summaryrefslogtreecommitdiffstats
path: root/kernel/sched/rt.c
blob: d8c43d73e078806ac468450732b76282fb13f798 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Real-Time Scheduling Class (mapped to the SCHED_FIFO and SCHED_RR
 * policies)
 */

#include "sched.h"

#include <linux/slab.h>
#include <linux/irq_work.h>

int sched_rr_timeslice = RR_TIMESLICE;
int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;

static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);

struct rt_bandwidth def_rt_bandwidth;

static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
{
	struct rt_bandwidth *rt_b =
		container_of(timer, struct rt_bandwidth, rt_period_timer);
	int idle = 0;
	int overrun;

	raw_spin_lock(&rt_b->rt_runtime_lock);
	for (;;) {
		overrun = hrtimer_forward_now(timer, rt_b->rt_period);
		if (!overrun)
			break;

		raw_spin_unlock(&rt_b->rt_runtime_lock);
		idle = do_sched_rt_period_timer(rt_b, overrun);
		raw_spin_lock(&rt_b->rt_runtime_lock);
	}
	if (idle)
		rt_b->rt_period_active = 0;
	raw_spin_unlock(&rt_b->rt_runtime_lock);

	return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
}

void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
{
	rt_b->rt_period = ns_to_ktime(period);
	rt_b->rt_runtime = runtime;

	raw_spin_lock_init(&rt_b->rt_runtime_lock);

	hrtimer_init(&rt_b->rt_period_timer,
			CLOCK_MONOTONIC, HRTIMER_MODE_REL);
	rt_b->rt_period_timer.function = sched_rt_period_timer;
}

static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
{
	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
		return;

	raw_spin_lock(&rt_b->rt_runtime_lock);
	if (!rt_b->rt_period_active) {
		rt_b->rt_period_active = 1;
		/*
		 * SCHED_DEADLINE updates the bandwidth, as a run away
		 * RT task with a DL task could hog a CPU. But DL does
		 * not reset the period. If a deadline task was running
		 * without an RT task running, it can cause RT tasks to
		 * throttle when they start up. Kick the timer right away
		 * to update the period.
		 */
		hrtimer_forward_now(&rt_b->rt_period_timer, ns_to_ktime(0));
		hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED);
	}
	raw_spin_unlock(&rt_b->rt_runtime_lock);
}

void init_rt_rq(struct rt_rq *rt_rq)
{
	struct rt_prio_array *array;
	int i;

	array = &rt_rq->active;
	for (i = 0; i < MAX_RT_PRIO; i++) {
		INIT_LIST_HEAD(array->queue + i);
		__clear_bit(i, array->bitmap);
	}
	/* delimiter for bitsearch: */
	__set_bit(MAX_RT_PRIO, array->bitmap);

#if defined CONFIG_SMP
	rt_rq->highest_prio.curr = MAX_RT_PRIO;
	rt_rq->highest_prio.next = MAX_RT_PRIO;
	rt_rq->rt_nr_migratory = 0;
	rt_rq->overloaded = 0;
	plist_head_init(&rt_rq->pushable_tasks);
#endif /* CONFIG_SMP */
	/* We start is dequeued state, because no RT tasks are queued */
	rt_rq->rt_queued = 0;

	rt_rq->rt_time = 0;
	rt_rq->rt_throttled = 0;
	rt_rq->rt_runtime = 0;
	raw_spin_lock_init(&rt_rq->rt_runtime_lock);
}

#ifdef CONFIG_RT_GROUP_SCHED
static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
{
	hrtimer_cancel(&rt_b->rt_period_timer);
}

#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)

static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
{
#ifdef CONFIG_SCHED_DEBUG
	WARN_ON_ONCE(!rt_entity_is_task(rt_se));
#endif
	return container_of(rt_se, struct task_struct, rt);
}

static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
	return rt_rq->rq;
}

static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
{
	return rt_se->rt_rq;
}

static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
{
	struct rt_rq *rt_rq = rt_se->rt_rq;

	return rt_rq->rq;
}

void free_rt_sched_group(struct task_group *tg)
{
	int i;

	if (tg->rt_se)
		destroy_rt_bandwidth(&tg->rt_bandwidth);

	for_each_possible_cpu(i) {
		if (tg->rt_rq)
			kfree(tg->rt_rq[i]);
		if (tg->rt_se)
			kfree(tg->rt_se[i]);
	}

	kfree(tg->rt_rq);
	kfree(tg->rt_se);
}

void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
		struct sched_rt_entity *rt_se, int cpu,
		struct sched_rt_entity *parent)
{
	struct rq *rq = cpu_rq(cpu);

	rt_rq->highest_prio.curr = MAX_RT_PRIO;
	rt_rq->rt_nr_boosted = 0;
	rt_rq->rq = rq;
	rt_rq->tg = tg;

	tg->rt_rq[cpu] = rt_rq;
	tg->rt_se[cpu] = rt_se;

	if (!rt_se)
		return;

	if (!parent)
		rt_se->rt_rq = &rq->rt;
	else
		rt_se->rt_rq = parent->my_q;

	rt_se->my_q = rt_rq;
	rt_se->parent = parent;
	INIT_LIST_HEAD(&rt_se->run_list);
}

int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
{
	struct rt_rq *rt_rq;
	struct sched_rt_entity *rt_se;
	int i;

	tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL);
	if (!tg->rt_rq)
		goto err;
	tg->rt_se = kzalloc(sizeof(rt_se) * nr_cpu_ids, GFP_KERNEL);
	if (!tg->rt_se)
		goto err;

	init_rt_bandwidth(&tg->rt_bandwidth,
			ktime_to_ns(def_rt_bandwidth.rt_period), 0);

	for_each_possible_cpu(i) {
		rt_rq = kzalloc_node(sizeof(struct rt_rq),
				     GFP_KERNEL, cpu_to_node(i));
		if (!rt_rq)
			goto err;

		rt_se = kzalloc_node(sizeof(struct sched_rt_entity),
				     GFP_KERNEL, cpu_to_node(i));
		if (!rt_se)
			goto err_free_rq;

		init_rt_rq(rt_rq);
		rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
		init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]);
	}

	return 1;

err_free_rq:
	kfree(rt_rq);
err:
	return 0;
}

#else /* CONFIG_RT_GROUP_SCHED */

#define rt_entity_is_task(rt_se) (1)

static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
{
	return container_of(rt_se, struct task_struct, rt);
}

static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
	return container_of(rt_rq, struct rq, rt);
}

static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
{
	struct task_struct *p = rt_task_of(rt_se);

	return task_rq(p);
}

static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
{
	struct rq *rq = rq_of_rt_se(rt_se);

	return &rq->rt;
}

void free_rt_sched_group(struct task_group *tg) { }

int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
{
	return 1;
}
#endif /* CONFIG_RT_GROUP_SCHED */

#ifdef CONFIG_SMP

static void pull_rt_task(struct rq *this_rq);

static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
{
	/* Try to pull RT tasks here if we lower this rq's prio */
	return rq->rt.highest_prio.curr > prev->prio;
}

static inline int rt_overloaded(struct rq *rq)
{
	return atomic_read(&rq->rd->rto_count);
}

static inline void rt_set_overload(struct rq *rq)
{
	if (!rq->online)
		return;

	cpumask_set_cpu(rq->cpu, rq->rd->rto_mask);
	/*
	 * Make sure the mask is visible before we set
	 * the overload count. That is checked to determine
	 * if we should look at the mask. It would be a shame
	 * if we looked at the mask, but the mask was not
	 * updated yet.
	 *
	 * Matched by the barrier in pull_rt_task().
	 */
	smp_wmb();
	atomic_inc(&rq->rd->rto_count);
}

static inline void rt_clear_overload(struct rq *rq)
{
	if (!rq->online)
		return;

	/* the order here really doesn't matter */
	atomic_dec(&rq->rd->rto_count);
	cpumask_clear_cpu(rq->cpu, rq->rd->rto_mask);
}

static void update_rt_migration(struct rt_rq *rt_rq)
{
	if (rt_rq->rt_nr_migratory && rt_rq->rt_nr_total > 1) {
		if (!rt_rq->overloaded) {
			rt_set_overload(rq_of_rt_rq(rt_rq));
			rt_rq->overloaded = 1;
		}
	} else if (rt_rq->overloaded) {
		rt_clear_overload(rq_of_rt_rq(rt_rq));
		rt_rq->overloaded = 0;
	}
}

static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	struct task_struct *p;

	if (!rt_entity_is_task(rt_se))
		return;

	p = rt_task_of(rt_se);
	rt_rq = &rq_of_rt_rq(rt_rq)->rt;

	rt_rq->rt_nr_total++;
	if (p->nr_cpus_allowed > 1)
		rt_rq->rt_nr_migratory++;

	update_rt_migration(rt_rq);
}

static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	struct task_struct *p;

	if (!rt_entity_is_task(rt_se))
		return;

	p = rt_task_of(rt_se);
	rt_rq = &rq_of_rt_rq(rt_rq)->rt;

	rt_rq->rt_nr_total--;
	if (p->nr_cpus_allowed > 1)
		rt_rq->rt_nr_migratory--;

	update_rt_migration(rt_rq);
}

static inline int has_pushable_tasks(struct rq *rq)
{
	return !plist_head_empty(&rq->rt.pushable_tasks);
}

static DEFINE_PER_CPU(struct callback_head, rt_push_head);
static DEFINE_PER_CPU(struct callback_head, rt_pull_head);

static void push_rt_tasks(struct rq *);
static void pull_rt_task(struct rq *);

static inline void queue_push_tasks(struct rq *rq)
{
	if (!has_pushable_tasks(rq))
		return;

	queue_balance_callback(rq, &per_cpu(rt_push_head, rq->cpu), push_rt_tasks);
}

static inline void queue_pull_task(struct rq *rq)
{
	queue_balance_callback(rq, &per_cpu(rt_pull_head, rq->cpu), pull_rt_task);
}

static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
{
	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
	plist_node_init(&p->pushable_tasks, p->prio);
	plist_add(&p->pushable_tasks, &rq->rt.pushable_tasks);

