aboutsummaryrefslogtreecommitdiff
path: root/block/blk-throttle.c
blob: 39bb6e68a9a294bc47ad7ada8338673e27404cef (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Interface for controlling IO bandwidth on a request queue
 *
 * Copyright (C) 2010 Vivek Goyal <vgoyal@redhat.com>
 */

#include <linux/module.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/blktrace_api.h>
#include <linux/blk-cgroup.h>
#include "blk.h"
#include "blk-cgroup-rwstat.h"
#include "blk-throttle.h"

/* Max dispatch from a group in 1 round */
#define THROTL_GRP_QUANTUM 8

/* Total max dispatch from all groups in one round */
#define THROTL_QUANTUM 32

/* Throttling is performed over a slice and after that slice is renewed */
#define DFL_THROTL_SLICE_HD (HZ / 10)
#define DFL_THROTL_SLICE_SSD (HZ / 50)
#define MAX_THROTL_SLICE (HZ)
#define MAX_IDLE_TIME (5L * 1000 * 1000) /* 5 s */
#define MIN_THROTL_BPS (320 * 1024)
#define MIN_THROTL_IOPS (10)
#define DFL_LATENCY_TARGET (-1L)
#define DFL_IDLE_THRESHOLD (0)
#define DFL_HD_BASELINE_LATENCY (4000L) /* 4ms */
#define LATENCY_FILTERED_SSD (0)
/*
 * For HD, very small latency comes from sequential IO. Such IO is helpless to
 * help determine if its IO is impacted by others, hence we ignore the IO
 */
#define LATENCY_FILTERED_HD (1000L) /* 1ms */

/* A workqueue to queue throttle related work */
static struct workqueue_struct *kthrotld_workqueue;

enum tg_state_flags {
	THROTL_TG_PENDING	= 1 << 0,	/* on parent's pending tree */
	THROTL_TG_WAS_EMPTY	= 1 << 1,	/* bio_lists[] became non-empty */
};

#define rb_entry_tg(node)	rb_entry((node), struct throtl_grp, rb_node)

/* We measure latency for request size from <= 4k to >= 1M */
#define LATENCY_BUCKET_SIZE 9

struct latency_bucket {
	unsigned long total_latency; /* ns / 1024 */
	int samples;
};

struct avg_latency_bucket {
	unsigned long latency; /* ns / 1024 */
	bool valid;
};

struct throtl_data
{
	/* service tree for active throtl groups */
	struct throtl_service_queue service_queue;

	struct request_queue *queue;

	/* Total Number of queued bios on READ and WRITE lists */
	unsigned int nr_queued[2];

	unsigned int throtl_slice;

	/* Work for dispatching throttled bios */
	struct work_struct dispatch_work;
	unsigned int limit_index;
	bool limit_valid[LIMIT_CNT];

	unsigned long low_upgrade_time;
	unsigned long low_downgrade_time;

	unsigned int scale;

	struct latency_bucket tmp_buckets[2][LATENCY_BUCKET_SIZE];
	struct avg_latency_bucket avg_buckets[2][LATENCY_BUCKET_SIZE];
	struct latency_bucket __percpu *latency_buckets[2];
	unsigned long last_calculate_time;
	unsigned long filtered_latency;

	bool track_bio_latency;
};

static void throtl_pending_timer_fn(struct timer_list *t);

static inline struct blkcg_gq *tg_to_blkg(struct throtl_grp *tg)
{
	return pd_to_blkg(&tg->pd);
}

/**
 * sq_to_tg - return the throl_grp the specified service queue belongs to
 * @sq: the throtl_service_queue of interest
 *
 * Return the throtl_grp @sq belongs to.  If @sq is the top-level one
 * embedded in throtl_data, %NULL is returned.
 */
static struct throtl_grp *sq_to_tg(struct throtl_service_queue *sq)
{
	if (sq && sq->parent_sq)
		return container_of(sq, struct throtl_grp, service_queue);
	else
		return NULL;
}

/**
 * sq_to_td - return throtl_data the specified service queue belongs to
 * @sq: the throtl_service_queue of interest
 *
 * A service_queue can be embedded in either a throtl_grp or throtl_data.
 * Determine the associated throtl_data accordingly and return it.
 */
static struct throtl_data *sq_to_td(struct throtl_service_queue *sq)
{
	struct throtl_grp *tg = sq_to_tg(sq);

	if (tg)
		return tg->td;
	else
		return container_of(sq, struct throtl_data, service_queue);
}

/*
 * cgroup's limit in LIMIT_MAX is scaled if low limit is set. This scale is to
 * make the IO dispatch more smooth.
 * Scale up: linearly scale up according to lapsed time since upgrade. For
 *           every throtl_slice, the limit scales up 1/2 .low limit till the
 *           limit hits .max limit
 * Scale down: exponentially scale down if a cgroup doesn't hit its .low limit
 */
static uint64_t throtl_adjusted_limit(uint64_t low, struct throtl_data *td)
{
	/* arbitrary value to avoid too big scale */
	if (td->scale < 4096 && time_after_eq(jiffies,
	    td->low_upgrade_time + td->scale * td->throtl_slice))
		td->scale = (jiffies - td->low_upgrade_time) / td->throtl_slice;

	return low + (low >> 1) * td->scale;
}

static uint64_t tg_bps_limit(struct throtl_grp *tg, int rw)
{
	struct blkcg_gq *blkg = tg_to_blkg(tg);
	struct throtl_data *td;
	uint64_t ret;

	if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
		return U64_MAX;

	td = tg->td;
	ret = tg->bps[rw][td->limit_index];
	if (ret == 0 && td->limit_index == LIMIT_LOW) {
		/* intermediate node or iops isn't 0 */
		if (!list_empty(&blkg->blkcg->css.children) ||
		    tg->iops[rw][td->limit_index])
			return U64_MAX;
		else
			return MIN_THROTL_BPS;
	}

	if (td->limit_index == LIMIT_MAX && tg->bps[rw][LIMIT_LOW] &&
	    tg->bps[rw][LIMIT_LOW] != tg->bps[rw][LIMIT_MAX]) {
		uint64_t adjusted;

		adjusted = throtl_adjusted_limit(tg->bps[rw][LIMIT_LOW], td);
		ret = min(tg->bps[rw][LIMIT_MAX], adjusted);
	}
	return ret;
}

static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw)
{
	struct blkcg_gq *blkg = tg_to_blkg(tg);
	struct throtl_data *td;
	unsigned int ret;

	if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
		return UINT_MAX;

	td = tg->td;
	ret = tg->iops[rw][td->limit_index];
	if (ret == 0 && tg->td->limit_index == LIMIT_LOW) {
		/* intermediate node or bps isn't 0 */
		if (!list_empty(&blkg->blkcg->css.children) ||
		    tg->bps[rw][td->limit_index])
			return UINT_MAX;
		else
			return MIN_THROTL_IOPS;
	}

	if (td->limit_index == LIMIT_MAX && tg->iops[rw][LIMIT_LOW] &&
	    tg->iops[rw][LIMIT_LOW] != tg->iops[rw][LIMIT_MAX]) {
		uint64_t adjusted;

		adjusted = throtl_adjusted_limit(tg->iops[rw][LIMIT_LOW], td);
		if (adjusted > UINT_MAX)
			adjusted = UINT_MAX;
		ret = min_t(unsigned int, tg->iops[rw][LIMIT_MAX], adjusted);
	}
	return ret;
}

#define request_bucket_index(sectors) \
	clamp_t(int, order_base_2(sectors) - 3, 0, LATENCY_BUCKET_SIZE - 1)

/**
 * throtl_log - log debug message via blktrace
 * @sq: the service_queue being reported
 * @fmt: printf format string
 * @args: printf args
 *
 * The messages are prefixed with "throtl BLKG_NAME" if @sq belongs to a
 * throtl_grp; otherwise, just "throtl".
 */
#define throtl_log(sq, fmt, args...)	do {				\
	struct throtl_grp *__tg = sq_to_tg((sq));			\
	struct throtl_data *__td = sq_to_td((sq));			\
									\
	(void)__td;							\
	if (likely(!blk_trace_note_message_enabled(__td->queue)))	\
		break;							\
	if ((__tg)) {							\
		blk_add_cgroup_trace_msg(__td->queue,			\
			tg_to_blkg(__tg)->blkcg, "throtl " fmt, ##args);\
	} else {							\
		blk_add_trace_msg(__td->queue, "throtl " fmt, ##args);	\
	}								\
} while (0)

static inline unsigned int throtl_bio_data_size(struct bio *bio)
{
	/* assume it's one sector */
	if (unlikely(bio_op(bio) == REQ_OP_DISCARD))
		return 512;
	return bio->bi_iter.bi_size;
}

static void throtl_qnode_init(struct throtl_qnode *qn, struct throtl_grp *tg)
{
	INIT_LIST_HEAD(&qn->node);
	bio_list_init(&qn->bios);
	qn->tg = tg;
}

/**
 * throtl_qnode_add_bio - add a bio to a throtl_qnode and activate it
 * @bio: bio being added
 * @qn: qnode to add bio to
 * @queued: the service_queue->queued[] list @qn belongs to
 *
 * Add @bio to @qn and put @qn on @queued if it's not already on.
 * @qn->tg's reference count is bumped when @qn is activated.  See the
 * comment on top of throtl_qnode definition for details.
 */
static void throtl_qnode_add_bio(struct bio *bio, struct throtl_qnode *qn,
				 struct list_head *queued)
{
	bio_list_add(&qn->bios, bio);
	if (list_empty(&qn->node)) {
		list_add_tail(&qn->node, queued);
		blkg_get(tg_to_blkg(qn->tg));
	}
}

/**
 * throtl_peek_queued - peek the first bio on a qnode list
 * @queued: the qnode list to peek
 */
static struct bio *throtl_peek_queued(struct list_head *queued)
{
	struct throtl_qnode *qn;
	struct bio *bio;

	if (list_empty(queued))
		return NULL;

	qn = list_first_entry(queued, struct throtl_qnode, node);
	bio = bio_list_peek(&qn->bios);
	WARN_ON_ONCE(!bio);
	return bio;
}

