summaryrefslogtreecommitdiff
path: root/sys-kernel/linux-sources-redcore-lts/files/0001-BFQ-v8r12-20171108.patch
blob: db7d064b0ff53b388b86fe1cf6cba7480502cc00 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
7753
7754
7755
7756
7757
7758
7759
7760
7761
7762
7763
7764
7765
7766
7767
7768
7769
7770
7771
7772
7773
7774
7775
7776
7777
7778
7779
7780
7781
7782
7783
7784
7785
7786
7787
7788
7789
7790
7791
7792
7793
7794
7795
7796
7797
7798
7799
7800
7801
7802
7803
7804
7805
7806
7807
7808
7809
7810
7811
7812
7813
7814
7815
7816
7817
7818
7819
7820
7821
7822
7823
7824
7825
7826
7827
7828
7829
7830
7831
7832
7833
7834
7835
7836
7837
7838
7839
7840
7841
7842
7843
7844
7845
7846
7847
7848
7849
7850
7851
7852
7853
7854
7855
7856
7857
7858
7859
7860
7861
7862
7863
7864
7865
7866
7867
7868
7869
7870
7871
7872
7873
7874
7875
7876
7877
7878
7879
7880
7881
7882
7883
7884
7885
7886
7887
7888
7889
7890
7891
7892
7893
7894
7895
7896
7897
7898
7899
7900
7901
7902
7903
7904
7905
7906
7907
7908
7909
7910
7911
7912
7913
7914
7915
7916
7917
7918
7919
7920
7921
7922
7923
7924
7925
7926
7927
7928
7929
7930
7931
7932
7933
7934
7935
7936
7937
7938
7939
7940
7941
7942
7943
7944
7945
7946
7947
7948
7949
7950
7951
7952
7953
7954
7955
7956
7957
7958
7959
7960
7961
7962
7963
7964
7965
7966
7967
7968
7969
7970
7971
7972
7973
7974
7975
7976
7977
7978
7979
7980
7981
7982
7983
7984
7985
7986
7987
7988
7989
7990
7991
7992
7993
7994
7995
7996
7997
7998
7999
8000
8001
8002
8003
8004
8005
8006
8007
8008
8009
8010
8011
8012
8013
8014
8015
8016
8017
8018
8019
8020
8021
8022
8023
8024
8025
8026
8027
8028
8029
8030
8031
8032
8033
8034
8035
8036
8037
8038
8039
8040
8041
8042
8043
8044
8045
8046
8047
8048
8049
8050
8051
8052
8053
8054
8055
8056
8057
8058
8059
8060
8061
8062
8063
8064
8065
8066
8067
8068
8069
8070
8071
8072
8073
8074
8075
8076
8077
8078
8079
8080
8081
8082
8083
8084
8085
8086
8087
8088
8089
8090
8091
8092
8093
8094
8095
8096
8097
8098
8099
8100
8101
8102
8103
8104
8105
8106
8107
8108
8109
8110
8111
8112
8113
8114
8115
8116
8117
8118
8119
8120
8121
8122
8123
8124
8125
8126
8127
8128
8129
8130
8131
8132
8133
8134
8135
8136
8137
8138
8139
8140
8141
8142
8143
8144
8145
8146
8147
8148
8149
8150
8151
8152
8153
8154
8155
8156
8157
8158
8159
8160
8161
8162
8163
8164
8165
8166
8167
8168
8169
8170
8171
8172
8173
8174
8175
8176
8177
8178
8179
8180
8181
8182
8183
8184
8185
8186
8187
8188
8189
8190
8191
8192
8193
8194
8195
8196
8197
8198
8199
8200
8201
8202
8203
8204
8205
8206
8207
8208
8209
8210
8211
8212
8213
8214
8215
8216
8217
8218
8219
8220
8221
8222
8223
8224
8225
8226
8227
8228
8229
8230
8231
8232
8233
8234
8235
8236
8237
8238
8239
8240
8241
8242
8243
8244
8245
8246
8247
8248
8249
8250
8251
8252
8253
8254
8255
8256
8257
8258
8259
8260
8261
8262
8263
8264
8265
8266
8267
8268
8269
8270
8271
8272
8273
8274
8275
8276
8277
8278
8279
8280
8281
8282
8283
8284
8285
8286
8287
8288
8289
8290
8291
8292
8293
8294
8295
8296
8297
8298
8299
8300
8301
8302
8303
8304
8305
8306
8307
8308
8309
8310
8311
8312
8313
8314
8315
8316
8317
8318
8319
8320
8321
8322
8323
8324
8325
8326
8327
8328
8329
8330
8331
8332
8333
8334
8335
8336
8337
8338
8339
8340
8341
8342
8343
8344
8345
8346
8347
8348
8349
8350
8351
8352
8353
8354
8355
8356
8357
8358
8359
8360
8361
8362
8363
8364
8365
8366
8367
8368
8369
8370
8371
8372
8373
8374
8375
8376
8377
8378
8379
8380
8381
8382
8383
8384
8385
8386
8387
8388
8389
8390
8391
8392
8393
8394
8395
8396
8397
8398
8399
8400
8401
8402
8403
8404
8405
8406
8407
8408
8409
8410
8411
8412
8413
8414
8415
8416
8417
8418
8419
8420
8421
8422
8423
8424
8425
8426
8427
8428
8429
8430
8431
8432
8433
8434
8435
8436
8437
8438
8439
8440
8441
8442
8443
8444
8445
8446
8447
8448
8449
8450
8451
8452
8453
8454
8455
8456
8457
8458
8459
8460
8461
8462
8463
8464
8465
8466
8467
8468
8469
8470
8471
8472
8473
8474
8475
8476
8477
8478
8479
8480
8481
8482
8483
8484
8485
8486
8487
8488
8489
8490
8491
8492
8493
8494
8495
8496
8497
8498
8499
8500
8501
8502
8503
8504
8505
8506
8507
8508
8509
8510
8511
8512
8513
8514
8515
8516
8517
8518
8519
8520
8521
8522
8523
8524
8525
8526
8527
8528
8529
8530
8531
8532
8533
8534
8535
8536
8537
8538
8539
8540
8541
8542
8543
8544
8545
8546
8547
8548
8549
8550
8551
8552
8553
8554
8555
8556
8557
8558
8559
8560
8561
8562
8563
8564
8565
8566
8567
8568
8569
8570
8571
8572
8573
8574
8575
8576
8577
8578
8579
8580
8581
8582
8583
8584
8585
8586
8587
8588
8589
8590
8591
8592
8593
8594
8595
8596
8597
8598
8599
8600
8601
8602
8603
8604
8605
8606
8607
8608
8609
8610
8611
8612
8613
8614
8615
8616
8617
8618
8619
8620
8621
8622
8623
8624
8625
8626
8627
8628
8629
8630
8631
8632
8633
8634
8635
8636
8637
8638
8639
8640
8641
8642
8643
8644
8645
8646
8647
8648
8649
8650
8651
8652
8653
8654
8655
8656
8657
8658
8659
8660
8661
8662
8663
8664
8665
8666
8667
8668
8669
8670
8671
8672
8673
8674
8675
8676
8677
8678
8679
8680
8681
8682
8683
8684
8685
8686
8687
8688
8689
8690
8691
8692
8693
8694
8695
8696
8697
8698
8699
8700
8701
8702
8703
8704
8705
8706
8707
8708
8709
8710
8711
8712
8713
8714
8715
8716
8717
8718
8719
8720
8721
8722
8723
8724
8725
8726
8727
8728
8729
8730
8731
8732
8733
8734
8735
8736
8737
8738
8739
8740
8741
8742
8743
8744
8745
8746
8747
8748
8749
8750
8751
8752
8753
8754
8755
8756
8757
8758
8759
8760
8761
8762
8763
8764
8765
8766
8767
8768
8769
8770
8771
8772
8773
8774
8775
8776
8777
8778
8779
8780
8781
8782
8783
8784
8785
8786
8787
8788
8789
8790
8791
8792
8793
8794
8795
8796
8797
8798
8799
8800
8801
8802
8803
8804
8805
8806
8807
8808
8809
8810
8811
8812
8813
8814
8815
8816
8817
8818
8819
8820
8821
8822
8823
8824
8825
8826
8827
8828
8829
8830
8831
8832
8833
8834
8835
8836
8837
8838
8839
8840
8841
8842
8843
8844
8845
8846
8847
8848
8849
8850
8851
8852
8853
8854
8855
8856
8857
8858
8859
8860
8861
8862
8863
8864
8865
8866
8867
8868
8869
8870
8871
8872
8873
8874
8875
8876
8877
8878
8879
8880
8881
8882
8883
8884
8885
8886
8887
8888
8889
8890
8891
8892
8893
8894
8895
8896
8897
8898
8899
8900
8901
8902
8903
8904
8905
8906
8907
8908
8909
8910
8911
8912
8913
8914
8915
8916
8917
8918
8919
8920
8921
8922
8923
8924
8925
8926
8927
8928
8929
8930
8931
8932
8933
8934
8935
8936
8937
8938
8939
8940
8941
8942
8943
8944
8945
8946
8947
8948
8949
8950
8951
8952
8953
8954
8955
8956
8957
8958
8959
8960
8961
8962
8963
8964
8965
8966
8967
8968
8969
8970
8971
8972
8973
8974
8975
8976
8977
8978
8979
8980
8981
8982
8983
8984
8985
8986
8987
8988
8989
8990
8991
8992
8993
8994
8995
8996
8997
8998
8999
9000
9001
9002
9003
9004
9005
9006
9007
9008
9009
9010
9011
9012
9013
9014
9015
9016
9017
9018
9019
9020
9021
9022
9023
9024
9025
9026
9027
9028
9029
9030
9031
9032
9033
9034
9035
9036
9037
9038
9039
9040
9041
9042
9043
9044
9045
9046
9047
9048
9049
9050
9051
9052
9053
9054
9055
9056
9057
9058
9059
9060
9061
9062
9063
9064
9065
9066
9067
9068
9069
9070
9071
9072
9073
9074
9075
9076
9077
9078
9079
9080
9081
9082
9083
9084
9085
9086
9087
9088
9089
9090
9091
9092
9093
9094
9095
9096
9097
9098
9099
9100
9101
9102
9103
9104
9105
9106
9107
9108
9109
9110
9111
9112
9113
9114
9115
9116
9117
9118
9119
9120
9121
9122
9123
9124
9125
9126
9127
9128
9129
9130
9131
9132
9133
9134
9135
9136
9137
9138
9139
9140
9141
9142
9143
9144
9145
9146
9147
9148
9149
9150
9151
9152
9153
9154
9155
9156
9157
9158
9159
9160
9161
9162
9163
9164
9165
9166
9167
9168
9169
9170
9171
9172
9173
9174
9175
9176
9177
9178
9179
9180
9181
9182
9183
9184
9185
9186
9187
9188
9189
9190
9191
9192
9193
9194
9195
9196
9197
9198
9199
9200
9201
9202
9203
9204
9205
9206
9207
9208
9209
9210
9211
9212
9213
9214
9215
9216
9217
9218
9219
9220
9221
9222
9223
9224
9225
9226
9227
9228
9229
9230
9231
9232
9233
9234
9235
9236
9237
9238
9239
9240
9241
9242
9243
9244
9245
9246
9247
9248
9249
9250
9251
9252
9253
9254
9255
9256
9257
9258
9259
9260
9261
9262
9263
9264
9265
9266
9267
9268
9269
9270
9271
9272
9273
9274
9275
9276
9277
9278
9279
9280
9281
9282
9283
9284
9285
9286
9287
9288
9289
9290
9291
9292
9293
9294
9295
9296
9297
9298
9299
9300
9301
9302
9303
9304
9305
9306
9307
9308
9309
9310
9311
9312
9313
9314
9315
9316
9317
9318
9319
9320
9321
9322
9323
9324
9325
9326
9327
9328
9329
9330
9331
9332
9333
9334
9335
9336
9337
9338
9339
9340
9341
9342
9343
9344
9345
9346
9347
9348
9349
9350
9351
9352
9353
9354
9355
9356
9357
9358
9359
9360
9361
9362
9363
9364
9365
9366
9367
9368
9369
9370
9371
9372
9373
9374
9375
9376
9377
9378
9379
9380
9381
9382
9383
9384
9385
9386
9387
9388
9389
9390
9391
9392
9393
9394
9395
9396
9397
9398
9399
9400
9401
9402
9403
9404
9405
9406
9407
9408
9409
9410
9411
9412
9413
9414
9415
9416
9417
9418
9419
9420
9421
9422
9423
9424
9425
9426
9427
9428
9429
9430
9431
9432
9433
9434
9435
9436
9437
9438
9439
9440
9441
9442
9443
9444
9445
9446
9447
9448
9449
9450
9451
9452
9453
9454
9455
9456
9457
9458
9459
9460
9461
9462
9463
9464
9465
9466
9467
9468
9469
9470
9471
9472
9473
9474
9475
9476
9477
9478
9479
9480
9481
9482
9483
9484
9485
9486
9487
9488
9489
9490
9491
9492
9493
9494
9495
9496
9497
9498
9499
9500
9501
9502
9503
9504
9505
9506
9507
9508
9509
9510
9511
9512
9513
9514
9515
9516
9517
9518
9519
9520
9521
9522
9523
9524
9525
9526
9527
9528
9529
9530
9531
9532
9533
9534
9535
9536
9537
9538
9539
9540
9541
9542
9543
9544
9545
9546
9547
9548
9549
9550
9551
9552
9553
9554
9555
9556
9557
9558
9559
9560
9561
9562
9563
9564
9565
9566
9567
9568
9569
9570
9571
9572
9573
9574
9575
9576
9577
9578
9579
9580
9581
9582
9583
9584
9585
9586
9587
9588
9589
9590
9591
9592
9593
9594
9595
9596
9597
9598
9599
9600
9601
9602
9603
9604
9605
9606
9607
9608
9609
9610
9611
9612
9613
9614
9615
9616
9617
9618
9619
9620
9621
9622
9623
9624
9625
9626
9627
9628
9629
9630
9631
9632
9633
9634
9635
9636
9637
9638
9639
9640
9641
9642
9643
9644
9645
9646
9647
9648
9649
9650
9651
9652
9653
9654
9655
9656
9657
9658
9659
9660
9661
9662
9663
9664
9665
9666
9667
9668
9669
9670
9671
9672
9673
9674
9675
9676
9677
9678
9679
9680
9681
9682
9683
9684
9685
9686
9687
9688
9689
9690
9691
9692
9693
9694
9695
9696
9697
9698
9699
9700
9701
9702
9703
9704
9705
9706
9707
9708
9709
9710
9711
9712
9713
9714
9715
9716
9717
9718
9719
9720
9721
9722
9723
9724
9725
9726
9727
9728
9729
9730
9731
9732
9733
9734
9735
9736
9737
9738
9739
9740
9741
9742
9743
9744
9745
9746
9747
9748
9749
9750
9751
9752
9753
9754
9755
9756
9757
9758
9759
9760
9761
9762
9763
9764
9765
9766
9767
9768
9769
9770
9771
9772
9773
9774
9775
9776
9777
9778
9779
9780
9781
9782
9783
9784
9785
9786
9787
9788
9789
9790
9791
9792
9793
9794
9795
9796
9797
9798
9799
9800
9801
9802
9803
9804
9805
9806
9807
9808
9809
9810
9811
9812
9813
9814
9815
9816
9817
9818
9819
9820
9821
9822
9823
9824
9825
9826
9827
9828
9829
9830
9831
9832
9833
9834
9835
9836
9837
9838
9839
9840
9841
9842
9843
9844
9845
9846
9847
9848
9849
9850
9851
9852
9853
9854
9855
9856
9857
9858
9859
9860
9861
9862
9863
9864
9865
9866
9867
9868
9869
9870
9871
9872
9873
9874
9875
9876
9877
9878
9879
9880
9881
9882
9883
9884
9885
9886
9887
9888
9889
9890
9891
9892
9893
9894
9895
9896
9897
9898
9899
9900
9901
9902
9903
9904
9905
9906
9907
9908
9909
9910
9911
9912
9913
9914
9915
9916
9917
9918
9919
9920
9921
9922
9923
9924
9925
9926
9927
9928
9929
9930
9931
9932
9933
9934
9935
9936
9937
9938
9939
9940
9941
9942
9943
9944
9945
9946
9947
9948
9949
9950
9951
9952
9953
9954
9955
9956
9957
9958
9959
9960
9961
9962
9963
9964
9965
9966
9967
9968
9969
9970
9971
9972
9973
9974
9975
9976
9977
9978
9979
9980
9981
9982
9983
9984
9985
9986
9987
9988
9989
9990
9991
9992
9993
9994
9995
9996
9997
9998
9999
10000
10001
10002
10003
10004
10005
10006
10007
10008
10009
10010
10011
10012
10013
10014
10015
10016
10017
10018
10019
10020
10021
10022
10023
10024
10025
10026
10027
10028
10029
10030
10031
10032
10033
10034
10035
10036
10037
10038
10039
10040
10041
10042
10043
10044
10045
10046
10047
10048
10049
10050
10051
10052
10053
10054
10055
10056
10057
10058
10059
10060
10061
10062
10063
10064
10065
10066
10067
10068
10069
10070
10071
10072
10073
10074
10075
10076
10077
10078
10079
10080
10081
10082
10083
10084
10085
10086
10087
10088
10089
10090
10091
10092
10093
10094
10095
10096
10097
10098
10099
10100
10101
10102
10103
10104
10105
10106
10107
10108
10109
10110
10111
10112
10113
10114
10115
10116
10117
10118
10119
10120
10121
10122
10123
10124
10125
10126
10127
10128
10129
10130
10131
10132
10133
10134
10135
10136
10137
10138
10139
10140
10141
10142
10143
10144
10145
10146
10147
10148
10149
10150
10151
10152
10153
10154
10155
10156
10157
10158
10159
10160
10161
10162
10163
10164
10165
10166
10167
10168
10169
10170
10171
10172
10173
10174
10175
10176
10177
10178
10179
10180
10181
10182
10183
10184
10185
10186
10187
10188
10189
10190
10191
10192
10193
10194
10195
10196
10197
10198
10199
10200
10201
10202
10203
10204
10205
10206
10207
10208
10209
10210
10211
10212
10213
10214
10215
10216
10217
10218
10219
10220
10221
10222
10223
10224
10225
10226
10227
10228
10229
10230
10231
10232
10233
10234
10235
10236
10237
10238
10239
10240
10241
10242
10243
10244
10245
10246
10247
10248
10249
10250
10251
10252
10253
10254
10255
10256
10257
10258
10259
10260
10261
10262
10263
10264
10265
10266
10267
10268
10269
10270
10271
10272
10273
10274
10275
10276
10277
10278
10279
10280
10281
10282
10283
10284
10285
10286
10287
10288
10289
10290
10291
10292
10293
10294
10295
10296
10297
10298
10299
10300
10301
10302
10303
10304
10305
10306
10307
10308
10309
10310
10311
10312
10313
10314
10315
10316
10317
10318
10319
10320
10321
10322
10323
10324
10325
10326
10327
10328
10329
10330
10331
10332
10333
10334
10335
10336
10337
10338
10339
10340
10341
10342
10343
10344
10345
10346
10347
10348
10349
10350
10351
10352
10353
10354
10355
10356
10357
10358
10359
10360
10361
10362
10363
10364
10365
10366
10367
10368
10369
10370
10371
10372
10373
10374
10375
10376
10377
10378
10379
10380
10381
10382
10383
10384
10385
10386
10387
10388
10389
10390
10391
10392
10393
10394
10395
10396
10397
10398
10399
10400
10401
10402
10403
10404
10405
10406
10407
10408
10409
10410
10411
10412
10413
10414
10415
10416
10417
10418
10419
10420
10421
10422
10423
10424
10425
10426
10427
10428
10429
10430
10431
10432
10433
10434
10435
10436
10437
10438
10439
10440
10441
10442
10443
10444
10445
10446
10447
10448
10449
10450
10451
10452
10453
10454
10455
10456
10457
10458
10459
10460
10461
10462
10463
10464
10465
10466
10467
10468
10469
10470
10471
10472
10473
10474
10475
10476
10477
10478
10479
10480
10481
10482
10483
10484
10485
10486
10487
10488
10489
10490
10491
10492
10493
10494
10495
10496
10497
10498
10499
10500
10501
10502
10503
10504
10505
10506
10507
10508
10509
10510
10511
10512
10513
10514
10515
10516
10517
10518
10519
10520
10521
10522
10523
10524
10525
10526
10527
10528
10529
10530
10531
10532
10533
10534
10535
10536
10537
10538
10539
10540
10541
10542
10543
10544
10545
10546
10547
10548
10549
10550
10551
10552
10553
10554
10555
10556
10557
10558
10559
10560
10561
10562
10563
10564
10565
10566
10567
10568
10569
10570
10571
10572
10573
10574
10575
10576
10577
10578
10579
10580
10581
10582
10583
10584
10585
10586
10587
10588
10589
10590
10591
10592
10593
10594
10595
10596
10597
10598
10599
10600
10601
10602
10603
10604
10605
10606
10607
10608
10609
10610
10611
10612
10613
10614
10615
10616
10617
10618
10619
10620
10621
10622
10623
10624
10625
10626
10627
10628
10629
10630
10631
10632
10633
10634
10635
10636
10637
10638
10639
10640
10641
10642
10643
10644
10645
10646
10647
10648
10649
10650
10651
10652
10653
10654
10655
10656
10657
10658
10659
10660
10661
10662
10663
10664
10665
10666
10667
10668
10669
10670
10671
10672
10673
10674
10675
10676
10677
10678
10679
10680
10681
10682
10683
10684
10685
10686
10687
10688
10689
10690
10691
10692
10693
10694
10695
10696
10697
10698
10699
10700
10701
10702
10703
10704
10705
10706
10707
10708
10709
10710
10711
10712
10713
10714
10715
10716
10717
10718
10719
10720
10721
10722
10723
10724
10725
10726
10727
10728
10729
10730
10731
10732
10733
10734
10735
10736
10737
10738
10739
10740
10741
10742
10743
10744
10745
10746
10747
10748
10749
10750
10751
10752
10753
10754
10755
10756
10757
10758
10759
10760
10761
10762
10763
10764
10765
10766
10767
10768
10769
10770
10771
10772
10773
10774
10775
10776
10777
10778
10779
10780
10781
10782
10783
10784
10785
10786
10787
10788
10789
10790
10791
10792
10793
10794
10795
10796
10797
10798
10799
10800
10801
10802
10803
10804
10805
10806
10807
10808
10809
10810
10811
10812
10813
10814
10815
10816
10817
10818
10819
10820
10821
10822
10823
10824
10825
10826
10827
10828
10829
10830
10831
10832
10833
10834
10835
10836
10837
10838
10839
10840
10841
10842
10843
10844
10845
10846
10847
10848
10849
10850
10851
10852
10853
10854
10855
10856
10857
10858
10859
10860
10861
10862
10863
10864
10865
10866
10867
10868
10869
10870
10871
10872
10873
10874
10875
10876
10877
10878
10879
10880
10881
10882
10883
10884
10885
10886
10887
10888
10889
10890
10891
10892
10893
10894
10895
10896
10897
10898
10899
10900
10901
10902
10903
10904
10905
10906
10907
10908
10909
10910
10911
10912
10913
10914
10915
10916
10917
10918
10919
10920
10921
10922
10923
10924
10925
10926
10927
10928
10929
10930
10931
10932
10933
10934
10935
10936
10937
10938
10939
10940
10941
10942
10943
10944
10945
10946
10947
10948
10949
