summaryrefslogtreecommitdiffstats
path: root/block/bfq-iosched.c
blob: 1edac72ab51ddd1edb853c3e836670cc307a8d47 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
/*
 * Budget Fair Queueing (BFQ) I/O scheduler.
 *
 * Based on ideas and code from CFQ:
 * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
 *
 * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
 *		      Paolo Valente <paolo.valente@unimore.it>
 *
 * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
 *                    Arianna Avanzini <avanzini@google.com>
 *
 * Copyright (C) 2017 Paolo Valente <paolo.valente@linaro.org>
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License as
 *  published by the Free Software Foundation; either version 2 of the
 *  License, or (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 *  General Public License for more details.
 *
 * BFQ is a proportional-share I/O scheduler, with some extra
 * low-latency capabilities. BFQ also supports full hierarchical
 * scheduling through cgroups. Next paragraphs provide an introduction
 * on BFQ inner workings. Details on BFQ benefits, usage and
 * limitations can be found in Documentation/block/bfq-iosched.txt.
 *
 * BFQ is a proportional-share storage-I/O scheduling algorithm based
 * on the slice-by-slice service scheme of CFQ. But BFQ assigns
 * budgets, measured in number of sectors, to processes instead of
 * time slices. The device is not granted to the in-service process
 * for a given time slice, but until it has exhausted its assigned
 * budget. This change from the time to the service domain enables BFQ
 * to distribute the device throughput among processes as desired,
 * without any distortion due to throughput fluctuations, or to device
 * internal queueing. BFQ uses an ad hoc internal scheduler, called
 * B-WF2Q+, to schedule processes according to their budgets. More
 * precisely, BFQ schedules queues associated with processes. Each
 * process/queue is assigned a user-configurable weight, and B-WF2Q+
 * guarantees that each queue receives a fraction of the throughput
 * proportional to its weight. Thanks to the accurate policy of
 * B-WF2Q+, BFQ can afford to assign high budgets to I/O-bound
 * processes issuing sequential requests (to boost the throughput),
 * and yet guarantee a low latency to interactive and soft real-time
 * applications.
 *
 * In particular, to provide these low-latency guarantees, BFQ
 * explicitly privileges the I/O of two classes of time-sensitive
 * applications: interactive and soft real-time. This feature enables
 * BFQ to provide applications in these classes with a very low
 * latency. Finally, BFQ also features additional heuristics for
 * preserving both a low latency and a high throughput on NCQ-capable,
 * rotational or flash-based devices, and to get the job done quickly
 * for applications consisting in many I/O-bound processes.
 *
 * BFQ is described in [1], where also a reference to the initial, more
 * theoretical paper on BFQ can be found. The interested reader can find
 * in the latter paper full details on the main algorithm, as well as
 * formulas of the guarantees and formal proofs of all the properties.
 * With respect to the version of BFQ presented in these papers, this
 * implementation adds a few more heuristics, such as the one that
 * guarantees a low latency to soft real-time applications, and a
 * hierarchical extension based on H-WF2Q+.
 *
 * B-WF2Q+ is based on WF2Q+, which is described in [2], together with
 * H-WF2Q+, while the augmented tree used here to implement B-WF2Q+
 * with O(log N) complexity derives from the one introduced with EEVDF
 * in [3].
 *
 * [1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
 *     Scheduler", Proceedings of the First Workshop on Mobile System
 *     Technologies (MST-2015), May 2015.
 *     http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
 *
 * [2] Jon C.R. Bennett and H. Zhang, "Hierarchical Packet Fair Queueing
 *     Algorithms", IEEE/ACM Transactions on Networking, 5(5):675-689,
 *     Oct 1997.
 *
 * http://www.cs.cmu.edu/~hzhang/papers/TON-97-Oct.ps.gz
 *
 * [3] I. Stoica and H. Abdel-Wahab, "Earliest Eligible Virtual Deadline
 *     First: A Flexible and Accurate Mechanism for Proportional Share
 *     Resource Allocation", technical report.
 *
 * http://www.cs.berkeley.edu/~istoica/papers/eevdf-tr-95.pdf
 */
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/cgroup.h>
#include <linux/elevator.h>
#include <linux/ktime.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
#include <linux/sbitmap.h>
#include <linux/delay.h>

#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-tag.h"
#include "blk-mq-sched.h"
#include <linux/blktrace_api.h>
#include <linux/hrtimer.h>
#include <linux/blk-cgroup.h>

#define BFQ_IOPRIO_CLASSES	3
#define BFQ_CL_IDLE_TIMEOUT	(HZ/5)

#define BFQ_MIN_WEIGHT			1
#define BFQ_MAX_WEIGHT			1000
#define BFQ_WEIGHT_CONVERSION_COEFF	10

#define BFQ_DEFAULT_QUEUE_IOPRIO	4

#define BFQ_WEIGHT_LEGACY_DFL	100
#define BFQ_DEFAULT_GRP_IOPRIO	0
#define BFQ_DEFAULT_GRP_CLASS	IOPRIO_CLASS_BE

struct bfq_entity;

/**
 * struct bfq_service_tree - per ioprio_class service tree.
 *
 * Each service tree represents a B-WF2Q+ scheduler on its own.  Each
 * ioprio_class has its own independent scheduler, and so its own
 * bfq_service_tree.  All the fields are protected by the queue lock
 * of the containing bfqd.
 */
struct bfq_service_tree {
	/* tree for active entities (i.e., those backlogged) */
	struct rb_root active;
	/* tree for idle entities (i.e., not backlogged, with V <= F_i)*/
	struct rb_root idle;

	/* idle entity with minimum F_i */
	struct bfq_entity *first_idle;
	/* idle entity with maximum F_i */
	struct bfq_entity *last_idle;

	/* scheduler virtual time */
	u64 vtime;
	/* scheduler weight sum; active and idle entities contribute to it */
	unsigned long wsum;
};

/**
 * struct bfq_sched_data - multi-class scheduler.
 *
 * bfq_sched_data is the basic scheduler queue.  It supports three
 * ioprio_classes, and can be used either as a toplevel queue or as an
 * intermediate queue on a hierarchical setup.  @next_in_service
 * points to the active entity of the sched_data service trees that
 * will be scheduled next. It is used to reduce the number of steps
 * needed for each hierarchical-schedule update.
 *
 * The supported ioprio_classes are the same as in CFQ, in descending
 * priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE.
 * Requests from higher priority queues are served before all the
 * requests from lower priority queues; among requests of the same
 * queue requests are served according to B-WF2Q+.
 * All the fields are protected by the queue lock of the containing bfqd.
 */
struct bfq_sched_data {
	/* entity in service */
	struct bfq_entity *in_service_entity;
	/* head-of-line entity (see comments above) */
	struct bfq_entity *next_in_service;
	/* array of service trees, one per ioprio_class */
	struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES];
	/* last time CLASS_IDLE was served */
	unsigned long bfq_class_idle_last_service;

};

/**
 * struct bfq_entity - schedulable entity.
 *
 * A bfq_entity is used to represent either a bfq_queue (leaf node in the
 * cgroup hierarchy) or a bfq_group into the upper level scheduler.  Each
 * entity belongs to the sched_data of the parent group in the cgroup
 * hierarchy.  Non-leaf entities have also their own sched_data, stored
 * in @my_sched_data.
 *
 * Each entity stores independently its priority values; this would
 * allow different weights on different devices, but this
 * functionality is not exported to userspace by now.  Priorities and
 * weights are updated lazily, first storing the new values into the
 * new_* fields, then setting the @prio_changed flag.  As soon as
 * there is a transition in the entity state that allows the priority
 * update to take place the effective and the requested priority
 * values are synchronized.
 *
 * Unless cgroups are used, the weight value is calculated from the
 * ioprio to export the same interface as CFQ.  When dealing with
 * ``well-behaved'' queues (i.e., queues that do not spend too much
 * time to consume their budget and have true sequential behavior, and
 * when there are no external factors breaking anticipation) the
 * relative weights at each level of the cgroups hierarchy should be
 * guaranteed.  All the fields are protected by the queue lock of the
 * containing bfqd.
 */
struct bfq_entity {
	/* service_tree member */
	struct rb_node rb_node;

	/*
	 * Flag, true if the entity is on a tree (either the active or
	 * the idle one of its service_tree) or is in service.
	 */
	bool on_st;

	/* B-WF2Q+ start and finish timestamps [sectors/weight] */
	u64 start, finish;

	/* tree the entity is enqueued into; %NULL if not on a tree */
	struct rb_root *tree;

	/*
	 * minimum start time of the (active) subtree rooted at this
	 * entity; used for O(log N) lookups into active trees
	 */
	u64 min_start;

	/* amount of service received during the last service slot */
	int service;

	/* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
	int budget;

	/* weight of the queue */
	int weight;
	/* next weight if a change is in progress */
	int new_weight;

	/* original weight, used to implement weight boosting */
	int orig_weight;

	/* parent entity, for hierarchical scheduling */
	struct bfq_entity *parent;

	/*
	 * For non-leaf nodes in the hierarchy, the associated
	 * scheduler queue, %NULL on leaf nodes.
	 */
	struct bfq_sched_data *my_sched_data;
	/* the scheduler queue this entity belongs to */
	struct bfq_sched_data *sched_data;

	/* flag, set to request a weight, ioprio or ioprio_class change  */
	int prio_changed;
};

struct bfq_group;

/**
 * struct bfq_ttime - per process thinktime stats.
 */
struct bfq_ttime {
	/* completion time of the last request */
	u64 last_end_request;

	/* total process thinktime */
	u64 ttime_total;
	/* number of thinktime samples */
	unsigned long ttime_samples;
	/* average process thinktime */
	u64 ttime_mean;
};

/**
 * struct bfq_queue - leaf schedulable entity.
 *
 * A bfq_queue is a leaf request queue; it can be associated with an
 * io_context or more, if it is async. @cgroup holds a reference to
 * the cgroup, to be sure that it does not disappear while a bfqq
 * still references it (mostly to avoid races between request issuing
 * and task migration followed by cgroup destruction).  All the fields
 * are protected by the queue lock of the containing bfqd.
 */
struct bfq_queue {
	/* reference counter */
	int ref;
	/* parent bfq_data */
	struct bfq_data *bfqd;

	/* current ioprio and ioprio class */
	unsigned short ioprio, ioprio_class;
	/* next ioprio and ioprio class if a change is in progress */
	unsigned short new_ioprio, new_ioprio_class;

	/* sorted list of pending requests */
	struct rb_root sort_list;
	/* if fifo isn't expired, next request to serve */
	struct request *next_rq;
	/* number of sync and async requests queued */
	int queued[2];
	/* number of requests currently allocated */
	int allocated;
	/* number of pending metadata requests */
	int meta_pending;
	/* fifo list of requests in sort_list */
	struct list_head fifo;

	/* entity representing this queue in the scheduler */
	struct bfq_entity entity;

	/* maximum budget allowed from the feedback mechanism */
	int max_budget;
	/* budget expiration (in jiffies) */
	unsigned long budget_timeout;

	/* number of requests on the dispatch list or inside driver */
	int dispatched;

	/* status flags */
	unsigned long flags;

	/* node for active/idle bfqq list inside parent bfqd */
	struct list_head bfqq_list;

	/* associated @bfq_ttime struct */
	struct bfq_ttime ttime;

	/* bit vector: a 1 for each seeky requests in history */
	u32 seek_history;
	/* position of the last request enqueued */
	sector_t last_request_pos;

	/* Number of consecutive pairs of request completion and
	 * arrival, such that the queue becomes idle after the
	 * completion, but the next request arrives within an idle
	 * time slice; used only if the queue's IO_bound flag has been
	 * cleared.
	 */
	unsigned int requests_within_timer;

	/* pid of the process owning the queue, used for logging purposes */
	pid_t pid;
};

/**
 * struct bfq_io_cq - per (request_queue, io_context) structure.
 */
struct bfq_io_cq {
	/* associated io_cq structure */
	struct io_cq icq; /* must be the first member */
	/* array of two process queues, the sync and the async */
	struct bfq_queue *bfqq[2];
	/* per (request_queue, blkcg) ioprio */
	int ioprio;
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	uint64_t blkcg_serial_nr; /* the current blkcg serial */
#endif
};

/**
 * struct bfq_data - per-device data structure.
 *
 * All the fields are protected by @lock.
 */
struct bfq_data {
	/* device request queue */
	struct request_queue *queue;
	/* dispatch queue */
	struct list_head dispatch;

	/* root bfq_group for the device */
	struct bfq_group *root_group;

	/*
	 * Number of bfq_queues containing requests (including the
	 * queue in service, even if it is idling).
	 */
	int busy_queues;
	/* number of queued requests */
	int queued;
	/* number of requests dispatched and waiting for completion */
	int rq_in_driver;

	/*
	 * Maximum number of requests in driver in the last
	 * @hw_tag_samples completed requests.
	 */
	int max_rq_in_driver;
	/* number of samples used to calculate hw_tag */
	int hw_tag_samples;
	/* flag set to one if the driver is showing a queueing behavior */
	int hw_tag;

	/* number of budgets assigned */
	int budgets_assigned;

	/*
	 * Timer set when idling (waiting) for the next request from
	 * the queue in service.
	 */
	struct hrtimer idle_slice_timer;

	/* bfq_queue in service */
	struct bfq_queue *in_service_queue;
	/* bfq_io_cq (bic) associated with the @in_service_queue */
	struct bfq_io_cq *in_service_bic;

	/* on-disk position of the last served request */
	sector_t last_position;

	/* beginning of the last budget */
	ktime_t last_budget_start;
	/* beginning of the last idle slice */
	ktime_t last_idling_start;
	/* number of samples used to calculate @peak_rate */
	int peak_rate_samples;
	/*
	 * Peak read/write rate, observed during the service of a
	 * budget [BFQ_RATE_SHIFT * sectors/usec]. The value is
	 * left-shifted by BFQ_RATE_SHIFT to increase precision in
	 * fixed-point calculations.
	 */
	u64 peak_rate;
	/* maximum budget allotted to a bfq_queue before rescheduling */
	int bfq_max_budget;

	/* list of all the bfq_queues active on the device */
	struct list_head active_list;
	/* list of all the bfq_queues idle on the device */
	struct list_head idle_list;

	/*
	 * Timeout for async/sync requests; when it fires, requests
	 * are served in fifo order.
	 */
	u64 bfq_fifo_expire[2];
	/* weight of backward seeks wrt forward ones */
	unsigned int bfq_back_penalty;
	/* maximum allowed backward seek */
	unsigned int bfq_back_max;
	/* maximum idling time */
	u32 bfq_slice_idle;

	/* user-configured max budget value (0 for auto-tuning) */
	int bfq_user_max_budget;
	/*
	 * Timeout for bfq_queues to consume their budget; used to
	 * prevent seeky queues from imposing long latencies to
	 * sequential or quasi-sequential ones (this also implies that
	 * seeky queues cannot receive guarantees in the service
	 * domain; after a timeout they are charged for the time they
	 * have been in service, to preserve fairness among them, but
	 * without service-domain guarantees).
	 */
	unsigned int bfq_timeout;

	/*
	 * Number of consecutive requests that must be issued within
	 * the idle time slice to set again idling to a queue which
	 * was marked as non-I/O-bound (see the definition of the
	 * IO_bound flag for further details).
	 */
	unsigned int bfq_requests_within_timer;

	/*
	 * Force device idling whenever needed to provide accurate
	 * service guarantees, without caring about throughput
	 * issues. CAVEAT: this may even increase latencies, in case
	 * of useless idling for processes that did stop doing I/O.
	 */
	bool strict_guarantees;

	/* fallback dummy bfqq for extreme OOM conditions */
	struct bfq_queue oom_bfqq;

	spinlock_t lock;

	/*
	 * bic associated with the task issuing current bio for
	 * merging. This and the next field are used as a support to
	 * be able to perform the bic lookup, needed by bio-merge
	 * functions, before the scheduler lock is taken, and thus
	 * avoid taking the request-queue lock while the scheduler
	 * lock is being held.
	 */
	struct bfq_io_cq *bio_bic;
	/* bfqq associated with the task issuing current bio for merging */
	struct bfq_queue *bio_bfqq;
};

enum bfqq_state_flags {
	BFQQF_busy = 0,		/* has requests or is in service */
	BFQQF_wait_request,	/* waiting for a request */
	BFQQF_non_blocking_wait_rq, /*
				     * waiting for a request
				     * without idling the device
				     */
	BFQQF_fifo_expire,	/* FIFO checked in this slice */
	BFQQF_idle_window,	/* slice idling enabled */
	BFQQF_sync,		/* synchronous queue */
	BFQQF_budget_new,	/* no completion with this budget */
	BFQQF_IO_bound,		/*
				 * bfqq has timed-out at least once
				 * having consumed at most 2/10 of
				 * its budget
				 */
};

#define BFQ_BFQQ_FNS(name)						\
static void bfq_mark_bfqq_##name(struct bfq_queue *bfqq)		\
{									\
	__set_bit(BFQQF_##name, &(bfqq)->flags);			\
}									\
static void bfq_clear_bfqq_##name(struct bfq_queue *bfqq)		\
{									\
	__clear_bit(BFQQF_##name, &(bfqq)->flags);		\
}									\
static int bfq_bfqq_##name(const struct bfq_queue *bfqq)		\
{									\
	return test_bit(BFQQF_##name, &(bfqq)->flags);		\
}

BFQ_BFQQ_FNS(busy);
BFQ_BFQQ_FNS(wait_request);
BFQ_BFQQ_FNS(non_blocking_wait_rq);
BFQ_BFQQ_FNS(fifo_expire);
BFQ_BFQQ_FNS(idle_window);
BFQ_BFQQ_FNS(sync);
BFQ_BFQQ_FNS(budget_new);
BFQ_BFQQ_FNS(IO_bound);
#undef BFQ_BFQQ_FNS

/* Logging facilities. */
#ifdef CONFIG_BFQ_GROUP_IOSCHED
static struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);

#define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	do {			\
	char __pbuf[128];						\
									\
	blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
	blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid, \
			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
			  __pbuf, ##args);				\
} while (0)

#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)	do {			\
	char __pbuf[128];						\
									\
	blkg_path(bfqg_to_blkg(bfqg), __pbuf, sizeof(__pbuf));		\
	blk_add_trace_msg((bfqd)->queue, "%s " fmt, __pbuf, ##args);	\
} while (0)

#else /* CONFIG_BFQ_GROUP_IOSCHED */

#define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	\
	blk_add_trace_msg((bfqd)->queue, "bfq%d%c " fmt, (bfqq)->pid,	\
			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
				##args)
#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)		do {} while (0)

#endif /* CONFIG_BFQ_GROUP_IOSCHED */

#define bfq_log(bfqd, fmt, args...) \
	blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)

/* Expiration reasons. */
enum bfqq_expiration {
	BFQQE_TOO_IDLE = 0,		/*
					 * queue has been idling for
					 * too long
					 */
	BFQQE_BUDGET_TIMEOUT,	/* budget took too long to be used */
	BFQQE_BUDGET_EXHAUSTED,	/* budget consumed */
	BFQQE_NO_MORE_REQUESTS,	/* the queue has no more requests */
	BFQQE_PREEMPTED		/* preemption in progress */
};

struct bfqg_stats {
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	/* number of ios merged */
	struct blkg_rwstat		merged;
	/* total time spent on device in ns, may not be accurate w/ queueing */
	struct blkg_rwstat		service_time;
	/* total time spent waiting in scheduler queue in ns */
	struct blkg_rwstat		wait_time;
	/* number of IOs queued up */
	struct blkg_rwstat		queued;
	/* total disk time and nr sectors dispatched by this group */
	struct blkg_stat		time;
	/* sum of number of ios queued across all samples */
	struct blkg_stat		avg_queue_size_sum;
	/* count of samples taken for average */
	struct blkg_stat		avg_queue_size_samples;
	/* how many times this group has been removed from service tree */
	struct blkg_stat		dequeue;
	/* total time spent waiting for it to be assigned a timeslice. */
	struct blkg_stat		group_wait_time;
	/* time spent idling for this blkcg_gq */
	struct blkg_stat		idle_time;
	/* total time with empty current active q with other requests queued */
	struct blkg_stat		empty_time;
	/* fields after this shouldn't be cleared on stat reset */
	uint64_t			start_group_wait_time;
	uint64_t			start_idle_time;
	uint64_t			start_empty_time;
	uint16_t			flags;
#endif	/* CONFIG_BFQ_GROUP_IOSCHED */
};

#ifdef CONFIG_BFQ_GROUP_IOSCHED

/*
 * struct bfq_group_data - per-blkcg storage for the blkio subsystem.
 *
 * @ps: @blkcg_policy_storage that this structure inherits
 * @weight: weight of the bfq_group
 */
struct bfq_group_data {
	/* must be the first member */
	struct blkcg_policy_data pd;

	unsigned short weight;
};

/**
 * struct bfq_group - per (device, cgroup) data structure.
 * @entity: schedulable entity to insert into the parent group sched_data.
 * @sched_data: own sched_data, to contain child entities (they may be
 *              both bfq_queues and bfq_groups).
 * @bfqd: the bfq_data for the device this group acts upon.
 * @async_bfqq: array of async queues for all the tasks belonging to
 *              the group, one queue per ioprio value per ioprio_class,
 *              except for the idle class that has only one queue.
 * @async_idle_bfqq: async queue for the idle class (ioprio is ignored).
 * @my_entity: pointer to @entity, %NULL for the toplevel group; used
 *             to avoid too many special cases during group creation/
 *             migration.
 * @stats: stats for this bfqg.
 *
 * Each (device, cgroup) pair has its own bfq_group, i.e., for each cgroup
 * there is a set of bfq_groups, each one collecting the lower-level
 * entities belonging to the group that are acting on the same device.
 *
 * Locking works as follows:
 *    o @bfqd is protected by the queue lock, RCU is used to access it
 *      from the readers.
 *    o All the other fields are protected by the @bfqd queue lock.
 */
struct bfq_group {
	/* must be the first member */
	struct blkg_policy_data pd;

	struct bfq_entity entity;
	struct bfq_sched_data sched_data;

	void *bfqd;

	struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
	struct bfq_queue *async_idle_bfqq;

	struct bfq_entity *my_entity;

	struct bfqg_stats stats;
};

#else
struct bfq_group {
	struct bfq_sched_data sched_data;

	struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
	struct bfq_queue *async_idle_bfqq;

	struct rb_root rq_pos_tree;
};
#endif

static struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);

static unsigned int bfq_class_idx(struct bfq_entity *entity)
{
	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);

	return bfqq ? bfqq->ioprio_class - 1 :
		BFQ_DEFAULT_GRP_CLASS - 1;
}

static struct bfq_service_tree *
bfq_entity_service_tree(struct bfq_entity *entity)
{
	struct bfq_sched_data *sched_data = entity->sched_data;
	unsigned int idx = bfq_class_idx(entity);

	return sched_data->service_tree + idx;
}

static struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync)
{
	return bic->bfqq[is_sync];
}

static void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq,
			 bool is_sync)
{
	bic->bfqq[is_sync] = bfqq;
}

static struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
{
	return bic->icq.q->elevator->elevator_data;
}

static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio);
static void bfq_put_queue(struct bfq_queue *bfqq);
static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
				       struct bio *bio, bool is_sync,
				       struct bfq_io_cq *bic);
static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);