/**
 * throtl_pop_queued - pop the first bio form a qnode list
 * @queued: the qnode list to pop a bio from
 * @tg_to_put: optional out argument for throtl_grp to put
 *
 * Pop the first bio from the qnode list @queued.  After popping, the first
 * qnode is removed from @queued if empty or moved to the end of @queued so
 * that the popping order is round-robin.
 *
 * When the first qnode is removed, its associated throtl_grp should be put
 * too.  If @tg_to_put is NULL, this function automatically puts it;
 * otherwise, *@tg_to_put is set to the throtl_grp to put and the caller is
 * responsible for putting it.
 */
static struct bio *throtl_pop_queued(struct list_head *queued,
				     struct throtl_grp **tg_to_put)
{
	struct throtl_qnode *qn;
	struct bio *bio;

	if (list_empty(queued))
		return NULL;

	qn = list_first_entry(queued, struct throtl_qnode, node);
	bio = bio_list_pop(&qn->bios);
	WARN_ON_ONCE(!bio);

	if (bio_list_empty(&qn->bios)) {
		list_del_init(&qn->node);
		if (tg_to_put)
			*tg_to_put = qn->tg;
		else
			blkg_put(tg_to_blkg(qn->tg));
	} else {
		list_move_tail(&qn->node, queued);
	}

	return bio;
}

/* init a service_queue, assumes the caller zeroed it */
static void throtl_service_queue_init(struct throtl_service_queue *sq)
{
	INIT_LIST_HEAD(&sq->queued[0]);
	INIT_LIST_HEAD(&sq->queued[1]);
	sq->pending_tree = RB_ROOT_CACHED;
	timer_setup(&sq->pending_timer, throtl_pending_timer_fn, 0);
}

static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp,
						struct request_queue *q,
						struct blkcg *blkcg)
{
	struct throtl_grp *tg;
	int rw;

	tg = kzalloc_node(sizeof(*tg), gfp, q->node);
	if (!tg)
		return NULL;

	if (blkg_rwstat_init(&tg->stat_bytes, gfp))
		goto err_free_tg;

	if (blkg_rwstat_init(&tg->stat_ios, gfp))
		goto err_exit_stat_bytes;

	throtl_service_queue_init(&tg->service_queue);

	for (rw = READ; rw <= WRITE; rw++) {
		throtl_qnode_init(&tg->qnode_on_self[rw], tg);
		throtl_qnode_init(&tg->qnode_on_parent[rw], tg);
	}

	RB_CLEAR_NODE(&tg->rb_node);
	tg->bps[READ][LIMIT_MAX] = U64_MAX;
	tg->bps[WRITE][LIMIT_MAX] = U64_MAX;
	tg->iops[READ][LIMIT_MAX] = UINT_MAX;
	tg->iops[WRITE][LIMIT_MAX] = UINT_MAX;
	tg->bps_conf[READ][LIMIT_MAX] = U64_MAX;
	tg->bps_conf[WRITE][LIMIT_MAX] = U64_MAX;
	tg->iops_conf[READ][LIMIT_MAX] = UINT_MAX;
	tg->iops_conf[WRITE][LIMIT_MAX] = UINT_MAX;
	/* LIMIT_LOW will have default value 0 */

	tg->latency_target = DFL_LATENCY_TARGET;
	tg->latency_target_conf = DFL_LATENCY_TARGET;
	tg->idletime_threshold = DFL_IDLE_THRESHOLD;
	tg->idletime_threshold_conf = DFL_IDLE_THRESHOLD;

	return &tg->pd;

err_exit_stat_bytes:
	blkg_rwstat_exit(&tg->stat_bytes);
err_free_tg:
	kfree(tg);
	return NULL;
}

static void throtl_pd_init(struct blkg_policy_data *pd)
{
	struct throtl_grp *tg = pd_to_tg(pd);
	struct blkcg_gq *blkg = tg_to_blkg(tg);
	struct throtl_data *td = blkg->q->td;
	struct throtl_service_queue *sq = &tg->service_queue;

	/*
	 * If on the default hierarchy, we switch to properly hierarchical
	 * behavior where limits on a given throtl_grp are applied to the
	 * whole subtree rather than just the group itself.  e.g. If 16M
	 * read_bps limit is set on the root group, the whole system can't
	 * exceed 16M for the device.
	 *
	 * If not on the default hierarchy, the broken flat hierarchy
	 * behavior is retained where all throtl_grps are treated as if
	 * they're all separate root groups right below throtl_data.
	 * Limits of a group don't interact with limits of other groups
	 * regardless of the position of the group in the hierarchy.
	 */
	sq->parent_sq = &td->service_queue;
	if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent)
		sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue;
	tg->td = td;
}

/*
 * Set has_rules[] if @tg or any of its parents have limits configured.
 * This doesn't require walking up to the top of the hierarchy as the
 * parent's has_rules[] is guaranteed to be correct.
 */
static void tg_update_has_rules(struct throtl_grp *tg)
{
	struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq);
	struct throtl_data *td = tg->td;
	int rw;

	for (rw = READ; rw <= WRITE; rw++)
		tg->has_rules[rw] = (parent_tg && parent_tg->has_rules[rw]) ||
			(td->limit_valid[td->limit_index] &&
			 (tg_bps_limit(tg, rw) != U64_MAX ||
			  tg_iops_limit(tg, rw) != UINT_MAX));
}

static void throtl_pd_online(struct blkg_policy_data *pd)
{
	struct throtl_grp *tg = pd_to_tg(pd);
	/*
	 * We don't want new groups to escape the limits of its ancestors.
	 * Update has_rules[] after a new group is brought online.
	 */
	tg_update_has_rules(tg);
}

#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
static void blk_throtl_update_limit_valid(struct throtl_data *td)
{
	struct cgroup_subsys_state *pos_css;
	struct blkcg_gq *blkg;
	bool low_valid = false;

	rcu_read_lock();
	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
		struct throtl_grp *tg = blkg_to_tg(blkg);

		if (tg->bps[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] ||
		    tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) {
			low_valid = true;
			break;
		}
	}
	rcu_read_unlock();

	td->limit_valid[LIMIT_LOW] = low_valid;
}
#else
static inline void blk_throtl_update_limit_valid(struct throtl_data *td)
{
}
#endif

static void throtl_upgrade_state(struct throtl_data *td);
static void throtl_pd_offline(struct blkg_policy_data *pd)
{
	struct throtl_grp *tg = pd_to_tg(pd);

	tg->bps[READ][LIMIT_LOW] = 0;
	tg->bps[WRITE][LIMIT_LOW] = 0;
	tg->iops[READ][LIMIT_LOW] = 0;
	tg->iops[WRITE][LIMIT_LOW] = 0;

	blk_throtl_update_limit_valid(tg->td);

	if (!tg->td->limit_valid[tg->td->limit_index])
		throtl_upgrade_state(tg->td);
}

static void throtl_pd_free(struct blkg_policy_data *pd)
{
	struct throtl_grp *tg = pd_to_tg(pd);

	del_timer_sync(&tg->service_queue.pending_timer);
	blkg_rwstat_exit(&tg->stat_bytes);
	blkg_rwstat_exit(&tg->stat_ios);
	kfree(tg);
}

static struct throtl_grp *
throtl_rb_first(struct throtl_service_queue *parent_sq)
{
	struct rb_node *n;

	n = rb_first_cached(&parent_sq->pending_tree);
	WARN_ON_ONCE(!n);
	if (!n)
		return NULL;
	return rb_entry_tg(n);
}

static void throtl_rb_erase(struct rb_node *n,
			    struct throtl_service_queue *parent_sq)
{
	rb_erase_cached(n, &parent_sq->pending_tree);
	RB_CLEAR_NODE(n);
	--parent_sq->nr_pending;
}

static void update_min_dispatch_time(struct throtl_service_queue *parent_sq)
{
	struct throtl_grp *tg;

	tg = throtl_rb_first(parent_sq);
	if (!tg)
		return;

	parent_sq->first_pending_disptime = tg->disptime;
}

static void tg_service_queue_add(struct throtl_grp *tg)
{
	struct throtl_service_queue *parent_sq = tg->service_queue.parent_sq;
	struct rb_node **node = &parent_sq->pending_tree.rb_root.rb_node;
	struct rb_node *parent = NULL;
	struct throtl_grp *__tg;
	unsigned long key = tg->disptime;
	bool leftmost = true;

	while (*node != NULL) {
		parent = *node;
		__tg = rb_entry_tg(parent);

		if (time_before(key, __tg->disptime))
			node = &parent->rb_left;
		else {
			node = &parent->rb_right;
			leftmost = false;
		}
	}

	rb_link_node(&tg->rb_node, parent, node);
	rb_insert_color_cached(&tg->rb_node, &parent_sq->pending_tree,
			       leftmost);
}

static void throtl_enqueue_tg(struct throtl_grp *tg)
{
	if (!(tg->flags & THROTL_TG_PENDING)) {
		tg_service_queue_add(tg);
		tg->flags |= THROTL_TG_PENDING;
		tg->service_queue.parent_sq->nr_pending++;
	}
}

static void throtl_dequeue_tg(struct throtl_grp *tg)
{
	if (tg->flags & THROTL_TG_PENDING) {
		throtl_rb_erase(&tg->rb_node, tg->service_queue.parent_sq);
		tg->flags &= ~THROTL_TG_PENDING;
	}
}

/* Call with queue lock held */
static void throtl_schedule_pending_timer(struct throtl_service_queue *sq,
					  unsigned long expires)
{
	unsigned long max_expire = jiffies + 8 * sq_to_td(sq)->throtl_slice;

