struct *p;
+	struct cpu_ctx *cpuc;
+	u32 zero = 0, batch = dsp_batch ?: 1;
+	void *fifo;
+	s32 i, pid;
+
+	if (scx_bpf_consume(SHARED_DSQ))
+		return;
+
+	if (dsp_inf_loop_after && nr_dispatched > dsp_inf_loop_after) {
+		/*
+		 * PID 2 should be kthreadd which should mostly be idle and off
+		 * the scheduler. Let's keep dispatching it to force the kernel
+		 * to call this function over and over again.
+		 */
+		p = bpf_task_from_pid(2);
+		if (p) {
+			scx_bpf_dispatch(p, SCX_DSQ_LOCAL, slice_ns, 0);
+			bpf_task_release(p);
+			return;
+		}
+	}
+
+	if (!(cpuc = bpf_map_lookup_elem(&cpu_ctx_stor, &zero))) {
+		scx_bpf_error("failed to look up cpu_ctx");
+		return;
+	}
+
+	for (i = 0; i < 5; i++) {
+		/* Advance the dispatch cursor and pick the fifo. */
+		if (!cpuc->dsp_cnt) {
+			cpuc->dsp_idx = (cpuc->dsp_idx + 1) % 5;
+			cpuc->dsp_cnt = 1 << cpuc->dsp_idx;
+		}
+
+		fifo = bpf_map_lookup_elem(&queue_arr, &cpuc->dsp_idx);
+		if (!fifo) {
+			scx_bpf_error("failed to find ring %llu", cpuc->dsp_idx);
+			return;
+		}
+
+		/* Dispatch or advance. */
+		bpf_repeat(BPF_MAX_LOOPS) {
+			if (bpf_map_pop_elem(fifo, &pid))
+				break;
+
+			p = bpf_task_from_pid(pid);
+			if (!p)
+				continue;
+
+			update_core_sched_head_seq(p);
+			__sync_fetch_and_add(&nr_dispatched, 1);
+			scx_bpf_dispatch(p, SHARED_DSQ, slice_ns, 0);
+			bpf_task_release(p);
+			batch--;
+			cpuc->dsp_cnt--;
+			if (!batch || !scx_bpf_dispatch_nr_slots()) {
+				scx_bpf_consume(SHARED_DSQ);
+				return;
+			}
+			if (!cpuc->dsp_cnt)
+				break;
+		}
+
+		cpuc->dsp_cnt = 0;
+	}
+}
+
+void BPF_STRUCT_OPS(qmap_tick, struct task_struct *p)
+{
+	struct cpu_ctx *cpuc;
+	u32 zero = 0;
+	int idx;
+
+	if (!(cpuc = bpf_map_lookup_elem(&cpu_ctx_stor, &zero))) {
+		scx_bpf_error("failed to look up cpu_ctx");
+		return;
+	}
+
+	/*
+	 * Use the running avg of weights to select the target cpuperf level.
+	 * This is a demonstration of the cpuperf feature rather than a
+	 * practical strategy to regulate CPU frequency.
+	 */
+	cpuc->avg_weight = cpuc->avg_weight * 3 / 4 + p->scx.weight / 4;
+	idx = weight_to_idx(cpuc->avg_weight);
+	cpuc->cpuperf_target = qidx_to_cpuperf_target[idx];
+
+	scx_bpf_cpuperf_set(scx_bpf_task_cpu(p), cpuc->cpuperf_target);
+}
+
+/*
+ * The distance from the head of the queue scaled by the weight of the queue.
+ * The lower the number, the older the task and the higher the priority.
+ */
+static s64 task_qdist(struct task_struct *p)
+{
+	int idx = weight_to_idx(p->scx.weight);
+	struct task_ctx *tctx;
+	s64 qdist;
+
+	tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0);
+	if (!tctx) {
+		scx_bpf_error("task_ctx lookup failed");
+		return 0;
+	}
+
+	qdist = tctx->core_sched_seq - core_sched_head_seqs[idx];
+
+	/*
+	 * As queue index increments, the priority doubles. The queue w/ index 3
+	 * is dispatched twice more frequently than 2. Reflect the difference by
+	 * scaling qdists accordingly. Note that the shift amount needs to be
+	 * flipped depending on the sign to avoid flipping priority direction.
+	 */
+	if (qdist >= 0)
+		return qdist << (4 - idx);
+	else
+		return qdist << idx;
+}
+
+/*
+ * This is called to determine the task ordering when core-sched is picking
+ * tasks to execute on SMT siblings and should encode about the same ordering as
+ * the regular scheduling path. Use the priority-scaled distances from the head
+ * of the queues to compare the two tasks which should be consistent with the
+ * dispatch path behavior.
+ */
+bool BPF_STRUCT_OPS(qmap_core_sched_before,
+		    struct task_struct *a, struct task_struct *b)
+{
+	return task_qdist(a) > task_qdist(b);
+}
+
+void BPF_STRUCT_OPS(qmap_cpu_release, s32 cpu, struct scx_cpu_release_args *args)
+{
+	u32 cnt;
+
+	/*
+	 * Called when @cpu is taken by a higher priority scheduling class. This
+	 * makes @cpu no longer available for executing sched_ext tasks. As we
+	 * don't want the tasks in @cpu's local dsq to sit there until @cpu
+	 * becomes available again, re-enqueue them into the global dsq. See
+	 * %SCX_ENQ_REENQ handling in qmap_enqueue().
+	 */
+	cnt = scx_bpf_reenqueue_local();
+	if (cnt)
+		__sync_fetch_and_add(&nr_reenqueued, cnt);
+}
+
+s32 BPF_STRUCT_OPS(qmap_init_task, struct task_struct *p,
+		   struct scx_init_task_args *args)
+{
+	if (p->tgid == disallow_tgid)
+		p->scx.disallow = true;
+
+	/*
+	 * @p is new. Let's ensure that its task_ctx is available. We can sleep
+	 * in this function and the following will automatically use GFP_KERNEL.
+	 */
+	if (bpf_task_storage_get(&task_ctx_stor, p, 0,
+				 BPF_LOCAL_STORAGE_GET_F_CREATE))
+		return 0;
+	else
+		return -ENOMEM;
+}
+
+void BPF_STRUCT_OPS(qmap_dump, struct scx_dump_ctx *dctx)
+{
+	s32 i, pid;
+
+	if (suppress_dump)
+		return;
+
+	bpf_for(i, 0, 5) {
+		void *fifo;
+
+		if (!(fifo = bpf_map_lookup_elem(&queue_arr, &i)))
+			return;
+
+		scx_bpf_dump("QMAP FIFO[%d]:", i);
+		bpf_repeat(4096) {
+			if (bpf_map_pop_elem(fifo, &pid))
+				break;
+			scx_bpf_dump(" %d", pid);
+		}
+		scx_bpf_dump("\n");
+	}
+}
+
+void BPF_STRUCT_OPS(qmap_dump_cpu, struct scx_dump_ctx *dctx, s32 cpu, bool idle)
+{
+	u32 zero = 0;
+	struct cpu_ctx *cpuc;
+
+	if (suppress_dump || idle)
+		return;
+	if (!(cpuc = bpf_map_lookup_percpu_elem(&cpu_ctx_stor, &zero, cpu)))
+		return;
+
+	scx_bpf_dump("QMAP: dsp_idx=%llu dsp_cnt=%llu avg_weight=%u cpuperf_target=%u",
+		     cpuc->dsp_idx, cpuc->dsp_cnt, cpuc->avg_weight,
+		     cpuc->cpuperf_target);
+}
+
+void BPF_STRUCT_OPS(qmap_dump_task, struct scx_dump_ctx *dctx, struct task_struct *p)
+{
+	struct task_ctx *taskc;
+
+	if (suppress_dump)
+		return;
+	if (!(taskc = bpf_task_storage_get(&task_ctx_stor, p, 0, 0)))
+		return;
+
+	scx_bpf_dump("QMAP: force_local=%d core_sched_seq=%llu",
+		     taskc->force_local, taskc->core_sched_seq);
+}
+
+/*
+ * Print out the online and possible CPU map using bpf_printk() as a
+ * demonstration of using the cpumask kfuncs and ops.cpu_on/offline().
+ */
+static void print_cpus(void)
+{
+	const struct cpumask *possible, *online;
+	s32 cpu;
+	char buf[128] = "", *p;
+	int idx;
+
+	possible = scx_bpf_get_possible_cpumask();
+	online = scx_bpf_get_online_cpumask();
+
+	idx = 0;
+	bpf_for(cpu, 0, scx_bpf_nr_cpu_ids()) {
+		if (!(p = MEMBER_VPTR(buf, [idx++])))
+			break;
+		if (bpf_cpumask_test_cpu(cpu, online))
+			*p++ = 'O';
+		else if (bpf_cpumask_test_cpu(cpu, possible))
+			*p++ = 'X';
+		else
+			*p++ = ' ';
+
+		if ((cpu & 7) == 7) {
+			if (!(p = MEMBER_VPTR(buf, [idx++])))
+				break;
+			*p++ = '|';
+		}
+	}
+	buf[sizeof(buf) - 1] = '\0';
+
+	scx_bpf_put_cpumask(online);
+	scx_bpf_put_cpumask(possible);
+
+	bpf_printk("CPUS: |%s", buf);
+}
+
+void BPF_STRUCT_OPS(qmap_cpu_online, s32 cpu)
+{
+	bpf_printk("CPU %d coming online", cpu);
+	/* @cpu is already online at this point */
+	print_cpus();
+}
+
+void BPF_STRUCT_OPS(qmap_cpu_offline, s32 cpu)
+{
+	bpf_printk("CPU %d going offline", cpu);
+	/* @cpu is still online at this point */
+	print_cpus();
+}
+
+struct monitor_timer {
+	struct bpf_timer timer;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, u32);
+	__type(value, struct monitor_timer);
+} monitor_timer SEC(".maps");
+
+/*
+ * Print out the min, avg and max performance levels of CPUs every second to
+ * demonstrate the cpuperf interface.
+ */
+static void monitor_cpuperf(void)
+{
+	u32 zero = 0, nr_cpu_ids;
+	u64 cap_sum = 0, cur_sum = 0, cur_min = SCX_CPUPERF_ONE, cur_max = 0;
+	u64 target_sum = 0, target_min = SCX_CPUPERF_ONE, target_max = 0;
+	const struct cpumask *online;
+	int i, nr_online_cpus = 0;
+
+	nr_cpu_ids = scx_bpf_nr_cpu_ids();
+	online = scx_bpf_get_online_cpumask();
+
+	bpf_for(i, 0, nr_cpu_ids) {
+		struct cpu_ctx *cpuc;
+		u32 cap, cur;
+
+		if (!bpf_cpumask_test_cpu(i, online))
+			continue;
+		nr_online_cpus++;
+
+		/* collect the capacity and current cpuperf */
+		cap = scx_bpf_cpuperf_cap(i);
+		cur = scx_bpf_cpuperf_cur(i);
+
+		cur_min = cur < cur_min ? cur : cur_min;
+		cur_max = cur > cur_max ? cur : cur_max;
+
+		/*
+		 * $cur is relative to $cap. Scale it down accordingly so that
+		 * it's in the same scale as other CPUs and $cur_sum/$cap_sum
+		 * makes sense.
+		 */
+		cur_sum += cur * cap / SCX_CPUPERF_ONE;
+		cap_sum += cap;
+
+		if (!(cpuc = bpf_map_lookup_percpu_elem(&cpu_ctx_stor, &zero, i))) {
+			scx_bpf_error("failed to look up cpu_ctx");
+			goto out;
+		}
+
+		/* collect target */
+		cur = cpuc->cpuperf_target;
+		target_sum += cur;
+		target_min = cur < target_min ? cur : target_min;
+		target_max = cur > target_max ? cur : target_max;
+	}
+
+	cpuperf_min = cur_min;
+	cpuperf_avg = cur_sum * SCX_CPUPERF_ONE / cap_sum;
+	cpuperf_max = cur_max;
+
+	cpuperf_target_min = target_min;
+	cpuperf_target_avg = target_sum / nr_online_cpus;
+	cpuperf_target_max = target_max;
+out:
+	scx_bpf_put_cpumask(online);
+}
+
+/*
+ * Dump the currently queued tasks in the shared DSQ to demonstrate the usage of
+ * scx_bpf_dsq_nr_queued() and DSQ iterator. Raise the dispatch batch count to
+ * see meaningful dumps in the trace pipe.
