summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu/resctrl/rdtgroup.c
blob: 011e17efb1a66e5b003fee07b53c13633f9f0f58 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * User interface for Resource Allocation in Resource Director Technology(RDT)
 *
 * Copyright (C) 2016 Intel Corporation
 *
 * Author: Fenghua Yu <fenghua.yu@intel.com>
 *
 * More information about RDT be found in the Intel (R) x86 Architecture
 * Software Developer Manual.
 */

#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt

#include <linux/cacheinfo.h>
#include <linux/cpu.h>
#include <linux/debugfs.h>
#include <linux/fs.h>
#include <linux/fs_parser.h>
#include <linux/sysfs.h>
#include <linux/kernfs.h>
#include <linux/seq_buf.h>
#include <linux/seq_file.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/slab.h>
#include <linux/task_work.h>
#include <linux/user_namespace.h>

#include <uapi/linux/magic.h>

#include <asm/resctrl.h>
#include "internal.h"

DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key);

/* Mutex to protect rdtgroup access. */
DEFINE_MUTEX(rdtgroup_mutex);

static struct kernfs_root *rdt_root;
struct rdtgroup rdtgroup_default;
LIST_HEAD(rdt_all_groups);

/* list of entries for the schemata file */
LIST_HEAD(resctrl_schema_all);

/* The filesystem can only be mounted once. */
bool resctrl_mounted;

/* Kernel fs node for "info" directory under root */
static struct kernfs_node *kn_info;

/* Kernel fs node for "mon_groups" directory under root */
static struct kernfs_node *kn_mongrp;

/* Kernel fs node for "mon_data" directory under root */
static struct kernfs_node *kn_mondata;

static struct seq_buf last_cmd_status;
static char last_cmd_status_buf[512];

static int rdtgroup_setup_root(struct rdt_fs_context *ctx);
static void rdtgroup_destroy_root(void);

struct dentry *debugfs_resctrl;

static bool resctrl_debug;

void rdt_last_cmd_clear(void)
{
	lockdep_assert_held(&rdtgroup_mutex);
	seq_buf_clear(&last_cmd_status);
}

void rdt_last_cmd_puts(const char *s)
{
	lockdep_assert_held(&rdtgroup_mutex);
	seq_buf_puts(&last_cmd_status, s);
}

void rdt_last_cmd_printf(const char *fmt, ...)
{
	va_list ap;

	va_start(ap, fmt);
	lockdep_assert_held(&rdtgroup_mutex);
	seq_buf_vprintf(&last_cmd_status, fmt, ap);
	va_end(ap);
}

void rdt_staged_configs_clear(void)
{
	struct rdt_resource *r;
	struct rdt_domain *dom;

	lockdep_assert_held(&rdtgroup_mutex);

	for_each_alloc_capable_rdt_resource(r) {
		list_for_each_entry(dom, &r->domains, list)
			memset(dom->staged_config, 0, sizeof(dom->staged_config));
	}
}

/*
 * Trivial allocator for CLOSIDs. Since h/w only supports a small number,
 * we can keep a bitmap of free CLOSIDs in a single integer.
 *
 * Using a global CLOSID across all resources has some advantages and
 * some drawbacks:
 * + We can simply set current's closid to assign a task to a resource
 *   group.
 * + Context switch code can avoid extra memory references deciding which
 *   CLOSID to load into the PQR_ASSOC MSR
 * - We give up some options in configuring resource groups across multi-socket
 *   systems.
 * - Our choices on how to configure each resource become progressively more
 *   limited as the number of resources grows.
 */
static unsigned long closid_free_map;
static int closid_free_map_len;

int closids_supported(void)
{
	return closid_free_map_len;
}

static void closid_init(void)
{
	struct resctrl_schema *s;
	u32 rdt_min_closid = 32;

	/* Compute rdt_min_closid across all resources */
	list_for_each_entry(s, &resctrl_schema_all, list)
		rdt_min_closid = min(rdt_min_closid, s->num_closid);

	closid_free_map = BIT_MASK(rdt_min_closid) - 1;

	/* RESCTRL_RESERVED_CLOSID is always reserved for the default group */
	__clear_bit(RESCTRL_RESERVED_CLOSID, &closid_free_map);
	closid_free_map_len = rdt_min_closid;
}

static int closid_alloc(void)
{
	int cleanest_closid;
	u32 closid;

	lockdep_assert_held(&rdtgroup_mutex);

	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
		cleanest_closid = resctrl_find_cleanest_closid();
		if (cleanest_closid < 0)
			return cleanest_closid;
		closid = cleanest_closid;
	} else {
		closid = ffs(closid_free_map);
		if (closid == 0)
			return -ENOSPC;
		closid--;
	}
	__clear_bit(closid, &closid_free_map);

	return closid;
}

void closid_free(int closid)
{
	lockdep_assert_held(&rdtgroup_mutex);

	__set_bit(closid, &closid_free_map);
}

/**
 * closid_allocated - test if provided closid is in use
 * @closid: closid to be tested
 *
 * Return: true if @closid is currently associated with a resource group,
 * false if @closid is free
 */
bool closid_allocated(unsigned int closid)
{
	lockdep_assert_held(&rdtgroup_mutex);

	return !test_bit(closid, &closid_free_map);
}

/**
 * rdtgroup_mode_by_closid - Return mode of resource group with closid
 * @closid: closid if the resource group
 *
 * Each resource group is associated with a @closid. Here the mode
 * of a resource group can be queried by searching for it using its closid.
 *
 * Return: mode as &enum rdtgrp_mode of resource group with closid @closid
 */
enum rdtgrp_mode rdtgroup_mode_by_closid(int closid)
{
	struct rdtgroup *rdtgrp;

	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
		if (rdtgrp->closid == closid)
			return rdtgrp->mode;
	}

	return RDT_NUM_MODES;
}

static const char * const rdt_mode_str[] = {
	[RDT_MODE_SHAREABLE]		= "shareable",
	[RDT_MODE_EXCLUSIVE]		= "exclusive",
	[RDT_MODE_PSEUDO_LOCKSETUP]	= "pseudo-locksetup",
	[RDT_MODE_PSEUDO_LOCKED]	= "pseudo-locked",
};

/**
 * rdtgroup_mode_str - Return the string representation of mode
 * @mode: the resource group mode as &enum rdtgroup_mode
 *
 * Return: string representation of valid mode, "unknown" otherwise
 */
static const char *rdtgroup_mode_str(enum rdtgrp_mode mode)
{
	if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES)
		return "unknown";

	return rdt_mode_str[mode];
}

/* set uid and gid of rdtgroup dirs and files to that of the creator */
static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
{
	struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
				.ia_uid = current_fsuid(),
				.ia_gid = current_fsgid(), };

	if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
	    gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
		return 0;

	return kernfs_setattr(kn, &iattr);
}

static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft)
{
	struct kernfs_node *kn;
	int ret;

	kn = __kernfs_create_file(parent_kn, rft->name, rft->mode,
				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
				  0, rft->kf_ops, rft, NULL, NULL);
	if (IS_ERR(kn))
		return PTR_ERR(kn);

	ret = rdtgroup_kn_set_ugid(kn);
	if (ret) {
		kernfs_remove(kn);
		return ret;
	}

	return 0;
}

static int rdtgroup_seqfile_show(struct seq_file *m, void *arg)
{
	struct kernfs_open_file *of = m->private;
	struct rftype *rft = of->kn->priv;

	if (rft->seq_show)
		return rft->seq_show(of, m, arg);
	return 0;
}

static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf,
				   size_t nbytes, loff_t off)
{
	struct rftype *rft = of->kn->priv;

	if (rft->write)
		return rft->write(of, buf, nbytes, off);

	return -EINVAL;
}

static const struct kernfs_ops rdtgroup_kf_single_ops = {
	.atomic_write_len	= PAGE_SIZE,
	.write			= rdtgroup_file_write,
	.seq_show		= rdtgroup_seqfile_show,
};

static const struct kernfs_ops kf_mondata_ops = {
	.atomic_write_len	= PAGE_SIZE,
	.seq_show		= rdtgroup_mondata_show,
};

static bool is_cpu_list(struct kernfs_open_file *of)
{
	struct rftype *rft = of->kn->priv;

	return rft->flags & RFTYPE_FLAGS_CPUS_LIST;
}

static int rdtgroup_cpus_show(struct kernfs_open_file *of,
			      struct seq_file *s, void *v)
{
	struct rdtgroup *rdtgrp;
	struct cpumask *mask;
	int ret = 0;

	rdtgrp = rdtgroup_kn_lock_live(of->kn);

	if (rdtgrp) {
		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
			if (!rdtgrp->plr->d) {
				rdt_last_cmd_clear();
				rdt_last_cmd_puts("Cache domain offline\n");
				ret = -ENODEV;
			} else {
				mask = &rdtgrp->plr->d->cpu_mask;
				seq_printf(s, is_cpu_list(of) ?
					   "%*pbl\n" : "%*pb\n",
					   cpumask_pr_args(mask));
			}
		} else {
			seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
				   cpumask_pr_args(&rdtgrp->cpu_mask));
		}
	} else {
		ret = -ENOENT;
	}
	rdtgroup_kn_unlock(of->kn);

	return ret;
}

/*
 * This is safe against resctrl_sched_in() called from __switch_to()
 * because __switch_to() is executed with interrupts disabled. A local call
 * from update_closid_rmid() is protected against __switch_to() because
 * preemption is disabled.
 */
static void update_cpu_closid_rmid(void *info)
{
	struct rdtgroup *r = info;

	if (r) {
		this_cpu_write(pqr_state.default_closid, r->closid);
		this_cpu_write(pqr_state.default_rmid, r->mon.rmid);
	}

	/*
	 * We cannot unconditionally write the MSR because the current
	 * executing task might have its own closid selected. Just reuse
	 * the context switch code.
	 */
	resctrl_sched_in(current);
}

/*
 * Update the PGR_ASSOC MSR on all cpus in @cpu_mask,
 *
 * Per task closids/rmids must have been set up before calling this function.
 */
static void
update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r)
{
	on_each_cpu_mask(cpu_mask, update_cpu_closid_rmid, r, 1);
}

static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
			  cpumask_var_t tmpmask)
{
	struct rdtgroup *prgrp = rdtgrp->mon.parent, *crgrp;
	struct list_head *head;

	/* Check whether cpus belong to parent ctrl group */
	cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask);
	if (!cpumask_empty(tmpmask)) {
		rdt_last_cmd_puts("Can only add CPUs to mongroup that belong to parent\n");
		return -EINVAL;
	}

	/* Check whether cpus are dropped from this group */
	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
	if (!cpumask_empty(tmpmask)) {
		/* Give any dropped cpus to parent rdtgroup */
		cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask);
		update_closid_rmid(tmpmask, prgrp);
	}

	/*
	 * If we added cpus, remove them from previous group that owned them
	 * and update per-cpu rmid
	 */
	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
	if (!cpumask_empty(tmpmask)) {
		head = &prgrp->mon.crdtgrp_list;
		list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
			if (crgrp == rdtgrp)
				continue;
			cpumask_andnot(&crgrp->cpu_mask, &crgrp->cpu_mask,
				       tmpmask);
		}
		update_closid_rmid(tmpmask, rdtgrp);
	}

	/* Done pushing/pulling - update this group with new mask */
	cpumask_copy(&rdtgrp->cpu_mask, newmask);

	return 0;
}

static void cpumask_rdtgrp_clear(struct rdtgroup *r, struct cpumask *m)
{
	struct rdtgroup *crgrp;

	cpumask_andnot(&r->cpu_mask, &r->cpu_mask, m);
	/* update the child mon group masks as well*/
	list_for_each_entry(crgrp, &r->mon.crdtgrp_list, mon.crdtgrp_list)
		cpumask_and(&crgrp->cpu_mask, &r->cpu_mask, &crgrp->cpu_mask);
}

static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
			   cpumask_var_t tmpmask, cpumask_var_t tmpmask1)
{
	struct rdtgroup *r, *crgrp;
	struct list_head *head;

	/* Check whether cpus are dropped from this group */
	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
	if (!cpumask_empty(tmpmask)) {
		/* Can't drop from default group */
		if (rdtgrp == &rdtgroup_default) {
			rdt_last_cmd_puts("Can't drop CPUs from default group\n");
			return -EINVAL;
		}

		/* Give any dropped cpus to rdtgroup_default */
		cpumask_or(&rdtgroup_default.cpu_mask,
			   &rdtgroup_default.cpu_mask, tmpmask);
		update_closid_rmid(tmpmask, &rdtgroup_default);
	}

	/*
	 * If we added cpus, remove them from previous group and
	 * the prev group's child groups that owned them
	 * and update per-cpu closid/rmid.
	 */
	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
	if (!cpumask_empty(tmpmask)) {
		list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) {
			if (r == rdtgrp)
				continue;
			cpumask_and(tmpmask1, &r->cpu_mask, tmpmask);
			if (!cpumask_empty(tmpmask1))
				cpumask_rdtgrp_clear(r, tmpmask1);
		}
		update_closid_rmid(tmpmask, rdtgrp);
	}

	/* Done pushing/pulling - update this group with new mask */
	cpumask_copy(&rdtgrp->cpu_mask, newmask);

	/*
	 * Clear child mon group masks since there is a new parent mask
	 * now and update the rmid for the cpus the child lost.
	 */
	head = &rdtgrp->mon.crdtgrp_list;
	list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
		cpumask_and(tmpmask, &rdtgrp->cpu_mask, &crgrp->cpu_mask);
		update_closid_rmid(tmpmask, rdtgrp);
		cpumask_clear(&crgrp->cpu_mask);
	}

	return 0;
}

static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
				   char *buf, size_t nbytes, loff_t off)
{
	cpumask_var_t tmpmask, newmask, tmpmask1;
	struct rdtgroup *rdtgrp;
	int ret;

	if (!buf)
		return -EINVAL;

	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
		return -ENOMEM;
	if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) {
		free_cpumask_var(tmpmask);
		return -ENOMEM;
	}
	if (!zalloc_cpumask_var(&tmpmask1, GFP_KERNEL)) {
		free_cpumask_var(tmpmask);
		free_cpumask_var(newmask);
		return -ENOMEM;
	}

	rdtgrp = rdtgroup_kn_lock_live(of->kn);
	if (!rdtgrp) {
		ret = -ENOENT;
		goto unlock;
	}