10950
10951
10952
10953
10954
10955
10956
10957
10958
10959
10960
10961
10962
10963
10964
10965
10966
10967
10968
10969
10970
10971
10972
10973
10974
10975
10976
10977
10978
10979
10980
10981
10982
10983
10984
10985
10986
10987
10988
10989
10990
10991
10992
10993
10994
10995
10996
10997
10998
10999
11000
11001
11002
11003
11004
11005
11006
11007
11008
11009
11010
11011
11012
11013
11014
11015
11016
11017
11018
11019
11020
11021
11022
11023
11024
11025
11026
11027
11028
11029
11030
11031
11032
11033
11034
11035
11036
11037
11038
11039
11040
11041
11042
11043
11044
11045
11046
11047
11048
11049
11050
11051
11052
11053
11054
11055
11056
11057
11058
11059
11060
11061
11062
11063
11064
11065
11066
11067
11068
11069
11070
11071
11072
11073
11074
11075
11076
11077
11078
11079
11080
11081
11082
11083
11084
11085
11086
11087
11088
11089
11090
11091
11092
11093
11094
11095
11096
11097
11098
11099
11100
11101
11102
11103
11104
11105
11106
11107
11108
11109
11110
11111
11112
11113
11114
11115
11116
11117
11118
11119
11120
11121
11122
11123
11124
11125
11126
11127
11128
11129
11130
11131
11132
11133
11134
11135
11136
11137
11138
11139
11140
11141
11142
11143
11144
11145
11146
11147
11148
11149
11150
11151
11152
11153
11154
11155
11156
11157
11158
11159
11160
11161
11162
11163
11164
11165
11166
11167
11168
11169
11170
11171
11172
11173
11174
11175
11176
11177
11178
11179
11180
11181
11182
11183
11184
11185
11186
11187
11188
11189
11190
11191
11192
11193
11194
11195
11196
11197
11198
11199
11200
11201
11202
11203
11204
11205
11206
11207
11208
11209
11210
11211
11212
11213
11214
11215
11216
11217
11218
11219
11220
11221
11222
11223
11224
11225
11226
11227
11228
11229
11230
11231
11232
11233
11234
11235
11236
11237
11238
11239
11240
11241
11242
11243
11244
11245
11246
11247
11248
11249
11250
11251
11252
11253
11254
11255
11256
11257
11258
11259
11260
11261
11262
11263
11264
11265
11266
11267
11268
11269
11270
11271
11272
11273
11274
11275
11276
11277
11278
11279
11280
11281
11282
11283
11284
11285
11286
11287
11288
11289
11290
11291
11292
11293
11294
11295
11296
11297
11298
11299
11300
11301
11302
11303
11304
11305
11306
11307
11308
11309
11310
11311
11312
11313
11314
11315
11316
11317
11318
11319
11320
11321
11322
11323
11324
11325
11326
11327
11328
11329
11330
11331
11332
11333
11334
11335
11336
11337
11338
11339
11340
11341
11342
11343
11344
11345
11346
11347
11348
11349
11350
11351
11352
11353
11354
11355
11356
11357
11358
11359
11360
11361
11362
11363
11364
11365
11366
11367
11368
11369
11370
11371
11372
11373
11374
11375
11376
11377
11378
11379
11380
11381
11382
11383
11384
11385
11386
11387
11388
11389
11390
11391
11392
11393
11394
11395
11396
11397
11398
11399
11400
11401
11402
11403
11404
11405
11406
11407
11408
11409
11410
11411
11412
11413
11414
11415
11416
11417
11418
11419
11420
11421
11422
11423
11424
11425
11426
11427
11428
11429
11430
11431
11432
11433
11434
11435
11436
11437
11438
11439
11440
11441
11442
11443
11444
11445
11446
11447
11448
11449
11450
11451
11452
11453
11454
11455
11456
11457
11458
11459
11460
11461
11462
11463
11464
11465
11466
11467
11468
11469
11470
11471
11472
11473
11474
11475
11476
11477
11478
11479
11480
11481
11482
11483
11484
11485
11486
11487
11488
11489
11490
11491
11492
11493
11494
11495
11496
11497
11498
11499
11500
11501
11502
11503
11504
11505
11506
11507
11508
11509
11510
11511
11512
11513
11514
11515
11516
11517
11518
11519
11520
11521
11522
11523
11524
11525
11526
11527
11528
11529
11530
11531
11532
11533
11534
11535
11536
11537
11538
11539
11540
11541
11542
11543
11544
11545
11546
11547
11548
11549
11550
11551
11552
11553
11554
11555
11556
11557
11558
11559
11560
11561
11562
11563
11564
11565
11566
11567
11568
11569
11570
11571
11572
11573
11574
11575
11576
11577
11578
11579
11580
11581
11582
11583
11584
11585
11586
11587
11588
11589
11590
11591
11592
11593
11594
11595
11596
11597
11598
11599
11600
11601
11602
11603
11604
11605
11606
11607
11608
11609
11610
11611
11612
11613
11614
11615
11616
11617
11618
11619
11620
11621
11622
11623
11624
11625
11626
11627
11628
11629
11630
11631
11632
11633
11634
11635
11636
11637
11638
11639
11640
11641
11642
11643
11644
11645
11646
11647
11648
11649
11650
11651
11652
11653
11654
11655
11656
11657
11658
11659
11660
11661
11662
11663
11664
11665
11666
11667
11668
11669
11670
11671
11672
11673
11674
11675
11676
11677
11678
11679
11680
11681
11682
11683
11684
11685
11686
11687
11688
11689
11690
11691
11692
11693
11694
11695
11696
11697
11698
11699
11700
11701
11702
11703
11704
11705
11706
11707
11708
11709
11710
11711
11712
11713
11714
11715
11716
11717
11718
11719
11720
11721
11722
11723
11724
11725
11726
11727
11728
11729
11730
11731
11732
11733
11734
11735
11736
11737
11738
11739
11740
11741
11742
11743
11744
11745
11746
11747
11748
11749
11750
11751
11752
11753
11754
11755
11756
11757
11758
11759
11760
11761
11762
11763
11764
11765
11766
11767
11768
11769
11770
11771
11772
11773
11774
11775
11776
11777
11778
11779
11780
11781
11782
11783
11784
11785
11786
11787
11788
11789
11790
11791
11792
11793
11794
11795
11796
11797
11798
11799
11800
11801
11802
11803
11804
11805
11806
11807
11808
11809
11810
11811
11812
11813
11814
11815
11816
11817
11818
11819
11820
11821
11822
11823
11824
11825
11826
11827
11828
11829
11830
11831
11832
11833
11834
11835
11836
11837
11838
11839
11840
11841
11842
11843
11844
11845
11846
11847
11848
11849
11850
11851
11852
11853
11854
11855
11856
11857
11858
11859
11860
11861
11862
11863
11864
11865
11866
11867
11868
11869
11870
11871
11872
11873
11874
11875
11876
11877
11878
11879
11880
11881
11882
11883
11884
11885
11886
11887
11888
11889
11890
11891
11892
11893
11894
11895
11896
11897
11898
11899
11900
11901
11902
11903
11904
11905
11906
11907
11908
11909
11910
11911
11912
11913
11914
11915
11916
11917
11918
11919
11920
11921
11922
11923
11924
11925
11926
11927
11928
11929
11930
11931
11932
11933
11934
11935
11936
11937
11938
11939
11940
11941
11942
11943
11944
11945
11946
11947
11948
11949
11950
11951
11952
11953
11954
11955
11956
11957
11958
11959
11960
11961
11962
11963
11964
11965
11966
11967
11968
11969
11970
11971
11972
11973
11974
11975
11976
11977
11978
11979
11980
11981
11982
11983
11984
11985
11986
11987
11988
11989
11990
11991
11992
11993
11994
11995
11996
11997
11998
11999
12000
12001
12002
12003
12004
12005
12006
12007
12008
12009
12010
12011
12012
12013
12014
12015
12016
12017
12018
12019
12020
12021
12022
12023
12024
12025
12026
12027
12028
12029
12030
12031
12032
12033
12034
12035
12036
12037
12038
12039
12040
12041
12042
12043
12044
12045
12046
12047
12048
12049
12050
12051
12052
12053
12054
12055
12056
12057
12058
12059
12060
12061
12062
12063
12064
12065
12066
12067
12068
12069
12070
12071
12072
12073
12074
12075
12076
12077
12078
12079
12080
12081
12082
12083
12084
12085
12086
12087
12088
12089
12090
12091
12092
12093
12094
12095
12096
12097
12098
12099
12100
12101
12102
12103
12104
12105
12106
12107
12108
12109
12110
12111
12112
12113
12114
12115
12116
12117
12118
12119
12120
12121
12122
12123
12124
12125
12126
12127
12128
12129
12130
12131
12132
12133
12134
12135
12136
12137
12138
12139
12140
12141
12142
12143
12144
12145
12146
12147
12148
12149
12150
12151
12152
12153
12154
12155
12156
12157
12158
12159
12160
12161
12162
12163
12164
12165
12166
12167
12168
12169
12170
12171
12172
12173
12174
12175
12176
12177
12178
12179
12180
12181
12182
12183
12184
12185
12186
12187
12188
12189
12190
12191
12192
12193
12194
12195
12196
12197
12198
12199
12200
12201
12202
12203
12204
12205
12206
12207
12208
12209
12210
12211
12212
12213
12214
12215
12216
12217
12218
12219
12220
12221
12222
12223
12224
12225
12226
12227
12228
12229
12230
12231
12232
12233
12234
12235
12236
12237
12238
12239
12240
12241
12242
12243
12244
12245
12246
12247
12248
12249
12250
12251
12252
12253
12254
12255
12256
12257
12258
12259
12260
12261
12262
12263
12264
12265
12266
12267
12268
12269
12270
12271
12272
12273
12274
12275
12276
12277
12278
12279
12280
12281
12282
12283
12284
12285
12286
12287
12288
12289
12290
12291
12292
12293
12294
12295
12296
12297
12298
12299
12300
12301
12302
12303
12304
12305
12306
12307
12308
12309
12310
12311
12312
12313
12314
12315
12316
12317
12318
12319
12320
12321
12322
12323
12324
12325
12326
12327
12328
12329
12330
12331
12332
12333
12334
12335
12336
12337
12338
12339
12340
12341
12342
12343
12344
12345
12346
12347
12348
12349
12350
12351
12352
12353
12354
12355
12356
12357
12358
12359
12360
12361
12362
12363
12364
12365
12366
12367
12368
12369
12370
12371
12372
12373
12374
12375
12376
12377
12378
12379
12380
12381
12382
12383
12384
12385
12386
12387
12388
12389
12390
12391
12392
12393
12394
12395
12396
12397
12398
12399
12400
12401
12402
12403
12404
12405
12406
12407
12408
12409
12410
12411
12412
12413
12414
12415
12416
12417
12418
12419
12420
12421
12422
12423
12424
12425
12426
12427
12428
12429
12430
12431
12432
12433
12434
12435
12436
12437
12438
12439
12440
12441
12442
12443
12444
12445
12446
12447
12448
12449
12450
12451
12452
12453
12454
12455
12456
12457
12458
12459
12460
12461
12462
12463
12464
12465
12466
12467
12468
12469
12470
12471
12472
12473
12474
12475
12476
12477
12478
12479
12480
12481
12482
12483
12484
12485
12486
12487
12488
12489
12490
12491
12492
12493
12494
12495
12496
12497
12498
12499
12500
12501
12502
12503
12504
12505
12506
12507
12508
12509
12510
12511
12512
12513
12514
12515
12516
12517
12518
12519
12520
12521
12522
12523
12524
12525
12526
12527
12528
12529
12530
12531
12532
12533
12534
12535
12536
12537
12538
12539
12540
12541
12542
12543
12544
12545
12546
12547
12548
12549
12550
12551
12552
12553
12554
12555
12556
12557
12558
12559
12560
12561
12562
12563
12564
12565
12566
12567
12568
12569
12570
12571
12572
12573
12574
12575
12576
12577
12578
12579
12580
12581
12582
12583
12584
12585
12586
12587
12588
12589
12590
12591
12592
12593
12594
12595
12596
12597
12598
12599
12600
12601
12602
12603
12604
12605
12606
12607
12608
12609
12610
12611
12612
12613
12614
12615
12616
12617
12618
12619
12620
12621
12622
12623
12624
12625
12626
12627
12628
12629
12630
12631
12632
12633
12634
12635
12636
12637
12638
12639
12640
12641
12642
12643
12644
12645
12646
12647
12648
12649
12650
12651
12652
12653
12654
12655
12656
12657
12658
12659
12660
12661
12662
12663
12664
12665
12666
12667
12668
12669
12670
12671
12672
12673
12674
12675
12676
12677
12678
12679
12680
12681
12682
12683
12684
12685
12686
12687
12688
12689
12690
12691
12692
12693
12694
12695
12696
12697
12698
12699
12700
12701
12702
12703
12704
12705
12706
12707
12708
12709
12710
12711
12712
12713
12714
12715
12716
12717
12718
12719
12720
12721
12722
12723
12724
12725
12726
12727
12728
12729
12730
12731
12732
12733
12734
12735
12736
12737
12738
12739
12740
12741
12742
12743
12744
12745
12746
12747
12748
12749
12750
12751
12752
12753
12754
12755
12756
12757
12758
12759
12760
12761
12762
12763
12764
12765
12766
12767
12768
12769
12770
12771
12772
12773
12774
12775
12776
12777
12778
12779
12780
12781
12782
12783
12784
12785
12786
12787
12788
12789
12790
12791
12792
12793
12794
12795
12796
12797
12798
12799
12800
12801
12802
12803
12804
12805
12806
12807
12808
12809
12810
12811
12812
12813
12814
12815
12816
12817
12818
12819
12820
12821
12822
12823
12824
12825
12826
12827
12828
12829
12830
12831
12832
12833
12834
12835
12836
12837
12838
12839
12840
12841
12842
12843
12844
12845
12846
12847
12848
12849
12850
12851
12852
12853
12854
12855
12856
12857
12858
12859
12860
12861
12862
12863
12864
12865
12866
12867
12868
12869
12870
12871
12872
12873
12874
12875
12876
12877
12878
12879
12880
12881
12882
12883
12884
12885
12886
12887
12888
12889
12890
12891
12892
12893
12894
12895
12896
12897
12898
12899
12900
12901
12902
12903
12904
12905
12906
12907
12908
12909
12910
12911
12912
12913
12914
12915
12916
12917
12918
12919
12920
12921
12922
12923
12924
12925
12926
12927
12928
12929
12930
12931
12932
12933
12934
12935
12936
12937
12938
12939
12940
12941
12942
12943
12944
12945
12946
12947
12948
12949
12950
12951
12952
12953
12954
12955
12956
12957
12958
12959
12960
12961
12962
12963
12964
12965
12966
12967
12968
12969
12970
12971
12972
12973
12974
12975
12976
12977
12978
12979
12980
12981
12982
12983
12984
12985
12986
12987
12988
12989
12990
12991
12992
12993
12994
12995
12996
12997
12998
12999
13000
13001
13002
13003
13004
13005
13006
13007
13008
13009
13010
13011
13012
13013
13014
13015
13016
13017
13018
13019
13020
13021
13022
13023
13024
13025
13026
13027
13028
13029
13030
13031
13032
13033
13034
13035
13036
13037
13038
13039
13040
13041
13042
13043
13044
13045
13046
13047
13048
13049
13050
13051
13052
13053
13054
13055
13056
13057
13058
13059
13060
13061
13062
13063
13064
13065
13066
13067
13068
13069
13070
13071
13072
13073
13074
13075
13076
13077
13078
13079
13080
13081
13082
13083
13084
13085
13086
13087
13088
13089
13090
13091
13092
13093
13094
13095
13096
13097
13098
13099
13100
13101
13102
13103
13104
13105
13106
13107
13108
13109
13110
13111
13112
13113
13114
13115
13116
13117
13118
13119
13120
13121
13122
13123
13124
13125
13126
13127
13128
13129
13130
13131
13132
13133
13134
13135
13136
13137
13138
13139
13140
13141
13142
13143
13144
13145
13146
13147
13148
13149
13150
13151
13152
13153
13154
13155
13156
13157
13158
13159
13160
13161
13162
13163
13164
13165
13166
13167
13168
13169
13170
13171
13172
13173
13174
13175
13176
13177
13178
13179
13180
13181
13182
13183
13184
13185
13186
13187
13188
13189
13190
13191
13192
13193
13194
13195
13196
13197
13198
13199
13200
13201
13202
13203
13204
13205
13206
13207
13208
13209
13210
13211
13212
13213
13214
13215
13216
13217
13218
13219
13220
13221
13222
13223
13224
13225
13226
13227
13228
13229
13230
13231
13232
13233
13234
13235
13236
13237
13238
13239
13240
13241
13242
13243
13244
13245
13246
13247
13248
13249
13250
13251
13252
13253
13254
13255
13256
13257
13258
13259
13260
13261
13262
13263
13264
13265
13266
13267
13268
13269
13270
13271
13272
13273
13274
13275
13276
13277
13278
13279
13280
13281
13282
13283
13284
13285
13286
13287
13288
13289
13290
13291
13292
13293
13294
13295
13296
13297
13298
13299
13300
13301
13302
13303
13304
13305
13306
13307
13308
13309
13310
13311
13312
13313
13314
13315
13316
13317
13318
13319
13320
13321
13322
13323
13324
13325
13326
13327
13328
13329
13330
13331
13332
13333
13334
13335
13336
13337
13338
13339
13340
13341
13342
13343
13344
13345
13346
13347
13348
13349
13350
13351
13352
13353
13354
13355
13356
13357
13358
13359
13360
13361
13362
13363
13364
13365
13366
13367
13368
13369
13370
13371
13372
13373
13374
13375
13376
13377
13378
13379
13380
13381
13382
13383
13384
13385
13386
13387
13388
13389
13390
13391
13392
13393
13394
13395
13396
13397
13398
13399
13400
13401
13402
13403
13404
13405
13406
13407
13408
13409
13410
13411
13412
13413
13414
13415
13416
13417
13418
13419
13420
13421
13422
13423
13424
13425
13426
13427
13428
13429
13430
13431
13432
13433
13434
13435
13436
13437
13438
13439
13440
13441
13442
13443
13444
13445
13446
13447
13448
13449
13450
13451
13452
13453
13454
13455
13456
13457
13458
13459
13460
13461
13462
13463
13464
13465
13466
13467
13468
13469
13470
13471
13472
13473
13474
13475
13476
13477
13478
13479
13480
13481
13482
13483
13484
13485
13486
13487
13488
13489
13490
13491
13492
13493
13494
13495
13496
13497
13498
13499
13500
13501
13502
13503
13504
13505
13506
13507
13508
13509
13510
13511
13512
13513
13514
13515
13516
13517
13518
13519
13520
13521
13522
13523
13524
13525
13526
13527
13528
13529
13530
13531
13532
13533
13534
13535
13536
13537
13538
13539
13540
13541
13542
13543
13544
13545
13546
13547
13548
13549
13550
13551
13552
13553
13554
13555
13556
13557
13558
13559
13560
13561
13562
13563
13564
13565
13566
13567
13568
13569
13570
13571
13572
13573
13574
13575
13576
13577
13578
13579
13580
13581
13582
13583
13584
13585
13586
13587
13588
13589
13590
13591
13592
13593
13594
13595
13596
13597
13598
13599
13600
13601
13602
13603
13604
13605
13606
13607
13608
13609
13610
13611
13612
13613
13614
13615
13616
13617
13618
13619
13620
13621
13622
13623
13624
13625
13626
13627
13628
13629
13630
13631
13632
13633
13634
13635
13636
13637
13638
13639
13640
13641
13642
13643
13644
13645
13646
13647
13648
13649
13650
13651
13652
13653
13654
13655
13656
13657
13658
13659
13660
13661
13662
13663
13664
13665
13666
13667
13668
13669
13670
13671
13672
13673
13674
13675
13676
13677
13678
13679
13680
13681
13682
13683
13684
13685
13686
13687
13688
13689
13690
13691
13692
13693
13694
13695
13696
13697
13698
13699
13700
13701
13702
13703
13704
13705
13706
13707
13708
13709
13710
13711
13712
13713
13714
13715
13716
13717
13718
13719
13720
13721
13722
13723
13724
13725
13726
13727
13728
13729
13730
13731
13732
13733
13734
13735
13736
13737
13738
13739
13740
13741
13742
13743
13744
13745
13746
13747
13748
13749
13750
13751
13752
13753
13754
13755
13756
13757
13758
13759
13760
13761
13762
13763
13764
13765
13766
13767
13768
13769
13770
13771
13772
13773
13774
13775
13776
13777
13778
13779
13780
13781
13782
13783
13784
13785
13786
13787
13788
13789
13790
13791
13792
13793
13794
13795
13796
13797
13798
13799
13800
13801
13802
13803
13804
13805
13806
13807