	/*
	 * Since we are adjusting the throttle limit dynamically, the sleep
	 * time calculated according to previous limit might be invalid. It's
	 * possible the cgroup sleep time is very long and no other cgroups
	 * have IO running so notify the limit changes. Make sure the cgroup
	 * doesn't sleep too long to avoid the missed notification.
	 */
	if (time_after(expires, max_expire))
		expires = max_expire;
	mod_timer(&sq->pending_timer, expires);
	throtl_log(sq, "schedule timer. delay=%lu jiffies=%lu",
		   expires - jiffies, jiffies);
}

/**
 * throtl_schedule_next_dispatch - schedule the next dispatch cycle
 * @sq: the service_queue to schedule dispatch for
 * @force: force scheduling
 *
 * Arm @sq->pending_timer so that the next dispatch cycle starts on the
 * dispatch time of the first pending child.  Returns %true if either timer
 * is armed or there's no pending child left.  %false if the current
 * dispatch window is still open and the caller should continue
 * dispatching.
 *
 * If @force is %true, the dispatch timer is always scheduled and this
 * function is guaranteed to return %true.  This is to be used when the
 * caller can't dispatch itself and needs to invoke pending_timer
 * unconditionally.  Note that forced scheduling is likely to induce short
 * delay before dispatch starts even if @sq->first_pending_disptime is not
 * in the future and thus shouldn't be used in hot paths.
 */
static bool throtl_schedule_next_dispatch(struct throtl_service_queue *sq,
					  bool force)
{
	/* any pending children left? */
	if (!sq->nr_pending)
		return true;

	update_min_dispatch_time(sq);

	/* is the next dispatch time in the future? */
	if (force || time_after(sq->first_pending_disptime, jiffies)) {
		throtl_schedule_pending_timer(sq, sq->first_pending_disptime);
		return true;
	}

	/* tell the caller to continue dispatching */
	return false;
}

static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg,
		bool rw, unsigned long start)
{
	tg->bytes_disp[rw] = 0;
	tg->io_disp[rw] = 0;

	atomic_set(&tg->io_split_cnt[rw], 0);

	/*
	 * Previous slice has expired. We must have trimmed it after last
	 * bio dispatch. That means since start of last slice, we never used
	 * that bandwidth. Do try to make use of that bandwidth while giving
	 * credit.
	 */
	if (time_after_eq(start, tg->slice_start[rw]))
		tg->slice_start[rw] = start;

	tg->slice_end[rw] = jiffies + tg->td->throtl_slice;
	throtl_log(&tg->service_queue,
		   "[%c] new slice with credit start=%lu end=%lu jiffies=%lu",
		   rw == READ ? 'R' : 'W', tg->slice_start[rw],
		   tg->slice_end[rw], jiffies);
}

static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw)
{
	tg->bytes_disp[rw] = 0;
	tg->io_disp[rw] = 0;
	tg->slice_start[rw] = jiffies;
	tg->slice_end[rw] = jiffies + tg->td->throtl_slice;

	atomic_set(&tg->io_split_cnt[rw], 0);

	throtl_log(&tg->service_queue,
		   "[%c] new slice start=%lu end=%lu jiffies=%lu",
		   rw == READ ? 'R' : 'W', tg->slice_start[rw],
		   tg->slice_end[rw], jiffies);
}

static inline void throtl_set_slice_end(struct throtl_grp *tg, bool rw,
					unsigned long jiffy_end)
{
	tg->slice_end[rw] = roundup(jiffy_end, tg->td->throtl_slice);
}

static inline void throtl_extend_slice(struct throtl_grp *tg, bool rw,
				       unsigned long jiffy_end)
{
	throtl_set_slice_end(tg, rw, jiffy_end);
	throtl_log(&tg->service_queue,
		   "[%c] extend slice start=%lu end=%lu jiffies=%lu",
		   rw == READ ? 'R' : 'W', tg->slice_start[rw],
		   tg->slice_end[rw], jiffies);
}

/* Determine if previously allocated or extended slice is complete or not */
static bool throtl_slice_used(struct throtl_grp *tg, bool rw)
{
	if (time_in_range(jiffies, tg->slice_start[rw], tg->slice_end[rw]))
		return false;

	return true;
}

/* Trim the used slices and adjust slice start accordingly */
static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
{
	unsigned long nr_slices, time_elapsed, io_trim;
	u64 bytes_trim, tmp;

	BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw]));

	/*
	 * If bps are unlimited (-1), then time slice don't get
	 * renewed. Don't try to trim the slice if slice is used. A new
	 * slice will start when appropriate.
	 */
	if (throtl_slice_used(tg, rw))
		return;

	/*
	 * A bio has been dispatched. Also adjust slice_end. It might happen
	 * that initially cgroup limit was very low resulting in high
	 * slice_end, but later limit was bumped up and bio was dispatched
	 * sooner, then we need to reduce slice_end. A high bogus slice_end
	 * is bad because it does not allow new slice to start.
	 */

	throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice);

	time_elapsed = jiffies - tg->slice_start[rw];

	nr_slices = time_elapsed / tg->td->throtl_slice;

	if (!nr_slices)
		return;
	tmp = tg_bps_limit(tg, rw) * tg->td->throtl_slice * nr_slices;
	do_div(tmp, HZ);
	bytes_trim = tmp;

	io_trim = (tg_iops_limit(tg, rw) * tg->td->throtl_slice * nr_slices) /
		HZ;

	if (!bytes_trim && !io_trim)
		return;

	if (tg->bytes_disp[rw] >= bytes_trim)
		tg->bytes_disp[rw] -= bytes_trim;
	else
		tg->bytes_disp[rw] = 0;

	if (tg->io_disp[rw] >= io_trim)
		tg->io_disp[rw] -= io_trim;
	else
		tg->io_disp[rw] = 0;

	tg->slice_start[rw] += nr_slices * tg->td->throtl_slice;

	throtl_log(&tg->service_queue,
		   "[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu",
		   rw == READ ? 'R' : 'W', nr_slices, bytes_trim, io_trim,
		   tg->slice_start[rw], tg->slice_end[rw], jiffies);
}

static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
				  u32 iops_limit, unsigned long *wait)
{
	bool rw = bio_data_dir(bio);
	unsigned int io_allowed;
	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
	u64 tmp;

	if (iops_limit == UINT_MAX) {
		if (wait)
			*wait = 0;
		return true;
	}

	jiffy_elapsed = jiffies - tg->slice_start[rw];

	/* Round up to the next throttle slice, wait time must be nonzero */
	jiffy_elapsed_rnd = roundup(jiffy_elapsed + 1, tg->td->throtl_slice);

	/*
	 * jiffy_elapsed_rnd should not be a big value as minimum iops can be
	 * 1 then at max jiffy elapsed should be equivalent of 1 second as we
	 * will allow dispatch after 1 second and after that slice should
	 * have been trimmed.
	 */

	tmp = (u64)iops_limit * jiffy_elapsed_rnd;
	do_div(tmp, HZ);

	if (tmp > UINT_MAX)
		io_allowed = UINT_MAX;
	else
		io_allowed = tmp;

	if (tg->io_disp[rw] + 1 <= io_allowed) {
		if (wait)
			*wait = 0;
		return true;
	}

	/* Calc approx time to dispatch */
	jiffy_wait = jiffy_elapsed_rnd - jiffy_elapsed;

	if (wait)
		*wait = jiffy_wait;
	return false;
}

static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
				 u64 bps_limit, unsigned long *wait)
{
	bool rw = bio_data_dir(bio);
	u64 bytes_allowed, extra_bytes, tmp;
	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
	unsigned int bio_size = throtl_bio_data_size(bio);

	if (bps_limit == U64_MAX) {
		if (wait)
			*wait = 0;
		return true;
	}

	jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw];

	/* Slice has just started. Consider one slice interval */
	if (!jiffy_elapsed)
		jiffy_elapsed_rnd = tg->td->throtl_slice;

	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);

	tmp = bps_limit * jiffy_elapsed_rnd;
	do_div(tmp, HZ);
	bytes_allowed = tmp;

	if (tg->bytes_disp[rw] + bio_size <= bytes_allowed) {
		if (wait)
			*wait = 0;
		return true;
	}

	/* Calc approx time to dispatch */
	extra_bytes = tg->bytes_disp[rw] + bio_size - bytes_allowed;
	jiffy_wait = div64_u64(extra_bytes * HZ, bps_limit);

	if (!jiffy_wait)
		jiffy_wait = 1;

	/*
	 * This wait time is without taking into consideration the rounding
	 * up we did. Add that time also.
	 */
	jiffy_wait = jiffy_wait + (jiffy_elapsed_rnd - jiffy_elapsed);
	if (wait)
		*wait = jiffy_wait;
	return false;
}

/*
 * Returns whether one can dispatch a bio or not. Also returns approx number
 * of jiffies to wait before this bio is with-in IO rate and can be dispatched
 */
static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
			    unsigned long *wait)
{
	bool rw = bio_data_dir(bio);
	unsigned long bps_wait = 0, iops_wait = 0, max_wait = 0;
	u64 bps_limit = tg_bps_limit(tg, rw);
	u32 iops_limit = tg_iops_limit(tg, rw);

	/*
 	 * Currently whole state machine of group depends on first bio
	 * queued in the group bio list. So one should not be calling
	 * this function with a different bio if there are other bios
	 * queued.
	 */
	BUG_ON(tg->service_queue.nr_queued[rw] &&
	       bio != throtl_peek_queued(&tg->service_queue.queued[rw]));

	/* If tg->bps = -1, then BW is unlimited */
	if (bps_limit == U64_MAX && iops_limit == UINT_MAX) {
		if (wait)
			*wait = 0;
		return true;
	}