	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
		ret = -EINVAL;
		rdt_last_cmd_puts("Pseudo-locking in progress\n");
		goto unlock;
	}

	if (is_cpu_list(of))
		ret = cpulist_parse(buf, newmask);
	else
		ret = cpumask_parse(buf, newmask);

	if (ret) {
		rdt_last_cmd_puts("Bad CPU list/mask\n");
		goto unlock;
	}

	/* check that user didn't specify any offline cpus */
	cpumask_andnot(tmpmask, newmask, cpu_online_mask);
	if (!cpumask_empty(tmpmask)) {
		ret = -EINVAL;
		rdt_last_cmd_puts("Can only assign online CPUs\n");
		goto unlock;
	}

	if (rdtgrp->type == RDTCTRL_GROUP)
		ret = cpus_ctrl_write(rdtgrp, newmask, tmpmask, tmpmask1);
	else if (rdtgrp->type == RDTMON_GROUP)
		ret = cpus_mon_write(rdtgrp, newmask, tmpmask);
	else
		ret = -EINVAL;

unlock:
	rdtgroup_kn_unlock(of->kn);
	free_cpumask_var(tmpmask);
	free_cpumask_var(newmask);
	free_cpumask_var(tmpmask1);

	return ret ?: nbytes;
}

/**
 * rdtgroup_remove - the helper to remove resource group safely
 * @rdtgrp: resource group to remove
 *
 * On resource group creation via a mkdir, an extra kernfs_node reference is
 * taken to ensure that the rdtgroup structure remains accessible for the
 * rdtgroup_kn_unlock() calls where it is removed.
 *
 * Drop the extra reference here, then free the rdtgroup structure.
 *
 * Return: void
 */
static void rdtgroup_remove(struct rdtgroup *rdtgrp)
{
	kernfs_put(rdtgrp->kn);
	kfree(rdtgrp);
}

static void _update_task_closid_rmid(void *task)
{
	/*
	 * If the task is still current on this CPU, update PQR_ASSOC MSR.
	 * Otherwise, the MSR is updated when the task is scheduled in.
	 */
	if (task == current)
		resctrl_sched_in(task);
}

static void update_task_closid_rmid(struct task_struct *t)
{
	if (IS_ENABLED(CONFIG_SMP) && task_curr(t))
		smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1);
	else
		_update_task_closid_rmid(t);
}

static bool task_in_rdtgroup(struct task_struct *tsk, struct rdtgroup *rdtgrp)
{
	u32 closid, rmid = rdtgrp->mon.rmid;

	if (rdtgrp->type == RDTCTRL_GROUP)
		closid = rdtgrp->closid;
	else if (rdtgrp->type == RDTMON_GROUP)
		closid = rdtgrp->mon.parent->closid;
	else
		return false;

	return resctrl_arch_match_closid(tsk, closid) &&
	       resctrl_arch_match_rmid(tsk, closid, rmid);
}

static int __rdtgroup_move_task(struct task_struct *tsk,
				struct rdtgroup *rdtgrp)
{
	/* If the task is already in rdtgrp, no need to move the task. */
	if (task_in_rdtgroup(tsk, rdtgrp))
		return 0;

	/*
	 * Set the task's closid/rmid before the PQR_ASSOC MSR can be
	 * updated by them.
	 *
	 * For ctrl_mon groups, move both closid and rmid.
	 * For monitor groups, can move the tasks only from
	 * their parent CTRL group.
	 */
	if (rdtgrp->type == RDTMON_GROUP &&
	    !resctrl_arch_match_closid(tsk, rdtgrp->mon.parent->closid)) {
		rdt_last_cmd_puts("Can't move task to different control group\n");
		return -EINVAL;
	}

	if (rdtgrp->type == RDTMON_GROUP)
		resctrl_arch_set_closid_rmid(tsk, rdtgrp->mon.parent->closid,
					     rdtgrp->mon.rmid);
	else
		resctrl_arch_set_closid_rmid(tsk, rdtgrp->closid,
					     rdtgrp->mon.rmid);

	/*
	 * Ensure the task's closid and rmid are written before determining if
	 * the task is current that will decide if it will be interrupted.
	 * This pairs with the full barrier between the rq->curr update and
	 * resctrl_sched_in() during context switch.
	 */
	smp_mb();

	/*
	 * By now, the task's closid and rmid are set. If the task is current
	 * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource
	 * group go into effect. If the task is not current, the MSR will be
	 * updated when the task is scheduled in.
	 */
	update_task_closid_rmid(tsk);

	return 0;
}

static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
{
	return (resctrl_arch_alloc_capable() && (r->type == RDTCTRL_GROUP) &&
		resctrl_arch_match_closid(t, r->closid));
}

static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
{
	return (resctrl_arch_mon_capable() && (r->type == RDTMON_GROUP) &&
		resctrl_arch_match_rmid(t, r->mon.parent->closid,
					r->mon.rmid));
}

/**
 * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group
 * @r: Resource group
 *
 * Return: 1 if tasks have been assigned to @r, 0 otherwise
 */
int rdtgroup_tasks_assigned(struct rdtgroup *r)
{
	struct task_struct *p, *t;
	int ret = 0;

	lockdep_assert_held(&rdtgroup_mutex);

	rcu_read_lock();
	for_each_process_thread(p, t) {
		if (is_closid_match(t, r) || is_rmid_match(t, r)) {
			ret = 1;
			break;
		}
	}
	rcu_read_unlock();

	return ret;
}

static int rdtgroup_task_write_permission(struct task_struct *task,
					  struct kernfs_open_file *of)
{
	const struct cred *tcred = get_task_cred(task);
	const struct cred *cred = current_cred();
	int ret = 0;

	/*
	 * Even if we're attaching all tasks in the thread group, we only
	 * need to check permissions on one of them.
	 */
	if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
	    !uid_eq(cred->euid, tcred->uid) &&
	    !uid_eq(cred->euid, tcred->suid)) {
		rdt_last_cmd_printf("No permission to move task %d\n", task->pid);
		ret = -EPERM;
	}

	put_cred(tcred);
	return ret;
}

static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp,
			      struct kernfs_open_file *of)
{
	struct task_struct *tsk;
	int ret;

	rcu_read_lock();
	if (pid) {
		tsk = find_task_by_vpid(pid);
		if (!tsk) {
			rcu_read_unlock();
			rdt_last_cmd_printf("No task %d\n", pid);
			return -ESRCH;
		}
	} else {
		tsk = current;
	}

	get_task_struct(tsk);
	rcu_read_unlock();

	ret = rdtgroup_task_write_permission(tsk, of);
	if (!ret)
		ret = __rdtgroup_move_task(tsk, rdtgrp);

	put_task_struct(tsk);
	return ret;
}

static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
				    char *buf, size_t nbytes, loff_t off)
{
	struct rdtgroup *rdtgrp;
	char *pid_str;
	int ret = 0;
	pid_t pid;

	rdtgrp = rdtgroup_kn_lock_live(of->kn);
	if (!rdtgrp) {
		rdtgroup_kn_unlock(of->kn);
		return -ENOENT;
	}
	rdt_last_cmd_clear();

	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
		ret = -EINVAL;
		rdt_last_cmd_puts("Pseudo-locking in progress\n");
		goto unlock;
	}

	while (buf && buf[0] != '\0' && buf[0] != '\n') {
		pid_str = strim(strsep(&buf, ","));

		if (kstrtoint(pid_str, 0, &pid)) {
			rdt_last_cmd_printf("Task list parsing error pid %s\n", pid_str);
			ret = -EINVAL;
			break;
		}

		if (pid < 0) {
			rdt_last_cmd_printf("Invalid pid %d\n", pid);
			ret = -EINVAL;
			break;
		}

		ret = rdtgroup_move_task(pid, rdtgrp, of);
		if (ret) {
			rdt_last_cmd_printf("Error while processing task %d\n", pid);
			break;
		}
	}

unlock:
	rdtgroup_kn_unlock(of->kn);

	return ret ?: nbytes;
}

static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
{
	struct task_struct *p, *t;
	pid_t pid;

	rcu_read_lock();
	for_each_process_thread(p, t) {
		if (is_closid_match(t, r) || is_rmid_match(t, r)) {
			pid = task_pid_vnr(t);
			if (pid)
				seq_printf(s, "%d\n", pid);
		}
	}
	rcu_read_unlock();
}

static int rdtgroup_tasks_show(struct kernfs_open_file *of,
			       struct seq_file *s, void *v)
{
	struct rdtgroup *rdtgrp;
	int ret = 0;

	rdtgrp = rdtgroup_kn_lock_live(of->kn);
	if (rdtgrp)
		show_rdt_tasks(rdtgrp, s);
	else
		ret = -ENOENT;
	rdtgroup_kn_unlock(of->kn);

	return ret;
}

static int rdtgroup_closid_show(struct kernfs_open_file *of,
				struct seq_file *s, void *v)
{
	struct rdtgroup *rdtgrp;
	int ret = 0;

	rdtgrp = rdtgroup_kn_lock_live(of->kn);
	if (rdtgrp)
		seq_printf(s, "%u\n", rdtgrp->closid);
	else
		ret = -ENOENT;
	rdtgroup_kn_unlock(of->kn);

	return ret;
}

static int rdtgroup_rmid_show(struct kernfs_open_file *of,
			      struct seq_file *s, void *v)
{
	struct rdtgroup *rdtgrp;
	int ret = 0;

	rdtgrp = rdtgroup_kn_lock_live(of->kn);
	if (rdtgrp)
		seq_printf(s, "%u\n", rdtgrp->mon.rmid);
	else
		ret = -ENOENT;
	rdtgroup_kn_unlock(of->kn);

	return ret;
}

#ifdef CONFIG_PROC_CPU_RESCTRL

/*
 * A task can only be part of one resctrl control group and of one monitor
 * group which is associated to that control group.
 *
 * 1)   res:
 *      mon:
 *
 *    resctrl is not available.
 *
 * 2)   res:/
 *      mon:
 *
 *    Task is part of the root resctrl control group, and it is not associated
 *    to any monitor group.
 *
 * 3)  res:/
 *     mon:mon0
 *
 *    Task is part of the root resctrl control group and monitor group mon0.
 *
 * 4)  res:group0
 *     mon:
 *
 *    Task is part of resctrl control group group0, and it is not associated
 *    to any monitor group.
 *
 * 5) res:group0
 *    mon:mon1
 *
 *    Task is part of resctrl control group group0 and monitor group mon1.
 */
int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
		      struct pid *pid, struct task_struct *tsk)
{
	struct rdtgroup *rdtg;
	int ret = 0;

	mutex_lock(&rdtgroup_mutex);

	/* Return empty if resctrl has not been mounted. */
	if (!resctrl_mounted) {
		seq_puts(s, "res:\nmon:\n");
		goto unlock;
	}

	list_for_each_entry(rdtg, &rdt_all_groups, rdtgroup_list) {
		struct rdtgroup *crg;

		/*
		 * Task information is only relevant for shareable
		 * and exclusive groups.
		 */
		if (rdtg->mode != RDT_MODE_SHAREABLE &&
		    rdtg->mode != RDT_MODE_EXCLUSIVE)
			continue;

		if (!resctrl_arch_match_closid(tsk, rdtg->closid))
			continue;

		seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "",
			   rdtg->kn->name);
		seq_puts(s, "mon:");
		list_for_each_entry(crg, &rdtg->mon.crdtgrp_list,
				    mon.crdtgrp_list) {
			if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid,
						     crg->mon.rmid))
				continue;
			seq_printf(s, "%s", crg->kn->name);
			break;
		}
		seq_putc(s, '\n');
		goto unlock;
	}
	/*
	 * The above search should succeed. Otherwise return
	 * with an error.
	 */
	ret = -ENOENT;
unlock:
	mutex_unlock(&rdtgroup_mutex);

	return ret;
}
#endif

static int rdt_last_cmd_status_show(struct kernfs_open_file *of,
				    struct seq_file *seq, void *v)
{
	int len;

	mutex_lock(&rdtgroup_mutex);
	len = seq_buf_used(&last_cmd_status);
	if (len)
		seq_printf(seq, "%.*s", len, last_cmd_status_buf);
	else
		seq_puts(seq, "ok\n");
	mutex_unlock(&rdtgroup_mutex);
	return 0;
}

static int rdt_num_closids_show(struct kernfs_open_file *of,
				struct seq_file *seq, void *v)
{
	struct resctrl_schema *s = of->kn->parent->priv;

	seq_printf(seq, "%u\n", s->num_closid);
	return 0;
}

static int rdt_default_ctrl_show(struct kernfs_open_file *of,
			     struct seq_file *seq, void *v)
{
	struct resctrl_schema *s = of->kn->parent->priv;
	struct rdt_resource *r = s->res;

	seq_printf(seq, "%x\n", r->default_ctrl);
	return 0;
}

static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
			     struct seq_file *seq, void *v)
{
	struct resctrl_schema *s = of->kn->parent->priv;
	struct rdt_resource *r = s->res;

	seq_printf(seq, "%u\n", r->cache.min_cbm_bits);
	return 0;
}

static int rdt_shareable_bits_show(struct kernfs_open_file *of,
				   struct seq_file *seq, void *v)
{
	struct resctrl_schema *s = of->kn->parent->priv;
	struct rdt_resource *r = s->res;

	seq_printf(seq, "%x\n", r->cache.shareable_bits);
	return 0;
}

/*
 * rdt_bit_usage_show - Display current usage of resources
 *
 * A domain is a shared resource that can now be allocated differently. Here
 * we display the current regions of the domain as an annotated bitmask.
 * For each domain of this resource its allocation bitmask
 * is annotated as below to indicate the current usage of the corresponding bit:
 *   0 - currently unused
 *   X - currently available for sharing and used by software and hardware
 *   H - currently used by hardware only but available for software use
 *   S - currently used and shareable by software only
 *   E - currently used exclusively by one resource group
 *   P - currently pseudo-locked by one resource group
 */
static int rdt_bit_usage_show(struct kernfs_open_file *of,
			      struct seq_file *seq, void *v)
{
	struct resctrl_schema *s = of->kn->parent->priv;
	/*
	 * Use unsigned long even though only 32 bits are used to ensure
	 * test_bit() is used safely.
	 */
	unsigned long sw_shareable = 0, hw_shareable = 0;
	unsigned long exclusive = 0, pseudo_locked = 0;
	struct rdt_resource *r = s->res;
	struct rdt_domain *dom;
	int i, hwb, swb, excl, psl;
	enum rdtgrp_mode mode;
	bool sep = false;
	u32 ctrl_val;