	/* Update the highest prio pushable task */
	if (p->prio < rq->rt.highest_prio.next)
		rq->rt.highest_prio.next = p->prio;
}

static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
{
	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);

	/* Update the new highest prio pushable task */
	if (has_pushable_tasks(rq)) {
		p = plist_first_entry(&rq->rt.pushable_tasks,
				      struct task_struct, pushable_tasks);
		rq->rt.highest_prio.next = p->prio;
	} else
		rq->rt.highest_prio.next = MAX_RT_PRIO;
}

#else

static inline void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
{
}

static inline void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
{
}

static inline
void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
}

static inline
void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
}

static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
{
	return false;
}

static inline void pull_rt_task(struct rq *this_rq)
{
}

static inline void queue_push_tasks(struct rq *rq)
{
}
#endif /* CONFIG_SMP */

static void enqueue_top_rt_rq(struct rt_rq *rt_rq);
static void dequeue_top_rt_rq(struct rt_rq *rt_rq);

static inline int on_rt_rq(struct sched_rt_entity *rt_se)
{
	return rt_se->on_rq;
}

#ifdef CONFIG_RT_GROUP_SCHED

static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
{
	if (!rt_rq->tg)
		return RUNTIME_INF;

	return rt_rq->rt_runtime;
}

static inline u64 sched_rt_period(struct rt_rq *rt_rq)
{
	return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period);
}

typedef struct task_group *rt_rq_iter_t;

static inline struct task_group *next_task_group(struct task_group *tg)
{
	do {
		tg = list_entry_rcu(tg->list.next,
			typeof(struct task_group), list);
	} while (&tg->list != &task_groups && task_group_is_autogroup(tg));

	if (&tg->list == &task_groups)
		tg = NULL;

	return tg;
}

#define for_each_rt_rq(rt_rq, iter, rq)					\
	for (iter = container_of(&task_groups, typeof(*iter), list);	\
		(iter = next_task_group(iter)) &&			\
		(rt_rq = iter->rt_rq[cpu_of(rq)]);)

#define for_each_sched_rt_entity(rt_se) \
	for (; rt_se; rt_se = rt_se->parent)

static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
{
	return rt_se->my_q;
}

static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags);
static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags);

static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
{
	struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
	struct rq *rq = rq_of_rt_rq(rt_rq);
	struct sched_rt_entity *rt_se;

	int cpu = cpu_of(rq);

	rt_se = rt_rq->tg->rt_se[cpu];

	if (rt_rq->rt_nr_running) {
		if (!rt_se)
			enqueue_top_rt_rq(rt_rq);
		else if (!on_rt_rq(rt_se))
			enqueue_rt_entity(rt_se, 0);

		if (rt_rq->highest_prio.curr < curr->prio)
			resched_curr(rq);
	}
}

static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
{
	struct sched_rt_entity *rt_se;
	int cpu = cpu_of(rq_of_rt_rq(rt_rq));

	rt_se = rt_rq->tg->rt_se[cpu];

	if (!rt_se)
		dequeue_top_rt_rq(rt_rq);
	else if (on_rt_rq(rt_se))
		dequeue_rt_entity(rt_se, 0);
}

static inline int rt_rq_throttled(struct rt_rq *rt_rq)
{
	return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
}

static int rt_se_boosted(struct sched_rt_entity *rt_se)
{
	struct rt_rq *rt_rq = group_rt_rq(rt_se);
	struct task_struct *p;

	if (rt_rq)
		return !!rt_rq->rt_nr_boosted;

	p = rt_task_of(rt_se);
	return p->prio != p->normal_prio;
}

#ifdef CONFIG_SMP
static inline const struct cpumask *sched_rt_period_mask(void)
{
	return this_rq()->rd->span;
}
#else
static inline const struct cpumask *sched_rt_period_mask(void)
{
	return cpu_online_mask;
}
#endif

static inline
struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
{
	return container_of(rt_b, struct task_group, rt_bandwidth)->rt_rq[cpu];
}

static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
{
	return &rt_rq->tg->rt_bandwidth;
}

#else /* !CONFIG_RT_GROUP_SCHED */

static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
{
	return rt_rq->rt_runtime;
}

static inline u64 sched_rt_period(struct rt_rq *rt_rq)
{
	return ktime_to_ns(def_rt_bandwidth.rt_period);
}

typedef struct rt_rq *rt_rq_iter_t;

#define for_each_rt_rq(rt_rq, iter, rq) \
	for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL)

#define for_each_sched_rt_entity(rt_se) \
	for (; rt_se; rt_se = NULL)

static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
{
	return NULL;
}

static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
{
	struct rq *rq = rq_of_rt_rq(rt_rq);

	if (!rt_rq->rt_nr_running)
		return;

	enqueue_top_rt_rq(rt_rq);
	resched_curr(rq);
}

static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
{
	dequeue_top_rt_rq(rt_rq);
}

static inline int rt_rq_throttled(struct rt_rq *rt_rq)
{
	return rt_rq->rt_throttled;
}

static inline const struct cpumask *sched_rt_period_mask(void)
{
	return cpu_online_mask;
}

static inline
struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
{
	return &cpu_rq(cpu)->rt;
}

static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
{
	return &def_rt_bandwidth;
}

#endif /* CONFIG_RT_GROUP_SCHED */

bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
{
	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);

	return (hrtimer_active(&rt_b->rt_period_timer) ||
		rt_rq->rt_time < rt_b->rt_runtime);
}

#ifdef CONFIG_SMP
/*
 * We ran out of runtime, see if we can borrow some from our neighbours.
 */
static void do_balance_runtime(struct rt_rq *rt_rq)
{
	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
	struct root_domain *rd = rq_of_rt_rq(rt_rq)->rd;
	int i, weight;
	u64 rt_period;

	weight = cpumask_weight(rd->span);

	raw_spin_lock(&rt_b->rt_runtime_lock);
	rt_period = ktime_to_ns(rt_b->rt_period);
	for_each_cpu(i, rd->span) {
		struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
		s64 diff;

		if (iter == rt_rq)
			continue;

		raw_spin_lock(&iter->rt_runtime_lock);
		/*
		 * Either all rqs have inf runtime and there's nothing to steal
		 * or __disable_runtime() below sets a specific rq to inf to
		 * indicate its been disabled and disalow stealing.
		 */
		if (iter->rt_runtime == RUNTIME_INF)
			goto next;

		/*
		 * From runqueues with spare time, take 1/n part of their
		 * spare time, but no more than our period.
		 */
		diff = iter->rt_runtime - iter->rt_time;
		if (diff > 0) {
			diff = div_u64((u64)diff, weight);
			if (rt_rq->rt_runtime + diff > rt_period)
				diff = rt_period - rt_rq->rt_runtime;
			iter->rt_runtime -= diff;
			rt_rq->rt_runtime += diff;
			if (rt_rq->rt_runtime == rt_period) {
				raw_spin_unlock(&iter->rt_runtime_lock);
				break;
			}
		}
next:
		raw_spin_unlock(&iter->rt_runtime_lock);
	}
	raw_spin_unlock(&rt_b->rt_runtime_lock);
}

/*
 * Ensure this RQ takes back all the runtime it lend to its neighbours.
 */
static void __disable_runtime(struct rq *rq)
{
	struct root_domain *rd = rq->rd;
	rt_rq_iter_t iter;
	struct rt_rq *rt_rq;

	if (unlikely(!scheduler_running))
		return;

	for_each_rt_rq(rt_rq, iter, rq) {
		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
		s64 want;
		int i;

		raw_spin_lock(&rt_b->rt_runtime_lock);
		raw_spin_lock(&rt_rq->rt_runtime_lock);
		/*
		 * Either we're all inf and nobody needs to borrow, or we're
		 * already disabled and thus have nothing to do, or we have
		 * exactly the right amount of runtime to take out.
		 */
		if (rt_rq->rt_runtime == RUNTIME_INF ||
				rt_rq->rt_runtime == rt_b->rt_runtime)
			goto balanced;
		raw_spin_unlock(&rt_rq->rt_runtime_lock);