13808
13809
13810
13811
13812
13813
13814
13815
13816
13817
13818
13819
13820
13821
13822
13823
13824
13825
13826
13827
13828
13829
13830
13831
13832
13833
13834
13835
13836
13837
13838
13839
13840
13841
13842
13843
13844
13845
13846
13847
13848
13849
13850
13851
13852
13853
13854
13855
13856
13857
13858
13859
13860
13861
13862
13863
13864
13865
13866
13867
13868
13869
13870
13871
13872
13873
13874
13875
13876
13877
13878
13879
13880
13881
13882
13883
13884
13885
13886
13887
13888
13889
13890
13891
13892
13893
13894
13895
13896
13897
13898
13899
13900
13901
13902
13903
13904
13905
13906
13907
13908
13909
13910
13911
13912
13913
13914
13915
13916
13917
13918
13919
13920
13921
13922
13923
13924
13925
13926
13927
13928
13929
13930
13931
13932
13933
13934
13935
13936
13937
13938
13939
13940
13941
13942
13943
13944
13945
13946
13947
13948
13949
13950
13951
13952
13953
13954
13955
13956
13957
13958
13959
13960
13961
13962
13963
13964
13965
13966
13967
13968
13969
13970
13971
13972
13973
13974
13975
13976
13977
13978
13979
13980
13981
13982
13983
13984
13985
13986
13987
13988
13989
13990
13991
13992
13993
13994
13995
13996
13997
13998
13999
14000
14001
14002
14003
14004
14005
14006
14007
14008
14009
14010
14011
14012
14013
14014
14015
14016
14017
14018
14019
14020
14021
14022
14023
14024
14025
14026
14027
14028
14029
14030
14031
14032
14033
14034
14035
14036
14037
14038
14039
14040
14041
14042
14043
14044
14045
14046
14047
14048
14049
14050
14051
14052
14053
14054
14055
14056
14057
14058
14059
14060
14061
14062
14063
14064
14065
14066
14067
14068
14069
14070
14071
14072
14073
14074
14075
14076
14077
14078
14079
14080
14081
14082
14083
14084
14085
14086
14087
14088
14089
14090
14091
14092
14093
14094
14095
14096
14097
14098
14099
14100
14101
14102
14103
14104
14105
14106
14107
14108
14109
14110
14111
14112
14113
14114
14115
14116
14117
14118
14119
14120
14121
14122
14123
14124
14125
14126
14127
14128
14129
14130
14131
14132
14133
14134
14135
14136
14137
14138
14139
14140
14141
14142
14143
14144
14145
14146
14147
14148
14149
14150
14151
14152
14153
14154
14155
14156
14157
14158
14159
14160
14161
14162
14163
14164
14165
14166
14167
14168
14169
14170
14171
14172
14173
14174
14175
14176
14177
14178
14179
14180
14181
14182
14183
14184
14185
14186
14187
14188
14189
14190
14191
14192
14193
14194
14195
14196
14197
14198
14199
14200
14201
14202
14203
14204
14205
14206
14207
14208
14209
14210
14211
14212
14213
14214
14215
14216
14217
14218
14219
14220
14221
14222
14223
14224
14225
14226
14227
14228
14229
14230
14231
14232
14233
14234
14235
14236
14237
14238
14239
14240
14241
14242
14243
14244
14245
14246
14247
14248
14249
14250
14251
14252
14253
14254
14255
14256
14257
14258
14259
14260
14261
14262
14263
14264
14265
14266
14267
14268
14269
14270
14271
14272
14273
14274
14275
14276
14277
14278
14279
14280
14281
14282
14283
14284
14285
14286
14287
14288
14289
14290
14291
14292
14293
14294
14295
14296
14297
14298
14299
14300
14301
14302
14303
14304
14305
14306
14307
14308
14309
14310
14311
14312
14313
14314
14315
14316
14317
14318
14319
14320
14321
14322
14323
14324
14325
14326
14327
14328
14329
14330
14331
14332
14333
14334
14335
14336
14337
14338
14339
14340
14341
14342
14343
14344
14345
14346
14347
14348
14349
14350
14351
14352
14353
14354
14355
14356
14357
14358
14359
14360
14361
14362
14363
14364
14365
14366
14367
14368
14369
14370
14371
14372
14373
14374
14375
14376
14377
14378
14379
14380
14381
14382
14383
14384
14385
14386
14387
14388
14389
14390
14391
14392
14393
14394
14395
14396
14397
14398
14399
14400
14401
14402
14403
14404
14405
14406
14407
14408
14409
14410
14411
14412
14413
14414
14415
14416
14417
14418
14419
14420
14421
14422
14423
14424
14425
14426
14427
14428
14429
14430
14431
14432
14433
14434
14435
14436
14437
14438
14439
14440
14441
14442
14443
14444
14445
14446
14447
14448
14449
14450
14451
14452
14453
14454
14455
14456
14457
14458
14459
14460
14461
14462
14463
14464
14465
14466
14467
14468
14469
14470
14471
14472
14473
14474
14475
14476
14477
14478
14479
14480
14481
14482
14483
14484
14485
14486
14487
14488
14489
14490
14491
14492
14493
14494
14495
14496
14497
14498
14499
14500
14501
14502
14503
14504
14505
14506
14507
14508
14509
14510
14511
14512
14513
14514
14515
14516
14517
14518
14519
14520
14521
14522
14523
14524
14525
14526
14527
14528
14529
14530
14531
14532
14533
14534
14535
14536
14537
14538
14539
14540
14541
14542
14543
14544
14545
14546
14547
14548
14549
14550
14551
14552
14553
14554
14555
14556
14557
14558
14559
14560
14561
14562
14563
14564
14565
14566
14567
14568
14569
14570
14571
14572
14573
14574
14575
14576
14577
14578
14579
14580
14581
14582
14583
14584
14585
14586
14587
14588
14589
14590
14591
14592
14593
14594
14595
14596
14597
14598
14599
14600
14601
14602
14603
14604
14605
14606
14607
14608
14609
14610
14611
14612
14613
14614
14615
14616
14617
14618
14619
14620
14621
14622
14623
14624
14625
14626
14627
14628
14629
14630
14631
14632
14633
14634
14635
14636
14637
14638
14639
14640
14641
14642
14643
14644
14645
14646
14647
14648
14649
14650
14651
14652
14653
14654
14655
14656
14657
14658
14659
14660
14661
14662
14663
14664
14665
14666
14667
14668
14669
14670
14671
14672
14673
14674
14675
14676
14677
14678
14679
14680
14681
14682
14683
14684
14685
14686
14687
14688
14689
14690
14691
14692
14693
14694
14695
14696
14697
14698
14699
14700
14701
14702
14703
14704
14705
14706
14707
14708
14709
14710
14711
14712
14713
14714
14715
14716
14717
14718
14719
14720
14721
14722
14723
14724
14725
14726
14727
14728
14729
14730
14731
14732
14733
14734
14735
14736
14737
14738
14739
14740
14741
14742
14743
14744
14745
14746
14747
14748
14749
14750
14751
14752
14753
14754
14755
14756
14757
14758
14759
14760
14761
14762
14763
14764
14765
14766
14767
14768
14769
14770
14771
14772
14773
14774
14775
14776
14777
14778
14779
14780
14781
14782
14783
14784
14785
14786
14787
14788
14789
14790
14791
14792
14793
14794
14795
14796
14797
14798
14799
14800
14801
14802
14803
14804
14805
14806
14807
14808
14809
14810
14811
14812
14813
14814
14815
14816
14817
14818
14819
14820
14821
14822
14823
14824
14825
14826
14827
14828
14829
14830
14831
14832
14833
14834
14835
14836
14837
14838
14839
14840
14841
14842
14843
14844
14845
14846
14847
14848
14849
14850
14851
14852
14853
14854
14855
14856
14857
14858
14859
14860
14861
14862
14863
14864
14865
14866
14867
14868
14869
14870
14871
14872
14873
14874
14875
14876
14877
14878
14879
14880
14881
14882
14883
14884
14885
14886
14887
14888
14889
14890
14891
14892
14893
14894
14895
14896
14897
14898
14899
14900
14901
14902
14903
14904
14905
14906
14907
14908
14909
14910
14911
14912
14913
14914
14915
14916
14917
14918
14919
14920
14921
14922
14923
14924
14925
14926
14927
14928
14929
14930
14931
14932
14933
14934
14935
14936
14937
14938
14939
14940
14941
14942
14943
14944
14945
14946
14947
14948
14949
14950
14951
14952
14953
14954
14955
14956
14957
14958
14959
14960
14961
14962
14963
14964
14965
14966
14967
14968
14969
14970
14971
14972
14973
14974
14975
14976
14977
14978
14979
14980
14981
14982
14983
14984
14985
14986
14987
14988
14989
14990
14991
14992
14993
14994
14995
14996
14997
14998
14999
15000
15001
15002
15003
15004
15005
15006
15007
15008
15009
15010
15011
15012
15013
15014
15015
15016
15017
15018
15019
15020
15021
15022
15023
15024
15025
15026
15027
15028
15029
15030
15031
15032
15033
15034
15035
15036
15037
15038
15039
15040
15041
15042
15043
15044
15045
15046
15047
15048
15049
15050
15051
15052
15053
15054
15055
15056
15057
15058
15059
15060
15061
15062
15063
15064
15065
15066
15067
15068
15069
15070
15071
15072
15073
15074
15075
15076
15077
15078
15079
15080
15081
15082
15083
15084
15085
15086
15087
15088
15089
15090
15091
15092
15093
15094
15095
15096
15097
15098
15099
15100
15101
15102
15103
15104
15105
15106
15107
15108
15109
15110
15111
15112
15113
15114
15115
15116
15117
15118
15119
15120
15121
15122
15123
15124
15125
15126
15127
15128
15129
15130
15131
15132
15133
15134
15135
15136
15137
15138
15139
15140
15141
15142
15143
15144
15145
15146
15147
15148
15149
15150
15151
15152
15153
15154
15155
15156
15157
15158
15159
15160
15161
15162
15163
15164
15165
15166
15167
15168
15169
15170
15171
15172
15173
15174
15175
15176
15177
15178
15179
15180
15181
15182
15183
15184
15185
15186
15187
15188
15189
15190
15191
15192
15193
15194
15195
15196
15197
15198
15199
15200
15201
15202
15203
15204
15205
15206
15207
15208
15209
15210
15211
15212
15213
15214
15215
15216
15217
15218
15219
15220
15221
15222
15223
15224
15225
15226
15227
15228
15229
15230
15231
15232
15233
15234
15235
15236
15237
15238
15239
15240
15241
15242
15243
15244
15245
15246
15247
15248
15249
15250
15251
15252
15253
15254
15255
15256
15257
15258
15259
15260
15261
15262
15263
15264
15265
15266
15267
15268
15269
15270
15271
15272
15273
15274
15275
15276
15277
15278
15279
15280
15281
15282
15283
15284
15285
15286
15287
15288
15289
15290
15291
15292
15293
15294
15295
15296
15297
15298
15299
15300
15301
15302
15303
15304
15305
15306
15307
15308
15309
15310
15311
15312
15313
15314
15315
15316
15317
15318
15319
15320
15321
15322
15323
15324
15325
15326
15327
15328
15329
15330
15331
15332
15333
15334
15335
15336
15337
15338
15339
15340
15341
15342
15343
15344
15345
15346
15347
15348
15349
15350
15351
15352
15353
15354
15355
15356
15357
15358
15359
15360
15361
15362
15363
15364
15365
15366
15367
15368
15369
15370
15371
15372
15373
15374
15375
15376
15377
15378
15379
15380
15381
15382
15383
15384
15385
15386
15387
15388
15389
15390
15391
15392
15393
15394
15395
15396
15397
15398
15399
15400
15401
15402
15403
15404
15405
15406
15407
15408
15409
15410
15411
15412
15413
15414
15415
15416
15417
15418
15419
15420
15421
15422
15423
15424
15425
15426
15427
15428
15429
15430
15431
15432
15433
15434
15435
15436
15437
15438
15439
15440
15441
15442
15443
15444
15445
15446
15447
15448
15449
15450
15451
15452
15453
15454
15455
15456
15457
15458
15459
15460
15461
15462
15463
15464
15465
15466
15467
15468
15469
15470
15471
15472
15473
15474
15475
15476
15477
15478
15479
15480
15481
15482
15483
15484
15485
15486
15487
15488
15489
15490
15491
15492
15493
15494
15495
15496
15497
15498
15499
15500
15501
15502
15503
15504
15505
15506
15507
15508
15509
15510
15511
15512
15513
15514
15515
15516
15517
15518
15519
15520
15521
15522
15523
15524
15525
15526
15527
15528
15529
15530
15531
15532
15533
15534
15535
15536
15537
15538
15539
15540
15541
15542
15543
15544
15545
15546
15547
15548
15549
15550
15551
15552
15553
15554
15555
15556
15557
15558
15559
15560
15561
15562
15563
15564
15565
15566
15567
15568
15569
15570
15571
15572
15573
15574
15575
15576
15577
15578
15579
15580
15581
15582
15583
15584
15585
15586
15587
15588
15589
15590
15591
15592
15593
15594
15595
15596
15597
15598
15599
15600
15601
15602
15603
15604
15605
15606
15607
15608
15609
15610
15611
15612
15613
15614
15615
15616
15617
15618
15619
15620
15621
15622
15623
15624
15625
15626
15627
15628
15629
15630
15631
15632
15633
15634
15635
15636
15637
15638
15639
15640
15641
15642
15643
15644
15645
15646
15647
15648
15649
15650
15651
15652
15653
15654
15655
15656
15657
15658
15659
15660
15661
15662
15663
15664
15665
15666
15667
15668
15669
15670
15671
15672
15673
15674
15675
15676
15677
15678
15679
15680
15681
15682
15683
15684
15685
15686
15687
15688
15689
15690
15691
15692
15693
15694
15695
15696
15697
15698
15699
15700
15701
15702
15703
15704
15705
15706
15707
15708
15709
15710
15711
15712
15713
15714
15715
15716
15717
15718
15719
15720
15721
15722
15723
15724
15725
15726
15727
15728
15729
15730
15731
15732
15733
15734
15735
15736
15737
15738
15739
15740
15741
15742
15743
15744
15745
15746
15747
15748
15749
15750
15751
15752
15753
15754
15755
15756
15757
15758
15759
15760
15761
15762
15763
15764
15765
15766
15767
15768
15769
15770
15771
15772
15773
15774
15775
15776
15777
15778
15779
15780
15781
15782
15783
15784
15785
15786
15787
15788
15789
15790
15791
15792
15793
15794
15795
15796
15797
15798
15799
15800
15801
15802
15803
15804
15805
15806
15807
15808
15809
15810
15811
15812
15813
15814
15815
15816
15817
15818
15819
15820
15821
15822
15823
15824
15825
15826
15827
15828
15829
15830
15831
15832
15833
15834
15835
15836
15837
15838
15839
15840
15841
15842
15843
15844
15845
15846
15847
15848
15849
15850
15851
15852
15853
15854
15855
15856
15857
15858
15859
15860
15861
15862
15863
15864
15865
15866
15867
15868
15869
15870
15871
15872
15873
15874
15875
15876
15877
15878
15879
15880
15881
15882
15883
15884
15885
15886
15887
15888
15889
15890
15891
15892
15893
15894
15895
15896
15897
15898
15899
15900
15901
15902
15903
15904
15905
15906
15907
15908
15909
15910
15911
15912
15913
15914
15915
15916
15917
15918
15919
15920
15921
15922
15923
15924
15925
15926
15927
15928
15929
15930
15931
15932
15933
15934
15935
15936
15937
15938
15939
15940
15941
15942
15943
15944
15945
15946
15947
15948
15949
15950
15951
15952
15953
15954
15955
15956
15957
15958
15959
15960
15961
15962
15963
15964
15965
15966
15967
15968
15969
15970
15971
15972
15973
15974
15975
15976
15977
15978
15979
15980
15981
15982
15983
15984
15985
15986
15987
15988
15989
15990
15991
15992
15993
15994
15995
15996
15997
15998
15999
16000
16001
16002
16003
16004
16005
16006
16007
16008
16009
16010
16011
16012
16013
16014
16015
16016
16017
16018
16019
16020
16021
16022
16023
16024
16025
16026
16027
16028
16029
16030
16031
16032
16033
16034
16035
16036
16037
16038
16039
16040
16041
16042
16043
16044
16045
16046
16047
16048
16049
16050
16051
16052
16053
16054
16055
16056
16057
16058
16059
16060
16061
16062
16063
16064
16065
16066
16067
16068
16069
16070
16071
16072
16073
16074
16075
16076
16077
16078
16079
16080
16081
16082
16083
16084
16085
16086
16087
16088
16089
16090
16091
16092
16093
16094
16095
16096
16097
16098
16099
16100
16101
16102
16103
16104
16105
16106
16107
16108
16109
16110
16111
16112
16113
16114
16115
16116
16117
16118
16119
16120
16121
16122
16123
16124
16125
16126
16127
16128
16129
16130
16131
16132
16133
16134
16135
16136
16137
16138
16139
16140
16141
16142
16143
16144
16145
16146
16147
16148
16149
16150
16151
16152
16153
16154
16155
16156
16157
16158
16159
16160
16161
16162
16163
16164
16165
16166
16167
16168
16169
16170
16171
16172
16173
16174
16175
16176
16177
16178
16179
16180
16181
16182
16183
16184
16185
16186
16187
16188
16189
16190
16191
16192
16193
16194
16195
16196
16197
16198
16199
16200
16201
16202
16203
16204
16205
16206
16207
16208
16209
16210
16211
16212
16213
16214
16215
16216
16217
16218
16219
16220
16221
16222
16223
16224
16225
16226
16227
16228
16229
16230
16231
16232
16233
16234
16235
16236
16237
16238
16239
16240
16241
16242
16243
16244
16245
16246
16247
16248
16249
16250
16251
16252
16253
16254
16255
16256
16257
16258
16259
16260
16261
16262
16263
16264
16265
16266
16267
16268
16269
16270
16271
16272
16273
16274
16275
16276
16277
16278
16279
16280
16281
16282
16283
16284
16285
16286
16287
16288
16289
16290
16291
16292
16293
16294
16295
16296
16297
16298
16299
16300
16301
16302
16303
16304
16305
16306
16307
16308
16309
16310
16311
16312
16313
16314
16315
16316
16317
16318
16319
16320
16321
16322
16323
16324
16325
16326
16327
16328
16329
16330
16331
16332
16333
16334
16335
16336
16337
16338
16339
16340
16341
16342
16343
16344
16345
16346
16347
16348
16349
16350
16351
16352
16353
16354
16355
16356
16357
16358
16359
16360
16361
16362
16363
16364
16365
16366
16367
16368
16369
16370
16371
16372
16373
16374
16375
16376
16377
16378
16379
16380
16381
16382
16383
16384
16385
16386
16387
16388
16389
16390
16391
16392
16393
16394
16395
16396
16397
16398
16399
16400
16401
16402
16403
16404
16405
16406
16407
16408
16409
16410
16411
16412
16413
16414
16415
16416
16417
16418
16419
16420
16421
16422
16423
16424
16425
16426
16427
16428
16429
16430
16431
16432
16433
16434
16435
16436
16437
16438
16439
16440
16441
16442
16443
16444
16445
16446
16447
16448
16449
16450
16451
16452
16453
16454
16455
16456
16457
16458
16459
16460
16461
16462
16463
16464
16465
16466
16467
16468
16469
16470
16471
16472
16473
16474
16475
16476
16477
16478
16479
16480
16481
16482
16483
16484
16485
16486
16487
16488
16489
16490
16491
16492
16493
16494
16495
16496
16497
16498
16499
16500
16501
16502
16503
16504
16505
16506
16507
16508
16509
16510
16511
16512
16513
16514
16515
16516
16517
16518
16519
16520
16521
16522
16523
16524
16525
16526
16527
16528
16529
16530
16531
16532
16533
16534
16535
16536
16537
16538
16539
16540
16541
16542
16543
16544
16545
16546
16547
16548
16549
16550
16551
16552
16553
16554
16555
16556
16557
16558
16559
16560
16561
16562
16563
16564
16565
16566
16567
16568
16569
16570
16571
16572
16573
16574
16575
16576
16577
16578
16579
16580
16581
16582
16583
16584
16585
16586
16587
16588
16589
16590
16591
16592
16593
16594
16595
16596
16597
16598
16599
16600
16601
16602
16603
16604
16605
16606
16607
16608
16609
16610
16611
16612
16613
16614
16615
16616
16617
16618
16619
16620
16621
16622
16623
16624
16625
16626
16627
16628
16629
16630
16631
16632
16633
16634
16635
16636
16637
16638
16639
16640
16641
16642
16643
16644
16645
16646
16647
16648
16649
16650
16651
16652
16653
16654
16655
16656
16657
16658
16659
16660
16661
16662
16663
16664
16665