/* Expiration time of sync (0) and async (1) requests, in ns. */
static const u64 bfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 8 };

/* Maximum backwards seek (magic number lifted from CFQ), in KiB. */
static const int bfq_back_max = 16 * 1024;

/* Penalty of a backwards seek, in number of sectors. */
static const int bfq_back_penalty = 2;

/* Idling period duration, in ns. */
static u64 bfq_slice_idle = NSEC_PER_SEC / 125;

/* Minimum number of assigned budgets for which stats are safe to compute. */
static const int bfq_stats_min_budgets = 194;

/* Default maximum budget values, in sectors and number of requests. */
static const int bfq_default_max_budget = 16 * 1024;

/* Default timeout values, in jiffies, approximating CFQ defaults. */
static const int bfq_timeout = HZ / 8;

static struct kmem_cache *bfq_pool;

/* Below this threshold (in ms), we consider thinktime immediate. */
#define BFQ_MIN_TT		(2 * NSEC_PER_MSEC)

/* hw_tag detection: parallel requests threshold and min samples needed. */
#define BFQ_HW_QUEUE_THRESHOLD	4
#define BFQ_HW_QUEUE_SAMPLES	32

#define BFQQ_SEEK_THR		(sector_t)(8 * 100)
#define BFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)
#define BFQQ_CLOSE_THR		(sector_t)(8 * 1024)
#define BFQQ_SEEKY(bfqq)	(hweight32(bfqq->seek_history) > 32/8)

/* Min samples used for peak rate estimation (for autotuning). */
#define BFQ_PEAK_RATE_SAMPLES	32

/* Shift used for peak rate fixed precision calculations. */
#define BFQ_RATE_SHIFT		16

#define BFQ_SERVICE_TREE_INIT	((struct bfq_service_tree)		\
				{ RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 })

#define RQ_BIC(rq)		((struct bfq_io_cq *) (rq)->elv.priv[0])
#define RQ_BFQQ(rq)		((rq)->elv.priv[1])

/**
 * icq_to_bic - convert iocontext queue structure to bfq_io_cq.
 * @icq: the iocontext queue.
 */
static struct bfq_io_cq *icq_to_bic(struct io_cq *icq)
{
	/* bic->icq is the first member, %NULL will convert to %NULL */
	return container_of(icq, struct bfq_io_cq, icq);
}

/**
 * bfq_bic_lookup - search into @ioc a bic associated to @bfqd.
 * @bfqd: the lookup key.
 * @ioc: the io_context of the process doing I/O.
 * @q: the request queue.
 */
static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
					struct io_context *ioc,
					struct request_queue *q)
{
	if (ioc) {
		unsigned long flags;
		struct bfq_io_cq *icq;

		spin_lock_irqsave(q->queue_lock, flags);
		icq = icq_to_bic(ioc_lookup_icq(ioc, q));
		spin_unlock_irqrestore(q->queue_lock, flags);

		return icq;
	}

	return NULL;
}

/*
 * Scheduler run of queue, if there are requests pending and no one in the
 * driver that will restart queueing.
 */
static void bfq_schedule_dispatch(struct bfq_data *bfqd)
{
	if (bfqd->queued != 0) {
		bfq_log(bfqd, "schedule dispatch");
		blk_mq_run_hw_queues(bfqd->queue, true);
	}
}

/**
 * bfq_gt - compare two timestamps.
 * @a: first ts.
 * @b: second ts.
 *
 * Return @a > @b, dealing with wrapping correctly.
 */
static int bfq_gt(u64 a, u64 b)
{
	return (s64)(a - b) > 0;
}

static struct bfq_entity *bfq_root_active_entity(struct rb_root *tree)
{
	struct rb_node *node = tree->rb_node;

	return rb_entry(node, struct bfq_entity, rb_node);
}

static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd);

static bool bfq_update_parent_budget(struct bfq_entity *next_in_service);

/**
 * bfq_update_next_in_service - update sd->next_in_service
 * @sd: sched_data for which to perform the update.
 * @new_entity: if not NULL, pointer to the entity whose activation,
 *		requeueing or repositionig triggered the invocation of
 *		this function.
 *
 * This function is called to update sd->next_in_service, which, in
 * its turn, may change as a consequence of the insertion or
 * extraction of an entity into/from one of the active trees of
 * sd. These insertions/extractions occur as a consequence of
 * activations/deactivations of entities, with some activations being
 * 'true' activations, and other activations being requeueings (i.e.,
 * implementing the second, requeueing phase of the mechanism used to
 * reposition an entity in its active tree; see comments on
 * __bfq_activate_entity and __bfq_requeue_entity for details). In
 * both the last two activation sub-cases, new_entity points to the
 * just activated or requeued entity.
 *
 * Returns true if sd->next_in_service changes in such a way that
 * entity->parent may become the next_in_service for its parent
 * entity.
 */
static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
				       struct bfq_entity *new_entity)
{
	struct bfq_entity *next_in_service = sd->next_in_service;
	bool parent_sched_may_change = false;

	/*
	 * If this update is triggered by the activation, requeueing
	 * or repositiong of an entity that does not coincide with
	 * sd->next_in_service, then a full lookup in the active tree
	 * can be avoided. In fact, it is enough to check whether the
	 * just-modified entity has a higher priority than
	 * sd->next_in_service, or, even if it has the same priority
	 * as sd->next_in_service, is eligible and has a lower virtual
	 * finish time than sd->next_in_service. If this compound
	 * condition holds, then the new entity becomes the new
	 * next_in_service. Otherwise no change is needed.
	 */
	if (new_entity && new_entity != sd->next_in_service) {
		/*
		 * Flag used to decide whether to replace
		 * sd->next_in_service with new_entity. Tentatively
		 * set to true, and left as true if
		 * sd->next_in_service is NULL.
		 */
		bool replace_next = true;

		/*
		 * If there is already a next_in_service candidate
		 * entity, then compare class priorities or timestamps
		 * to decide whether to replace sd->service_tree with
		 * new_entity.
		 */
		if (next_in_service) {
			unsigned int new_entity_class_idx =
				bfq_class_idx(new_entity);
			struct bfq_service_tree *st =
				sd->service_tree + new_entity_class_idx;

			/*
			 * For efficiency, evaluate the most likely
			 * sub-condition first.
			 */
			replace_next =
				(new_entity_class_idx ==
				 bfq_class_idx(next_in_service)
				 &&
				 !bfq_gt(new_entity->start, st->vtime)
				 &&
				 bfq_gt(next_in_service->finish,
					new_entity->finish))
				||
				new_entity_class_idx <
				bfq_class_idx(next_in_service);
		}

		if (replace_next)
			next_in_service = new_entity;
	} else /* invoked because of a deactivation: lookup needed */
		next_in_service = bfq_lookup_next_entity(sd);

	if (next_in_service) {
		parent_sched_may_change = !sd->next_in_service ||
			bfq_update_parent_budget(next_in_service);
	}

	sd->next_in_service = next_in_service;

	if (!next_in_service)
		return parent_sched_may_change;

	return parent_sched_may_change;
}

#ifdef CONFIG_BFQ_GROUP_IOSCHED
/* both next loops stop at one of the child entities of the root group */
#define for_each_entity(entity)	\
	for (; entity ; entity = entity->parent)

/*
 * For each iteration, compute parent in advance, so as to be safe if
 * entity is deallocated during the iteration. Such a deallocation may
 * happen as a consequence of a bfq_put_queue that frees the bfq_queue
 * containing entity.
 */
#define for_each_entity_safe(entity, parent) \
	for (; entity && ({ parent = entity->parent; 1; }); entity = parent)

/*
 * Returns true if this budget changes may let next_in_service->parent
 * become the next_in_service entity for its parent entity.
 */
static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
{
	struct bfq_entity *bfqg_entity;
	struct bfq_group *bfqg;
	struct bfq_sched_data *group_sd;
	bool ret = false;

	group_sd = next_in_service->sched_data;

	bfqg = container_of(group_sd, struct bfq_group, sched_data);
	/*
	 * bfq_group's my_entity field is not NULL only if the group
	 * is not the root group. We must not touch the root entity
	 * as it must never become an in-service entity.
	 */
	bfqg_entity = bfqg->my_entity;
	if (bfqg_entity) {
		if (bfqg_entity->budget > next_in_service->budget)
			ret = true;
		bfqg_entity->budget = next_in_service->budget;
	}

	return ret;
}

/*
 * This function tells whether entity stops being a candidate for next
 * service, according to the following logic.
 *
 * This function is invoked for an entity that is about to be set in
 * service. If such an entity is a queue, then the entity is no longer
 * a candidate for next service (i.e, a candidate entity to serve
 * after the in-service entity is expired). The function then returns
 * true.
 */
static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
{
	if (bfq_entity_to_bfqq(entity))
		return true;

	return false;
}

#else /* CONFIG_BFQ_GROUP_IOSCHED */
/*
 * Next two macros are fake loops when cgroups support is not
 * enabled. I fact, in such a case, there is only one level to go up
 * (to reach the root group).
 */
#define for_each_entity(entity)	\
	for (; entity ; entity = NULL)

#define for_each_entity_safe(entity, parent) \
	for (parent = NULL; entity ; entity = parent)

static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
{
	return false;
}

static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
{
	return true;
}

#endif /* CONFIG_BFQ_GROUP_IOSCHED */

/*
 * Shift for timestamp calculations.  This actually limits the maximum
 * service allowed in one timestamp delta (small shift values increase it),
 * the maximum total weight that can be used for the queues in the system
 * (big shift values increase it), and the period of virtual time
 * wraparounds.
 */
#define WFQ_SERVICE_SHIFT	22

static struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity)
{
	struct bfq_queue *bfqq = NULL;

	if (!entity->my_sched_data)
		bfqq = container_of(entity, struct bfq_queue, entity);

	return bfqq;
}


/**
 * bfq_delta - map service into the virtual time domain.
 * @service: amount of service.
 * @weight: scale factor (weight of an entity or weight sum).
 */
static u64 bfq_delta(unsigned long service, unsigned long weight)
{
	u64 d = (u64)service << WFQ_SERVICE_SHIFT;

	do_div(d, weight);
	return d;
}

/**
 * bfq_calc_finish - assign the finish time to an entity.
 * @entity: the entity to act upon.
 * @service: the service to be charged to the entity.
 */
static void bfq_calc_finish(struct bfq_entity *entity, unsigned long service)
{
	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);

	entity->finish = entity->start +
		bfq_delta(service, entity->weight);

	if (bfqq) {
		bfq_log_bfqq(bfqq->bfqd, bfqq,
			"calc_finish: serv %lu, w %d",
			service, entity->weight);
		bfq_log_bfqq(bfqq->bfqd, bfqq,
			"calc_finish: start %llu, finish %llu, delta %llu",
			entity->start, entity->finish,
			bfq_delta(service, entity->weight));
	}
}

/**
 * bfq_entity_of - get an entity from a node.
 * @node: the node field of the entity.
 *
 * Convert a node pointer to the relative entity.  This is used only
 * to simplify the logic of some functions and not as the generic
 * conversion mechanism because, e.g., in the tree walking functions,
 * the check for a %NULL value would be redundant.
 */
static struct bfq_entity *bfq_entity_of(struct rb_node *node)
{
	struct bfq_entity *entity = NULL;

	if (node)
		entity = rb_entry(node, struct bfq_entity, rb_node);

	return entity;
}

/**
 * bfq_extract - remove an entity from a tree.
 * @root: the tree root.
 * @entity: the entity to remove.
 */
static void bfq_extract(struct rb_root *root, struct bfq_entity *entity)
{
	entity->tree = NULL;
	rb_erase(&entity->rb_node, root);
}

/**
 * bfq_idle_extract - extract an entity from the idle tree.
 * @st: the service tree of the owning @entity.
 * @entity: the entity being removed.
 */
static void bfq_idle_extract(struct bfq_service_tree *st,
			     struct bfq_entity *entity)
{
	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
	struct rb_node *next;

	if (entity == st->first_idle) {
		next = rb_next(&entity->rb_node);
		st->first_idle = bfq_entity_of(next);
	}

	if (entity == st->last_idle) {
		next = rb_prev(&entity->rb_node);
		st->last_idle = bfq_entity_of(next);
	}

	bfq_extract(&st->idle, entity);

	if (bfqq)
		list_del(&bfqq->bfqq_list);
}

/**
 * bfq_insert - generic tree insertion.
 * @root: tree root.
 * @entity: entity to insert.
 *
 * This is used for the idle and the active tree, since they are both
 * ordered by finish time.
 */
static void bfq_insert(struct rb_root *root, struct bfq_entity *entity)
{
	struct bfq_entity *entry;
	struct rb_node **node = &root->rb_node;
	struct rb_node *parent = NULL;

	while (*node) {
		parent = *node;
		entry = rb_entry(parent, struct bfq_entity, rb_node);

		if (bfq_gt(entry->finish, entity->finish))
			node = &parent->rb_left;
		else
			node = &parent->rb_right;
	}

	rb_link_node(&entity->rb_node, parent, node);
	rb_insert_color(&entity->rb_node, root);

	entity->tree = root;
}

/**
 * bfq_update_min - update the min_start field of a entity.
 * @entity: the entity to update.
 * @node: one of its children.
 *
 * This function is called when @entity may store an invalid value for
 * min_start due to updates to the active tree.  The function  assumes
 * that the subtree rooted at @node (which may be its left or its right
 * child) has a valid min_start value.
 */
static void bfq_update_min(struct bfq_entity *entity, struct rb_node *node)
{
	struct bfq_entity *child;

	if (node) {
		child = rb_entry(node, struct bfq_entity, rb_node);
		if (bfq_gt(entity->min_start, child->min_start))
			entity->min_start = child->min_start;
	}
}

/**
 * bfq_update_active_node - recalculate min_start.
 * @node: the node to update.
 *
 * @node may have changed position or one of its children may have moved,
 * this function updates its min_start value.  The left and right subtrees
 * are assumed to hold a correct min_start value.
 */
static void bfq_update_active_node(struct rb_node *node)
{
	struct bfq_entity *entity = rb_entry(node, struct bfq_entity, rb_node);

	entity->min_start = entity->start;
	bfq_update_min(entity, node->rb_right);
	bfq_update_min(entity, node->rb_left);
}

/**
 * bfq_update_active_tree - update min_start for the whole active tree.
 * @node: the starting node.
 *
 * @node must be the deepest modified node after an update.  This function
 * updates its min_start using the values held by its children, assuming
 * that they did not change, and then updates all the nodes that may have
 * changed in the path to the root.  The only nodes that may have changed
 * are the ones in the path or their siblings.
 */
static void bfq_update_active_tree(struct rb_node *node)
{
	struct rb_node *parent;

up:
	bfq_update_active_node(node);

	parent = rb_parent(node);
	if (!parent)
		return;

	if (node == parent->rb_left && parent->rb_right)
		bfq_update_active_node(parent->rb_right);
	else if (parent->rb_left)
		bfq_update_active_node(parent->rb_left);

	node = parent;
	goto up;
}

/**
 * bfq_active_insert - insert an entity in the active tree of its
 *                     group/device.
 * @st: the service tree of the entity.
 * @entity: the entity being inserted.
 *
 * The active tree is ordered by finish time, but an extra key is kept
 * per each node, containing the minimum value for the start times of
 * its children (and the node itself), so it's possible to search for
 * the eligible node with the lowest finish time in logarithmic time.
 */
static void bfq_active_insert(struct bfq_service_tree *st,
			      struct bfq_entity *entity)
{
	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
	struct rb_node *node = &entity->rb_node;
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	struct bfq_sched_data *sd = NULL;
	struct bfq_group *bfqg = NULL;
	struct bfq_data *bfqd = NULL;
#endif

	bfq_insert(&st->active, entity);

	if (node->rb_left)
		node = node->rb_left;
	else if (node->rb_right)
		node = node->rb_right;

	bfq_update_active_tree(node);

#ifdef CONFIG_BFQ_GROUP_IOSCHED
	sd = entity->sched_data;
	bfqg = container_of(sd, struct bfq_group, sched_data);
	bfqd = (struct bfq_data *)bfqg->bfqd;
#endif
	if (bfqq)
		list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
}

/**
 * bfq_ioprio_to_weight - calc a weight from an ioprio.
 * @ioprio: the ioprio value to convert.
 */
static unsigned short bfq_ioprio_to_weight(int ioprio)
{
	return (IOPRIO_BE_NR - ioprio) * BFQ_WEIGHT_CONVERSION_COEFF;
}

/**
 * bfq_weight_to_ioprio - calc an ioprio from a weight.
 * @weight: the weight value to convert.
 *
 * To preserve as much as possible the old only-ioprio user interface,
 * 0 is used as an escape ioprio value for weights (numerically) equal or
 * larger than IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF.
 */
static unsigned short bfq_weight_to_ioprio(int weight)
{
	return max_t(int, 0,
		     IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - weight);
}

static void bfq_get_entity(struct bfq_entity *entity)
{
	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);

	if (bfqq) {
		bfqq->ref++;
		bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d",
			     bfqq, bfqq->ref);
	}
}

/**
 * bfq_find_deepest - find the deepest node that an extraction can modify.
 * @node: the node being removed.
 *
 * Do the first step of an extraction in an rb tree, looking for the
 * node that will replace @node, and returning the deepest node that
 * the following modifications to the tree can touch.  If @node is the
 * last node in the tree return %NULL.
 */
static struct rb_node *bfq_find_deepest(struct rb_node *node)
{
	struct rb_node *deepest;

	if (!node->rb_right && !node->rb_left)
		deepest = rb_parent(node);
	else if (!node->rb_right)
		deepest = node->rb_left;
	else if (!node->rb_left)
		deepest = node->rb_right;
	else {
		deepest = rb_next(node);
		if (deepest->rb_right)
			deepest = deepest->rb_right;
		else if (rb_parent(deepest) != node)
			deepest = rb_parent(deepest);
	}

	return deepest;
}

/**
 * bfq_active_extract - remove an entity from the active tree.
 * @st: the service_tree containing the tree.
 * @entity: the entity being removed.
 */
static void bfq_active_extract(struct bfq_service_tree *st,
			       struct bfq_entity *entity)
{
	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
	struct rb_node *node;
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	struct bfq_sched_data *sd = NULL;
	struct bfq_group *bfqg = NULL;
	struct bfq_data *bfqd = NULL;
#endif

	node = bfq_find_deepest(&entity->rb_node);
	bfq_extract(&st->active, entity);

	if (node)
		bfq_update_active_tree(node);

#ifdef CONFIG_BFQ_GROUP_IOSCHED
	sd = entity->sched_data;
	bfqg = container_of(sd, struct bfq_group, sched_data);
	bfqd = (struct bfq_data *)bfqg->bfqd;
#endif
	if (bfqq)
		list_del(&bfqq->bfqq_list);
}

/**
 * bfq_idle_insert - insert an entity into the idle tree.
 * @st: the service tree containing the tree.
 * @entity: the entity to insert.
 */
static void bfq_idle_insert(struct bfq_service_tree *st,
			    struct bfq_entity *entity)
{
	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
	struct bfq_entity *first_idle = st->first_idle;
	struct bfq_entity *last_idle = st->last_idle;

	if (!first_idle || bfq_gt(first_idle->finish, entity->finish))
		st->first_idle = entity;
	if (!last_idle || bfq_gt(entity->finish, last_idle->finish))
		st->last_idle = entity;

	bfq_insert(&st->idle, entity);

	if (bfqq)
		list_add(&bfqq->bfqq_list, &bfqq->bfqd->idle_list);
}

/**
 * bfq_forget_entity - do not consider entity any longer for scheduling
 * @st: the service tree.
 * @entity: the entity being removed.
 * @is_in_service: true if entity is currently the in-service entity.
 *
 * Forget everything about @entity. In addition, if entity represents
 * a queue, and the latter is not in service, then release the service
 * reference to the queue (the one taken through bfq_get_entity). In
 * fact, in this case, there is really no more service reference to
 * the queue, as the latter is also outside any service tree. If,
 * instead, the queue is in service, then __bfq_bfqd_reset_in_service
 * will take care of putting the reference when the queue finally
 * stops being served.
 */
static void bfq_forget_entity(struct bfq_service_tree *st,
			      struct bfq_entity *entity,
			      bool is_in_service)
{
	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);

	entity->on_st = false;
	st->wsum -= entity->weight;
	if (bfqq && !is_in_service)
		bfq_put_queue(bfqq);
}

/**
 * bfq_put_idle_entity - release the idle tree ref of an entity.
 * @st: service tree for the entity.
 * @entity: the entity being released.
 */
static void bfq_put_idle_entity(struct bfq_service_tree *st,
				struct bfq_entity *entity)
{
	bfq_idle_extract(st, entity);
	bfq_forget_entity(st, entity,
			  entity == entity->sched_data->in_service_entity);
}

/**
 * bfq_forget_idle - update the idle tree if necessary.
 * @st: the service tree to act upon.
 *
 * To preserve the global O(log N) complexity we only remove one entry here;
 * as the idle tree will not grow indefinitely this can be done safely.
 */
static void bfq_forget_idle(struct bfq_service_tree *st)
{
	struct bfq_entity *first_idle = st->first_idle;
	struct bfq_entity *last_idle = st->last_idle;

	if (RB_EMPTY_ROOT(&st->active) && last_idle &&
	    !bfq_gt(last_idle->finish, st->vtime)) {
		/*
		 * Forget the whole idle tree, increasing the vtime past
		 * the last finish time of idle entities.
		 */
		st->vtime = last_idle->finish;
	}

	if (first_idle && !bfq_gt(first_idle->finish, st->vtime))
		bfq_put_idle_entity(st, first_idle);
}

static struct bfq_service_tree *
__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
				struct bfq_entity *entity)
{
	struct bfq_service_tree *new_st = old_st;

	if (entity->prio_changed) {
		struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
		unsigned short prev_weight, new_weight;
		struct bfq_data *bfqd = NULL;
#ifdef CONFIG_BFQ_GROUP_IOSCHED
		struct bfq_sched_data *sd;
		struct bfq_group *bfqg;
#endif

		if (bfqq)
			bfqd = bfqq->bfqd;
#ifdef CONFIG_BFQ_GROUP_IOSCHED
		else {
			sd = entity->my_sched_data;
			bfqg = container_of(sd, struct bfq_group, sched_data);
			bfqd = (struct bfq_data *)bfqg->bfqd;
		}
#endif

		old_st->wsum -= entity->weight;

		if (entity->new_weight != entity->orig_weight) {
			if (entity->new_weight < BFQ_MIN_WEIGHT ||
			    entity->new_weight > BFQ_MAX_WEIGHT) {
				pr_crit("update_weight_prio: new_weight %d\n",
					entity->new_weight);
				if (entity->new_weight < BFQ_MIN_WEIGHT)
					entity->new_weight = BFQ_MIN_WEIGHT;
				else
					entity->new_weight = BFQ_MAX_WEIGHT;
			}
			entity->orig_weight = entity->new_weight;
			if (bfqq)
				bfqq->ioprio =
				  bfq_weight_to_ioprio(entity->orig_weight);
		}

		if (bfqq)
			bfqq->ioprio_class = bfqq->new_ioprio_class;
		entity->prio_changed = 0;