		/*
		 * Calculate the difference between what we started out with
		 * and what we current have, that's the amount of runtime
		 * we lend and now have to reclaim.
		 */
		want = rt_b->rt_runtime - rt_rq->rt_runtime;

		/*
		 * Greedy reclaim, take back as much as we can.
		 */
		for_each_cpu(i, rd->span) {
			struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
			s64 diff;

			/*
			 * Can't reclaim from ourselves or disabled runqueues.
			 */
			if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF)
				continue;

			raw_spin_lock(&iter->rt_runtime_lock);
			if (want > 0) {
				diff = min_t(s64, iter->rt_runtime, want);
				iter->rt_runtime -= diff;
				want -= diff;
			} else {
				iter->rt_runtime -= want;
				want -= want;
			}
			raw_spin_unlock(&iter->rt_runtime_lock);

			if (!want)
				break;
		}

		raw_spin_lock(&rt_rq->rt_runtime_lock);
		/*
		 * We cannot be left wanting - that would mean some runtime
		 * leaked out of the system.
		 */
		BUG_ON(want);
balanced:
		/*
		 * Disable all the borrow logic by pretending we have inf
		 * runtime - in which case borrowing doesn't make sense.
		 */
		rt_rq->rt_runtime = RUNTIME_INF;
		rt_rq->rt_throttled = 0;
		raw_spin_unlock(&rt_rq->rt_runtime_lock);
		raw_spin_unlock(&rt_b->rt_runtime_lock);

		/* Make rt_rq available for pick_next_task() */
		sched_rt_rq_enqueue(rt_rq);
	}
}

static void __enable_runtime(struct rq *rq)
{
	rt_rq_iter_t iter;
	struct rt_rq *rt_rq;

	if (unlikely(!scheduler_running))
		return;

	/*
	 * Reset each runqueue's bandwidth settings
	 */
	for_each_rt_rq(rt_rq, iter, rq) {
		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);

		raw_spin_lock(&rt_b->rt_runtime_lock);
		raw_spin_lock(&rt_rq->rt_runtime_lock);
		rt_rq->rt_runtime = rt_b->rt_runtime;
		rt_rq->rt_time = 0;
		rt_rq->rt_throttled = 0;
		raw_spin_unlock(&rt_rq->rt_runtime_lock);
		raw_spin_unlock(&rt_b->rt_runtime_lock);
	}
}

static void balance_runtime(struct rt_rq *rt_rq)
{
	if (!sched_feat(RT_RUNTIME_SHARE))
		return;

	if (rt_rq->rt_time > rt_rq->rt_runtime) {
		raw_spin_unlock(&rt_rq->rt_runtime_lock);
		do_balance_runtime(rt_rq);
		raw_spin_lock(&rt_rq->rt_runtime_lock);
	}
}
#else /* !CONFIG_SMP */
static inline void balance_runtime(struct rt_rq *rt_rq) {}
#endif /* CONFIG_SMP */

static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
{
	int i, idle = 1, throttled = 0;
	const struct cpumask *span;

	span = sched_rt_period_mask();
#ifdef CONFIG_RT_GROUP_SCHED
	/*
	 * FIXME: isolated CPUs should really leave the root task group,
	 * whether they are isolcpus or were isolated via cpusets, lest
	 * the timer run on a CPU which does not service all runqueues,
	 * potentially leaving other CPUs indefinitely throttled.  If
	 * isolation is really required, the user will turn the throttle
	 * off to kill the perturbations it causes anyway.  Meanwhile,
	 * this maintains functionality for boot and/or troubleshooting.
	 */
	if (rt_b == &root_task_group.rt_bandwidth)
		span = cpu_online_mask;
#endif
	for_each_cpu(i, span) {
		int enqueue = 0;
		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
		struct rq *rq = rq_of_rt_rq(rt_rq);
		int skip;

		/*
		 * When span == cpu_online_mask, taking each rq->lock
		 * can be time-consuming. Try to avoid it when possible.
		 */
		raw_spin_lock(&rt_rq->rt_runtime_lock);
		skip = !rt_rq->rt_time && !rt_rq->rt_nr_running;
		raw_spin_unlock(&rt_rq->rt_runtime_lock);
		if (skip)
			continue;

		raw_spin_lock(&rq->lock);
		if (rt_rq->rt_time) {
			u64 runtime;

			raw_spin_lock(&rt_rq->rt_runtime_lock);
			if (rt_rq->rt_throttled)
				balance_runtime(rt_rq);
			runtime = rt_rq->rt_runtime;
			rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime);
			if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
				rt_rq->rt_throttled = 0;
				enqueue = 1;

				/*
				 * When we're idle and a woken (rt) task is
				 * throttled check_preempt_curr() will set
				 * skip_update and the time between the wakeup
				 * and this unthrottle will get accounted as
				 * 'runtime'.
				 */
				if (rt_rq->rt_nr_running && rq->curr == rq->idle)
					rq_clock_skip_update(rq, false);
			}
			if (rt_rq->rt_time || rt_rq->rt_nr_running)
				idle = 0;
			raw_spin_unlock(&rt_rq->rt_runtime_lock);
		} else if (rt_rq->rt_nr_running) {
			idle = 0;
			if (!rt_rq_throttled(rt_rq))
				enqueue = 1;
		}
		if (rt_rq->rt_throttled)
			throttled = 1;

		if (enqueue)
			sched_rt_rq_enqueue(rt_rq);
		raw_spin_unlock(&rq->lock);
	}

	if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF))
		return 1;

	return idle;
}

static inline int rt_se_prio(struct sched_rt_entity *rt_se)
{
#ifdef CONFIG_RT_GROUP_SCHED
	struct rt_rq *rt_rq = group_rt_rq(rt_se);

	if (rt_rq)
		return rt_rq->highest_prio.curr;
#endif

	return rt_task_of(rt_se)->prio;
}

static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
{
	u64 runtime = sched_rt_runtime(rt_rq);

	if (rt_rq->rt_throttled)
		return rt_rq_throttled(rt_rq);

	if (runtime >= sched_rt_period(rt_rq))
		return 0;

	balance_runtime(rt_rq);
	runtime = sched_rt_runtime(rt_rq);
	if (runtime == RUNTIME_INF)
		return 0;

	if (rt_rq->rt_time > runtime) {
		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);

		/*
		 * Don't actually throttle groups that have no runtime assigned
		 * but accrue some time due to boosting.
		 */
		if (likely(rt_b->rt_runtime)) {
			rt_rq->rt_throttled = 1;
			printk_deferred_once("sched: RT throttling activated\n");
		} else {
			/*
			 * In case we did anyway, make it go away,
			 * replenishment is a joke, since it will replenish us
			 * with exactly 0 ns.
			 */
			rt_rq->rt_time = 0;
		}

		if (rt_rq_throttled(rt_rq)) {
			sched_rt_rq_dequeue(rt_rq);
			return 1;
		}
	}

	return 0;
}

/*
 * Update the current task's runtime statistics. Skip current tasks that
 * are not in our scheduling class.
 */
static void update_curr_rt(struct rq *rq)
{
	struct task_struct *curr = rq->curr;
	struct sched_rt_entity *rt_se = &curr->rt;
	u64 delta_exec;

	if (curr->sched_class != &rt_sched_class)
		return;

	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
	if (unlikely((s64)delta_exec <= 0))
		return;

	/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
	cpufreq_update_util(rq, SCHED_CPUFREQ_RT);

	schedstat_set(curr->se.statistics.exec_max,
		      max(curr->se.statistics.exec_max, delta_exec));

	curr->se.sum_exec_runtime += delta_exec;
	account_group_exec_runtime(curr, delta_exec);

	curr->se.exec_start = rq_clock_task(rq);
	cpuacct_charge(curr, delta_exec);

	sched_rt_avg_update(rq, delta_exec);

	if (!rt_bandwidth_enabled())
		return;

	for_each_sched_rt_entity(rt_se) {
		struct rt_rq *rt_rq = rt_rq_of_se(rt_se);

		if (sched_rt_runtime(rt_rq) != RUNTIME_INF) {
			raw_spin_lock(&rt_rq->rt_runtime_lock);
			rt_rq->rt_time += delta_exec;
			if (sched_rt_runtime_exceeded(rt_rq))
				resched_curr(rq);
			raw_spin_unlock(&rt_rq->rt_runtime_lock);
		}
	}
}

static void
dequeue_top_rt_rq(struct rt_rq *rt_rq)
{
	struct rq *rq = rq_of_rt_rq(rt_rq);

	BUG_ON(&rq->rt != rt_rq);

	if (!rt_rq->rt_queued)
		return;