	cpus_read_lock();
	mutex_lock(&rdtgroup_mutex);
	hw_shareable = r->cache.shareable_bits;
	list_for_each_entry(dom, &r->domains, list) {
		if (sep)
			seq_putc(seq, ';');
		sw_shareable = 0;
		exclusive = 0;
		seq_printf(seq, "%d=", dom->id);
		for (i = 0; i < closids_supported(); i++) {
			if (!closid_allocated(i))
				continue;
			ctrl_val = resctrl_arch_get_config(r, dom, i,
							   s->conf_type);
			mode = rdtgroup_mode_by_closid(i);
			switch (mode) {
			case RDT_MODE_SHAREABLE:
				sw_shareable |= ctrl_val;
				break;
			case RDT_MODE_EXCLUSIVE:
				exclusive |= ctrl_val;
				break;
			case RDT_MODE_PSEUDO_LOCKSETUP:
			/*
			 * RDT_MODE_PSEUDO_LOCKSETUP is possible
			 * here but not included since the CBM
			 * associated with this CLOSID in this mode
			 * is not initialized and no task or cpu can be
			 * assigned this CLOSID.
			 */
				break;
			case RDT_MODE_PSEUDO_LOCKED:
			case RDT_NUM_MODES:
				WARN(1,
				     "invalid mode for closid %d\n", i);
				break;
			}
		}
		for (i = r->cache.cbm_len - 1; i >= 0; i--) {
			pseudo_locked = dom->plr ? dom->plr->cbm : 0;
			hwb = test_bit(i, &hw_shareable);
			swb = test_bit(i, &sw_shareable);
			excl = test_bit(i, &exclusive);
			psl = test_bit(i, &pseudo_locked);
			if (hwb && swb)
				seq_putc(seq, 'X');
			else if (hwb && !swb)
				seq_putc(seq, 'H');
			else if (!hwb && swb)
				seq_putc(seq, 'S');
			else if (excl)
				seq_putc(seq, 'E');
			else if (psl)
				seq_putc(seq, 'P');
			else /* Unused bits remain */
				seq_putc(seq, '0');
		}
		sep = true;
	}
	seq_putc(seq, '\n');
	mutex_unlock(&rdtgroup_mutex);
	cpus_read_unlock();
	return 0;
}

static int rdt_min_bw_show(struct kernfs_open_file *of,
			     struct seq_file *seq, void *v)
{
	struct resctrl_schema *s = of->kn->parent->priv;
	struct rdt_resource *r = s->res;

	seq_printf(seq, "%u\n", r->membw.min_bw);
	return 0;
}

static int rdt_num_rmids_show(struct kernfs_open_file *of,
			      struct seq_file *seq, void *v)
{
	struct rdt_resource *r = of->kn->parent->priv;

	seq_printf(seq, "%d\n", r->num_rmid);

	return 0;
}

static int rdt_mon_features_show(struct kernfs_open_file *of,
				 struct seq_file *seq, void *v)
{
	struct rdt_resource *r = of->kn->parent->priv;
	struct mon_evt *mevt;

	list_for_each_entry(mevt, &r->evt_list, list) {
		seq_printf(seq, "%s\n", mevt->name);
		if (mevt->configurable)
			seq_printf(seq, "%s_config\n", mevt->name);
	}

	return 0;
}

static int rdt_bw_gran_show(struct kernfs_open_file *of,
			     struct seq_file *seq, void *v)
{
	struct resctrl_schema *s = of->kn->parent->priv;
	struct rdt_resource *r = s->res;

	seq_printf(seq, "%u\n", r->membw.bw_gran);
	return 0;
}

static int rdt_delay_linear_show(struct kernfs_open_file *of,
			     struct seq_file *seq, void *v)
{
	struct resctrl_schema *s = of->kn->parent->priv;
	struct rdt_resource *r = s->res;

	seq_printf(seq, "%u\n", r->membw.delay_linear);
	return 0;
}

static int max_threshold_occ_show(struct kernfs_open_file *of,
				  struct seq_file *seq, void *v)
{
	seq_printf(seq, "%u\n", resctrl_rmid_realloc_threshold);

	return 0;
}

static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
					 struct seq_file *seq, void *v)
{
	struct resctrl_schema *s = of->kn->parent->priv;
	struct rdt_resource *r = s->res;

	if (r->membw.throttle_mode == THREAD_THROTTLE_PER_THREAD)
		seq_puts(seq, "per-thread\n");
	else
		seq_puts(seq, "max\n");

	return 0;
}

static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
				       char *buf, size_t nbytes, loff_t off)
{
	unsigned int bytes;
	int ret;

	ret = kstrtouint(buf, 0, &bytes);
	if (ret)
		return ret;

	if (bytes > resctrl_rmid_realloc_limit)
		return -EINVAL;

	resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(bytes);

	return nbytes;
}

/*
 * rdtgroup_mode_show - Display mode of this resource group
 */
static int rdtgroup_mode_show(struct kernfs_open_file *of,
			      struct seq_file *s, void *v)
{
	struct rdtgroup *rdtgrp;

	rdtgrp = rdtgroup_kn_lock_live(of->kn);
	if (!rdtgrp) {
		rdtgroup_kn_unlock(of->kn);
		return -ENOENT;
	}

	seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode));

	rdtgroup_kn_unlock(of->kn);
	return 0;
}

static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type)
{
	switch (my_type) {
	case CDP_CODE:
		return CDP_DATA;
	case CDP_DATA:
		return CDP_CODE;
	default:
	case CDP_NONE:
		return CDP_NONE;
	}
}

static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of,
					struct seq_file *seq, void *v)
{
	struct resctrl_schema *s = of->kn->parent->priv;
	struct rdt_resource *r = s->res;

	seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks);

	return 0;
}

/**
 * __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
 * @r: Resource to which domain instance @d belongs.
 * @d: The domain instance for which @closid is being tested.
 * @cbm: Capacity bitmask being tested.
 * @closid: Intended closid for @cbm.
 * @type: CDP type of @r.
 * @exclusive: Only check if overlaps with exclusive resource groups
 *
 * Checks if provided @cbm intended to be used for @closid on domain
 * @d overlaps with any other closids or other hardware usage associated
 * with this domain. If @exclusive is true then only overlaps with
 * resource groups in exclusive mode will be considered. If @exclusive
 * is false then overlaps with any resource group or hardware entities
 * will be considered.
 *
 * @cbm is unsigned long, even if only 32 bits are used, to make the
 * bitmap functions work correctly.
 *
 * Return: false if CBM does not overlap, true if it does.
 */
static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
				    unsigned long cbm, int closid,
				    enum resctrl_conf_type type, bool exclusive)
{
	enum rdtgrp_mode mode;
	unsigned long ctrl_b;
	int i;

	/* Check for any overlap with regions used by hardware directly */
	if (!exclusive) {
		ctrl_b = r->cache.shareable_bits;
		if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len))
			return true;
	}

	/* Check for overlap with other resource groups */
	for (i = 0; i < closids_supported(); i++) {
		ctrl_b = resctrl_arch_get_config(r, d, i, type);
		mode = rdtgroup_mode_by_closid(i);
		if (closid_allocated(i) && i != closid &&
		    mode != RDT_MODE_PSEUDO_LOCKSETUP) {
			if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) {
				if (exclusive) {
					if (mode == RDT_MODE_EXCLUSIVE)
						return true;
					continue;
				}
				return true;
			}
		}
	}

	return false;
}

/**
 * rdtgroup_cbm_overlaps - Does CBM overlap with other use of hardware
 * @s: Schema for the resource to which domain instance @d belongs.
 * @d: The domain instance for which @closid is being tested.
 * @cbm: Capacity bitmask being tested.
 * @closid: Intended closid for @cbm.
 * @exclusive: Only check if overlaps with exclusive resource groups
 *
 * Resources that can be allocated using a CBM can use the CBM to control
 * the overlap of these allocations. rdtgroup_cmb_overlaps() is the test
 * for overlap. Overlap test is not limited to the specific resource for
 * which the CBM is intended though - when dealing with CDP resources that
 * share the underlying hardware the overlap check should be performed on
 * the CDP resource sharing the hardware also.
 *
 * Refer to description of __rdtgroup_cbm_overlaps() for the details of the
 * overlap test.
 *
 * Return: true if CBM overlap detected, false if there is no overlap
 */
bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d,
			   unsigned long cbm, int closid, bool exclusive)
{
	enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
	struct rdt_resource *r = s->res;

	if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, s->conf_type,
				    exclusive))
		return true;

	if (!resctrl_arch_get_cdp_enabled(r->rid))
		return false;
	return  __rdtgroup_cbm_overlaps(r, d, cbm, closid, peer_type, exclusive);
}

/**
 * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive
 * @rdtgrp: Resource group identified through its closid.
 *
 * An exclusive resource group implies that there should be no sharing of
 * its allocated resources. At the time this group is considered to be
 * exclusive this test can determine if its current schemata supports this
 * setting by testing for overlap with all other resource groups.
 *
 * Return: true if resource group can be exclusive, false if there is overlap
 * with allocations of other resource groups and thus this resource group
 * cannot be exclusive.
 */
static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
{
	int closid = rdtgrp->closid;
	struct resctrl_schema *s;
	struct rdt_resource *r;
	bool has_cache = false;
	struct rdt_domain *d;
	u32 ctrl;

	/* Walking r->domains, ensure it can't race with cpuhp */
	lockdep_assert_cpus_held();

	list_for_each_entry(s, &resctrl_schema_all, list) {
		r = s->res;
		if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)
			continue;
		has_cache = true;
		list_for_each_entry(d, &r->domains, list) {
			ctrl = resctrl_arch_get_config(r, d, closid,
						       s->conf_type);
			if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) {
				rdt_last_cmd_puts("Schemata overlaps\n");
				return false;
			}
		}
	}

	if (!has_cache) {
		rdt_last_cmd_puts("Cannot be exclusive without CAT/CDP\n");
		return false;
	}

	return true;
}

/*
 * rdtgroup_mode_write - Modify the resource group's mode
 */
static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
				   char *buf, size_t nbytes, loff_t off)
{
	struct rdtgroup *rdtgrp;
	enum rdtgrp_mode mode;
	int ret = 0;

	/* Valid input requires a trailing newline */
	if (nbytes == 0 || buf[nbytes - 1] != '\n')
		return -EINVAL;
	buf[nbytes - 1] = '\0';

	rdtgrp = rdtgroup_kn_lock_live(of->kn);
	if (!rdtgrp) {
		rdtgroup_kn_unlock(of->kn);
		return -ENOENT;
	}

	rdt_last_cmd_clear();

	mode = rdtgrp->mode;

	if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) ||
	    (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE) ||
	    (!strcmp(buf, "pseudo-locksetup") &&
	     mode == RDT_MODE_PSEUDO_LOCKSETUP) ||
	    (!strcmp(buf, "pseudo-locked") && mode == RDT_MODE_PSEUDO_LOCKED))
		goto out;

	if (mode == RDT_MODE_PSEUDO_LOCKED) {
		rdt_last_cmd_puts("Cannot change pseudo-locked group\n");
		ret = -EINVAL;
		goto out;
	}

	if (!strcmp(buf, "shareable")) {
		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
			ret = rdtgroup_locksetup_exit(rdtgrp);
			if (ret)
				goto out;
		}
		rdtgrp->mode = RDT_MODE_SHAREABLE;
	} else if (!strcmp(buf, "exclusive")) {
		if (!rdtgroup_mode_test_exclusive(rdtgrp)) {
			ret = -EINVAL;
			goto out;
		}
		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
			ret = rdtgroup_locksetup_exit(rdtgrp);
			if (ret)
				goto out;
		}
		rdtgrp->mode = RDT_MODE_EXCLUSIVE;
	} else if (!strcmp(buf, "pseudo-locksetup")) {
		ret = rdtgroup_locksetup_enter(rdtgrp);
		if (ret)
			goto out;
		rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP;
	} else {
		rdt_last_cmd_puts("Unknown or unsupported mode\n");
		ret = -EINVAL;
	}

out:
	rdtgroup_kn_unlock(of->kn);
	return ret ?: nbytes;
}

/**
 * rdtgroup_cbm_to_size - Translate CBM to size in bytes
 * @r: RDT resource to which @d belongs.
 * @d: RDT domain instance.
 * @cbm: bitmask for which the size should be computed.
 *
 * The bitmask provided associated with the RDT domain instance @d will be
 * translated into how many bytes it represents. The size in bytes is
 * computed by first dividing the total cache size by the CBM length to
 * determine how many bytes each bit in the bitmask represents. The result
 * is multiplied with the number of bits set in the bitmask.
 *
 * @cbm is unsigned long, even if only 32 bits are used to make the
 * bitmap functions work correctly.
 */
unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
				  struct rdt_domain *d, unsigned long cbm)
{
	struct cpu_cacheinfo *ci;
	unsigned int size = 0;
	int num_b, i;

	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
	for (i = 0; i < ci->num_leaves; i++) {
		if (ci->info_list[i].level == r->cache_level) {
			size = ci->info_list[i].size / r->cache.cbm_len * num_b;
			break;
		}
	}

	return size;
}

/*
 * rdtgroup_size_show - Display size in bytes of allocated regions
 *
 * The "size" file mirrors the layout of the "schemata" file, printing the
 * size in bytes of each region instead of the capacity bitmask.
 */
static int rdtgroup_size_show(struct kernfs_open_file *of,
			      struct seq_file *s, void *v)
{
	struct resctrl_schema *schema;
	enum resctrl_conf_type type;
	struct rdtgroup *rdtgrp;
	struct rdt_resource *r;
	struct rdt_domain *d;
	unsigned int size;
	int ret = 0;
	u32 closid;
	bool sep;
	u32 ctrl;

	rdtgrp = rdtgroup_kn_lock_live(of->kn);
	if (!rdtgrp) {
		rdtgroup_kn_unlock(of->kn);
		return -ENOENT;
	}