		/*
		 * NOTE: here we may be changing the weight too early,
		 * this will cause unfairness.  The correct approach
		 * would have required additional complexity to defer
		 * weight changes to the proper time instants (i.e.,
		 * when entity->finish <= old_st->vtime).
		 */
		new_st = bfq_entity_service_tree(entity);

		prev_weight = entity->weight;
		new_weight = entity->orig_weight;
		entity->weight = new_weight;

		new_st->wsum += entity->weight;

		if (new_st != old_st)
			entity->start = new_st->vtime;
	}

	return new_st;
}

static void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
static struct bfq_group *bfqq_group(struct bfq_queue *bfqq);

/**
 * bfq_bfqq_served - update the scheduler status after selection for
 *                   service.
 * @bfqq: the queue being served.
 * @served: bytes to transfer.
 *
 * NOTE: this can be optimized, as the timestamps of upper level entities
 * are synchronized every time a new bfqq is selected for service.  By now,
 * we keep it to better check consistency.
 */
static void bfq_bfqq_served(struct bfq_queue *bfqq, int served)
{
	struct bfq_entity *entity = &bfqq->entity;
	struct bfq_service_tree *st;

	for_each_entity(entity) {
		st = bfq_entity_service_tree(entity);

		entity->service += served;

		st->vtime += bfq_delta(served, st->wsum);
		bfq_forget_idle(st);
	}
	bfqg_stats_set_start_empty_time(bfqq_group(bfqq));
	bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %d secs", served);
}

/**
 * bfq_bfqq_charge_full_budget - set the service to the entity budget.
 * @bfqq: the queue that needs a service update.
 *
 * When it's not possible to be fair in the service domain, because
 * a queue is not consuming its budget fast enough (the meaning of
 * fast depends on the timeout parameter), we charge it a full
 * budget.  In this way we should obtain a sort of time-domain
 * fairness among all the seeky/slow queues.
 */
static void bfq_bfqq_charge_full_budget(struct bfq_queue *bfqq)
{
	struct bfq_entity *entity = &bfqq->entity;

	bfq_log_bfqq(bfqq->bfqd, bfqq, "charge_full_budget");

	bfq_bfqq_served(bfqq, entity->budget - entity->service);
}

static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
					struct bfq_service_tree *st,
					bool backshifted)
{
	st = __bfq_entity_update_weight_prio(st, entity);
	bfq_calc_finish(entity, entity->budget);

	/*
	 * If some queues enjoy backshifting for a while, then their
	 * (virtual) finish timestamps may happen to become lower and
	 * lower than the system virtual time.	In particular, if
	 * these queues often happen to be idle for short time
	 * periods, and during such time periods other queues with
	 * higher timestamps happen to be busy, then the backshifted
	 * timestamps of the former queues can become much lower than
	 * the system virtual time. In fact, to serve the queues with
	 * higher timestamps while the ones with lower timestamps are
	 * idle, the system virtual time may be pushed-up to much
	 * higher values than the finish timestamps of the idle
	 * queues. As a consequence, the finish timestamps of all new
	 * or newly activated queues may end up being much larger than
	 * those of lucky queues with backshifted timestamps. The
	 * latter queues may then monopolize the device for a lot of
	 * time. This would simply break service guarantees.
	 *
	 * To reduce this problem, push up a little bit the
	 * backshifted timestamps of the queue associated with this
	 * entity (only a queue can happen to have the backshifted
	 * flag set): just enough to let the finish timestamp of the
	 * queue be equal to the current value of the system virtual
	 * time. This may introduce a little unfairness among queues
	 * with backshifted timestamps, but it does not break
	 * worst-case fairness guarantees.
	 */
	if (backshifted && bfq_gt(st->vtime, entity->finish)) {
		unsigned long delta = st->vtime - entity->finish;

		entity->start += delta;
		entity->finish += delta;
	}

	bfq_active_insert(st, entity);
}

/**
 * __bfq_activate_entity - handle activation of entity.
 * @entity: the entity being activated.
 * @non_blocking_wait_rq: true if entity was waiting for a request
 *
 * Called for a 'true' activation, i.e., if entity is not active and
 * one of its children receives a new request.
 *
 * Basically, this function updates the timestamps of entity and
 * inserts entity into its active tree, ater possible extracting it
 * from its idle tree.
 */
static void __bfq_activate_entity(struct bfq_entity *entity,
				  bool non_blocking_wait_rq)
{
	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
	bool backshifted = false;
	unsigned long long min_vstart;

	/* See comments on bfq_fqq_update_budg_for_activation */
	if (non_blocking_wait_rq && bfq_gt(st->vtime, entity->finish)) {
		backshifted = true;
		min_vstart = entity->finish;
	} else
		min_vstart = st->vtime;

	if (entity->tree == &st->idle) {
		/*
		 * Must be on the idle tree, bfq_idle_extract() will
		 * check for that.
		 */
		bfq_idle_extract(st, entity);
		entity->start = bfq_gt(min_vstart, entity->finish) ?
			min_vstart : entity->finish;
	} else {
		/*
		 * The finish time of the entity may be invalid, and
		 * it is in the past for sure, otherwise the queue
		 * would have been on the idle tree.
		 */
		entity->start = min_vstart;
		st->wsum += entity->weight;
		/*
		 * entity is about to be inserted into a service tree,
		 * and then set in service: get a reference to make
		 * sure entity does not disappear until it is no
		 * longer in service or scheduled for service.
		 */
		bfq_get_entity(entity);

		entity->on_st = true;
	}

	bfq_update_fin_time_enqueue(entity, st, backshifted);
}

/**
 * __bfq_requeue_entity - handle requeueing or repositioning of an entity.
 * @entity: the entity being requeued or repositioned.
 *
 * Requeueing is needed if this entity stops being served, which
 * happens if a leaf descendant entity has expired. On the other hand,
 * repositioning is needed if the next_inservice_entity for the child
 * entity has changed. See the comments inside the function for
 * details.
 *
 * Basically, this function: 1) removes entity from its active tree if
 * present there, 2) updates the timestamps of entity and 3) inserts
 * entity back into its active tree (in the new, right position for
 * the new values of the timestamps).
 */
static void __bfq_requeue_entity(struct bfq_entity *entity)
{
	struct bfq_sched_data *sd = entity->sched_data;
	struct bfq_service_tree *st = bfq_entity_service_tree(entity);

	if (entity == sd->in_service_entity) {
		/*
		 * We are requeueing the current in-service entity,
		 * which may have to be done for one of the following
		 * reasons:
		 * - entity represents the in-service queue, and the
		 *   in-service queue is being requeued after an
		 *   expiration;
		 * - entity represents a group, and its budget has
		 *   changed because one of its child entities has
		 *   just been either activated or requeued for some
		 *   reason; the timestamps of the entity need then to
		 *   be updated, and the entity needs to be enqueued
		 *   or repositioned accordingly.
		 *
		 * In particular, before requeueing, the start time of
		 * the entity must be moved forward to account for the
		 * service that the entity has received while in
		 * service. This is done by the next instructions. The
		 * finish time will then be updated according to this
		 * new value of the start time, and to the budget of
		 * the entity.
		 */
		bfq_calc_finish(entity, entity->service);
		entity->start = entity->finish;
		/*
		 * In addition, if the entity had more than one child
		 * when set in service, then was not extracted from
		 * the active tree. This implies that the position of
		 * the entity in the active tree may need to be
		 * changed now, because we have just updated the start
		 * time of the entity, and we will update its finish
		 * time in a moment (the requeueing is then, more
		 * precisely, a repositioning in this case). To
		 * implement this repositioning, we: 1) dequeue the
		 * entity here, 2) update the finish time and
		 * requeue the entity according to the new
		 * timestamps below.
		 */
		if (entity->tree)
			bfq_active_extract(st, entity);
	} else { /* The entity is already active, and not in service */
		/*
		 * In this case, this function gets called only if the
		 * next_in_service entity below this entity has
		 * changed, and this change has caused the budget of
		 * this entity to change, which, finally implies that
		 * the finish time of this entity must be
		 * updated. Such an update may cause the scheduling,
		 * i.e., the position in the active tree, of this
		 * entity to change. We handle this change by: 1)
		 * dequeueing the entity here, 2) updating the finish
		 * time and requeueing the entity according to the new
		 * timestamps below. This is the same approach as the
		 * non-extracted-entity sub-case above.
		 */
		bfq_active_extract(st, entity);
	}

	bfq_update_fin_time_enqueue(entity, st, false);
}

static void __bfq_activate_requeue_entity(struct bfq_entity *entity,
					  struct bfq_sched_data *sd,
					  bool non_blocking_wait_rq)
{
	struct bfq_service_tree *st = bfq_entity_service_tree(entity);

	if (sd->in_service_entity == entity || entity->tree == &st->active)
		 /*
		  * in service or already queued on the active tree,
		  * requeue or reposition
		  */
		__bfq_requeue_entity(entity);
	else
		/*
		 * Not in service and not queued on its active tree:
		 * the activity is idle and this is a true activation.
		 */
		__bfq_activate_entity(entity, non_blocking_wait_rq);
}


/**
 * bfq_activate_entity - activate or requeue an entity representing a bfq_queue,
 *			 and activate, requeue or reposition all ancestors
 *			 for which such an update becomes necessary.
 * @entity: the entity to activate.
 * @non_blocking_wait_rq: true if this entity was waiting for a request
 * @requeue: true if this is a requeue, which implies that bfqq is
 *	     being expired; thus ALL its ancestors stop being served and must
 *	     therefore be requeued
 */
static void bfq_activate_requeue_entity(struct bfq_entity *entity,
					bool non_blocking_wait_rq,
					bool requeue)
{
	struct bfq_sched_data *sd;

	for_each_entity(entity) {
		sd = entity->sched_data;
		__bfq_activate_requeue_entity(entity, sd, non_blocking_wait_rq);

		if (!bfq_update_next_in_service(sd, entity) && !requeue)
			break;
	}
}

/**
 * __bfq_deactivate_entity - deactivate an entity from its service tree.
 * @entity: the entity to deactivate.
 * @ins_into_idle_tree: if false, the entity will not be put into the
 *			idle tree.
 *
 * Deactivates an entity, independently from its previous state.  Must
 * be invoked only if entity is on a service tree. Extracts the entity
 * from that tree, and if necessary and allowed, puts it on the idle
 * tree.
 */
static bool __bfq_deactivate_entity(struct bfq_entity *entity,
				    bool ins_into_idle_tree)
{
	struct bfq_sched_data *sd = entity->sched_data;
	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
	int is_in_service = entity == sd->in_service_entity;

	if (!entity->on_st) /* entity never activated, or already inactive */
		return false;

	if (is_in_service)
		bfq_calc_finish(entity, entity->service);

	if (entity->tree == &st->active)
		bfq_active_extract(st, entity);
	else if (!is_in_service && entity->tree == &st->idle)
		bfq_idle_extract(st, entity);

	if (!ins_into_idle_tree || !bfq_gt(entity->finish, st->vtime))
		bfq_forget_entity(st, entity, is_in_service);
	else
		bfq_idle_insert(st, entity);

	return true;
}

/**
 * bfq_deactivate_entity - deactivate an entity representing a bfq_queue.
 * @entity: the entity to deactivate.
 * @ins_into_idle_tree: true if the entity can be put on the idle tree
 */
static void bfq_deactivate_entity(struct bfq_entity *entity,
				  bool ins_into_idle_tree,
				  bool expiration)
{
	struct bfq_sched_data *sd;
	struct bfq_entity *parent = NULL;

	for_each_entity_safe(entity, parent) {
		sd = entity->sched_data;

		if (!__bfq_deactivate_entity(entity, ins_into_idle_tree)) {
			/*
			 * entity is not in any tree any more, so
			 * this deactivation is a no-op, and there is
			 * nothing to change for upper-level entities
			 * (in case of expiration, this can never
			 * happen).
			 */
			return;
		}

		if (sd->next_in_service == entity)
			/*
			 * entity was the next_in_service entity,
			 * then, since entity has just been
			 * deactivated, a new one must be found.
			 */
			bfq_update_next_in_service(sd, NULL);

		if (sd->next_in_service)
			/*
			 * The parent entity is still backlogged,
			 * because next_in_service is not NULL. So, no
			 * further upwards deactivation must be
			 * performed.  Yet, next_in_service has
			 * changed.  Then the schedule does need to be
			 * updated upwards.
			 */
			break;

		/*
		 * If we get here, then the parent is no more
		 * backlogged and we need to propagate the
		 * deactivation upwards. Thus let the loop go on.
		 */

		/*
		 * Also let parent be queued into the idle tree on
		 * deactivation, to preserve service guarantees, and
		 * assuming that who invoked this function does not
		 * need parent entities too to be removed completely.
		 */
		ins_into_idle_tree = true;
	}

	/*
	 * If the deactivation loop is fully executed, then there are
	 * no more entities to touch and next loop is not executed at
	 * all. Otherwise, requeue remaining entities if they are
	 * about to stop receiving service, or reposition them if this
	 * is not the case.
	 */
	entity = parent;
	for_each_entity(entity) {
		/*
		 * Invoke __bfq_requeue_entity on entity, even if
		 * already active, to requeue/reposition it in the
		 * active tree (because sd->next_in_service has
		 * changed)
		 */
		__bfq_requeue_entity(entity);

		sd = entity->sched_data;
		if (!bfq_update_next_in_service(sd, entity) &&
		    !expiration)
			/*
			 * next_in_service unchanged or not causing
			 * any change in entity->parent->sd, and no
			 * requeueing needed for expiration: stop
			 * here.
			 */
			break;
	}
}

/**
 * bfq_calc_vtime_jump - compute the value to which the vtime should jump,
 *                       if needed, to have at least one entity eligible.
 * @st: the service tree to act upon.
 *
 * Assumes that st is not empty.
 */
static u64 bfq_calc_vtime_jump(struct bfq_service_tree *st)
{
	struct bfq_entity *root_entity = bfq_root_active_entity(&st->active);

	if (bfq_gt(root_entity->min_start, st->vtime))
		return root_entity->min_start;

	return st->vtime;
}

static void bfq_update_vtime(struct bfq_service_tree *st, u64 new_value)
{
	if (new_value > st->vtime) {
		st->vtime = new_value;
		bfq_forget_idle(st);
	}
}

/**
 * bfq_first_active_entity - find the eligible entity with
 *                           the smallest finish time
 * @st: the service tree to select from.
 * @vtime: the system virtual to use as a reference for eligibility
 *
 * This function searches the first schedulable entity, starting from the
 * root of the tree and going on the left every time on this side there is
 * a subtree with at least one eligible (start >= vtime) entity. The path on
 * the right is followed only if a) the left subtree contains no eligible
 * entities and b) no eligible entity has been found yet.
 */
static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st,
						  u64 vtime)
{
	struct bfq_entity *entry, *first = NULL;
	struct rb_node *node = st->active.rb_node;

	while (node) {
		entry = rb_entry(node, struct bfq_entity, rb_node);
left:
		if (!bfq_gt(entry->start, vtime))
			first = entry;

		if (node->rb_left) {
			entry = rb_entry(node->rb_left,
					 struct bfq_entity, rb_node);
			if (!bfq_gt(entry->min_start, vtime)) {
				node = node->rb_left;
				goto left;
			}
		}
		if (first)
			break;
		node = node->rb_right;
	}

	return first;
}

/**
 * __bfq_lookup_next_entity - return the first eligible entity in @st.
 * @st: the service tree.
 *
 * If there is no in-service entity for the sched_data st belongs to,
 * then return the entity that will be set in service if:
 * 1) the parent entity this st belongs to is set in service;
 * 2) no entity belonging to such parent entity undergoes a state change
 * that would influence the timestamps of the entity (e.g., becomes idle,
 * becomes backlogged, changes its budget, ...).
 *
 * In this first case, update the virtual time in @st too (see the
 * comments on this update inside the function).
 *
 * In constrast, if there is an in-service entity, then return the
 * entity that would be set in service if not only the above
 * conditions, but also the next one held true: the currently
 * in-service entity, on expiration,
 * 1) gets a finish time equal to the current one, or
 * 2) is not eligible any more, or
 * 3) is idle.
 */
static struct bfq_entity *
__bfq_lookup_next_entity(struct bfq_service_tree *st, bool in_service)
{
	struct bfq_entity *entity;
	u64 new_vtime;

	if (RB_EMPTY_ROOT(&st->active))
		return NULL;

	/*
	 * Get the value of the system virtual time for which at
	 * least one entity is eligible.
	 */
	new_vtime = bfq_calc_vtime_jump(st);

	/*
	 * If there is no in-service entity for the sched_data this
	 * active tree belongs to, then push the system virtual time
	 * up to the value that guarantees that at least one entity is
	 * eligible. If, instead, there is an in-service entity, then
	 * do not make any such update, because there is already an
	 * eligible entity, namely the in-service one (even if the
	 * entity is not on st, because it was extracted when set in
	 * service).
	 */
	if (!in_service)
		bfq_update_vtime(st, new_vtime);

	entity = bfq_first_active_entity(st, new_vtime);

	return entity;
}

/**
 * bfq_lookup_next_entity - return the first eligible entity in @sd.
 * @sd: the sched_data.
 *
 * This function is invoked when there has been a change in the trees
 * for sd, and we need know what is the new next entity after this
 * change.
 */
static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd)
{
	struct bfq_service_tree *st = sd->service_tree;
	struct bfq_service_tree *idle_class_st = st + (BFQ_IOPRIO_CLASSES - 1);
	struct bfq_entity *entity = NULL;
	int class_idx = 0;

	/*
	 * Choose from idle class, if needed to guarantee a minimum
	 * bandwidth to this class (and if there is some active entity
	 * in idle class). This should also mitigate
	 * priority-inversion problems in case a low priority task is
	 * holding file system resources.
	 */
	if (time_is_before_jiffies(sd->bfq_class_idle_last_service +
				   BFQ_CL_IDLE_TIMEOUT)) {
		if (!RB_EMPTY_ROOT(&idle_class_st->active))
			class_idx = BFQ_IOPRIO_CLASSES - 1;
		/* About to be served if backlogged, or not yet backlogged */
		sd->bfq_class_idle_last_service = jiffies;
	}

	/*
	 * Find the next entity to serve for the highest-priority
	 * class, unless the idle class needs to be served.
	 */
	for (; class_idx < BFQ_IOPRIO_CLASSES; class_idx++) {
		entity = __bfq_lookup_next_entity(st + class_idx,
						  sd->in_service_entity);

		if (entity)
			break;
	}

	if (!entity)
		return NULL;

	return entity;
}

static bool next_queue_may_preempt(struct bfq_data *bfqd)
{
	struct bfq_sched_data *sd = &bfqd->root_group->sched_data;

	return sd->next_in_service != sd->in_service_entity;
}

/*
 * Get next queue for service.
 */
static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
{
	struct bfq_entity *entity = NULL;
	struct bfq_sched_data *sd;
	struct bfq_queue *bfqq;

	if (bfqd->busy_queues == 0)
		return NULL;

	/*
	 * Traverse the path from the root to the leaf entity to
	 * serve. Set in service all the entities visited along the
	 * way.
	 */
	sd = &bfqd->root_group->sched_data;
	for (; sd ; sd = entity->my_sched_data) {
		/*
		 * WARNING. We are about to set the in-service entity
		 * to sd->next_in_service, i.e., to the (cached) value
		 * returned by bfq_lookup_next_entity(sd) the last
		 * time it was invoked, i.e., the last time when the
		 * service order in sd changed as a consequence of the
		 * activation or deactivation of an entity. In this
		 * respect, if we execute bfq_lookup_next_entity(sd)
		 * in this very moment, it may, although with low
		 * probability, yield a different entity than that
		 * pointed to by sd->next_in_service. This rare event
		 * happens in case there was no CLASS_IDLE entity to
		 * serve for sd when bfq_lookup_next_entity(sd) was
		 * invoked for the last time, while there is now one
		 * such entity.
		 *
		 * If the above event happens, then the scheduling of
		 * such entity in CLASS_IDLE is postponed until the
		 * service of the sd->next_in_service entity
		 * finishes. In fact, when the latter is expired,
		 * bfq_lookup_next_entity(sd) gets called again,
		 * exactly to update sd->next_in_service.
		 */

		/* Make next_in_service entity become in_service_entity */
		entity = sd->next_in_service;
		sd->in_service_entity = entity;

		/*
		 * Reset the accumulator of the amount of service that
		 * the entity is about to receive.
		 */
		entity->service = 0;

		/*
		 * If entity is no longer a candidate for next
		 * service, then we extract it from its active tree,
		 * for the following reason. To further boost the
		 * throughput in some special case, BFQ needs to know
		 * which is the next candidate entity to serve, while
		 * there is already an entity in service. In this
		 * respect, to make it easy to compute/update the next
		 * candidate entity to serve after the current
		 * candidate has been set in service, there is a case
		 * where it is necessary to extract the current
		 * candidate from its service tree. Such a case is
		 * when the entity just set in service cannot be also
		 * a candidate for next service. Details about when
		 * this conditions holds are reported in the comments
		 * on the function bfq_no_longer_next_in_service()
		 * invoked below.
		 */
		if (bfq_no_longer_next_in_service(entity))
			bfq_active_extract(bfq_entity_service_tree(entity),
					   entity);

		/*
		 * For the same reason why we may have just extracted
		 * entity from its active tree, we may need to update
		 * next_in_service for the sched_data of entity too,
		 * regardless of whether entity has been extracted.
		 * In fact, even if entity has not been extracted, a
		 * descendant entity may get extracted. Such an event
		 * would cause a change in next_in_service for the
		 * level of the descendant entity, and thus possibly
		 * back to upper levels.
		 *
		 * We cannot perform the resulting needed update
		 * before the end of this loop, because, to know which
		 * is the correct next-to-serve candidate entity for
		 * each level, we need first to find the leaf entity
		 * to set in service. In fact, only after we know
		 * which is the next-to-serve leaf entity, we can
		 * discover whether the parent entity of the leaf
		 * entity becomes the next-to-serve, and so on.
		 */

	}

	bfqq = bfq_entity_to_bfqq(entity);

	/*
	 * We can finally update all next-to-serve entities along the
	 * path from the leaf entity just set in service to the root.
	 */
	for_each_entity(entity) {
		struct bfq_sched_data *sd = entity->sched_data;

		if (!bfq_update_next_in_service(sd, NULL))
			break;
	}

	return bfqq;
}

static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
{
	struct bfq_queue *in_serv_bfqq = bfqd->in_service_queue;
	struct bfq_entity *in_serv_entity = &in_serv_bfqq->entity;
	struct bfq_entity *entity = in_serv_entity;

	if (bfqd->in_service_bic) {
		put_io_context(bfqd->in_service_bic->icq.ioc);
		bfqd->in_service_bic = NULL;
	}

	bfq_clear_bfqq_wait_request(in_serv_bfqq);
	hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
	bfqd->in_service_queue = NULL;