	BUG_ON(!rq->nr_running);

	sub_nr_running(rq, rt_rq->rt_nr_running);
	rt_rq->rt_queued = 0;
}

static void
enqueue_top_rt_rq(struct rt_rq *rt_rq)
{
	struct rq *rq = rq_of_rt_rq(rt_rq);

	BUG_ON(&rq->rt != rt_rq);

	if (rt_rq->rt_queued)
		return;
	if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running)
		return;

	add_nr_running(rq, rt_rq->rt_nr_running);
	rt_rq->rt_queued = 1;
}

#if defined CONFIG_SMP

static void
inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
{
	struct rq *rq = rq_of_rt_rq(rt_rq);

#ifdef CONFIG_RT_GROUP_SCHED
	/*
	 * Change rq's cpupri only if rt_rq is the top queue.
	 */
	if (&rq->rt != rt_rq)
		return;
#endif
	if (rq->online && prio < prev_prio)
		cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
}

static void
dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
{
	struct rq *rq = rq_of_rt_rq(rt_rq);

#ifdef CONFIG_RT_GROUP_SCHED
	/*
	 * Change rq's cpupri only if rt_rq is the top queue.
	 */
	if (&rq->rt != rt_rq)
		return;
#endif
	if (rq->online && rt_rq->highest_prio.curr != prev_prio)
		cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
}

#else /* CONFIG_SMP */

static inline
void inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) {}
static inline
void dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) {}

#endif /* CONFIG_SMP */

#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
static void
inc_rt_prio(struct rt_rq *rt_rq, int prio)
{
	int prev_prio = rt_rq->highest_prio.curr;

	if (prio < prev_prio)
		rt_rq->highest_prio.curr = prio;

	inc_rt_prio_smp(rt_rq, prio, prev_prio);
}

static void
dec_rt_prio(struct rt_rq *rt_rq, int prio)
{
	int prev_prio = rt_rq->highest_prio.curr;

	if (rt_rq->rt_nr_running) {

		WARN_ON(prio < prev_prio);

		/*
		 * This may have been our highest task, and therefore
		 * we may have some recomputation to do
		 */
		if (prio == prev_prio) {
			struct rt_prio_array *array = &rt_rq->active;

			rt_rq->highest_prio.curr =
				sched_find_first_bit(array->bitmap);
		}

	} else
		rt_rq->highest_prio.curr = MAX_RT_PRIO;

	dec_rt_prio_smp(rt_rq, prio, prev_prio);
}

#else

static inline void inc_rt_prio(struct rt_rq *rt_rq, int prio) {}
static inline void dec_rt_prio(struct rt_rq *rt_rq, int prio) {}

#endif /* CONFIG_SMP || CONFIG_RT_GROUP_SCHED */

#ifdef CONFIG_RT_GROUP_SCHED

static void
inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	if (rt_se_boosted(rt_se))
		rt_rq->rt_nr_boosted++;

	if (rt_rq->tg)
		start_rt_bandwidth(&rt_rq->tg->rt_bandwidth);
}

static void
dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	if (rt_se_boosted(rt_se))
		rt_rq->rt_nr_boosted--;

	WARN_ON(!rt_rq->rt_nr_running && rt_rq->rt_nr_boosted);
}

#else /* CONFIG_RT_GROUP_SCHED */

static void
inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	start_rt_bandwidth(&def_rt_bandwidth);
}

static inline
void dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) {}

#endif /* CONFIG_RT_GROUP_SCHED */

static inline
unsigned int rt_se_nr_running(struct sched_rt_entity *rt_se)
{
	struct rt_rq *group_rq = group_rt_rq(rt_se);

	if (group_rq)
		return group_rq->rt_nr_running;
	else
		return 1;
}

static inline
unsigned int rt_se_rr_nr_running(struct sched_rt_entity *rt_se)
{
	struct rt_rq *group_rq = group_rt_rq(rt_se);
	struct task_struct *tsk;

	if (group_rq)
		return group_rq->rr_nr_running;

	tsk = rt_task_of(rt_se);

	return (tsk->policy == SCHED_RR) ? 1 : 0;
}

static inline
void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	int prio = rt_se_prio(rt_se);

	WARN_ON(!rt_prio(prio));
	rt_rq->rt_nr_running += rt_se_nr_running(rt_se);
	rt_rq->rr_nr_running += rt_se_rr_nr_running(rt_se);

	inc_rt_prio(rt_rq, prio);
	inc_rt_migration(rt_se, rt_rq);
	inc_rt_group(rt_se, rt_rq);
}

static inline
void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
	WARN_ON(!rt_rq->rt_nr_running);
	rt_rq->rt_nr_running -= rt_se_nr_running(rt_se);
	rt_rq->rr_nr_running -= rt_se_rr_nr_running(rt_se);

	dec_rt_prio(rt_rq, rt_se_prio(rt_se));
	dec_rt_migration(rt_se, rt_rq);
	dec_rt_group(rt_se, rt_rq);
}

/*
 * Change rt_se->run_list location unless SAVE && !MOVE
 *
 * assumes ENQUEUE/DEQUEUE flags match
 */
static inline bool move_entity(unsigned int flags)
{
	if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) == DEQUEUE_SAVE)
		return false;

	return true;
}

static void __delist_rt_entity(struct sched_rt_entity *rt_se, struct rt_prio_array *array)
{
	list_del_init(&rt_se->run_list);

	if (list_empty(array->queue + rt_se_prio(rt_se)))
		__clear_bit(rt_se_prio(rt_se), array->bitmap);

	rt_se->on_list = 0;
}

static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
{
	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
	struct rt_prio_array *array = &rt_rq->active;
	struct rt_rq *group_rq = group_rt_rq(rt_se);
	struct list_head *queue = array->queue + rt_se_prio(rt_se);

	/*
	 * Don't enqueue the group if its throttled, or when empty.
	 * The latter is a consequence of the former when a child group
	 * get throttled and the current group doesn't have any other
	 * active members.
	 */
	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) {
		if (rt_se->on_list)
			__delist_rt_entity(rt_se, array);
		return;
	}

	if (move_entity(flags)) {
		WARN_ON_ONCE(rt_se->on_list);
		if (flags & ENQUEUE_HEAD)
			list_add(&rt_se->run_list, queue);
		else
			list_add_tail(&rt_se->run_list, queue);

		__set_bit(rt_se_prio(rt_se), array->bitmap);
		rt_se->on_list = 1;
	}
	rt_se->on_rq = 1;

	inc_rt_tasks(rt_se, rt_rq);
}

static void __dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
{
	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
	struct rt_prio_array *array = &rt_rq->active;

	if (move_entity(flags)) {
		WARN_ON_ONCE(!rt_se->on_list);
		__delist_rt_entity(rt_se, array);
	}
	rt_se->on_rq = 0;

	dec_rt_tasks(rt_se, rt_rq);
}

/*
 * Because the prio of an upper entry depends on the lower
 * entries, we must remove entries top - down.
 */
static void dequeue_rt_stack(struct sched_rt_entity *rt_se, unsigned int flags)
{
	struct sched_rt_entity *back = NULL;

	for_each_sched_rt_entity(rt_se) {
		rt_se->back = back;
		back = rt_se;
	}

	dequeue_top_rt_rq(rt_rq_of_se(back));

	for (rt_se = back; rt_se; rt_se = rt_se->back) {
		if (on_rt_rq(rt_se))
			__dequeue_rt_entity(rt_se, flags);
	}
}

static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
{
	struct rq *rq = rq_of_rt_se(rt_se);

	dequeue_rt_stack(rt_se, flags);
	for_each_sched_rt_entity(rt_se)
		__enqueue_rt_entity(rt_se, flags);
	enqueue_top_rt_rq(&rq->rt);
}

static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
{
	struct rq *rq = rq_of_rt_se(rt_se);

	dequeue_rt_stack(rt_se, flags);

	for_each_sched_rt_entity(rt_se) {
		struct rt_rq *rt_rq = group_rt_rq(rt_se);

		if (rt_rq && rt_rq->rt_nr_running)
			__enqueue_rt_entity(rt_se, flags);
	}
	enqueue_top_rt_rq(&rq->rt);
}

/*
 * Adding/removing a task to/from a priority array:
 */
static void
enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
{
	struct sched_rt_entity *rt_se = &p->rt;

	if (flags & ENQUEUE_WAKEUP)
		rt_se->timeout = 0;

	enqueue_rt_entity(rt_se, flags);