16666
16667
16668
16669
16670
16671
16672
16673
16674
16675
16676
16677
16678
16679
16680
16681
16682
16683
16684
16685
16686
16687
16688
16689
16690
16691
16692
16693
16694
16695
16696
16697
16698
16699
16700
16701
16702
16703
16704
16705
16706
16707
16708
16709
16710
16711
16712
16713
16714
16715
16716
16717
16718
16719
16720
16721
16722
16723
16724
16725
16726
16727
16728
16729
16730
16731
16732
16733
16734
16735
16736
16737
16738
16739
16740
16741
16742
16743
16744
16745
16746
16747
16748
16749
16750
16751
16752
16753
16754
16755
16756
16757
16758
16759
16760
16761
16762
16763
16764
16765
16766
16767
16768
16769
16770
16771
16772
16773
16774
16775
16776
16777
16778
16779
16780
16781
16782
16783
16784
16785
16786
16787
16788
16789
16790
16791
16792
16793
16794
16795
16796
16797
16798
16799
16800
16801
16802
16803
16804
16805
16806
16807
16808
16809
16810
16811
16812
16813
16814
16815
16816
16817
16818
16819
16820
16821
16822
16823
16824
16825
16826
16827
16828
16829
16830
16831
16832
16833
16834
16835
16836
16837
16838
16839
16840
16841
16842
16843
16844
16845
16846
16847
16848
16849
16850
16851
16852
16853
16854
16855
16856
16857
16858
16859
16860
16861
16862
16863
16864
16865
16866
16867
16868
16869
16870
16871
16872
16873
16874
16875
16876
16877
16878
16879
16880
16881
16882
16883
16884
16885
16886
16887
16888
16889
16890
16891
16892
16893
16894
16895
16896
16897
16898
16899
16900
16901
16902
16903
16904
16905
16906
16907
16908
16909
16910
16911
16912
16913
16914
16915
16916
16917
16918
16919
16920
16921
16922
16923
16924
16925
16926
16927
16928
16929
16930
16931
16932
16933
16934
16935
16936
16937
16938
16939
16940
16941
16942
16943
16944
16945
16946
16947
16948
16949
16950
16951
16952
16953
16954
16955
16956
16957
16958
16959
16960
16961
16962
16963
16964
16965
16966
16967
16968
16969
16970
16971
16972
16973
16974
16975
16976
16977
16978
16979
16980
16981
16982
16983
16984
16985
16986
16987
16988
16989
16990
16991
16992
16993
16994
16995
16996
16997
16998
16999
17000
17001
17002
17003
17004
17005
17006
17007
17008
17009
17010
17011
17012
17013
17014
17015
17016
17017
17018
17019
17020
17021
17022
17023
17024
17025
17026
17027
17028
17029
17030
17031
17032
17033
17034
17035
17036
17037
17038
17039
17040
17041
17042
17043
17044
17045
17046
17047
17048
17049
17050
17051
17052
17053
17054
17055
17056
17057
17058
17059
17060
17061
17062
17063
17064
17065
17066
17067
17068
17069
17070
17071
17072
17073
17074
17075
17076
17077
17078
17079
17080
17081
17082
17083
17084
17085
17086
17087
17088
17089
17090
17091
17092
17093
17094
17095
17096
17097
17098
17099
17100
17101
17102
17103
17104
17105
17106
17107
17108
17109
17110
17111
17112
17113
17114
17115
17116
17117
17118
17119
17120
17121
17122
17123
17124
17125
17126
17127
17128
17129
17130
17131
17132
17133
17134
17135
17136
17137
17138
17139
17140
17141
17142
17143
17144
17145
17146
17147
17148
17149
17150
17151
17152
17153
17154
17155
17156
17157
17158
17159
17160
17161
17162
17163
17164
17165
17166
17167
17168
17169
17170
17171
17172
17173
17174
17175
17176
17177
17178
17179
17180
17181
17182
17183
17184
17185
17186
17187
17188
17189
17190
17191
17192
17193
17194
17195
17196
17197
17198
17199
17200
17201
17202
17203
17204
17205
17206
17207
17208
17209
17210
17211
17212
17213
17214
17215
17216
17217
17218
17219
17220
17221
17222
17223
17224
17225
17226
17227
17228
17229
17230
17231
17232
17233
17234
17235
17236
17237
17238
17239
17240
17241
17242
17243
17244
17245
17246
17247
17248
17249
17250
17251
17252
17253
17254
17255
17256
17257
17258
17259
17260
17261
17262
17263
17264
17265
17266
17267
17268
17269
17270
17271
17272
17273
17274
17275
17276
17277
17278
17279
17280
17281
17282
17283
17284
17285
17286
17287
17288
17289
17290
17291
17292
17293
17294
17295
17296
17297
17298
17299
17300
17301
17302
17303
17304
17305
17306
17307
17308
17309
17310
17311
17312
17313
17314
17315
17316
17317
17318
17319
17320
17321
17322
17323
17324
17325
17326
17327
17328
17329
17330
17331
17332
17333
17334
17335
17336
17337
17338
17339
17340
17341
17342
17343
17344
17345
17346
17347
17348
17349
17350
17351
17352
17353
17354
17355
17356
17357
17358
17359
17360
17361
17362
17363
17364
17365
17366
17367
17368
17369
17370
17371
17372
17373
17374
17375
17376
17377
17378
17379
17380
17381
17382
17383
17384
17385
17386
17387
17388
17389
17390
17391
17392
17393
17394
17395
17396
17397
17398
17399
17400
17401
17402
17403
17404
17405
17406
17407
17408
17409
17410
17411
17412
17413
17414
17415
17416
17417
17418
17419
17420
17421
17422
17423
17424
17425
17426
17427
17428
17429
17430
17431
17432
17433
17434
17435
17436
17437
17438
17439
17440
17441
17442
17443
17444
17445
17446
17447
17448
17449
17450
17451
17452
17453
17454
17455
17456
17457
17458
17459
17460
17461
17462
17463
17464
17465
17466
17467
17468
17469
17470
17471
17472
17473
17474
17475
17476
17477
17478
17479
17480
17481
17482
17483
17484
17485
17486
17487
17488
17489
17490
17491
17492
17493
17494
17495
17496
17497
17498
17499
17500
17501
17502
17503
17504
17505
17506
17507
17508
17509
17510
17511
17512
17513
17514
17515
17516
17517
17518
17519
17520
17521
17522
17523
17524
17525
17526
17527
17528
17529
17530
17531
17532
17533
17534
17535
17536
17537
17538
17539
17540
17541
17542
17543
17544
17545
17546
17547
17548
17549
17550
17551
17552
17553
17554
17555
17556
17557
17558
17559
17560
17561
17562
17563
17564
17565
17566
17567
17568
17569
17570
17571
17572
17573
17574
17575
17576
17577
17578
17579
17580
17581
17582
17583
17584
17585
17586
17587
17588
17589
17590
17591
17592
17593
17594
17595
17596
17597
17598
17599
17600
17601
17602
17603
17604
17605
17606
17607
17608
17609
17610
17611
17612
17613
17614
17615
17616
17617
17618
17619
17620
17621
17622
17623
17624
17625
17626
17627
17628
17629
17630
17631
17632
17633
17634
17635
17636
17637
17638
17639
17640
17641
17642
17643
17644
17645
17646
17647
17648
17649
17650
17651
17652
17653
17654
17655
17656
17657
17658
17659
17660
17661
17662
17663
17664
17665
17666
17667
17668
17669
17670
17671
17672
17673
17674
17675
17676
17677
17678
17679
17680
17681
17682
17683
17684
17685
17686
17687
17688
17689
17690
17691
17692
17693
17694
17695
17696
17697
17698
17699
17700
17701
17702
17703
17704
17705
17706
17707
17708
17709
17710
17711
17712
17713
17714
17715
17716
17717
17718
17719
17720
17721
17722
17723
17724
17725
17726
17727
17728
17729
17730
17731
17732
17733
17734
17735
17736
17737
17738
17739
17740
17741
17742
17743
17744
17745
17746
17747
17748
17749
17750
17751
17752
17753
17754
17755
17756
17757
17758
17759
17760
17761
17762
17763
17764
17765
17766
17767
17768
17769
17770
17771
17772
17773
17774
17775
17776
17777
17778
17779
17780
17781
17782
17783
17784
17785
17786
17787
17788
17789
17790
17791
17792
17793
17794
17795
17796
17797
17798
17799
17800
17801
17802
17803
17804
17805
17806
17807
17808
17809
17810
17811
17812
17813
17814
17815
17816
17817
17818
17819
17820
17821
17822
17823
17824
17825
17826
17827
17828
17829
17830
17831
17832
17833
17834
17835
17836
17837
17838
17839
17840
17841
17842
17843
17844
17845
17846
17847
17848
17849
17850
17851
17852
17853
17854
17855
17856
17857
17858
17859
17860
17861
17862
17863
17864
17865
17866
17867
17868
17869
17870
17871
17872
17873
17874
17875
17876
17877
17878
17879
17880
17881
17882
17883
17884
17885
17886
17887
17888
17889
17890
17891
17892
17893
17894
17895
17896
17897
17898
17899
17900
17901
17902
17903
17904
17905
17906
17907
17908
17909
17910
17911
17912
17913
17914
17915
17916
17917
17918
17919
17920
17921
17922
17923
17924
17925
17926
17927
17928
17929
17930
17931
17932
17933
17934
17935
17936
17937
17938
17939
17940
17941
17942
17943
17944
17945
17946
17947
17948
17949
17950
17951
17952
17953
17954
17955
17956
17957
17958
17959
17960
17961
17962
17963
17964
17965
17966
17967
17968
17969
17970
17971
17972
17973
17974
17975
17976
17977
17978
17979
17980
17981
17982
17983
17984
17985
17986
17987
17988
17989
17990
17991
17992
17993
17994
17995
17996
17997
17998
17999
18000
18001
18002
18003
18004
18005
18006
18007
18008
18009
18010
18011
18012
18013
18014
18015
18016
18017
18018
18019
18020
18021
18022
18023
18024
18025
18026
18027
18028
18029
18030
18031
18032
18033
18034
18035
18036
18037
18038
18039
18040
18041
18042
18043
18044
18045
18046
18047
18048
18049
18050
18051
18052
18053
18054
18055
18056
18057
18058
18059
18060
18061
18062
18063
18064
18065
18066
18067
18068
18069
18070
18071
18072
18073
18074
18075
18076
18077
18078
18079
18080
18081
18082
18083
18084
18085
18086
18087
18088
18089
18090
18091
18092
18093
18094
18095
18096
18097
18098
18099
18100
18101
18102
18103
18104
18105
18106
18107
18108
18109
18110
18111
18112
18113
18114
18115
18116
18117
18118
18119
18120
18121
18122
18123
18124
18125
18126
18127
18128
18129
18130
18131
18132
18133
18134
18135
18136
18137
18138
18139
18140
18141
18142
18143
18144
18145
18146
18147
18148
18149
18150
18151
18152
18153
18154
18155
18156
18157
18158
18159
18160
18161
18162
18163
18164
18165
18166
18167
18168
18169
18170
18171
18172
18173
18174
18175
18176
18177
18178
18179
18180
18181
18182
18183
18184
18185
18186
18187
18188
18189
18190
18191
18192
18193
18194
18195
18196
18197
18198
18199
18200
18201
18202
18203
18204
18205
18206
18207
18208
18209
18210
18211
18212
18213
18214
18215
18216
18217
18218
18219
18220
18221
18222
18223
18224
18225
18226
18227
18228
18229
18230
18231
18232
18233
18234
18235
18236
18237
18238
18239
18240
18241
18242
18243
18244
18245
18246
18247
18248
18249
18250
18251
18252
18253
18254
18255
18256
18257
18258
18259
18260
18261
18262
18263
18264
18265
18266
18267
18268
18269
18270
18271
18272
18273
18274
18275
18276
18277
18278
18279
18280
18281
18282
18283
18284
18285
18286
18287
18288
18289
18290
18291
18292
18293
18294
18295
18296
18297
18298
18299
18300
18301
18302
18303
18304
18305
18306
18307
18308
18309
18310
18311
18312
18313
18314
18315
18316
18317
18318
18319
18320
18321
18322
18323
18324
18325
18326
18327
18328
18329
18330
18331
18332
18333
18334
18335
18336
18337
18338
18339
18340
18341
18342
18343
18344
18345
18346
18347
18348
18349
18350
18351
18352
18353
18354
18355
18356
18357
18358
18359
18360
18361
18362
18363
18364
18365
18366
18367
18368
18369
18370
18371
18372
18373
18374
18375
18376
18377
18378
18379
18380
18381
18382
18383
18384
18385
18386
18387
18388
18389
18390
18391
18392
18393
18394
18395
18396
18397
18398
18399
18400
18401
18402
18403
18404
18405
18406
18407
18408
18409
18410
18411
18412
18413
18414
18415
18416
18417
18418
18419
18420
18421
18422
18423
18424
18425
18426
18427
18428
18429
18430
18431
18432
18433
18434
18435
18436
18437
18438
18439
18440
18441
18442
18443
18444
18445
18446
18447
18448
18449
18450
18451
18452
18453
18454
18455
18456
18457
18458
18459
18460
18461
18462
18463
18464
18465
18466
18467
18468
18469
18470
18471
18472
18473
18474
18475
18476
18477
18478
18479
18480
18481
18482
18483
18484
18485
18486
18487
18488
18489
18490
18491
18492
18493
18494
18495
18496
18497
18498
18499
18500
18501
18502
18503
18504
18505
18506
18507
18508
18509
18510
18511
18512
18513
18514
18515
18516
18517
18518
18519
18520
18521
18522
18523
18524
18525
18526
18527
18528
18529
18530
18531
18532
18533
18534
18535
18536
18537
18538
18539
18540
18541
18542
18543
18544
18545
18546
18547
18548
18549
18550
18551
18552
18553
18554
18555
18556
18557
18558
18559
18560
18561
18562
18563
18564
18565
18566
18567
18568
18569
18570
18571
18572
18573
18574
18575
18576
18577
18578
18579
18580
18581
18582
18583
18584
18585
18586
18587
18588
18589
18590
18591
18592
18593
18594
18595
18596
18597
18598
18599
18600
18601
18602
18603
18604
18605
18606
18607
18608
18609
18610
18611
18612
18613
18614
18615
18616
18617
18618
18619
18620
18621
18622
18623
18624
18625
18626
18627
18628
18629
18630
18631
18632
18633
18634
18635
18636
18637
18638
18639
18640
18641
18642
18643
18644
18645
18646
18647
18648
18649
18650
18651
18652
18653
18654
18655
18656
18657
18658
18659
18660
18661
18662
18663
18664
18665
18666
18667
18668
18669
18670
18671
18672
18673
18674
18675
18676
18677
18678
18679
18680
18681
18682
18683
18684
18685
18686
18687
18688
18689
18690
18691
18692
18693
18694
18695
18696
18697
18698
18699
18700
18701
18702
18703
18704
18705
18706
18707
18708
18709
18710
18711
18712
18713
18714
18715
18716
18717
18718
18719
18720
18721
18722
18723
18724
18725
18726
18727
18728
18729
18730
18731
18732
18733
18734
18735
18736
18737
18738
18739
18740
18741
18742
18743
18744
18745
18746
18747
18748
18749
18750
18751
18752
18753
18754
18755
18756
18757
18758
18759
18760
18761
18762
18763
18764
18765
18766
18767
18768
18769
18770
18771
18772
18773
18774
18775
18776
18777
18778
18779
18780
18781
18782
18783
18784
18785
18786
18787
18788
18789
18790
18791
18792
18793
18794
18795
18796
18797
18798
18799
18800
18801
18802
18803
18804
18805
18806
18807
18808
18809
18810
18811
18812
18813
18814
18815
18816
18817
18818
18819
18820
18821
18822
18823
18824
18825
18826
18827
18828
18829
18830
18831
18832
18833
18834
18835
18836
18837
18838
18839
18840
18841
18842
18843
18844
18845
18846
18847
18848
18849
18850
18851
18852
18853
18854
18855
18856
18857
18858
18859
18860
18861
18862
18863
18864
18865
18866
18867
18868
18869
18870
18871
18872
18873
18874
18875
18876
18877
18878
18879
18880
18881
18882
18883
18884
18885
18886
18887
18888
18889
18890
18891
18892
18893
18894
18895
18896
18897
18898
18899
18900
18901
18902
18903
18904
18905
18906
18907
18908
18909
18910
18911
18912
18913
18914
18915
18916
18917
18918
18919
18920
18921
18922
18923
18924
18925
18926
18927
18928
18929
18930
18931
18932
18933
18934
18935
18936
18937
18938
18939
18940
18941
18942
18943
18944
18945
18946
18947
18948
18949
18950
18951
18952
18953
18954
18955
18956
18957
18958
18959
18960
18961
18962
18963
18964
18965
18966
18967
18968
18969
18970
18971
18972
18973
18974
18975
18976
18977
18978
18979
18980
18981
18982
18983
18984
18985
18986
18987
18988
18989
18990
18991
18992
18993
18994
18995
18996
18997
18998
18999
19000
19001
19002
19003
19004
19005
19006
19007
19008
19009
19010
19011
19012
19013
19014
19015
19016
19017
19018
19019
19020
19021
19022
19023
19024
19025
19026
19027
19028
19029
19030
19031
19032
19033
19034
19035
19036
19037
19038
19039
19040
19041
19042
19043
19044
19045
19046
19047
19048
19049
19050
19051
19052
19053
19054
19055
19056
19057
19058
19059
19060
19061
19062
19063
19064
19065
19066
19067
19068
19069
19070
19071
19072
19073
19074
19075
19076
19077
19078
19079
19080
19081
19082
19083
19084
19085
19086
19087
19088
19089
19090
19091
19092
19093
19094
19095
19096
19097
19098
19099
19100
19101
19102
19103
19104
19105
19106
19107
19108
19109
19110
19111
19112
19113
19114
19115
19116
19117
19118
19119
19120
19121
19122
19123
19124
19125
19126
19127
19128
19129
19130
19131
19132
19133
19134
19135
19136
19137
19138
19139
19140
19141
19142
19143
19144
19145
19146
19147
19148
19149
19150
19151
19152
19153
19154
19155
19156
19157
19158
19159
19160
19161
19162
19163
19164
19165
19166
19167
19168
19169
19170
19171
19172
19173
19174
19175
19176
19177
19178
19179
19180
19181
19182
19183
19184
19185
19186
19187
19188
19189
19190
19191
19192
19193
19194
19195
19196
19197
19198
19199
19200
19201
19202
19203
19204
19205
19206
19207
19208
19209
19210
19211
19212
19213
19214
19215
19216
19217
19218
19219
19220
19221
19222
19223
19224
19225
19226
19227
19228
19229
19230
19231
19232
19233
19234
19235
19236
19237
19238
19239
19240
19241
19242
19243
19244
19245
19246
19247
19248
19249
19250
19251
19252
19253
19254
19255
19256
19257
19258
19259
19260
19261
19262
19263
19264
19265
19266
19267
19268
19269
19270
19271
19272
19273
19274
19275
19276
19277
19278
19279
19280
19281
19282
19283
19284
19285
19286
19287
19288
19289
19290
19291
19292
19293
19294
19295
19296
19297
19298
19299
19300
19301
19302
19303
19304
19305
19306
19307
19308
19309
19310
19311
19312
19313
19314
19315
19316
19317
19318
19319
19320
19321
19322
19323
19324
19325
19326
19327
19328
19329
19330
19331
19332
19333
19334
19335
19336
19337
19338
19339
19340
19341
19342
19343
19344
19345
19346
19347
19348
19349
19350
19351
19352
19353
19354
19355
19356
19357
19358
19359
19360
19361
19362
19363
19364
19365
19366
19367
19368
19369
19370
19371
19372
19373
19374
19375
19376
19377
19378
19379
19380
19381
19382
19383
19384
19385
19386
19387
19388
19389
19390
19391
19392
19393
19394
19395
19396
19397
19398
19399
19400
19401
19402
19403
19404
19405
19406
19407
19408
19409
19410
19411
19412
19413
19414
19415
19416
19417
19418
19419
19420
19421
19422
19423
19424
19425
19426
19427
19428
19429
19430
19431
19432
19433
19434
19435
19436
19437
19438
19439
19440
19441
19442
19443
19444
19445
19446
19447
19448
19449
19450
19451
19452
19453
19454
19455
19456
19457
19458
19459
19460
19461
19462
19463
19464
19465
19466
19467
19468
19469
19470
19471
19472
19473
19474
19475
19476
19477
19478
19479
19480
19481
19482
19483
19484
19485
19486
19487
19488
19489
19490
19491
19492
19493
19494
19495
19496
19497
19498
19499
19500
19501
19502
19503
19504
19505
19506
19507
19508
19509
19510
19511
19512
19513
19514
19515
19516
19517
19518
19519
19520
19521
19522
19523