	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
		if (!rdtgrp->plr->d) {
			rdt_last_cmd_clear();
			rdt_last_cmd_puts("Cache domain offline\n");
			ret = -ENODEV;
		} else {
			seq_printf(s, "%*s:", max_name_width,
				   rdtgrp->plr->s->name);
			size = rdtgroup_cbm_to_size(rdtgrp->plr->s->res,
						    rdtgrp->plr->d,
						    rdtgrp->plr->cbm);
			seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
		}
		goto out;
	}

	closid = rdtgrp->closid;

	list_for_each_entry(schema, &resctrl_schema_all, list) {
		r = schema->res;
		type = schema->conf_type;
		sep = false;
		seq_printf(s, "%*s:", max_name_width, schema->name);
		list_for_each_entry(d, &r->domains, list) {
			if (sep)
				seq_putc(s, ';');
			if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
				size = 0;
			} else {
				if (is_mba_sc(r))
					ctrl = d->mbps_val[closid];
				else
					ctrl = resctrl_arch_get_config(r, d,
								       closid,
								       type);
				if (r->rid == RDT_RESOURCE_MBA ||
				    r->rid == RDT_RESOURCE_SMBA)
					size = ctrl;
				else
					size = rdtgroup_cbm_to_size(r, d, ctrl);
			}
			seq_printf(s, "%d=%u", d->id, size);
			sep = true;
		}
		seq_putc(s, '\n');
	}

out:
	rdtgroup_kn_unlock(of->kn);

	return ret;
}

struct mon_config_info {
	u32 evtid;
	u32 mon_config;
};

#define INVALID_CONFIG_INDEX   UINT_MAX

/**
 * mon_event_config_index_get - get the hardware index for the
 *                              configurable event
 * @evtid: event id.
 *
 * Return: 0 for evtid == QOS_L3_MBM_TOTAL_EVENT_ID
 *         1 for evtid == QOS_L3_MBM_LOCAL_EVENT_ID
 *         INVALID_CONFIG_INDEX for invalid evtid
 */
static inline unsigned int mon_event_config_index_get(u32 evtid)
{
	switch (evtid) {
	case QOS_L3_MBM_TOTAL_EVENT_ID:
		return 0;
	case QOS_L3_MBM_LOCAL_EVENT_ID:
		return 1;
	default:
		/* Should never reach here */
		return INVALID_CONFIG_INDEX;
	}
}

static void mon_event_config_read(void *info)
{
	struct mon_config_info *mon_info = info;
	unsigned int index;
	u64 msrval;

	index = mon_event_config_index_get(mon_info->evtid);
	if (index == INVALID_CONFIG_INDEX) {
		pr_warn_once("Invalid event id %d\n", mon_info->evtid);
		return;
	}
	rdmsrl(MSR_IA32_EVT_CFG_BASE + index, msrval);

	/* Report only the valid event configuration bits */
	mon_info->mon_config = msrval & MAX_EVT_CONFIG_BITS;
}

static void mondata_config_read(struct rdt_domain *d, struct mon_config_info *mon_info)
{
	smp_call_function_any(&d->cpu_mask, mon_event_config_read, mon_info, 1);
}

static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid)
{
	struct mon_config_info mon_info = {0};
	struct rdt_domain *dom;
	bool sep = false;

	cpus_read_lock();
	mutex_lock(&rdtgroup_mutex);

	list_for_each_entry(dom, &r->domains, list) {
		if (sep)
			seq_puts(s, ";");

		memset(&mon_info, 0, sizeof(struct mon_config_info));
		mon_info.evtid = evtid;
		mondata_config_read(dom, &mon_info);

		seq_printf(s, "%d=0x%02x", dom->id, mon_info.mon_config);
		sep = true;
	}
	seq_puts(s, "\n");

	mutex_unlock(&rdtgroup_mutex);
	cpus_read_unlock();

	return 0;
}

static int mbm_total_bytes_config_show(struct kernfs_open_file *of,
				       struct seq_file *seq, void *v)
{
	struct rdt_resource *r = of->kn->parent->priv;

	mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID);

	return 0;
}

static int mbm_local_bytes_config_show(struct kernfs_open_file *of,
				       struct seq_file *seq, void *v)
{
	struct rdt_resource *r = of->kn->parent->priv;

	mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID);

	return 0;
}

static void mon_event_config_write(void *info)
{
	struct mon_config_info *mon_info = info;
	unsigned int index;

	index = mon_event_config_index_get(mon_info->evtid);
	if (index == INVALID_CONFIG_INDEX) {
		pr_warn_once("Invalid event id %d\n", mon_info->evtid);
		return;
	}
	wrmsr(MSR_IA32_EVT_CFG_BASE + index, mon_info->mon_config, 0);
}

static void mbm_config_write_domain(struct rdt_resource *r,
				    struct rdt_domain *d, u32 evtid, u32 val)
{
	struct mon_config_info mon_info = {0};

	/*
	 * Read the current config value first. If both are the same then
	 * no need to write it again.
	 */
	mon_info.evtid = evtid;
	mondata_config_read(d, &mon_info);
	if (mon_info.mon_config == val)
		return;

	mon_info.mon_config = val;

	/*
	 * Update MSR_IA32_EVT_CFG_BASE MSR on one of the CPUs in the
	 * domain. The MSRs offset from MSR MSR_IA32_EVT_CFG_BASE
	 * are scoped at the domain level. Writing any of these MSRs
	 * on one CPU is observed by all the CPUs in the domain.
	 */
	smp_call_function_any(&d->cpu_mask, mon_event_config_write,
			      &mon_info, 1);

	/*
	 * When an Event Configuration is changed, the bandwidth counters
	 * for all RMIDs and Events will be cleared by the hardware. The
	 * hardware also sets MSR_IA32_QM_CTR.Unavailable (bit 62) for
	 * every RMID on the next read to any event for every RMID.
	 * Subsequent reads will have MSR_IA32_QM_CTR.Unavailable (bit 62)
	 * cleared while it is tracked by the hardware. Clear the
	 * mbm_local and mbm_total counts for all the RMIDs.
	 */
	resctrl_arch_reset_rmid_all(r, d);
}

static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
{
	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
	char *dom_str = NULL, *id_str;
	unsigned long dom_id, val;
	struct rdt_domain *d;

	/* Walking r->domains, ensure it can't race with cpuhp */
	lockdep_assert_cpus_held();

next:
	if (!tok || tok[0] == '\0')
		return 0;

	/* Start processing the strings for each domain */
	dom_str = strim(strsep(&tok, ";"));
	id_str = strsep(&dom_str, "=");

	if (!id_str || kstrtoul(id_str, 10, &dom_id)) {
		rdt_last_cmd_puts("Missing '=' or non-numeric domain id\n");
		return -EINVAL;
	}

	if (!dom_str || kstrtoul(dom_str, 16, &val)) {
		rdt_last_cmd_puts("Non-numeric event configuration value\n");
		return -EINVAL;
	}

	/* Value from user cannot be more than the supported set of events */
	if ((val & hw_res->mbm_cfg_mask) != val) {
		rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n",
				    hw_res->mbm_cfg_mask);
		return -EINVAL;
	}

	list_for_each_entry(d, &r->domains, list) {
		if (d->id == dom_id) {
			mbm_config_write_domain(r, d, evtid, val);
			goto next;
		}
	}

	return -EINVAL;
}

static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of,
					    char *buf, size_t nbytes,
					    loff_t off)
{
	struct rdt_resource *r = of->kn->parent->priv;
	int ret;

	/* Valid input requires a trailing newline */
	if (nbytes == 0 || buf[nbytes - 1] != '\n')
		return -EINVAL;

	cpus_read_lock();
	mutex_lock(&rdtgroup_mutex);

	rdt_last_cmd_clear();

	buf[nbytes - 1] = '\0';

	ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID);

	mutex_unlock(&rdtgroup_mutex);
	cpus_read_unlock();

	return ret ?: nbytes;
}

static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
					    char *buf, size_t nbytes,
					    loff_t off)
{
	struct rdt_resource *r = of->kn->parent->priv;
	int ret;

	/* Valid input requires a trailing newline */
	if (nbytes == 0 || buf[nbytes - 1] != '\n')
		return -EINVAL;

	cpus_read_lock();
	mutex_lock(&rdtgroup_mutex);

	rdt_last_cmd_clear();

	buf[nbytes - 1] = '\0';

	ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID);

	mutex_unlock(&rdtgroup_mutex);
	cpus_read_unlock();

	return ret ?: nbytes;
}

/* rdtgroup information files for one cache resource. */
static struct rftype res_common_files[] = {
	{
		.name		= "last_cmd_status",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_last_cmd_status_show,
		.fflags		= RFTYPE_TOP_INFO,
	},
	{
		.name		= "num_closids",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_num_closids_show,
		.fflags		= RFTYPE_CTRL_INFO,
	},
	{
		.name		= "mon_features",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_mon_features_show,
		.fflags		= RFTYPE_MON_INFO,
	},
	{
		.name		= "num_rmids",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_num_rmids_show,
		.fflags		= RFTYPE_MON_INFO,
	},
	{
		.name		= "cbm_mask",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_default_ctrl_show,
		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
	},
	{
		.name		= "min_cbm_bits",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_min_cbm_bits_show,
		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
	},
	{
		.name		= "shareable_bits",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_shareable_bits_show,
		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
	},
	{
		.name		= "bit_usage",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_bit_usage_show,
		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
	},
	{
		.name		= "min_bandwidth",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_min_bw_show,
		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
	},
	{
		.name		= "bandwidth_gran",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_bw_gran_show,
		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
	},
	{
		.name		= "delay_linear",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_delay_linear_show,
		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
	},
	/*
	 * Platform specific which (if any) capabilities are provided by
	 * thread_throttle_mode. Defer "fflags" initialization to platform
	 * discovery.
	 */
	{
		.name		= "thread_throttle_mode",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_thread_throttle_mode_show,
	},
	{
		.name		= "max_threshold_occupancy",
		.mode		= 0644,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.write		= max_threshold_occ_write,
		.seq_show	= max_threshold_occ_show,
		.fflags		= RFTYPE_MON_INFO | RFTYPE_RES_CACHE,
	},
	{
		.name		= "mbm_total_bytes_config",
		.mode		= 0644,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= mbm_total_bytes_config_show,
		.write		= mbm_total_bytes_config_write,
	},
	{
		.name		= "mbm_local_bytes_config",
		.mode		= 0644,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= mbm_local_bytes_config_show,
		.write		= mbm_local_bytes_config_write,
	},
	{
		.name		= "cpus",
		.mode		= 0644,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.write		= rdtgroup_cpus_write,
		.seq_show	= rdtgroup_cpus_show,
		.fflags		= RFTYPE_BASE,
	},
	{
		.name		= "cpus_list",
		.mode		= 0644,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.write		= rdtgroup_cpus_write,
		.seq_show	= rdtgroup_cpus_show,
		.flags		= RFTYPE_FLAGS_CPUS_LIST,
		.fflags		= RFTYPE_BASE,
	},
	{
		.name		= "tasks",
		.mode		= 0644,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.write		= rdtgroup_tasks_write,
		.seq_show	= rdtgroup_tasks_show,
		.fflags		= RFTYPE_BASE,
	},
	{
		.name		= "mon_hw_id",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdtgroup_rmid_show,
		.fflags		= RFTYPE_MON_BASE | RFTYPE_DEBUG,
	},
	{
		.name		= "schemata",
		.mode		= 0644,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.write		= rdtgroup_schemata_write,
		.seq_show	= rdtgroup_schemata_show,
		.fflags		= RFTYPE_CTRL_BASE,
	},
	{
		.name		= "mode",
		.mode		= 0644,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.write		= rdtgroup_mode_write,
		.seq_show	= rdtgroup_mode_show,
		.fflags		= RFTYPE_CTRL_BASE,
	},
	{
		.name		= "size",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdtgroup_size_show,
		.fflags		= RFTYPE_CTRL_BASE,
	},
	{
		.name		= "sparse_masks",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_has_sparse_bitmasks_show,
		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
	},
	{
		.name		= "ctrl_hw_id",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdtgroup_closid_show,
		.fflags		= RFTYPE_CTRL_BASE | RFTYPE_DEBUG,
	},

};

static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
{
	struct rftype *rfts, *rft;
	int ret, len;

	rfts = res_common_files;
	len = ARRAY_SIZE(res_common_files);

	lockdep_assert_held(&rdtgroup_mutex);

	if (resctrl_debug)
		fflags |= RFTYPE_DEBUG;

	for (rft = rfts; rft < rfts + len; rft++) {
		if (rft->fflags && ((fflags & rft->fflags) == rft->fflags)) {
			ret = rdtgroup_add_file(kn, rft);
			if (ret)
				goto error;
		}
	}

	return 0;
error:
	pr_warn("Failed to add %s, err=%d\n", rft->name, ret);
	while (--rft >= rfts) {
		if ((fflags & rft->fflags) == rft->fflags)
			kernfs_remove_by_name(kn, rft->name);
	}
	return ret;
}

static struct rftype *rdtgroup_get_rftype_by_name(const char *name)
{
	struct rftype *rfts, *rft;
	int len;

	rfts = res_common_files;
	len = ARRAY_SIZE(res_common_files);

	for (rft = rfts; rft < rfts + len; rft++) {
		if (!strcmp(rft->name, name))
			return rft;
	}

	return NULL;
}

void __init thread_throttle_mode_init(void)
{
	struct rftype *rft;

	rft = rdtgroup_get_rftype_by_name("thread_throttle_mode");
	if (!rft)
		return;

	rft->fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB;
}

void __init mbm_config_rftype_init(const char *config)
{
	struct rftype *rft;

	rft = rdtgroup_get_rftype_by_name(config);
	if (rft)
		rft->fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE;
}