	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
		enqueue_pushable_task(rq, p);
}

static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
{
	struct sched_rt_entity *rt_se = &p->rt;

	update_curr_rt(rq);
	dequeue_rt_entity(rt_se, flags);

	dequeue_pushable_task(rq, p);
}

/*
 * Put task to the head or the end of the run list without the overhead of
 * dequeue followed by enqueue.
 */
static void
requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int head)
{
	if (on_rt_rq(rt_se)) {
		struct rt_prio_array *array = &rt_rq->active;
		struct list_head *queue = array->queue + rt_se_prio(rt_se);

		if (head)
			list_move(&rt_se->run_list, queue);
		else
			list_move_tail(&rt_se->run_list, queue);
	}
}

static void requeue_task_rt(struct rq *rq, struct task_struct *p, int head)
{
	struct sched_rt_entity *rt_se = &p->rt;
	struct rt_rq *rt_rq;

	for_each_sched_rt_entity(rt_se) {
		rt_rq = rt_rq_of_se(rt_se);
		requeue_rt_entity(rt_rq, rt_se, head);
	}
}

static void yield_task_rt(struct rq *rq)
{
	requeue_task_rt(rq, rq->curr, 0);
}

#ifdef CONFIG_SMP
static int find_lowest_rq(struct task_struct *task);

static int
select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
{
	struct task_struct *curr;
	struct rq *rq;

	/* For anything but wake ups, just return the task_cpu */
	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
		goto out;

	rq = cpu_rq(cpu);

	rcu_read_lock();
	curr = READ_ONCE(rq->curr); /* unlocked access */

	/*
	 * If the current task on @p's runqueue is an RT task, then
	 * try to see if we can wake this RT task up on another
	 * runqueue. Otherwise simply start this RT task
	 * on its current runqueue.
	 *
	 * We want to avoid overloading runqueues. If the woken
	 * task is a higher priority, then it will stay on this CPU
	 * and the lower prio task should be moved to another CPU.
	 * Even though this will probably make the lower prio task
	 * lose its cache, we do not want to bounce a higher task
	 * around just because it gave up its CPU, perhaps for a
	 * lock?
	 *
	 * For equal prio tasks, we just let the scheduler sort it out.
	 *
	 * Otherwise, just let it ride on the affined RQ and the
	 * post-schedule router will push the preempted task away
	 *
	 * This test is optimistic, if we get it wrong the load-balancer
	 * will have to sort it out.
	 */
	if (curr && unlikely(rt_task(curr)) &&
	    (curr->nr_cpus_allowed < 2 ||
	     curr->prio <= p->prio)) {
		int target = find_lowest_rq(p);

		/*
		 * Don't bother moving it if the destination CPU is
		 * not running a lower priority task.
		 */
		if (target != -1 &&
		    p->prio < cpu_rq(target)->rt.highest_prio.curr)
			cpu = target;
	}
	rcu_read_unlock();

out:
	return cpu;
}

static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
{
	/*
	 * Current can't be migrated, useless to reschedule,
	 * let's hope p can move out.
	 */
	if (rq->curr->nr_cpus_allowed == 1 ||
	    !cpupri_find(&rq->rd->cpupri, rq->curr, NULL))
		return;

	/*
	 * p is migratable, so let's not schedule it and
	 * see if it is pushed or pulled somewhere else.
	 */
	if (p->nr_cpus_allowed != 1
	    && cpupri_find(&rq->rd->cpupri, p, NULL))
		return;

	/*
	 * There appears to be other cpus that can accept
	 * current and none to run 'p', so lets reschedule
	 * to try and push current away:
	 */
	requeue_task_rt(rq, p, 1);
	resched_curr(rq);
}

#endif /* CONFIG_SMP */

/*
 * Preempt the current task with a newly woken task if needed:
 */
static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flags)
{
	if (p->prio < rq->curr->prio) {
		resched_curr(rq);
		return;
	}

#ifdef CONFIG_SMP
	/*
	 * If:
	 *
	 * - the newly woken task is of equal priority to the current task
	 * - the newly woken task is non-migratable while current is migratable
	 * - current will be preempted on the next reschedule
	 *
	 * we should check to see if current can readily move to a different
	 * cpu.  If so, we will reschedule to allow the push logic to try
	 * to move current somewhere else, making room for our non-migratable
	 * task.
	 */
	if (p->prio == rq->curr->prio && !test_tsk_need_resched(rq->curr))
		check_preempt_equal_prio(rq, p);
#endif
}

static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
						   struct rt_rq *rt_rq)
{
	struct rt_prio_array *array = &rt_rq->active;
	struct sched_rt_entity *next = NULL;
	struct list_head *queue;
	int idx;

	idx = sched_find_first_bit(array->bitmap);
	BUG_ON(idx >= MAX_RT_PRIO);

	queue = array->queue + idx;
	next = list_entry(queue->next, struct sched_rt_entity, run_list);

	return next;
}

static struct task_struct *_pick_next_task_rt(struct rq *rq)
{
	struct sched_rt_entity *rt_se;
	struct task_struct *p;
	struct rt_rq *rt_rq  = &rq->rt;

	do {
		rt_se = pick_next_rt_entity(rq, rt_rq);
		BUG_ON(!rt_se);
		rt_rq = group_rt_rq(rt_se);
	} while (rt_rq);

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

	return p;
}

static struct task_struct *
pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
	struct task_struct *p;
	struct rt_rq *rt_rq = &rq->rt;

	if (need_pull_rt_task(rq, prev)) {
		/*
		 * This is OK, because current is on_cpu, which avoids it being
		 * picked for load-balance and preemption/IRQs are still
		 * disabled avoiding further scheduler activity on it and we're
		 * being very careful to re-start the picking loop.
		 */
		rq_unpin_lock(rq, rf);
		pull_rt_task(rq);
		rq_repin_lock(rq, rf);
		/*
		 * pull_rt_task() can drop (and re-acquire) rq->lock; this
		 * means a dl or stop task can slip in, in which case we need
		 * to re-start task selection.
		 */
		if (unlikely((rq->stop && task_on_rq_queued(rq->stop)) ||
			     rq->dl.dl_nr_running))
			return RETRY_TASK;
	}

	/*
	 * We may dequeue prev's rt_rq in put_prev_task().
	 * So, we update time before rt_nr_running check.
	 */
	if (prev->sched_class == &rt_sched_class)
		update_curr_rt(rq);

	if (!rt_rq->rt_queued)
		return NULL;

	put_prev_task(rq, prev);

	p = _pick_next_task_rt(rq);

	/* The running task is never eligible for pushing */
	dequeue_pushable_task(rq, p);

	queue_push_tasks(rq);

	return p;
}

static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
{
	update_curr_rt(rq);

	/*
	 * The previous task needs to be made eligible for pushing
	 * if it is still active
	 */
	if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
		enqueue_pushable_task(rq, p);
}

#ifdef CONFIG_SMP

/* Only try algorithms three times */
#define RT_MAX_TRIES 3

static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
{
	if (!task_running(rq, p) &&
	    cpumask_test_cpu(cpu, &p->cpus_allowed))
		return 1;
	return 0;
}

/*
 * Return the highest pushable rq's task, which is suitable to be executed
 * on the cpu, NULL otherwise
 */
static struct task_struct *pick_highest_pushable_task(struct rq *rq, int cpu)
{
	struct plist_head *head = &rq->rt.pushable_tasks;
	struct task_struct *p;

	if (!has_pushable_tasks(rq))
		return NULL;

	plist_for_each_entry(p, head, pushable_tasks) {
		if (pick_rt_task(rq, p, cpu))
			return p;
	}

	return NULL;
}

static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);

static int find_lowest_rq(struct task_struct *task)
{
	struct sched_domain *sd;
	struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
	int this_cpu = smp_processor_id();
	int cpu      = task_cpu(task);

	/* Make sure the mask is initialized first */
	if (unlikely(!lowest_mask))
		return -1;

	if (task->nr_cpus_allowed == 1)
		return -1; /* No other targets possible */

	if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
		return -1; /* No targets found */

	/*
	 * At this point we have built a mask of cpus representing the
	 * lowest priority tasks in the system.  Now we want to elect
	 * the best one based on our affinity and topology.
	 *
	 * We prioritize the last cpu that the task executed on since
	 * it is most likely cache-hot in that location.
	 */
	if (cpumask_test_cpu(cpu, lowest_mask))
		return cpu;

	/*
	 * Otherwise, we consult the sched_domains span maps to figure
	 * out which cpu is logically closest to our hot cache data.
	 */
	if (!cpumask_test_cpu(this_cpu, lowest_mask))
		this_cpu = -1; /* Skip this_cpu opt if not among lowest */

	rcu_read_lock();
	for_each_domain(cpu, sd) {
		if (sd->flags & SD_WAKE_AFFINE) {
			int best_cpu;

			/*
			 * "this_cpu" is cheaper to preempt than a
			 * remote processor.
			 */
			if (this_cpu != -1 &&
			    cpumask_test_cpu(this_cpu, sched_domain_span(sd))) {
				rcu_read_unlock();
				return this_cpu;
			}

			best_cpu = cpumask_first_and(lowest_mask,
						     sched_domain_span(sd));
			if (best_cpu < nr_cpu_ids) {
				rcu_read_unlock();
				return best_cpu;
			}
		}
	}
	rcu_read_unlock();

	/*
	 * And finally, if there were no matches within the domains
	 * just give the caller *something* to work with from the compatible
	 * locations.
	 */
	if (this_cpu != -1)
		return this_cpu;

	cpu = cpumask_any(lowest_mask);
	if (cpu < nr_cpu_ids)
		return cpu;
	return -1;
}