+ */
+static void dump_shared_dsq(void)
+{
+	struct task_struct *p;
+	s32 nr;
+
+	if (!(nr = scx_bpf_dsq_nr_queued(SHARED_DSQ)))
+		return;
+
+	bpf_printk("Dumping %d tasks in SHARED_DSQ in reverse order", nr);
+
+	bpf_rcu_read_lock();
+	bpf_for_each(scx_dsq, p, SHARED_DSQ, SCX_DSQ_ITER_REV)
+		bpf_printk("%s[%d]", p->comm, p->pid);
+	bpf_rcu_read_unlock();
+}
+
+static int monitor_timerfn(void *map, int *key, struct bpf_timer *timer)
+{
+	monitor_cpuperf();
+
+	if (print_shared_dsq)
+		dump_shared_dsq();
+
+	bpf_timer_start(timer, ONE_SEC_IN_NS, 0);
+	return 0;
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(qmap_init)
+{
+	u32 key = 0;
+	struct bpf_timer *timer;
+	s32 ret;
+
+	print_cpus();
+
+	ret = scx_bpf_create_dsq(SHARED_DSQ, -1);
+	if (ret)
+		return ret;
+
+	timer = bpf_map_lookup_elem(&monitor_timer, &key);
+	if (!timer)
+		return -ESRCH;
+
+	bpf_timer_init(timer, &monitor_timer, CLOCK_MONOTONIC);
+	bpf_timer_set_callback(timer, monitor_timerfn);
+
+	return bpf_timer_start(timer, ONE_SEC_IN_NS, 0);
+}
+
+void BPF_STRUCT_OPS(qmap_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SCX_OPS_DEFINE(qmap_ops,
+	       .select_cpu		= (void *)qmap_select_cpu,
+	       .enqueue			= (void *)qmap_enqueue,
+	       .dequeue			= (void *)qmap_dequeue,
+	       .dispatch		= (void *)qmap_dispatch,
+	       .tick			= (void *)qmap_tick,
+	       .core_sched_before	= (void *)qmap_core_sched_before,
+	       .cpu_release		= (void *)qmap_cpu_release,
+	       .init_task		= (void *)qmap_init_task,
+	       .dump			= (void *)qmap_dump,
+	       .dump_cpu		= (void *)qmap_dump_cpu,
+	       .dump_task		= (void *)qmap_dump_task,
+	       .cpu_online		= (void *)qmap_cpu_online,
+	       .cpu_offline		= (void *)qmap_cpu_offline,
+	       .init			= (void *)qmap_init,
+	       .exit			= (void *)qmap_exit,
+	       .flags			= SCX_OPS_ENQ_LAST,
+	       .timeout_ms		= 5000U,
+	       .name			= "qmap");
diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
new file mode 100644
index 000000000000..c9ca30d62b2b
--- /dev/null
+++ b/tools/sched_ext/scx_qmap.c
@@ -0,0 +1,144 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2022 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2022 David Vernet <dvernet@meta.com>
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <signal.h>
+#include <libgen.h>
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include "scx_qmap.bpf.skel.h"
+
+const char help_fmt[] =
+"A simple five-level FIFO queue sched_ext scheduler.\n"
+"\n"
+"See the top-level comment in .bpf.c for more details.\n"
+"\n"
+"Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-l COUNT] [-b COUNT]\n"
+"       [-P] [-d PID] [-D LEN] [-p] [-v]\n"
+"\n"
+"  -s SLICE_US   Override slice duration\n"
+"  -e COUNT      Trigger scx_bpf_error() after COUNT enqueues\n"
+"  -t COUNT      Stall every COUNT'th user thread\n"
+"  -T COUNT      Stall every COUNT'th kernel thread\n"
+"  -l COUNT      Trigger dispatch infinite looping after COUNT dispatches\n"
+"  -b COUNT      Dispatch upto COUNT tasks together\n"
+"  -P            Print out DSQ content to trace_pipe every second, use with -b\n"
+"  -d PID        Disallow a process from switching into SCHED_EXT (-1 for self)\n"
+"  -D LEN        Set scx_exit_info.dump buffer length\n"
+"  -S            Suppress qmap-specific debug dump\n"
+"  -p            Switch only tasks on SCHED_EXT policy instead of all\n"
+"  -v            Print libbpf debug messages\n"
+"  -h            Display this help and exit\n";
+
+static bool verbose;
+static volatile int exit_req;
+
+static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args)
+{
+	if (level == LIBBPF_DEBUG && !verbose)
+		return 0;
+	return vfprintf(stderr, format, args);
+}
+
+static void sigint_handler(int dummy)
+{
+	exit_req = 1;
+}
+
+int main(int argc, char **argv)
+{
+	struct scx_qmap *skel;
+	struct bpf_link *link;
+	int opt;
+
+	libbpf_set_print(libbpf_print_fn);
+	signal(SIGINT, sigint_handler);
+	signal(SIGTERM, sigint_handler);
+
+	skel = SCX_OPS_OPEN(qmap_ops, scx_qmap);
+
+	while ((opt = getopt(argc, argv, "s:e:t:T:l:b:Pd:D:Spvh")) != -1) {
+		switch (opt) {
+		case 's':
+			skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
+			break;
+		case 'e':
+			skel->bss->test_error_cnt = strtoul(optarg, NULL, 0);
+			break;
+		case 't':
+			skel->rodata->stall_user_nth = strtoul(optarg, NULL, 0);
+			break;
+		case 'T':
+			skel->rodata->stall_kernel_nth = strtoul(optarg, NULL, 0);
+			break;
+		case 'l':
+			skel->rodata->dsp_inf_loop_after = strtoul(optarg, NULL, 0);
+			break;
+		case 'b':
+			skel->rodata->dsp_batch = strtoul(optarg, NULL, 0);
+			break;
+		case 'P':
+			skel->rodata->print_shared_dsq = true;
+			break;
+		case 'd':
+			skel->rodata->disallow_tgid = strtol(optarg, NULL, 0);
+			if (skel->rodata->disallow_tgid < 0)
+				skel->rodata->disallow_tgid = getpid();
+			break;
+		case 'D':
+			skel->struct_ops.qmap_ops->exit_dump_len = strtoul(optarg, NULL, 0);
+			break;
+		case 'S':
+			skel->rodata->suppress_dump = true;
+			break;
+		case 'p':
+			skel->struct_ops.qmap_ops->flags |= SCX_OPS_SWITCH_PARTIAL;
+			break;
+		case 'v':
+			verbose = true;
+			break;
+		default:
+			fprintf(stderr, help_fmt, basename(argv[0]));
+			return opt != 'h';
+		}
+	}
+
+	SCX_OPS_LOAD(skel, qmap_ops, scx_qmap, uei);
+	link = SCX_OPS_ATTACH(skel, qmap_ops, scx_qmap);
+
+	while (!exit_req && !UEI_EXITED(skel, uei)) {
+		long nr_enqueued = skel->bss->nr_enqueued;
+		long nr_dispatched = skel->bss->nr_dispatched;
+
+		printf("stats  : enq=%lu dsp=%lu delta=%ld reenq=%"PRIu64" deq=%"PRIu64" core=%"PRIu64" enq_ddsp=%"PRIu64"\n",
+		       nr_enqueued, nr_dispatched, nr_enqueued - nr_dispatched,
+		       skel->bss->nr_reenqueued, skel->bss->nr_dequeued,
+		       skel->bss->nr_core_sched_execed,
+		       skel->bss->nr_ddsp_from_enq);
+		if (__COMPAT_has_ksym("scx_bpf_cpuperf_cur"))
+			printf("cpuperf: cur min/avg/max=%u/%u/%u target min/avg/max=%u/%u/%u\n",
+			       skel->bss->cpuperf_min,
+			       skel->bss->cpuperf_avg,
+			       skel->bss->cpuperf_max,
+			       skel->bss->cpuperf_target_min,
+			       skel->bss->cpuperf_target_avg,
+			       skel->bss->cpuperf_target_max);
+		fflush(stdout);
+		sleep(1);
+	}
+
+	bpf_link__destroy(link);
+	UEI_REPORT(skel, uei);
+	scx_qmap__destroy(skel);
+	/*
+	 * scx_qmap implements ops.cpu_on/offline() and doesn't need to restart
+	 * on CPU hotplug events.
+	 */
+	return 0;
+}
diff --git a/tools/sched_ext/scx_show_state.py b/tools/sched_ext/scx_show_state.py
new file mode 100644
index 000000000000..d457d2a74e1e
--- /dev/null
+++ b/tools/sched_ext/scx_show_state.py
@@ -0,0 +1,39 @@
+#!/usr/bin/env drgn
+#
+# Copyright (C) 2024 Tejun Heo <tj@kernel.org>
+# Copyright (C) 2024 Meta Platforms, Inc. and affiliates.
+
+desc = """
+This is a drgn script to show the current sched_ext state.
+For more info on drgn, visit https://github.com/osandov/drgn.
+"""
+
+import drgn
+import sys
+
+def err(s):
+    print(s, file=sys.stderr, flush=True)
+    sys.exit(1)
+
+def read_int(name):
+    return int(prog[name].value_())
+
+def read_atomic(name):
+    return prog[name].counter.value_()
+
+def read_static_key(name):
+    return prog[name].key.enabled.counter.value_()
+
+def ops_state_str(state):
+    return prog['scx_ops_enable_state_str'][state].string_().decode()
+
+ops = prog['scx_ops']
+enable_state = read_atomic("scx_ops_enable_state_var")
+
+print(f'ops           : {ops.name.string_().decode()}')
+print(f'enabled       : {read_static_key("__scx_ops_enabled")}')
+print(f'switching_all : {read_int("scx_switching_all")}')
+print(f'switched_all  : {read_static_key("__scx_switched_all")}')
+print(f'enable_state  : {ops_state_str(enable_state)} ({enable_state})')
+print(f'bypass_depth  : {read_atomic("scx_ops_bypass_depth")}')
+print(f'nr_rejected   : {read_atomic("scx_nr_rejected")}')
diff --git a/tools/sched_ext/scx_simple.bpf.c b/tools/sched_ext/scx_simple.bpf.c
new file mode 100644
index 000000000000..ed7e8d535fc5
--- /dev/null
+++ b/tools/sched_ext/scx_simple.bpf.c
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A simple scheduler.
+ *
+ * By default, it operates as a simple global weighted vtime scheduler and can
+ * be switched to FIFO scheduling. It also demonstrates the following niceties.
+ *
+ * - Statistics tracking how many tasks are queued to local and global dsq's.
+ * - Termination notification for userspace.
+ *
+ * While very simple, this scheduler should work reasonably well on CPUs with a
+ * uniform L3 cache topology. While preemption is not implemented, the fact that
+ * the scheduling queue is shared across all CPUs means that whatever is at the
+ * front of the queue is likely to be executed fairly quickly given enough
+ * number of CPUs. The FIFO scheduling mode may be beneficial to some workloads
+ * but comes with the usual problems with FIFO scheduling where saturating
+ * threads can easily drown out interactive ones.
+ *
+ * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2022 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2022 David Vernet <dvernet@meta.com>
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+const volatile bool fifo_sched;
+
+static u64 vtime_now;
+UEI_DEFINE(uei);
+
+/*
+ * Built-in DSQs such as SCX_DSQ_GLOBAL cannot be used as priority queues
+ * (meaning, cannot be dispatched to with scx_bpf_dispatch_vtime()). We
+ * therefore create a separate DSQ with ID 0 that we dispatch to and consume
+ * from. If scx_simple only supported global FIFO scheduling, then we could
+ * just use SCX_DSQ_GLOBAL.
+ */
+#define SHARED_DSQ 0
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(u64));
+	__uint(max_entries, 2);			/* [local, global] */
+} stats SEC(".maps");
+
+static void stat_inc(u32 idx)
+{
+	u64 *cnt_p = bpf_map_lookup_elem(&stats, &idx);
+	if (cnt_p)
+		(*cnt_p)++;
+}
+
+static inline bool vtime_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}
+
+s32 BPF_STRUCT_OPS(simple_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags)
+{
+	bool is_idle = false;
+	s32 cpu;
+
+	cpu = scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags, &is_idle);
+	if (is_idle) {
+		stat_inc(0);	/* count local queueing */
+		scx_bpf_dispatch(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0);
+	}
+
+	return cpu;
+}
+
+void BPF_STRUCT_OPS(simple_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	stat_inc(1);	/* count global queueing */
+
+	if (fifo_sched) {
+		scx_bpf_dispatch(p, SHARED_DSQ, SCX_SLICE_DFL, enq_flags);
+	} else {
+		u64 vtime = p->scx.dsq_vtime;
+
+		/*
+		 * Limit the amount of budget that an idling task can accumulate
+		 * to one slice.
+		 */
+		if (vtime_before(vtime, vtime_now - SCX_SLICE_DFL))
+			vtime = vtime_now - SCX_SLICE_DFL;
+
+		scx_bpf_dispatch_vtime(p, SHARED_DSQ, SCX_SLICE_DFL, vtime,
+				       enq_flags);
+	}
+}
+
+void BPF_STRUCT_OPS(simple_dispatch, s32 cpu, struct task_struct *prev)
+{
+	scx_bpf_consume(SHARED_DSQ);
+}
+
+void BPF_STRUCT_OPS(simple_running, struct task_struct *p)
+{
+	if (fifo_sched)
+		return;
+
+	/*
+	 * Global vtime always progresses forward as tasks start executing. The
+	 * test and update can be performed concurrently from multiple CPUs and
+	 * thus racy. Any error should be contained and temporary. Let's just
+	 * live with it.
+	 */
+	if (vtime_before(vtime_now, p->scx.dsq_vtime))
+		vtime_now = p->scx.dsq_vtime;
+}
+
+void BPF_STRUCT_OPS(simple_stopping, struct task_struct *p, bool runnable)
+{
+	if (fifo_sched)
+		return;
+
+	/*
+	 * Scale the execution time by the inverse of the weight and charge.
+	 *
+	 * Note that the default yield implementation yields by setting
+	 * @p->scx.slice to zero and the following would treat the yielding task
+	 * as if it has consumed all its slice. If this penalizes yielding tasks
+	 * too much, determine the execution time by taking explicit timestamps
+	 * instead of depending on @p->scx.slice.