	/*
	 * When this function is called, all in-service entities have
	 * been properly deactivated or requeued, so we can safely
	 * execute the final step: reset in_service_entity along the
	 * path from entity to the root.
	 */
	for_each_entity(entity)
		entity->sched_data->in_service_entity = NULL;

	/*
	 * in_serv_entity is no longer in service, so, if it is in no
	 * service tree either, then release the service reference to
	 * the queue it represents (taken with bfq_get_entity).
	 */
	if (!in_serv_entity->on_st)
		bfq_put_queue(in_serv_bfqq);
}

static void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
				bool ins_into_idle_tree, bool expiration)
{
	struct bfq_entity *entity = &bfqq->entity;

	bfq_deactivate_entity(entity, ins_into_idle_tree, expiration);
}

static void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
	struct bfq_entity *entity = &bfqq->entity;

	bfq_activate_requeue_entity(entity, bfq_bfqq_non_blocking_wait_rq(bfqq),
				    false);
	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
}

static void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
	struct bfq_entity *entity = &bfqq->entity;

	bfq_activate_requeue_entity(entity, false,
				    bfqq == bfqd->in_service_queue);
}

static void bfqg_stats_update_dequeue(struct bfq_group *bfqg);

/*
 * Called when the bfqq no longer has requests pending, remove it from
 * the service tree. As a special case, it can be invoked during an
 * expiration.
 */
static void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
			      bool expiration)
{
	bfq_log_bfqq(bfqd, bfqq, "del from busy");

	bfq_clear_bfqq_busy(bfqq);

	bfqd->busy_queues--;

	bfqg_stats_update_dequeue(bfqq_group(bfqq));

	bfq_deactivate_bfqq(bfqd, bfqq, true, expiration);
}

/*
 * Called when an inactive queue receives a new request.
 */
static void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
	bfq_log_bfqq(bfqd, bfqq, "add to busy");

	bfq_activate_bfqq(bfqd, bfqq);

	bfq_mark_bfqq_busy(bfqq);
	bfqd->busy_queues++;
}

#ifdef CONFIG_BFQ_GROUP_IOSCHED

/* bfqg stats flags */
enum bfqg_stats_flags {
	BFQG_stats_waiting = 0,
	BFQG_stats_idling,
	BFQG_stats_empty,
};

#define BFQG_FLAG_FNS(name)						\
static void bfqg_stats_mark_##name(struct bfqg_stats *stats)	\
{									\
	stats->flags |= (1 << BFQG_stats_##name);			\
}									\
static void bfqg_stats_clear_##name(struct bfqg_stats *stats)	\
{									\
	stats->flags &= ~(1 << BFQG_stats_##name);			\
}									\
static int bfqg_stats_##name(struct bfqg_stats *stats)		\
{									\
	return (stats->flags & (1 << BFQG_stats_##name)) != 0;		\
}									\

BFQG_FLAG_FNS(waiting)
BFQG_FLAG_FNS(idling)
BFQG_FLAG_FNS(empty)
#undef BFQG_FLAG_FNS

/* This should be called with the queue_lock held. */
static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
{
	unsigned long long now;

	if (!bfqg_stats_waiting(stats))
		return;

	now = sched_clock();
	if (time_after64(now, stats->start_group_wait_time))
		blkg_stat_add(&stats->group_wait_time,
			      now - stats->start_group_wait_time);
	bfqg_stats_clear_waiting(stats);
}

/* This should be called with the queue_lock held. */
static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
						 struct bfq_group *curr_bfqg)
{
	struct bfqg_stats *stats = &bfqg->stats;

	if (bfqg_stats_waiting(stats))
		return;
	if (bfqg == curr_bfqg)
		return;
	stats->start_group_wait_time = sched_clock();
	bfqg_stats_mark_waiting(stats);
}

/* This should be called with the queue_lock held. */
static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
{
	unsigned long long now;

	if (!bfqg_stats_empty(stats))
		return;

	now = sched_clock();
	if (time_after64(now, stats->start_empty_time))
		blkg_stat_add(&stats->empty_time,
			      now - stats->start_empty_time);
	bfqg_stats_clear_empty(stats);
}

static void bfqg_stats_update_dequeue(struct bfq_group *bfqg)
{
	blkg_stat_add(&bfqg->stats.dequeue, 1);
}

static void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg)
{
	struct bfqg_stats *stats = &bfqg->stats;

	if (blkg_rwstat_total(&stats->queued))
		return;

	/*
	 * group is already marked empty. This can happen if bfqq got new
	 * request in parent group and moved to this group while being added
	 * to service tree. Just ignore the event and move on.
	 */
	if (bfqg_stats_empty(stats))
		return;

	stats->start_empty_time = sched_clock();
	bfqg_stats_mark_empty(stats);
}

static void bfqg_stats_update_idle_time(struct bfq_group *bfqg)
{
	struct bfqg_stats *stats = &bfqg->stats;

	if (bfqg_stats_idling(stats)) {
		unsigned long long now = sched_clock();

		if (time_after64(now, stats->start_idle_time))
			blkg_stat_add(&stats->idle_time,
				      now - stats->start_idle_time);
		bfqg_stats_clear_idling(stats);
	}
}

static void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg)
{
	struct bfqg_stats *stats = &bfqg->stats;

	stats->start_idle_time = sched_clock();
	bfqg_stats_mark_idling(stats);
}

static void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg)
{
	struct bfqg_stats *stats = &bfqg->stats;

	blkg_stat_add(&stats->avg_queue_size_sum,
		      blkg_rwstat_total(&stats->queued));
	blkg_stat_add(&stats->avg_queue_size_samples, 1);
	bfqg_stats_update_group_wait_time(stats);
}

/*
 * blk-cgroup policy-related handlers
 * The following functions help in converting between blk-cgroup
 * internal structures and BFQ-specific structures.
 */

static struct bfq_group *pd_to_bfqg(struct blkg_policy_data *pd)
{
	return pd ? container_of(pd, struct bfq_group, pd) : NULL;
}

static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg)
{
	return pd_to_blkg(&bfqg->pd);
}

static struct blkcg_policy blkcg_policy_bfq;

static struct bfq_group *blkg_to_bfqg(struct blkcg_gq *blkg)
{
	return pd_to_bfqg(blkg_to_pd(blkg, &blkcg_policy_bfq));
}

/*
 * bfq_group handlers
 * The following functions help in navigating the bfq_group hierarchy
 * by allowing to find the parent of a bfq_group or the bfq_group
 * associated to a bfq_queue.
 */

static struct bfq_group *bfqg_parent(struct bfq_group *bfqg)
{
	struct blkcg_gq *pblkg = bfqg_to_blkg(bfqg)->parent;

	return pblkg ? blkg_to_bfqg(pblkg) : NULL;
}

static struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
{
	struct bfq_entity *group_entity = bfqq->entity.parent;

	return group_entity ? container_of(group_entity, struct bfq_group,
					   entity) :
			      bfqq->bfqd->root_group;
}

/*
 * The following two functions handle get and put of a bfq_group by
 * wrapping the related blk-cgroup hooks.
 */

static void bfqg_get(struct bfq_group *bfqg)
{
	return blkg_get(bfqg_to_blkg(bfqg));
}

static void bfqg_put(struct bfq_group *bfqg)
{
	return blkg_put(bfqg_to_blkg(bfqg));
}

static void bfqg_stats_update_io_add(struct bfq_group *bfqg,
				     struct bfq_queue *bfqq,
				     unsigned int op)
{
	blkg_rwstat_add(&bfqg->stats.queued, op, 1);
	bfqg_stats_end_empty_time(&bfqg->stats);
	if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue))
		bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq));
}

static void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op)
{
	blkg_rwstat_add(&bfqg->stats.queued, op, -1);
}

static void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op)
{
	blkg_rwstat_add(&bfqg->stats.merged, op, 1);
}

static void bfqg_stats_update_completion(struct bfq_group *bfqg,
			uint64_t start_time, uint64_t io_start_time,
			unsigned int op)
{
	struct bfqg_stats *stats = &bfqg->stats;
	unsigned long long now = sched_clock();

	if (time_after64(now, io_start_time))
		blkg_rwstat_add(&stats->service_time, op,
				now - io_start_time);
	if (time_after64(io_start_time, start_time))
		blkg_rwstat_add(&stats->wait_time, op,
				io_start_time - start_time);
}

/* @stats = 0 */
static void bfqg_stats_reset(struct bfqg_stats *stats)
{
	/* queued stats shouldn't be cleared */
	blkg_rwstat_reset(&stats->merged);
	blkg_rwstat_reset(&stats->service_time);
	blkg_rwstat_reset(&stats->wait_time);
	blkg_stat_reset(&stats->time);
	blkg_stat_reset(&stats->avg_queue_size_sum);
	blkg_stat_reset(&stats->avg_queue_size_samples);
	blkg_stat_reset(&stats->dequeue);
	blkg_stat_reset(&stats->group_wait_time);
	blkg_stat_reset(&stats->idle_time);
	blkg_stat_reset(&stats->empty_time);
}

/* @to += @from */
static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from)
{
	if (!to || !from)
		return;

	/* queued stats shouldn't be cleared */
	blkg_rwstat_add_aux(&to->merged, &from->merged);
	blkg_rwstat_add_aux(&to->service_time, &from->service_time);
	blkg_rwstat_add_aux(&to->wait_time, &from->wait_time);
	blkg_stat_add_aux(&from->time, &from->time);
	blkg_stat_add_aux(&to->avg_queue_size_sum, &from->avg_queue_size_sum);
	blkg_stat_add_aux(&to->avg_queue_size_samples,
			  &from->avg_queue_size_samples);
	blkg_stat_add_aux(&to->dequeue, &from->dequeue);
	blkg_stat_add_aux(&to->group_wait_time, &from->group_wait_time);
	blkg_stat_add_aux(&to->idle_time, &from->idle_time);
	blkg_stat_add_aux(&to->empty_time, &from->empty_time);
}

/*
 * Transfer @bfqg's stats to its parent's aux counts so that the ancestors'
 * recursive stats can still account for the amount used by this bfqg after
 * it's gone.
 */
static void bfqg_stats_xfer_dead(struct bfq_group *bfqg)
{
	struct bfq_group *parent;

	if (!bfqg) /* root_group */
		return;

	parent = bfqg_parent(bfqg);

	lockdep_assert_held(bfqg_to_blkg(bfqg)->q->queue_lock);

	if (unlikely(!parent))
		return;

	bfqg_stats_add_aux(&parent->stats, &bfqg->stats);
	bfqg_stats_reset(&bfqg->stats);
}

static void bfq_init_entity(struct bfq_entity *entity,
			    struct bfq_group *bfqg)
{
	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);

	entity->weight = entity->new_weight;
	entity->orig_weight = entity->new_weight;
	if (bfqq) {
		bfqq->ioprio = bfqq->new_ioprio;
		bfqq->ioprio_class = bfqq->new_ioprio_class;
		bfqg_get(bfqg);
	}
	entity->parent = bfqg->my_entity; /* NULL for root group */
	entity->sched_data = &bfqg->sched_data;
}

static void bfqg_stats_exit(struct bfqg_stats *stats)
{
	blkg_rwstat_exit(&stats->merged);
	blkg_rwstat_exit(&stats->service_time);
	blkg_rwstat_exit(&stats->wait_time);
	blkg_rwstat_exit(&stats->queued);
	blkg_stat_exit(&stats->time);
	blkg_stat_exit(&stats->avg_queue_size_sum);
	blkg_stat_exit(&stats->avg_queue_size_samples);
	blkg_stat_exit(&stats->dequeue);
	blkg_stat_exit(&stats->group_wait_time);
	blkg_stat_exit(&stats->idle_time);
	blkg_stat_exit(&stats->empty_time);
}

static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
{
	if (blkg_rwstat_init(&stats->merged, gfp) ||
	    blkg_rwstat_init(&stats->service_time, gfp) ||
	    blkg_rwstat_init(&stats->wait_time, gfp) ||
	    blkg_rwstat_init(&stats->queued, gfp) ||
	    blkg_stat_init(&stats->time, gfp) ||
	    blkg_stat_init(&stats->avg_queue_size_sum, gfp) ||
	    blkg_stat_init(&stats->avg_queue_size_samples, gfp) ||
	    blkg_stat_init(&stats->dequeue, gfp) ||
	    blkg_stat_init(&stats->group_wait_time, gfp) ||
	    blkg_stat_init(&stats->idle_time, gfp) ||
	    blkg_stat_init(&stats->empty_time, gfp)) {
		bfqg_stats_exit(stats);
		return -ENOMEM;
	}

	return 0;
}

static struct bfq_group_data *cpd_to_bfqgd(struct blkcg_policy_data *cpd)
{
	return cpd ? container_of(cpd, struct bfq_group_data, pd) : NULL;
}

static struct bfq_group_data *blkcg_to_bfqgd(struct blkcg *blkcg)
{
	return cpd_to_bfqgd(blkcg_to_cpd(blkcg, &blkcg_policy_bfq));
}

static struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp)
{
	struct bfq_group_data *bgd;

	bgd = kzalloc(sizeof(*bgd), gfp);
	if (!bgd)
		return NULL;
	return &bgd->pd;
}

static void bfq_cpd_init(struct blkcg_policy_data *cpd)
{
	struct bfq_group_data *d = cpd_to_bfqgd(cpd);

	d->weight = cgroup_subsys_on_dfl(io_cgrp_subsys) ?
		CGROUP_WEIGHT_DFL : BFQ_WEIGHT_LEGACY_DFL;
}

static void bfq_cpd_free(struct blkcg_policy_data *cpd)
{
	kfree(cpd_to_bfqgd(cpd));
}

static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node)
{
	struct bfq_group *bfqg;

	bfqg = kzalloc_node(sizeof(*bfqg), gfp, node);
	if (!bfqg)
		return NULL;

	if (bfqg_stats_init(&bfqg->stats, gfp)) {
		kfree(bfqg);
		return NULL;
	}

	return &bfqg->pd;
}

static void bfq_pd_init(struct blkg_policy_data *pd)
{
	struct blkcg_gq *blkg = pd_to_blkg(pd);
	struct bfq_group *bfqg = blkg_to_bfqg(blkg);
	struct bfq_data *bfqd = blkg->q->elevator->elevator_data;
	struct bfq_entity *entity = &bfqg->entity;
	struct bfq_group_data *d = blkcg_to_bfqgd(blkg->blkcg);

	entity->orig_weight = entity->weight = entity->new_weight = d->weight;
	entity->my_sched_data = &bfqg->sched_data;
	bfqg->my_entity = entity; /*
				   * the root_group's will be set to NULL
				   * in bfq_init_queue()
				   */
	bfqg->bfqd = bfqd;
}

static void bfq_pd_free(struct blkg_policy_data *pd)
{
	struct bfq_group *bfqg = pd_to_bfqg(pd);

	bfqg_stats_exit(&bfqg->stats);
	return kfree(bfqg);
}

static void bfq_pd_reset_stats(struct blkg_policy_data *pd)
{
	struct bfq_group *bfqg = pd_to_bfqg(pd);

	bfqg_stats_reset(&bfqg->stats);
}

static void bfq_group_set_parent(struct bfq_group *bfqg,
					struct bfq_group *parent)
{
	struct bfq_entity *entity;

	entity = &bfqg->entity;
	entity->parent = parent->my_entity;
	entity->sched_data = &parent->sched_data;
}

static struct bfq_group *bfq_lookup_bfqg(struct bfq_data *bfqd,
					 struct blkcg *blkcg)
{
	struct blkcg_gq *blkg;

	blkg = blkg_lookup(blkcg, bfqd->queue);
	if (likely(blkg))
		return blkg_to_bfqg(blkg);
	return NULL;
}

static struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
					    struct blkcg *blkcg)
{
	struct bfq_group *bfqg, *parent;
	struct bfq_entity *entity;

	bfqg = bfq_lookup_bfqg(bfqd, blkcg);

	if (unlikely(!bfqg))
		return NULL;

	/*
	 * Update chain of bfq_groups as we might be handling a leaf group
	 * which, along with some of its relatives, has not been hooked yet
	 * to the private hierarchy of BFQ.
	 */
	entity = &bfqg->entity;
	for_each_entity(entity) {
		bfqg = container_of(entity, struct bfq_group, entity);
		if (bfqg != bfqd->root_group) {
			parent = bfqg_parent(bfqg);
			if (!parent)
				parent = bfqd->root_group;
			bfq_group_set_parent(bfqg, parent);
		}
	}

	return bfqg;
}

static void bfq_bfqq_expire(struct bfq_data *bfqd,
			    struct bfq_queue *bfqq,
			    bool compensate,
			    enum bfqq_expiration reason);

/**
 * bfq_bfqq_move - migrate @bfqq to @bfqg.
 * @bfqd: queue descriptor.
 * @bfqq: the queue to move.
 * @bfqg: the group to move to.
 *
 * Move @bfqq to @bfqg, deactivating it from its old group and reactivating
 * it on the new one.  Avoid putting the entity on the old group idle tree.
 *
 * Must be called under the queue lock; the cgroup owning @bfqg must
 * not disappear (by now this just means that we are called under
 * rcu_read_lock()).
 */
static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
			  struct bfq_group *bfqg)
{
	struct bfq_entity *entity = &bfqq->entity;

	/* If bfqq is empty, then bfq_bfqq_expire also invokes
	 * bfq_del_bfqq_busy, thereby removing bfqq and its entity
	 * from data structures related to current group. Otherwise we
	 * need to remove bfqq explicitly with bfq_deactivate_bfqq, as
	 * we do below.
	 */
	if (bfqq == bfqd->in_service_queue)
		bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
				false, BFQQE_PREEMPTED);

	if (bfq_bfqq_busy(bfqq))
		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
	else if (entity->on_st)
		bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
	bfqg_put(bfqq_group(bfqq));

	/*
	 * Here we use a reference to bfqg.  We don't need a refcounter
	 * as the cgroup reference will not be dropped, so that its
	 * destroy() callback will not be invoked.
	 */
	entity->parent = bfqg->my_entity;
	entity->sched_data = &bfqg->sched_data;
	bfqg_get(bfqg);

	if (bfq_bfqq_busy(bfqq))
		bfq_activate_bfqq(bfqd, bfqq);

	if (!bfqd->in_service_queue && !bfqd->rq_in_driver)
		bfq_schedule_dispatch(bfqd);
}

/**
 * __bfq_bic_change_cgroup - move @bic to @cgroup.
 * @bfqd: the queue descriptor.
 * @bic: the bic to move.
 * @blkcg: the blk-cgroup to move to.
 *
 * Move bic to blkcg, assuming that bfqd->queue is locked; the caller
 * has to make sure that the reference to cgroup is valid across the call.
 *
 * NOTE: an alternative approach might have been to store the current
 * cgroup in bfqq and getting a reference to it, reducing the lookup
 * time here, at the price of slightly more complex code.
 */
static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
						struct bfq_io_cq *bic,
						struct blkcg *blkcg)
{
	struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0);
	struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1);
	struct bfq_group *bfqg;
	struct bfq_entity *entity;

	bfqg = bfq_find_set_group(bfqd, blkcg);

	if (unlikely(!bfqg))
		bfqg = bfqd->root_group;

	if (async_bfqq) {
		entity = &async_bfqq->entity;

		if (entity->sched_data != &bfqg->sched_data) {
			bic_set_bfqq(bic, NULL, 0);
			bfq_log_bfqq(bfqd, async_bfqq,
				     "bic_change_group: %p %d",
				     async_bfqq,
				     async_bfqq->ref);
			bfq_put_queue(async_bfqq);
		}
	}

	if (sync_bfqq) {
		entity = &sync_bfqq->entity;
		if (entity->sched_data != &bfqg->sched_data)
			bfq_bfqq_move(bfqd, sync_bfqq, bfqg);
	}

	return bfqg;
}

static void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
{
	struct bfq_data *bfqd = bic_to_bfqd(bic);
	struct bfq_group *bfqg = NULL;
	uint64_t serial_nr;

	rcu_read_lock();
	serial_nr = bio_blkcg(bio)->css.serial_nr;

	/*
	 * Check whether blkcg has changed.  The condition may trigger
	 * spuriously on a newly created cic but there's no harm.
	 */
	if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr))
		goto out;

	bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio));
	bic->blkcg_serial_nr = serial_nr;
out:
	rcu_read_unlock();
}

/**
 * bfq_flush_idle_tree - deactivate any entity on the idle tree of @st.
 * @st: the service tree being flushed.
 */
static void bfq_flush_idle_tree(struct bfq_service_tree *st)
{
	struct bfq_entity *entity = st->first_idle;

	for (; entity ; entity = st->first_idle)
		__bfq_deactivate_entity(entity, false);
}

/**
 * bfq_reparent_leaf_entity - move leaf entity to the root_group.
 * @bfqd: the device data structure with the root group.
 * @entity: the entity to move.
 */
static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
				     struct bfq_entity *entity)
{
	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);

	bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
}

/**
 * bfq_reparent_active_entities - move to the root group all active
 *                                entities.
 * @bfqd: the device data structure with the root group.
 * @bfqg: the group to move from.
 * @st: the service tree with the entities.
 *
 * Needs queue_lock to be taken and reference to be valid over the call.
 */
static void bfq_reparent_active_entities(struct bfq_data *bfqd,
					 struct bfq_group *bfqg,
					 struct bfq_service_tree *st)
{
	struct rb_root *active = &st->active;
	struct bfq_entity *entity = NULL;

	if (!RB_EMPTY_ROOT(&st->active))
		entity = bfq_entity_of(rb_first(active));

	for (; entity ; entity = bfq_entity_of(rb_first(active)))
		bfq_reparent_leaf_entity(bfqd, entity);

	if (bfqg->sched_data.in_service_entity)
		bfq_reparent_leaf_entity(bfqd,
			bfqg->sched_data.in_service_entity);
}

/**
 * bfq_pd_offline - deactivate the entity associated with @pd,
 *		    and reparent its children entities.
 * @pd: descriptor of the policy going offline.
 *
 * blkio already grabs the queue_lock for us, so no need to use
 * RCU-based magic
 */
static void bfq_pd_offline(struct blkg_policy_data *pd)
{
	struct bfq_service_tree *st;
	struct bfq_group *bfqg = pd_to_bfqg(pd);
	struct bfq_data *bfqd = bfqg->bfqd;
	struct bfq_entity *entity = bfqg->my_entity;
	unsigned long flags;
	int i;

	if (!entity) /* root group */
		return;

	spin_lock_irqsave(&bfqd->lock, flags);
	/*
	 * Empty all service_trees belonging to this group before
	 * deactivating the group itself.
	 */
	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) {
		st = bfqg->sched_data.service_tree + i;

		/*
		 * The idle tree may still contain bfq_queues belonging
		 * to exited task because they never migrated to a different
		 * cgroup from the one being destroyed now.  No one else
		 * can access them so it's safe to act without any lock.
		 */
		bfq_flush_idle_tree(st);