19524
19525
19526
19527
19528
19529
19530
19531
19532
19533
19534
19535
19536
19537
19538
19539
19540
19541
19542
19543
19544
19545
19546
19547
19548
19549
19550
19551
19552
19553
19554
19555
19556
19557
19558
19559
19560
19561
19562
19563
19564
19565
19566
19567
19568
19569
19570
19571
19572
19573
19574
19575
19576
19577
19578
19579
19580
19581
19582
19583
19584
19585
19586
19587
19588
19589
19590
19591
19592
19593
19594
19595
19596
19597
19598
19599
19600
19601
19602
19603
19604
19605
19606
19607
19608
19609
19610
19611
19612
19613
19614
19615
19616
19617
19618
19619
19620
19621
19622
19623
19624
19625
19626
19627
19628
19629
19630
19631
19632
19633
19634
19635
19636
19637
19638
19639
19640
19641
19642
19643
19644
19645
19646
19647
19648
19649
19650
19651
19652
19653
19654
19655
19656
19657
19658
19659
19660
19661
19662
19663
19664
19665
19666
19667
19668
19669
19670
19671
19672
19673
19674
19675
19676
19677
19678
19679
19680
19681
19682
19683
19684
19685
19686
19687
19688
19689
19690
19691
19692
19693
19694
19695
19696
19697
19698
19699
19700
19701
19702
19703
19704
19705
19706
19707
19708
19709
19710
19711
19712
19713
19714
19715
19716
19717
19718
19719
19720
19721
19722
19723
19724
19725
19726
19727
19728
19729
19730
19731
19732
19733
19734
19735
19736
19737
19738
19739
19740
19741
19742
19743
19744
19745
19746
19747
19748
19749
19750
19751
19752
19753
19754
19755
19756
19757
19758
19759
19760
19761
19762
19763
19764
19765
19766
19767
19768
19769
19770
19771
19772
19773
19774
19775
19776
19777
19778
19779
19780
19781
19782
19783
19784
19785
19786
19787
19788
19789
19790
19791
19792
19793
19794
19795
19796
19797
19798
19799
19800
19801
19802
19803
19804
19805
19806
19807
19808
19809
19810
19811
19812
19813
19814
19815
19816
19817
19818
19819
19820
19821
19822
19823
19824
19825
19826
19827
19828
19829
19830
19831
19832
19833
19834
19835
19836
19837
19838
19839
19840
19841
19842
19843
19844
19845
19846
19847
19848
19849
19850
19851
19852
19853
19854
19855
19856
19857
19858
19859
19860
19861
19862
19863
19864
19865
19866
19867
19868
19869
19870
19871
19872
19873
19874
19875
19876
19877
19878
19879
19880
19881
19882
19883
19884
19885
19886
19887
19888
19889
19890
19891
19892
19893
19894
19895
19896
19897
19898
19899
19900
19901
19902
19903
19904
19905
19906
19907
19908
19909
19910
19911
19912
19913
19914
19915
19916
19917
19918
19919
19920
19921
19922
19923
19924
19925
19926
19927
19928
19929
19930
19931
19932
19933
19934
19935
19936
19937
19938
19939
19940
19941
19942
19943
19944
19945
19946
19947
19948
19949
19950
19951
19952
19953
19954
19955
19956
19957
19958
19959
19960
19961
19962
19963
19964
19965
19966
19967
19968
19969
19970
19971
19972
19973
19974
19975
19976
19977
19978
19979
19980
19981
19982
19983
19984
19985
19986
19987
19988
19989
19990
19991
19992
19993
19994
19995
19996
19997
19998
19999
20000
20001
20002
20003
20004
20005
20006
20007
20008
20009
20010
20011
20012
20013
20014
20015
20016
20017
20018
20019
20020
20021
20022
20023
20024
20025
20026
20027
20028
20029
20030
20031
20032
20033
20034
20035
20036
20037
20038
20039
20040
20041
20042
20043
20044
20045
20046
20047
20048
20049
20050
20051
20052
20053
20054
20055
20056
20057
20058
20059
20060
20061
20062
20063
20064
20065
20066
20067
20068
20069
20070
20071
20072
20073
20074
20075
20076
20077
20078
20079
20080
20081
20082
20083
20084
20085
20086
20087
20088
20089
20090
20091
20092
20093
20094
20095
20096
20097
20098
20099
20100
20101
20102
20103
20104
20105
20106
20107
20108
20109
20110
20111
20112
20113
20114
20115
20116
20117
20118
20119
20120
20121
20122
20123
20124
20125
20126
20127
20128
20129
20130
20131
20132
20133
20134
20135
20136
20137
20138
20139
20140
20141
20142
20143
20144
20145
20146
20147
20148
20149
20150
20151
20152
20153
20154
20155
20156
20157
20158
20159
20160
20161
20162
20163
20164
20165
20166
20167
20168
20169
20170
20171
20172
20173
20174
20175
20176
20177
20178
20179
20180
20181
20182
20183
20184
20185
20186
20187
20188
20189
20190
20191
20192
20193
20194
20195
20196
20197
20198
20199
20200
20201
20202
20203
20204
20205
20206
20207
20208
20209
20210
20211
20212
20213
20214
20215
20216
20217
20218
20219
20220
20221
20222
20223
20224
20225
20226
20227
20228
20229
20230
20231
20232
20233
20234
20235
20236
20237
20238
20239
20240
20241
20242
20243
20244
20245
20246
20247
20248
20249
20250
20251
20252
20253
20254
20255
20256
20257
20258
20259
20260
20261
20262
20263
20264
20265
20266
20267
20268
20269
20270
20271
20272
20273
20274
20275
20276
20277
20278
20279
20280
20281
20282
20283
20284
20285
20286
20287
20288
20289
20290
20291
20292
20293
20294
20295
20296
20297
20298
20299
20300
20301
20302
20303
20304
20305
20306
20307
20308
20309
20310
20311
20312
20313
20314
20315
20316
20317
20318
20319
20320
20321
20322
20323
20324
20325
20326
20327
20328
20329
20330
20331
20332
20333
20334
20335
20336
20337
20338
20339
20340
20341
20342
20343
20344
20345
20346
20347
20348
20349
20350
20351
20352
20353
20354
20355
20356
20357
20358
20359
20360
20361
20362
20363
20364
20365
20366
20367
20368
20369
20370
20371
20372
20373
20374
20375
20376
20377
20378
20379
20380
20381
20382
20383
20384
20385
20386
20387
20388
20389
20390
20391
20392
20393
20394
20395
20396
20397
20398
20399
20400
20401
20402
20403
20404
20405
20406
20407
20408
20409
20410
20411
20412
20413
20414
20415
20416
20417
20418
20419
20420
20421
20422
20423
20424
20425
20426
20427
20428
20429
20430
20431
20432
20433
20434
20435
20436
20437
20438
20439
20440
20441
20442
20443
20444
20445
20446
20447
20448
20449
20450
20451
20452
20453
20454
20455
20456
20457
20458
20459
20460
20461
20462
20463
20464
20465
20466
20467
20468
20469
20470
20471
20472
20473
20474
20475
20476
20477
20478
20479
20480
20481
20482
20483
20484
20485
20486
20487
20488
20489
20490
20491
20492
20493
20494
20495
20496
20497
20498
20499
20500
20501
20502
20503
20504
20505
20506
20507
20508
20509
20510
20511
20512
20513
20514
20515
20516
20517
20518
20519
20520
20521
20522
20523
20524
20525
20526
20527
20528
20529
20530
20531
20532
20533
20534
20535
20536
20537
20538
20539
20540
20541
20542
20543
20544
20545
20546
20547
20548
20549
20550
20551
20552
20553
20554
20555
20556
20557
20558
20559
20560
20561
20562
20563
20564
20565
20566
20567
20568
20569
20570
20571
20572
20573
20574
20575
20576
20577
20578
20579
20580
20581
20582
20583
20584
20585
20586
20587
20588
20589
20590
20591
20592
20593
20594
20595
20596
20597
20598
20599
20600
20601
20602
20603
20604
20605
20606
20607
20608
20609
20610
20611
20612
20613
20614
20615
20616
20617
20618
20619
20620
20621
20622
20623
20624
20625
20626
20627
20628
20629
20630
20631
20632
20633
20634
20635
20636
20637
20638
20639
20640
20641
20642
20643
20644
20645
20646
20647
20648
20649
20650
20651
20652
20653
20654
20655
20656
20657
20658
20659
20660
20661
20662
20663
20664
20665
20666
20667
20668
20669
20670
20671
20672
20673
20674
20675
20676
20677
20678
20679
20680
20681
20682
20683
20684
20685
20686
20687
20688
20689
20690
20691
20692
20693
20694
20695
20696
20697
20698
20699
20700
20701
20702
20703
20704
20705
20706
20707
20708
20709
20710
20711
20712
20713
20714
20715
20716
20717
20718
20719
20720
20721
20722
20723
20724
20725
20726
20727
20728
20729
20730
20731
20732
20733
20734
20735
20736
20737
20738
20739
20740
20741
20742
20743
20744
20745
20746
20747
20748
20749
20750
20751
20752
20753
20754
20755
20756
20757
20758
20759
20760
20761
20762
20763
20764
20765
20766
20767
20768
20769
20770
20771
20772
20773
20774
20775
20776
20777
20778
20779
20780
20781
20782
20783
20784
20785
20786
20787
20788
20789
20790
20791
20792
20793
20794
20795
20796
20797
20798
20799
20800
20801
20802
20803
20804
20805
20806
20807
20808
20809
20810
20811
20812
20813
20814
20815
20816
20817
20818
20819
20820
20821
20822
20823
20824
20825
20826
20827
20828
20829
20830
20831
20832
20833
20834
20835
20836
20837
20838
20839
20840
20841
20842
20843
20844
20845
20846
20847
20848
20849
20850
20851
20852
20853
20854
20855
20856
20857
20858
20859
20860
20861
20862
20863
20864
20865
20866
20867
20868
20869
20870
20871
20872
20873
20874
20875
20876
20877
20878
20879
20880
20881
20882
20883
20884
20885
20886
20887
20888
20889
20890
20891
20892
20893
20894
20895
20896
20897
20898
20899
20900
20901
20902
20903
20904
20905
20906
20907
20908
20909
20910
20911
20912
20913
20914
20915
20916
20917
20918
20919
20920
20921
20922
20923
20924
20925
20926
20927
20928
20929
20930
20931
20932
20933
20934
20935
20936
20937
20938
20939
20940
20941
20942
20943
20944
20945
20946
20947
20948
20949
20950
20951
20952
20953
20954
20955
20956
20957
20958
20959
20960
20961
20962
20963
20964
20965
20966
20967
20968
20969
20970
20971
20972
20973
20974
20975
20976
20977
20978
20979
20980
20981
20982
20983
20984
20985
20986
20987
20988
20989
20990
20991
20992
20993
20994
20995
20996
20997
20998
20999
21000
21001
21002
21003
21004
21005
21006
21007
21008
21009
21010
21011
21012
21013
21014
21015
21016
21017
21018
21019
21020
21021
21022
21023
21024
21025
21026
21027
21028
21029
21030
21031
21032
21033
21034
21035
21036
21037
21038
21039
21040
21041
21042
21043
21044
21045
21046
21047
21048
21049
21050
21051
21052
21053
21054
21055
21056
21057
21058
21059
21060
21061
21062
21063
21064
21065
21066
21067
21068
21069
21070
21071
21072
21073
21074
21075
21076
21077
21078
21079
21080
21081
21082
21083
21084
21085
21086
21087
21088
21089
21090
21091
21092
21093
21094
21095
21096
21097
21098
21099
21100
21101
21102
21103
21104
21105
21106
21107
21108
21109
21110
21111
21112
21113
21114
21115
21116
21117
21118
21119
21120
21121
21122
21123
21124
21125
21126
21127
21128
21129
21130
21131
21132
21133
21134
21135
21136
21137
21138
21139
21140
21141
21142
21143
21144
21145
21146
21147
21148
21149
21150
21151
21152
21153
21154
21155
21156
21157
21158
21159
21160
21161
21162
21163
21164
21165
21166
21167
21168
21169
21170
21171
21172
21173
21174
21175
21176
21177
21178
21179
21180
21181
21182
21183
21184
21185
21186
21187
21188
21189
21190
21191
21192
21193
21194
21195
21196
21197
21198
21199
21200
21201
21202
21203
21204
21205
21206
21207
21208
21209
21210
21211
21212
21213
21214
21215
21216
21217
21218
21219
21220
21221
21222
21223
21224
21225
21226
21227
21228
21229
21230
21231
21232
21233
21234
21235
21236
21237
21238
21239
21240
21241
21242
21243
21244
21245
21246
21247
21248
21249
21250
21251
21252
21253
21254
21255
21256
21257
21258
21259
21260
21261
21262
21263
21264
21265
21266
21267
21268
21269
21270
21271
21272
21273
21274
21275
21276
21277
21278
21279
21280
21281
21282
21283
21284
21285
21286
21287
21288
21289
21290
21291
21292
21293
21294
21295
21296
21297
21298
21299
21300
21301
21302
21303
21304
21305
21306
21307
21308
21309
21310
21311
21312
21313
21314
21315
21316
21317
21318
21319
21320
21321
21322
21323
21324
21325
21326
21327
21328
21329
21330
21331
21332
21333
21334
21335
21336
21337
21338
21339
21340
21341
21342
21343
21344
21345
21346
21347
21348
21349
21350
21351
21352
21353
21354
21355
21356
21357
21358
21359
21360
21361
21362
21363
21364
21365
21366
21367
21368
21369
21370
21371
21372
21373
21374
21375
21376
21377
21378
21379
21380
21381
21382
21383
21384
21385
21386
21387
21388
21389
21390
21391
21392
21393
21394
21395
21396
21397
21398
21399
21400
21401
21402
21403
21404
21405
21406
21407
21408
21409
21410
21411
21412
21413
21414
21415
21416
21417
21418
21419
21420
21421
21422
21423
21424
21425
21426
21427
21428
21429
21430
21431
21432
21433
21434
21435
21436
21437
21438
21439
21440
21441
21442
21443
21444
21445
21446
21447
21448
21449
21450
21451
21452
21453
21454
21455
21456
21457
21458
21459
21460
21461
21462
21463
21464
21465
21466
21467
21468
21469
21470
21471
21472
21473
21474
21475
21476
21477
21478
21479
21480
21481
21482
21483
21484
21485
21486
21487
21488
21489
21490
21491
21492
21493
21494
21495
21496
21497
21498
21499
21500
21501
21502
21503
21504
21505
21506
21507
21508
21509
21510
21511
21512
21513
21514
21515
21516
21517
21518
21519
21520
21521
21522
21523
21524
21525
21526
21527
21528
21529
21530
21531
21532
21533
21534
21535
21536
21537
21538
21539
21540
21541
21542
21543
21544
21545
21546
21547
21548
21549
21550
21551
21552
21553
21554
21555
21556
21557
21558
21559
21560
21561
21562
21563
21564
21565
21566
21567
21568
21569
21570
21571
21572
21573
21574
21575
21576
21577
21578
21579
21580
21581
21582
21583
21584
21585
21586
21587
21588
21589
21590
21591
21592
21593
21594
21595
21596
21597
21598
21599
21600
21601
21602
21603
21604
21605
21606
21607
21608
21609
21610
21611
21612
21613
21614
21615
21616
21617
21618
21619
21620
21621
21622
21623
21624
21625
21626
21627
21628
21629
21630
21631
21632
21633
21634
21635
21636
21637
21638
21639
21640
21641
21642
21643
21644
21645
21646
21647
21648
21649
21650
21651
21652
21653
21654
21655
21656
21657
21658
21659
21660
21661
21662
21663
21664
21665
21666
21667
21668
21669
21670
21671
21672
21673
21674
21675
21676
21677
21678
21679
21680
21681
21682
21683
21684
21685
21686
21687
21688
21689
21690
21691
21692
21693
21694
21695
21696
21697
21698
21699
21700
21701
21702
21703
21704
21705
21706
21707
21708
21709
21710
21711
21712
21713
21714
21715
21716
21717
21718
21719
21720
21721
21722
21723
21724
21725
21726
21727
21728
21729
21730
21731
21732
21733
21734
21735
21736
21737
21738
21739
21740
21741
21742
21743
21744
21745
21746
21747
21748
21749
21750
21751
21752
21753
21754
21755
21756
21757
21758
21759
21760
21761
21762
21763
21764
21765
21766
21767
21768
21769
21770
21771
21772
21773
21774
21775
21776
21777
21778
21779
21780
21781
21782
21783
21784
21785
21786
21787
21788
21789
21790
21791
21792
21793
21794
21795
21796
21797
21798
21799
21800
21801
21802
21803
21804
21805
21806
21807
21808
21809
21810
21811
21812
21813
21814
21815
21816
21817
21818
21819
21820
21821
21822
21823
21824
21825
21826
21827
21828
21829
21830
21831
21832
21833
21834
21835
21836
21837
21838
21839
21840
21841
21842
21843
21844
21845
21846
21847
21848
21849
21850
21851
21852
21853
21854
21855
21856
21857
21858
21859
21860
21861
21862
21863
21864
21865
21866
21867
21868
21869
21870
21871
21872
21873
21874
21875
21876
21877
21878
21879
21880
21881
21882
21883
21884
21885
21886
21887
21888
21889
21890
21891
21892
21893
21894
21895
21896
21897
21898
21899
21900
21901
21902
21903
21904
21905
21906
21907
21908
21909
21910
21911
21912
21913
21914
21915
21916
21917
21918
21919
21920
21921
21922
21923
21924
21925
21926
21927
21928
21929
21930
21931
21932
21933
21934
21935
21936
21937
21938
21939
21940
21941
21942
21943
21944
21945
21946
21947
21948
21949
21950
21951
21952
21953
21954
21955
21956
21957
21958
21959
21960
21961
21962
21963
21964
21965
21966
21967
21968
21969
21970
21971
21972
21973
21974
21975
21976
21977
21978
21979
21980
21981
21982
21983
21984
21985
21986
21987
21988
21989
21990
21991
21992
21993
21994
21995
21996
21997
21998
21999
22000
22001
22002
22003
22004
22005
22006
22007
22008
22009
22010
22011
22012
22013
22014
22015
22016
22017
22018
22019
22020
22021
22022
22023
22024
22025
22026
22027
22028
22029
22030
22031
22032
22033
22034
22035
22036
22037
22038
22039
22040
22041
22042
22043
22044
22045
22046
22047
22048
22049
22050
22051
22052
22053
22054
22055
22056
22057
22058
22059
22060
22061
22062
22063
22064
22065
22066
22067
22068
22069
22070
22071
22072
22073
22074
22075
22076
22077
22078
22079
22080
22081
22082
22083
22084
22085
22086
22087
22088
22089
22090
22091
22092
22093
22094
22095
22096
22097
22098
22099
22100
22101
22102
22103
22104
22105
22106
22107
22108
22109
22110
22111
22112
22113
22114
22115
22116
22117
22118
22119
22120
22121
22122
22123
22124
22125
22126
22127
22128
22129
22130
22131
22132
22133
22134
22135
22136
22137
22138
22139
22140
22141
22142
22143
22144
22145
22146
22147
22148
22149
22150
22151
22152
22153
22154
22155
22156
22157
22158
22159
22160
22161
22162
22163
22164
22165
22166
22167
22168
22169
22170
22171
22172
22173
22174
22175
22176
22177
22178
22179
22180
22181
22182
22183
22184
22185
22186
22187
22188
22189
22190
22191
22192
22193
22194
22195
22196
22197
22198
22199
22200
22201
22202
22203
22204
22205
22206
22207
22208
22209
22210
22211
22212
22213
22214
22215
22216
22217
22218
22219
22220
22221
22222
22223
22224
22225
22226
22227
22228
22229
22230
22231
22232
22233
22234
22235
22236
22237
22238
22239
22240
22241
22242
22243
22244
22245
22246
22247
22248
22249
22250
22251
22252
22253
22254
22255
22256
22257
22258
22259
22260
22261
22262
22263
22264
22265
22266
22267
22268
22269
22270
22271
22272
22273
22274
22275
22276
22277
22278
22279
22280
22281
22282
22283
22284
22285
22286
22287
22288
22289
22290
22291
22292
22293
22294
22295
22296
22297
22298
22299
22300
22301
22302
22303
22304
22305
22306
22307
22308
22309
22310
22311
22312
22313
22314
22315
22316
22317
22318
22319
22320
22321
22322
22323
22324
22325
22326
22327
22328
22329
22330
22331
22332
22333
22334
22335
22336
22337
22338
22339
22340
22341
22342
22343
22344
22345
22346
22347
22348
22349
22350
22351
22352
22353
22354
22355
22356
22357
22358
22359
22360
22361
22362
22363
22364
22365
22366
22367
22368
22369
22370
22371
22372
22373
22374
22375
22376
22377
22378
22379
22380
22381