+	 */
+	p->scx.dsq_vtime += (SCX_SLICE_DFL - p->scx.slice) * 100 / p->scx.weight;
+}
+
+void BPF_STRUCT_OPS(simple_enable, struct task_struct *p)
+{
+	p->scx.dsq_vtime = vtime_now;
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(simple_init)
+{
+	return scx_bpf_create_dsq(SHARED_DSQ, -1);
+}
+
+void BPF_STRUCT_OPS(simple_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SCX_OPS_DEFINE(simple_ops,
+	       .select_cpu		= (void *)simple_select_cpu,
+	       .enqueue			= (void *)simple_enqueue,
+	       .dispatch		= (void *)simple_dispatch,
+	       .running			= (void *)simple_running,
+	       .stopping		= (void *)simple_stopping,
+	       .enable			= (void *)simple_enable,
+	       .init			= (void *)simple_init,
+	       .exit			= (void *)simple_exit,
+	       .name			= "simple");
diff --git a/tools/sched_ext/scx_simple.c b/tools/sched_ext/scx_simple.c
new file mode 100644
index 000000000000..76d83199545c
--- /dev/null
+++ b/tools/sched_ext/scx_simple.c
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2022 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2022 David Vernet <dvernet@meta.com>
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <signal.h>
+#include <libgen.h>
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include "scx_simple.bpf.skel.h"
+
+const char help_fmt[] =
+"A simple sched_ext scheduler.\n"
+"\n"
+"See the top-level comment in .bpf.c for more details.\n"
+"\n"
+"Usage: %s [-f] [-v]\n"
+"\n"
+"  -f            Use FIFO scheduling instead of weighted vtime scheduling\n"
+"  -v            Print libbpf debug messages\n"
+"  -h            Display this help and exit\n";
+
+static bool verbose;
+static volatile int exit_req;
+
+static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args)
+{
+	if (level == LIBBPF_DEBUG && !verbose)
+		return 0;
+	return vfprintf(stderr, format, args);
+}
+
+static void sigint_handler(int simple)
+{
+	exit_req = 1;
+}
+
+static void read_stats(struct scx_simple *skel, __u64 *stats)
+{
+	int nr_cpus = libbpf_num_possible_cpus();
+	__u64 cnts[2][nr_cpus];
+	__u32 idx;
+
+	memset(stats, 0, sizeof(stats[0]) * 2);
+
+	for (idx = 0; idx < 2; idx++) {
+		int ret, cpu;
+
+		ret = bpf_map_lookup_elem(bpf_map__fd(skel->maps.stats),
+					  &idx, cnts[idx]);
+		if (ret < 0)
+			continue;
+		for (cpu = 0; cpu < nr_cpus; cpu++)
+			stats[idx] += cnts[idx][cpu];
+	}
+}
+
+int main(int argc, char **argv)
+{
+	struct scx_simple *skel;
+	struct bpf_link *link;
+	__u32 opt;
+	__u64 ecode;
+
+	libbpf_set_print(libbpf_print_fn);
+	signal(SIGINT, sigint_handler);
+	signal(SIGTERM, sigint_handler);
+restart:
+	skel = SCX_OPS_OPEN(simple_ops, scx_simple);
+
+	while ((opt = getopt(argc, argv, "fvh")) != -1) {
+		switch (opt) {
+		case 'f':
+			skel->rodata->fifo_sched = true;
+			break;
+		case 'v':
+			verbose = true;
+			break;
+		default:
+			fprintf(stderr, help_fmt, basename(argv[0]));
+			return opt != 'h';
+		}
+	}
+
+	SCX_OPS_LOAD(skel, simple_ops, scx_simple, uei);
+	link = SCX_OPS_ATTACH(skel, simple_ops, scx_simple);
+
+	while (!exit_req && !UEI_EXITED(skel, uei)) {
+		__u64 stats[2];
+
+		read_stats(skel, stats);
+		printf("local=%llu global=%llu\n", stats[0], stats[1]);
+		fflush(stdout);
+		sleep(1);
+	}
+
+	bpf_link__destroy(link);
+	ecode = UEI_REPORT(skel, uei);
+	scx_simple__destroy(skel);
+
+	if (UEI_ECODE_RESTART(ecode))
+		goto restart;
+	return 0;
+}
diff --git a/tools/testing/selftests/sched_ext/.gitignore b/tools/testing/selftests/sched_ext/.gitignore
new file mode 100644
index 000000000000..ae5491a114c0
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/.gitignore
@@ -0,0 +1,6 @@
+*
+!*.c
+!*.h
+!Makefile
+!.gitignore
+!config
diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
new file mode 100644
index 000000000000..0754a2c110a1
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -0,0 +1,218 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+include ../../../build/Build.include
+include ../../../scripts/Makefile.arch
+include ../../../scripts/Makefile.include
+include ../lib.mk
+
+ifneq ($(LLVM),)
+ifneq ($(filter %/,$(LLVM)),)
+LLVM_PREFIX := $(LLVM)
+else ifneq ($(filter -%,$(LLVM)),)
+LLVM_SUFFIX := $(LLVM)
+endif
+
+CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) $(CLANG_FLAGS) -fintegrated-as
+else
+CC := gcc
+endif # LLVM
+
+ifneq ($(CROSS_COMPILE),)
+$(error CROSS_COMPILE not supported for scx selftests)
+endif # CROSS_COMPILE
+
+CURDIR := $(abspath .)
+REPOROOT := $(abspath ../../../..)
+TOOLSDIR := $(REPOROOT)/tools
+LIBDIR := $(TOOLSDIR)/lib
+BPFDIR := $(LIBDIR)/bpf
+TOOLSINCDIR := $(TOOLSDIR)/include
+BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool
+APIDIR := $(TOOLSINCDIR)/uapi
+GENDIR := $(REPOROOT)/include/generated
+GENHDR := $(GENDIR)/autoconf.h
+SCXTOOLSDIR := $(TOOLSDIR)/sched_ext
+SCXTOOLSINCDIR := $(TOOLSDIR)/sched_ext/include
+
+OUTPUT_DIR := $(CURDIR)/build
+OBJ_DIR := $(OUTPUT_DIR)/obj
+INCLUDE_DIR := $(OUTPUT_DIR)/include
+BPFOBJ_DIR := $(OBJ_DIR)/libbpf
+SCXOBJ_DIR := $(OBJ_DIR)/sched_ext
+BPFOBJ := $(BPFOBJ_DIR)/libbpf.a
+LIBBPF_OUTPUT := $(OBJ_DIR)/libbpf/libbpf.a
+DEFAULT_BPFTOOL := $(OUTPUT_DIR)/sbin/bpftool
+HOST_BUILD_DIR := $(OBJ_DIR)
+HOST_OUTPUT_DIR := $(OUTPUT_DIR)
+
+VMLINUX_BTF_PATHS ?= ../../../../vmlinux					\
+		     /sys/kernel/btf/vmlinux					\
+		     /boot/vmlinux-$(shell uname -r)
+VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+ifeq ($(VMLINUX_BTF),)
+$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)")
+endif
+
+BPFTOOL ?= $(DEFAULT_BPFTOOL)
+
+ifneq ($(wildcard $(GENHDR)),)
+  GENFLAGS := -DHAVE_GENHDR
+endif
+
+CFLAGS += -g -O2 -rdynamic -pthread -Wall -Werror $(GENFLAGS)			\
+	  -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)				\
+	  -I$(TOOLSINCDIR) -I$(APIDIR) -I$(CURDIR)/include -I$(SCXTOOLSINCDIR)
+
+# Silence some warnings when compiled with clang
+ifneq ($(LLVM),)
+CFLAGS += -Wno-unused-command-line-argument
+endif
+
+LDFLAGS = -lelf -lz -lpthread -lzstd
+
+IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null |				\
+			grep 'define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__')
+
+# Get Clang's default includes on this system, as opposed to those seen by
+# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
+#
+# Use '-idirafter': Don't interfere with include mechanics except where the
+# build would have failed anyways.
+define get_sys_includes
+$(shell $(1) -v -E - </dev/null 2>&1 \
+	| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
+$(shell $(1) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}')
+endef
+
+BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH)					\
+	     $(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian)		\
+	     -I$(CURDIR)/include -I$(CURDIR)/include/bpf-compat			\
+	     -I$(INCLUDE_DIR) -I$(APIDIR) -I$(SCXTOOLSINCDIR)			\
+	     -I$(REPOROOT)/include						\
+	     $(call get_sys_includes,$(CLANG))					\
+	     -Wall -Wno-compare-distinct-pointer-types				\
+	     -Wno-incompatible-function-pointer-types				\
+	     -O2 -mcpu=v3
+
+# sort removes libbpf duplicates when not cross-building
+MAKE_DIRS := $(sort $(OBJ_DIR)/libbpf $(OBJ_DIR)/libbpf				\
+	       $(OBJ_DIR)/bpftool $(OBJ_DIR)/resolve_btfids			\
+	       $(INCLUDE_DIR) $(SCXOBJ_DIR))
+
+$(MAKE_DIRS):
+	$(call msg,MKDIR,,$@)
+	$(Q)mkdir -p $@
+
+$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)			\
+	   $(APIDIR)/linux/bpf.h						\
+	   | $(OBJ_DIR)/libbpf
+	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(OBJ_DIR)/libbpf/	\
+		    EXTRA_CFLAGS='-g -O0 -fPIC'					\
+		    DESTDIR=$(OUTPUT_DIR) prefix= all install_headers
+
+$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)	\
+		    $(LIBBPF_OUTPUT) | $(OBJ_DIR)/bpftool
+	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)				\
+		    ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD)		\
+		    EXTRA_CFLAGS='-g -O0'					\
+		    OUTPUT=$(OBJ_DIR)/bpftool/					\
+		    LIBBPF_OUTPUT=$(OBJ_DIR)/libbpf/				\
+		    LIBBPF_DESTDIR=$(OUTPUT_DIR)/				\
+		    prefix= DESTDIR=$(OUTPUT_DIR)/ install-bin
+
+$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR)
+ifeq ($(VMLINUX_H),)
+	$(call msg,GEN,,$@)
+	$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
+else
+	$(call msg,CP,,$@)
+	$(Q)cp "$(VMLINUX_H)" $@
+endif
+
+$(SCXOBJ_DIR)/%.bpf.o: %.bpf.c $(INCLUDE_DIR)/vmlinux.h	| $(BPFOBJ) $(SCXOBJ_DIR)
+	$(call msg,CLNG-BPF,,$(notdir $@))
+	$(Q)$(CLANG) $(BPF_CFLAGS) -target bpf -c $< -o $@
+
+$(INCLUDE_DIR)/%.bpf.skel.h: $(SCXOBJ_DIR)/%.bpf.o $(INCLUDE_DIR)/vmlinux.h $(BPFTOOL) | $(INCLUDE_DIR)
+	$(eval sched=$(notdir $@))
+	$(call msg,GEN-SKEL,,$(sched))
+	$(Q)$(BPFTOOL) gen object $(<:.o=.linked1.o) $<
+	$(Q)$(BPFTOOL) gen object $(<:.o=.linked2.o) $(<:.o=.linked1.o)
+	$(Q)$(BPFTOOL) gen object $(<:.o=.linked3.o) $(<:.o=.linked2.o)
+	$(Q)diff $(<:.o=.linked2.o) $(<:.o=.linked3.o)
+	$(Q)$(BPFTOOL) gen skeleton $(<:.o=.linked3.o) name $(subst .bpf.skel.h,,$(sched)) > $@
+	$(Q)$(BPFTOOL) gen subskeleton $(<:.o=.linked3.o) name $(subst .bpf.skel.h,,$(sched)) > $(@:.skel.h=.subskel.h)
+
+################
+# C schedulers #
+################
+
+override define CLEAN
+	rm -rf $(OUTPUT_DIR)
+	rm -f *.o *.bpf.o *.bpf.skel.h *.bpf.subskel.h
+	rm -f $(TEST_GEN_PROGS)
+	rm -f runner
+endef
+
+# Every testcase takes all of the BPF progs are dependencies by default. This
+# allows testcases to load any BPF scheduler, which is useful for testcases
+# that don't need their own prog to run their test.
+all_test_bpfprogs := $(foreach prog,$(wildcard *.bpf.c),$(INCLUDE_DIR)/$(patsubst %.c,%.skel.h,$(prog)))
+
+auto-test-targets :=			\
+	create_dsq			\
+	enq_last_no_enq_fails		\
+	enq_select_cpu_fails		\
+	ddsp_bogus_dsq_fail		\
+	ddsp_vtimelocal_fail		\
+	dsp_local_on			\
+	exit				\
+	hotplug				\
+	init_enable_count		\
+	maximal				\
+	maybe_null			\
+	minimal				\
+	prog_run			\
+	reload_loop			\
+	select_cpu_dfl			\
+	select_cpu_dfl_nodispatch	\
+	select_cpu_dispatch		\
+	select_cpu_dispatch_bad_dsq	\
+	select_cpu_dispatch_dbl_dsp	\
+	select_cpu_vtime		\
+	test_example			\
+
+testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets)))
+
+$(SCXOBJ_DIR)/runner.o: runner.c | $(SCXOBJ_DIR)
+	$(CC) $(CFLAGS) -c $< -o $@
+
+# Create all of the test targets object files, whose testcase objects will be
+# registered into the runner in ELF constructors.
+#
+# Note that we must do double expansion here in order to support conditionally
+# compiling BPF object files only if one is present, as the wildcard Make
+# function doesn't support using implicit rules otherwise.
+$(testcase-targets): $(SCXOBJ_DIR)/%.o: %.c $(SCXOBJ_DIR)/runner.o $(all_test_bpfprogs) | $(SCXOBJ_DIR)
+	$(eval test=$(patsubst %.o,%.c,$(notdir $@)))
+	$(CC) $(CFLAGS) -c $< -o $@ $(SCXOBJ_DIR)/runner.o
+
+$(SCXOBJ_DIR)/util.o: util.c | $(SCXOBJ_DIR)
+	$(CC) $(CFLAGS) -c $< -o $@
+
+runner: $(SCXOBJ_DIR)/runner.o $(SCXOBJ_DIR)/util.o $(BPFOBJ) $(testcase-targets)
+	@echo "$(testcase-targets)"
+	$(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS)
+
+TEST_GEN_PROGS := runner
+
+all: runner
+
+.PHONY: all clean help
+
+.DEFAULT_GOAL := all
+
+.DELETE_ON_ERROR:
+
+.SECONDARY:
diff --git a/tools/testing/selftests/sched_ext/config b/tools/testing/selftests/sched_ext/config
new file mode 100644
index 000000000000..0de9b4ee249d
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/config
@@ -0,0 +1,9 @@
+CONFIG_SCHED_DEBUG=y
+CONFIG_SCHED_CLASS_EXT=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_EXT_GROUP_SCHED=y
+CONFIG_BPF=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_BTF=y
diff --git a/tools/testing/selftests/sched_ext/create_dsq.bpf.c b/tools/testing/selftests/sched_ext/create_dsq.bpf.c
new file mode 100644
index 000000000000..23f79ed343f0
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/create_dsq.bpf.c
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Create and destroy DSQs in a loop.