		/*
		 * It may happen that some queues are still active
		 * (busy) upon group destruction (if the corresponding
		 * processes have been forced to terminate). We move
		 * all the leaf entities corresponding to these queues
		 * to the root_group.
		 * Also, it may happen that the group has an entity
		 * in service, which is disconnected from the active
		 * tree: it must be moved, too.
		 * There is no need to put the sync queues, as the
		 * scheduler has taken no reference.
		 */
		bfq_reparent_active_entities(bfqd, bfqg, st);
	}

	__bfq_deactivate_entity(entity, false);
	bfq_put_async_queues(bfqd, bfqg);

	spin_unlock_irqrestore(&bfqd->lock, flags);
	/*
	 * @blkg is going offline and will be ignored by
	 * blkg_[rw]stat_recursive_sum().  Transfer stats to the parent so
	 * that they don't get lost.  If IOs complete after this point, the
	 * stats for them will be lost.  Oh well...
	 */
	bfqg_stats_xfer_dead(bfqg);
}

static int bfq_io_show_weight(struct seq_file *sf, void *v)
{
	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
	struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
	unsigned int val = 0;

	if (bfqgd)
		val = bfqgd->weight;

	seq_printf(sf, "%u\n", val);

	return 0;
}

static int bfq_io_set_weight_legacy(struct cgroup_subsys_state *css,
				    struct cftype *cftype,
				    u64 val)
{
	struct blkcg *blkcg = css_to_blkcg(css);
	struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
	struct blkcg_gq *blkg;
	int ret = -ERANGE;

	if (val < BFQ_MIN_WEIGHT || val > BFQ_MAX_WEIGHT)
		return ret;

	ret = 0;
	spin_lock_irq(&blkcg->lock);
	bfqgd->weight = (unsigned short)val;
	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
		struct bfq_group *bfqg = blkg_to_bfqg(blkg);

		if (!bfqg)
			continue;
		/*
		 * Setting the prio_changed flag of the entity
		 * to 1 with new_weight == weight would re-set
		 * the value of the weight to its ioprio mapping.
		 * Set the flag only if necessary.
		 */
		if ((unsigned short)val != bfqg->entity.new_weight) {
			bfqg->entity.new_weight = (unsigned short)val;
			/*
			 * Make sure that the above new value has been
			 * stored in bfqg->entity.new_weight before
			 * setting the prio_changed flag. In fact,
			 * this flag may be read asynchronously (in
			 * critical sections protected by a different
			 * lock than that held here), and finding this
			 * flag set may cause the execution of the code
			 * for updating parameters whose value may
			 * depend also on bfqg->entity.new_weight (in
			 * __bfq_entity_update_weight_prio).
			 * This barrier makes sure that the new value
			 * of bfqg->entity.new_weight is correctly
			 * seen in that code.
			 */
			smp_wmb();
			bfqg->entity.prio_changed = 1;
		}
	}
	spin_unlock_irq(&blkcg->lock);

	return ret;
}

static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
				 char *buf, size_t nbytes,
				 loff_t off)
{
	u64 weight;
	/* First unsigned long found in the file is used */
	int ret = kstrtoull(strim(buf), 0, &weight);

	if (ret)
		return ret;

	return bfq_io_set_weight_legacy(of_css(of), NULL, weight);
}

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

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

static u64 bfqg_prfill_stat_recursive(struct seq_file *sf,
				      struct blkg_policy_data *pd, int off)
{
	u64 sum = blkg_stat_recursive_sum(pd_to_blkg(pd),
					  &blkcg_policy_bfq, off);
	return __blkg_prfill_u64(sf, pd, sum);
}

static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf,
					struct blkg_policy_data *pd, int off)
{
	struct blkg_rwstat sum = blkg_rwstat_recursive_sum(pd_to_blkg(pd),
							   &blkcg_policy_bfq,
							   off);
	return __blkg_prfill_rwstat(sf, pd, &sum);
}

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

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

static u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd,
			       int off)
{
	u64 sum = blkg_rwstat_total(&pd->blkg->stat_bytes);

	return __blkg_prfill_u64(sf, pd, sum >> 9);
}

static int bfqg_print_stat_sectors(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  bfqg_prfill_sectors, &blkcg_policy_bfq, 0, false);
	return 0;
}

static u64 bfqg_prfill_sectors_recursive(struct seq_file *sf,
					 struct blkg_policy_data *pd, int off)
{
	struct blkg_rwstat tmp = blkg_rwstat_recursive_sum(pd->blkg, NULL,
					offsetof(struct blkcg_gq, stat_bytes));
	u64 sum = atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_READ]) +
		atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_WRITE]);

	return __blkg_prfill_u64(sf, pd, sum >> 9);
}

static int bfqg_print_stat_sectors_recursive(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  bfqg_prfill_sectors_recursive, &blkcg_policy_bfq, 0,
			  false);
	return 0;
}

static u64 bfqg_prfill_avg_queue_size(struct seq_file *sf,
				      struct blkg_policy_data *pd, int off)
{
	struct bfq_group *bfqg = pd_to_bfqg(pd);
	u64 samples = blkg_stat_read(&bfqg->stats.avg_queue_size_samples);
	u64 v = 0;

	if (samples) {
		v = blkg_stat_read(&bfqg->stats.avg_queue_size_sum);
		v = div64_u64(v, samples);
	}
	__blkg_prfill_u64(sf, pd, v);
	return 0;
}

/* print avg_queue_size */
static int bfqg_print_avg_queue_size(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  bfqg_prfill_avg_queue_size, &blkcg_policy_bfq,
			  0, false);
	return 0;
}

static struct bfq_group *
bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
{
	int ret;

	ret = blkcg_activate_policy(bfqd->queue, &blkcg_policy_bfq);
	if (ret)
		return NULL;

	return blkg_to_bfqg(bfqd->queue->root_blkg);
}

static struct cftype bfq_blkcg_legacy_files[] = {
	{
		.name = "bfq.weight",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = bfq_io_show_weight,
		.write_u64 = bfq_io_set_weight_legacy,
	},

	/* statistics, covers only the tasks in the bfqg */
	{
		.name = "bfq.time",
		.private = offsetof(struct bfq_group, stats.time),
		.seq_show = bfqg_print_stat,
	},
	{
		.name = "bfq.sectors",
		.seq_show = bfqg_print_stat_sectors,
	},
	{
		.name = "bfq.io_service_bytes",
		.private = (unsigned long)&blkcg_policy_bfq,
		.seq_show = blkg_print_stat_bytes,
	},
	{
		.name = "bfq.io_serviced",
		.private = (unsigned long)&blkcg_policy_bfq,
		.seq_show = blkg_print_stat_ios,
	},
	{
		.name = "bfq.io_service_time",
		.private = offsetof(struct bfq_group, stats.service_time),
		.seq_show = bfqg_print_rwstat,
	},
	{
		.name = "bfq.io_wait_time",
		.private = offsetof(struct bfq_group, stats.wait_time),
		.seq_show = bfqg_print_rwstat,
	},
	{
		.name = "bfq.io_merged",
		.private = offsetof(struct bfq_group, stats.merged),
		.seq_show = bfqg_print_rwstat,
	},
	{
		.name = "bfq.io_queued",
		.private = offsetof(struct bfq_group, stats.queued),
		.seq_show = bfqg_print_rwstat,
	},

	/* the same statictics which cover the bfqg and its descendants */
	{
		.name = "bfq.time_recursive",
		.private = offsetof(struct bfq_group, stats.time),
		.seq_show = bfqg_print_stat_recursive,
	},
	{
		.name = "bfq.sectors_recursive",
		.seq_show = bfqg_print_stat_sectors_recursive,
	},
	{
		.name = "bfq.io_service_bytes_recursive",
		.private = (unsigned long)&blkcg_policy_bfq,
		.seq_show = blkg_print_stat_bytes_recursive,
	},
	{
		.name = "bfq.io_serviced_recursive",
		.private = (unsigned long)&blkcg_policy_bfq,
		.seq_show = blkg_print_stat_ios_recursive,
	},
	{
		.name = "bfq.io_service_time_recursive",
		.private = offsetof(struct bfq_group, stats.service_time),
		.seq_show = bfqg_print_rwstat_recursive,
	},
	{
		.name = "bfq.io_wait_time_recursive",
		.private = offsetof(struct bfq_group, stats.wait_time),
		.seq_show = bfqg_print_rwstat_recursive,
	},
	{
		.name = "bfq.io_merged_recursive",
		.private = offsetof(struct bfq_group, stats.merged),
		.seq_show = bfqg_print_rwstat_recursive,
	},
	{
		.name = "bfq.io_queued_recursive",
		.private = offsetof(struct bfq_group, stats.queued),
		.seq_show = bfqg_print_rwstat_recursive,
	},
	{
		.name = "bfq.avg_queue_size",
		.seq_show = bfqg_print_avg_queue_size,
	},
	{
		.name = "bfq.group_wait_time",
		.private = offsetof(struct bfq_group, stats.group_wait_time),
		.seq_show = bfqg_print_stat,
	},
	{
		.name = "bfq.idle_time",
		.private = offsetof(struct bfq_group, stats.idle_time),
		.seq_show = bfqg_print_stat,
	},
	{
		.name = "bfq.empty_time",
		.private = offsetof(struct bfq_group, stats.empty_time),
		.seq_show = bfqg_print_stat,
	},
	{
		.name = "bfq.dequeue",
		.private = offsetof(struct bfq_group, stats.dequeue),
		.seq_show = bfqg_print_stat,
	},
	{ }	/* terminate */
};

static struct cftype bfq_blkg_files[] = {
	{
		.name = "bfq.weight",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = bfq_io_show_weight,
		.write = bfq_io_set_weight,
	},
	{} /* terminate */
};

#else	/* CONFIG_BFQ_GROUP_IOSCHED */

static inline void bfqg_stats_update_io_add(struct bfq_group *bfqg,
			struct bfq_queue *bfqq, unsigned int op) { }
static inline void
bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { }
static inline void
bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { }
static inline void bfqg_stats_update_completion(struct bfq_group *bfqg,
			uint64_t start_time, uint64_t io_start_time,
			unsigned int op) { }
static inline void
bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
				     struct bfq_group *curr_bfqg) { }
static inline void bfqg_stats_end_empty_time(struct bfqg_stats *stats) { }
static inline void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
static inline void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
static inline void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
static inline void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { }
static inline void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { }

static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
			  struct bfq_group *bfqg) {}

static void bfq_init_entity(struct bfq_entity *entity,
			    struct bfq_group *bfqg)
{
	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);

	entity->weight = entity->new_weight;
	entity->orig_weight = entity->new_weight;
	if (bfqq) {
		bfqq->ioprio = bfqq->new_ioprio;
		bfqq->ioprio_class = bfqq->new_ioprio_class;
	}
	entity->sched_data = &bfqg->sched_data;
}

static void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) {}

static struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
					    struct blkcg *blkcg)
{
	return bfqd->root_group;
}

static struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
{
	return bfqq->bfqd->root_group;
}

static struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd,
						    int node)
{
	struct bfq_group *bfqg;
	int i;

	bfqg = kmalloc_node(sizeof(*bfqg), GFP_KERNEL | __GFP_ZERO, node);
	if (!bfqg)
		return NULL;

	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
		bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;

	return bfqg;
}
#endif	/* CONFIG_BFQ_GROUP_IOSCHED */

#define bfq_class_idle(bfqq)	((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
#define bfq_class_rt(bfqq)	((bfqq)->ioprio_class == IOPRIO_CLASS_RT)

#define bfq_sample_valid(samples)	((samples) > 80)

/*
 * Lifted from AS - choose which of rq1 and rq2 that is best served now.
 * We choose the request that is closesr to the head right now.  Distance
 * behind the head is penalized and only allowed to a certain extent.
 */
static struct request *bfq_choose_req(struct bfq_data *bfqd,
				      struct request *rq1,
				      struct request *rq2,
				      sector_t last)
{
	sector_t s1, s2, d1 = 0, d2 = 0;
	unsigned long back_max;
#define BFQ_RQ1_WRAP	0x01 /* request 1 wraps */
#define BFQ_RQ2_WRAP	0x02 /* request 2 wraps */
	unsigned int wrap = 0; /* bit mask: requests behind the disk head? */

	if (!rq1 || rq1 == rq2)
		return rq2;
	if (!rq2)
		return rq1;

	if (rq_is_sync(rq1) && !rq_is_sync(rq2))
		return rq1;
	else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
		return rq2;
	if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META))
		return rq1;
	else if ((rq2->cmd_flags & REQ_META) && !(rq1->cmd_flags & REQ_META))
		return rq2;

	s1 = blk_rq_pos(rq1);
	s2 = blk_rq_pos(rq2);

	/*
	 * By definition, 1KiB is 2 sectors.
	 */
	back_max = bfqd->bfq_back_max * 2;

	/*
	 * Strict one way elevator _except_ in the case where we allow
	 * short backward seeks which are biased as twice the cost of a
	 * similar forward seek.
	 */
	if (s1 >= last)
		d1 = s1 - last;
	else if (s1 + back_max >= last)
		d1 = (last - s1) * bfqd->bfq_back_penalty;
	else
		wrap |= BFQ_RQ1_WRAP;

	if (s2 >= last)
		d2 = s2 - last;
	else if (s2 + back_max >= last)
		d2 = (last - s2) * bfqd->bfq_back_penalty;
	else
		wrap |= BFQ_RQ2_WRAP;

	/* Found required data */

	/*
	 * By doing switch() on the bit mask "wrap" we avoid having to
	 * check two variables for all permutations: --> faster!
	 */
	switch (wrap) {
	case 0: /* common case for CFQ: rq1 and rq2 not wrapped */
		if (d1 < d2)
			return rq1;
		else if (d2 < d1)
			return rq2;

		if (s1 >= s2)
			return rq1;
		else
			return rq2;

	case BFQ_RQ2_WRAP:
		return rq1;
	case BFQ_RQ1_WRAP:
		return rq2;
	case BFQ_RQ1_WRAP|BFQ_RQ2_WRAP: /* both rqs wrapped */
	default:
		/*
		 * Since both rqs are wrapped,
		 * start with the one that's further behind head
		 * (--> only *one* back seek required),
		 * since back seek takes more time than forward.
		 */
		if (s1 <= s2)
			return rq1;
		else
			return rq2;
	}
}

/*
 * Return expired entry, or NULL to just start from scratch in rbtree.
 */
static struct request *bfq_check_fifo(struct bfq_queue *bfqq,
				      struct request *last)
{
	struct request *rq;

	if (bfq_bfqq_fifo_expire(bfqq))
		return NULL;

	bfq_mark_bfqq_fifo_expire(bfqq);

	rq = rq_entry_fifo(bfqq->fifo.next);

	if (rq == last || ktime_get_ns() < rq->fifo_time)
		return NULL;

	bfq_log_bfqq(bfqq->bfqd, bfqq, "check_fifo: returned %p", rq);
	return rq;
}

static struct request *bfq_find_next_rq(struct bfq_data *bfqd,
					struct bfq_queue *bfqq,
					struct request *last)
{
	struct rb_node *rbnext = rb_next(&last->rb_node);
	struct rb_node *rbprev = rb_prev(&last->rb_node);
	struct request *next, *prev = NULL;

	/* Follow expired path, else get first next available. */
	next = bfq_check_fifo(bfqq, last);
	if (next)
		return next;

	if (rbprev)
		prev = rb_entry_rq(rbprev);

	if (rbnext)
		next = rb_entry_rq(rbnext);
	else {
		rbnext = rb_first(&bfqq->sort_list);
		if (rbnext && rbnext != &last->rb_node)
			next = rb_entry_rq(rbnext);
	}

	return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last));
}

static unsigned long bfq_serv_to_charge(struct request *rq,
					struct bfq_queue *bfqq)
{
	return blk_rq_sectors(rq);
}

/**
 * bfq_updated_next_req - update the queue after a new next_rq selection.
 * @bfqd: the device data the queue belongs to.
 * @bfqq: the queue to update.
 *
 * If the first request of a queue changes we make sure that the queue
 * has enough budget to serve at least its first request (if the
 * request has grown).  We do this because if the queue has not enough
 * budget for its first request, it has to go through two dispatch
 * rounds to actually get it dispatched.
 */
static void bfq_updated_next_req(struct bfq_data *bfqd,
				 struct bfq_queue *bfqq)
{
	struct bfq_entity *entity = &bfqq->entity;
	struct request *next_rq = bfqq->next_rq;
	unsigned long new_budget;

	if (!next_rq)
		return;

	if (bfqq == bfqd->in_service_queue)
		/*
		 * In order not to break guarantees, budgets cannot be
		 * changed after an entity has been selected.
		 */
		return;

	new_budget = max_t(unsigned long, bfqq->max_budget,
			   bfq_serv_to_charge(next_rq, bfqq));
	if (entity->budget != new_budget) {
		entity->budget = new_budget;
		bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu",
					 new_budget);
		bfq_requeue_bfqq(bfqd, bfqq);
	}
}

static int bfq_bfqq_budget_left(struct bfq_queue *bfqq)
{
	struct bfq_entity *entity = &bfqq->entity;

	return entity->budget - entity->service;
}

/*
 * If enough samples have been computed, return the current max budget
 * stored in bfqd, which is dynamically updated according to the
 * estimated disk peak rate; otherwise return the default max budget
 */
static int bfq_max_budget(struct bfq_data *bfqd)
{
	if (bfqd->budgets_assigned < bfq_stats_min_budgets)
		return bfq_default_max_budget;
	else
		return bfqd->bfq_max_budget;
}

/*
 * Return min budget, which is a fraction of the current or default
 * max budget (trying with 1/32)
 */
static int bfq_min_budget(struct bfq_data *bfqd)
{
	if (bfqd->budgets_assigned < bfq_stats_min_budgets)
		return bfq_default_max_budget / 32;
	else
		return bfqd->bfq_max_budget / 32;
}

static void bfq_bfqq_expire(struct bfq_data *bfqd,
			    struct bfq_queue *bfqq,
			    bool compensate,
			    enum bfqq_expiration reason);

/*
 * The next function, invoked after the input queue bfqq switches from
 * idle to busy, updates the budget of bfqq. The function also tells
 * whether the in-service queue should be expired, by returning
 * true. The purpose of expiring the in-service queue is to give bfqq
 * the chance to possibly preempt the in-service queue, and the reason
 * for preempting the in-service queue is to achieve the following
 * goal: guarantee to bfqq its reserved bandwidth even if bfqq has
 * expired because it has remained idle.
 *
 * In particular, bfqq may have expired for one of the following two
 * reasons:
 *
 * - BFQQE_NO_MORE_REQUESTS bfqq did not enjoy any device idling
 *   and did not make it to issue a new request before its last
 *   request was served;
 *
 * - BFQQE_TOO_IDLE bfqq did enjoy device idling, but did not issue
 *   a new request before the expiration of the idling-time.
 *
 * Even if bfqq has expired for one of the above reasons, the process
 * associated with the queue may be however issuing requests greedily,
 * and thus be sensitive to the bandwidth it receives (bfqq may have
 * remained idle for other reasons: CPU high load, bfqq not enjoying
 * idling, I/O throttling somewhere in the path from the process to
 * the I/O scheduler, ...). But if, after every expiration for one of
 * the above two reasons, bfqq has to wait for the service of at least
 * one full budget of another queue before being served again, then
 * bfqq is likely to get a much lower bandwidth or resource time than
 * its reserved ones. To address this issue, two countermeasures need
 * to be taken.
 *
 * First, the budget and the timestamps of bfqq need to be updated in
 * a special way on bfqq reactivation: they need to be updated as if
 * bfqq did not remain idle and did not expire. In fact, if they are
 * computed as if bfqq expired and remained idle until reactivation,
 * then the process associated with bfqq is treated as if, instead of
 * being greedy, it stopped issuing requests when bfqq remained idle,
 * and restarts issuing requests only on this reactivation. In other
 * words, the scheduler does not help the process recover the "service
 * hole" between bfqq expiration and reactivation. As a consequence,
 * the process receives a lower bandwidth than its reserved one. In
 * contrast, to recover this hole, the budget must be updated as if
 * bfqq was not expired at all before this reactivation, i.e., it must
 * be set to the value of the remaining budget when bfqq was
 * expired. Along the same line, timestamps need to be assigned the
 * value they had the last time bfqq was selected for service, i.e.,
 * before last expiration. Thus timestamps need to be back-shifted
 * with respect to their normal computation (see [1] for more details
 * on this tricky aspect).
 *
 * Secondly, to allow the process to recover the hole, the in-service
 * queue must be expired too, to give bfqq the chance to preempt it
 * immediately. In fact, if bfqq has to wait for a full budget of the
 * in-service queue to be completed, then it may become impossible to
 * let the process recover the hole, even if the back-shifted
 * timestamps of bfqq are lower than those of the in-service queue. If
 * this happens for most or all of the holes, then the process may not
 * receive its reserved bandwidth. In this respect, it is worth noting
 * that, being the service of outstanding requests unpreemptible, a
 * little fraction of the holes may however be unrecoverable, thereby
 * causing a little loss of bandwidth.
 *
 * The last important point is detecting whether bfqq does need this
 * bandwidth recovery. In this respect, the next function deems the
 * process associated with bfqq greedy, and thus allows it to recover
 * the hole, if: 1) the process is waiting for the arrival of a new
 * request (which implies that bfqq expired for one of the above two
 * reasons), and 2) such a request has arrived soon. The first
 * condition is controlled through the flag non_blocking_wait_rq,
 * while the second through the flag arrived_in_time. If both
 * conditions hold, then the function computes the budget in the
 * above-described special way, and signals that the in-service queue
 * should be expired. Timestamp back-shifting is done later in
 * __bfq_activate_entity.
 */
static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
						struct bfq_queue *bfqq,
						bool arrived_in_time)
{
	struct bfq_entity *entity = &bfqq->entity;

	if (bfq_bfqq_non_blocking_wait_rq(bfqq) && arrived_in_time) {
		/*
		 * We do not clear the flag non_blocking_wait_rq here, as
		 * the latter is used in bfq_activate_bfqq to signal
		 * that timestamps need to be back-shifted (and is
		 * cleared right after).
		 */

		/*
		 * In next assignment we rely on that either
		 * entity->service or entity->budget are not updated
		 * on expiration if bfqq is empty (see
		 * __bfq_bfqq_recalc_budget). Thus both quantities
		 * remain unchanged after such an expiration, and the
		 * following statement therefore assigns to
		 * entity->budget the remaining budget on such an
		 * expiration. For clarity, entity->service is not
		 * updated on expiration in any case, and, in normal
		 * operation, is reset only when bfqq is selected for
		 * service (see bfq_get_next_queue).
		 */
		entity->budget = min_t(unsigned long,
				       bfq_bfqq_budget_left(bfqq),
				       bfqq->max_budget);

		return true;
	}

	entity->budget = max_t(unsigned long, bfqq->max_budget,
			       bfq_serv_to_charge(bfqq->next_rq, bfqq));
	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
	return false;
}

static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
					     struct bfq_queue *bfqq,
					     struct request *rq)
{
	bool bfqq_wants_to_preempt,
		/*
		 * See the comments on
		 * bfq_bfqq_update_budg_for_activation for
		 * details on the usage of the next variable.
		 */
		arrived_in_time =  ktime_get_ns() <=
			bfqq->ttime.last_end_request +
			bfqd->bfq_slice_idle * 3;

	bfqg_stats_update_io_add(bfqq_group(RQ_BFQQ(rq)), bfqq, rq->cmd_flags);