/* Will lock the rq it finds */
static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
{
	struct rq *lowest_rq = NULL;
	int tries;
	int cpu;

	for (tries = 0; tries < RT_MAX_TRIES; tries++) {
		cpu = find_lowest_rq(task);

		if ((cpu == -1) || (cpu == rq->cpu))
			break;

		lowest_rq = cpu_rq(cpu);

		if (lowest_rq->rt.highest_prio.curr <= task->prio) {
			/*
			 * Target rq has tasks of equal or higher priority,
			 * retrying does not release any lock and is unlikely
			 * to yield a different result.
			 */
			lowest_rq = NULL;
			break;
		}

		/* if the prio of this runqueue changed, try again */
		if (double_lock_balance(rq, lowest_rq)) {
			/*
			 * We had to unlock the run queue. In
			 * the mean time, task could have
			 * migrated already or had its affinity changed.
			 * Also make sure that it wasn't scheduled on its rq.
			 */
			if (unlikely(task_rq(task) != rq ||
				     !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) ||
				     task_running(rq, task) ||
				     !rt_task(task) ||
				     !task_on_rq_queued(task))) {

				double_unlock_balance(rq, lowest_rq);
				lowest_rq = NULL;
				break;
			}
		}

		/* If this rq is still suitable use it. */
		if (lowest_rq->rt.highest_prio.curr > task->prio)
			break;

		/* try again */
		double_unlock_balance(rq, lowest_rq);
		lowest_rq = NULL;
	}

	return lowest_rq;
}

static struct task_struct *pick_next_pushable_task(struct rq *rq)
{
	struct task_struct *p;

	if (!has_pushable_tasks(rq))
		return NULL;

	p = plist_first_entry(&rq->rt.pushable_tasks,
			      struct task_struct, pushable_tasks);

	BUG_ON(rq->cpu != task_cpu(p));
	BUG_ON(task_current(rq, p));
	BUG_ON(p->nr_cpus_allowed <= 1);

	BUG_ON(!task_on_rq_queued(p));
	BUG_ON(!rt_task(p));

	return p;
}

/*
 * If the current CPU has more than one RT task, see if the non
 * running task can migrate over to a CPU that is running a task
 * of lesser priority.
 */
static int push_rt_task(struct rq *rq)
{
	struct task_struct *next_task;
	struct rq *lowest_rq;
	int ret = 0;

	if (!rq->rt.overloaded)
		return 0;

	next_task = pick_next_pushable_task(rq);
	if (!next_task)
		return 0;

retry:
	if (unlikely(next_task == rq->curr)) {
		WARN_ON(1);
		return 0;
	}

	/*
	 * It's possible that the next_task slipped in of
	 * higher priority than current. If that's the case
	 * just reschedule current.
	 */
	if (unlikely(next_task->prio < rq->curr->prio)) {
		resched_curr(rq);
		return 0;
	}

	/* We might release rq lock */
	get_task_struct(next_task);

	/* find_lock_lowest_rq locks the rq if found */
	lowest_rq = find_lock_lowest_rq(next_task, rq);
	if (!lowest_rq) {
		struct task_struct *task;
		/*
		 * find_lock_lowest_rq releases rq->lock
		 * so it is possible that next_task has migrated.
		 *
		 * We need to make sure that the task is still on the same
		 * run-queue and is also still the next task eligible for
		 * pushing.
		 */
		task = pick_next_pushable_task(rq);
		if (task == next_task) {
			/*
			 * The task hasn't migrated, and is still the next
			 * eligible task, but we failed to find a run-queue
			 * to push it to.  Do not retry in this case, since
			 * other cpus will pull from us when ready.
			 */
			goto out;
		}

		if (!task)
			/* No more tasks, just exit */
			goto out;

		/*
		 * Something has shifted, try again.
		 */
		put_task_struct(next_task);
		next_task = task;
		goto retry;
	}

	deactivate_task(rq, next_task, 0);
	set_task_cpu(next_task, lowest_rq->cpu);
	activate_task(lowest_rq, next_task, 0);
	ret = 1;

	resched_curr(lowest_rq);

	double_unlock_balance(rq, lowest_rq);

out:
	put_task_struct(next_task);

	return ret;
}

static void push_rt_tasks(struct rq *rq)
{
	/* push_rt_task will return true if it moved an RT */
	while (push_rt_task(rq))
		;
}

#ifdef HAVE_RT_PUSH_IPI

/*
 * When a high priority task schedules out from a CPU and a lower priority
 * task is scheduled in, a check is made to see if there's any RT tasks
 * on other CPUs that are waiting to run because a higher priority RT task
 * is currently running on its CPU. In this case, the CPU with multiple RT
 * tasks queued on it (overloaded) needs to be notified that a CPU has opened
 * up that may be able to run one of its non-running queued RT tasks.
 *
 * All CPUs with overloaded RT tasks need to be notified as there is currently
 * no way to know which of these CPUs have the highest priority task waiting
 * to run. Instead of trying to take a spinlock on each of these CPUs,
 * which has shown to cause large latency when done on machines with many
 * CPUs, sending an IPI to the CPUs to have them push off the overloaded
 * RT tasks waiting to run.
 *
 * Just sending an IPI to each of the CPUs is also an issue, as on large
 * count CPU machines, this can cause an IPI storm on a CPU, especially
 * if its the only CPU with multiple RT tasks queued, and a large number
 * of CPUs scheduling a lower priority task at the same time.
 *
 * Each root domain has its own irq work function that can iterate over
 * all CPUs with RT overloaded tasks. Since all CPUs with overloaded RT
 * tassk must be checked if there's one or many CPUs that are lowering
 * their priority, there's a single irq work iterator that will try to
 * push off RT tasks that are waiting to run.
 *
 * When a CPU schedules a lower priority task, it will kick off the
 * irq work iterator that will jump to each CPU with overloaded RT tasks.
 * As it only takes the first CPU that schedules a lower priority task
 * to start the process, the rto_start variable is incremented and if
 * the atomic result is one, then that CPU will try to take the rto_lock.
 * This prevents high contention on the lock as the process handles all
 * CPUs scheduling lower priority tasks.
 *
 * All CPUs that are scheduling a lower priority task will increment the
 * rt_loop_next variable. This will make sure that the irq work iterator
 * checks all RT overloaded CPUs whenever a CPU schedules a new lower
 * priority task, even if the iterator is in the middle of a scan. Incrementing
 * the rt_loop_next will cause the iterator to perform another scan.
 *
 */
static int rto_next_cpu(struct rq *rq)
{
	struct root_domain *rd = rq->rd;
	int next;
	int cpu;

	/*
	 * When starting the IPI RT pushing, the rto_cpu is set to -1,
	 * rt_next_cpu() will simply return the first CPU found in
	 * the rto_mask.
	 *
	 * If rto_next_cpu() is called with rto_cpu is a valid cpu, it
	 * will return the next CPU found in the rto_mask.
	 *
	 * If there are no more CPUs left in the rto_mask, then a check is made
	 * against rto_loop and rto_loop_next. rto_loop is only updated with
	 * the rto_lock held, but any CPU may increment the rto_loop_next
	 * without any locking.
	 */
	for (;;) {

		/* When rto_cpu is -1 this acts like cpumask_first() */
		cpu = cpumask_next(rd->rto_cpu, rd->rto_mask);

		rd->rto_cpu = cpu;

		if (cpu < nr_cpu_ids)
			return cpu;

		rd->rto_cpu = -1;

		/*
		 * ACQUIRE ensures we see the @rto_mask changes
		 * made prior to the @next value observed.
		 *
		 * Matches WMB in rt_set_overload().
		 */
		next = atomic_read_acquire(&rd->rto_loop_next);

		if (rd->rto_loop == next)
			break;

		rd->rto_loop = next;
	}

	return -1;
}

static inline bool rto_start_trylock(atomic_t *v)
{
	return !atomic_cmpxchg_acquire(v, 0, 1);
}

static inline void rto_start_unlock(atomic_t *v)
{
	atomic_set_release(v, 0);
}

static void tell_cpu_to_push(struct rq *rq)
{
	int cpu = -1;

	/* Keep the loop going if the IPI is currently active */
	atomic_inc(&rq->rd->rto_loop_next);

	/* Only one CPU can initiate a loop at a time */
	if (!rto_start_trylock(&rq->rd->rto_loop_start))
		return;

	raw_spin_lock(&rq->rd->rto_lock);

	/*
	 * The rto_cpu is updated under the lock, if it has a valid cpu
	 * then the IPI is still running and will continue due to the
	 * update to loop_next, and nothing needs to be done here.
	 * Otherwise it is finishing up and an ipi needs to be sent.
	 */
	if (rq->rd->rto_cpu < 0)
		cpu = rto_next_cpu(rq);

	raw_spin_unlock(&rq->rd->rto_lock);

	rto_start_unlock(&rq->rd->rto_loop_start);

	if (cpu >= 0)
		irq_work_queue_on(&rq->rd->rto_push_work, cpu);
}

/* Called from hardirq context */
void rto_push_irq_work_func(struct irq_work *work)
{
	struct rq *rq;
	int cpu;

	rq = this_rq();