+ *
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+void BPF_STRUCT_OPS(create_dsq_exit_task, struct task_struct *p,
+		    struct scx_exit_task_args *args)
+{
+	scx_bpf_destroy_dsq(p->pid);
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(create_dsq_init_task, struct task_struct *p,
+			     struct scx_init_task_args *args)
+{
+	s32 err;
+
+	err = scx_bpf_create_dsq(p->pid, -1);
+	if (err)
+		scx_bpf_error("Failed to create DSQ for %s[%d]",
+			      p->comm, p->pid);
+
+	return err;
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(create_dsq_init)
+{
+	u32 i;
+	s32 err;
+
+	bpf_for(i, 0, 1024) {
+		err = scx_bpf_create_dsq(i, -1);
+		if (err) {
+			scx_bpf_error("Failed to create DSQ %d", i);
+			return 0;
+		}
+	}
+
+	bpf_for(i, 0, 1024) {
+		scx_bpf_destroy_dsq(i);
+	}
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops create_dsq_ops = {
+	.init_task		= create_dsq_init_task,
+	.exit_task		= create_dsq_exit_task,
+	.init			= create_dsq_init,
+	.name			= "create_dsq",
+};
diff --git a/tools/testing/selftests/sched_ext/create_dsq.c b/tools/testing/selftests/sched_ext/create_dsq.c
new file mode 100644
index 000000000000..fa946d9146d4
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/create_dsq.c
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "create_dsq.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct create_dsq *skel;
+
+	skel = create_dsq__open_and_load();
+	if (!skel) {
+		SCX_ERR("Failed to open and load skel");
+		return SCX_TEST_FAIL;
+	}
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct create_dsq *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.create_dsq_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		return SCX_TEST_FAIL;
+	}
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct create_dsq *skel = ctx;
+
+	create_dsq__destroy(skel);
+}
+
+struct scx_test create_dsq = {
+	.name = "create_dsq",
+	.description = "Create and destroy a dsq in a loop",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&create_dsq)
diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
new file mode 100644
index 000000000000..e97ad41d354a
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	s32 cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
+
+	if (cpu >= 0) {
+		/*
+		 * If we dispatch to a bogus DSQ that will fall back to the
+		 * builtin global DSQ, we fail gracefully.
+		 */
+		scx_bpf_dispatch_vtime(p, 0xcafef00d, SCX_SLICE_DFL,
+				       p->scx.dsq_vtime, 0);
+		return cpu;
+	}
+
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops ddsp_bogus_dsq_fail_ops = {
+	.select_cpu		= ddsp_bogus_dsq_fail_select_cpu,
+	.exit			= ddsp_bogus_dsq_fail_exit,
+	.name			= "ddsp_bogus_dsq_fail",
+	.timeout_ms		= 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c
new file mode 100644
index 000000000000..e65d22f23f3b
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "ddsp_bogus_dsq_fail.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct ddsp_bogus_dsq_fail *skel;
+
+	skel = ddsp_bogus_dsq_fail__open_and_load();
+	SCX_FAIL_IF(!skel, "Failed to open and load skel");
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct ddsp_bogus_dsq_fail *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.ddsp_bogus_dsq_fail_ops);
+	SCX_FAIL_IF(!link, "Failed to attach struct_ops");
+
+	sleep(1);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR));
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct ddsp_bogus_dsq_fail *skel = ctx;
+
+	ddsp_bogus_dsq_fail__destroy(skel);
+}
+
+struct scx_test ddsp_bogus_dsq_fail = {
+	.name = "ddsp_bogus_dsq_fail",
+	.description = "Verify we gracefully fail, and fall back to using a "
+		       "built-in DSQ, if we do a direct dispatch to an invalid"
+		       " DSQ in ops.select_cpu()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&ddsp_bogus_dsq_fail)
diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
new file mode 100644
index 000000000000..dde7e7dafbfb
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	s32 cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
+
+	if (cpu >= 0) {
+		/* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */
+		scx_bpf_dispatch_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL,
+				       p->scx.dsq_vtime, 0);
+		return cpu;
+	}
+
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(ddsp_vtimelocal_fail_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops ddsp_vtimelocal_fail_ops = {
+	.select_cpu		= ddsp_vtimelocal_fail_select_cpu,
+	.exit			= ddsp_vtimelocal_fail_exit,
+	.name			= "ddsp_vtimelocal_fail",
+	.timeout_ms		= 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c
new file mode 100644
index 000000000000..abafee587cd6
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <unistd.h>
+#include "ddsp_vtimelocal_fail.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct ddsp_vtimelocal_fail *skel;
+
+	skel = ddsp_vtimelocal_fail__open_and_load();
+	SCX_FAIL_IF(!skel, "Failed to open and load skel");
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct ddsp_vtimelocal_fail *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.ddsp_vtimelocal_fail_ops);
+	SCX_FAIL_IF(!link, "Failed to attach struct_ops");
+
+	sleep(1);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR));
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct ddsp_vtimelocal_fail *skel = ctx;
+
+	ddsp_vtimelocal_fail__destroy(skel);
+}
+
+struct scx_test ddsp_vtimelocal_fail = {
+	.name = "ddsp_vtimelocal_fail",
+	.description = "Verify we gracefully fail, and fall back to using a "
+		       "built-in DSQ, if we do a direct vtime dispatch to a "
+		       "built-in DSQ from DSQ in ops.select_cpu()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&ddsp_vtimelocal_fail)
diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
new file mode 100644
index 000000000000..efb4672decb4
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+const volatile s32 nr_cpus;
+
+UEI_DEFINE(uei);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_QUEUE);
+	__uint(max_entries, 8192);
+	__type(value, s32);
+} queue SEC(".maps");
+
+s32 BPF_STRUCT_OPS(dsp_local_on_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(dsp_local_on_enqueue, struct task_struct *p,
+		    u64 enq_flags)
+{
+	s32 pid = p->pid;
+
+	if (bpf_map_push_elem(&queue, &pid, 0))
+		scx_bpf_error("Failed to enqueue %s[%d]", p->comm, p->pid);
+}
+
+void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev)
+{
+	s32 pid, target;
+	struct task_struct *p;
+
+	if (bpf_map_pop_elem(&queue, &pid))
+		return;
+
+	p = bpf_task_from_pid(pid);
+	if (!p)
+		return;
+
+	target = bpf_get_prandom_u32() % nr_cpus;
+
+	scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0);
+	bpf_task_release(p);
+}
+
+void BPF_STRUCT_OPS(dsp_local_on_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops dsp_local_on_ops = {
+	.select_cpu		= dsp_local_on_select_cpu,
+	.enqueue		= dsp_local_on_enqueue,
+	.dispatch		= dsp_local_on_dispatch,
+	.exit			= dsp_local_on_exit,
+	.name			= "dsp_local_on",
+	.timeout_ms		= 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c
new file mode 100644
index 000000000000..472851b56854
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/dsp_local_on.c
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <unistd.h>
+#include "dsp_local_on.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct dsp_local_on *skel;
+
+	skel = dsp_local_on__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+
+	skel->rodata->nr_cpus = libbpf_num_possible_cpus();
+	SCX_FAIL_IF(dsp_local_on__load(skel), "Failed to load skel");
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct dsp_local_on *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.dsp_local_on_ops);
+	SCX_FAIL_IF(!link, "Failed to attach struct_ops");
+
+	/* Just sleeping is fine, plenty of scheduling events happening */
+	sleep(1);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR));
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct dsp_local_on *skel = ctx;
+
+	dsp_local_on__destroy(skel);
+}
+
+struct scx_test dsp_local_on = {
+	.name = "dsp_local_on",
+	.description = "Verify we can directly dispatch tasks to a local DSQs "
+		       "from osp.dispatch()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&dsp_local_on)
diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c
new file mode 100644
index 000000000000..b0b99531d5d5
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates the behavior of direct dispatching with a default
+ * select_cpu implementation.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC(".struct_ops.link")
+struct sched_ext_ops enq_last_no_enq_fails_ops = {
+	.name			= "enq_last_no_enq_fails",
+	/* Need to define ops.enqueue() with SCX_OPS_ENQ_LAST */
+	.flags			= SCX_OPS_ENQ_LAST,
+	.timeout_ms		= 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c
new file mode 100644
index 000000000000..2a3eda5e2c0b
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "enq_last_no_enq_fails.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct enq_last_no_enq_fails *skel;
+
+	skel = enq_last_no_enq_fails__open_and_load();
+	if (!skel) {
+		SCX_ERR("Failed to open and load skel");
+		return SCX_TEST_FAIL;
+	}
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct enq_last_no_enq_fails *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.enq_last_no_enq_fails_ops);
+	if (link) {
+		SCX_ERR("Incorrectly succeeded in to attaching scheduler");
+		return SCX_TEST_FAIL;
+	}
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct enq_last_no_enq_fails *skel = ctx;
+
+	enq_last_no_enq_fails__destroy(skel);
+}
+
+struct scx_test enq_last_no_enq_fails = {
+	.name = "enq_last_no_enq_fails",
+	.description = "Verify we fail to load a scheduler if we specify "
+		       "the SCX_OPS_ENQ_LAST flag without defining "
+		       "ops.enqueue()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&enq_last_no_enq_fails)
diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
new file mode 100644
index 000000000000..b3dfc1033cd6
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+/* Manually specify the signature until the kfunc is added to the scx repo. */
+s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
+			   bool *found) __ksym;
+
+s32 BPF_STRUCT_OPS(enq_select_cpu_fails_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p,
+		    u64 enq_flags)
+{
+	/*
+	 * Need to initialize the variable or the verifier will fail to load.
+	 * Improving these semantics is actively being worked on.
+	 */
+	bool found = false;
+
+	/* Can only call from ops.select_cpu() */
+	scx_bpf_select_cpu_dfl(p, 0, 0, &found);
+
+	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops enq_select_cpu_fails_ops = {
+	.select_cpu		= enq_select_cpu_fails_select_cpu,
+	.enqueue		= enq_select_cpu_fails_enqueue,
+	.name			= "enq_select_cpu_fails",
+	.timeout_ms		= 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c
new file mode 100644
index 000000000000..dd1350e5f002
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "enq_select_cpu_fails.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct enq_select_cpu_fails *skel;
+
+	skel = enq_select_cpu_fails__open_and_load();
+	if (!skel) {
+		SCX_ERR("Failed to open and load skel");
+		return SCX_TEST_FAIL;
+	}
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct enq_select_cpu_fails *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.enq_select_cpu_fails_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		return SCX_TEST_FAIL;
+	}
+
+	sleep(1);
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct enq_select_cpu_fails *skel = ctx;
+
+	enq_select_cpu_fails__destroy(skel);
+}
+
+struct scx_test enq_select_cpu_fails = {
+	.name = "enq_select_cpu_fails",
+	.description = "Verify we fail to call scx_bpf_select_cpu_dfl() "
+		       "from ops.enqueue()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&enq_select_cpu_fails)
diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c
new file mode 100644
index 000000000000..ae12ddaac921
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/exit.bpf.c
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+#include "exit_test.h"
+
+const volatile int exit_point;
+UEI_DEFINE(uei);
+
+#define EXIT_CLEANLY() scx_bpf_exit(exit_point, "%d", exit_point)
+
+s32 BPF_STRUCT_OPS(exit_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	bool found;
+
+	if (exit_point == EXIT_SELECT_CPU)
+		EXIT_CLEANLY();
+
+	return scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags, &found);
+}
+
+void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	if (exit_point == EXIT_ENQUEUE)
+		EXIT_CLEANLY();
+
+	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+}
+
+void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p)
+{
+	if (exit_point == EXIT_DISPATCH)
+		EXIT_CLEANLY();
+
+	scx_bpf_consume(SCX_DSQ_GLOBAL);
+}
+
+void BPF_STRUCT_OPS(exit_enable, struct task_struct *p)
+{
+	if (exit_point == EXIT_ENABLE)
+		EXIT_CLEANLY();
+}
+
+s32 BPF_STRUCT_OPS(exit_init_task, struct task_struct *p,
+		    struct scx_init_task_args *args)
+{
+	if (exit_point == EXIT_INIT_TASK)
+		EXIT_CLEANLY();
+
+	return 0;
+}
+
+void BPF_STRUCT_OPS(exit_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(exit_init)
+{
+	if (exit_point == EXIT_INIT)
+		EXIT_CLEANLY();
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops exit_ops = {
+	.select_cpu		= exit_select_cpu,
+	.enqueue		= exit_enqueue,
+	.dispatch		= exit_dispatch,
+	.init_task		= exit_init_task,
+	.enable			= exit_enable,
+	.exit			= exit_exit,
+	.init			= exit_init,
+	.name			= "exit",
+	.timeout_ms		= 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/exit.c b/tools/testing/selftests/sched_ext/exit.c
new file mode 100644
index 000000000000..31bcd06e21cd
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/exit.c
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <sched.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "exit.bpf.skel.h"
+#include "scx_test.h"
+
+#include "exit_test.h"
+
+static enum scx_test_status run(void *ctx)
+{
+	enum exit_test_case tc;
+
+	for (tc = 0; tc < NUM_EXITS; tc++) {
+		struct exit *skel;
+		struct bpf_link *link;
+		char buf[16];
+
+		skel = exit__open();
+		skel->rodata->exit_point = tc;
+		exit__load(skel);
+		link = bpf_map__attach_struct_ops(skel->maps.exit_ops);
+		if (!link) {
+			SCX_ERR("Failed to attach scheduler");
+			exit__destroy(skel);
+			return SCX_TEST_FAIL;
+		}
+
+		/* Assumes uei.kind is written last */
+		while (skel->data->uei.kind == EXIT_KIND(SCX_EXIT_NONE))
+			sched_yield();
+
+		SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG_BPF));
+		SCX_EQ(skel->data->uei.exit_code, tc);
+		sprintf(buf, "%d", tc);
+		SCX_ASSERT(!strcmp(skel->data->uei.msg, buf));
+		bpf_link__destroy(link);
+		exit__destroy(skel);
+	}
+
+	return SCX_TEST_PASS;
+}
+
+struct scx_test exit_test = {
+	.name = "exit",
+	.description = "Verify we can cleanly exit a scheduler in multiple places",
+	.run = run,
+};
+REGISTER_SCX_TEST(&exit_test)
diff --git a/tools/testing/selftests/sched_ext/exit_test.h b/tools/testing/selftests/sched_ext/exit_test.h
new file mode 100644
index 000000000000..94f0268b9cb8
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/exit_test.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+
+#ifndef __EXIT_TEST_H__
+#define __EXIT_TEST_H__
+
+enum exit_test_case {
+	EXIT_SELECT_CPU,
+	EXIT_ENQUEUE,
+	EXIT_DISPATCH,
+	EXIT_ENABLE,
+	EXIT_INIT_TASK,
+	EXIT_INIT,
+	NUM_EXITS,
+};
+
+#endif  // # __EXIT_TEST_H__
diff --git a/tools/testing/selftests/sched_ext/hotplug.bpf.c b/tools/testing/selftests/sched_ext/hotplug.bpf.c
new file mode 100644
index 000000000000..8f2601db39f3
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/hotplug.bpf.c
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+#include "hotplug_test.h"
+
+UEI_DEFINE(uei);
+
+void BPF_STRUCT_OPS(hotplug_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+static void exit_from_hotplug(s32 cpu, bool onlining)
+{
+	/*
+	 * Ignored, just used to verify that we can invoke blocking kfuncs
+	 * from the hotplug path.