22382
22383
22384
22385
22386
22387
22388
22389
22390
22391
22392
22393
22394
22395
22396
22397
22398
22399
22400
22401
22402
22403
22404
22405
22406
22407
22408
22409
22410
22411
22412
22413
22414
22415
22416
22417
22418
22419
22420
22421
22422
22423
22424
22425
22426
22427
22428
22429
22430
22431
22432
22433
22434
22435
22436
22437
22438
22439
22440
22441
22442
22443
22444
22445
22446
22447
22448
22449
22450
22451
22452
22453
22454
22455
22456
22457
22458
22459
22460
22461
22462
22463
22464
22465
22466
22467
22468
22469
22470
22471
22472
22473
22474
22475
22476
22477
22478
22479
22480
22481
22482
22483
22484
22485
22486
22487
22488
22489
22490
22491
22492
22493
22494
22495
22496
22497
22498
22499
22500
22501
22502
22503
22504
22505
22506
22507
22508
22509
22510
22511
22512
22513
22514
22515
22516
22517
22518
22519
22520
22521
22522
22523
22524
22525
22526
22527
22528
22529
22530
22531
22532
22533
22534
22535
22536
22537
22538
22539
22540
22541
22542
22543
22544
22545
22546
22547
22548
22549
22550
22551
22552
22553
22554
22555
22556
22557
22558
22559
22560
22561
22562
22563
22564
22565
22566
22567
22568
22569
22570
22571
22572
22573
22574
22575
22576
22577
22578
22579
22580
22581
22582
22583
22584
22585
22586
22587
22588
22589
22590
22591
22592
22593
22594
22595
22596
22597
22598
22599
22600
22601
22602
22603
22604
22605
22606
22607
22608
22609
22610
22611
22612
22613
22614
22615
22616
22617
22618
22619
22620
22621
22622
22623
22624
22625
22626
22627
22628
22629
22630
22631
22632
22633
22634
22635
22636
22637
22638
22639
22640
22641
22642
22643
22644
22645
22646
22647
22648
22649
22650
22651
22652
22653
22654
22655
22656
22657
22658
22659
22660
22661
22662
22663
22664
22665
22666
22667
22668
22669
22670
22671
22672
22673
22674
22675
22676
22677
22678
22679
22680
22681
22682
22683
22684
22685
22686
22687
22688
22689
22690
22691
22692
22693
22694
22695
22696
22697
22698
22699
22700
22701
22702
22703
22704
22705
22706
22707
22708
22709
22710
22711
22712
22713
22714
22715
22716
22717
22718
22719
22720
22721
22722
22723
22724
22725
22726
22727
22728
22729
22730
22731
22732
22733
22734
22735
22736
22737
22738
22739
22740
22741
22742
22743
22744
22745
22746
22747
22748
22749
22750
22751
22752
22753
22754
22755
22756
22757
22758
22759
22760
22761
22762
22763
22764
22765
22766
22767
22768
22769
22770
22771
22772
22773
22774
22775
22776
22777
22778
22779
22780
22781
22782
22783
22784
22785
22786
22787
22788
22789
22790
22791
22792
22793
22794
22795
22796
22797
22798
22799
22800
22801
22802
22803
22804
22805
22806
22807
22808
22809
22810
22811
22812
22813
22814
22815
22816
22817
22818
22819
22820
22821
22822
22823
22824
22825
22826
22827
22828
22829
22830
22831
22832
22833
22834
22835
22836
22837
22838
22839
22840
22841
22842
22843
22844
22845
22846
22847
22848
22849
22850
22851
22852
22853
22854
22855
22856
22857
22858
22859
22860
22861
22862
22863
22864
22865
22866
22867
22868
22869
22870
22871
22872
22873
22874
22875
22876
22877
22878
22879
22880
22881
22882
22883
22884
22885
22886
22887
22888
22889
22890
22891
22892
22893
22894
22895
22896
22897
22898
22899
22900
22901
22902
22903
22904
22905
22906
22907
22908
22909
22910
22911
22912
22913
22914
22915
22916
22917
22918
22919
22920
22921
22922
22923
22924
22925
22926
22927
22928
22929
22930
22931
22932
22933
22934
22935
22936
22937
22938
22939
22940
22941
22942
22943
22944
22945
22946
22947
22948
22949
22950
22951
22952
22953
22954
22955
22956
22957
22958
22959
22960
22961
22962
22963
22964
22965
22966
22967
22968
22969
22970
22971
22972
22973
22974
22975
22976
22977
22978
22979
22980
22981
22982
22983
22984
22985
22986
22987
22988
22989
22990
22991
22992
22993
22994
22995
22996
22997
22998
22999
23000
23001
23002
23003
23004
23005
23006
23007
23008
23009
23010
23011
23012
23013
23014
23015
23016
23017
23018
23019
23020
23021
23022
23023
23024
23025
23026
23027
23028
23029
23030
23031
23032
23033
23034
23035
23036
23037
23038
23039
23040
23041
23042
23043
23044
23045
23046
23047
23048
23049
23050
23051
23052
23053
23054
23055
23056
23057
23058
23059
23060
23061
23062
23063
23064
23065
23066
23067
23068
23069
23070
23071
23072
23073
23074
23075
23076
23077
23078
23079
23080
23081
23082
23083
23084
23085
23086
23087
23088
23089
23090
23091
23092
23093
23094
23095
23096
23097
23098
23099
23100
23101
23102
23103
23104
23105
23106
23107
23108
23109
23110
23111
23112
23113
23114
23115
23116
23117
23118
23119
23120
23121
23122
23123
23124
23125
23126
23127
23128
23129
23130
23131
23132
23133
23134
23135
23136
23137
23138
23139
23140
23141
23142
23143
23144
23145
23146
23147
23148
23149
23150
23151
23152
23153
23154
23155
23156
23157
23158
23159
23160
23161
23162
23163
23164
23165
23166
23167
23168
23169
23170
23171
23172
23173
23174
23175
23176
23177
23178
23179
23180
23181
23182
23183
23184
23185
23186
23187
23188
23189
23190
23191
23192
23193
23194
23195
23196
23197
23198
23199
23200
23201
23202
23203
23204
23205
23206
23207
23208
23209
23210
23211
23212
23213
23214
23215
23216
23217
23218
23219
23220
23221
23222
23223
23224
23225
23226
23227
23228
23229
23230
23231
23232
23233
23234
23235
23236
23237
23238
23239
23240
23241
23242
23243
23244
23245
23246
23247
23248
23249
23250
23251
23252
23253
23254
23255
23256
23257
23258
23259
23260
23261
23262
23263
23264
23265
23266
23267
23268
23269
23270
23271
23272
23273
23274
23275
23276
23277
23278
23279
23280
23281
23282
23283
23284
23285
23286
23287
23288
23289
23290
23291
23292
23293
23294
23295
23296
23297
23298
23299
23300
23301
23302
23303
23304
23305
23306
23307
23308
23309
23310
23311
23312
23313
23314
23315
23316
23317
23318
23319
23320
23321
23322
23323
23324
23325
23326
23327
23328
23329
23330
23331
23332
23333
23334
23335
23336
23337
23338
23339
23340
23341
23342
23343
23344
23345
23346
23347
23348
23349
23350
23351
23352
23353
23354
23355
23356
23357
23358
23359
23360
23361
23362
23363
23364
23365
23366
23367
23368
23369
23370
23371
23372
23373
23374
23375
23376
23377
23378
23379
23380
23381
23382
23383
23384
23385
23386
23387
23388
23389
23390
23391
23392
23393
23394
23395
23396
23397
23398
23399
23400
23401
23402
23403
23404
23405
23406
23407
23408
23409
23410
23411
23412
23413
23414
23415
23416
23417
23418
23419
23420
23421
23422
23423
23424
23425
23426
23427
23428
23429
23430
23431
23432
23433
23434
23435
23436
23437
23438
23439
23440
23441
23442
23443
23444
23445
23446
23447
23448
23449
23450
23451
23452
23453
23454
23455
23456
23457
23458
23459
23460
23461
23462
23463
23464
23465
23466
23467
23468
23469
23470
23471
23472
23473
23474
23475
23476
23477
23478
23479
23480
23481
23482
23483
23484
23485
23486
23487
23488
23489
23490
23491
23492
23493
23494
23495
23496
23497
23498
23499
23500
23501
23502
23503
23504
23505
23506
23507
23508
23509
23510
23511
23512
23513
23514
23515
23516
23517
23518
23519
23520
23521
23522
23523
23524
23525
23526
23527
23528
23529
23530
23531
23532
23533
23534
23535
23536
23537
23538
23539
23540
23541
23542
23543
23544
23545
23546
23547
23548
23549
23550
23551
23552
23553
23554
23555
23556
23557
23558
23559
23560
23561
23562
23563
23564
23565
23566
23567
23568
23569
23570
23571
23572
23573
23574
23575
23576
23577
23578
23579
23580
23581
23582
23583
23584
23585
23586
23587
23588
23589
23590
23591
23592
23593
23594
23595
23596
23597
23598
23599
23600
23601
23602
23603
23604
23605
23606
23607
23608
23609
23610
23611
23612
23613
23614
23615
23616
23617
23618
23619
23620
23621
23622
23623
23624
23625
23626
23627
23628
23629
23630
23631
23632
23633
23634
23635
23636
23637
23638
23639
23640
23641
23642
23643
23644
23645
23646
23647
23648
23649
23650
23651
23652
23653
23654
23655
23656
23657
23658
23659
23660
23661
23662
23663
23664
23665
23666
23667
23668
23669
23670
23671
23672
23673
23674
23675
23676
23677
23678
23679
23680
23681
23682
23683
23684
23685
23686
23687
23688
23689
23690
23691
23692
23693
23694
23695
23696
23697
23698
23699
23700
23701
23702
23703
23704
23705
23706
23707
23708
23709
23710
23711
23712
23713
23714
23715
23716
23717
23718
23719
23720
23721
23722
23723
23724
23725
23726
23727
23728
23729
23730
23731
23732
23733
23734
23735
23736
23737
23738
23739
23740
23741
23742
23743
23744
23745
23746
23747
23748
23749
23750
23751
23752
23753
23754
23755
23756
23757
23758
23759
23760
23761
23762
23763
23764
23765
23766
23767
23768
23769
23770
23771
23772
23773
23774
23775
23776
23777
23778
23779
23780
23781
23782
23783
23784
23785
23786
23787
23788
23789
23790
23791
23792
23793
23794
23795
23796
23797
23798
23799
23800
23801
23802
23803
23804
23805
23806
23807
23808
23809
23810
23811
23812
23813
23814
23815
23816
23817
23818
23819
23820
23821
23822
23823
23824
23825
23826
23827
23828
23829
23830
23831
23832
23833
23834
23835
23836
23837
23838
23839
23840
23841
23842
23843
23844
23845
23846
23847
23848
23849
23850
23851
23852
23853
23854
23855
23856
23857
23858
23859
23860
23861
23862
23863
23864
23865
23866
23867
23868
23869
23870
23871
23872
23873
23874
23875
23876
23877
23878
23879
23880
23881
23882
23883
23884
23885
23886
23887
23888
23889
23890
23891
23892
23893
23894
23895
23896
23897
23898
23899
23900
23901
23902
23903
23904
23905
23906
23907
23908
23909
23910
23911
23912
23913
23914
23915
23916
23917
23918
23919
23920
23921
23922
23923
23924
23925
23926
23927
23928
23929
23930
23931
23932
23933
23934
23935
23936
23937
23938
23939
23940
23941
23942
23943
23944
23945
23946
23947
23948
23949
23950
23951
23952
23953
23954
23955
23956
23957
23958
23959
23960
23961
23962
23963
23964
23965
23966
23967
23968
23969
23970
23971
23972
23973
23974
23975
23976
23977
23978
23979
23980
23981
23982
23983
23984
23985
23986
23987
23988
23989
23990
23991
23992
23993
23994
23995
23996
23997
23998
23999
24000
24001
24002
24003
24004
24005
24006
24007
24008
24009
24010
24011
24012
24013
24014
24015
24016
24017
24018
24019
24020
24021
24022
24023
24024
24025
24026
24027
24028
24029
24030
24031
24032
24033
24034
24035
24036
24037
24038
24039
24040
24041
24042
24043
24044
24045
24046
24047
24048
24049
24050
24051
24052
24053
24054
24055
24056
24057
24058
24059
24060
24061
24062
24063
24064
24065
24066
24067
24068
24069
24070
24071
24072
24073
24074
24075
24076
24077
24078
24079
24080
24081
24082
24083
24084
24085
24086
24087
24088
24089
24090
24091
24092
24093
24094
24095
24096
24097
24098
24099
24100
24101
24102
24103
24104
24105
24106
24107
24108
24109
24110
24111
24112
24113
24114
24115
24116
24117
24118
24119
24120
24121
24122
24123
24124
24125
24126
24127
24128
24129
24130
24131
24132
24133
24134
24135
24136
24137
24138
24139
24140
24141
24142
24143
24144
24145
24146
24147
24148
24149
24150
24151
24152
24153
24154
24155
24156
24157
24158
24159
24160
24161
24162
24163
24164
24165
24166
24167
24168
24169
24170
24171
24172
24173
24174
24175
24176
24177
24178
24179
24180
24181
24182
24183
24184
24185
24186
24187
24188
24189
24190
24191
24192
24193
24194
24195
24196
24197
24198
24199
24200
24201
24202
24203
24204
24205
24206
24207
24208
24209
24210
24211
24212
24213
24214
24215
24216
24217
24218
24219
24220
24221
24222
24223
24224
24225
24226
24227
24228
24229
24230
24231
24232
24233
24234
24235
24236
24237
24238
24239
24240
24241
24242
24243
24244
24245
24246
24247
24248
24249
24250
24251
24252
24253
24254
24255
24256
24257
24258
24259
24260
24261
24262
24263
24264
24265
24266
24267
24268
24269
24270
24271
24272
24273
24274
24275
24276
24277
24278
24279
24280
24281
24282
24283
24284
24285
24286
24287
24288
24289
24290
24291
24292
24293
24294
24295
24296
24297
24298
24299
24300
24301
24302
24303
24304
24305
24306
24307
24308
24309
24310
24311
24312
24313
24314
24315
24316
24317
24318
24319
24320
24321
24322
24323
24324
24325
24326
24327
24328
24329
24330
24331
24332
24333
24334
24335
24336
24337
24338
24339
24340
24341
24342
24343
24344
24345
24346
24347
24348
24349
24350
24351
24352
24353
24354
24355
24356
24357
24358
24359
24360
24361
24362
24363
24364
24365
24366
24367
24368
24369
24370
24371
24372
24373
24374
24375
24376
24377
24378
24379
24380
24381
24382
24383
24384
24385
24386
24387
24388
24389
24390
24391
24392
24393
24394
24395
24396
24397
24398
24399
24400
24401
24402
24403
24404
24405
24406
24407
24408
24409
24410
24411
24412
24413
24414
24415
24416
24417
24418
24419
24420
24421
24422
24423
24424
24425
24426
24427
24428
24429
24430
24431
24432
24433
24434
24435
24436
24437
24438
24439
24440
24441
24442
24443
24444
24445
24446
24447
24448
24449
24450
24451
24452
24453
24454
24455
24456
24457
24458
24459
24460
24461
24462
24463
24464
24465
24466
24467
24468
24469
24470
24471
24472
24473
24474
24475
24476
24477
24478
24479
24480
24481
24482
24483
24484
24485
24486
24487
24488
24489
24490
24491
24492
24493
24494
24495
24496
24497
24498
24499
24500
24501
24502
24503
24504
24505
24506
24507
24508
24509
24510
24511
24512
24513
24514
24515
24516
24517
24518
24519
24520
24521
24522
24523
24524
24525
24526
24527
24528
24529
24530
24531
24532
24533
24534
24535
24536
24537
24538
24539
24540
24541
24542
24543
24544
24545
24546
24547
24548
24549
24550
24551
24552
24553
24554
24555
24556
24557
24558
24559
24560
24561
24562
24563
24564
24565
24566
24567
24568
24569
24570
24571
24572
24573
24574
24575
24576
24577
24578
24579
24580
24581
24582
24583
24584
24585
24586
24587
24588
24589
24590
24591
24592
24593
24594
24595
24596
24597
24598
24599
24600
24601
24602
24603
24604
24605
24606
24607
24608
24609
24610
24611
24612
24613
24614
24615
24616
24617
24618
24619
24620
24621
24622
24623
24624
24625
24626
24627
24628
24629
24630
24631
24632
24633
24634
24635
24636
24637
24638
24639
24640
24641
24642
24643
24644
24645
24646
24647
24648
24649
24650
24651
24652
24653
24654
24655
24656
24657
24658
24659
24660
24661
24662
24663
24664
24665
24666
24667
24668
24669
24670
24671
24672
24673
24674
24675
24676
24677
24678
24679
24680
24681
24682
24683
24684
24685
24686
24687
24688
24689
24690
24691
24692
24693
24694
24695
24696
24697
24698
24699
24700
24701
24702
24703
24704
24705
24706
24707
24708
24709
24710
24711
24712
24713
24714
24715
24716
24717
24718
24719
24720
24721
24722
24723
24724
24725
24726
24727
24728
24729
24730
24731
24732
24733
24734
24735
24736
24737
24738
24739
24740
24741
24742
24743
24744
24745
24746
24747
24748
24749
24750
24751
24752
24753
24754
24755
24756
24757
24758
24759
24760
24761
24762
24763
24764
24765
24766
24767
24768
24769
24770
24771
24772
24773
24774
24775
24776
24777
24778
24779
24780
24781
24782
24783
24784
24785
24786
24787
24788
24789
24790
24791
24792
24793
24794
24795
24796
24797
24798
24799
24800
24801
24802
24803
24804
24805
24806
24807
24808
24809
24810
24811
24812
24813
24814
24815
24816
24817
24818
24819
24820
24821
24822
24823
24824
24825
24826
24827
24828
24829
24830
24831
24832
24833
24834
24835
24836
24837
24838
24839
24840
24841
24842
24843
24844
24845
24846
24847
24848
24849
24850
24851
24852
24853
24854
24855
24856
24857
24858
24859
24860
24861
24862
24863
24864
24865
24866
24867
24868
24869
24870
24871
24872
24873
24874
24875
24876
24877
24878
24879
24880
24881
24882
24883
24884
24885
24886
24887
24888
24889
24890
24891
24892
24893
24894
24895
24896
24897
24898
24899
24900
24901
24902
24903
24904
24905
24906
24907
24908
24909
24910
24911
24912
24913
24914
24915
24916
24917
24918
24919
24920
24921
24922
24923
24924
24925
24926
24927
24928
24929
24930
24931
24932
24933
24934
24935
24936
24937
24938
24939
24940
24941
24942
24943
24944
24945
24946
24947
24948
24949
24950
24951
24952
24953
24954
24955
24956
24957
24958
24959
24960
24961
24962
24963
24964
24965
24966
24967
24968
24969
24970
24971
24972
24973
24974
24975
24976
24977
24978
24979
24980
24981
24982
24983
24984
24985
24986
24987
24988
24989
24990
24991
24992
24993
24994
24995
24996
24997
24998
24999
25000
25001
25002
25003
25004
25005
25006
25007
25008
25009
25010
25011
25012
25013
25014
25015
25016
25017
25018
25019
25020
25021
25022
25023
25024
25025
25026
25027
25028
25029
25030
25031
25032
25033
25034
25035
25036
25037
25038
25039
25040
25041
25042
25043
25044
25045
25046
25047
25048
25049
25050
25051
25052
25053
25054
25055
25056
25057
25058
25059
25060
25061
25062
25063
25064
25065
25066
25067
25068
25069
25070
25071
25072
25073
25074
25075
25076
25077
25078
25079
25080
25081
25082
25083
25084
25085
25086
25087
25088
25089
25090
25091
25092
25093
25094
25095
25096
25097
25098
25099
25100
25101
25102
25103
25104
25105
25106
25107
25108
25109
25110
25111
25112
25113
25114
25115
25116
25117
25118
25119
25120
25121
25122
25123
25124
25125
25126
25127
25128
25129
25130
25131
25132
25133
25134
25135
25136
25137
25138
25139
25140
25141
25142
25143
25144
25145
25146
25147
25148
25149
25150
25151
25152
25153
25154
25155
25156
25157
25158
25159
25160
25161
25162
25163
25164
25165
25166
25167
25168
25169
25170
25171
25172
25173
25174
25175
25176
25177
25178
25179
25180
25181
25182
25183
25184
25185
25186
25187
25188
25189
25190
25191
25192
25193
25194
25195
25196
25197
25198
25199
From c21f53f17430230dab50df29b8ea1b71f99d09d6 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@unimore.it>
Date: Tue, 7 Apr 2015 13:39:12 +0200
Subject: [PATCH 01/51] Add BFQ-v8r12

This commit is the result of the following operations.