	/*
	 * We do not need to grab the lock to check for has_pushable_tasks.
	 * When it gets updated, a check is made if a push is possible.
	 */
	if (has_pushable_tasks(rq)) {
		raw_spin_lock(&rq->lock);
		push_rt_tasks(rq);
		raw_spin_unlock(&rq->lock);
	}

	raw_spin_lock(&rq->rd->rto_lock);

	/* Pass the IPI to the next rt overloaded queue */
	cpu = rto_next_cpu(rq);

	raw_spin_unlock(&rq->rd->rto_lock);

	if (cpu < 0)
		return;

	/* Try the next RT overloaded CPU */
	irq_work_queue_on(&rq->rd->rto_push_work, cpu);
}
#endif /* HAVE_RT_PUSH_IPI */

static void pull_rt_task(struct rq *this_rq)
{
	int this_cpu = this_rq->cpu, cpu;
	bool resched = false;
	struct task_struct *p;
	struct rq *src_rq;

	if (likely(!rt_overloaded(this_rq)))
		return;

	/*
	 * Match the barrier from rt_set_overloaded; this guarantees that if we
	 * see overloaded we must also see the rto_mask bit.
	 */
	smp_rmb();

#ifdef HAVE_RT_PUSH_IPI
	if (sched_feat(RT_PUSH_IPI)) {
		tell_cpu_to_push(this_rq);
		return;
	}
#endif

	for_each_cpu(cpu, this_rq->rd->rto_mask) {
		if (this_cpu == cpu)
			continue;

		src_rq = cpu_rq(cpu);

		/*
		 * Don't bother taking the src_rq->lock if the next highest
		 * task is known to be lower-priority than our current task.
		 * This may look racy, but if this value is about to go
		 * logically higher, the src_rq will push this task away.
		 * And if its going logically lower, we do not care
		 */
		if (src_rq->rt.highest_prio.next >=
		    this_rq->rt.highest_prio.curr)
			continue;

		/*
		 * We can potentially drop this_rq's lock in
		 * double_lock_balance, and another CPU could
		 * alter this_rq
		 */
		double_lock_balance(this_rq, src_rq);

		/*
		 * We can pull only a task, which is pushable
		 * on its rq, and no others.
		 */
		p = pick_highest_pushable_task(src_rq, this_cpu);

		/*
		 * Do we have an RT task that preempts
		 * the to-be-scheduled task?
		 */
		if (p && (p->prio < this_rq->rt.highest_prio.curr)) {
			WARN_ON(p == src_rq->curr);
			WARN_ON(!task_on_rq_queued(p));

			/*
			 * There's a chance that p is higher in priority
			 * than what's currently running on its cpu.
			 * This is just that p is wakeing up and hasn't
			 * had a chance to schedule. We only pull
			 * p if it is lower in priority than the
			 * current task on the run queue
			 */
			if (p->prio < src_rq->curr->prio)
				goto skip;

			resched = true;

			deactivate_task(src_rq, p, 0);
			set_task_cpu(p, this_cpu);
			activate_task(this_rq, p, 0);
			/*
			 * We continue with the search, just in
			 * case there's an even higher prio task
			 * in another runqueue. (low likelihood
			 * but possible)
			 */
		}
skip:
		double_unlock_balance(this_rq, src_rq);
	}

	if (resched)
		resched_curr(this_rq);
}

/*
 * If we are not running and we are not going to reschedule soon, we should
 * try to push tasks away now
 */
static void task_woken_rt(struct rq *rq, struct task_struct *p)
{
	if (!task_running(rq, p) &&
	    !test_tsk_need_resched(rq->curr) &&
	    p->nr_cpus_allowed > 1 &&
	    (dl_task(rq->curr) || rt_task(rq->curr)) &&
	    (rq->curr->nr_cpus_allowed < 2 ||
	     rq->curr->prio <= p->prio))
		push_rt_tasks(rq);
}

/* Assumes rq->lock is held */
static void rq_online_rt(struct rq *rq)
{
	if (rq->rt.overloaded)
		rt_set_overload(rq);

	__enable_runtime(rq);

	cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
}

/* Assumes rq->lock is held */
static void rq_offline_rt(struct rq *rq)
{
	if (rq->rt.overloaded)
		rt_clear_overload(rq);

	__disable_runtime(rq);

	cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_INVALID);
}

/*
 * When switch from the rt queue, we bring ourselves to a position
 * that we might want to pull RT tasks from other runqueues.
 */
static void switched_from_rt(struct rq *rq, struct task_struct *p)
{
	/*
	 * If there are other RT tasks then we will reschedule
	 * and the scheduling of the other RT tasks will handle
	 * the balancing. But if we are the last RT task
	 * we may need to handle the pulling of RT tasks
	 * now.
	 */
	if (!task_on_rq_queued(p) || rq->rt.rt_nr_running)
		return;

	queue_pull_task(rq);
}

void __init init_sched_rt_class(void)
{
	unsigned int i;

	for_each_possible_cpu(i) {
		zalloc_cpumask_var_node(&per_cpu(local_cpu_mask, i),
					GFP_KERNEL, cpu_to_node(i));
	}
}
#endif /* CONFIG_SMP */

/*
 * When switching a task to RT, we may overload the runqueue
 * with RT tasks. In this case we try to push them off to
 * other runqueues.
 */
static void switched_to_rt(struct rq *rq, struct task_struct *p)
{
	/*
	 * If we are already running, then there's nothing
	 * that needs to be done. But if we are not running
	 * we may need to preempt the current running task.
	 * If that current running task is also an RT task
	 * then see if we can move to another run queue.
	 */
	if (task_on_rq_queued(p) && rq->curr != p) {
#ifdef CONFIG_SMP
		if (p->nr_cpus_allowed > 1 && rq->rt.overloaded)
			queue_push_tasks(rq);
#endif /* CONFIG_SMP */
		if (p->prio < rq->curr->prio)
			resched_curr(rq);
	}
}

/*
 * Priority of the task has changed. This may cause
 * us to initiate a push or pull.
 */
static void
prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
{
	if (!task_on_rq_queued(p))
		return;

	if (rq->curr == p) {
#ifdef CONFIG_SMP
		/*
		 * If our priority decreases while running, we
		 * may need to pull tasks to this runqueue.
		 */
		if (oldprio < p->prio)
			queue_pull_task(rq);

		/*
		 * If there's a higher priority task waiting to run
		 * then reschedule.
		 */
		if (p->prio > rq->rt.highest_prio.curr)
			resched_curr(rq);
#else
		/* For UP simply resched on drop of prio */
		if (oldprio < p->prio)
			resched_curr(rq);
#endif /* CONFIG_SMP */
	} else {
		/*
		 * This task is not running, but if it is
		 * greater than the current running task
		 * then reschedule.
		 */
		if (p->prio < rq->curr->prio)
			resched_curr(rq);
	}
}

#ifdef CONFIG_POSIX_TIMERS
static void watchdog(struct rq *rq, struct task_struct *p)
{
	unsigned long soft, hard;

	/* max may change after cur was read, this will be fixed next tick */
	soft = task_rlimit(p, RLIMIT_RTTIME);
	hard = task_rlimit_max(p, RLIMIT_RTTIME);

	if (soft != RLIM_INFINITY) {
		unsigned long next;

		if (p->rt.watchdog_stamp != jiffies) {
			p->rt.timeout++;
			p->rt.watchdog_stamp = jiffies;
		}

		next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ);
		if (p->rt.timeout > next)
			p->cputime_expires.sched_exp = p->se.sum_exec_runtime;
	}
}
#else
static inline void watchdog(struct rq *rq, struct task_struct *p) { }
#endif

static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
{
	struct sched_rt_entity *rt_se = &p->rt;

	update_curr_rt(rq);

	watchdog(rq, p);

	/*
	 * RR tasks need a special form of timeslice management.
	 * FIFO tasks have no timeslices.
	 */
	if (p->policy != SCHED_RR)
		return;

	if (--p->rt.time_slice)
		return;

	p->rt.time_slice = sched_rr_timeslice;

	/*
	 * Requeue to the end of queue if we (and all of our ancestors) are not
	 * the only element on the queue
	 */
	for_each_sched_rt_entity(rt_se) {
		if (rt_se->run_list.prev != rt_se->run_list.next) {
			requeue_task_rt(rq, p, 0);
			resched_curr(rq);
			return;
		}
	}
}

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

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

	/* The running task is never eligible for pushing */
	dequeue_pushable_task(rq, p);
}

static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
{
	/*
	 * Time slice is 0 for SCHED_FIFO tasks
	 */
	if (task->policy == SCHED_RR)
		return sched_rr_timeslice;
	else
		return 0;
}

const struct sched_class rt_sched_class = {
	.next			= &fair_sched_class,
	.enqueue_task		= enqueue_task_rt,
	.dequeue_task		= dequeue_task_rt,
	.yield_task		= yield_task_rt,