+	 */
+	scx_bpf_create_dsq(0, -1);
+
+	s64 code = SCX_ECODE_ACT_RESTART | HOTPLUG_EXIT_RSN;
+
+	if (onlining)
+		code |= HOTPLUG_ONLINING;
+
+	scx_bpf_exit(code, "hotplug event detected (%d going %s)", cpu,
+		     onlining ? "online" : "offline");
+}
+
+void BPF_STRUCT_OPS_SLEEPABLE(hotplug_cpu_online, s32 cpu)
+{
+	exit_from_hotplug(cpu, true);
+}
+
+void BPF_STRUCT_OPS_SLEEPABLE(hotplug_cpu_offline, s32 cpu)
+{
+	exit_from_hotplug(cpu, false);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops hotplug_cb_ops = {
+	.cpu_online		= hotplug_cpu_online,
+	.cpu_offline		= hotplug_cpu_offline,
+	.exit			= hotplug_exit,
+	.name			= "hotplug_cbs",
+	.timeout_ms		= 1000U,
+};
+
+SEC(".struct_ops.link")
+struct sched_ext_ops hotplug_nocb_ops = {
+	.exit			= hotplug_exit,
+	.name			= "hotplug_nocbs",
+	.timeout_ms		= 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/hotplug.c b/tools/testing/selftests/sched_ext/hotplug.c
new file mode 100644
index 000000000000..87bf220b1bce
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/hotplug.c
@@ -0,0 +1,168 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <sched.h>
+#include <scx/common.h>
+#include <sched.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "hotplug_test.h"
+#include "hotplug.bpf.skel.h"
+#include "scx_test.h"
+#include "util.h"
+
+const char *online_path = "/sys/devices/system/cpu/cpu1/online";
+
+static bool is_cpu_online(void)
+{
+	return file_read_long(online_path) > 0;
+}
+
+static void toggle_online_status(bool online)
+{
+	long val = online ? 1 : 0;
+	int ret;
+
+	ret = file_write_long(online_path, val);
+	if (ret != 0)
+		fprintf(stderr, "Failed to bring CPU %s (%s)",
+			online ? "online" : "offline", strerror(errno));
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	if (!is_cpu_online())
+		return SCX_TEST_SKIP;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status test_hotplug(bool onlining, bool cbs_defined)
+{
+	struct hotplug *skel;
+	struct bpf_link *link;
+	long kind, code;
+
+	SCX_ASSERT(is_cpu_online());
+
+	skel = hotplug__open_and_load();
+	SCX_ASSERT(skel);
+
+	/* Testing the offline -> online path, so go offline before starting */
+	if (onlining)
+		toggle_online_status(0);
+
+	if (cbs_defined) {
+		kind = SCX_KIND_VAL(SCX_EXIT_UNREG_BPF);
+		code = SCX_ECODE_VAL(SCX_ECODE_ACT_RESTART) | HOTPLUG_EXIT_RSN;
+		if (onlining)
+			code |= HOTPLUG_ONLINING;
+	} else {
+		kind = SCX_KIND_VAL(SCX_EXIT_UNREG_KERN);
+		code = SCX_ECODE_VAL(SCX_ECODE_ACT_RESTART) |
+		       SCX_ECODE_VAL(SCX_ECODE_RSN_HOTPLUG);
+	}
+
+	if (cbs_defined)
+		link = bpf_map__attach_struct_ops(skel->maps.hotplug_cb_ops);
+	else
+		link = bpf_map__attach_struct_ops(skel->maps.hotplug_nocb_ops);
+
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		hotplug__destroy(skel);
+		return SCX_TEST_FAIL;
+	}
+
+	toggle_online_status(onlining ? 1 : 0);
+
+	while (!UEI_EXITED(skel, uei))
+		sched_yield();
+
+	SCX_EQ(skel->data->uei.kind, kind);
+	SCX_EQ(UEI_REPORT(skel, uei), code);
+
+	if (!onlining)
+		toggle_online_status(1);
+
+	bpf_link__destroy(link);
+	hotplug__destroy(skel);
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status test_hotplug_attach(void)
+{
+	struct hotplug *skel;
+	struct bpf_link *link;
+	enum scx_test_status status = SCX_TEST_PASS;
+	long kind, code;
+
+	SCX_ASSERT(is_cpu_online());
+	SCX_ASSERT(scx_hotplug_seq() > 0);
+
+	skel = SCX_OPS_OPEN(hotplug_nocb_ops, hotplug);
+	SCX_ASSERT(skel);
+
+	SCX_OPS_LOAD(skel, hotplug_nocb_ops, hotplug, uei);
+
+	/*
+	 * Take the CPU offline to increment the global hotplug seq, which
+	 * should cause attach to fail due to us setting the hotplug seq above
+	 */
+	toggle_online_status(0);
+	link = bpf_map__attach_struct_ops(skel->maps.hotplug_nocb_ops);
+
+	toggle_online_status(1);
+
+	SCX_ASSERT(link);
+	while (!UEI_EXITED(skel, uei))
+		sched_yield();
+
+	kind = SCX_KIND_VAL(SCX_EXIT_UNREG_KERN);
+	code = SCX_ECODE_VAL(SCX_ECODE_ACT_RESTART) |
+	       SCX_ECODE_VAL(SCX_ECODE_RSN_HOTPLUG);
+	SCX_EQ(skel->data->uei.kind, kind);
+	SCX_EQ(UEI_REPORT(skel, uei), code);
+
+	bpf_link__destroy(link);
+	hotplug__destroy(skel);
+
+	return status;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+
+#define HP_TEST(__onlining, __cbs_defined) ({				\
+	if (test_hotplug(__onlining, __cbs_defined) != SCX_TEST_PASS)	\
+		return SCX_TEST_FAIL;					\
+})
+
+	HP_TEST(true, true);
+	HP_TEST(false, true);
+	HP_TEST(true, false);
+	HP_TEST(false, false);
+
+#undef HP_TEST
+
+	return test_hotplug_attach();
+}
+
+static void cleanup(void *ctx)
+{
+	toggle_online_status(1);
+}
+
+struct scx_test hotplug_test = {
+	.name = "hotplug",
+	.description = "Verify hotplug behavior",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&hotplug_test)
diff --git a/tools/testing/selftests/sched_ext/hotplug_test.h b/tools/testing/selftests/sched_ext/hotplug_test.h
new file mode 100644
index 000000000000..73d236f90787
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/hotplug_test.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+
+#ifndef __HOTPLUG_TEST_H__
+#define __HOTPLUG_TEST_H__
+
+enum hotplug_test_flags {
+	HOTPLUG_EXIT_RSN = 1LLU << 0,
+	HOTPLUG_ONLINING = 1LLU << 1,
+};
+
+#endif  // # __HOTPLUG_TEST_H__
diff --git a/tools/testing/selftests/sched_ext/init_enable_count.bpf.c b/tools/testing/selftests/sched_ext/init_enable_count.bpf.c
new file mode 100644
index 000000000000..47ea89a626c3
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/init_enable_count.bpf.c
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that verifies that we do proper counting of init, enable, etc
+ * callbacks.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+u64 init_task_cnt, exit_task_cnt, enable_cnt, disable_cnt;
+u64 init_fork_cnt, init_transition_cnt;
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(cnt_init_task, struct task_struct *p,
+			     struct scx_init_task_args *args)
+{
+	__sync_fetch_and_add(&init_task_cnt, 1);
+
+	if (args->fork)
+		__sync_fetch_and_add(&init_fork_cnt, 1);
+	else
+		__sync_fetch_and_add(&init_transition_cnt, 1);
+
+	return 0;
+}
+
+void BPF_STRUCT_OPS(cnt_exit_task, struct task_struct *p)
+{
+	__sync_fetch_and_add(&exit_task_cnt, 1);
+}
+
+void BPF_STRUCT_OPS(cnt_enable, struct task_struct *p)
+{
+	__sync_fetch_and_add(&enable_cnt, 1);
+}
+
+void BPF_STRUCT_OPS(cnt_disable, struct task_struct *p)
+{
+	__sync_fetch_and_add(&disable_cnt, 1);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops init_enable_count_ops = {
+	.init_task	= cnt_init_task,
+	.exit_task	= cnt_exit_task,
+	.enable		= cnt_enable,
+	.disable	= cnt_disable,
+	.name		= "init_enable_count",
+};
diff --git a/tools/testing/selftests/sched_ext/init_enable_count.c b/tools/testing/selftests/sched_ext/init_enable_count.c
new file mode 100644
index 000000000000..97d45f1e5597
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/init_enable_count.c
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <sched.h>
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include "scx_test.h"
+#include "init_enable_count.bpf.skel.h"
+
+#define SCHED_EXT 7
+
+static struct init_enable_count *
+open_load_prog(bool global)
+{
+	struct init_enable_count *skel;
+
+	skel = init_enable_count__open();
+	SCX_BUG_ON(!skel, "Failed to open skel");
+
+	if (!global)
+		skel->struct_ops.init_enable_count_ops->flags |= SCX_OPS_SWITCH_PARTIAL;
+
+	SCX_BUG_ON(init_enable_count__load(skel), "Failed to load skel");
+
+	return skel;
+}
+
+static enum scx_test_status run_test(bool global)
+{
+	struct init_enable_count *skel;
+	struct bpf_link *link;
+	const u32 num_children = 5, num_pre_forks = 1024;
+	int ret, i, status;
+	struct sched_param param = {};
+	pid_t pids[num_pre_forks];
+
+	skel = open_load_prog(global);
+
+	/*
+	 * Fork a bunch of children before we attach the scheduler so that we
+	 * ensure (at least in practical terms) that there are more tasks that
+	 * transition from SCHED_OTHER -> SCHED_EXT than there are tasks that
+	 * take the fork() path either below or in other processes.
+	 */
+	for (i = 0; i < num_pre_forks; i++) {
+		pids[i] = fork();
+		SCX_FAIL_IF(pids[i] < 0, "Failed to fork child");
+		if (pids[i] == 0) {
+			sleep(1);
+			exit(0);
+		}
+	}
+
+	link = bpf_map__attach_struct_ops(skel->maps.init_enable_count_ops);
+	SCX_FAIL_IF(!link, "Failed to attach struct_ops");
+
+	for (i = 0; i < num_pre_forks; i++) {
+		SCX_FAIL_IF(waitpid(pids[i], &status, 0) != pids[i],
+			    "Failed to wait for pre-forked child\n");
+
+		SCX_FAIL_IF(status != 0, "Pre-forked child %d exited with status %d\n", i,
+			    status);
+	}
+
+	bpf_link__destroy(link);
+	SCX_GE(skel->bss->init_task_cnt, num_pre_forks);
+	SCX_GE(skel->bss->exit_task_cnt, num_pre_forks);
+
+	link = bpf_map__attach_struct_ops(skel->maps.init_enable_count_ops);
+	SCX_FAIL_IF(!link, "Failed to attach struct_ops");
+
+	/* SCHED_EXT children */
+	for (i = 0; i < num_children; i++) {
+		pids[i] = fork();
+		SCX_FAIL_IF(pids[i] < 0, "Failed to fork child");
+
+		if (pids[i] == 0) {
+			ret = sched_setscheduler(0, SCHED_EXT, &param);
+			SCX_BUG_ON(ret, "Failed to set sched to sched_ext");
+
+			/*
+			 * Reset to SCHED_OTHER for half of them. Counts for
+			 * everything should still be the same regardless, as
+			 * ops.disable() is invoked even if a task is still on
+			 * SCHED_EXT before it exits.
+			 */
+			if (i % 2 == 0) {
+				ret = sched_setscheduler(0, SCHED_OTHER, &param);
+				SCX_BUG_ON(ret, "Failed to reset sched to normal");
+			}
+			exit(0);
+		}
+	}
+	for (i = 0; i < num_children; i++) {
+		SCX_FAIL_IF(waitpid(pids[i], &status, 0) != pids[i],
+			    "Failed to wait for SCX child\n");
+
+		SCX_FAIL_IF(status != 0, "SCX child %d exited with status %d\n", i,
+			    status);
+	}
+
+	/* SCHED_OTHER children */
+	for (i = 0; i < num_children; i++) {
+		pids[i] = fork();
+		if (pids[i] == 0)
+			exit(0);
+	}
+
+	for (i = 0; i < num_children; i++) {
+		SCX_FAIL_IF(waitpid(pids[i], &status, 0) != pids[i],
+			    "Failed to wait for normal child\n");
+
+		SCX_FAIL_IF(status != 0, "Normal child %d exited with status %d\n", i,
+			    status);
+	}
+
+	bpf_link__destroy(link);
+
+	SCX_GE(skel->bss->init_task_cnt, 2 * num_children);
+	SCX_GE(skel->bss->exit_task_cnt, 2 * num_children);
+
+	if (global) {
+		SCX_GE(skel->bss->enable_cnt, 2 * num_children);
+		SCX_GE(skel->bss->disable_cnt, 2 * num_children);
+	} else {
+		SCX_EQ(skel->bss->enable_cnt, num_children);
+		SCX_EQ(skel->bss->disable_cnt, num_children);
+	}
+	/*
+	 * We forked a ton of tasks before we attached the scheduler above, so
+	 * this should be fine. Technically it could be flaky if a ton of forks
+	 * are happening at the same time in other processes, but that should
+	 * be exceedingly unlikely.