	/*
	 * Update budget and check whether bfqq may want to preempt
	 * the in-service queue.
	 */
	bfqq_wants_to_preempt =
		bfq_bfqq_update_budg_for_activation(bfqd, bfqq,
						    arrived_in_time);

	if (!bfq_bfqq_IO_bound(bfqq)) {
		if (arrived_in_time) {
			bfqq->requests_within_timer++;
			if (bfqq->requests_within_timer >=
			    bfqd->bfq_requests_within_timer)
				bfq_mark_bfqq_IO_bound(bfqq);
		} else
			bfqq->requests_within_timer = 0;
	}

	bfq_add_bfqq_busy(bfqd, bfqq);

	/*
	 * Expire in-service queue only if preemption may be needed
	 * for guarantees. In this respect, the function
	 * next_queue_may_preempt just checks a simple, necessary
	 * condition, and not a sufficient condition based on
	 * timestamps. In fact, for the latter condition to be
	 * evaluated, timestamps would need first to be updated, and
	 * this operation is quite costly (see the comments on the
	 * function bfq_bfqq_update_budg_for_activation).
	 */
	if (bfqd->in_service_queue && bfqq_wants_to_preempt &&
	    next_queue_may_preempt(bfqd))
		bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
				false, BFQQE_PREEMPTED);
}

static void bfq_add_request(struct request *rq)
{
	struct bfq_queue *bfqq = RQ_BFQQ(rq);
	struct bfq_data *bfqd = bfqq->bfqd;
	struct request *next_rq, *prev;

	bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
	bfqq->queued[rq_is_sync(rq)]++;
	bfqd->queued++;

	elv_rb_add(&bfqq->sort_list, rq);

	/*
	 * Check if this request is a better next-serve candidate.
	 */
	prev = bfqq->next_rq;
	next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position);
	bfqq->next_rq = next_rq;

	if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */
		bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, rq);
	else if (prev != bfqq->next_rq)
		bfq_updated_next_req(bfqd, bfqq);
}

static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
					  struct bio *bio,
					  struct request_queue *q)
{
	struct bfq_queue *bfqq = bfqd->bio_bfqq;


	if (bfqq)
		return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio));

	return NULL;
}

#if 0 /* Still not clear if we can do without next two functions */
static void bfq_activate_request(struct request_queue *q, struct request *rq)
{
	struct bfq_data *bfqd = q->elevator->elevator_data;

	bfqd->rq_in_driver++;
	bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
	bfq_log(bfqd, "activate_request: new bfqd->last_position %llu",
		(unsigned long long)bfqd->last_position);
}

static void bfq_deactivate_request(struct request_queue *q, struct request *rq)
{
	struct bfq_data *bfqd = q->elevator->elevator_data;

	bfqd->rq_in_driver--;
}
#endif

static void bfq_remove_request(struct request_queue *q,
			       struct request *rq)
{
	struct bfq_queue *bfqq = RQ_BFQQ(rq);
	struct bfq_data *bfqd = bfqq->bfqd;
	const int sync = rq_is_sync(rq);

	if (bfqq->next_rq == rq) {
		bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq);
		bfq_updated_next_req(bfqd, bfqq);
	}

	if (rq->queuelist.prev != &rq->queuelist)
		list_del_init(&rq->queuelist);
	bfqq->queued[sync]--;
	bfqd->queued--;
	elv_rb_del(&bfqq->sort_list, rq);

	elv_rqhash_del(q, rq);
	if (q->last_merge == rq)
		q->last_merge = NULL;

	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
		bfqq->next_rq = NULL;

		if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) {
			bfq_del_bfqq_busy(bfqd, bfqq, false);
			/*
			 * bfqq emptied. In normal operation, when
			 * bfqq is empty, bfqq->entity.service and
			 * bfqq->entity.budget must contain,
			 * respectively, the service received and the
			 * budget used last time bfqq emptied. These
			 * facts do not hold in this case, as at least
			 * this last removal occurred while bfqq is
			 * not in service. To avoid inconsistencies,
			 * reset both bfqq->entity.service and
			 * bfqq->entity.budget, if bfqq has still a
			 * process that may issue I/O requests to it.
			 */
			bfqq->entity.budget = bfqq->entity.service = 0;
		}
	}

	if (rq->cmd_flags & REQ_META)
		bfqq->meta_pending--;

	bfqg_stats_update_io_remove(bfqq_group(bfqq), rq->cmd_flags);
}

static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
{
	struct request_queue *q = hctx->queue;
	struct bfq_data *bfqd = q->elevator->elevator_data;
	struct request *free = NULL;
	/*
	 * bfq_bic_lookup grabs the queue_lock: invoke it now and
	 * store its return value for later use, to avoid nesting
	 * queue_lock inside the bfqd->lock. We assume that the bic
	 * returned by bfq_bic_lookup does not go away before
	 * bfqd->lock is taken.
	 */
	struct bfq_io_cq *bic = bfq_bic_lookup(bfqd, current->io_context, q);
	bool ret;

	spin_lock_irq(&bfqd->lock);

	if (bic)
		bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf));
	else
		bfqd->bio_bfqq = NULL;
	bfqd->bio_bic = bic;

	ret = blk_mq_sched_try_merge(q, bio, &free);

	if (free)
		blk_mq_free_request(free);
	spin_unlock_irq(&bfqd->lock);

	return ret;
}

static int bfq_request_merge(struct request_queue *q, struct request **req,
			     struct bio *bio)
{
	struct bfq_data *bfqd = q->elevator->elevator_data;
	struct request *__rq;

	__rq = bfq_find_rq_fmerge(bfqd, bio, q);
	if (__rq && elv_bio_merge_ok(__rq, bio)) {
		*req = __rq;
		return ELEVATOR_FRONT_MERGE;
	}

	return ELEVATOR_NO_MERGE;
}

static void bfq_request_merged(struct request_queue *q, struct request *req,
			       enum elv_merge type)
{
	if (type == ELEVATOR_FRONT_MERGE &&
	    rb_prev(&req->rb_node) &&
	    blk_rq_pos(req) <
	    blk_rq_pos(container_of(rb_prev(&req->rb_node),
				    struct request, rb_node))) {
		struct bfq_queue *bfqq = RQ_BFQQ(req);
		struct bfq_data *bfqd = bfqq->bfqd;
		struct request *prev, *next_rq;

		/* Reposition request in its sort_list */
		elv_rb_del(&bfqq->sort_list, req);
		elv_rb_add(&bfqq->sort_list, req);

		/* Choose next request to be served for bfqq */
		prev = bfqq->next_rq;
		next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req,
					 bfqd->last_position);
		bfqq->next_rq = next_rq;
		/*
		 * If next_rq changes, update the queue's budget to fit
		 * the new request.
		 */
		if (prev != bfqq->next_rq)
			bfq_updated_next_req(bfqd, bfqq);
	}
}

static void bfq_requests_merged(struct request_queue *q, struct request *rq,
				struct request *next)
{
	struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next);

	if (!RB_EMPTY_NODE(&rq->rb_node))
		goto end;
	spin_lock_irq(&bfqq->bfqd->lock);

	/*
	 * If next and rq belong to the same bfq_queue and next is older
	 * than rq, then reposition rq in the fifo (by substituting next
	 * with rq). Otherwise, if next and rq belong to different
	 * bfq_queues, never reposition rq: in fact, we would have to
	 * reposition it with respect to next's position in its own fifo,
	 * which would most certainly be too expensive with respect to
	 * the benefits.
	 */
	if (bfqq == next_bfqq &&
	    !list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
	    next->fifo_time < rq->fifo_time) {
		list_del_init(&rq->queuelist);
		list_replace_init(&next->queuelist, &rq->queuelist);
		rq->fifo_time = next->fifo_time;
	}

	if (bfqq->next_rq == next)
		bfqq->next_rq = rq;

	bfq_remove_request(q, next);

	spin_unlock_irq(&bfqq->bfqd->lock);
end:
	bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
}

static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
				struct bio *bio)
{
	struct bfq_data *bfqd = q->elevator->elevator_data;
	bool is_sync = op_is_sync(bio->bi_opf);
	struct bfq_queue *bfqq = bfqd->bio_bfqq;

	/*
	 * Disallow merge of a sync bio into an async request.
	 */
	if (is_sync && !rq_is_sync(rq))
		return false;

	/*
	 * Lookup the bfqq that this bio will be queued with. Allow
	 * merge only if rq is queued there.
	 */
	if (!bfqq)
		return false;

	return bfqq == RQ_BFQQ(rq);
}

static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
				       struct bfq_queue *bfqq)
{
	if (bfqq) {
		bfqg_stats_update_avg_queue_size(bfqq_group(bfqq));
		bfq_mark_bfqq_budget_new(bfqq);
		bfq_clear_bfqq_fifo_expire(bfqq);

		bfqd->budgets_assigned = (bfqd->budgets_assigned * 7 + 256) / 8;

		bfq_log_bfqq(bfqd, bfqq,
			     "set_in_service_queue, cur-budget = %d",
			     bfqq->entity.budget);
	}

	bfqd->in_service_queue = bfqq;
}

/*
 * Get and set a new queue for service.
 */
static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd)
{
	struct bfq_queue *bfqq = bfq_get_next_queue(bfqd);

	__bfq_set_in_service_queue(bfqd, bfqq);
	return bfqq;
}

static void bfq_arm_slice_timer(struct bfq_data *bfqd)
{
	struct bfq_queue *bfqq = bfqd->in_service_queue;
	struct bfq_io_cq *bic;
	u32 sl;

	/* Processes have exited, don't wait. */
	bic = bfqd->in_service_bic;
	if (!bic || atomic_read(&bic->icq.ioc->active_ref) == 0)
		return;

	bfq_mark_bfqq_wait_request(bfqq);

	/*
	 * We don't want to idle for seeks, but we do want to allow
	 * fair distribution of slice time for a process doing back-to-back
	 * seeks. So allow a little bit of time for him to submit a new rq.
	 */
	sl = bfqd->bfq_slice_idle;
	/*
	 * Grant only minimum idle time if the queue is seeky.
	 */
	if (BFQQ_SEEKY(bfqq))
		sl = min_t(u64, sl, BFQ_MIN_TT);

	bfqd->last_idling_start = ktime_get();
	hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),
		      HRTIMER_MODE_REL);
	bfqg_stats_set_start_idle_time(bfqq_group(bfqq));
}

/*
 * Set the maximum time for the in-service queue to consume its
 * budget. This prevents seeky processes from lowering the disk
 * throughput (always guaranteed with a time slice scheme as in CFQ).
 */
static void bfq_set_budget_timeout(struct bfq_data *bfqd)
{
	struct bfq_queue *bfqq = bfqd->in_service_queue;
	unsigned int timeout_coeff = bfqq->entity.weight /
				     bfqq->entity.orig_weight;

	bfqd->last_budget_start = ktime_get();

	bfq_clear_bfqq_budget_new(bfqq);
	bfqq->budget_timeout = jiffies +
		bfqd->bfq_timeout * timeout_coeff;

	bfq_log_bfqq(bfqd, bfqq, "set budget_timeout %u",
		jiffies_to_msecs(bfqd->bfq_timeout * timeout_coeff));
}

/*
 * Remove request from internal lists.
 */
static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
{
	struct bfq_queue *bfqq = RQ_BFQQ(rq);

	/*
	 * For consistency, the next instruction should have been
	 * executed after removing the request from the queue and
	 * dispatching it.  We execute instead this instruction before
	 * bfq_remove_request() (and hence introduce a temporary
	 * inconsistency), for efficiency.  In fact, should this
	 * dispatch occur for a non in-service bfqq, this anticipated
	 * increment prevents two counters related to bfqq->dispatched
	 * from risking to be, first, uselessly decremented, and then
	 * incremented again when the (new) value of bfqq->dispatched
	 * happens to be taken into account.
	 */
	bfqq->dispatched++;

	bfq_remove_request(q, rq);
}

static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
	if (RB_EMPTY_ROOT(&bfqq->sort_list))
		bfq_del_bfqq_busy(bfqd, bfqq, true);
	else
		bfq_requeue_bfqq(bfqd, bfqq);

	/*
	 * All in-service entities must have been properly deactivated
	 * or requeued before executing the next function, which
	 * resets all in-service entites as no more in service.
	 */
	__bfq_bfqd_reset_in_service(bfqd);
}

/**
 * __bfq_bfqq_recalc_budget - try to adapt the budget to the @bfqq behavior.
 * @bfqd: device data.
 * @bfqq: queue to update.
 * @reason: reason for expiration.
 *
 * Handle the feedback on @bfqq budget at queue expiration.
 * See the body for detailed comments.
 */
static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd,
				     struct bfq_queue *bfqq,
				     enum bfqq_expiration reason)
{
	struct request *next_rq;
	int budget, min_budget;

	budget = bfqq->max_budget;
	min_budget = bfq_min_budget(bfqd);

	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last budg %d, budg left %d",
		bfqq->entity.budget, bfq_bfqq_budget_left(bfqq));
	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last max_budg %d, min budg %d",
		budget, bfq_min_budget(bfqd));
	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: sync %d, seeky %d",
		bfq_bfqq_sync(bfqq), BFQQ_SEEKY(bfqd->in_service_queue));

	if (bfq_bfqq_sync(bfqq)) {
		switch (reason) {
		/*
		 * Caveat: in all the following cases we trade latency
		 * for throughput.
		 */
		case BFQQE_TOO_IDLE:
			/*
			 * This is the only case where we may reduce
			 * the budget: if there is no request of the
			 * process still waiting for completion, then
			 * we assume (tentatively) that the timer has
			 * expired because the batch of requests of
			 * the process could have been served with a
			 * smaller budget.  Hence, betting that
			 * process will behave in the same way when it
			 * becomes backlogged again, we reduce its
			 * next budget.  As long as we guess right,
			 * this budget cut reduces the latency
			 * experienced by the process.
			 *
			 * However, if there are still outstanding
			 * requests, then the process may have not yet
			 * issued its next request just because it is
			 * still waiting for the completion of some of
			 * the still outstanding ones.  So in this
			 * subcase we do not reduce its budget, on the
			 * contrary we increase it to possibly boost
			 * the throughput, as discussed in the
			 * comments to the BUDGET_TIMEOUT case.
			 */
			if (bfqq->dispatched > 0) /* still outstanding reqs */
				budget = min(budget * 2, bfqd->bfq_max_budget);
			else {
				if (budget > 5 * min_budget)
					budget -= 4 * min_budget;
				else
					budget = min_budget;
			}
			break;
		case BFQQE_BUDGET_TIMEOUT:
			/*
			 * We double the budget here because it gives
			 * the chance to boost the throughput if this
			 * is not a seeky process (and has bumped into
			 * this timeout because of, e.g., ZBR).
			 */
			budget = min(budget * 2, bfqd->bfq_max_budget);
			break;
		case BFQQE_BUDGET_EXHAUSTED:
			/*
			 * The process still has backlog, and did not
			 * let either the budget timeout or the disk
			 * idling timeout expire. Hence it is not
			 * seeky, has a short thinktime and may be
			 * happy with a higher budget too. So
			 * definitely increase the budget of this good
			 * candidate to boost the disk throughput.
			 */
			budget = min(budget * 4, bfqd->bfq_max_budget);
			break;
		case BFQQE_NO_MORE_REQUESTS:
			/*
			 * For queues that expire for this reason, it
			 * is particularly important to keep the
			 * budget close to the actual service they
			 * need. Doing so reduces the timestamp
			 * misalignment problem described in the
			 * comments in the body of
			 * __bfq_activate_entity. In fact, suppose
			 * that a queue systematically expires for
			 * BFQQE_NO_MORE_REQUESTS and presents a
			 * new request in time to enjoy timestamp
			 * back-shifting. The larger the budget of the
			 * queue is with respect to the service the
			 * queue actually requests in each service
			 * slot, the more times the queue can be
			 * reactivated with the same virtual finish
			 * time. It follows that, even if this finish
			 * time is pushed to the system virtual time
			 * to reduce the consequent timestamp
			 * misalignment, the queue unjustly enjoys for
			 * many re-activations a lower finish time
			 * than all newly activated queues.
			 *
			 * The service needed by bfqq is measured
			 * quite precisely by bfqq->entity.service.
			 * Since bfqq does not enjoy device idling,
			 * bfqq->entity.service is equal to the number
			 * of sectors that the process associated with
			 * bfqq requested to read/write before waiting
			 * for request completions, or blocking for
			 * other reasons.
			 */
			budget = max_t(int, bfqq->entity.service, min_budget);
			break;
		default:
			return;
		}
	} else {
		/*
		 * Async queues get always the maximum possible
		 * budget, as for them we do not care about latency
		 * (in addition, their ability to dispatch is limited
		 * by the charging factor).
		 */
		budget = bfqd->bfq_max_budget;
	}

	bfqq->max_budget = budget;

	if (bfqd->budgets_assigned >= bfq_stats_min_budgets &&
	    !bfqd->bfq_user_max_budget)
		bfqq->max_budget = min(bfqq->max_budget, bfqd->bfq_max_budget);

	/*
	 * If there is still backlog, then assign a new budget, making
	 * sure that it is large enough for the next request.  Since
	 * the finish time of bfqq must be kept in sync with the
	 * budget, be sure to call __bfq_bfqq_expire() *after* this
	 * update.
	 *
	 * If there is no backlog, then no need to update the budget;
	 * it will be updated on the arrival of a new request.
	 */
	next_rq = bfqq->next_rq;
	if (next_rq)
		bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget,
					    bfq_serv_to_charge(next_rq, bfqq));

	bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %d",
			next_rq ? blk_rq_sectors(next_rq) : 0,
			bfqq->entity.budget);
}

static unsigned long bfq_calc_max_budget(u64 peak_rate, u64 timeout)
{
	unsigned long max_budget;

	/*
	 * The max_budget calculated when autotuning is equal to the
	 * amount of sectors transferred in timeout at the estimated
	 * peak rate. To get this value, peak_rate is, first,
	 * multiplied by 1000, because timeout is measured in ms,
	 * while peak_rate is measured in sectors/usecs. Then the
	 * result of this multiplication is right-shifted by
	 * BFQ_RATE_SHIFT, because peak_rate is equal to the value of
	 * the peak rate left-shifted by BFQ_RATE_SHIFT.
	 */
	max_budget = (unsigned long)(peak_rate * 1000 *
				     timeout >> BFQ_RATE_SHIFT);

	return max_budget;
}

/*
 * In addition to updating the peak rate, checks whether the process
 * is "slow", and returns 1 if so. This slow flag is used, in addition
 * to the budget timeout, to reduce the amount of service provided to
 * seeky processes, and hence reduce their chances to lower the
 * throughput. See the code for more details.
 */
static bool bfq_update_peak_rate(struct bfq_data *bfqd, struct bfq_queue *bfqq,
				 bool compensate)
{
	u64 bw, usecs, expected, timeout;
	ktime_t delta;
	int update = 0;

	if (!bfq_bfqq_sync(bfqq) || bfq_bfqq_budget_new(bfqq))
		return false;

	if (compensate)
		delta = bfqd->last_idling_start;
	else
		delta = ktime_get();
	delta = ktime_sub(delta, bfqd->last_budget_start);
	usecs = ktime_to_us(delta);

	/* don't use too short time intervals */
	if (usecs < 1000)
		return false;

	/*
	 * Calculate the bandwidth for the last slice.  We use a 64 bit
	 * value to store the peak rate, in sectors per usec in fixed
	 * point math.  We do so to have enough precision in the estimate
	 * and to avoid overflows.
	 */
	bw = (u64)bfqq->entity.service << BFQ_RATE_SHIFT;
	do_div(bw, (unsigned long)usecs);

	timeout = jiffies_to_msecs(bfqd->bfq_timeout);

	/*
	 * Use only long (> 20ms) intervals to filter out spikes for
	 * the peak rate estimation.
	 */
	if (usecs > 20000) {
		if (bw > bfqd->peak_rate) {
			bfqd->peak_rate = bw;
			update = 1;
			bfq_log(bfqd, "new peak_rate=%llu", bw);
		}

		update |= bfqd->peak_rate_samples == BFQ_PEAK_RATE_SAMPLES - 1;

		if (bfqd->peak_rate_samples < BFQ_PEAK_RATE_SAMPLES)
			bfqd->peak_rate_samples++;

		if (bfqd->peak_rate_samples == BFQ_PEAK_RATE_SAMPLES &&
		    update && bfqd->bfq_user_max_budget == 0) {
			bfqd->bfq_max_budget =
				bfq_calc_max_budget(bfqd->peak_rate,
						    timeout);
			bfq_log(bfqd, "new max_budget=%d",
				bfqd->bfq_max_budget);
		}
	}

	/*
	 * A process is considered ``slow'' (i.e., seeky, so that we
	 * cannot treat it fairly in the service domain, as it would
	 * slow down too much the other processes) if, when a slice
	 * ends for whatever reason, it has received service at a
	 * rate that would not be high enough to complete the budget
	 * before the budget timeout expiration.
	 */
	expected = bw * 1000 * timeout >> BFQ_RATE_SHIFT;

	/*
	 * Caveat: processes doing IO in the slower disk zones will
	 * tend to be slow(er) even if not seeky. And the estimated
	 * peak rate will actually be an average over the disk
	 * surface. Hence, to not be too harsh with unlucky processes,
	 * we keep a budget/3 margin of safety before declaring a
	 * process slow.
	 */
	return expected > (4 * bfqq->entity.budget) / 3;
}

/*
 * Return the farthest past time instant according to jiffies
 * macros.
 */
static unsigned long bfq_smallest_from_now(void)
{
	return jiffies - MAX_JIFFY_OFFSET;
}

/**
 * bfq_bfqq_expire - expire a queue.
 * @bfqd: device owning the queue.
 * @bfqq: the queue to expire.
 * @compensate: if true, compensate for the time spent idling.
 * @reason: the reason causing the expiration.
 *
 *
 * If the process associated with the queue is slow (i.e., seeky), or
 * in case of budget timeout, or, finally, if it is async, we
 * artificially charge it an entire budget (independently of the
 * actual service it received). As a consequence, the queue will get
 * higher timestamps than the correct ones upon reactivation, and
 * hence it will be rescheduled as if it had received more service
 * than what it actually received. In the end, this class of processes
 * will receive less service in proportion to how slowly they consume
 * their budgets (and hence how seriously they tend to lower the
 * throughput).
 *
 * In contrast, when a queue expires because it has been idling for
 * too much or because it exhausted its budget, we do not touch the
 * amount of service it has received. Hence when the queue will be
 * reactivated and its timestamps updated, the latter will be in sync
 * with the actual service received by the queue until expiration.
 *
 * Charging a full budget to the first type of queues and the exact
 * service to the others has the effect of using the WF2Q+ policy to
 * schedule the former on a timeslice basis, without violating the
 * service domain guarantees of the latter.
 */
static void bfq_bfqq_expire(struct bfq_data *bfqd,
			    struct bfq_queue *bfqq,
			    bool compensate,
			    enum bfqq_expiration reason)
{
	bool slow;
	int ref;