	/*
	 * If previous slice expired, start a new one otherwise renew/extend
	 * existing slice to make sure it is at least throtl_slice interval
	 * long since now. New slice is started only for empty throttle group.
	 * If there is queued bio, that means there should be an active
	 * slice and it should be extended instead.
	 */
	if (throtl_slice_used(tg, rw) && !(tg->service_queue.nr_queued[rw]))
		throtl_start_new_slice(tg, rw);
	else {
		if (time_before(tg->slice_end[rw],
		    jiffies + tg->td->throtl_slice))
			throtl_extend_slice(tg, rw,
				jiffies + tg->td->throtl_slice);
	}

	if (iops_limit != UINT_MAX)
		tg->io_disp[rw] += atomic_xchg(&tg->io_split_cnt[rw], 0);

	if (tg_with_in_bps_limit(tg, bio, bps_limit, &bps_wait) &&
	    tg_with_in_iops_limit(tg, bio, iops_limit, &iops_wait)) {
		if (wait)
			*wait = 0;
		return true;
	}

	max_wait = max(bps_wait, iops_wait);

	if (wait)
		*wait = max_wait;

	if (time_before(tg->slice_end[rw], jiffies + max_wait))
		throtl_extend_slice(tg, rw, jiffies + max_wait);

	return false;
}

static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
{
	bool rw = bio_data_dir(bio);
	unsigned int bio_size = throtl_bio_data_size(bio);

	/* Charge the bio to the group */
	tg->bytes_disp[rw] += bio_size;
	tg->io_disp[rw]++;
	tg->last_bytes_disp[rw] += bio_size;
	tg->last_io_disp[rw]++;

	/*
	 * BIO_THROTTLED is used to prevent the same bio to be throttled
	 * more than once as a throttled bio will go through blk-throtl the
	 * second time when it eventually gets issued.  Set it when a bio
	 * is being charged to a tg.
	 */
	if (!bio_flagged(bio, BIO_THROTTLED))
		bio_set_flag(bio, BIO_THROTTLED);
}

/**
 * throtl_add_bio_tg - add a bio to the specified throtl_grp
 * @bio: bio to add
 * @qn: qnode to use
 * @tg: the target throtl_grp
 *
 * Add @bio to @tg's service_queue using @qn.  If @qn is not specified,
 * tg->qnode_on_self[] is used.
 */
static void throtl_add_bio_tg(struct bio *bio, struct throtl_qnode *qn,
			      struct throtl_grp *tg)
{
	struct throtl_service_queue *sq = &tg->service_queue;
	bool rw = bio_data_dir(bio);

	if (!qn)
		qn = &tg->qnode_on_self[rw];

	/*
	 * If @tg doesn't currently have any bios queued in the same
	 * direction, queueing @bio can change when @tg should be
	 * dispatched.  Mark that @tg was empty.  This is automatically
	 * cleared on the next tg_update_disptime().
	 */
	if (!sq->nr_queued[rw])
		tg->flags |= THROTL_TG_WAS_EMPTY;

	throtl_qnode_add_bio(bio, qn, &sq->queued[rw]);

	sq->nr_queued[rw]++;
	throtl_enqueue_tg(tg);
}

static void tg_update_disptime(struct throtl_grp *tg)
{
	struct throtl_service_queue *sq = &tg->service_queue;
	unsigned long read_wait = -1, write_wait = -1, min_wait = -1, disptime;
	struct bio *bio;

	bio = throtl_peek_queued(&sq->queued[READ]);
	if (bio)
		tg_may_dispatch(tg, bio, &read_wait);

	bio = throtl_peek_queued(&sq->queued[WRITE]);
	if (bio)
		tg_may_dispatch(tg, bio, &write_wait);

	min_wait = min(read_wait, write_wait);
	disptime = jiffies + min_wait;

	/* Update dispatch time */
	throtl_dequeue_tg(tg);
	tg->disptime = disptime;
	throtl_enqueue_tg(tg);

	/* see throtl_add_bio_tg() */
	tg->flags &= ~THROTL_TG_WAS_EMPTY;
}

static void start_parent_slice_with_credit(struct throtl_grp *child_tg,
					struct throtl_grp *parent_tg, bool rw)
{
	if (throtl_slice_used(parent_tg, rw)) {
		throtl_start_new_slice_with_credit(parent_tg, rw,
				child_tg->slice_start[rw]);
	}

}

static void tg_dispatch_one_bio(struct throtl_grp *tg, bool rw)
{
	struct throtl_service_queue *sq = &tg->service_queue;
	struct throtl_service_queue *parent_sq = sq->parent_sq;
	struct throtl_grp *parent_tg = sq_to_tg(parent_sq);
	struct throtl_grp *tg_to_put = NULL;
	struct bio *bio;

	/*
	 * @bio is being transferred from @tg to @parent_sq.  Popping a bio
	 * from @tg may put its reference and @parent_sq might end up
	 * getting released prematurely.  Remember the tg to put and put it
	 * after @bio is transferred to @parent_sq.
	 */
	bio = throtl_pop_queued(&sq->queued[rw], &tg_to_put);
	sq->nr_queued[rw]--;

	throtl_charge_bio(tg, bio);

	/*
	 * If our parent is another tg, we just need to transfer @bio to
	 * the parent using throtl_add_bio_tg().  If our parent is
	 * @td->service_queue, @bio is ready to be issued.  Put it on its
	 * bio_lists[] and decrease total number queued.  The caller is
	 * responsible for issuing these bios.
	 */
	if (parent_tg) {
		throtl_add_bio_tg(bio, &tg->qnode_on_parent[rw], parent_tg);
		start_parent_slice_with_credit(tg, parent_tg, rw);
	} else {
		throtl_qnode_add_bio(bio, &tg->qnode_on_parent[rw],
				     &parent_sq->queued[rw]);
		BUG_ON(tg->td->nr_queued[rw] <= 0);
		tg->td->nr_queued[rw]--;
	}

	throtl_trim_slice(tg, rw);

	if (tg_to_put)
		blkg_put(tg_to_blkg(tg_to_put));
}

static int throtl_dispatch_tg(struct throtl_grp *tg)
{
	struct throtl_service_queue *sq = &tg->service_queue;
	unsigned int nr_reads = 0, nr_writes = 0;
	unsigned int max_nr_reads = THROTL_GRP_QUANTUM * 3 / 4;
	unsigned int max_nr_writes = THROTL_GRP_QUANTUM - max_nr_reads;
	struct bio *bio;

	/* Try to dispatch 75% READS and 25% WRITES */

	while ((bio = throtl_peek_queued(&sq->queued[READ])) &&
	       tg_may_dispatch(tg, bio, NULL)) {

		tg_dispatch_one_bio(tg, bio_data_dir(bio));
		nr_reads++;

		if (nr_reads >= max_nr_reads)
			break;
	}

	while ((bio = throtl_peek_queued(&sq->queued[WRITE])) &&
	       tg_may_dispatch(tg, bio, NULL)) {

		tg_dispatch_one_bio(tg, bio_data_dir(bio));
		nr_writes++;

		if (nr_writes >= max_nr_writes)
			break;
	}

	return nr_reads + nr_writes;
}

static int throtl_select_dispatch(struct throtl_service_queue *parent_sq)
{
	unsigned int nr_disp = 0;

	while (1) {
		struct throtl_grp *tg;
		struct throtl_service_queue *sq;

		if (!parent_sq->nr_pending)
			break;

		tg = throtl_rb_first(parent_sq);
		if (!tg)
			break;

		if (time_before(jiffies, tg->disptime))
			break;

		throtl_dequeue_tg(tg);

		nr_disp += throtl_dispatch_tg(tg);

		sq = &tg->service_queue;
		if (sq->nr_queued[0] || sq->nr_queued[1])
			tg_update_disptime(tg);

		if (nr_disp >= THROTL_QUANTUM)
			break;
	}

	return nr_disp;
}

static bool throtl_can_upgrade(struct throtl_data *td,
	struct throtl_grp *this_tg);
/**
 * throtl_pending_timer_fn - timer function for service_queue->pending_timer
 * @t: the pending_timer member of the throtl_service_queue being serviced
 *
 * This timer is armed when a child throtl_grp with active bio's become
 * pending and queued on the service_queue's pending_tree and expires when
 * the first child throtl_grp should be dispatched.  This function
 * dispatches bio's from the children throtl_grps to the parent
 * service_queue.
 *
 * If the parent's parent is another throtl_grp, dispatching is propagated
 * by either arming its pending_timer or repeating dispatch directly.  If
 * the top-level service_tree is reached, throtl_data->dispatch_work is
 * kicked so that the ready bio's are issued.
 */
static void throtl_pending_timer_fn(struct timer_list *t)
{
	struct throtl_service_queue *sq = from_timer(sq, t, pending_timer);
	struct throtl_grp *tg = sq_to_tg(sq);
	struct throtl_data *td = sq_to_td(sq);
	struct request_queue *q = td->queue;
	struct throtl_service_queue *parent_sq;
	bool dispatched;
	int ret;

	spin_lock_irq(&q->queue_lock);
	if (throtl_can_upgrade(td, NULL))
		throtl_upgrade_state(td);

again:
	parent_sq = sq->parent_sq;
	dispatched = false;

	while (true) {
		throtl_log(sq, "dispatch nr_queued=%u read=%u write=%u",
			   sq->nr_queued[READ] + sq->nr_queued[WRITE],
			   sq->nr_queued[READ], sq->nr_queued[WRITE]);

		ret = throtl_select_dispatch(sq);
		if (ret) {
			throtl_log(sq, "bios disp=%u", ret);
			dispatched = true;
		}

		if (throtl_schedule_next_dispatch(sq, false))
			break;

		/* this dispatch windows is still open, relax and repeat */
		spin_unlock_irq(&q->queue_lock);
		cpu_relax();
		spin_lock_irq(&q->queue_lock);
	}

	if (!dispatched)
		goto out_unlock;

	if (parent_sq) {
		/* @parent_sq is another throl_grp, propagate dispatch */
		if (tg->flags & THROTL_TG_WAS_EMPTY) {
			tg_update_disptime(tg);
			if (!throtl_schedule_next_dispatch(parent_sq, false)) {
				/* window is already open, repeat dispatching */
				sq = parent_sq;
				tg = sq_to_tg(sq);
				goto again;
			}
		}
	} else {
		/* reached the top-level, queue issuing */
		queue_work(kthrotld_workqueue, &td->dispatch_work);
	}
out_unlock:
	spin_unlock_irq(&q->queue_lock);
}