	.check_preempt_curr	= check_preempt_curr_rt,

	.pick_next_task		= pick_next_task_rt,
	.put_prev_task		= put_prev_task_rt,

#ifdef CONFIG_SMP
	.select_task_rq		= select_task_rq_rt,

	.set_cpus_allowed       = set_cpus_allowed_common,
	.rq_online              = rq_online_rt,
	.rq_offline             = rq_offline_rt,
	.task_woken		= task_woken_rt,
	.switched_from		= switched_from_rt,
#endif

	.set_curr_task          = set_curr_task_rt,
	.task_tick		= task_tick_rt,

	.get_rr_interval	= get_rr_interval_rt,

	.prio_changed		= prio_changed_rt,
	.switched_to		= switched_to_rt,

	.update_curr		= update_curr_rt,
};

#ifdef CONFIG_RT_GROUP_SCHED
/*
 * Ensure that the real time constraints are schedulable.
 */
static DEFINE_MUTEX(rt_constraints_mutex);

/* Must be called with tasklist_lock held */
static inline int tg_has_rt_tasks(struct task_group *tg)
{
	struct task_struct *g, *p;

	/*
	 * Autogroups do not have RT tasks; see autogroup_create().
	 */
	if (task_group_is_autogroup(tg))
		return 0;

	for_each_process_thread(g, p) {
		if (rt_task(p) && task_group(p) == tg)
			return 1;
	}

	return 0;
}

struct rt_schedulable_data {
	struct task_group *tg;
	u64 rt_period;
	u64 rt_runtime;
};

static int tg_rt_schedulable(struct task_group *tg, void *data)
{
	struct rt_schedulable_data *d = data;
	struct task_group *child;
	unsigned long total, sum = 0;
	u64 period, runtime;

	period = ktime_to_ns(tg->rt_bandwidth.rt_period);
	runtime = tg->rt_bandwidth.rt_runtime;

	if (tg == d->tg) {
		period = d->rt_period;
		runtime = d->rt_runtime;
	}

	/*
	 * Cannot have more runtime than the period.
	 */
	if (runtime > period && runtime != RUNTIME_INF)
		return -EINVAL;

	/*
	 * Ensure we don't starve existing RT tasks.
	 */
	if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
		return -EBUSY;

	total = to_ratio(period, runtime);

	/*
	 * Nobody can have more than the global setting allows.
	 */
	if (total > to_ratio(global_rt_period(), global_rt_runtime()))
		return -EINVAL;

	/*
	 * The sum of our children's runtime should not exceed our own.
	 */
	list_for_each_entry_rcu(child, &tg->children, siblings) {
		period = ktime_to_ns(child->rt_bandwidth.rt_period);
		runtime = child->rt_bandwidth.rt_runtime;

		if (child == d->tg) {
			period = d->rt_period;
			runtime = d->rt_runtime;
		}

		sum += to_ratio(period, runtime);
	}

	if (sum > total)
		return -EINVAL;

	return 0;
}

static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
{
	int ret;

	struct rt_schedulable_data data = {
		.tg = tg,
		.rt_period = period,
		.rt_runtime = runtime,
	};

	rcu_read_lock();
	ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data);
	rcu_read_unlock();

	return ret;
}

static int tg_set_rt_bandwidth(struct task_group *tg,
		u64 rt_period, u64 rt_runtime)
{
	int i, err = 0;

	/*
	 * Disallowing the root group RT runtime is BAD, it would disallow the
	 * kernel creating (and or operating) RT threads.
	 */
	if (tg == &root_task_group && rt_runtime == 0)
		return -EINVAL;

	/* No period doesn't make any sense. */
	if (rt_period == 0)
		return -EINVAL;

	mutex_lock(&rt_constraints_mutex);
	read_lock(&tasklist_lock);
	err = __rt_schedulable(tg, rt_period, rt_runtime);
	if (err)
		goto unlock;

	raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
	tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
	tg->rt_bandwidth.rt_runtime = rt_runtime;

	for_each_possible_cpu(i) {
		struct rt_rq *rt_rq = tg->rt_rq[i];

		raw_spin_lock(&rt_rq->rt_runtime_lock);
		rt_rq->rt_runtime = rt_runtime;
		raw_spin_unlock(&rt_rq->rt_runtime_lock);
	}
	raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
unlock:
	read_unlock(&tasklist_lock);
	mutex_unlock(&rt_constraints_mutex);

	return err;
}

int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
{
	u64 rt_runtime, rt_period;

	rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
	rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
	if (rt_runtime_us < 0)
		rt_runtime = RUNTIME_INF;

	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
}

long sched_group_rt_runtime(struct task_group *tg)
{
	u64 rt_runtime_us;

	if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF)
		return -1;

	rt_runtime_us = tg->rt_bandwidth.rt_runtime;
	do_div(rt_runtime_us, NSEC_PER_USEC);
	return rt_runtime_us;
}

int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
{
	u64 rt_runtime, rt_period;

	rt_period = rt_period_us * NSEC_PER_USEC;
	rt_runtime = tg->rt_bandwidth.rt_runtime;

	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
}

long sched_group_rt_period(struct task_group *tg)
{
	u64 rt_period_us;

	rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period);
	do_div(rt_period_us, NSEC_PER_USEC);
	return rt_period_us;
}

static int sched_rt_global_constraints(void)
{
	int ret = 0;

	mutex_lock(&rt_constraints_mutex);
	read_lock(&tasklist_lock);
	ret = __rt_schedulable(NULL, 0, 0);
	read_unlock(&tasklist_lock);
	mutex_unlock(&rt_constraints_mutex);

	return ret;
}

int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
{
	/* Don't accept realtime tasks when there is no way for them to run */
	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
		return 0;

	return 1;
}

#else /* !CONFIG_RT_GROUP_SCHED */
static int sched_rt_global_constraints(void)
{
	unsigned long flags;
	int i;

	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
	for_each_possible_cpu(i) {
		struct rt_rq *rt_rq = &cpu_rq(i)->rt;

		raw_spin_lock(&rt_rq->rt_runtime_lock);
		rt_rq->rt_runtime = global_rt_runtime();
		raw_spin_unlock(&rt_rq->rt_runtime_lock);
	}
	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);

	return 0;
}
#endif /* CONFIG_RT_GROUP_SCHED */

static int sched_rt_global_validate(void)
{
	if (sysctl_sched_rt_period <= 0)
		return -EINVAL;

	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
		(sysctl_sched_rt_runtime > sysctl_sched_rt_period))
		return -EINVAL;

	return 0;
}

static void sched_rt_do_global(void)
{
	def_rt_bandwidth.rt_runtime = global_rt_runtime();
	def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
}

int sched_rt_handler(struct ctl_table *table, int write,
		void __user *buffer, size_t *lenp,
		loff_t *ppos)
{
	int old_period, old_runtime;
	static DEFINE_MUTEX(mutex);
	int ret;

	mutex_lock(&mutex);
	old_period = sysctl_sched_rt_period;
	old_runtime = sysctl_sched_rt_runtime;

	ret = proc_dointvec(table, write, buffer, lenp, ppos);

	if (!ret && write) {
		ret = sched_rt_global_validate();
		if (ret)
			goto undo;

		ret = sched_dl_global_validate();
		if (ret)
			goto undo;

		ret = sched_rt_global_constraints();
		if (ret)
			goto undo;

		sched_rt_do_global();
		sched_dl_do_global();
	}
	if (0) {
undo:
		sysctl_sched_rt_period = old_period;
		sysctl_sched_rt_runtime = old_runtime;
	}
	mutex_unlock(&mutex);

	return ret;
}

int sched_rr_handler(struct ctl_table *table, int write,
		void __user *buffer, size_t *lenp,
		loff_t *ppos)
{
	int ret;
	static DEFINE_MUTEX(mutex);

	mutex_lock(&mutex);
	ret = proc_dointvec(table, write, buffer, lenp, ppos);
	/*
	 * Make sure that internally we keep jiffies.
	 * Also, writing zero resets the timeslice to default:
	 */
	if (!ret && write) {
		sched_rr_timeslice =
			sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE :
			msecs_to_jiffies(sysctl_sched_rr_timeslice);
	}
	mutex_unlock(&mutex);
	return ret;
}

#ifdef CONFIG_SCHED_DEBUG
extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);

void print_rt_stats(struct seq_file *m, int cpu)
{
	rt_rq_iter_t iter;
	struct rt_rq *rt_rq;

	rcu_read_lock();
	for_each_rt_rq(rt_rq, iter, cpu_rq(cpu))
		print_rt_rq(m, cpu, rt_rq);
	rcu_read_unlock();
}
#endif /* CONFIG_SCHED_DEBUG */
OpenPOWER on IntegriCloud