	/*
	 * Update device peak rate for autotuning and check whether the
	 * process is slow (see bfq_update_peak_rate).
	 */
	slow = bfq_update_peak_rate(bfqd, bfqq, compensate);

	/*
	 * As above explained, 'punish' slow (i.e., seeky), timed-out
	 * and async queues, to favor sequential sync workloads.
	 */
	if (slow || reason == BFQQE_BUDGET_TIMEOUT)
		bfq_bfqq_charge_full_budget(bfqq);

	if (reason == BFQQE_TOO_IDLE &&
	    bfqq->entity.service <= 2 * bfqq->entity.budget / 10)
		bfq_clear_bfqq_IO_bound(bfqq);

	bfq_log_bfqq(bfqd, bfqq,
		"expire (%d, slow %d, num_disp %d, idle_win %d)", reason,
		slow, bfqq->dispatched, bfq_bfqq_idle_window(bfqq));

	/*
	 * Increase, decrease or leave budget unchanged according to
	 * reason.
	 */
	__bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
	ref = bfqq->ref;
	__bfq_bfqq_expire(bfqd, bfqq);

	/* mark bfqq as waiting a request only if a bic still points to it */
	if (ref > 1 && !bfq_bfqq_busy(bfqq) &&
	    reason != BFQQE_BUDGET_TIMEOUT &&
	    reason != BFQQE_BUDGET_EXHAUSTED)
		bfq_mark_bfqq_non_blocking_wait_rq(bfqq);
}

/*
 * Budget timeout is not implemented through a dedicated timer, but
 * just checked on request arrivals and completions, as well as on
 * idle timer expirations.
 */
static bool bfq_bfqq_budget_timeout(struct bfq_queue *bfqq)
{
	if (bfq_bfqq_budget_new(bfqq) ||
	    time_is_after_jiffies(bfqq->budget_timeout))
		return false;
	return true;
}

/*
 * If we expire a queue that is actively waiting (i.e., with the
 * device idled) for the arrival of a new request, then we may incur
 * the timestamp misalignment problem described in the body of the
 * function __bfq_activate_entity. Hence we return true only if this
 * condition does not hold, or if the queue is slow enough to deserve
 * only to be kicked off for preserving a high throughput.
 */
static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
{
	bfq_log_bfqq(bfqq->bfqd, bfqq,
		"may_budget_timeout: wait_request %d left %d timeout %d",
		bfq_bfqq_wait_request(bfqq),
			bfq_bfqq_budget_left(bfqq) >=  bfqq->entity.budget / 3,
		bfq_bfqq_budget_timeout(bfqq));

	return (!bfq_bfqq_wait_request(bfqq) ||
		bfq_bfqq_budget_left(bfqq) >=  bfqq->entity.budget / 3)
		&&
		bfq_bfqq_budget_timeout(bfqq);
}

/*
 * For a queue that becomes empty, device idling is allowed only if
 * this function returns true for the queue. And this function returns
 * true only if idling is beneficial for throughput.
 */
static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
{
	struct bfq_data *bfqd = bfqq->bfqd;
	bool idling_boosts_thr;

	if (bfqd->strict_guarantees)
		return true;

	/*
	 * The value of the next variable is computed considering that
	 * idling is usually beneficial for the throughput if:
	 * (a) the device is not NCQ-capable, or
	 * (b) regardless of the presence of NCQ, the request pattern
	 *     for bfqq is I/O-bound (possible throughput losses
	 *     caused by granting idling to seeky queues are mitigated
	 *     by the fact that, in all scenarios where boosting
	 *     throughput is the best thing to do, i.e., in all
	 *     symmetric scenarios, only a minimal idle time is
	 *     allowed to seeky queues).
	 */
	idling_boosts_thr = !bfqd->hw_tag || bfq_bfqq_IO_bound(bfqq);

	/*
	 * We have now the components we need to compute the return
	 * value of the function, which is true only if both the
	 * following conditions hold:
	 * 1) bfqq is sync, because idling make sense only for sync queues;
	 * 2) idling boosts the throughput.
	 */
	return bfq_bfqq_sync(bfqq) && idling_boosts_thr;
}

/*
 * If the in-service queue is empty but the function bfq_bfqq_may_idle
 * returns true, then:
 * 1) the queue must remain in service and cannot be expired, and
 * 2) the device must be idled to wait for the possible arrival of a new
 *    request for the queue.
 * See the comments on the function bfq_bfqq_may_idle for the reasons
 * why performing device idling is the best choice to boost the throughput
 * and preserve service guarantees when bfq_bfqq_may_idle itself
 * returns true.
 */
static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
{
	struct bfq_data *bfqd = bfqq->bfqd;

	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfqd->bfq_slice_idle != 0 &&
	       bfq_bfqq_may_idle(bfqq);
}

/*
 * Select a queue for service.  If we have a current queue in service,
 * check whether to continue servicing it, or retrieve and set a new one.
 */
static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
{
	struct bfq_queue *bfqq;
	struct request *next_rq;
	enum bfqq_expiration reason = BFQQE_BUDGET_TIMEOUT;

	bfqq = bfqd->in_service_queue;
	if (!bfqq)
		goto new_queue;

	bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");

	if (bfq_may_expire_for_budg_timeout(bfqq) &&
	    !bfq_bfqq_wait_request(bfqq) &&
	    !bfq_bfqq_must_idle(bfqq))
		goto expire;

check_queue:
	/*
	 * This loop is rarely executed more than once. Even when it
	 * happens, it is much more convenient to re-execute this loop
	 * than to return NULL and trigger a new dispatch to get a
	 * request served.
	 */
	next_rq = bfqq->next_rq;
	/*
	 * If bfqq has requests queued and it has enough budget left to
	 * serve them, keep the queue, otherwise expire it.
	 */
	if (next_rq) {
		if (bfq_serv_to_charge(next_rq, bfqq) >
			bfq_bfqq_budget_left(bfqq)) {
			/*
			 * Expire the queue for budget exhaustion,
			 * which makes sure that the next budget is
			 * enough to serve the next request, even if
			 * it comes from the fifo expired path.
			 */
			reason = BFQQE_BUDGET_EXHAUSTED;
			goto expire;
		} else {
			/*
			 * The idle timer may be pending because we may
			 * not disable disk idling even when a new request
			 * arrives.
			 */
			if (bfq_bfqq_wait_request(bfqq)) {
				/*
				 * If we get here: 1) at least a new request
				 * has arrived but we have not disabled the
				 * timer because the request was too small,
				 * 2) then the block layer has unplugged
				 * the device, causing the dispatch to be
				 * invoked.
				 *
				 * Since the device is unplugged, now the
				 * requests are probably large enough to
				 * provide a reasonable throughput.
				 * So we disable idling.
				 */
				bfq_clear_bfqq_wait_request(bfqq);
				hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
				bfqg_stats_update_idle_time(bfqq_group(bfqq));
			}
			goto keep_queue;
		}
	}

	/*
	 * No requests pending. However, if the in-service queue is idling
	 * for a new request, or has requests waiting for a completion and
	 * may idle after their completion, then keep it anyway.
	 */
	if (bfq_bfqq_wait_request(bfqq) ||
	    (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) {
		bfqq = NULL;
		goto keep_queue;
	}

	reason = BFQQE_NO_MORE_REQUESTS;
expire:
	bfq_bfqq_expire(bfqd, bfqq, false, reason);
new_queue:
	bfqq = bfq_set_in_service_queue(bfqd);
	if (bfqq) {
		bfq_log_bfqq(bfqd, bfqq, "select_queue: checking new queue");
		goto check_queue;
	}
keep_queue:
	if (bfqq)
		bfq_log_bfqq(bfqd, bfqq, "select_queue: returned this queue");
	else
		bfq_log(bfqd, "select_queue: no queue returned");

	return bfqq;
}

/*
 * Dispatch next request from bfqq.
 */
static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
						 struct bfq_queue *bfqq)
{
	struct request *rq = bfqq->next_rq;
	unsigned long service_to_charge;

	service_to_charge = bfq_serv_to_charge(rq, bfqq);

	bfq_bfqq_served(bfqq, service_to_charge);

	bfq_dispatch_remove(bfqd->queue, rq);

	if (!bfqd->in_service_bic) {
		atomic_long_inc(&RQ_BIC(rq)->icq.ioc->refcount);
		bfqd->in_service_bic = RQ_BIC(rq);
	}

	/*
	 * Expire bfqq, pretending that its budget expired, if bfqq
	 * belongs to CLASS_IDLE and other queues are waiting for
	 * service.
	 */
	if (bfqd->busy_queues > 1 && bfq_class_idle(bfqq))
		goto expire;

	return rq;

expire:
	bfq_bfqq_expire(bfqd, bfqq, false, BFQQE_BUDGET_EXHAUSTED);
	return rq;
}

static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
{
	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;

	/*
	 * Avoiding lock: a race on bfqd->busy_queues should cause at
	 * most a call to dispatch for nothing
	 */
	return !list_empty_careful(&bfqd->dispatch) ||
		bfqd->busy_queues > 0;
}

static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
{
	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
	struct request *rq = NULL;
	struct bfq_queue *bfqq = NULL;

	if (!list_empty(&bfqd->dispatch)) {
		rq = list_first_entry(&bfqd->dispatch, struct request,
				      queuelist);
		list_del_init(&rq->queuelist);

		bfqq = RQ_BFQQ(rq);

		if (bfqq) {
			/*
			 * Increment counters here, because this
			 * dispatch does not follow the standard
			 * dispatch flow (where counters are
			 * incremented)
			 */
			bfqq->dispatched++;

			goto inc_in_driver_start_rq;
		}

		/*
		 * We exploit the put_rq_private hook to decrement
		 * rq_in_driver, but put_rq_private will not be
		 * invoked on this request. So, to avoid unbalance,
		 * just start this request, without incrementing
		 * rq_in_driver. As a negative consequence,
		 * rq_in_driver is deceptively lower than it should be
		 * while this request is in service. This may cause
		 * bfq_schedule_dispatch to be invoked uselessly.
		 *
		 * As for implementing an exact solution, the
		 * put_request hook, if defined, is probably invoked
		 * also on this request. So, by exploiting this hook,
		 * we could 1) increment rq_in_driver here, and 2)
		 * decrement it in put_request. Such a solution would
		 * let the value of the counter be always accurate,
		 * but it would entail using an extra interface
		 * function. This cost seems higher than the benefit,
		 * being the frequency of non-elevator-private
		 * requests very low.
		 */
		goto start_rq;
	}

	bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues);

	if (bfqd->busy_queues == 0)
		goto exit;

	/*
	 * Force device to serve one request at a time if
	 * strict_guarantees is true. Forcing this service scheme is
	 * currently the ONLY way to guarantee that the request
	 * service order enforced by the scheduler is respected by a
	 * queueing device. Otherwise the device is free even to make
	 * some unlucky request wait for as long as the device
	 * wishes.
	 *
	 * Of course, serving one request at at time may cause loss of
	 * throughput.
	 */
	if (bfqd->strict_guarantees && bfqd->rq_in_driver > 0)
		goto exit;

	bfqq = bfq_select_queue(bfqd);
	if (!bfqq)
		goto exit;

	rq = bfq_dispatch_rq_from_bfqq(bfqd, bfqq);

	if (rq) {
inc_in_driver_start_rq:
		bfqd->rq_in_driver++;
start_rq:
		rq->rq_flags |= RQF_STARTED;
	}
exit:
	return rq;
}

static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
{
	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
	struct request *rq;

	spin_lock_irq(&bfqd->lock);
	rq = __bfq_dispatch_request(hctx);
	spin_unlock_irq(&bfqd->lock);

	return rq;
}

/*
 * Task holds one reference to the queue, dropped when task exits.  Each rq
 * in-flight on this queue also holds a reference, dropped when rq is freed.
 *
 * Scheduler lock must be held here. Recall not to use bfqq after calling
 * this function on it.
 */
static void bfq_put_queue(struct bfq_queue *bfqq)
{
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	struct bfq_group *bfqg = bfqq_group(bfqq);
#endif

	if (bfqq->bfqd)
		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d",
			     bfqq, bfqq->ref);

	bfqq->ref--;
	if (bfqq->ref)
		return;

	bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p freed", bfqq);

	kmem_cache_free(bfq_pool, bfqq);
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	bfqg_put(bfqg);
#endif
}

static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
	if (bfqq == bfqd->in_service_queue) {
		__bfq_bfqq_expire(bfqd, bfqq);
		bfq_schedule_dispatch(bfqd);
	}

	bfq_log_bfqq(bfqd, bfqq, "exit_bfqq: %p, %d", bfqq, bfqq->ref);

	bfq_put_queue(bfqq); /* release process reference */
}

static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
{
	struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);
	struct bfq_data *bfqd;

	if (bfqq)
		bfqd = bfqq->bfqd; /* NULL if scheduler already exited */

	if (bfqq && bfqd) {
		unsigned long flags;

		spin_lock_irqsave(&bfqd->lock, flags);
		bfq_exit_bfqq(bfqd, bfqq);
		bic_set_bfqq(bic, NULL, is_sync);
		spin_unlock_irq(&bfqd->lock);
	}
}

static void bfq_exit_icq(struct io_cq *icq)
{
	struct bfq_io_cq *bic = icq_to_bic(icq);

	bfq_exit_icq_bfqq(bic, true);
	bfq_exit_icq_bfqq(bic, false);
}

/*
 * Update the entity prio values; note that the new values will not
 * be used until the next (re)activation.
 */
static void
bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
{
	struct task_struct *tsk = current;
	int ioprio_class;
	struct bfq_data *bfqd = bfqq->bfqd;

	if (!bfqd)
		return;

	ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
	switch (ioprio_class) {
	default:
		dev_err(bfqq->bfqd->queue->backing_dev_info->dev,
			"bfq: bad prio class %d\n", ioprio_class);
	case IOPRIO_CLASS_NONE:
		/*
		 * No prio set, inherit CPU scheduling settings.
		 */
		bfqq->new_ioprio = task_nice_ioprio(tsk);
		bfqq->new_ioprio_class = task_nice_ioclass(tsk);
		break;
	case IOPRIO_CLASS_RT:
		bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
		bfqq->new_ioprio_class = IOPRIO_CLASS_RT;
		break;
	case IOPRIO_CLASS_BE:
		bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
		bfqq->new_ioprio_class = IOPRIO_CLASS_BE;
		break;
	case IOPRIO_CLASS_IDLE:
		bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE;
		bfqq->new_ioprio = 7;
		bfq_clear_bfqq_idle_window(bfqq);
		break;
	}

	if (bfqq->new_ioprio >= IOPRIO_BE_NR) {
		pr_crit("bfq_set_next_ioprio_data: new_ioprio %d\n",
			bfqq->new_ioprio);
		bfqq->new_ioprio = IOPRIO_BE_NR;
	}

	bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio);
	bfqq->entity.prio_changed = 1;
}

static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio)
{
	struct bfq_data *bfqd = bic_to_bfqd(bic);
	struct bfq_queue *bfqq;
	int ioprio = bic->icq.ioc->ioprio;

	/*
	 * This condition may trigger on a newly created bic, be sure to
	 * drop the lock before returning.
	 */
	if (unlikely(!bfqd) || likely(bic->ioprio == ioprio))
		return;

	bic->ioprio = ioprio;

	bfqq = bic_to_bfqq(bic, false);
	if (bfqq) {
		/* release process reference on this queue */
		bfq_put_queue(bfqq);
		bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic);
		bic_set_bfqq(bic, bfqq, false);
	}

	bfqq = bic_to_bfqq(bic, true);
	if (bfqq)
		bfq_set_next_ioprio_data(bfqq, bic);
}

static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
			  struct bfq_io_cq *bic, pid_t pid, int is_sync)
{
	RB_CLEAR_NODE(&bfqq->entity.rb_node);
	INIT_LIST_HEAD(&bfqq->fifo);

	bfqq->ref = 0;
	bfqq->bfqd = bfqd;

	if (bic)
		bfq_set_next_ioprio_data(bfqq, bic);

	if (is_sync) {
		if (!bfq_class_idle(bfqq))
			bfq_mark_bfqq_idle_window(bfqq);
		bfq_mark_bfqq_sync(bfqq);
	} else
		bfq_clear_bfqq_sync(bfqq);

	/* set end request to minus infinity from now */
	bfqq->ttime.last_end_request = ktime_get_ns() + 1;

	bfq_mark_bfqq_IO_bound(bfqq);

	bfqq->pid = pid;

	/* Tentative initial value to trade off between thr and lat */
	bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3;
	bfqq->budget_timeout = bfq_smallest_from_now();

	/* first request is almost certainly seeky */
	bfqq->seek_history = 1;
}

static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd,
					       struct bfq_group *bfqg,
					       int ioprio_class, int ioprio)
{
	switch (ioprio_class) {
	case IOPRIO_CLASS_RT:
		return &bfqg->async_bfqq[0][ioprio];
	case IOPRIO_CLASS_NONE:
		ioprio = IOPRIO_NORM;
		/* fall through */
	case IOPRIO_CLASS_BE:
		return &bfqg->async_bfqq[1][ioprio];
	case IOPRIO_CLASS_IDLE:
		return &bfqg->async_idle_bfqq;
	default:
		return NULL;
	}
}

static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
				       struct bio *bio, bool is_sync,
				       struct bfq_io_cq *bic)
{
	const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
	const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
	struct bfq_queue **async_bfqq = NULL;
	struct bfq_queue *bfqq;
	struct bfq_group *bfqg;

	rcu_read_lock();

	bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio));
	if (!bfqg) {
		bfqq = &bfqd->oom_bfqq;
		goto out;
	}

	if (!is_sync) {
		async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class,
						  ioprio);
		bfqq = *async_bfqq;
		if (bfqq)
			goto out;
	}

	bfqq = kmem_cache_alloc_node(bfq_pool,
				     GFP_NOWAIT | __GFP_ZERO | __GFP_NOWARN,
				     bfqd->queue->node);

	if (bfqq) {
		bfq_init_bfqq(bfqd, bfqq, bic, current->pid,
			      is_sync);
		bfq_init_entity(&bfqq->entity, bfqg);
		bfq_log_bfqq(bfqd, bfqq, "allocated");
	} else {
		bfqq = &bfqd->oom_bfqq;
		bfq_log_bfqq(bfqd, bfqq, "using oom bfqq");
		goto out;
	}

	/*
	 * Pin the queue now that it's allocated, scheduler exit will
	 * prune it.
	 */
	if (async_bfqq) {
		bfqq->ref++; /*
			      * Extra group reference, w.r.t. sync
			      * queue. This extra reference is removed
			      * only if bfqq->bfqg disappears, to
			      * guarantee that this queue is not freed
			      * until its group goes away.
			      */
		bfq_log_bfqq(bfqd, bfqq, "get_queue, bfqq not in async: %p, %d",
			     bfqq, bfqq->ref);
		*async_bfqq = bfqq;
	}

out:
	bfqq->ref++; /* get a process reference to this queue */
	bfq_log_bfqq(bfqd, bfqq, "get_queue, at end: %p, %d", bfqq, bfqq->ref);
	rcu_read_unlock();
	return bfqq;
}

static void bfq_update_io_thinktime(struct bfq_data *bfqd,
				    struct bfq_queue *bfqq)
{
	struct bfq_ttime *ttime = &bfqq->ttime;
	u64 elapsed = ktime_get_ns() - bfqq->ttime.last_end_request;

	elapsed = min_t(u64, elapsed, 2ULL * bfqd->bfq_slice_idle);

	ttime->ttime_samples = (7*bfqq->ttime.ttime_samples + 256) / 8;
	ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed,  8);
	ttime->ttime_mean = div64_ul(ttime->ttime_total + 128,
				     ttime->ttime_samples);
}

static void
bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq,
		       struct request *rq)
{
	sector_t sdist = 0;

	if (bfqq->last_request_pos) {
		if (bfqq->last_request_pos < blk_rq_pos(rq))
			sdist = blk_rq_pos(rq) - bfqq->last_request_pos;
		else
			sdist = bfqq->last_request_pos - blk_rq_pos(rq);
	}

	bfqq->seek_history <<= 1;
	bfqq->seek_history |= sdist > BFQQ_SEEK_THR &&
		(!blk_queue_nonrot(bfqd->queue) ||
		 blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT);
}

/*
 * Disable idle window if the process thinks too long or seeks so much that
 * it doesn't matter.
 */
static void bfq_update_idle_window(struct bfq_data *bfqd,
				   struct bfq_queue *bfqq,
				   struct bfq_io_cq *bic)
{
	int enable_idle;

	/* Don't idle for async or idle io prio class. */
	if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq))
		return;

	enable_idle = bfq_bfqq_idle_window(bfqq);

	if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
	    bfqd->bfq_slice_idle == 0 ||
		(bfqd->hw_tag && BFQQ_SEEKY(bfqq)))
		enable_idle = 0;
	else if (bfq_sample_valid(bfqq->ttime.ttime_samples)) {
		if (bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle)
			enable_idle = 0;
		else
			enable_idle = 1;
	}
	bfq_log_bfqq(bfqd, bfqq, "update_idle_window: enable_idle %d",
		enable_idle);

	if (enable_idle)
		bfq_mark_bfqq_idle_window(bfqq);
	else
		bfq_clear_bfqq_idle_window(bfqq);
}

/*
 * Called when a new fs request (rq) is added to bfqq.  Check if there's
 * something we should do about it.
 */
static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
			    struct request *rq)
{
	struct bfq_io_cq *bic = RQ_BIC(rq);

	if (rq->cmd_flags & REQ_META)
		bfqq->meta_pending++;

	bfq_update_io_thinktime(bfqd, bfqq);
	bfq_update_io_seektime(bfqd, bfqq, rq);
	if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 ||
	    !BFQQ_SEEKY(bfqq))
		bfq_update_idle_window(bfqd, bfqq, bic);

	bfq_log_bfqq(bfqd, bfqq,
		     "rq_enqueued: idle_window=%d (seeky %d)",
		     bfq_bfqq_idle_window(bfqq), BFQQ_SEEKY(bfqq));

	bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);

	if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) {
		bool small_req = bfqq->queued[rq_is_sync(rq)] == 1 &&
				 blk_rq_sectors(rq) < 32;
		bool budget_timeout = bfq_bfqq_budget_timeout(bfqq);

		/*
		 * There is just this request queued: if the request
		 * is small and the queue is not to be expired, then
		 * just exit.
		 *
		 * In this way, if the device is being idled to wait
		 * for a new request from the in-service queue, we
		 * avoid unplugging the device and committing the
		 * device to serve just a small request. On the
		 * contrary, we wait for the block layer to decide
		 * when to unplug the device: hopefully, new requests
		 * will be merged to this one quickly, then the device
		 * will be unplugged and larger requests will be
		 * dispatched.
		 */
		if (small_req && !budget_timeout)
			return;