/**
 * blk_throtl_dispatch_work_fn - work function for throtl_data->dispatch_work
 * @work: work item being executed
 *
 * This function is queued for execution when bios reach the bio_lists[]
 * of throtl_data->service_queue.  Those bios are ready and issued by this
 * function.
 */
static void blk_throtl_dispatch_work_fn(struct work_struct *work)
{
	struct throtl_data *td = container_of(work, struct throtl_data,
					      dispatch_work);
	struct throtl_service_queue *td_sq = &td->service_queue;
	struct request_queue *q = td->queue;
	struct bio_list bio_list_on_stack;
	struct bio *bio;
	struct blk_plug plug;
	int rw;

	bio_list_init(&bio_list_on_stack);

	spin_lock_irq(&q->queue_lock);
	for (rw = READ; rw <= WRITE; rw++)
		while ((bio = throtl_pop_queued(&td_sq->queued[rw], NULL)))
			bio_list_add(&bio_list_on_stack, bio);
	spin_unlock_irq(&q->queue_lock);

	if (!bio_list_empty(&bio_list_on_stack)) {
		blk_start_plug(&plug);
		while ((bio = bio_list_pop(&bio_list_on_stack)))
			submit_bio_noacct(bio);
		blk_finish_plug(&plug);
	}
}

static u64 tg_prfill_conf_u64(struct seq_file *sf, struct blkg_policy_data *pd,
			      int off)
{
	struct throtl_grp *tg = pd_to_tg(pd);
	u64 v = *(u64 *)((void *)tg + off);

	if (v == U64_MAX)
		return 0;
	return __blkg_prfill_u64(sf, pd, v);
}

static u64 tg_prfill_conf_uint(struct seq_file *sf, struct blkg_policy_data *pd,
			       int off)
{
	struct throtl_grp *tg = pd_to_tg(pd);
	unsigned int v = *(unsigned int *)((void *)tg + off);

	if (v == UINT_MAX)
		return 0;
	return __blkg_prfill_u64(sf, pd, v);
}

static int tg_print_conf_u64(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_conf_u64,
			  &blkcg_policy_throtl, seq_cft(sf)->private, false);
	return 0;
}

static int tg_print_conf_uint(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_conf_uint,
			  &blkcg_policy_throtl, seq_cft(sf)->private, false);
	return 0;
}

static void tg_conf_updated(struct throtl_grp *tg, bool global)
{
	struct throtl_service_queue *sq = &tg->service_queue;
	struct cgroup_subsys_state *pos_css;
	struct blkcg_gq *blkg;

	throtl_log(&tg->service_queue,
		   "limit change rbps=%llu wbps=%llu riops=%u wiops=%u",
		   tg_bps_limit(tg, READ), tg_bps_limit(tg, WRITE),
		   tg_iops_limit(tg, READ), tg_iops_limit(tg, WRITE));

	/*
	 * Update has_rules[] flags for the updated tg's subtree.  A tg is
	 * considered to have rules if either the tg itself or any of its
	 * ancestors has rules.  This identifies groups without any
	 * restrictions in the whole hierarchy and allows them to bypass
	 * blk-throttle.
	 */
	blkg_for_each_descendant_pre(blkg, pos_css,
			global ? tg->td->queue->root_blkg : tg_to_blkg(tg)) {
		struct throtl_grp *this_tg = blkg_to_tg(blkg);
		struct throtl_grp *parent_tg;

		tg_update_has_rules(this_tg);
		/* ignore root/second level */
		if (!cgroup_subsys_on_dfl(io_cgrp_subsys) || !blkg->parent ||
		    !blkg->parent->parent)
			continue;
		parent_tg = blkg_to_tg(blkg->parent);
		/*
		 * make sure all children has lower idle time threshold and
		 * higher latency target
		 */
		this_tg->idletime_threshold = min(this_tg->idletime_threshold,
				parent_tg->idletime_threshold);
		this_tg->latency_target = max(this_tg->latency_target,
				parent_tg->latency_target);
	}

	/*
	 * We're already holding queue_lock and know @tg is valid.  Let's
	 * apply the new config directly.
	 *
	 * Restart the slices for both READ and WRITES. It might happen
	 * that a group's limit are dropped suddenly and we don't want to
	 * account recently dispatched IO with new low rate.
	 */
	throtl_start_new_slice(tg, READ);
	throtl_start_new_slice(tg, WRITE);

	if (tg->flags & THROTL_TG_PENDING) {
		tg_update_disptime(tg);
		throtl_schedule_next_dispatch(sq->parent_sq, true);
	}
}

static ssize_t tg_set_conf(struct kernfs_open_file *of,
			   char *buf, size_t nbytes, loff_t off, bool is_u64)
{
	struct blkcg *blkcg = css_to_blkcg(of_css(of));
	struct blkg_conf_ctx ctx;
	struct throtl_grp *tg;
	int ret;
	u64 v;

	ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx);
	if (ret)
		return ret;

	ret = -EINVAL;
	if (sscanf(ctx.body, "%llu", &v) != 1)
		goto out_finish;
	if (!v)
		v = U64_MAX;

	tg = blkg_to_tg(ctx.blkg);

	if (is_u64)
		*(u64 *)((void *)tg + of_cft(of)->private) = v;
	else
		*(unsigned int *)((void *)tg + of_cft(of)->private) = v;

	tg_conf_updated(tg, false);
	ret = 0;
out_finish:
	blkg_conf_finish(&ctx);
	return ret ?: nbytes;
}

static ssize_t tg_set_conf_u64(struct kernfs_open_file *of,
			       char *buf, size_t nbytes, loff_t off)
{
	return tg_set_conf(of, buf, nbytes, off, true);
}

static ssize_t tg_set_conf_uint(struct kernfs_open_file *of,
				char *buf, size_t nbytes, loff_t off)
{
	return tg_set_conf(of, buf, nbytes, off, false);
}

static int tg_print_rwstat(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  blkg_prfill_rwstat, &blkcg_policy_throtl,
			  seq_cft(sf)->private, true);
	return 0;
}

static u64 tg_prfill_rwstat_recursive(struct seq_file *sf,
				      struct blkg_policy_data *pd, int off)
{
	struct blkg_rwstat_sample sum;

	blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_throtl, off,
				  &sum);
	return __blkg_prfill_rwstat(sf, pd, &sum);
}

static int tg_print_rwstat_recursive(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  tg_prfill_rwstat_recursive, &blkcg_policy_throtl,
			  seq_cft(sf)->private, true);
	return 0;
}

static struct cftype throtl_legacy_files[] = {
	{
		.name = "throttle.read_bps_device",
		.private = offsetof(struct throtl_grp, bps[READ][LIMIT_MAX]),
		.seq_show = tg_print_conf_u64,
		.write = tg_set_conf_u64,
	},
	{
		.name = "throttle.write_bps_device",
		.private = offsetof(struct throtl_grp, bps[WRITE][LIMIT_MAX]),
		.seq_show = tg_print_conf_u64,
		.write = tg_set_conf_u64,
	},
	{
		.name = "throttle.read_iops_device",
		.private = offsetof(struct throtl_grp, iops[READ][LIMIT_MAX]),
		.seq_show = tg_print_conf_uint,
		.write = tg_set_conf_uint,
	},
	{
		.name = "throttle.write_iops_device",
		.private = offsetof(struct throtl_grp, iops[WRITE][LIMIT_MAX]),
		.seq_show = tg_print_conf_uint,
		.write = tg_set_conf_uint,
	},
	{
		.name = "throttle.io_service_bytes",
		.private = offsetof(struct throtl_grp, stat_bytes),
		.seq_show = tg_print_rwstat,
	},
	{
		.name = "throttle.io_service_bytes_recursive",
		.private = offsetof(struct throtl_grp, stat_bytes),
		.seq_show = tg_print_rwstat_recursive,
	},
	{
		.name = "throttle.io_serviced",
		.private = offsetof(struct throtl_grp, stat_ios),
		.seq_show = tg_print_rwstat,
	},
	{
		.name = "throttle.io_serviced_recursive",
		.private = offsetof(struct throtl_grp, stat_ios),
		.seq_show = tg_print_rwstat_recursive,
	},
	{ }	/* terminate */
};

static u64 tg_prfill_limit(struct seq_file *sf, struct blkg_policy_data *pd,
			 int off)
{
	struct throtl_grp *tg = pd_to_tg(pd);
	const char *dname = blkg_dev_name(pd->blkg);
	char bufs[4][21] = { "max", "max", "max", "max" };
	u64 bps_dft;
	unsigned int iops_dft;
	char idle_time[26] = "";
	char latency_time[26] = "";

	if (!dname)
		return 0;

	if (off == LIMIT_LOW) {
		bps_dft = 0;
		iops_dft = 0;
	} else {
		bps_dft = U64_MAX;
		iops_dft = UINT_MAX;
	}

	if (tg->bps_conf[READ][off] == bps_dft &&
	    tg->bps_conf[WRITE][off] == bps_dft &&
	    tg->iops_conf[READ][off] == iops_dft &&
	    tg->iops_conf[WRITE][off] == iops_dft &&
	    (off != LIMIT_LOW ||
	     (tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD &&
	      tg->latency_target_conf == DFL_LATENCY_TARGET)))
		return 0;

	if (tg->bps_conf[READ][off] != U64_MAX)
		snprintf(bufs[0], sizeof(bufs[0]), "%llu",
			tg->bps_conf[READ][off]);
	if (tg->bps_conf[WRITE][off] != U64_MAX)
		snprintf(bufs[1], sizeof(bufs[1]), "%llu",
			tg->bps_conf[WRITE][off]);
	if (tg->iops_conf[READ][off] != UINT_MAX)
		snprintf(bufs[2], sizeof(bufs[2]), "%u",
			tg->iops_conf[READ][off]);
	if (tg->iops_conf[WRITE][off] != UINT_MAX)
		snprintf(bufs[3], sizeof(bufs[3]), "%u",
			tg->iops_conf[WRITE][off]);
	if (off == LIMIT_LOW) {
		if (tg->idletime_threshold_conf == ULONG_MAX)
			strcpy(idle_time, " idle=max");
		else
			snprintf(idle_time, sizeof(idle_time), " idle=%lu",
				tg->idletime_threshold_conf);

		if (tg->latency_target_conf == ULONG_MAX)
			strcpy(latency_time, " latency=max");
		else
			snprintf(latency_time, sizeof(latency_time),
				" latency=%lu", tg->latency_target_conf);
	}

	seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s%s%s\n",
		   dname, bufs[0], bufs[1], bufs[2], bufs[3], idle_time,
		   latency_time);
	return 0;
}

static int tg_print_limit(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_limit,
			  &blkcg_policy_throtl, seq_cft(sf)->private, false);
	return 0;
}

static ssize_t tg_set_limit(struct kernfs_open_file *of,
			  char *buf, size_t nbytes, loff_t off)
{
	struct blkcg *blkcg = css_to_blkcg(of_css(of));
	struct blkg_conf_ctx ctx;
	struct throtl_grp *tg;
	u64 v[4];
	unsigned long idle_time;
	unsigned long latency_time;
	int ret;
	int index = of_cft(of)->private;

	ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx);
	if (ret)
		return ret;

	tg = blkg_to_tg(ctx.blkg);

	v[0] = tg->bps_conf[READ][index];
	v[1] = tg->bps_conf[WRITE][index];
	v[2] = tg->iops_conf[READ][index];
	v[3] = tg->iops_conf[WRITE][index];

	idle_time = tg->idletime_threshold_conf;
	latency_time = tg->latency_target_conf;
	while (true) {
		char tok[27];	/* wiops=18446744073709551616 */
		char *p;
		u64 val = U64_MAX;
		int len;

		if (sscanf(ctx.body, "%26s%n", tok, &len) != 1)
			break;
		if (tok[0] == '\0')
			break;
		ctx.body += len;

		ret = -EINVAL;
		p = tok;
		strsep(&p, "=");
		if (!p || (sscanf(p, "%llu", &val) != 1 && strcmp(p, "max")))
			goto out_finish;

		ret = -ERANGE;
		if (!val)
			goto out_finish;

		ret = -EINVAL;
		if (!strcmp(tok, "rbps") && val > 1)
			v[0] = val;
		else if (!strcmp(tok, "wbps") && val > 1)
			v[1] = val;
		else if (!strcmp(tok, "riops") && val > 1)
			v[2] = min_t(u64, val, UINT_MAX);
		else if (!strcmp(tok, "wiops") && val > 1)
			v[3] = min_t(u64, val, UINT_MAX);
		else if (off == LIMIT_LOW && !strcmp(tok, "idle"))
			idle_time = val;
		else if (off == LIMIT_LOW && !strcmp(tok, "latency"))
			latency_time = val;
		else
			goto out_finish;
	}

	tg->bps_conf[READ][index] = v[0];
	tg->bps_conf[WRITE][index] = v[1];
	tg->iops_conf[READ][index] = v[2];
	tg->iops_conf[WRITE][index] = v[3];

	if (index == LIMIT_MAX) {
		tg->bps[READ][index] = v[0];
		tg->bps[WRITE][index] = v[1];
		tg->iops[READ][index] = v[2];
		tg->iops[WRITE][index] = v[3];
	}
	tg->bps[READ][LIMIT_LOW] = min(tg->bps_conf[READ][LIMIT_LOW],
		tg->bps_conf[READ][LIMIT_MAX]);
	tg->bps[WRITE][LIMIT_LOW] = min(tg->bps_conf[WRITE][LIMIT_LOW],
		tg->bps_conf[WRITE][LIMIT_MAX]);
	tg->iops[READ][LIMIT_LOW] = min(tg->iops_conf[READ][LIMIT_LOW],
		tg->iops_conf[READ][LIMIT_MAX]);
	tg->iops[WRITE][LIMIT_LOW] = min(tg->iops_conf[WRITE][LIMIT_LOW],
		tg->iops_conf[WRITE][LIMIT_MAX]);
	tg->idletime_threshold_conf = idle_time;
	tg->latency_target_conf = latency_time;

	/* force user to configure all settings for low limit  */
	if (!(tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW] ||
	      tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) ||
	    tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD ||
	    tg->latency_target_conf == DFL_LATENCY_TARGET) {
		tg->bps[READ][LIMIT_LOW] = 0;
		tg->bps[WRITE][LIMIT_LOW] = 0;
		tg->iops[READ][LIMIT_LOW] = 0;
		tg->iops[WRITE][LIMIT_LOW] = 0;
		tg->idletime_threshold = DFL_IDLE_THRESHOLD;
		tg->latency_target = DFL_LATENCY_TARGET;
	} else if (index == LIMIT_LOW) {
		tg->idletime_threshold = tg->idletime_threshold_conf;
		tg->latency_target = tg->latency_target_conf;
	}

	blk_throtl_update_limit_valid(tg->td);
	if (tg->td->limit_valid[LIMIT_LOW]) {
		if (index == LIMIT_LOW)
			tg->td->limit_index = LIMIT_LOW;
	} else
		tg->td->limit_index = LIMIT_MAX;
	tg_conf_updated(tg, index == LIMIT_LOW &&
		tg->td->limit_valid[LIMIT_LOW]);
	ret = 0;
out_finish:
	blkg_conf_finish(&ctx);
	return ret ?: nbytes;
}

static struct cftype throtl_files[] = {
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
	{
		.name = "low",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = tg_print_limit,
		.write = tg_set_limit,
		.private = LIMIT_LOW,
	},
#endif
	{
		.name = "max",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = tg_print_limit,
		.write = tg_set_limit,
		.private = LIMIT_MAX,
	},
	{ }	/* terminate */
};

static void throtl_shutdown_wq(struct request_queue *q)
{
	struct throtl_data *td = q->td;

	cancel_work_sync(&td->dispatch_work);
}

struct blkcg_policy blkcg_policy_throtl = {
	.dfl_cftypes		= throtl_files,
	.legacy_cftypes		= throtl_legacy_files,

	.pd_alloc_fn		= throtl_pd_alloc,
	.pd_init_fn		= throtl_pd_init,
	.pd_online_fn		= throtl_pd_online,
	.pd_offline_fn		= throtl_pd_offline,
	.pd_free_fn		= throtl_pd_free,
};

static unsigned long __tg_last_low_overflow_time(struct throtl_grp *tg)
{
	unsigned long rtime = jiffies, wtime = jiffies;

	if (tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW])
		rtime = tg->last_low_overflow_time[READ];
	if (tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW])
		wtime = tg->last_low_overflow_time[WRITE];
	return min(rtime, wtime);
}

/* tg should not be an intermediate node */
static unsigned long tg_last_low_overflow_time(struct throtl_grp *tg)
{
	struct throtl_service_queue *parent_sq;
	struct throtl_grp *parent = tg;
	unsigned long ret = __tg_last_low_overflow_time(tg);

	while (true) {
		parent_sq = parent->service_queue.parent_sq;
		parent = sq_to_tg(parent_sq);
		if (!parent)
			break;

		/*
		 * The parent doesn't have low limit, it always reaches low
		 * limit. Its overflow time is useless for children
		 */
		if (!parent->bps[READ][LIMIT_LOW] &&
		    !parent->iops[READ][LIMIT_LOW] &&
		    !parent->bps[WRITE][LIMIT_LOW] &&
		    !parent->iops[WRITE][LIMIT_LOW])
			continue;
		if (time_after(__tg_last_low_overflow_time(parent), ret))
			ret = __tg_last_low_overflow_time(parent);
	}
	return ret;
}

static bool throtl_tg_is_idle(struct throtl_grp *tg)
{
	/*
	 * cgroup is idle if:
	 * - single idle is too long, longer than a fixed value (in case user
	 *   configure a too big threshold) or 4 times of idletime threshold
	 * - average think time is more than threshold
	 * - IO latency is largely below threshold
	 */
	unsigned long time;
	bool ret;

	time = min_t(unsigned long, MAX_IDLE_TIME, 4 * tg->idletime_threshold);
	ret = tg->latency_target == DFL_LATENCY_TARGET ||
	      tg->idletime_threshold == DFL_IDLE_THRESHOLD ||
	      (ktime_get_ns() >> 10) - tg->last_finish_time > time ||
	      tg->avg_idletime > tg->idletime_threshold ||
	      (tg->latency_target && tg->bio_cnt &&
		tg->bad_bio_cnt * 5 < tg->bio_cnt);
	throtl_log(&tg->service_queue,
		"avg_idle=%ld, idle_threshold=%ld, bad_bio=%d, total_bio=%d, is_idle=%d, scale=%d",
		tg->avg_idletime, tg->idletime_threshold, tg->bad_bio_cnt,
		tg->bio_cnt, ret, tg->td->scale);
	return ret;
}

static bool throtl_tg_can_upgrade(struct throtl_grp *tg)
{
	struct throtl_service_queue *sq = &tg->service_queue;
	bool read_limit, write_limit;