+	 */
+	SCX_GT(skel->bss->init_transition_cnt, skel->bss->init_fork_cnt);
+	SCX_GE(skel->bss->init_fork_cnt, 2 * num_children);
+
+	init_enable_count__destroy(skel);
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	enum scx_test_status status;
+
+	status = run_test(true);
+	if (status != SCX_TEST_PASS)
+		return status;
+
+	return run_test(false);
+}
+
+struct scx_test init_enable_count = {
+	.name = "init_enable_count",
+	.description = "Verify we do the correct amount of counting of init, "
+		       "enable, etc callbacks.",
+	.run = run,
+};
+REGISTER_SCX_TEST(&init_enable_count)
diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c
new file mode 100644
index 000000000000..44612fdaf399
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/maximal.bpf.c
@@ -0,0 +1,132 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler with every callback defined.
+ *
+ * This scheduler defines every callback.
+ *
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu,
+		   u64 wake_flags)
+{
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+}
+
+void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags)
+{}
+
+void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev)
+{
+	scx_bpf_consume(SCX_DSQ_GLOBAL);
+}
+
+void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags)
+{}
+
+void BPF_STRUCT_OPS(maximal_running, struct task_struct *p)
+{}
+
+void BPF_STRUCT_OPS(maximal_stopping, struct task_struct *p, bool runnable)
+{}
+
+void BPF_STRUCT_OPS(maximal_quiescent, struct task_struct *p, u64 deq_flags)
+{}
+
+bool BPF_STRUCT_OPS(maximal_yield, struct task_struct *from,
+		    struct task_struct *to)
+{
+	return false;
+}
+
+bool BPF_STRUCT_OPS(maximal_core_sched_before, struct task_struct *a,
+		    struct task_struct *b)
+{
+	return false;
+}
+
+void BPF_STRUCT_OPS(maximal_set_weight, struct task_struct *p, u32 weight)
+{}
+
+void BPF_STRUCT_OPS(maximal_set_cpumask, struct task_struct *p,
+		    const struct cpumask *cpumask)
+{}
+
+void BPF_STRUCT_OPS(maximal_update_idle, s32 cpu, bool idle)
+{}
+
+void BPF_STRUCT_OPS(maximal_cpu_acquire, s32 cpu,
+		    struct scx_cpu_acquire_args *args)
+{}
+
+void BPF_STRUCT_OPS(maximal_cpu_release, s32 cpu,
+		    struct scx_cpu_release_args *args)
+{}
+
+void BPF_STRUCT_OPS(maximal_cpu_online, s32 cpu)
+{}
+
+void BPF_STRUCT_OPS(maximal_cpu_offline, s32 cpu)
+{}
+
+s32 BPF_STRUCT_OPS(maximal_init_task, struct task_struct *p,
+		   struct scx_init_task_args *args)
+{
+	return 0;
+}
+
+void BPF_STRUCT_OPS(maximal_enable, struct task_struct *p)
+{}
+
+void BPF_STRUCT_OPS(maximal_exit_task, struct task_struct *p,
+		    struct scx_exit_task_args *args)
+{}
+
+void BPF_STRUCT_OPS(maximal_disable, struct task_struct *p)
+{}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init)
+{
+	return 0;
+}
+
+void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info)
+{}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops maximal_ops = {
+	.select_cpu		= maximal_select_cpu,
+	.enqueue		= maximal_enqueue,
+	.dequeue		= maximal_dequeue,
+	.dispatch		= maximal_dispatch,
+	.runnable		= maximal_runnable,
+	.running		= maximal_running,
+	.stopping		= maximal_stopping,
+	.quiescent		= maximal_quiescent,
+	.yield			= maximal_yield,
+	.core_sched_before	= maximal_core_sched_before,
+	.set_weight		= maximal_set_weight,
+	.set_cpumask		= maximal_set_cpumask,
+	.update_idle		= maximal_update_idle,
+	.cpu_acquire		= maximal_cpu_acquire,
+	.cpu_release		= maximal_cpu_release,
+	.cpu_online		= maximal_cpu_online,
+	.cpu_offline		= maximal_cpu_offline,
+	.init_task		= maximal_init_task,
+	.enable			= maximal_enable,
+	.exit_task		= maximal_exit_task,
+	.disable		= maximal_disable,
+	.init			= maximal_init,
+	.exit			= maximal_exit,
+	.name			= "maximal",
+};
diff --git a/tools/testing/selftests/sched_ext/maximal.c b/tools/testing/selftests/sched_ext/maximal.c
new file mode 100644
index 000000000000..f38fc973c380
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/maximal.c
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "maximal.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct maximal *skel;
+
+	skel = maximal__open_and_load();
+	SCX_FAIL_IF(!skel, "Failed to open and load skel");
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct maximal *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.maximal_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct maximal *skel = ctx;
+
+	maximal__destroy(skel);
+}
+
+struct scx_test maximal = {
+	.name = "maximal",
+	.description = "Verify we can load a scheduler with every callback defined",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&maximal)
diff --git a/tools/testing/selftests/sched_ext/maybe_null.bpf.c b/tools/testing/selftests/sched_ext/maybe_null.bpf.c
new file mode 100644
index 000000000000..27d0f386acfb
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/maybe_null.bpf.c
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+u64 vtime_test;
+
+void BPF_STRUCT_OPS(maybe_null_running, struct task_struct *p)
+{}
+
+void BPF_STRUCT_OPS(maybe_null_success_dispatch, s32 cpu, struct task_struct *p)
+{
+	if (p != NULL)
+		vtime_test = p->scx.dsq_vtime;
+}
+
+bool BPF_STRUCT_OPS(maybe_null_success_yield, struct task_struct *from,
+		    struct task_struct *to)
+{
+	if (to)
+		bpf_printk("Yielding to %s[%d]", to->comm, to->pid);
+
+	return false;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops maybe_null_success = {
+	.dispatch               = maybe_null_success_dispatch,
+	.yield			= maybe_null_success_yield,
+	.enable			= maybe_null_running,
+	.name			= "minimal",
+};
diff --git a/tools/testing/selftests/sched_ext/maybe_null.c b/tools/testing/selftests/sched_ext/maybe_null.c
new file mode 100644
index 000000000000..31cfafb0cf65
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/maybe_null.c
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "maybe_null.bpf.skel.h"
+#include "maybe_null_fail_dsp.bpf.skel.h"
+#include "maybe_null_fail_yld.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status run(void *ctx)
+{
+	struct maybe_null *skel;
+	struct maybe_null_fail_dsp *fail_dsp;
+	struct maybe_null_fail_yld *fail_yld;
+
+	skel = maybe_null__open_and_load();
+	if (!skel) {
+		SCX_ERR("Failed to open and load maybe_null skel");
+		return SCX_TEST_FAIL;
+	}
+	maybe_null__destroy(skel);
+
+	fail_dsp = maybe_null_fail_dsp__open_and_load();
+	if (fail_dsp) {
+		maybe_null_fail_dsp__destroy(fail_dsp);
+		SCX_ERR("Should failed to open and load maybe_null_fail_dsp skel");
+		return SCX_TEST_FAIL;
+	}
+
+	fail_yld = maybe_null_fail_yld__open_and_load();
+	if (fail_yld) {
+		maybe_null_fail_yld__destroy(fail_yld);
+		SCX_ERR("Should failed to open and load maybe_null_fail_yld skel");
+		return SCX_TEST_FAIL;
+	}
+
+	return SCX_TEST_PASS;
+}
+
+struct scx_test maybe_null = {
+	.name = "maybe_null",
+	.description = "Verify if PTR_MAYBE_NULL work for .dispatch",
+	.run = run,
+};
+REGISTER_SCX_TEST(&maybe_null)
diff --git a/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c b/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c
new file mode 100644
index 000000000000..c0641050271d
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+u64 vtime_test;
+
+void BPF_STRUCT_OPS(maybe_null_running, struct task_struct *p)
+{}
+
+void BPF_STRUCT_OPS(maybe_null_fail_dispatch, s32 cpu, struct task_struct *p)
+{
+	vtime_test = p->scx.dsq_vtime;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops maybe_null_fail = {
+	.dispatch               = maybe_null_fail_dispatch,
+	.enable			= maybe_null_running,
+	.name			= "maybe_null_fail_dispatch",
+};
diff --git a/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c b/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c
new file mode 100644
index 000000000000..3c1740028e3b
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+u64 vtime_test;
+
+void BPF_STRUCT_OPS(maybe_null_running, struct task_struct *p)
+{}
+
+bool BPF_STRUCT_OPS(maybe_null_fail_yield, struct task_struct *from,
+		    struct task_struct *to)
+{
+	bpf_printk("Yielding to %s[%d]", to->comm, to->pid);
+
+	return false;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops maybe_null_fail = {
+	.yield			= maybe_null_fail_yield,
+	.enable			= maybe_null_running,
+	.name			= "maybe_null_fail_yield",
+};
diff --git a/tools/testing/selftests/sched_ext/minimal.bpf.c b/tools/testing/selftests/sched_ext/minimal.bpf.c
new file mode 100644
index 000000000000..6a7eccef0104
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/minimal.bpf.c
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A completely minimal scheduler.
+ *
+ * This scheduler defines the absolute minimal set of struct sched_ext_ops
+ * fields: its name. It should _not_ fail to be loaded, and can be used to
+ * exercise the default scheduling paths in ext.c.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC(".struct_ops.link")
+struct sched_ext_ops minimal_ops = {
+	.name			= "minimal",
+};
diff --git a/tools/testing/selftests/sched_ext/minimal.c b/tools/testing/selftests/sched_ext/minimal.c
new file mode 100644
index 000000000000..6c5db8ebbf8a
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/minimal.c
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "minimal.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct minimal *skel;
+
+	skel = minimal__open_and_load();
+	if (!skel) {
+		SCX_ERR("Failed to open and load skel");
+		return SCX_TEST_FAIL;
+	}
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct minimal *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.minimal_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		return SCX_TEST_FAIL;
+	}
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct minimal *skel = ctx;
+
+	minimal__destroy(skel);
+}
+
+struct scx_test minimal = {
+	.name = "minimal",
+	.description = "Verify we can load a fully minimal scheduler",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&minimal)
diff --git a/tools/testing/selftests/sched_ext/prog_run.bpf.c b/tools/testing/selftests/sched_ext/prog_run.bpf.c
new file mode 100644
index 000000000000..fd2c8f12af16
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/prog_run.bpf.c
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates that we can invoke sched_ext kfuncs in
+ * BPF_PROG_TYPE_SYSCALL programs.
+ *
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+
+#include <scx/common.bpf.h>
+
+UEI_DEFINE(uei);
+
+char _license[] SEC("license") = "GPL";
+
+SEC("syscall")
+int BPF_PROG(prog_run_syscall)
+{
+	scx_bpf_exit(0xdeadbeef, "Exited from PROG_RUN");
+	return 0;
+}
+
+void BPF_STRUCT_OPS(prog_run_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops prog_run_ops = {
+	.exit			= prog_run_exit,
+	.name			= "prog_run",
+};
diff --git a/tools/testing/selftests/sched_ext/prog_run.c b/tools/testing/selftests/sched_ext/prog_run.c
new file mode 100644
index 000000000000..3cd57ef8daaa
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/prog_run.c
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <sched.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "prog_run.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct prog_run *skel;
+
+	skel = prog_run__open_and_load();
+	if (!skel) {
+		SCX_ERR("Failed to open and load skel");
+		return SCX_TEST_FAIL;
+	}
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct prog_run *skel = ctx;
+	struct bpf_link *link;
+	int prog_fd, err = 0;
+
+	prog_fd = bpf_program__fd(skel->progs.prog_run_syscall);
+	if (prog_fd < 0) {
+		SCX_ERR("Failed to get BPF_PROG_RUN prog");
+		return SCX_TEST_FAIL;
+	}
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	link = bpf_map__attach_struct_ops(skel->maps.prog_run_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		close(prog_fd);
+		return SCX_TEST_FAIL;
+	}
+
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	SCX_EQ(err, 0);
+
+	/* Assumes uei.kind is written last */
+	while (skel->data->uei.kind == EXIT_KIND(SCX_EXIT_NONE))
+		sched_yield();
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG_BPF));
+	SCX_EQ(skel->data->uei.exit_code, 0xdeadbeef);
+	close(prog_fd);
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct prog_run *skel = ctx;
+
+	prog_run__destroy(skel);
+}
+
+struct scx_test prog_run = {
+	.name = "prog_run",
+	.description = "Verify we can call into a scheduler with BPF_PROG_RUN, and invoke kfuncs",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&prog_run)
diff --git a/tools/testing/selftests/sched_ext/reload_loop.c b/tools/testing/selftests/sched_ext/reload_loop.c
new file mode 100644
index 000000000000..5cfba2d6e056
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/reload_loop.c
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <pthread.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "maximal.bpf.skel.h"
+#include "scx_test.h"
+
+static struct maximal *skel;
+static pthread_t threads[2];
+
+bool force_exit = false;
+
+static enum scx_test_status setup(void **ctx)
+{
+	skel = maximal__open_and_load();
+	if (!skel) {
+		SCX_ERR("Failed to open and load skel");
+		return SCX_TEST_FAIL;
+	}
+
+	return SCX_TEST_PASS;
+}
+
+static void *do_reload_loop(void *arg)
+{
+	u32 i;
+
+	for (i = 0; i < 1024 && !force_exit; i++) {
+		struct bpf_link *link;
+
+		link = bpf_map__attach_struct_ops(skel->maps.maximal_ops);
+		if (link)
+			bpf_link__destroy(link);
+	}
+
+	return NULL;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	int err;
+	void *ret;
+
+	err = pthread_create(&threads[0], NULL, do_reload_loop, NULL);
+	SCX_FAIL_IF(err, "Failed to create thread 0");
+
+	err = pthread_create(&threads[1], NULL, do_reload_loop, NULL);
+	SCX_FAIL_IF(err, "Failed to create thread 1");
+
+	SCX_FAIL_IF(pthread_join(threads[0], &ret), "thread 0 failed");
+	SCX_FAIL_IF(pthread_join(threads[1], &ret), "thread 1 failed");
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	force_exit = true;
+	maximal__destroy(skel);
+}
+
+struct scx_test reload_loop = {
+	.name = "reload_loop",
+	.description = "Stress test loading and unloading schedulers repeatedly in a tight loop",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&reload_loop)
diff --git a/tools/testing/selftests/sched_ext/runner.c b/tools/testing/selftests/sched_ext/runner.c
new file mode 100644
index 000000000000..eab48c7ff309
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/runner.c
@@ -0,0 +1,201 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <signal.h>
+#include <libgen.h>
+#include <bpf/bpf.h>
+#include "scx_test.h"
+
+const char help_fmt[] =
+"The runner for sched_ext tests.\n"
+"\n"
+"The runner is statically linked against all testcases, and runs them all serially.\n"
+"It's required for the testcases to be serial, as only a single host-wide sched_ext\n"
+"scheduler may be loaded at any given time."