1. The squash of all the commits between "block: cgroups, kconfig,
build bits for BFQ-v7r11-4.5.0" and BFQ-v8r12 in the branch
bfq-mq-v8-v4.11

2. The renaming of two files (block/bfq-cgroup.c ->
block/bfq-cgroup-included.c and block/bfq-iosched.c ->
block/bfq-sq-iosched.c) and of one option (CONFIG_BFQ_GROUP_IOSCHED ->
CONFIG_BFQ_SQ_GROUP_IOSCHED), to avoid name clashes. These name
clashes are due to the presence of bfq in mainline from 4.12.

3. The modification of block/Makefile and block/Kconfig.iosched to
comply with the above renaming.

Signed-off-by: Mauro Andreolini <mauro.andreolini@unimore.it>
Signed-off-by: Arianna Avanzini <avanzini@google.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 Makefile                    |    2 +-
 block/Kconfig.iosched       |   31 +
 block/bfq-cgroup-included.c | 1190 ++++++++++
 block/bfq-ioc.c             |   36 +
 block/bfq-sched.c           | 2002 ++++++++++++++++
 block/bfq-sq-iosched.c      | 5379 +++++++++++++++++++++++++++++++++++++++++++
 block/bfq.h                 |  948 ++++++++
 include/linux/blkdev.h      |    2 +-
 9 files changed, 9589 insertions(+), 2 deletions(-)
 create mode 100644 block/bfq-cgroup-included.c
 create mode 100644 block/bfq-ioc.c
 create mode 100644 block/bfq-sched.c
 create mode 100644 block/bfq-sq-iosched.c
 create mode 100644 block/bfq.h

diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index a4a8914bf7a4..9e3f4c2f7390 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -40,6 +40,26 @@ config CFQ_GROUP_IOSCHED
 	---help---
 	  Enable group IO scheduling in CFQ.
 
+config IOSCHED_BFQ_SQ
+	tristate "BFQ-SQ I/O scheduler"
+	default n
+	---help---
+	The BFQ-SQ I/O scheduler (for legacy blk: SQ stands for
+	SingleQueue) distributes bandwidth among all processes
+	according to their weights, regardless of the device
+	parameters and with any workload. It also guarantees a low
+	latency to interactive and soft real-time applications.
+	Details in Documentation/block/bfq-iosched.txt
+
+config BFQ_SQ_GROUP_IOSCHED
+	bool "BFQ-SQ hierarchical scheduling support"
+	depends on IOSCHED_BFQ_SQ && BLK_CGROUP
+	default n
+	---help---
+
+	Enable hierarchical scheduling in BFQ-SQ, using the blkio
+	(cgroups-v1) or io (cgroups-v2) controller.
+
 choice
 
 	prompt "Default I/O scheduler"
@@ -54,6 +74,16 @@ choice
 	config DEFAULT_CFQ
 		bool "CFQ" if IOSCHED_CFQ=y
 
+	config DEFAULT_BFQ_SQ
+		bool "BFQ-SQ" if IOSCHED_BFQ_SQ=y
+		help
+		  Selects BFQ-SQ as the default I/O scheduler which will be
+		  used by default for all block devices.
+		  The BFQ-SQ I/O scheduler aims at distributing the bandwidth
+		  as desired, independently of the disk parameters and with
+		  any workload. It also tries to guarantee low latency to
+		  interactive and soft real-time applications.
+
 	config DEFAULT_NOOP
 		bool "No-op"
 
@@ -63,6 +93,7 @@ config DEFAULT_IOSCHED
 	string
 	default "deadline" if DEFAULT_DEADLINE
 	default "cfq" if DEFAULT_CFQ
+	default "bfq-sq" if DEFAULT_BFQ_SQ
 	default "noop" if DEFAULT_NOOP
 
 config MQ_IOSCHED_DEADLINE
diff --git a/block/Makefile b/block/Makefile
index 6a56303b9925..59026b425791 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -24,6 +24,7 @@ obj-$(CONFIG_MQ_IOSCHED_DEADLINE)	+= mq-deadline.o
 obj-$(CONFIG_MQ_IOSCHED_KYBER)	+= kyber-iosched.o
 bfq-y				:= bfq-iosched.o bfq-wf2q.o bfq-cgroup.o
 obj-$(CONFIG_IOSCHED_BFQ)	+= bfq.o
+obj-$(CONFIG_IOSCHED_BFQ_SQ)	+= bfq-sq-iosched.o
 
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
diff --git a/block/bfq-cgroup-included.c b/block/bfq-cgroup-included.c
new file mode 100644
index 000000000000..af7c216a3540
--- /dev/null
+++ b/block/bfq-cgroup-included.c
@@ -0,0 +1,1190 @@
+/*
+ * BFQ: CGROUPS support.
+ *
+ * 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) 2015 Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2016 Paolo Valente <paolo.valente@linaro.org>
+ *
+ * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ
+ * file.
+ */
+
+#ifdef CONFIG_BFQ_SQ_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);
+}
+
+static struct blkcg_policy blkcg_policy_bfq;
+
+/*
+ * 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 bfq_group *blkg_to_bfqg(struct blkcg_gq *blkg)
+{
+	struct blkg_policy_data *pd = blkg_to_pd(blkg, &blkcg_policy_bfq);
+
+	return pd_to_bfqg(pd);
+}
+
+/*
+ * 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 dead_stats 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;
+	struct bfq_group *bfqg;
+	struct bfq_data *bfqd;
+	struct bfq_entity *entity;
+	struct bfq_group_data *d;
+
+	blkg = pd_to_blkg(pd);
+	BUG_ON(!blkg);
+	bfqg = blkg_to_bfqg(blkg);
+	bfqd = blkg->q->elevator->elevator_data;
+	entity = &bfqg->entity;
+	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;
+	bfqg->active_entities = 0;
+	bfqg->rq_pos_tree = RB_ROOT;
+}
+
+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;
+
+	BUG_ON(!parent);
+	BUG_ON(!bfqg);
+	BUG_ON(bfqg == parent);
+
+	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;
+
+	assert_spin_locked(bfqd->queue->queue_lock);
+
+	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);
+		BUG_ON(!bfqg);
+		if (bfqg != bfqd->root_group) {
+			parent = bfqg_parent(bfqg);
+			if (!parent)
+				parent = bfqd->root_group;
+			BUG_ON(!parent);
+			bfq_group_set_parent(bfqg, parent);
+		}
+	}
+
+	return bfqg;
+}
+
+static void bfq_pos_tree_add_move(struct bfq_data *bfqd,
+				  struct bfq_queue *bfqq);
+
+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;
+
+	BUG_ON(!bfq_bfqq_busy(bfqq) && !RB_EMPTY_ROOT(&bfqq->sort_list));
+	BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list) && !entity->on_st);
+	BUG_ON(bfq_bfqq_busy(bfqq) && RB_EMPTY_ROOT(&bfqq->sort_list)
+	       && entity->on_st &&
+	       bfqq != bfqd->in_service_queue);
+	BUG_ON(!bfq_bfqq_busy(bfqq) && bfqq == bfqd->in_service_queue);
+
+	/* 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, BFQ_BFQQ_PREEMPTED);
+
+	BUG_ON(entity->on_st && !bfq_bfqq_busy(bfqq)
+	    && &bfq_entity_service_tree(entity)->idle !=
+	       entity->tree);
+
+	BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_busy(bfqq));
+
+	if (bfq_bfqq_busy(bfqq))
+		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
+	else if (entity->on_st) {
+		BUG_ON(&bfq_entity_service_tree(entity)->idle !=
+		       entity->tree);
+		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);
+
+	BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_busy(bfqq));
+	if (bfq_bfqq_busy(bfqq)) {
+		bfq_pos_tree_add_move(bfqd, bfqq);
+		bfq_activate_bfqq(bfqd, bfqq);
+	}
+
+	if (!bfqd->in_service_queue && !bfqd->rq_in_driver)
+		bfq_schedule_dispatch(bfqd);
+	BUG_ON(entity->on_st && !bfq_bfqq_busy(bfqq)
+	       && &bfq_entity_service_tree(entity)->idle !=
+	       entity->tree);
+}
+
+/**
+ * __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;
+
+	lockdep_assert_held(bfqd->queue->queue_lock);
+
+	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);
+
+	BUG_ON(!bfqq);
+	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;
+	struct bfq_data *bfqd;
+	struct bfq_entity *entity;
+	int i;
+
+	BUG_ON(!pd);
+	bfqg = pd_to_bfqg(pd);
+	BUG_ON(!bfqg);
+	bfqd = bfqg->bfqd;
+	BUG_ON(bfqd && !bfqd->root_group);
+
+	entity = bfqg->my_entity;
+
+	if (!entity) /* root group */
+		return;
+
+	/*
+	 * Empty all service_trees belonging to this group before
+	 * deactivating the group itself.
+	 */
+	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) {
+		BUG_ON(!bfqg->sched_data.service_tree);
+		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);
+		BUG_ON(!RB_EMPTY_ROOT(&st->active));
+		BUG_ON(!RB_EMPTY_ROOT(&st->idle));
+	}
+	BUG_ON(bfqg->sched_data.next_in_service);
+	BUG_ON(bfqg->sched_data.in_service_entity);
+
+	__bfq_deactivate_entity(entity, false);
+	bfq_put_async_queues(bfqd, bfqg);
+
+	/*
+	 * @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 void bfq_end_wr_async(struct bfq_data *bfqd)
+{
+	struct blkcg_gq *blkg;
+
+	list_for_each_entry(blkg, &bfqd->queue->blkg_list, q_node) {
+		struct bfq_group *bfqg = blkg_to_bfqg(blkg);
+		BUG_ON(!bfqg);
+
+		bfq_end_wr_async_queues(bfqd, bfqg);
+	}
+	bfq_end_wr_async_queues(bfqd, bfqd->root_group);
+}
+
+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_SQ_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 void bfq_end_wr_async(struct bfq_data *bfqd)
+{
+	bfq_end_wr_async_queues(bfqd, bfqd->root_group);
+}
+
+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
diff --git a/block/bfq-ioc.c b/block/bfq-ioc.c
new file mode 100644
index 000000000000..fb7bb8f08b75
--- /dev/null
+++ b/block/bfq-ioc.c
@@ -0,0 +1,36 @@
+/*
+ * BFQ: I/O context handling.
+ *
+ * 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>
+ */
+
+/**
+ * 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.
+ *
+ * Queue lock must be held.
+ */
+static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
+					struct io_context *ioc)
+{
+	if (ioc)
+		return icq_to_bic(ioc_lookup_icq(ioc, bfqd->queue));
+	return NULL;
+}
diff --git a/block/bfq-sched.c b/block/bfq-sched.c
new file mode 100644
index 000000000000..ac8991bca9fa
--- /dev/null
+++ b/block/bfq-sched.c
@@ -0,0 +1,2002 @@
+/*
+ * BFQ: Hierarchical B-WF2Q+ 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) 2015 Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2016 Paolo Valente <paolo.valente@linaro.org>
+ */
+
+static struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
+
+/**
+ * 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;
+	struct bfq_queue *bfqq;
+	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;
+
+	bfqq = bfq_entity_to_bfqq(next_in_service);
+	if (bfqq)
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+			     "update_next_in_service: chosen this queue");
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	else {
+		struct bfq_group *bfqg =
+			container_of(next_in_service,
+				     struct bfq_group, entity);
+
+		bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
+			     "update_next_in_service: chosen this entity");
+	}
+#endif
+	return parent_sched_may_change;
+}
+
+#ifdef CONFIG_BFQ_SQ_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;
+
+	BUG_ON(!next_in_service);
+
+	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.
+ *
+ * In contrast, the entity could stil be a candidate for next service
+ * if it is not a queue, and has more than one child. In fact, even if
+ * one of its children is about to be set in service, other children
+ * may still be the next to serve. As a consequence, a non-queue
+ * entity is not a candidate for next-service only if it has only one
+ * child. And only if this condition holds, then the function returns
+ * true for a non-queue entity.
+ */
+static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
+{
+	struct bfq_group *bfqg;
+
+	if (bfq_entity_to_bfqq(entity))
+		return true;
+
+	bfqg = container_of(entity, struct bfq_group, entity);
+
+	BUG_ON(bfqg == ((struct bfq_data *)(bfqg->bfqd))->root_group);
+	BUG_ON(bfqg->active_entities == 0);
+	if (bfqg->active_entities == 1)
+		return true;
+
+	return false;
+}
+
+#else /* CONFIG_BFQ_SQ_GROUP_IOSCHED */
+#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_SQ_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;
+
+	BUG_ON(!entity);
+
+	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);
+	unsigned long long start, finish, delta;
+
+	BUG_ON(entity->weight == 0);
+
+	entity->finish = entity->start +
+		bfq_delta(service, entity->weight);
+
+	start = ((entity->start>>10)*1000)>>12;
+	finish = ((entity->finish>>10)*1000)>>12;
+	delta = ((bfq_delta(service, entity->weight)>>10)*1000)>>12;
+
+	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",
+			start, finish, delta);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	} else {
+		struct bfq_group *bfqg =
+			container_of(entity, struct bfq_group, entity);
+
+		bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
+			"calc_finish group: serv %lu, w %d",
+			     service, entity->weight);
+		bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
+			"calc_finish group: start %llu, finish %llu, delta %llu",
+			start, finish, delta);
+#endif
+	}
+}
+
+/**
+ * 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)
+{
+	BUG_ON(entity->tree != root);
+
+	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;
+
+	BUG_ON(entity->tree != &st->idle);
+
+	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;
+
+	BUG_ON(entity->tree);
+
+	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);
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	entity->min_start = entity->start;
+	bfq_update_min(entity, node->rb_right);
+	bfq_update_min(entity, node->rb_left);
+
+	if (bfqq) {
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+			     "update_active_node: new min_start %llu",
+			     ((entity->min_start>>10)*1000)>>12);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	} else {
+		struct bfq_group *bfqg =
+			container_of(entity, struct bfq_group, entity);
+
+		bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
+			     "update_active_node: new min_start %llu",
+			     ((entity->min_start>>10)*1000)>>12);
+#endif
+	}
+}
+
+/**
+ * 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;
+}
+
+static void bfq_weights_tree_add(struct bfq_data *bfqd,
+				 struct bfq_entity *entity,
+				 struct rb_root *root);
+
+static void bfq_weights_tree_remove(struct bfq_data *bfqd,
+				    struct bfq_entity *entity,
+				    struct rb_root *root);
+
+
+/**
+ * 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_SQ_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_SQ_GROUP_IOSCHED
+	sd = entity->sched_data;
+	bfqg = container_of(sd, struct bfq_group, sched_data);
+	BUG_ON(!bfqg);
+	bfqd = (struct bfq_data *)bfqg->bfqd;
+#endif
+	if (bfqq)
+		list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	else { /* bfq_group */
+		BUG_ON(!bfqd);
+		bfq_weights_tree_add(bfqd, entity, &bfqd->group_weights_tree);
+	}
+	if (bfqg != bfqd->root_group) {
+		BUG_ON(!bfqg);
+		BUG_ON(!bfqd);
+		bfqg->active_entities++;
+	}
+#endif
+}
+
+/**
+ * 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)
+{
+	BUG_ON(ioprio < 0 || ioprio >= IOPRIO_BE_NR);
+	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)
+{
+	BUG_ON(weight < BFQ_MIN_WEIGHT || weight > BFQ_MAX_WEIGHT);
+	return IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - weight < 0 ?
+		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_SQ_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_SQ_GROUP_IOSCHED
+	sd = entity->sched_data;
+	bfqg = container_of(sd, struct bfq_group, sched_data);
+	BUG_ON(!bfqg);
+	bfqd = (struct bfq_data *)bfqg->bfqd;
+#endif
+	if (bfqq)
+		list_del(&bfqq->bfqq_list);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	else { /* bfq_group */
+		BUG_ON(!bfqd);
+		bfq_weights_tree_remove(bfqd, entity,
+					&bfqd->group_weights_tree);
+	}
+	if (bfqg != bfqd->root_group) {
+		BUG_ON(!bfqg);
+		BUG_ON(!bfqd);
+		BUG_ON(!bfqg->active_entities);
+		bfqg->active_entities--;
+	}
+#endif
+}
+
+/**
+ * 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);
+	BUG_ON(!entity->on_st);
+
+	entity->on_st = false;
+	st->wsum -= entity->weight;
+	if (bfqq && !is_in_service) {
+		bfq_log_bfqq(bfqq->bfqd, bfqq, "forget_entity (before): %p %d",
+			     bfqq, bfqq->ref);
+		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);
+}
+
+/*
+ * Update weight and priority of entity. If update_class_too is true,
+ * then update the ioprio_class of entity too.
+ *
+ * The reason why the update of ioprio_class is controlled through the
+ * last parameter is as follows. Changing the ioprio class of an
+ * entity implies changing the destination service trees for that
+ * entity. If such a change occurred when the entity is already on one
+ * of the service trees for its previous class, then the state of the
+ * entity would become more complex: none of the new possible service
+ * trees for the entity, according to bfq_entity_service_tree(), would
+ * match any of the possible service trees on which the entity
+ * is. Complex operations involving these trees, such as entity
+ * activations and deactivations, should take into account this
+ * additional complexity.  To avoid this issue, this function is
+ * invoked with update_class_too unset in the points in the code where
+ * entity may happen to be on some tree.
+ */
+static struct bfq_service_tree *
+__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
+				struct bfq_entity *entity,
+				bool update_class_too)
+{
+	struct bfq_service_tree *new_st = old_st;
+
+	if (entity->prio_changed) {
+		struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+		unsigned int prev_weight, new_weight;
+		struct bfq_data *bfqd = NULL;
+		struct rb_root *root;
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+		struct bfq_sched_data *sd;
+		struct bfq_group *bfqg;
+#endif
+
+		if (bfqq)
+			bfqd = bfqq->bfqd;
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+		else {
+			sd = entity->my_sched_data;
+			bfqg = container_of(sd, struct bfq_group, sched_data);
+			BUG_ON(!bfqg);
+			bfqd = (struct bfq_data *)bfqg->bfqd;
+			BUG_ON(!bfqd);
+		}
+#endif
+
+		BUG_ON(old_st->wsum < entity->weight);
+		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 && update_class_too)
+			bfqq->ioprio_class = bfqq->new_ioprio_class;
+
+		/*
+		 * Reset prio_changed only if the ioprio_class change
+		 * is not pending any longer.
+		 */
+		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 *
+			     (bfqq ? bfqq->wr_coeff : 1);
+		/*
+		 * If the weight of the entity changes, remove the entity
+		 * from its old weight counter (if there is a counter
+		 * associated with the entity), and add it to the counter
+		 * associated with its new weight.
+		 */
+		if (prev_weight != new_weight) {
+			if (bfqq)
+				bfq_log_bfqq(bfqq->bfqd, bfqq,
+					     "weight changed %d %d(%d %d)",
+					     prev_weight, new_weight,
+					     entity->orig_weight,
+					     bfqq->wr_coeff);
+
+			root = bfqq ? &bfqd->queue_weights_tree :
+				      &bfqd->group_weights_tree;
+			bfq_weights_tree_remove(bfqd, entity, root);
+		}
+		entity->weight = new_weight;
+		/*
+		 * Add the entity to its weights tree only if it is
+		 * not associated with a weight-raised queue.
+		 */
+		if (prev_weight != new_weight &&
+		    (bfqq ? bfqq->wr_coeff == 1 : 1))
+			/* If we get here, root has been initialized. */
+			bfq_weights_tree_add(bfqd, entity, root);
+
+		new_st->wsum += entity->weight;
+
+		if (new_st != old_st)
+			entity->start = new_st->vtime;
+	}
+
+	return new_st;
+}
+
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+static void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
+#endif
+
+/**
+ * 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;
+
+		BUG_ON(st->wsum == 0);
+
+		st->vtime += bfq_delta(served, st->wsum);
+		bfq_forget_idle(st);
+	}
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	bfqg_stats_set_start_empty_time(bfqq_group(bfqq));
+#endif
+	st = bfq_entity_service_tree(&bfqq->entity);
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %d secs, vtime %llu on %p",
+		     served,  ((st->vtime>>10)*1000)>>12, st);
+}
+
+/**
+ * bfq_bfqq_charge_time - charge an amount of service equivalent to the length
+ *			  of the time interval during which bfqq has been in
+ *			  service.
+ * @bfqd: the device
+ * @bfqq: the queue that needs a service update.
+ * @time_ms: the amount of time during which the queue has received service
+ *
+ * If a queue does not consume its budget fast enough, then providing
+ * the queue with service fairness may impair throughput, more or less
+ * severely. For this reason, queues that consume their budget slowly
+ * are provided with time fairness instead of service fairness. This
+ * goal is achieved through the BFQ scheduling engine, even if such an
+ * engine works in the service, and not in the time domain. The trick
+ * is charging these queues with an inflated amount of service, equal
+ * to the amount of service that they would have received during their
+ * service slot if they had been fast, i.e., if their requests had
+ * been dispatched at a rate equal to the estimated peak rate.