	/*
	 * if cgroup reaches low limit (if low limit is 0, the cgroup always
	 * reaches), it's ok to upgrade to next limit
	 */
	read_limit = tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW];
	write_limit = tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW];
	if (!read_limit && !write_limit)
		return true;
	if (read_limit && sq->nr_queued[READ] &&
	    (!write_limit || sq->nr_queued[WRITE]))
		return true;
	if (write_limit && sq->nr_queued[WRITE] &&
	    (!read_limit || sq->nr_queued[READ]))
		return true;

	if (time_after_eq(jiffies,
		tg_last_low_overflow_time(tg) + tg->td->throtl_slice) &&
	    throtl_tg_is_idle(tg))
		return true;
	return false;
}

static bool throtl_hierarchy_can_upgrade(struct throtl_grp *tg)
{
	while (true) {
		if (throtl_tg_can_upgrade(tg))
			return true;
		tg = sq_to_tg(tg->service_queue.parent_sq);
		if (!tg || !tg_to_blkg(tg)->parent)
			return false;
	}
	return false;
}

static bool throtl_can_upgrade(struct throtl_data *td,
	struct throtl_grp *this_tg)
{
	struct cgroup_subsys_state *pos_css;
	struct blkcg_gq *blkg;

	if (td->limit_index != LIMIT_LOW)
		return false;

	if (time_before(jiffies, td->low_downgrade_time + td->throtl_slice))
		return false;

	rcu_read_lock();
	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
		struct throtl_grp *tg = blkg_to_tg(blkg);

		if (tg == this_tg)
			continue;
		if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children))
			continue;
		if (!throtl_hierarchy_can_upgrade(tg)) {
			rcu_read_unlock();
			return false;
		}
	}
	rcu_read_unlock();
	return true;
}

static void throtl_upgrade_check(struct throtl_grp *tg)
{
	unsigned long now = jiffies;

	if (tg->td->limit_index != LIMIT_LOW)
		return;

	if (time_after(tg->last_check_time + tg->td->throtl_slice, now))
		return;

	tg->last_check_time = now;

	if (!time_after_eq(now,
	     __tg_last_low_overflow_time(tg) + tg->td->throtl_slice))
		return;

	if (throtl_can_upgrade(tg->td, NULL))
		throtl_upgrade_state(tg->td);
}

static void throtl_upgrade_state(struct throtl_data *td)
{
	struct cgroup_subsys_state *pos_css;
	struct blkcg_gq *blkg;

	throtl_log(&td->service_queue, "upgrade to max");
	td->limit_index = LIMIT_MAX;
	td->low_upgrade_time = jiffies;
	td->scale = 0;
	rcu_read_lock();
	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
		struct throtl_grp *tg = blkg_to_tg(blkg);
		struct throtl_service_queue *sq = &tg->service_queue;

		tg->disptime = jiffies - 1;
		throtl_select_dispatch(sq);
		throtl_schedule_next_dispatch(sq, true);
	}
	rcu_read_unlock();
	throtl_select_dispatch(&td->service_queue);
	throtl_schedule_next_dispatch(&td->service_queue, true);
	queue_work(kthrotld_workqueue, &td->dispatch_work);
}

static void throtl_downgrade_state(struct throtl_data *td)
{
	td->scale /= 2;

	throtl_log(&td->service_queue, "downgrade, scale %d", td->scale);
	if (td->scale) {
		td->low_upgrade_time = jiffies - td->scale * td->throtl_slice;
		return;
	}

	td->limit_index = LIMIT_LOW;
	td->low_downgrade_time = jiffies;
}

static bool throtl_tg_can_downgrade(struct throtl_grp *tg)
{
	struct throtl_data *td = tg->td;
	unsigned long now = jiffies;

	/*
	 * If cgroup is below low limit, consider downgrade and throttle other
	 * cgroups
	 */
	if (time_after_eq(now, td->low_upgrade_time + td->throtl_slice) &&
	    time_after_eq(now, tg_last_low_overflow_time(tg) +
					td->throtl_slice) &&
	    (!throtl_tg_is_idle(tg) ||
	     !list_empty(&tg_to_blkg(tg)->blkcg->css.children)))
		return true;
	return false;
}

static bool throtl_hierarchy_can_downgrade(struct throtl_grp *tg)
{
	while (true) {
		if (!throtl_tg_can_downgrade(tg))
			return false;
		tg = sq_to_tg(tg->service_queue.parent_sq);
		if (!tg || !tg_to_blkg(tg)->parent)
			break;
	}
	return true;
}

static void throtl_downgrade_check(struct throtl_grp *tg)
{
	uint64_t bps;
	unsigned int iops;
	unsigned long elapsed_time;
	unsigned long now = jiffies;

	if (tg->td->limit_index != LIMIT_MAX ||
	    !tg->td->limit_valid[LIMIT_LOW])
		return;
	if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children))
		return;
	if (time_after(tg->last_check_time + tg->td->throtl_slice, now))
		return;

	elapsed_time = now - tg->last_check_time;
	tg->last_check_time = now;

	if (time_before(now, tg_last_low_overflow_time(tg) +
			tg->td->throtl_slice))
		return;

	if (tg->bps[READ][LIMIT_LOW]) {
		bps = tg->last_bytes_disp[READ] * HZ;
		do_div(bps, elapsed_time);
		if (bps >= tg->bps[READ][LIMIT_LOW])
			tg->last_low_overflow_time[READ] = now;
	}

	if (tg->bps[WRITE][LIMIT_LOW]) {
		bps = tg->last_bytes_disp[WRITE] * HZ;
		do_div(bps, elapsed_time);
		if (bps >= tg->bps[WRITE][LIMIT_LOW])
			tg->last_low_overflow_time[WRITE] = now;
	}

	if (tg->iops[READ][LIMIT_LOW]) {
		tg->last_io_disp[READ] += atomic_xchg(&tg->last_io_split_cnt[READ], 0);
		iops = tg->last_io_disp[READ] * HZ / elapsed_time;
		if (iops >= tg->iops[READ][LIMIT_LOW])
			tg->last_low_overflow_time[READ] = now;
	}

	if (tg->iops[WRITE][LIMIT_LOW]) {
		tg->last_io_disp[WRITE] += atomic_xchg(&tg->last_io_split_cnt[WRITE], 0);
		iops = tg->last_io_disp[WRITE] * HZ / elapsed_time;
		if (iops >= tg->iops[WRITE][LIMIT_LOW])
			tg->last_low_overflow_time[WRITE] = now;
	}

	/*
	 * If cgroup is below low limit, consider downgrade and throttle other
	 * cgroups
	 */
	if (throtl_hierarchy_can_downgrade(tg))
		throtl_downgrade_state(tg->td);

	tg->last_bytes_disp[READ] = 0;
	tg->last_bytes_disp[WRITE] = 0;
	tg->last_io_disp[READ] = 0;
	tg->last_io_disp[WRITE] = 0;
}

static void blk_throtl_update_idletime(struct throtl_grp *tg)
{
	unsigned long now;
	unsigned long last_finish_time = tg->last_finish_time;

	if (last_finish_time == 0)
		return;

	now = ktime_get_ns() >> 10;
	if (now <= last_finish_time ||
	    last_finish_time == tg->checked_last_finish_time)
		return;

	tg->avg_idletime = (tg->avg_idletime * 7 + now - last_finish_time) >> 3;
	tg->checked_last_finish_time = last_finish_time;
}

#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
static void throtl_update_latency_buckets(struct throtl_data *td)
{
	struct avg_latency_bucket avg_latency[2][LATENCY_BUCKET_SIZE];
	int i, cpu, rw;
	unsigned long last_latency[2] = { 0 };
	unsigned long latency[2];

	if (!blk_queue_nonrot(td->queue) || !td->limit_valid[LIMIT_LOW])
		return;
	if (time_before(jiffies, td->last_calculate_time + HZ))
		return;
	td->last_calculate_time = jiffies;

	memset(avg_latency, 0, sizeof(avg_latency));
	for (rw = READ; rw <= WRITE; rw++) {
		for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
			struct latency_bucket *tmp = &td->tmp_buckets[rw][i];

			for_each_possible_cpu(cpu) {
				struct latency_bucket *bucket;

				/* this isn't race free, but ok in practice */
				bucket = per_cpu_ptr(td->latency_buckets[rw],
					cpu);
				tmp->total_latency += bucket[i].total_latency;
				tmp->samples += bucket[i].samples;
				bucket[i].total_latency = 0;
				bucket[i].samples = 0;
			}

			if (tmp->samples >= 32) {
				int samples = tmp->samples;

				latency[rw] = tmp->total_latency;

				tmp->total_latency = 0;
				tmp->samples = 0;
				latency[rw] /= samples;
				if (latency[rw] == 0)
					continue;
				avg_latency[rw][i].latency = latency[rw];
			}
		}
	}

	for (rw = READ; rw <= WRITE; rw++) {
		for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
			if (!avg_latency[rw][i].latency) {
				if (td->avg_buckets[rw][i].latency < last_latency[rw])
					td->avg_buckets[rw][i].latency =
						last_latency[rw];
				continue;
			}

			if (!td->avg_buckets[rw][i].valid)
				latency[rw] = avg_latency[rw][i].latency;
			else
				latency[rw] = (td->avg_buckets[rw][i].latency * 7 +
					avg_latency[rw][i].latency) >> 3;

			td->avg_buckets[rw][i].latency = max(latency[rw],
				last_latency[rw]);
			td->avg_buckets[rw][i].valid = true;
			last_latency[rw] = td->avg_buckets[rw][i].latency;
		}
	}

	for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
		throtl_log(&td->service_queue,
			"Latency bucket %d: read latency=%ld, read valid=%d, "
			"write latency=%ld, write valid=%d", i,
			td->avg_buckets[READ][i].latency,
			td->avg_buckets[READ][i].valid,
			td->avg_buckets[WRITE][i].latency,
			td->avg_buckets[WRITE][i].valid);
}
#else
static inline void throtl_update_latency_buckets(struct throtl_data *td)
{
}
#endif

void blk_throtl_charge_bio_split(struct bio *bio)
{
	struct blkcg_gq *blkg = bio->bi_blkg;
	struct throtl_grp *parent = blkg_to_tg(blkg);
	struct throtl_service_queue *parent_sq;
	bool rw = bio_data_dir(bio);

	do {
		if (!parent->has_rules[rw])
			break;

		atomic_inc(&parent->io_split_cnt[rw]);
		atomic_inc(&parent->last_io_split_cnt[rw]);

		parent_sq = parent->service_queue.parent_sq;
		parent = sq_to_tg(parent_sq);
	} while (parent);
}

bool __blk_throtl_bio(struct bio *bio)
{
	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
	struct blkcg_gq *blkg = bio->bi_blkg;
	struct throtl_qnode *qn = NULL;
	struct throtl_grp *tg = blkg_to_tg(blkg);
	struct throtl_service_queue *sq;
	bool rw = bio_data_dir(bio);
	bool throttled = false;
	struct throtl_data *td = tg->td;

	rcu_read_lock();

	if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) {
		blkg_rwstat_add(&tg->stat_bytes, bio->bi_opf,
				bio->bi_iter.bi_size);
		blkg_rwstat_add(&tg->stat_ios, bio->bi_opf, 1);
	}

	spin_lock_irq(&q->queue_lock);

	throtl_update_latency_buckets(td);

	blk_throtl_update_idletime(tg);

	sq = &tg->service_queue;

again:
	while (true) {
		if (tg->last_low_overflow_time[rw] == 0)
			tg->last_low_overflow_time[rw] = jiffies;
		throtl_downgrade_check(tg);
		throtl_upgrade_check(tg);
		/* throtl is FIFO - if bios are already queued, should queue */
		if (sq->nr_queued[rw])
			break;