+"\n"
+"Usage: %s [-t TEST] [-h]\n"
+"\n"
+"  -t TEST       Only run tests whose name includes this string\n"
+"  -s            Include print output for skipped tests\n"
+"  -q            Don't print the test descriptions during run\n"
+"  -h            Display this help and exit\n";
+
+static volatile int exit_req;
+static bool quiet, print_skipped;
+
+#define MAX_SCX_TESTS 2048
+
+static struct scx_test __scx_tests[MAX_SCX_TESTS];
+static unsigned __scx_num_tests = 0;
+
+static void sigint_handler(int simple)
+{
+	exit_req = 1;
+}
+
+static void print_test_preamble(const struct scx_test *test, bool quiet)
+{
+	printf("===== START =====\n");
+	printf("TEST: %s\n", test->name);
+	if (!quiet)
+		printf("DESCRIPTION: %s\n", test->description);
+	printf("OUTPUT:\n");
+}
+
+static const char *status_to_result(enum scx_test_status status)
+{
+	switch (status) {
+	case SCX_TEST_PASS:
+	case SCX_TEST_SKIP:
+		return "ok";
+	case SCX_TEST_FAIL:
+		return "not ok";
+	default:
+		return "<UNKNOWN>";
+	}
+}
+
+static void print_test_result(const struct scx_test *test,
+			      enum scx_test_status status,
+			      unsigned int testnum)
+{
+	const char *result = status_to_result(status);
+	const char *directive = status == SCX_TEST_SKIP ? "SKIP " : "";
+
+	printf("%s %u %s # %s\n", result, testnum, test->name, directive);
+	printf("=====  END  =====\n");
+}
+
+static bool should_skip_test(const struct scx_test *test, const char * filter)
+{
+	return !strstr(test->name, filter);
+}
+
+static enum scx_test_status run_test(const struct scx_test *test)
+{
+	enum scx_test_status status;
+	void *context = NULL;
+
+	if (test->setup) {
+		status = test->setup(&context);
+		if (status != SCX_TEST_PASS)
+			return status;
+	}
+
+	status = test->run(context);
+
+	if (test->cleanup)
+		test->cleanup(context);
+
+	return status;
+}
+
+static bool test_valid(const struct scx_test *test)
+{
+	if (!test) {
+		fprintf(stderr, "NULL test detected\n");
+		return false;
+	}
+
+	if (!test->name) {
+		fprintf(stderr,
+			"Test with no name found. Must specify test name.\n");
+		return false;
+	}
+
+	if (!test->description) {
+		fprintf(stderr, "Test %s requires description.\n", test->name);
+		return false;
+	}
+
+	if (!test->run) {
+		fprintf(stderr, "Test %s has no run() callback\n", test->name);
+		return false;
+	}
+
+	return true;
+}
+
+int main(int argc, char **argv)
+{
+	const char *filter = NULL;
+	unsigned testnum = 0, i;
+	unsigned passed = 0, skipped = 0, failed = 0;
+	int opt;
+
+	signal(SIGINT, sigint_handler);
+	signal(SIGTERM, sigint_handler);
+
+	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+
+	while ((opt = getopt(argc, argv, "qst:h")) != -1) {
+		switch (opt) {
+		case 'q':
+			quiet = true;
+			break;
+		case 's':
+			print_skipped = true;
+			break;
+		case 't':
+			filter = optarg;
+			break;
+		default:
+			fprintf(stderr, help_fmt, basename(argv[0]));
+			return opt != 'h';
+		}
+	}
+
+	for (i = 0; i < __scx_num_tests; i++) {
+		enum scx_test_status status;
+		struct scx_test *test = &__scx_tests[i];
+
+		if (filter && should_skip_test(test, filter)) {
+			/*
+			 * Printing the skipped tests and their preambles can
+			 * add a lot of noise to the runner output. Printing
+			 * this is only really useful for CI, so let's skip it
+			 * by default.
+			 */
+			if (print_skipped) {
+				print_test_preamble(test, quiet);
+				print_test_result(test, SCX_TEST_SKIP, ++testnum);
+			}
+			continue;
+		}
+
+		print_test_preamble(test, quiet);
+		status = run_test(test);
+		print_test_result(test, status, ++testnum);
+		switch (status) {
+		case SCX_TEST_PASS:
+			passed++;
+			break;
+		case SCX_TEST_SKIP:
+			skipped++;
+			break;
+		case SCX_TEST_FAIL:
+			failed++;
+			break;
+		}
+	}
+	printf("\n\n=============================\n\n");
+	printf("RESULTS:\n\n");
+	printf("PASSED:  %u\n", passed);
+	printf("SKIPPED: %u\n", skipped);
+	printf("FAILED:  %u\n", failed);
+
+	return 0;
+}
+
+void scx_test_register(struct scx_test *test)
+{
+	SCX_BUG_ON(!test_valid(test), "Invalid test found");
+	SCX_BUG_ON(__scx_num_tests >= MAX_SCX_TESTS, "Maximum tests exceeded");
+
+	__scx_tests[__scx_num_tests++] = *test;
+}
diff --git a/tools/testing/selftests/sched_ext/scx_test.h b/tools/testing/selftests/sched_ext/scx_test.h
new file mode 100644
index 000000000000..90b8d6915bb7
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/scx_test.h
@@ -0,0 +1,131 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ */
+
+#ifndef __SCX_TEST_H__
+#define __SCX_TEST_H__
+
+#include <errno.h>
+#include <scx/common.h>
+#include <scx/compat.h>
+
+enum scx_test_status {
+	SCX_TEST_PASS = 0,
+	SCX_TEST_SKIP,
+	SCX_TEST_FAIL,
+};
+
+#define EXIT_KIND(__ent) __COMPAT_ENUM_OR_ZERO("scx_exit_kind", #__ent)
+
+struct scx_test {
+	/**
+	 * name - The name of the testcase.
+	 */
+	const char *name;
+
+	/**
+	 * description - A description of your testcase: what it tests and is
+	 * meant to validate.
+	 */
+	const char *description;
+
+	/*
+	 * setup - Setup the test.
+	 * @ctx: A pointer to a context object that will be passed to run and
+	 *	 cleanup.
+	 *
+	 * An optional callback that allows a testcase to perform setup for its
+	 * run. A test may return SCX_TEST_SKIP to skip the run.
+	 */
+	enum scx_test_status (*setup)(void **ctx);
+
+	/*
+	 * run - Run the test.
+	 * @ctx: Context set in the setup() callback. If @ctx was not set in
+	 *	 setup(), it is NULL.
+	 *
+	 * The main test. Callers should return one of:
+	 *
+	 * - SCX_TEST_PASS: Test passed
+	 * - SCX_TEST_SKIP: Test should be skipped
+	 * - SCX_TEST_FAIL: Test failed
+	 *
+	 * This callback must be defined.
+	 */
+	enum scx_test_status (*run)(void *ctx);
+
+	/*
+	 * cleanup - Perform cleanup following the test
+	 * @ctx: Context set in the setup() callback. If @ctx was not set in
+	 *	 setup(), it is NULL.
+	 *
+	 * An optional callback that allows a test to perform cleanup after
+	 * being run. This callback is run even if the run() callback returns
+	 * SCX_TEST_SKIP or SCX_TEST_FAIL. It is not run if setup() returns
+	 * SCX_TEST_SKIP or SCX_TEST_FAIL.
+	 */
+	void (*cleanup)(void *ctx);
+};
+
+void scx_test_register(struct scx_test *test);
+
+#define REGISTER_SCX_TEST(__test)			\
+	__attribute__((constructor))			\
+	static void ___scxregister##__LINE__(void)	\
+	{						\
+		scx_test_register(__test);		\
+	}
+
+#define SCX_ERR(__fmt, ...)						\
+	do {								\
+		fprintf(stderr, "ERR: %s:%d\n", __FILE__, __LINE__);	\
+		fprintf(stderr, __fmt"\n", ##__VA_ARGS__);			\
+	} while (0)
+
+#define SCX_FAIL(__fmt, ...)						\
+	do {								\
+		SCX_ERR(__fmt, ##__VA_ARGS__);				\
+		return SCX_TEST_FAIL;					\
+	} while (0)
+
+#define SCX_FAIL_IF(__cond, __fmt, ...)					\
+	do {								\
+		if (__cond)						\
+			SCX_FAIL(__fmt, ##__VA_ARGS__);			\
+	} while (0)
+
+#define SCX_GT(_x, _y) SCX_FAIL_IF((_x) <= (_y), "Expected %s > %s (%lu > %lu)",	\
+				   #_x, #_y, (u64)(_x), (u64)(_y))
+#define SCX_GE(_x, _y) SCX_FAIL_IF((_x) < (_y), "Expected %s >= %s (%lu >= %lu)",	\
+				   #_x, #_y, (u64)(_x), (u64)(_y))
+#define SCX_LT(_x, _y) SCX_FAIL_IF((_x) >= (_y), "Expected %s < %s (%lu < %lu)",	\
+				   #_x, #_y, (u64)(_x), (u64)(_y))
+#define SCX_LE(_x, _y) SCX_FAIL_IF((_x) > (_y), "Expected %s <= %s (%lu <= %lu)",	\
+				   #_x, #_y, (u64)(_x), (u64)(_y))
+#define SCX_EQ(_x, _y) SCX_FAIL_IF((_x) != (_y), "Expected %s == %s (%lu == %lu)",	\
+				   #_x, #_y, (u64)(_x), (u64)(_y))
+#define SCX_ASSERT(_x) SCX_FAIL_IF(!(_x), "Expected %s to be true (%lu)",		\
+				   #_x, (u64)(_x))
+
+#define SCX_ECODE_VAL(__ecode) ({						\
+        u64 __val = 0;								\
+	bool __found = false;							\
+										\
+	__found = __COMPAT_read_enum("scx_exit_code", #__ecode, &__val);	\
+	SCX_ASSERT(__found);							\
+	(s64)__val;								\
+})
+
+#define SCX_KIND_VAL(__kind) ({							\
+        u64 __val = 0;								\
+	bool __found = false;							\
+										\
+	__found = __COMPAT_read_enum("scx_exit_kind", #__kind, &__val);		\
+	SCX_ASSERT(__found);							\
+	__val;									\
+})
+
+#endif  // # __SCX_TEST_H__
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
new file mode 100644
index 000000000000..2ed2991afafe
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates the behavior of direct dispatching with a default
+ * select_cpu implementation.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+bool saw_local = false;
+
+static bool task_is_test(const struct task_struct *p)
+{
+	return !bpf_strncmp(p->comm, 9, "select_cpu");
+}
+
+void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p,
+		    u64 enq_flags)
+{
+	const struct cpumask *idle_mask = scx_bpf_get_idle_cpumask();
+
+	if (task_is_test(p) &&
+	    bpf_cpumask_test_cpu(scx_bpf_task_cpu(p), idle_mask)) {
+		saw_local = true;
+	}
+	scx_bpf_put_idle_cpumask(idle_mask);
+
+	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops select_cpu_dfl_ops = {
+	.enqueue		= select_cpu_dfl_enqueue,
+	.name			= "select_cpu_dfl",
+};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.c
new file mode 100644
index 000000000000..a53a40c2d2f0
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.c
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "select_cpu_dfl.bpf.skel.h"
+#include "scx_test.h"
+
+#define NUM_CHILDREN 1028
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct select_cpu_dfl *skel;
+
+	skel = select_cpu_dfl__open_and_load();
+	SCX_FAIL_IF(!skel, "Failed to open and load skel");
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct select_cpu_dfl *skel = ctx;
+	struct bpf_link *link;
+	pid_t pids[NUM_CHILDREN];
+	int i, status;
+
+	link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dfl_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	for (i = 0; i < NUM_CHILDREN; i++) {
+		pids[i] = fork();
+		if (pids[i] == 0) {
+			sleep(1);
+			exit(0);
+		}
+	}
+
+	for (i = 0; i < NUM_CHILDREN; i++) {
+		SCX_EQ(waitpid(pids[i], &status, 0), pids[i]);
+		SCX_EQ(status, 0);
+	}
+
+	SCX_ASSERT(!skel->bss->saw_local);
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct select_cpu_dfl *skel = ctx;
+
+	select_cpu_dfl__destroy(skel);
+}
+
+struct scx_test select_cpu_dfl = {
+	.name = "select_cpu_dfl",
+	.description = "Verify the default ops.select_cpu() dispatches tasks "
+		       "when idles cores are found, and skips ops.enqueue()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&select_cpu_dfl)
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
new file mode 100644
index 000000000000..4bb5abb2d369
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates the behavior of direct dispatching with a default
+ * select_cpu implementation, and with the SCX_OPS_ENQ_DFL_NO_DISPATCH ops flag
+ * specified.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+bool saw_local = false;
+
+/* Per-task scheduling context */
+struct task_ctx {
+	bool	force_local;	/* CPU changed by ops.select_cpu() */
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct task_ctx);
+} task_ctx_stor SEC(".maps");
+
+/* Manually specify the signature until the kfunc is added to the scx repo. */
+s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
+			   bool *found) __ksym;
+
+s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	struct task_ctx *tctx;
+	s32 cpu;
+
+	tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0);
+	if (!tctx) {
+		scx_bpf_error("task_ctx lookup failed");
+		return -ESRCH;
+	}
+
+	cpu = scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags,
+				     &tctx->force_local);
+
+	return cpu;
+}
+
+void BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_enqueue, struct task_struct *p,
+		    u64 enq_flags)
+{
+	u64 dsq_id = SCX_DSQ_GLOBAL;
+	struct task_ctx *tctx;
+
+	tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0);
+	if (!tctx) {
+		scx_bpf_error("task_ctx lookup failed");
+		return;
+	}
+
+	if (tctx->force_local) {
+		dsq_id = SCX_DSQ_LOCAL;
+		tctx->force_local = false;
+		saw_local = true;
+	}
+
+	scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, enq_flags);
+}
+
+s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task,
+		   struct task_struct *p, struct scx_init_task_args *args)
+{
+	if (bpf_task_storage_get(&task_ctx_stor, p, 0,
+				 BPF_LOCAL_STORAGE_GET_F_CREATE))
+		return 0;
+	else
+		return -ENOMEM;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops select_cpu_dfl_nodispatch_ops = {
+	.select_cpu		= select_cpu_dfl_nodispatch_select_cpu,
+	.enqueue		= select_cpu_dfl_nodispatch_enqueue,
+	.init_task		= select_cpu_dfl_nodispatch_init_task,
+	.name			= "select_cpu_dfl_nodispatch",
+};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c
new file mode 100644
index 000000000000..1d85bf4bf3a3
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "select_cpu_dfl_nodispatch.bpf.skel.h"
+#include "scx_test.h"
+
+#define NUM_CHILDREN 1028
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct select_cpu_dfl_nodispatch *skel;
+
+	skel = select_cpu_dfl_nodispatch__open_and_load();
+	SCX_FAIL_IF(!skel, "Failed to open and load skel");