/**
 * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file
 * @r: The resource group with which the file is associated.
 * @name: Name of the file
 *
 * The permissions of named resctrl file, directory, or link are modified
 * to not allow read, write, or execute by any user.
 *
 * WARNING: This function is intended to communicate to the user that the
 * resctrl file has been locked down - that it is not relevant to the
 * particular state the system finds itself in. It should not be relied
 * on to protect from user access because after the file's permissions
 * are restricted the user can still change the permissions using chmod
 * from the command line.
 *
 * Return: 0 on success, <0 on failure.
 */
int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name)
{
	struct iattr iattr = {.ia_valid = ATTR_MODE,};
	struct kernfs_node *kn;
	int ret = 0;

	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
	if (!kn)
		return -ENOENT;

	switch (kernfs_type(kn)) {
	case KERNFS_DIR:
		iattr.ia_mode = S_IFDIR;
		break;
	case KERNFS_FILE:
		iattr.ia_mode = S_IFREG;
		break;
	case KERNFS_LINK:
		iattr.ia_mode = S_IFLNK;
		break;
	}

	ret = kernfs_setattr(kn, &iattr);
	kernfs_put(kn);
	return ret;
}

/**
 * rdtgroup_kn_mode_restore - Restore user access to named resctrl file
 * @r: The resource group with which the file is associated.
 * @name: Name of the file
 * @mask: Mask of permissions that should be restored
 *
 * Restore the permissions of the named file. If @name is a directory the
 * permissions of its parent will be used.
 *
 * Return: 0 on success, <0 on failure.
 */
int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
			     umode_t mask)
{
	struct iattr iattr = {.ia_valid = ATTR_MODE,};
	struct kernfs_node *kn, *parent;
	struct rftype *rfts, *rft;
	int ret, len;

	rfts = res_common_files;
	len = ARRAY_SIZE(res_common_files);

	for (rft = rfts; rft < rfts + len; rft++) {
		if (!strcmp(rft->name, name))
			iattr.ia_mode = rft->mode & mask;
	}

	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
	if (!kn)
		return -ENOENT;

	switch (kernfs_type(kn)) {
	case KERNFS_DIR:
		parent = kernfs_get_parent(kn);
		if (parent) {
			iattr.ia_mode |= parent->mode;
			kernfs_put(parent);
		}
		iattr.ia_mode |= S_IFDIR;
		break;
	case KERNFS_FILE:
		iattr.ia_mode |= S_IFREG;
		break;
	case KERNFS_LINK:
		iattr.ia_mode |= S_IFLNK;
		break;
	}

	ret = kernfs_setattr(kn, &iattr);
	kernfs_put(kn);
	return ret;
}

static int rdtgroup_mkdir_info_resdir(void *priv, char *name,
				      unsigned long fflags)
{
	struct kernfs_node *kn_subdir;
	int ret;

	kn_subdir = kernfs_create_dir(kn_info, name,
				      kn_info->mode, priv);
	if (IS_ERR(kn_subdir))
		return PTR_ERR(kn_subdir);

	ret = rdtgroup_kn_set_ugid(kn_subdir);
	if (ret)
		return ret;

	ret = rdtgroup_add_files(kn_subdir, fflags);
	if (!ret)
		kernfs_activate(kn_subdir);

	return ret;
}

static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
{
	struct resctrl_schema *s;
	struct rdt_resource *r;
	unsigned long fflags;
	char name[32];
	int ret;

	/* create the directory */
	kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
	if (IS_ERR(kn_info))
		return PTR_ERR(kn_info);

	ret = rdtgroup_add_files(kn_info, RFTYPE_TOP_INFO);
	if (ret)
		goto out_destroy;

	/* loop over enabled controls, these are all alloc_capable */
	list_for_each_entry(s, &resctrl_schema_all, list) {
		r = s->res;
		fflags = r->fflags | RFTYPE_CTRL_INFO;
		ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags);
		if (ret)
			goto out_destroy;
	}

	for_each_mon_capable_rdt_resource(r) {
		fflags = r->fflags | RFTYPE_MON_INFO;
		sprintf(name, "%s_MON", r->name);
		ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
		if (ret)
			goto out_destroy;
	}

	ret = rdtgroup_kn_set_ugid(kn_info);
	if (ret)
		goto out_destroy;

	kernfs_activate(kn_info);

	return 0;

out_destroy:
	kernfs_remove(kn_info);
	return ret;
}

static int
mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp,
		    char *name, struct kernfs_node **dest_kn)
{
	struct kernfs_node *kn;
	int ret;

	/* create the directory */
	kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
	if (IS_ERR(kn))
		return PTR_ERR(kn);

	if (dest_kn)
		*dest_kn = kn;

	ret = rdtgroup_kn_set_ugid(kn);
	if (ret)
		goto out_destroy;

	kernfs_activate(kn);

	return 0;

out_destroy:
	kernfs_remove(kn);
	return ret;
}

static void l3_qos_cfg_update(void *arg)
{
	bool *enable = arg;

	wrmsrl(MSR_IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
}

static void l2_qos_cfg_update(void *arg)
{
	bool *enable = arg;

	wrmsrl(MSR_IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
}

static inline bool is_mba_linear(void)
{
	return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.delay_linear;
}

static int set_cache_qos_cfg(int level, bool enable)
{
	void (*update)(void *arg);
	struct rdt_resource *r_l;
	cpumask_var_t cpu_mask;
	struct rdt_domain *d;
	int cpu;

	/* Walking r->domains, ensure it can't race with cpuhp */
	lockdep_assert_cpus_held();

	if (level == RDT_RESOURCE_L3)
		update = l3_qos_cfg_update;
	else if (level == RDT_RESOURCE_L2)
		update = l2_qos_cfg_update;
	else
		return -EINVAL;

	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
		return -ENOMEM;

	r_l = &rdt_resources_all[level].r_resctrl;
	list_for_each_entry(d, &r_l->domains, list) {
		if (r_l->cache.arch_has_per_cpu_cfg)
			/* Pick all the CPUs in the domain instance */
			for_each_cpu(cpu, &d->cpu_mask)
				cpumask_set_cpu(cpu, cpu_mask);
		else
			/* Pick one CPU from each domain instance to update MSR */
			cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
	}

	/* Update QOS_CFG MSR on all the CPUs in cpu_mask */
	on_each_cpu_mask(cpu_mask, update, &enable, 1);

	free_cpumask_var(cpu_mask);

	return 0;
}

/* Restore the qos cfg state when a domain comes online */
void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
{
	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);

	if (!r->cdp_capable)
		return;

	if (r->rid == RDT_RESOURCE_L2)
		l2_qos_cfg_update(&hw_res->cdp_enabled);

	if (r->rid == RDT_RESOURCE_L3)
		l3_qos_cfg_update(&hw_res->cdp_enabled);
}

static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_domain *d)
{
	u32 num_closid = resctrl_arch_get_num_closid(r);
	int cpu = cpumask_any(&d->cpu_mask);
	int i;

	d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val),
				   GFP_KERNEL, cpu_to_node(cpu));
	if (!d->mbps_val)
		return -ENOMEM;

	for (i = 0; i < num_closid; i++)
		d->mbps_val[i] = MBA_MAX_MBPS;

	return 0;
}

static void mba_sc_domain_destroy(struct rdt_resource *r,
				  struct rdt_domain *d)
{
	kfree(d->mbps_val);
	d->mbps_val = NULL;
}

/*
 * MBA software controller is supported only if
 * MBM is supported and MBA is in linear scale.
 */
static bool supports_mba_mbps(void)
{
	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;

	return (is_mbm_local_enabled() &&
		r->alloc_capable && is_mba_linear());
}

/*
 * Enable or disable the MBA software controller
 * which helps user specify bandwidth in MBps.
 */
static int set_mba_sc(bool mba_sc)
{
	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
	u32 num_closid = resctrl_arch_get_num_closid(r);
	struct rdt_domain *d;
	int i;

	if (!supports_mba_mbps() || mba_sc == is_mba_sc(r))
		return -EINVAL;

	r->membw.mba_sc = mba_sc;

	list_for_each_entry(d, &r->domains, list) {
		for (i = 0; i < num_closid; i++)
			d->mbps_val[i] = MBA_MAX_MBPS;
	}

	return 0;
}

static int cdp_enable(int level)
{
	struct rdt_resource *r_l = &rdt_resources_all[level].r_resctrl;
	int ret;

	if (!r_l->alloc_capable)
		return -EINVAL;

	ret = set_cache_qos_cfg(level, true);
	if (!ret)
		rdt_resources_all[level].cdp_enabled = true;

	return ret;
}

static void cdp_disable(int level)
{
	struct rdt_hw_resource *r_hw = &rdt_resources_all[level];

	if (r_hw->cdp_enabled) {
		set_cache_qos_cfg(level, false);
		r_hw->cdp_enabled = false;
	}
}

int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable)
{
	struct rdt_hw_resource *hw_res = &rdt_resources_all[l];

	if (!hw_res->r_resctrl.cdp_capable)
		return -EINVAL;

	if (enable)
		return cdp_enable(l);

	cdp_disable(l);

	return 0;
}

/*
 * We don't allow rdtgroup directories to be created anywhere
 * except the root directory. Thus when looking for the rdtgroup
 * structure for a kernfs node we are either looking at a directory,
 * in which case the rdtgroup structure is pointed at by the "priv"
 * field, otherwise we have a file, and need only look to the parent
 * to find the rdtgroup.
 */
static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn)
{
	if (kernfs_type(kn) == KERNFS_DIR) {
		/*
		 * All the resource directories use "kn->priv"
		 * to point to the "struct rdtgroup" for the
		 * resource. "info" and its subdirectories don't
		 * have rdtgroup structures, so return NULL here.
		 */
		if (kn == kn_info || kn->parent == kn_info)
			return NULL;
		else
			return kn->priv;
	} else {
		return kn->parent->priv;
	}
}

static void rdtgroup_kn_get(struct rdtgroup *rdtgrp, struct kernfs_node *kn)
{
	atomic_inc(&rdtgrp->waitcount);
	kernfs_break_active_protection(kn);
}

static void rdtgroup_kn_put(struct rdtgroup *rdtgrp, struct kernfs_node *kn)
{
	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
	    (rdtgrp->flags & RDT_DELETED)) {
		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
			rdtgroup_pseudo_lock_remove(rdtgrp);
		kernfs_unbreak_active_protection(kn);
		rdtgroup_remove(rdtgrp);
	} else {
		kernfs_unbreak_active_protection(kn);
	}
}

struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn)
{
	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);

	if (!rdtgrp)
		return NULL;

	rdtgroup_kn_get(rdtgrp, kn);

	cpus_read_lock();
	mutex_lock(&rdtgroup_mutex);

	/* Was this group deleted while we waited? */
	if (rdtgrp->flags & RDT_DELETED)
		return NULL;

	return rdtgrp;
}

void rdtgroup_kn_unlock(struct kernfs_node *kn)
{
	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);

	if (!rdtgrp)
		return;

	mutex_unlock(&rdtgroup_mutex);
	cpus_read_unlock();

	rdtgroup_kn_put(rdtgrp, kn);
}

static int mkdir_mondata_all(struct kernfs_node *parent_kn,
			     struct rdtgroup *prgrp,
			     struct kernfs_node **mon_data_kn);

static void rdt_disable_ctx(void)
{
	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
	set_mba_sc(false);

	resctrl_debug = false;
}

static int rdt_enable_ctx(struct rdt_fs_context *ctx)
{
	int ret = 0;

	if (ctx->enable_cdpl2) {
		ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, true);
		if (ret)
			goto out_done;
	}

	if (ctx->enable_cdpl3) {
		ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, true);
		if (ret)
			goto out_cdpl2;
	}

	if (ctx->enable_mba_mbps) {
		ret = set_mba_sc(true);
		if (ret)
			goto out_cdpl3;
	}

	if (ctx->enable_debug)
		resctrl_debug = true;

	return 0;

out_cdpl3:
	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
out_cdpl2:
	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
out_done:
	return ret;
}

static int schemata_list_add(struct rdt_resource *r, enum resctrl_conf_type type)
{
	struct resctrl_schema *s;
	const char *suffix = "";
	int ret, cl;

	s = kzalloc(sizeof(*s), GFP_KERNEL);
	if (!s)
		return -ENOMEM;

	s->res = r;
	s->num_closid = resctrl_arch_get_num_closid(r);
	if (resctrl_arch_get_cdp_enabled(r->rid))
		s->num_closid /= 2;

	s->conf_type = type;
	switch (type) {
	case CDP_CODE:
		suffix = "CODE";
		break;
	case CDP_DATA:
		suffix = "DATA";
		break;
	case CDP_NONE:
		suffix = "";
		break;
	}

	ret = snprintf(s->name, sizeof(s->name), "%s%s", r->name, suffix);
	if (ret >= sizeof(s->name)) {
		kfree(s);
		return -EINVAL;
	}

	cl = strlen(s->name);

	/*
	 * If CDP is supported by this resource, but not enabled,
	 * include the suffix. This ensures the tabular format of the
	 * schemata file does not change between mounts of the filesystem.
	 */
	if (r->cdp_capable && !resctrl_arch_get_cdp_enabled(r->rid))
		cl += 4;

	if (cl > max_name_width)
		max_name_width = cl;

	INIT_LIST_HEAD(&s->list);
	list_add(&s->list, &resctrl_schema_all);

	return 0;
}

static int schemata_list_create(void)
{
	struct rdt_resource *r;
	int ret = 0;

	for_each_alloc_capable_rdt_resource(r) {
		if (resctrl_arch_get_cdp_enabled(r->rid)) {
			ret = schemata_list_add(r, CDP_CODE);
			if (ret)
				break;

			ret = schemata_list_add(r, CDP_DATA);
		} else {
			ret = schemata_list_add(r, CDP_NONE);
		}

		if (ret)
			break;
	}

	return ret;
}

static void schemata_list_destroy(void)
{
	struct resctrl_schema *s, *tmp;

	list_for_each_entry_safe(s, tmp, &resctrl_schema_all, list) {
		list_del(&s->list);
		kfree(s);
	}
}

static int rdt_get_tree(struct fs_context *fc)
{
	struct rdt_fs_context *ctx = rdt_fc2context(fc);
	unsigned long flags = RFTYPE_CTRL_BASE;
	struct rdt_domain *dom;
	struct rdt_resource *r;
	int ret;

	cpus_read_lock();
	mutex_lock(&rdtgroup_mutex);
	/*
	 * resctrl file system can only be mounted once.
	 */
	if (resctrl_mounted) {
		ret = -EBUSY;
		goto out;
	}

	ret = rdtgroup_setup_root(ctx);
	if (ret)
		goto out;

	ret = rdt_enable_ctx(ctx);
	if (ret)
		goto out_root;

	ret = schemata_list_create();
	if (ret) {
		schemata_list_destroy();
		goto out_ctx;
	}

	closid_init();

	if (resctrl_arch_mon_capable())
		flags |= RFTYPE_MON;

	ret = rdtgroup_add_files(rdtgroup_default.kn, flags);
	if (ret)
		goto out_schemata_free;

	kernfs_activate(rdtgroup_default.kn);

	ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
	if (ret < 0)
		goto out_schemata_free;

	if (resctrl_arch_mon_capable()) {
		ret = mongroup_create_dir(rdtgroup_default.kn,
					  &rdtgroup_default, "mon_groups",
					  &kn_mongrp);
		if (ret < 0)
			goto out_info;

		ret = mkdir_mondata_all(rdtgroup_default.kn,
					&rdtgroup_default, &kn_mondata);
		if (ret < 0)
			goto out_mongrp;
		rdtgroup_default.mon.mon_data_kn = kn_mondata;
	}

	ret = rdt_pseudo_lock_init();
	if (ret)
		goto out_mondata;

	ret = kernfs_get_tree(fc);
	if (ret < 0)
		goto out_psl;

	if (resctrl_arch_alloc_capable())
		resctrl_arch_enable_alloc();
	if (resctrl_arch_mon_capable())
		resctrl_arch_enable_mon();

	if (resctrl_arch_alloc_capable() || resctrl_arch_mon_capable())
		resctrl_mounted = true;

	if (is_mbm_enabled()) {
		r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
		list_for_each_entry(dom, &r->domains, list)
			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
						   RESCTRL_PICK_ANY_CPU);
	}

	goto out;

out_psl:
	rdt_pseudo_lock_release();
out_mondata:
	if (resctrl_arch_mon_capable())
		kernfs_remove(kn_mondata);
out_mongrp:
	if (resctrl_arch_mon_capable())
		kernfs_remove(kn_mongrp);
out_info:
	kernfs_remove(kn_info);
out_schemata_free:
	schemata_list_destroy();
out_ctx:
	rdt_disable_ctx();
out_root:
	rdtgroup_destroy_root();
out:
	rdt_last_cmd_clear();
	mutex_unlock(&rdtgroup_mutex);
	cpus_read_unlock();
	return ret;
}

enum rdt_param {
	Opt_cdp,
	Opt_cdpl2,
	Opt_mba_mbps,
	Opt_debug,
	nr__rdt_params
};

static const struct fs_parameter_spec rdt_fs_parameters[] = {
	fsparam_flag("cdp",		Opt_cdp),
	fsparam_flag("cdpl2",		Opt_cdpl2),
	fsparam_flag("mba_MBps",	Opt_mba_mbps),
	fsparam_flag("debug",		Opt_debug),
	{}
};

static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
	struct rdt_fs_context *ctx = rdt_fc2context(fc);
	struct fs_parse_result result;
	int opt;

	opt = fs_parse(fc, rdt_fs_parameters, param, &result);
	if (opt < 0)
		return opt;

	switch (opt) {
	case Opt_cdp:
		ctx->enable_cdpl3 = true;
		return 0;
	case Opt_cdpl2:
		ctx->enable_cdpl2 = true;
		return 0;
	case Opt_mba_mbps:
		if (!supports_mba_mbps())
			return -EINVAL;
		ctx->enable_mba_mbps = true;
		return 0;
	case Opt_debug:
		ctx->enable_debug = true;
		return 0;
	}

	return -EINVAL;
}

static void rdt_fs_context_free(struct fs_context *fc)
{
	struct rdt_fs_context *ctx = rdt_fc2context(fc);

	kernfs_free_fs_context(fc);
	kfree(ctx);
}

static const struct fs_context_operations rdt_fs_context_ops = {
	.free		= rdt_fs_context_free,
	.parse_param	= rdt_parse_param,
	.get_tree	= rdt_get_tree,
};

static int rdt_init_fs_context(struct fs_context *fc)
{
	struct rdt_fs_context *ctx;

	ctx = kzalloc(sizeof(struct rdt_fs_context), GFP_KERNEL);
	if (!ctx)
		return -ENOMEM;

	ctx->kfc.magic = RDTGROUP_SUPER_MAGIC;
	fc->fs_private = &ctx->kfc;
	fc->ops = &rdt_fs_context_ops;
	put_user_ns(fc->user_ns);
	fc->user_ns = get_user_ns(&init_user_ns);
	fc->global = true;
	return 0;
}

static int reset_all_ctrls(struct rdt_resource *r)
{
	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
	struct rdt_hw_domain *hw_dom;
	struct msr_param msr_param;
	cpumask_var_t cpu_mask;
	struct rdt_domain *d;
	int i;

	/* Walking r->domains, ensure it can't race with cpuhp */
	lockdep_assert_cpus_held();

	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
		return -ENOMEM;

	msr_param.res = r;
	msr_param.low = 0;
	msr_param.high = hw_res->num_closid;

	/*
	 * Disable resource control for this resource by setting all
	 * CBMs in all domains to the maximum mask value. Pick one CPU
	 * from each domain to update the MSRs below.
	 */
	list_for_each_entry(d, &r->domains, list) {
		hw_dom = resctrl_to_arch_dom(d);
		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);

		for (i = 0; i < hw_res->num_closid; i++)
			hw_dom->ctrl_val[i] = r->default_ctrl;
	}

	/* Update CBM on all the CPUs in cpu_mask */
	on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1);

	free_cpumask_var(cpu_mask);

	return 0;
}

/*
 * Move tasks from one to the other group. If @from is NULL, then all tasks
 * in the systems are moved unconditionally (used for teardown).
 *
 * If @mask is not NULL the cpus on which moved tasks are running are set
 * in that mask so the update smp function call is restricted to affected
 * cpus.
 */
static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
				 struct cpumask *mask)
{
	struct task_struct *p, *t;

	read_lock(&tasklist_lock);
	for_each_process_thread(p, t) {
		if (!from || is_closid_match(t, from) ||
		    is_rmid_match(t, from)) {
			resctrl_arch_set_closid_rmid(t, to->closid,
						     to->mon.rmid);

			/*
			 * Order the closid/rmid stores above before the loads
			 * in task_curr(). This pairs with the full barrier
			 * between the rq->curr update and resctrl_sched_in()
			 * during context switch.
			 */
			smp_mb();

			/*
			 * If the task is on a CPU, set the CPU in the mask.
			 * The detection is inaccurate as tasks might move or
			 * schedule before the smp function call takes place.
			 * In such a case the function call is pointless, but
			 * there is no other side effect.
			 */
			if (IS_ENABLED(CONFIG_SMP) && mask && task_curr(t))
				cpumask_set_cpu(task_cpu(t), mask);
		}
	}
	read_unlock(&tasklist_lock);
}

static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
{
	struct rdtgroup *sentry, *stmp;
	struct list_head *head;

	head = &rdtgrp->mon.crdtgrp_list;
	list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
		free_rmid(sentry->closid, sentry->mon.rmid);
		list_del(&sentry->mon.crdtgrp_list);

		if (atomic_read(&sentry->waitcount) != 0)
			sentry->flags = RDT_DELETED;
		else
			rdtgroup_remove(sentry);
	}
}

/*
 * Forcibly remove all of subdirectories under root.
 */
static void rmdir_all_sub(void)
{
	struct rdtgroup *rdtgrp, *tmp;

	/* Move all tasks to the default resource group */
	rdt_move_group_tasks(NULL, &rdtgroup_default, NULL);

	list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) {
		/* Free any child rmids */
		free_all_child_rdtgrp(rdtgrp);

		/* Remove each rdtgroup other than root */
		if (rdtgrp == &rdtgroup_default)
			continue;

		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
			rdtgroup_pseudo_lock_remove(rdtgrp);

		/*
		 * Give any CPUs back to the default group. We cannot copy
		 * cpu_online_mask because a CPU might have executed the
		 * offline callback already, but is still marked online.
		 */
		cpumask_or(&rdtgroup_default.cpu_mask,
			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);

		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);

		kernfs_remove(rdtgrp->kn);
		list_del(&rdtgrp->rdtgroup_list);

		if (atomic_read(&rdtgrp->waitcount) != 0)
			rdtgrp->flags = RDT_DELETED;
		else
			rdtgroup_remove(rdtgrp);
	}
	/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
	update_closid_rmid(cpu_online_mask, &rdtgroup_default);

	kernfs_remove(kn_info);
	kernfs_remove(kn_mongrp);
	kernfs_remove(kn_mondata);
}

static void rdt_kill_sb(struct super_block *sb)
{
	struct rdt_resource *r;

	cpus_read_lock();
	mutex_lock(&rdtgroup_mutex);

	rdt_disable_ctx();

	/*Put everything back to default values. */
	for_each_alloc_capable_rdt_resource(r)
		reset_all_ctrls(r);
	rmdir_all_sub();
	rdt_pseudo_lock_release();
	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
	schemata_list_destroy();
	rdtgroup_destroy_root();
	if (resctrl_arch_alloc_capable())
		resctrl_arch_disable_alloc();
	if (resctrl_arch_mon_capable())
		resctrl_arch_disable_mon();
	resctrl_mounted = false;
	kernfs_kill_sb(sb);
	mutex_unlock(&rdtgroup_mutex);
	cpus_read_unlock();
}

static struct file_system_type rdt_fs_type = {
	.name			= "resctrl",
	.init_fs_context	= rdt_init_fs_context,
	.parameters		= rdt_fs_parameters,
	.kill_sb		= rdt_kill_sb,
};

static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
		       void *priv)
{
	struct kernfs_node *kn;
	int ret = 0;

	kn = __kernfs_create_file(parent_kn, name, 0444,
				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0,
				  &kf_mondata_ops, priv, NULL, NULL);
	if (IS_ERR(kn))
		return PTR_ERR(kn);

	ret = rdtgroup_kn_set_ugid(kn);
	if (ret) {
		kernfs_remove(kn);
		return ret;
	}

	return ret;
}

/*
 * Remove all subdirectories of mon_data of ctrl_mon groups
 * and monitor groups with given domain id.
 */
static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
					   unsigned int dom_id)
{
	struct rdtgroup *prgrp, *crgrp;
	char name[32];

	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
		sprintf(name, "mon_%s_%02d", r->name, dom_id);
		kernfs_remove_by_name(prgrp->mon.mon_data_kn, name);

		list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list)
			kernfs_remove_by_name(crgrp->mon.mon_data_kn, name);
	}
}

static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
				struct rdt_domain *d,
				struct rdt_resource *r, struct rdtgroup *prgrp)
{
	union mon_data_bits priv;
	struct kernfs_node *kn;
	struct mon_evt *mevt;
	struct rmid_read rr;
	char name[32];
	int ret;

	sprintf(name, "mon_%s_%02d", r->name, d->id);
	/* create the directory */
	kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
	if (IS_ERR(kn))
		return PTR_ERR(kn);

	ret = rdtgroup_kn_set_ugid(kn);
	if (ret)
		goto out_destroy;

	if (WARN_ON(list_empty(&r->evt_list))) {
		ret = -EPERM;
		goto out_destroy;
	}

	priv.u.rid = r->rid;
	priv.u.domid = d->id;
	list_for_each_entry(mevt, &r->evt_list, list) {
		priv.u.evtid = mevt->evtid;
		ret = mon_addfile(kn, mevt->name, priv.priv);
		if (ret)
			goto out_destroy;

		if (is_mbm_event(mevt->evtid))
			mon_event_read(&rr, r, d, prgrp, mevt->evtid, true);
	}
	kernfs_activate(kn);
	return 0;

out_destroy:
	kernfs_remove(kn);
	return ret;
}

/*
 * Add all subdirectories of mon_data for "ctrl_mon" groups
 * and "monitor" groups with given domain id.
 */
static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
					   struct rdt_domain *d)
{
	struct kernfs_node *parent_kn;
	struct rdtgroup *prgrp, *crgrp;
	struct list_head *head;

	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
		parent_kn = prgrp->mon.mon_data_kn;
		mkdir_mondata_subdir(parent_kn, d, r, prgrp);

		head = &prgrp->mon.crdtgrp_list;
		list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
			parent_kn = crgrp->mon.mon_data_kn;
			mkdir_mondata_subdir(parent_kn, d, r, crgrp);
		}
	}
}

static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
				       struct rdt_resource *r,
				       struct rdtgroup *prgrp)
{
	struct rdt_domain *dom;
	int ret;

	/* Walking r->domains, ensure it can't race with cpuhp */
	lockdep_assert_cpus_held();

	list_for_each_entry(dom, &r->domains, list) {
		ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
		if (ret)
			return ret;
	}

	return 0;
}

/*
 * This creates a directory mon_data which contains the monitored data.
 *
 * mon_data has one directory for each domain which are named
 * in the format mon_<domain_name>_<domain_id>. For ex: A mon_data
 * with L3 domain looks as below:
 * ./mon_data:
 * mon_L3_00
 * mon_L3_01
 * mon_L3_02
 * ...
 *
 * Each domain directory has one file per event:
 * ./mon_L3_00/:
 * llc_occupancy
 *
 */
static int mkdir_mondata_all(struct kernfs_node *parent_kn,
			     struct rdtgroup *prgrp,
			     struct kernfs_node **dest_kn)
{
	struct rdt_resource *r;
	struct kernfs_node *kn;
	int ret;

	/*
	 * Create the mon_data directory first.
	 */
	ret = mongroup_create_dir(parent_kn, prgrp, "mon_data", &kn);
	if (ret)
		return ret;

	if (dest_kn)
		*dest_kn = kn;