		/*
		 * A large enough request arrived, or the queue is to
		 * be expired: in both cases disk idling is to be
		 * stopped, so clear wait_request flag and reset
		 * timer.
		 */
		bfq_clear_bfqq_wait_request(bfqq);
		hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
		bfqg_stats_update_idle_time(bfqq_group(bfqq));

		/*
		 * The queue is not empty, because a new request just
		 * arrived. Hence we can safely expire the queue, in
		 * case of budget timeout, without risking that the
		 * timestamps of the queue are not updated correctly.
		 * See [1] for more details.
		 */
		if (budget_timeout)
			bfq_bfqq_expire(bfqd, bfqq, false,
					BFQQE_BUDGET_TIMEOUT);
	}
}

static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
{
	struct bfq_queue *bfqq = RQ_BFQQ(rq);

	bfq_add_request(rq);

	rq->fifo_time = ktime_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
	list_add_tail(&rq->queuelist, &bfqq->fifo);

	bfq_rq_enqueued(bfqd, bfqq, rq);
}

static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
			       bool at_head)
{
	struct request_queue *q = hctx->queue;
	struct bfq_data *bfqd = q->elevator->elevator_data;

	spin_lock_irq(&bfqd->lock);
	if (blk_mq_sched_try_insert_merge(q, rq)) {
		spin_unlock_irq(&bfqd->lock);
		return;
	}

	spin_unlock_irq(&bfqd->lock);

	blk_mq_sched_request_inserted(rq);

	spin_lock_irq(&bfqd->lock);
	if (at_head || blk_rq_is_passthrough(rq)) {
		if (at_head)
			list_add(&rq->queuelist, &bfqd->dispatch);
		else
			list_add_tail(&rq->queuelist, &bfqd->dispatch);
	} else {
		__bfq_insert_request(bfqd, rq);

		if (rq_mergeable(rq)) {
			elv_rqhash_add(q, rq);
			if (!q->last_merge)
				q->last_merge = rq;
		}
	}

	spin_unlock_irq(&bfqd->lock);
}

static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
				struct list_head *list, bool at_head)
{
	while (!list_empty(list)) {
		struct request *rq;

		rq = list_first_entry(list, struct request, queuelist);
		list_del_init(&rq->queuelist);
		bfq_insert_request(hctx, rq, at_head);
	}
}

static void bfq_update_hw_tag(struct bfq_data *bfqd)
{
	bfqd->max_rq_in_driver = max_t(int, bfqd->max_rq_in_driver,
				       bfqd->rq_in_driver);

	if (bfqd->hw_tag == 1)
		return;

	/*
	 * This sample is valid if the number of outstanding requests
	 * is large enough to allow a queueing behavior.  Note that the
	 * sum is not exact, as it's not taking into account deactivated
	 * requests.
	 */
	if (bfqd->rq_in_driver + bfqd->queued < BFQ_HW_QUEUE_THRESHOLD)
		return;

	if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES)
		return;

	bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD;
	bfqd->max_rq_in_driver = 0;
	bfqd->hw_tag_samples = 0;
}

static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
{
	bfq_update_hw_tag(bfqd);

	bfqd->rq_in_driver--;
	bfqq->dispatched--;

	bfqq->ttime.last_end_request = ktime_get_ns();

	/*
	 * If this is the in-service queue, check if it needs to be expired,
	 * or if we want to idle in case it has no pending requests.
	 */
	if (bfqd->in_service_queue == bfqq) {
		if (bfq_bfqq_budget_new(bfqq))
			bfq_set_budget_timeout(bfqd);

		if (bfq_bfqq_must_idle(bfqq)) {
			bfq_arm_slice_timer(bfqd);
			return;
		} else if (bfq_may_expire_for_budg_timeout(bfqq))
			bfq_bfqq_expire(bfqd, bfqq, false,
					BFQQE_BUDGET_TIMEOUT);
		else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
			 (bfqq->dispatched == 0 ||
			  !bfq_bfqq_may_idle(bfqq)))
			bfq_bfqq_expire(bfqd, bfqq, false,
					BFQQE_NO_MORE_REQUESTS);
	}
}

static void bfq_put_rq_priv_body(struct bfq_queue *bfqq)
{
	bfqq->allocated--;

	bfq_put_queue(bfqq);
}

static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
{
	struct bfq_queue *bfqq = RQ_BFQQ(rq);
	struct bfq_data *bfqd = bfqq->bfqd;

	if (rq->rq_flags & RQF_STARTED)
		bfqg_stats_update_completion(bfqq_group(bfqq),
					     rq_start_time_ns(rq),
					     rq_io_start_time_ns(rq),
					     rq->cmd_flags);

	if (likely(rq->rq_flags & RQF_STARTED)) {
		unsigned long flags;

		spin_lock_irqsave(&bfqd->lock, flags);

		bfq_completed_request(bfqq, bfqd);
		bfq_put_rq_priv_body(bfqq);

		spin_unlock_irqrestore(&bfqd->lock, flags);
	} else {
		/*
		 * Request rq may be still/already in the scheduler,
		 * in which case we need to remove it. And we cannot
		 * defer such a check and removal, to avoid
		 * inconsistencies in the time interval from the end
		 * of this function to the start of the deferred work.
		 * This situation seems to occur only in process
		 * context, as a consequence of a merge. In the
		 * current version of the code, this implies that the
		 * lock is held.
		 */

		if (!RB_EMPTY_NODE(&rq->rb_node))
			bfq_remove_request(q, rq);
		bfq_put_rq_priv_body(bfqq);
	}

	rq->elv.priv[0] = NULL;
	rq->elv.priv[1] = NULL;
}

/*
 * Allocate bfq data structures associated with this request.
 */
static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
			      struct bio *bio)
{
	struct bfq_data *bfqd = q->elevator->elevator_data;
	struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
	const int is_sync = rq_is_sync(rq);
	struct bfq_queue *bfqq;

	spin_lock_irq(&bfqd->lock);

	bfq_check_ioprio_change(bic, bio);

	if (!bic)
		goto queue_fail;

	bfq_bic_update_cgroup(bic, bio);

	bfqq = bic_to_bfqq(bic, is_sync);
	if (!bfqq || bfqq == &bfqd->oom_bfqq) {
		if (bfqq)
			bfq_put_queue(bfqq);
		bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);
		bic_set_bfqq(bic, bfqq, is_sync);
	}

	bfqq->allocated++;
	bfqq->ref++;
	bfq_log_bfqq(bfqd, bfqq, "get_request %p: bfqq %p, %d",
		     rq, bfqq, bfqq->ref);

	rq->elv.priv[0] = bic;
	rq->elv.priv[1] = bfqq;

	spin_unlock_irq(&bfqd->lock);

	return 0;

queue_fail:
	spin_unlock_irq(&bfqd->lock);

	return 1;
}

static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
{
	struct bfq_data *bfqd = bfqq->bfqd;
	enum bfqq_expiration reason;
	unsigned long flags;

	spin_lock_irqsave(&bfqd->lock, flags);
	bfq_clear_bfqq_wait_request(bfqq);

	if (bfqq != bfqd->in_service_queue) {
		spin_unlock_irqrestore(&bfqd->lock, flags);
		return;
	}

	if (bfq_bfqq_budget_timeout(bfqq))
		/*
		 * Also here the queue can be safely expired
		 * for budget timeout without wasting
		 * guarantees
		 */
		reason = BFQQE_BUDGET_TIMEOUT;
	else if (bfqq->queued[0] == 0 && bfqq->queued[1] == 0)
		/*
		 * The queue may not be empty upon timer expiration,
		 * because we may not disable the timer when the
		 * first request of the in-service queue arrives
		 * during disk idling.
		 */
		reason = BFQQE_TOO_IDLE;
	else
		goto schedule_dispatch;

	bfq_bfqq_expire(bfqd, bfqq, true, reason);

schedule_dispatch:
	spin_unlock_irqrestore(&bfqd->lock, flags);
	bfq_schedule_dispatch(bfqd);
}

/*
 * Handler of the expiration of the timer running if the in-service queue
 * is idling inside its time slice.
 */
static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer)
{
	struct bfq_data *bfqd = container_of(timer, struct bfq_data,
					     idle_slice_timer);
	struct bfq_queue *bfqq = bfqd->in_service_queue;

	/*
	 * Theoretical race here: the in-service queue can be NULL or
	 * different from the queue that was idling if a new request
	 * arrives for the current queue and there is a full dispatch
	 * cycle that changes the in-service queue.  This can hardly
	 * happen, but in the worst case we just expire a queue too
	 * early.
	 */
	if (bfqq)
		bfq_idle_slice_timer_body(bfqq);

	return HRTIMER_NORESTART;
}

static void __bfq_put_async_bfqq(struct bfq_data *bfqd,
				 struct bfq_queue **bfqq_ptr)
{
	struct bfq_queue *bfqq = *bfqq_ptr;

	bfq_log(bfqd, "put_async_bfqq: %p", bfqq);
	if (bfqq) {
		bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);

		bfq_log_bfqq(bfqd, bfqq, "put_async_bfqq: putting %p, %d",
			     bfqq, bfqq->ref);
		bfq_put_queue(bfqq);
		*bfqq_ptr = NULL;
	}
}

/*
 * Release all the bfqg references to its async queues.  If we are
 * deallocating the group these queues may still contain requests, so
 * we reparent them to the root cgroup (i.e., the only one that will
 * exist for sure until all the requests on a device are gone).
 */
static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
{
	int i, j;

	for (i = 0; i < 2; i++)
		for (j = 0; j < IOPRIO_BE_NR; j++)
			__bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]);

	__bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq);
}

static void bfq_exit_queue(struct elevator_queue *e)
{
	struct bfq_data *bfqd = e->elevator_data;
	struct bfq_queue *bfqq, *n;

	hrtimer_cancel(&bfqd->idle_slice_timer);

	spin_lock_irq(&bfqd->lock);
	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
	spin_unlock_irq(&bfqd->lock);

	hrtimer_cancel(&bfqd->idle_slice_timer);

#ifdef CONFIG_BFQ_GROUP_IOSCHED
	blkcg_deactivate_policy(bfqd->queue, &blkcg_policy_bfq);
#else
	spin_lock_irq(&bfqd->lock);
	bfq_put_async_queues(bfqd, bfqd->root_group);
	kfree(bfqd->root_group);
	spin_unlock_irq(&bfqd->lock);
#endif

	kfree(bfqd);
}

static void bfq_init_root_group(struct bfq_group *root_group,
				struct bfq_data *bfqd)
{
	int i;

#ifdef CONFIG_BFQ_GROUP_IOSCHED
	root_group->entity.parent = NULL;
	root_group->my_entity = NULL;
	root_group->bfqd = bfqd;
#endif
	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
		root_group->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
	root_group->sched_data.bfq_class_idle_last_service = jiffies;
}

static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
{
	struct bfq_data *bfqd;
	struct elevator_queue *eq;

	eq = elevator_alloc(q, e);
	if (!eq)
		return -ENOMEM;

	bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node);
	if (!bfqd) {
		kobject_put(&eq->kobj);
		return -ENOMEM;
	}
	eq->elevator_data = bfqd;

	spin_lock_irq(q->queue_lock);
	q->elevator = eq;
	spin_unlock_irq(q->queue_lock);

	/*
	 * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues.
	 * Grab a permanent reference to it, so that the normal code flow
	 * will not attempt to free it.
	 */
	bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, NULL, 1, 0);
	bfqd->oom_bfqq.ref++;
	bfqd->oom_bfqq.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO;
	bfqd->oom_bfqq.new_ioprio_class = IOPRIO_CLASS_BE;
	bfqd->oom_bfqq.entity.new_weight =
		bfq_ioprio_to_weight(bfqd->oom_bfqq.new_ioprio);
	/*
	 * Trigger weight initialization, according to ioprio, at the
	 * oom_bfqq's first activation. The oom_bfqq's ioprio and ioprio
	 * class won't be changed any more.
	 */
	bfqd->oom_bfqq.entity.prio_changed = 1;

	bfqd->queue = q;

	INIT_LIST_HEAD(&bfqd->dispatch);

	hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC,
		     HRTIMER_MODE_REL);
	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;

	INIT_LIST_HEAD(&bfqd->active_list);
	INIT_LIST_HEAD(&bfqd->idle_list);

	bfqd->hw_tag = -1;

	bfqd->bfq_max_budget = bfq_default_max_budget;

	bfqd->bfq_fifo_expire[0] = bfq_fifo_expire[0];
	bfqd->bfq_fifo_expire[1] = bfq_fifo_expire[1];
	bfqd->bfq_back_max = bfq_back_max;
	bfqd->bfq_back_penalty = bfq_back_penalty;
	bfqd->bfq_slice_idle = bfq_slice_idle;
	bfqd->bfq_timeout = bfq_timeout;

	bfqd->bfq_requests_within_timer = 120;

	spin_lock_init(&bfqd->lock);

	/*
	 * The invocation of the next bfq_create_group_hierarchy
	 * function is the head of a chain of function calls
	 * (bfq_create_group_hierarchy->blkcg_activate_policy->
	 * blk_mq_freeze_queue) that may lead to the invocation of the
	 * has_work hook function. For this reason,
	 * bfq_create_group_hierarchy is invoked only after all
	 * scheduler data has been initialized, apart from the fields
	 * that can be initialized only after invoking
	 * bfq_create_group_hierarchy. This, in particular, enables
	 * has_work to correctly return false. Of course, to avoid
	 * other inconsistencies, the blk-mq stack must then refrain
	 * from invoking further scheduler hooks before this init
	 * function is finished.
	 */
	bfqd->root_group = bfq_create_group_hierarchy(bfqd, q->node);
	if (!bfqd->root_group)
		goto out_free;
	bfq_init_root_group(bfqd->root_group, bfqd);
	bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group);


	return 0;

out_free:
	kfree(bfqd);
	kobject_put(&eq->kobj);
	return -ENOMEM;
}

static void bfq_slab_kill(void)
{
	kmem_cache_destroy(bfq_pool);
}

static int __init bfq_slab_setup(void)
{
	bfq_pool = KMEM_CACHE(bfq_queue, 0);
	if (!bfq_pool)
		return -ENOMEM;
	return 0;
}

static ssize_t bfq_var_show(unsigned int var, char *page)
{
	return sprintf(page, "%u\n", var);
}

static ssize_t bfq_var_store(unsigned long *var, const char *page,
			     size_t count)
{
	unsigned long new_val;
	int ret = kstrtoul(page, 10, &new_val);

	if (ret == 0)
		*var = new_val;

	return count;
}

#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
{									\
	struct bfq_data *bfqd = e->elevator_data;			\
	u64 __data = __VAR;						\
	if (__CONV == 1)						\
		__data = jiffies_to_msecs(__data);			\
	else if (__CONV == 2)						\
		__data = div_u64(__data, NSEC_PER_MSEC);		\
	return bfq_var_show(__data, (page));				\
}
SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 2);
SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 2);
SHOW_FUNCTION(bfq_back_seek_max_show, bfqd->bfq_back_max, 0);
SHOW_FUNCTION(bfq_back_seek_penalty_show, bfqd->bfq_back_penalty, 0);
SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 2);
SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0);
SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout, 1);
SHOW_FUNCTION(bfq_strict_guarantees_show, bfqd->strict_guarantees, 0);
#undef SHOW_FUNCTION

#define USEC_SHOW_FUNCTION(__FUNC, __VAR)				\
static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
{									\
	struct bfq_data *bfqd = e->elevator_data;			\
	u64 __data = __VAR;						\
	__data = div_u64(__data, NSEC_PER_USEC);			\
	return bfq_var_show(__data, (page));				\
}
USEC_SHOW_FUNCTION(bfq_slice_idle_us_show, bfqd->bfq_slice_idle);
#undef USEC_SHOW_FUNCTION

#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
static ssize_t								\
__FUNC(struct elevator_queue *e, const char *page, size_t count)	\
{									\
	struct bfq_data *bfqd = e->elevator_data;			\
	unsigned long uninitialized_var(__data);			\
	int ret = bfq_var_store(&__data, (page), count);		\
	if (__data < (MIN))						\
		__data = (MIN);						\
	else if (__data > (MAX))					\
		__data = (MAX);						\
	if (__CONV == 1)						\
		*(__PTR) = msecs_to_jiffies(__data);			\
	else if (__CONV == 2)						\
		*(__PTR) = (u64)__data * NSEC_PER_MSEC;			\
	else								\
		*(__PTR) = __data;					\
	return ret;							\
}
STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1,
		INT_MAX, 2);
STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1,
		INT_MAX, 2);
STORE_FUNCTION(bfq_back_seek_max_store, &bfqd->bfq_back_max, 0, INT_MAX, 0);
STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1,
		INT_MAX, 0);
STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 2);
#undef STORE_FUNCTION

#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)			\
static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)\
{									\
	struct bfq_data *bfqd = e->elevator_data;			\
	unsigned long uninitialized_var(__data);			\
	int ret = bfq_var_store(&__data, (page), count);		\
	if (__data < (MIN))						\
		__data = (MIN);						\
	else if (__data > (MAX))					\
		__data = (MAX);						\
	*(__PTR) = (u64)__data * NSEC_PER_USEC;				\
	return ret;							\
}
USEC_STORE_FUNCTION(bfq_slice_idle_us_store, &bfqd->bfq_slice_idle, 0,
		    UINT_MAX);
#undef USEC_STORE_FUNCTION

static unsigned long bfq_estimated_max_budget(struct bfq_data *bfqd)
{
	u64 timeout = jiffies_to_msecs(bfqd->bfq_timeout);

	if (bfqd->peak_rate_samples >= BFQ_PEAK_RATE_SAMPLES)
		return bfq_calc_max_budget(bfqd->peak_rate, timeout);
	else
		return bfq_default_max_budget;
}

static ssize_t bfq_max_budget_store(struct elevator_queue *e,
				    const char *page, size_t count)
{
	struct bfq_data *bfqd = e->elevator_data;
	unsigned long uninitialized_var(__data);
	int ret = bfq_var_store(&__data, (page), count);

	if (__data == 0)
		bfqd->bfq_max_budget = bfq_estimated_max_budget(bfqd);
	else {
		if (__data > INT_MAX)
			__data = INT_MAX;
		bfqd->bfq_max_budget = __data;
	}

	bfqd->bfq_user_max_budget = __data;

	return ret;
}

/*
 * Leaving this name to preserve name compatibility with cfq
 * parameters, but this timeout is used for both sync and async.
 */
static ssize_t bfq_timeout_sync_store(struct elevator_queue *e,
				      const char *page, size_t count)
{
	struct bfq_data *bfqd = e->elevator_data;
	unsigned long uninitialized_var(__data);
	int ret = bfq_var_store(&__data, (page), count);

	if (__data < 1)
		__data = 1;
	else if (__data > INT_MAX)
		__data = INT_MAX;

	bfqd->bfq_timeout = msecs_to_jiffies(__data);
	if (bfqd->bfq_user_max_budget == 0)
		bfqd->bfq_max_budget = bfq_estimated_max_budget(bfqd);

	return ret;
}

static ssize_t bfq_strict_guarantees_store(struct elevator_queue *e,
				     const char *page, size_t count)
{
	struct bfq_data *bfqd = e->elevator_data;
	unsigned long uninitialized_var(__data);
	int ret = bfq_var_store(&__data, (page), count);

	if (__data > 1)
		__data = 1;
	if (!bfqd->strict_guarantees && __data == 1
	    && bfqd->bfq_slice_idle < 8 * NSEC_PER_MSEC)
		bfqd->bfq_slice_idle = 8 * NSEC_PER_MSEC;

	bfqd->strict_guarantees = __data;

	return ret;
}

#define BFQ_ATTR(name) \
	__ATTR(name, 0644, bfq_##name##_show, bfq_##name##_store)

static struct elv_fs_entry bfq_attrs[] = {
	BFQ_ATTR(fifo_expire_sync),
	BFQ_ATTR(fifo_expire_async),
	BFQ_ATTR(back_seek_max),
	BFQ_ATTR(back_seek_penalty),
	BFQ_ATTR(slice_idle),
	BFQ_ATTR(slice_idle_us),
	BFQ_ATTR(max_budget),
	BFQ_ATTR(timeout_sync),
	BFQ_ATTR(strict_guarantees),
	__ATTR_NULL
};

static struct elevator_type iosched_bfq_mq = {
	.ops.mq = {
		.get_rq_priv		= bfq_get_rq_private,
		.put_rq_priv		= bfq_put_rq_private,
		.exit_icq		= bfq_exit_icq,
		.insert_requests	= bfq_insert_requests,
		.dispatch_request	= bfq_dispatch_request,
		.next_request		= elv_rb_latter_request,
		.former_request		= elv_rb_former_request,
		.allow_merge		= bfq_allow_bio_merge,
		.bio_merge		= bfq_bio_merge,
		.request_merge		= bfq_request_merge,
		.requests_merged	= bfq_requests_merged,
		.request_merged		= bfq_request_merged,
		.has_work		= bfq_has_work,
		.init_sched		= bfq_init_queue,
		.exit_sched		= bfq_exit_queue,
	},

	.uses_mq =		true,
	.icq_size =		sizeof(struct bfq_io_cq),
	.icq_align =		__alignof__(struct bfq_io_cq),
	.elevator_attrs =	bfq_attrs,
	.elevator_name =	"bfq",
	.elevator_owner =	THIS_MODULE,
};

#ifdef CONFIG_BFQ_GROUP_IOSCHED
static struct blkcg_policy blkcg_policy_bfq = {
	.dfl_cftypes		= bfq_blkg_files,
	.legacy_cftypes		= bfq_blkcg_legacy_files,

	.cpd_alloc_fn		= bfq_cpd_alloc,
	.cpd_init_fn		= bfq_cpd_init,
	.cpd_bind_fn	        = bfq_cpd_init,
	.cpd_free_fn		= bfq_cpd_free,

	.pd_alloc_fn		= bfq_pd_alloc,
	.pd_init_fn		= bfq_pd_init,
	.pd_offline_fn		= bfq_pd_offline,
	.pd_free_fn		= bfq_pd_free,
	.pd_reset_stats_fn	= bfq_pd_reset_stats,
};
#endif

static int __init bfq_init(void)
{
	int ret;

#ifdef CONFIG_BFQ_GROUP_IOSCHED
	ret = blkcg_policy_register(&blkcg_policy_bfq);
	if (ret)
		return ret;
#endif

	ret = -ENOMEM;
	if (bfq_slab_setup())
		goto err_pol_unreg;

	ret = elv_register(&iosched_bfq_mq);
	if (ret)
		goto err_pol_unreg;

	return 0;

err_pol_unreg:
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	blkcg_policy_unregister(&blkcg_policy_bfq);
#endif
	return ret;
}

static void __exit bfq_exit(void)
{
	elv_unregister(&iosched_bfq_mq);
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	blkcg_policy_unregister(&blkcg_policy_bfq);
#endif
	bfq_slab_kill();
}

module_init(bfq_init);
module_exit(bfq_exit);

MODULE_AUTHOR("Paolo Valente");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("MQ Budget Fair Queueing I/O Scheduler");