		/* if above limits, break to queue */
		if (!tg_may_dispatch(tg, bio, NULL)) {
			tg->last_low_overflow_time[rw] = jiffies;
			if (throtl_can_upgrade(td, tg)) {
				throtl_upgrade_state(td);
				goto again;
			}
			break;
		}

		/* within limits, let's charge and dispatch directly */
		throtl_charge_bio(tg, bio);

		/*
		 * We need to trim slice even when bios are not being queued
		 * otherwise it might happen that a bio is not queued for
		 * a long time and slice keeps on extending and trim is not
		 * called for a long time. Now if limits are reduced suddenly
		 * we take into account all the IO dispatched so far at new
		 * low rate and * newly queued IO gets a really long dispatch
		 * time.
		 *
		 * So keep on trimming slice even if bio is not queued.
		 */
		throtl_trim_slice(tg, rw);

		/*
		 * @bio passed through this layer without being throttled.
		 * Climb up the ladder.  If we're already at the top, it
		 * can be executed directly.
		 */
		qn = &tg->qnode_on_parent[rw];
		sq = sq->parent_sq;
		tg = sq_to_tg(sq);
		if (!tg)
			goto out_unlock;
	}

	/* out-of-limit, queue to @tg */
	throtl_log(sq, "[%c] bio. bdisp=%llu sz=%u bps=%llu iodisp=%u iops=%u queued=%d/%d",
		   rw == READ ? 'R' : 'W',
		   tg->bytes_disp[rw], bio->bi_iter.bi_size,
		   tg_bps_limit(tg, rw),
		   tg->io_disp[rw], tg_iops_limit(tg, rw),
		   sq->nr_queued[READ], sq->nr_queued[WRITE]);

	tg->last_low_overflow_time[rw] = jiffies;

	td->nr_queued[rw]++;
	throtl_add_bio_tg(bio, qn, tg);
	throttled = true;

	/*
	 * Update @tg's dispatch time and force schedule dispatch if @tg
	 * was empty before @bio.  The forced scheduling isn't likely to
	 * cause undue delay as @bio is likely to be dispatched directly if
	 * its @tg's disptime is not in the future.
	 */
	if (tg->flags & THROTL_TG_WAS_EMPTY) {
		tg_update_disptime(tg);
		throtl_schedule_next_dispatch(tg->service_queue.parent_sq, true);
	}

out_unlock:
	spin_unlock_irq(&q->queue_lock);
	bio_set_flag(bio, BIO_THROTTLED);

#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
	if (throttled || !td->track_bio_latency)
		bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY;
#endif
	rcu_read_unlock();
	return throttled;
}

#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
static void throtl_track_latency(struct throtl_data *td, sector_t size,
	int op, unsigned long time)
{
	struct latency_bucket *latency;
	int index;

	if (!td || td->limit_index != LIMIT_LOW ||
	    !(op == REQ_OP_READ || op == REQ_OP_WRITE) ||
	    !blk_queue_nonrot(td->queue))
		return;

	index = request_bucket_index(size);

	latency = get_cpu_ptr(td->latency_buckets[op]);
	latency[index].total_latency += time;
	latency[index].samples++;
	put_cpu_ptr(td->latency_buckets[op]);
}

void blk_throtl_stat_add(struct request *rq, u64 time_ns)
{
	struct request_queue *q = rq->q;
	struct throtl_data *td = q->td;

	throtl_track_latency(td, blk_rq_stats_sectors(rq), req_op(rq),
			     time_ns >> 10);
}

void blk_throtl_bio_endio(struct bio *bio)
{
	struct blkcg_gq *blkg;
	struct throtl_grp *tg;
	u64 finish_time_ns;
	unsigned long finish_time;
	unsigned long start_time;
	unsigned long lat;
	int rw = bio_data_dir(bio);

	blkg = bio->bi_blkg;
	if (!blkg)
		return;
	tg = blkg_to_tg(blkg);
	if (!tg->td->limit_valid[LIMIT_LOW])
		return;

	finish_time_ns = ktime_get_ns();
	tg->last_finish_time = finish_time_ns >> 10;

	start_time = bio_issue_time(&bio->bi_issue) >> 10;
	finish_time = __bio_issue_time(finish_time_ns) >> 10;
	if (!start_time || finish_time <= start_time)
		return;

	lat = finish_time - start_time;
	/* this is only for bio based driver */
	if (!(bio->bi_issue.value & BIO_ISSUE_THROTL_SKIP_LATENCY))
		throtl_track_latency(tg->td, bio_issue_size(&bio->bi_issue),
				     bio_op(bio), lat);

	if (tg->latency_target && lat >= tg->td->filtered_latency) {
		int bucket;
		unsigned int threshold;

		bucket = request_bucket_index(bio_issue_size(&bio->bi_issue));
		threshold = tg->td->avg_buckets[rw][bucket].latency +
			tg->latency_target;
		if (lat > threshold)
			tg->bad_bio_cnt++;
		/*
		 * Not race free, could get wrong count, which means cgroups
		 * will be throttled
		 */
		tg->bio_cnt++;
	}

	if (time_after(jiffies, tg->bio_cnt_reset_time) || tg->bio_cnt > 1024) {
		tg->bio_cnt_reset_time = tg->td->throtl_slice + jiffies;
		tg->bio_cnt /= 2;
		tg->bad_bio_cnt /= 2;
	}
}
#endif

int blk_throtl_init(struct request_queue *q)
{
	struct throtl_data *td;
	int ret;

	td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
	if (!td)
		return -ENOMEM;
	td->latency_buckets[READ] = __alloc_percpu(sizeof(struct latency_bucket) *
		LATENCY_BUCKET_SIZE, __alignof__(u64));
	if (!td->latency_buckets[READ]) {
		kfree(td);
		return -ENOMEM;
	}
	td->latency_buckets[WRITE] = __alloc_percpu(sizeof(struct latency_bucket) *
		LATENCY_BUCKET_SIZE, __alignof__(u64));
	if (!td->latency_buckets[WRITE]) {
		free_percpu(td->latency_buckets[READ]);
		kfree(td);
		return -ENOMEM;
	}

	INIT_WORK(&td->dispatch_work, blk_throtl_dispatch_work_fn);
	throtl_service_queue_init(&td->service_queue);

	q->td = td;
	td->queue = q;

	td->limit_valid[LIMIT_MAX] = true;
	td->limit_index = LIMIT_MAX;
	td->low_upgrade_time = jiffies;
	td->low_downgrade_time = jiffies;

	/* activate policy */
	ret = blkcg_activate_policy(q, &blkcg_policy_throtl);
	if (ret) {
		free_percpu(td->latency_buckets[READ]);
		free_percpu(td->latency_buckets[WRITE]);
		kfree(td);
	}
	return ret;
}

void blk_throtl_exit(struct request_queue *q)
{
	BUG_ON(!q->td);
	del_timer_sync(&q->td->service_queue.pending_timer);
	throtl_shutdown_wq(q);
	blkcg_deactivate_policy(q, &blkcg_policy_throtl);
	free_percpu(q->td->latency_buckets[READ]);
	free_percpu(q->td->latency_buckets[WRITE]);
	kfree(q->td);
}

void blk_throtl_register_queue(struct request_queue *q)
{
	struct throtl_data *td;
	int i;

	td = q->td;
	BUG_ON(!td);

	if (blk_queue_nonrot(q)) {
		td->throtl_slice = DFL_THROTL_SLICE_SSD;
		td->filtered_latency = LATENCY_FILTERED_SSD;
	} else {
		td->throtl_slice = DFL_THROTL_SLICE_HD;
		td->filtered_latency = LATENCY_FILTERED_HD;
		for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
			td->avg_buckets[READ][i].latency = DFL_HD_BASELINE_LATENCY;
			td->avg_buckets[WRITE][i].latency = DFL_HD_BASELINE_LATENCY;
		}
	}
#ifndef CONFIG_BLK_DEV_THROTTLING_LOW
	/* if no low limit, use previous default */
	td->throtl_slice = DFL_THROTL_SLICE_HD;
#endif

	td->track_bio_latency = !queue_is_mq(q);
	if (!td->track_bio_latency)
		blk_stat_enable_accounting(q);
}

#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page)
{
	if (!q->td)
		return -EINVAL;
	return sprintf(page, "%u\n", jiffies_to_msecs(q->td->throtl_slice));
}

ssize_t blk_throtl_sample_time_store(struct request_queue *q,
	const char *page, size_t count)
{
	unsigned long v;
	unsigned long t;

	if (!q->td)
		return -EINVAL;
	if (kstrtoul(page, 10, &v))
		return -EINVAL;
	t = msecs_to_jiffies(v);
	if (t == 0 || t > MAX_THROTL_SLICE)
		return -EINVAL;
	q->td->throtl_slice = t;
	return count;
}
#endif

static int __init throtl_init(void)
{
	kthrotld_workqueue = alloc_workqueue("kthrotld", WQ_MEM_RECLAIM, 0);
	if (!kthrotld_workqueue)
		panic("Failed to create kthrotld\n");

	return blkcg_policy_register(&blkcg_policy_throtl);
}

module_init(throtl_init);