	/*
	 * Create the subdirectories for each domain. Note that all events
	 * in a domain like L3 are grouped into a resource whose domain is L3
	 */
	for_each_mon_capable_rdt_resource(r) {
		ret = mkdir_mondata_subdir_alldom(kn, r, prgrp);
		if (ret)
			goto out_destroy;
	}

	return 0;

out_destroy:
	kernfs_remove(kn);
	return ret;
}

/**
 * cbm_ensure_valid - Enforce validity on provided CBM
 * @_val:	Candidate CBM
 * @r:		RDT resource to which the CBM belongs
 *
 * The provided CBM represents all cache portions available for use. This
 * may be represented by a bitmap that does not consist of contiguous ones
 * and thus be an invalid CBM.
 * Here the provided CBM is forced to be a valid CBM by only considering
 * the first set of contiguous bits as valid and clearing all bits.
 * The intention here is to provide a valid default CBM with which a new
 * resource group is initialized. The user can follow this with a
 * modification to the CBM if the default does not satisfy the
 * requirements.
 */
static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r)
{
	unsigned int cbm_len = r->cache.cbm_len;
	unsigned long first_bit, zero_bit;
	unsigned long val = _val;

	if (!val)
		return 0;

	first_bit = find_first_bit(&val, cbm_len);
	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);

	/* Clear any remaining bits to ensure contiguous region */
	bitmap_clear(&val, zero_bit, cbm_len - zero_bit);
	return (u32)val;
}

/*
 * Initialize cache resources per RDT domain
 *
 * Set the RDT domain up to start off with all usable allocations. That is,
 * all shareable and unused bits. All-zero CBM is invalid.
 */
static int __init_one_rdt_domain(struct rdt_domain *d, struct resctrl_schema *s,
				 u32 closid)
{
	enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
	enum resctrl_conf_type t = s->conf_type;
	struct resctrl_staged_config *cfg;
	struct rdt_resource *r = s->res;
	u32 used_b = 0, unused_b = 0;
	unsigned long tmp_cbm;
	enum rdtgrp_mode mode;
	u32 peer_ctl, ctrl_val;
	int i;

	cfg = &d->staged_config[t];
	cfg->have_new_ctrl = false;
	cfg->new_ctrl = r->cache.shareable_bits;
	used_b = r->cache.shareable_bits;
	for (i = 0; i < closids_supported(); i++) {
		if (closid_allocated(i) && i != closid) {
			mode = rdtgroup_mode_by_closid(i);
			if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
				/*
				 * ctrl values for locksetup aren't relevant
				 * until the schemata is written, and the mode
				 * becomes RDT_MODE_PSEUDO_LOCKED.
				 */
				continue;
			/*
			 * If CDP is active include peer domain's
			 * usage to ensure there is no overlap
			 * with an exclusive group.
			 */
			if (resctrl_arch_get_cdp_enabled(r->rid))
				peer_ctl = resctrl_arch_get_config(r, d, i,
								   peer_type);
			else
				peer_ctl = 0;
			ctrl_val = resctrl_arch_get_config(r, d, i,
							   s->conf_type);
			used_b |= ctrl_val | peer_ctl;
			if (mode == RDT_MODE_SHAREABLE)
				cfg->new_ctrl |= ctrl_val | peer_ctl;
		}
	}
	if (d->plr && d->plr->cbm > 0)
		used_b |= d->plr->cbm;
	unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
	unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
	cfg->new_ctrl |= unused_b;
	/*
	 * Force the initial CBM to be valid, user can
	 * modify the CBM based on system availability.
	 */
	cfg->new_ctrl = cbm_ensure_valid(cfg->new_ctrl, r);
	/*
	 * Assign the u32 CBM to an unsigned long to ensure that
	 * bitmap_weight() does not access out-of-bound memory.
	 */
	tmp_cbm = cfg->new_ctrl;
	if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) {
		rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->id);
		return -ENOSPC;
	}
	cfg->have_new_ctrl = true;

	return 0;
}

/*
 * Initialize cache resources with default values.
 *
 * A new RDT group is being created on an allocation capable (CAT)
 * supporting system. Set this group up to start off with all usable
 * allocations.
 *
 * If there are no more shareable bits available on any domain then
 * the entire allocation will fail.
 */
static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
{
	struct rdt_domain *d;
	int ret;

	list_for_each_entry(d, &s->res->domains, list) {
		ret = __init_one_rdt_domain(d, s, closid);
		if (ret < 0)
			return ret;
	}

	return 0;
}

/* Initialize MBA resource with default values. */
static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid)
{
	struct resctrl_staged_config *cfg;
	struct rdt_domain *d;

	list_for_each_entry(d, &r->domains, list) {
		if (is_mba_sc(r)) {
			d->mbps_val[closid] = MBA_MAX_MBPS;
			continue;
		}

		cfg = &d->staged_config[CDP_NONE];
		cfg->new_ctrl = r->default_ctrl;
		cfg->have_new_ctrl = true;
	}
}

/* Initialize the RDT group's allocations. */
static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
{
	struct resctrl_schema *s;
	struct rdt_resource *r;
	int ret = 0;

	rdt_staged_configs_clear();

	list_for_each_entry(s, &resctrl_schema_all, list) {
		r = s->res;
		if (r->rid == RDT_RESOURCE_MBA ||
		    r->rid == RDT_RESOURCE_SMBA) {
			rdtgroup_init_mba(r, rdtgrp->closid);
			if (is_mba_sc(r))
				continue;
		} else {
			ret = rdtgroup_init_cat(s, rdtgrp->closid);
			if (ret < 0)
				goto out;
		}

		ret = resctrl_arch_update_domains(r, rdtgrp->closid);
		if (ret < 0) {
			rdt_last_cmd_puts("Failed to initialize allocations\n");
			goto out;
		}

	}

	rdtgrp->mode = RDT_MODE_SHAREABLE;

out:
	rdt_staged_configs_clear();
	return ret;
}

static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp)
{
	int ret;

	if (!resctrl_arch_mon_capable())
		return 0;

	ret = alloc_rmid(rdtgrp->closid);
	if (ret < 0) {
		rdt_last_cmd_puts("Out of RMIDs\n");
		return ret;
	}
	rdtgrp->mon.rmid = ret;

	ret = mkdir_mondata_all(rdtgrp->kn, rdtgrp, &rdtgrp->mon.mon_data_kn);
	if (ret) {
		rdt_last_cmd_puts("kernfs subdir error\n");
		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
		return ret;
	}

	return 0;
}

static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp)
{
	if (resctrl_arch_mon_capable())
		free_rmid(rgrp->closid, rgrp->mon.rmid);
}

static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
			     const char *name, umode_t mode,
			     enum rdt_group_type rtype, struct rdtgroup **r)
{
	struct rdtgroup *prdtgrp, *rdtgrp;
	unsigned long files = 0;
	struct kernfs_node *kn;
	int ret;

	prdtgrp = rdtgroup_kn_lock_live(parent_kn);
	if (!prdtgrp) {
		ret = -ENODEV;
		goto out_unlock;
	}

	if (rtype == RDTMON_GROUP &&
	    (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
	     prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) {
		ret = -EINVAL;
		rdt_last_cmd_puts("Pseudo-locking in progress\n");
		goto out_unlock;
	}

	/* allocate the rdtgroup. */
	rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
	if (!rdtgrp) {
		ret = -ENOSPC;
		rdt_last_cmd_puts("Kernel out of memory\n");
		goto out_unlock;
	}
	*r = rdtgrp;
	rdtgrp->mon.parent = prdtgrp;
	rdtgrp->type = rtype;
	INIT_LIST_HEAD(&rdtgrp->mon.crdtgrp_list);

	/* kernfs creates the directory for rdtgrp */
	kn = kernfs_create_dir(parent_kn, name, mode, rdtgrp);
	if (IS_ERR(kn)) {
		ret = PTR_ERR(kn);
		rdt_last_cmd_puts("kernfs create error\n");
		goto out_free_rgrp;
	}
	rdtgrp->kn = kn;

	/*
	 * kernfs_remove() will drop the reference count on "kn" which
	 * will free it. But we still need it to stick around for the
	 * rdtgroup_kn_unlock(kn) call. Take one extra reference here,
	 * which will be dropped by kernfs_put() in rdtgroup_remove().
	 */
	kernfs_get(kn);

	ret = rdtgroup_kn_set_ugid(kn);
	if (ret) {
		rdt_last_cmd_puts("kernfs perm error\n");
		goto out_destroy;
	}

	if (rtype == RDTCTRL_GROUP) {
		files = RFTYPE_BASE | RFTYPE_CTRL;
		if (resctrl_arch_mon_capable())
			files |= RFTYPE_MON;
	} else {
		files = RFTYPE_BASE | RFTYPE_MON;
	}

	ret = rdtgroup_add_files(kn, files);
	if (ret) {
		rdt_last_cmd_puts("kernfs fill error\n");
		goto out_destroy;
	}

	/*
	 * The caller unlocks the parent_kn upon success.
	 */
	return 0;

out_destroy:
	kernfs_put(rdtgrp->kn);
	kernfs_remove(rdtgrp->kn);
out_free_rgrp:
	kfree(rdtgrp);
out_unlock:
	rdtgroup_kn_unlock(parent_kn);
	return ret;
}

static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp)
{
	kernfs_remove(rgrp->kn);
	rdtgroup_remove(rgrp);
}

/*
 * Create a monitor group under "mon_groups" directory of a control
 * and monitor group(ctrl_mon). This is a resource group
 * to monitor a subset of tasks and cpus in its parent ctrl_mon group.
 */
static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn,
			      const char *name, umode_t mode)
{
	struct rdtgroup *rdtgrp, *prgrp;
	int ret;

	ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTMON_GROUP, &rdtgrp);
	if (ret)
		return ret;

	prgrp = rdtgrp->mon.parent;
	rdtgrp->closid = prgrp->closid;

	ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp);
	if (ret) {
		mkdir_rdt_prepare_clean(rdtgrp);
		goto out_unlock;
	}

	kernfs_activate(rdtgrp->kn);

	/*
	 * Add the rdtgrp to the list of rdtgrps the parent
	 * ctrl_mon group has to track.
	 */
	list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list);

out_unlock:
	rdtgroup_kn_unlock(parent_kn);
	return ret;
}

/*
 * These are rdtgroups created under the root directory. Can be used
 * to allocate and monitor resources.
 */
static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
				   const char *name, umode_t mode)
{
	struct rdtgroup *rdtgrp;
	struct kernfs_node *kn;
	u32 closid;
	int ret;

	ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTCTRL_GROUP, &rdtgrp);
	if (ret)
		return ret;

	kn = rdtgrp->kn;
	ret = closid_alloc();
	if (ret < 0) {
		rdt_last_cmd_puts("Out of CLOSIDs\n");
		goto out_common_fail;
	}
	closid = ret;
	ret = 0;

	rdtgrp->closid = closid;

	ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp);
	if (ret)
		goto out_closid_free;

	kernfs_activate(rdtgrp->kn);

	ret = rdtgroup_init_alloc(rdtgrp);
	if (ret < 0)
		goto out_rmid_free;

	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);

	if (resctrl_arch_mon_capable()) {
		/*
		 * Create an empty mon_groups directory to hold the subset
		 * of tasks and cpus to monitor.
		 */
		ret = mongroup_create_dir(kn, rdtgrp, "mon_groups", NULL);
		if (ret) {
			rdt_last_cmd_puts("kernfs subdir error\n");
			goto out_del_list;
		}
	}

	goto out_unlock;

out_del_list:
	list_del(&rdtgrp->rdtgroup_list);
out_rmid_free:
	mkdir_rdt_prepare_rmid_free(rdtgrp);
out_closid_free:
	closid_free(closid);
out_common_fail:
	mkdir_rdt_prepare_clean(rdtgrp);
out_unlock:
	rdtgroup_kn_unlock(parent_kn);
	return ret;
}

/*
 * We allow creating mon groups only with in a directory called "mon_groups"
 * which is present in every ctrl_mon group. Check if this is a valid
 * "mon_groups" directory.
 *
 * 1. The directory should be named "mon_groups".
 * 2. The mon group itself should "not" be named "mon_groups".
 *   This makes sure "mon_groups" directory always has a ctrl_mon group
 *   as parent.
 */
static bool is_mon_groups(struct kernfs_node *kn, const char *name)
{
	return (!strcmp(kn->name, "mon_groups") &&
		strcmp(name, "mon_groups"));
}

static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
			  umode_t mode)
{
	/* Do not accept '\n' to avoid unparsable situation. */
	if (strchr(name, '\n'))
		return -EINVAL;

	/*
	 * If the parent directory is the root directory and RDT
	 * allocation is supported, add a control and monitoring
	 * subdirectory
	 */
	if (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn)
		return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode);

	/*
	 * If RDT monitoring is supported and the parent directory is a valid
	 * "mon_groups" directory, add a monitoring subdirectory.
	 */
	if (resctrl_arch_mon_capable() && is_mon_groups(parent_kn, name))
		return rdtgroup_mkdir_mon(parent_kn, name, mode);

	return -EPERM;
}

static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
{
	struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
	int cpu;

	/* Give any tasks back to the parent group */
	rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask);

	/* Update per cpu rmid of the moved CPUs first */
	for_each_cpu(cpu, &rdtgrp->cpu_mask)
		per_cpu(pqr_state.default_rmid, cpu) = prdtgrp->mon.rmid;
	/*
	 * Update the MSR on moved CPUs and CPUs which have moved
	 * task running on them.
	 */
	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
	update_closid_rmid(tmpmask, NULL);

	rdtgrp->flags = RDT_DELETED;
	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);

	/*
	 * Remove the rdtgrp from the parent ctrl_mon group's list
	 */
	WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
	list_del(&rdtgrp->mon.crdtgrp_list);

	kernfs_remove(rdtgrp->kn);

	return 0;
}

static int rdtgroup_ctrl_remove(struct rdtgroup *rdtgrp)
{
	rdtgrp->flags = RDT_DELETED;
	list_del(&rdtgrp->rdtgroup_list);

	kernfs_remove(rdtgrp->kn);
	return 0;
}

static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
{
	int cpu;

	/* Give any tasks back to the default group */
	rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask);

	/* Give any CPUs back to the default group */
	cpumask_or(&rdtgroup_default.cpu_mask,
		   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);

	/* Update per cpu closid and rmid of the moved CPUs first */
	for_each_cpu(cpu, &rdtgrp->cpu_mask) {
		per_cpu(pqr_state.default_closid, cpu) = rdtgroup_default.closid;
		per_cpu(pqr_state.default_rmid, cpu) = rdtgroup_default.mon.rmid;
	}