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct select_cpu_dfl_nodispatch *skel = ctx;
+	struct bpf_link *link;
+	pid_t pids[NUM_CHILDREN];
+	int i, status;
+
+	link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dfl_nodispatch_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	for (i = 0; i < NUM_CHILDREN; i++) {
+		pids[i] = fork();
+		if (pids[i] == 0) {
+			sleep(1);
+			exit(0);
+		}
+	}
+
+	for (i = 0; i < NUM_CHILDREN; i++) {
+		SCX_EQ(waitpid(pids[i], &status, 0), pids[i]);
+		SCX_EQ(status, 0);
+	}
+
+	SCX_ASSERT(skel->bss->saw_local);
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct select_cpu_dfl_nodispatch *skel = ctx;
+
+	select_cpu_dfl_nodispatch__destroy(skel);
+}
+
+struct scx_test select_cpu_dfl_nodispatch = {
+	.name = "select_cpu_dfl_nodispatch",
+	.description = "Verify behavior of scx_bpf_select_cpu_dfl() in "
+		       "ops.select_cpu()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&select_cpu_dfl_nodispatch)
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
new file mode 100644
index 000000000000..f0b96a4a04b2
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates the behavior of direct dispatching with a default
+ * select_cpu implementation.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	u64 dsq_id = SCX_DSQ_LOCAL;
+	s32 cpu = prev_cpu;
+
+	if (scx_bpf_test_and_clear_cpu_idle(cpu))
+		goto dispatch;
+
+	cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
+	if (cpu >= 0)
+		goto dispatch;
+
+	dsq_id = SCX_DSQ_GLOBAL;
+	cpu = prev_cpu;
+
+dispatch:
+	scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, 0);
+	return cpu;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops select_cpu_dispatch_ops = {
+	.select_cpu		= select_cpu_dispatch_select_cpu,
+	.name			= "select_cpu_dispatch",
+	.timeout_ms		= 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.c
new file mode 100644
index 000000000000..0309ca8785b3
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.c
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "select_cpu_dispatch.bpf.skel.h"
+#include "scx_test.h"
+
+#define NUM_CHILDREN 1028
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct select_cpu_dispatch *skel;
+
+	skel = select_cpu_dispatch__open_and_load();
+	SCX_FAIL_IF(!skel, "Failed to open and load skel");
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct select_cpu_dispatch *skel = ctx;
+	struct bpf_link *link;
+	pid_t pids[NUM_CHILDREN];
+	int i, status;
+
+	link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dispatch_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	for (i = 0; i < NUM_CHILDREN; i++) {
+		pids[i] = fork();
+		if (pids[i] == 0) {
+			sleep(1);
+			exit(0);
+		}
+	}
+
+	for (i = 0; i < NUM_CHILDREN; i++) {
+		SCX_EQ(waitpid(pids[i], &status, 0), pids[i]);
+		SCX_EQ(status, 0);
+	}
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct select_cpu_dispatch *skel = ctx;
+
+	select_cpu_dispatch__destroy(skel);
+}
+
+struct scx_test select_cpu_dispatch = {
+	.name = "select_cpu_dispatch",
+	.description = "Test direct dispatching to built-in DSQs from "
+		       "ops.select_cpu()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&select_cpu_dispatch)
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
new file mode 100644
index 000000000000..7b42ddce0f56
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates the behavior of direct dispatching with a default
+ * select_cpu implementation.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+s32 BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	/* Dispatching to a random DSQ should fail. */
+	scx_bpf_dispatch(p, 0xcafef00d, SCX_SLICE_DFL, 0);
+
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops select_cpu_dispatch_bad_dsq_ops = {
+	.select_cpu		= select_cpu_dispatch_bad_dsq_select_cpu,
+	.exit			= select_cpu_dispatch_bad_dsq_exit,
+	.name			= "select_cpu_dispatch_bad_dsq",
+	.timeout_ms		= 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c
new file mode 100644
index 000000000000..47eb6ed7627d
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "select_cpu_dispatch_bad_dsq.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct select_cpu_dispatch_bad_dsq *skel;
+
+	skel = select_cpu_dispatch_bad_dsq__open_and_load();
+	SCX_FAIL_IF(!skel, "Failed to open and load skel");
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct select_cpu_dispatch_bad_dsq *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dispatch_bad_dsq_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	sleep(1);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR));
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct select_cpu_dispatch_bad_dsq *skel = ctx;
+
+	select_cpu_dispatch_bad_dsq__destroy(skel);
+}
+
+struct scx_test select_cpu_dispatch_bad_dsq = {
+	.name = "select_cpu_dispatch_bad_dsq",
+	.description = "Verify graceful failure if we direct-dispatch to a "
+		       "bogus DSQ in ops.select_cpu()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&select_cpu_dispatch_bad_dsq)
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
new file mode 100644
index 000000000000..653e3dc0b4dc
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates the behavior of direct dispatching with a default
+ * select_cpu implementation.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+s32 BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	/* Dispatching twice in a row is disallowed. */
+	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops select_cpu_dispatch_dbl_dsp_ops = {
+	.select_cpu		= select_cpu_dispatch_dbl_dsp_select_cpu,
+	.exit			= select_cpu_dispatch_dbl_dsp_exit,
+	.name			= "select_cpu_dispatch_dbl_dsp",
+	.timeout_ms		= 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c
new file mode 100644
index 000000000000..48ff028a3c46
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "select_cpu_dispatch_dbl_dsp.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct select_cpu_dispatch_dbl_dsp *skel;
+
+	skel = select_cpu_dispatch_dbl_dsp__open_and_load();
+	SCX_FAIL_IF(!skel, "Failed to open and load skel");
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct select_cpu_dispatch_dbl_dsp *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dispatch_dbl_dsp_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	sleep(1);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR));
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct select_cpu_dispatch_dbl_dsp *skel = ctx;
+
+	select_cpu_dispatch_dbl_dsp__destroy(skel);
+}
+
+struct scx_test select_cpu_dispatch_dbl_dsp = {
+	.name = "select_cpu_dispatch_dbl_dsp",
+	.description = "Verify graceful failure if we dispatch twice to a "
+		       "DSQ in ops.select_cpu()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&select_cpu_dispatch_dbl_dsp)
diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
new file mode 100644
index 000000000000..7f3ebf4fc2ea
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates that enqueue flags are properly stored and
+ * applied at dispatch time when a task is directly dispatched from
+ * ops.select_cpu(). We validate this by using scx_bpf_dispatch_vtime(), and
+ * making the test a very basic vtime scheduler.
+ *
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+volatile bool consumed;
+
+static u64 vtime_now;
+
+#define VTIME_DSQ 0
+
+static inline bool vtime_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}
+
+static inline u64 task_vtime(const struct task_struct *p)
+{
+	u64 vtime = p->scx.dsq_vtime;
+
+	if (vtime_before(vtime, vtime_now - SCX_SLICE_DFL))
+		return vtime_now - SCX_SLICE_DFL;
+	else
+		return vtime;
+}
+
+s32 BPF_STRUCT_OPS(select_cpu_vtime_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	s32 cpu;
+
+	cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
+	if (cpu >= 0)
+		goto ddsp;
+
+	cpu = prev_cpu;
+	scx_bpf_test_and_clear_cpu_idle(cpu);
+ddsp:
+	scx_bpf_dispatch_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0);
+	return cpu;
+}
+
+void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p)
+{
+	if (scx_bpf_consume(VTIME_DSQ))
+		consumed = true;
+}
+
+void BPF_STRUCT_OPS(select_cpu_vtime_running, struct task_struct *p)
+{
+	if (vtime_before(vtime_now, p->scx.dsq_vtime))
+		vtime_now = p->scx.dsq_vtime;
+}
+
+void BPF_STRUCT_OPS(select_cpu_vtime_stopping, struct task_struct *p,
+		    bool runnable)
+{
+	p->scx.dsq_vtime += (SCX_SLICE_DFL - p->scx.slice) * 100 / p->scx.weight;
+}
+
+void BPF_STRUCT_OPS(select_cpu_vtime_enable, struct task_struct *p)
+{
+	p->scx.dsq_vtime = vtime_now;
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(select_cpu_vtime_init)
+{
+	return scx_bpf_create_dsq(VTIME_DSQ, -1);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops select_cpu_vtime_ops = {
+	.select_cpu		= select_cpu_vtime_select_cpu,
+	.dispatch		= select_cpu_vtime_dispatch,
+	.running		= select_cpu_vtime_running,
+	.stopping		= select_cpu_vtime_stopping,
+	.enable			= select_cpu_vtime_enable,
+	.init			= select_cpu_vtime_init,
+	.name			= "select_cpu_vtime",
+	.timeout_ms		= 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.c
new file mode 100644
index 000000000000..b4629c2364f5
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.c
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "select_cpu_vtime.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct select_cpu_vtime *skel;
+
+	skel = select_cpu_vtime__open_and_load();
+	SCX_FAIL_IF(!skel, "Failed to open and load skel");
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct select_cpu_vtime *skel = ctx;
+	struct bpf_link *link;
+
+	SCX_ASSERT(!skel->bss->consumed);
+
+	link = bpf_map__attach_struct_ops(skel->maps.select_cpu_vtime_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	sleep(1);
+
+	SCX_ASSERT(skel->bss->consumed);
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct select_cpu_vtime *skel = ctx;
+
+	select_cpu_vtime__destroy(skel);
+}
+
+struct scx_test select_cpu_vtime = {
+	.name = "select_cpu_vtime",
+	.description = "Test doing direct vtime-dispatching from "
+		       "ops.select_cpu(), to a non-built-in DSQ",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&select_cpu_vtime)
diff --git a/tools/testing/selftests/sched_ext/test_example.c b/tools/testing/selftests/sched_ext/test_example.c
new file mode 100644
index 000000000000..ce36cdf03cdc
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/test_example.c
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include "scx_test.h"
+
+static bool setup_called = false;
+static bool run_called = false;
+static bool cleanup_called = false;
+
+static int context = 10;
+
+static enum scx_test_status setup(void **ctx)
+{
+	setup_called = true;
+	*ctx = &context;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	int *arg = ctx;
+
+	SCX_ASSERT(setup_called);
+	SCX_ASSERT(!run_called && !cleanup_called);
+	SCX_EQ(*arg, context);
+
+	run_called = true;
+	return SCX_TEST_PASS;
+}
+
+static void cleanup (void *ctx)
+{
+	SCX_BUG_ON(!run_called || cleanup_called, "Wrong callbacks invoked");
+}
+
+struct scx_test example = {
+	.name		= "example",
+	.description	= "Validate the basic function of the test suite itself",
+	.setup		= setup,
+	.run		= run,
+	.cleanup	= cleanup,
+};
+REGISTER_SCX_TEST(&example)
diff --git a/tools/testing/selftests/sched_ext/util.c b/tools/testing/selftests/sched_ext/util.c
new file mode 100644
index 000000000000..e47769c91918
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/util.c
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+/* Returns read len on success, or -errno on failure. */
+static ssize_t read_text(const char *path, char *buf, size_t max_len)
+{
+	ssize_t len;
+	int fd;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return -errno;
+
+	len = read(fd, buf, max_len - 1);
+
+	if (len >= 0)
+		buf[len] = 0;
+
+	close(fd);
+	return len < 0 ? -errno : len;
+}
+
+/* Returns written len on success, or -errno on failure. */
+static ssize_t write_text(const char *path, char *buf, ssize_t len)
+{
+	int fd;
+	ssize_t written;
+
+	fd = open(path, O_WRONLY | O_APPEND);
+	if (fd < 0)
+		return -errno;
+
+	written = write(fd, buf, len);
+	close(fd);
+	return written < 0 ? -errno : written;
+}
+
+long file_read_long(const char *path)
+{
+	char buf[128];
+
+
+	if (read_text(path, buf, sizeof(buf)) <= 0)
+		return -1;
+
+	return atol(buf);
+}
+
+int file_write_long(const char *path, long val)
+{
+	char buf[64];
+	int ret;
+
+	ret = sprintf(buf, "%lu", val);
+	if (ret < 0)
+		return ret;
+
+	if (write_text(path, buf, sizeof(buf)) <= 0)
+		return -1;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/sched_ext/util.h b/tools/testing/selftests/sched_ext/util.h
new file mode 100644
index 000000000000..bc13dfec1267
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/util.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <void@manifault.com>
+ */
+
+#ifndef __SCX_TEST_UTIL_H__
+#define __SCX_TEST_UTIL_H__
+
+long file_read_long(const char *path);
+int file_write_long(const char *path, long val);
+
+#endif // __SCX_TEST_H__