	/*
	 * Update the MSR on moved CPUs and CPUs which have moved
	 * task running on them.
	 */
	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
	update_closid_rmid(tmpmask, NULL);

	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
	closid_free(rdtgrp->closid);

	rdtgroup_ctrl_remove(rdtgrp);

	/*
	 * Free all the child monitor group rmids.
	 */
	free_all_child_rdtgrp(rdtgrp);

	return 0;
}

static int rdtgroup_rmdir(struct kernfs_node *kn)
{
	struct kernfs_node *parent_kn = kn->parent;
	struct rdtgroup *rdtgrp;
	cpumask_var_t tmpmask;
	int ret = 0;

	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
		return -ENOMEM;

	rdtgrp = rdtgroup_kn_lock_live(kn);
	if (!rdtgrp) {
		ret = -EPERM;
		goto out;
	}

	/*
	 * If the rdtgroup is a ctrl_mon group and parent directory
	 * is the root directory, remove the ctrl_mon group.
	 *
	 * If the rdtgroup is a mon group and parent directory
	 * is a valid "mon_groups" directory, remove the mon group.
	 */
	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn &&
	    rdtgrp != &rdtgroup_default) {
		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
			ret = rdtgroup_ctrl_remove(rdtgrp);
		} else {
			ret = rdtgroup_rmdir_ctrl(rdtgrp, tmpmask);
		}
	} else if (rdtgrp->type == RDTMON_GROUP &&
		 is_mon_groups(parent_kn, kn->name)) {
		ret = rdtgroup_rmdir_mon(rdtgrp, tmpmask);
	} else {
		ret = -EPERM;
	}

out:
	rdtgroup_kn_unlock(kn);
	free_cpumask_var(tmpmask);
	return ret;
}

/**
 * mongrp_reparent() - replace parent CTRL_MON group of a MON group
 * @rdtgrp:		the MON group whose parent should be replaced
 * @new_prdtgrp:	replacement parent CTRL_MON group for @rdtgrp
 * @cpus:		cpumask provided by the caller for use during this call
 *
 * Replaces the parent CTRL_MON group for a MON group, resulting in all member
 * tasks' CLOSID immediately changing to that of the new parent group.
 * Monitoring data for the group is unaffected by this operation.
 */
static void mongrp_reparent(struct rdtgroup *rdtgrp,
			    struct rdtgroup *new_prdtgrp,
			    cpumask_var_t cpus)
{
	struct rdtgroup *prdtgrp = rdtgrp->mon.parent;

	WARN_ON(rdtgrp->type != RDTMON_GROUP);
	WARN_ON(new_prdtgrp->type != RDTCTRL_GROUP);

	/* Nothing to do when simply renaming a MON group. */
	if (prdtgrp == new_prdtgrp)
		return;

	WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
	list_move_tail(&rdtgrp->mon.crdtgrp_list,
		       &new_prdtgrp->mon.crdtgrp_list);

	rdtgrp->mon.parent = new_prdtgrp;
	rdtgrp->closid = new_prdtgrp->closid;

	/* Propagate updated closid to all tasks in this group. */
	rdt_move_group_tasks(rdtgrp, rdtgrp, cpus);

	update_closid_rmid(cpus, NULL);
}

static int rdtgroup_rename(struct kernfs_node *kn,
			   struct kernfs_node *new_parent, const char *new_name)
{
	struct rdtgroup *new_prdtgrp;
	struct rdtgroup *rdtgrp;
	cpumask_var_t tmpmask;
	int ret;

	rdtgrp = kernfs_to_rdtgroup(kn);
	new_prdtgrp = kernfs_to_rdtgroup(new_parent);
	if (!rdtgrp || !new_prdtgrp)
		return -ENOENT;

	/* Release both kernfs active_refs before obtaining rdtgroup mutex. */
	rdtgroup_kn_get(rdtgrp, kn);
	rdtgroup_kn_get(new_prdtgrp, new_parent);

	mutex_lock(&rdtgroup_mutex);

	rdt_last_cmd_clear();

	/*
	 * Don't allow kernfs_to_rdtgroup() to return a parent rdtgroup if
	 * either kernfs_node is a file.
	 */
	if (kernfs_type(kn) != KERNFS_DIR ||
	    kernfs_type(new_parent) != KERNFS_DIR) {
		rdt_last_cmd_puts("Source and destination must be directories");
		ret = -EPERM;
		goto out;
	}

	if ((rdtgrp->flags & RDT_DELETED) || (new_prdtgrp->flags & RDT_DELETED)) {
		ret = -ENOENT;
		goto out;
	}

	if (rdtgrp->type != RDTMON_GROUP || !kn->parent ||
	    !is_mon_groups(kn->parent, kn->name)) {
		rdt_last_cmd_puts("Source must be a MON group\n");
		ret = -EPERM;
		goto out;
	}

	if (!is_mon_groups(new_parent, new_name)) {
		rdt_last_cmd_puts("Destination must be a mon_groups subdirectory\n");
		ret = -EPERM;
		goto out;
	}

	/*
	 * If the MON group is monitoring CPUs, the CPUs must be assigned to the
	 * current parent CTRL_MON group and therefore cannot be assigned to
	 * the new parent, making the move illegal.
	 */
	if (!cpumask_empty(&rdtgrp->cpu_mask) &&
	    rdtgrp->mon.parent != new_prdtgrp) {
		rdt_last_cmd_puts("Cannot move a MON group that monitors CPUs\n");
		ret = -EPERM;
		goto out;
	}

	/*
	 * Allocate the cpumask for use in mongrp_reparent() to avoid the
	 * possibility of failing to allocate it after kernfs_rename() has
	 * succeeded.
	 */
	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) {
		ret = -ENOMEM;
		goto out;
	}

	/*
	 * Perform all input validation and allocations needed to ensure
	 * mongrp_reparent() will succeed before calling kernfs_rename(),
	 * otherwise it would be necessary to revert this call if
	 * mongrp_reparent() failed.
	 */
	ret = kernfs_rename(kn, new_parent, new_name);
	if (!ret)
		mongrp_reparent(rdtgrp, new_prdtgrp, tmpmask);

	free_cpumask_var(tmpmask);

out:
	mutex_unlock(&rdtgroup_mutex);
	rdtgroup_kn_put(rdtgrp, kn);
	rdtgroup_kn_put(new_prdtgrp, new_parent);
	return ret;
}

static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
{
	if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3))
		seq_puts(seq, ",cdp");

	if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2))
		seq_puts(seq, ",cdpl2");

	if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl))
		seq_puts(seq, ",mba_MBps");

	if (resctrl_debug)
		seq_puts(seq, ",debug");

	return 0;
}

static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
	.mkdir		= rdtgroup_mkdir,
	.rmdir		= rdtgroup_rmdir,
	.rename		= rdtgroup_rename,
	.show_options	= rdtgroup_show_options,
};

static int rdtgroup_setup_root(struct rdt_fs_context *ctx)
{
	rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
				      KERNFS_ROOT_CREATE_DEACTIVATED |
				      KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK,
				      &rdtgroup_default);
	if (IS_ERR(rdt_root))
		return PTR_ERR(rdt_root);

	ctx->kfc.root = rdt_root;
	rdtgroup_default.kn = kernfs_root_to_node(rdt_root);

	return 0;
}

static void rdtgroup_destroy_root(void)
{
	kernfs_destroy_root(rdt_root);
	rdtgroup_default.kn = NULL;
}

static void __init rdtgroup_setup_default(void)
{
	mutex_lock(&rdtgroup_mutex);

	rdtgroup_default.closid = RESCTRL_RESERVED_CLOSID;
	rdtgroup_default.mon.rmid = RESCTRL_RESERVED_RMID;
	rdtgroup_default.type = RDTCTRL_GROUP;
	INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list);

	list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups);

	mutex_unlock(&rdtgroup_mutex);
}

static void domain_destroy_mon_state(struct rdt_domain *d)
{
	bitmap_free(d->rmid_busy_llc);
	kfree(d->mbm_total);
	kfree(d->mbm_local);
}

void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d)
{
	mutex_lock(&rdtgroup_mutex);

	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
		mba_sc_domain_destroy(r, d);

	if (!r->mon_capable)
		goto out_unlock;

	/*
	 * If resctrl is mounted, remove all the
	 * per domain monitor data directories.
	 */
	if (resctrl_mounted && resctrl_arch_mon_capable())
		rmdir_mondata_subdir_allrdtgrp(r, d->id);

	if (is_mbm_enabled())
		cancel_delayed_work(&d->mbm_over);
	if (is_llc_occupancy_enabled() && has_busy_rmid(d)) {
		/*
		 * When a package is going down, forcefully
		 * decrement rmid->ebusy. There is no way to know
		 * that the L3 was flushed and hence may lead to
		 * incorrect counts in rare scenarios, but leaving
		 * the RMID as busy creates RMID leaks if the
		 * package never comes back.
		 */
		__check_limbo(d, true);
		cancel_delayed_work(&d->cqm_limbo);
	}

	domain_destroy_mon_state(d);

out_unlock:
	mutex_unlock(&rdtgroup_mutex);
}

static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
{
	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
	size_t tsize;

	if (is_llc_occupancy_enabled()) {
		d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL);
		if (!d->rmid_busy_llc)
			return -ENOMEM;
	}
	if (is_mbm_total_enabled()) {
		tsize = sizeof(*d->mbm_total);
		d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL);
		if (!d->mbm_total) {
			bitmap_free(d->rmid_busy_llc);
			return -ENOMEM;
		}
	}
	if (is_mbm_local_enabled()) {
		tsize = sizeof(*d->mbm_local);
		d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL);
		if (!d->mbm_local) {
			bitmap_free(d->rmid_busy_llc);
			kfree(d->mbm_total);
			return -ENOMEM;
		}
	}

	return 0;
}

int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d)
{
	int err = 0;

	mutex_lock(&rdtgroup_mutex);

	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) {
		/* RDT_RESOURCE_MBA is never mon_capable */
		err = mba_sc_domain_allocate(r, d);
		goto out_unlock;
	}

	if (!r->mon_capable)
		goto out_unlock;

	err = domain_setup_mon_state(r, d);
	if (err)
		goto out_unlock;

	if (is_mbm_enabled()) {
		INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
		mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL,
					   RESCTRL_PICK_ANY_CPU);
	}

	if (is_llc_occupancy_enabled())
		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);

	/*
	 * If the filesystem is not mounted then only the default resource group
	 * exists. Creation of its directories is deferred until mount time
	 * by rdt_get_tree() calling mkdir_mondata_all().
	 * If resctrl is mounted, add per domain monitor data directories.
	 */
	if (resctrl_mounted && resctrl_arch_mon_capable())
		mkdir_mondata_subdir_allrdtgrp(r, d);

out_unlock:
	mutex_unlock(&rdtgroup_mutex);

	return err;
}

void resctrl_online_cpu(unsigned int cpu)
{
	mutex_lock(&rdtgroup_mutex);
	/* The CPU is set in default rdtgroup after online. */
	cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
	mutex_unlock(&rdtgroup_mutex);
}

static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
{
	struct rdtgroup *cr;

	list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) {
		if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask))
			break;
	}
}

void resctrl_offline_cpu(unsigned int cpu)
{
	struct rdt_resource *l3 = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
	struct rdtgroup *rdtgrp;
	struct rdt_domain *d;

	mutex_lock(&rdtgroup_mutex);
	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) {
			clear_childcpus(rdtgrp, cpu);
			break;
		}
	}

	if (!l3->mon_capable)
		goto out_unlock;

	d = get_domain_from_cpu(cpu, l3);
	if (d) {
		if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
			cancel_delayed_work(&d->mbm_over);
			mbm_setup_overflow_handler(d, 0, cpu);
		}
		if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu &&
		    has_busy_rmid(d)) {
			cancel_delayed_work(&d->cqm_limbo);
			cqm_setup_limbo_handler(d, 0, cpu);
		}
	}

out_unlock:
	mutex_unlock(&rdtgroup_mutex);
}

/*
 * rdtgroup_init - rdtgroup initialization
 *
 * Setup resctrl file system including set up root, create mount point,
 * register rdtgroup filesystem, and initialize files under root directory.
 *
 * Return: 0 on success or -errno
 */
int __init rdtgroup_init(void)
{
	int ret = 0;

	seq_buf_init(&last_cmd_status, last_cmd_status_buf,
		     sizeof(last_cmd_status_buf));

	rdtgroup_setup_default();

	ret = sysfs_create_mount_point(fs_kobj, "resctrl");
	if (ret)
		return ret;

	ret = register_filesystem(&rdt_fs_type);
	if (ret)
		goto cleanup_mountpoint;

	/*
	 * Adding the resctrl debugfs directory here may not be ideal since
	 * it would let the resctrl debugfs directory appear on the debugfs
	 * filesystem before the resctrl filesystem is mounted.
	 * It may also be ok since that would enable debugging of RDT before
	 * resctrl is mounted.
	 * The reason why the debugfs directory is created here and not in
	 * rdt_get_tree() is because rdt_get_tree() takes rdtgroup_mutex and
	 * during the debugfs directory creation also &sb->s_type->i_mutex_key
	 * (the lockdep class of inode->i_rwsem). Other filesystem
	 * interactions (eg. SyS_getdents) have the lock ordering:
	 * &sb->s_type->i_mutex_key --> &mm->mmap_lock
	 * During mmap(), called with &mm->mmap_lock, the rdtgroup_mutex
	 * is taken, thus creating dependency:
	 * &mm->mmap_lock --> rdtgroup_mutex for the latter that can cause
	 * issues considering the other two lock dependencies.
	 * By creating the debugfs directory here we avoid a dependency
	 * that may cause deadlock (even though file operations cannot
	 * occur until the filesystem is mounted, but I do not know how to
	 * tell lockdep that).
	 */
	debugfs_resctrl = debugfs_create_dir("resctrl", NULL);

	return 0;

cleanup_mountpoint:
	sysfs_remove_mount_point(fs_kobj, "resctrl");

	return ret;
}

void __exit rdtgroup_exit(void)
{
	debugfs_remove_recursive(debugfs_resctrl);
	unregister_filesystem(&rdt_fs_type);
	sysfs_remove_mount_point(fs_kobj, "resctrl");
}