+ *
+ * It is worth noting that time fairness can cause important
+ * distortions in terms of bandwidth distribution, on devices with
+ * internal queueing. The reason is that I/O requests dispatched
+ * during the service slot of a queue may be served after that service
+ * slot is finished, and may have a total processing time loosely
+ * correlated with the duration of the service slot. This is
+ * especially true for short service slots.
+ */
+static void bfq_bfqq_charge_time(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+				 unsigned long time_ms)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+	int tot_serv_to_charge = entity->service;
+	unsigned int timeout_ms = jiffies_to_msecs(bfq_timeout);
+
+	if (time_ms > 0 && time_ms < timeout_ms)
+		tot_serv_to_charge =
+			(bfqd->bfq_max_budget * time_ms) / timeout_ms;
+
+	if (tot_serv_to_charge < entity->service)
+		tot_serv_to_charge = entity->service;
+
+	bfq_log_bfqq(bfqq->bfqd, bfqq,
+		     "charge_time: %lu/%u ms, %d/%d/%d sectors",
+		     time_ms, timeout_ms, entity->service,
+		     tot_serv_to_charge, entity->budget);
+
+	/* Increase budget to avoid inconsistencies */
+	if (tot_serv_to_charge > entity->budget)
+		entity->budget = tot_serv_to_charge;
+
+	bfq_bfqq_served(bfqq,
+			max_t(int, 0, tot_serv_to_charge - entity->service));
+}
+
+static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
+					struct bfq_service_tree *st,
+					bool backshifted)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct bfq_sched_data *sd = entity->sched_data;
+
+	/*
+	 * When this function is invoked, entity is not in any service
+	 * tree, then it is safe to invoke next function with the last
+	 * parameter set (see the comments on the function).
+	 */
+	st = __bfq_entity_update_weight_prio(st, entity, true);
+	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.
+	 *
+	 * As a special case, if bfqq is weight-raised, push up
+	 * timestamps much less, to keep very low the probability that
+	 * this push up causes the backshifted finish timestamps of
+	 * weight-raised queues to become higher than the backshifted
+	 * finish timestamps of non weight-raised queues.
+	 */
+	if (backshifted && bfq_gt(st->vtime, entity->finish)) {
+		unsigned long delta = st->vtime - entity->finish;
+
+		if (bfqq)
+			delta /= bfqq->wr_coeff;
+
+		entity->start += delta;
+		entity->finish += delta;
+
+		if (bfqq) {
+			bfq_log_bfqq(bfqq->bfqd, bfqq,
+				     "__activate_entity: new queue finish %llu",
+				     ((entity->finish>>10)*1000)>>12);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+		} else {
+			struct bfq_group *bfqg =
+				container_of(entity, struct bfq_group, entity);
+
+			bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
+				     "__activate_entity: new group finish %llu",
+				     ((entity->finish>>10)*1000)>>12);
+#endif
+		}
+	}
+
+	bfq_active_insert(st, entity);
+
+	if (bfqq) {
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+			"__activate_entity: queue %seligible in st %p",
+			     entity->start <= st->vtime ? "" : "non ", st);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	} else {
+		struct bfq_group *bfqg =
+			container_of(entity, struct bfq_group, entity);
+
+		bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
+			"__activate_entity: group %seligible in st %p",
+			     entity->start <= st->vtime ? "" : "non ", st);
+#endif
+	}
+	BUG_ON(RB_EMPTY_ROOT(&st->active));
+	BUG_ON(&st->active != &sd->service_tree->active &&
+	       &st->active != &(sd->service_tree+1)->active &&
+	       &st->active != &(sd->service_tree+2)->active);
+}
+
+/**
+ * __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_sched_data *sd = entity->sched_data;
+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	bool backshifted = false;
+	unsigned long long min_vstart;
+
+	BUG_ON(!sd);
+	BUG_ON(!st);
+
+	/* 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);
+
+		BUG_ON(entity->on_st && bfqq);
+
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+		if (entity->on_st && !bfqq) {
+			struct bfq_group *bfqg =
+				container_of(entity, struct bfq_group,
+					     entity);
+
+			bfq_log_bfqg((struct bfq_data *)bfqg->bfqd,
+				     bfqg,
+				     "activate bug, class %d in_service %p",
+				     bfq_class_idx(entity), sd->in_service_entity);
+		}
+#endif
+		BUG_ON(entity->on_st && !bfqq);
+		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);
+
+	BUG_ON(!sd);
+	BUG_ON(!st);
+
+	BUG_ON(entity != sd->in_service_entity &&
+	       entity->tree != &st->active);
+
+	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;
+		BUG_ON(entity->tree && entity->tree != &st->active);
+		/*
+		 * 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) {
+		BUG_ON(!entity);
+		sd = entity->sched_data;
+		__bfq_activate_requeue_entity(entity, sd, non_blocking_wait_rq);
+
+		BUG_ON(RB_EMPTY_ROOT(&sd->service_tree->active) &&
+		       RB_EMPTY_ROOT(&(sd->service_tree+1)->active) &&
+		       RB_EMPTY_ROOT(&(sd->service_tree+2)->active));
+
+		if (!bfq_update_next_in_service(sd, entity) && !requeue) {
+			BUG_ON(!sd->next_in_service);
+			break;
+		}
+		BUG_ON(!sd->next_in_service);
+	}
+}
+
+/**
+ * __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;
+	bool is_in_service;
+
+	if (!entity->on_st) { /* entity never activated, or already inactive */
+		BUG_ON(sd && entity == sd->in_service_entity);
+		return false;
+	}
+
+	/*
+	 * If we get here, then entity is active, which implies that
+	 * bfq_group_set_parent has already been invoked for the group
+	 * represented by entity. Therefore, the field
+	 * entity->sched_data has been set, and we can safely use it.
+	 */
+	st = bfq_entity_service_tree(entity);
+	is_in_service = entity == sd->in_service_entity;
+
+	BUG_ON(is_in_service && entity->tree && entity->tree != &st->active);
+
+	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);
+	else if (entity->tree)
+		BUG();
+
+	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;
+
+		BUG_ON(sd == NULL); /*
+				     * It would mean that this is the
+				     * root group.
+				     */
+
+		BUG_ON(expiration && entity != sd->in_service_entity);
+
+		BUG_ON(entity != sd->in_service_entity &&
+		       entity->tree ==
+		       &bfq_entity_service_tree(entity)->active &&
+		       !sd->next_in_service);
+
+		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).
+			 */
+			BUG_ON(expiration); /*
+					     * entity cannot be already out of
+					     * any tree
+					     */
+			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.
+			 */
+			BUG_ON(sd->next_in_service == entity);
+			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) {
+		struct bfq_queue *bfqq = bfq_entity_to_bfqq(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;
+		BUG_ON(expiration && sd->in_service_entity != entity);
+
+		if (bfqq)
+			bfq_log_bfqq(bfqq->bfqd, bfqq,
+				     "invoking udpdate_next for this queue");
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+		else {
+			struct bfq_group *bfqg =
+				container_of(entity,
+					     struct bfq_group, entity);
+
+			bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
+				     "invoking udpdate_next for this entity");
+		}
+#endif
+		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)) {
+		struct bfq_queue *bfqq = bfq_entity_to_bfqq(root_entity);
+
+		if (bfqq)
+			bfq_log_bfqq(bfqq->bfqd, bfqq,
+				     "calc_vtime_jump: new value %llu",
+				     root_entity->min_start);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+		else {
+			struct bfq_group *bfqg =
+				container_of(root_entity, struct bfq_group,
+					     entity);
+
+			bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
+				     "calc_vtime_jump: new value %llu",
+				     root_entity->min_start);
+		}
+#endif
+		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;
+
+		BUG_ON(bfq_gt(entry->min_start, vtime));
+
+		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;
+	}
+
+	BUG_ON(!first && !RB_EMPTY_ROOT(&st->active));
+	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
+#if 0
+			 , bool force
+#endif
+	)
+{
+	struct bfq_entity *entity
+#if 0
+		, *new_next_in_service = NULL
+#endif
+		;
+	u64 new_vtime;
+	struct bfq_queue *bfqq;
+
+	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);
+	BUG_ON(bfq_gt(entity->start, new_vtime));
+
+	/* Log some information */
+	bfqq = bfq_entity_to_bfqq(entity);
+	if (bfqq)
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+			     "__lookup_next: start %llu vtime %llu st %p",
+			     ((entity->start>>10)*1000)>>12,
+			     ((new_vtime>>10)*1000)>>12, st);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	else {
+		struct bfq_group *bfqg =
+			container_of(entity, struct bfq_group, entity);
+
+		bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
+			     "__lookup_next: start %llu vtime %llu st %p",
+			     ((entity->start>>10)*1000)>>12,
+			     ((new_vtime>>10)*1000)>>12, st);
+	}
+#endif
+
+	BUG_ON(!entity);
+
+	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;
+	struct bfq_queue *bfqq;
+	int class_idx = 0;
+
+	BUG_ON(!sd);
+	BUG_ON(!st);
+	/*
+	 * 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;
+	}
+
+	BUG_ON(!entity &&
+	       (!RB_EMPTY_ROOT(&st->active) || !RB_EMPTY_ROOT(&(st+1)->active) ||
+		!RB_EMPTY_ROOT(&(st+2)->active)));
+
+	if (!entity)
+		return NULL;
+
+	/* Log some information */
+	bfqq = bfq_entity_to_bfqq(entity);
+	if (bfqq)
+		bfq_log_bfqq(bfqq->bfqd, bfqq, "chosen from st %p %d",
+			     st + class_idx, class_idx);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	else {
+		struct bfq_group *bfqg =
+			container_of(entity, struct bfq_group, entity);
+
+		bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
+			     "chosen from st %p %d",
+			     st + class_idx, class_idx);
+	}
+#endif
+
+	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;
+
+	BUG_ON(bfqd->in_service_queue);
+
+	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) {
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+		if (entity) {
+			struct bfq_group *bfqg =
+				container_of(entity, struct bfq_group, entity);
+
+			bfq_log_bfqg(bfqd, bfqg,
+				     "get_next_queue: lookup in this group");
+			if (!sd->next_in_service)
+				pr_crit("get_next_queue: lookup in this group");
+		} else {
+			bfq_log_bfqg(bfqd, bfqd->root_group,
+				     "get_next_queue: lookup in root group");
+			if (!sd->next_in_service)
+				pr_crit("get_next_queue: lookup in root group");
+		}
+#endif
+
+		BUG_ON(!sd->next_in_service);
+
+		/*
+		 * 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.
+		 */
+
+		/* Log some information */
+		bfqq = bfq_entity_to_bfqq(entity);
+		if (bfqq)
+			bfq_log_bfqq(bfqd, bfqq,
+			     "get_next_queue: this queue, finish %llu",
+				(((entity->finish>>10)*1000)>>10)>>2);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+		else {
+			struct bfq_group *bfqg =
+				container_of(entity, struct bfq_group, entity);
+
+			bfq_log_bfqg(bfqd, bfqg,
+			     "get_next_queue: this entity, finish %llu",
+				(((entity->finish>>10)*1000)>>10)>>2);
+		}
+#endif
+
+	}
+
+	BUG_ON(!entity);
+	bfqq = bfq_entity_to_bfqq(entity);
+	BUG_ON(!bfqq);
+
+	/*
+	 * 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;
+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+
+	BUG_ON(bfqq == bfqd->in_service_queue);
+	BUG_ON(entity->tree != &st->active && entity->tree != &st->idle &&
+	       entity->on_st);
+
+	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)
+{
+	BUG_ON(!bfq_bfqq_busy(bfqq));
+	BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
+
+	bfq_log_bfqq(bfqd, bfqq, "del from busy");
+
+	bfq_clear_bfqq_busy(bfqq);
+
+	BUG_ON(bfqd->busy_queues == 0);
+	bfqd->busy_queues--;
+
+	if (!bfqq->dispatched)
+		bfq_weights_tree_remove(bfqd, &bfqq->entity,
+					&bfqd->queue_weights_tree);
+
+	if (bfqq->wr_coeff > 1) {
+		bfqd->wr_busy_queues--;
+		BUG_ON(bfqd->wr_busy_queues < 0);
+	}
+
+	bfqg_stats_update_dequeue(bfqq_group(bfqq));
+
+	BUG_ON(bfqq->entity.budget < 0);
+
+	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)
+{
+	BUG_ON(bfq_bfqq_busy(bfqq));
+	BUG_ON(bfqq == bfqd->in_service_queue);
+
+	bfq_log_bfqq(bfqd, bfqq, "add to busy");
+
+	bfq_activate_bfqq(bfqd, bfqq);
+
+	bfq_mark_bfqq_busy(bfqq);
+	bfqd->busy_queues++;
+
+	if (!bfqq->dispatched)
+		if (bfqq->wr_coeff == 1)
+			bfq_weights_tree_add(bfqd, &bfqq->entity,
+					     &bfqd->queue_weights_tree);
+
+	if (bfqq->wr_coeff > 1) {
+		bfqd->wr_busy_queues++;
+		BUG_ON(bfqd->wr_busy_queues > bfqd->busy_queues);
+	}
+
+}
diff --git a/block/bfq-sq-iosched.c b/block/bfq-sq-iosched.c
new file mode 100644
index 000000000000..65e7c7e77f3c
--- /dev/null
+++ b/block/bfq-sq-iosched.c
@@ -0,0 +1,5379 @@
+/*
+ * 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) 2015 Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2017 Paolo Valente <paolo.valente@linaro.org>
+ *
+ * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ
+ * file.
+ *
+ * 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 and usage 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. 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.
+ *
+ * NOTE: if the main or only goal, with a given device, is to achieve
+ * the maximum-possible throughput at all times, then do switch off
+ * all low-latency heuristics for that device, by setting low_latency
+ * to 0.
+ *
+ * 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+, that is described in [2], together with
+ * H-WF2Q+, while the augmented tree used 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
+ *
+ * http://algogroup.unimo.it/people/paolo/disk_sched/bf1-v1-suite-results.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/jiffies.h>
+#include <linux/rbtree.h>
+#include <linux/ioprio.h>
+#include "blk.h"
+#include "bfq.h"
+
+/* 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, 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 u32 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);
+
+/*
+ * Async to sync throughput distribution is controlled as follows:
+ * when an async request is served, the entity is charged the number
+ * of sectors of the request, multiplied by the factor below
+ */
+static const int bfq_async_charge_factor = 10;
+
+/* 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 ns), 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 number of samples required to perform peak-rate update */
+#define BFQ_RATE_MIN_SAMPLES	32
+/* Min observation time interval required to perform a peak-rate update (ns) */
+#define BFQ_RATE_MIN_INTERVAL	(300*NSEC_PER_MSEC)
+/* Target observation time interval for a peak-rate update (ns) */
+#define BFQ_RATE_REF_INTERVAL	NSEC_PER_SEC
+
+/* Shift used for peak rate fixed precision calculations. */
+#define BFQ_RATE_SHIFT		16
+
+/*
+ * By default, BFQ computes the duration of the weight raising for
+ * interactive applications automatically, using the following formula:
+ * duration = (R / r) * T, where r is the peak rate of the device, and
+ * R and T are two reference parameters.
+ * In particular, R is the peak rate of the reference device (see below),
+ * and T is a reference time: given the systems that are likely to be
+ * installed on the reference device according to its speed class, T is
+ * about the maximum time needed, under BFQ and while reading two files in
+ * parallel, to load typical large applications on these systems.
+ * In practice, the slower/faster the device at hand is, the more/less it
+ * takes to load applications with respect to the reference device.
+ * Accordingly, the longer/shorter BFQ grants weight raising to interactive
+ * applications.
+ *
+ * BFQ uses four different reference pairs (R, T), depending on:
+ * . whether the device is rotational or non-rotational;
+ * . whether the device is slow, such as old or portable HDDs, as well as
+ *   SD cards, or fast, such as newer HDDs and SSDs.
+ *
+ * The device's speed class is dynamically (re)detected in
+ * bfq_update_peak_rate() every time the estimated peak rate is updated.
+ *
+ * In the following definitions, R_slow[0]/R_fast[0] and
+ * T_slow[0]/T_fast[0] are the reference values for a slow/fast
+ * rotational device, whereas R_slow[1]/R_fast[1] and
+ * T_slow[1]/T_fast[1] are the reference values for a slow/fast
+ * non-rotational device. Finally, device_speed_thresh are the
+ * thresholds used to switch between speed classes. The reference
+ * rates are not the actual peak rates of the devices used as a
+ * reference, but slightly lower values. The reason for using these
+ * slightly lower values is that the peak-rate estimator tends to
+ * yield slightly lower values than the actual peak rate (it can yield
+ * the actual peak rate only if there is only one process doing I/O,
+ * and the process does sequential I/O).
+ *
+ * Both the reference peak rates and the thresholds are measured in
+ * sectors/usec, left-shifted by BFQ_RATE_SHIFT.
+ */
+static int R_slow[2] = {1000, 10700};
+static int R_fast[2] = {14000, 33000};
+/*
+ * To improve readability, a conversion function is used to initialize the
+ * following arrays, which entails that they can be initialized only in a
+ * function.
+ */
+static int T_slow[2];
+static int T_fast[2];
+static int device_speed_thresh[2];
+
+#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])
+
+static void bfq_schedule_dispatch(struct bfq_data *bfqd);
+
+#include "bfq-ioc.c"
+#include "bfq-sched.c"
+#include "bfq-cgroup-included.c"
+
+#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)
+
+/*
+ * 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");
+		kblockd_schedule_work(&bfqd->unplug_work);
+	}
+}
+
+/*
+ * 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;
+	}
+}
+
+static struct bfq_queue *
+bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
+		     sector_t sector, struct rb_node **ret_parent,
+		     struct rb_node ***rb_link)
+{
+	struct rb_node **p, *parent;
+	struct bfq_queue *bfqq = NULL;
+
+	parent = NULL;
+	p = &root->rb_node;
+	while (*p) {
+		struct rb_node **n;
+
+		parent = *p;
+		bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+
+		/*
+		 * Sort strictly based on sector. Smallest to the left,
+		 * largest to the right.
+		 */
+		if (sector > blk_rq_pos(bfqq->next_rq))
+			n = &(*p)->rb_right;
+		else if (sector < blk_rq_pos(bfqq->next_rq))
+			n = &(*p)->rb_left;
+		else
+			break;
+		p = n;
+		bfqq = NULL;
+	}
+
+	*ret_parent = parent;
+	if (rb_link)
+		*rb_link = p;
+
+	bfq_log(bfqd, "rq_pos_tree_lookup %llu: returning %d",
+		(unsigned long long) sector,
+		bfqq ? bfqq->pid : 0);
+
+	return bfqq;
+}
+
+static void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct rb_node **p, *parent;
+	struct bfq_queue *__bfqq;
+
+	if (bfqq->pos_root) {
+		rb_erase(&bfqq->pos_node, bfqq->pos_root);
+		bfqq->pos_root = NULL;
+	}
+
+	if (bfq_class_idle(bfqq))
+		return;
+	if (!bfqq->next_rq)
+		return;
+
+	bfqq->pos_root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
+	__bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root,
+			blk_rq_pos(bfqq->next_rq), &parent, &p);
+	if (!__bfqq) {
+		rb_link_node(&bfqq->pos_node, parent, p);
+		rb_insert_color(&bfqq->pos_node, bfqq->pos_root);
+	} else
+		bfqq->pos_root = NULL;
+}
+
+/*
+ * Tell whether there are active queues or groups with differentiated weights.
+ */
+static bool bfq_differentiated_weights(struct bfq_data *bfqd)
+{
+	/*
+	 * For weights to differ, at least one of the trees must contain
+	 * at least two nodes.
+	 */
+	return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
+		(bfqd->queue_weights_tree.rb_node->rb_left ||
+		 bfqd->queue_weights_tree.rb_node->rb_right)
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	       ) ||
+	       (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) &&
+		(bfqd->group_weights_tree.rb_node->rb_left ||
+		 bfqd->group_weights_tree.rb_node->rb_right)
+#endif
+	       );
+}
+
+/*
+ * The following function returns true if every queue must receive the
+ * same share of the throughput (this condition is used when deciding
+ * whether idling may be disabled, see the comments in the function
+ * bfq_bfqq_may_idle()).
+ *
+ * Such a scenario occurs when:
+ * 1) all active queues have the same weight,
+ * 2) all active groups at the same level in the groups tree have the same
+ *    weight,
+ * 3) all active groups at the same level in the groups tree have the same
+ *    number of children.
+ *
+ * Unfortunately, keeping the necessary state for evaluating exactly the
+ * above symmetry conditions would be quite complex and time-consuming.
+ * Therefore this function evaluates, instead, the following stronger
+ * sub-conditions, for which it is much easier to maintain the needed
+ * state:
+ * 1) all active queues have the same weight,
+ * 2) all active groups have the same weight,
+ * 3) all active groups have at most one active child each.
+ * In particular, the last two conditions are always true if hierarchical
+ * support and the cgroups interface are not enabled, thus no state needs
+ * to be maintained in this case.
+ */
+static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
+{
+	return !bfq_differentiated_weights(bfqd);
+}
+
+/*
+ * If the weight-counter tree passed as input contains no counter for
+ * the weight of the input entity, then add that counter; otherwise just
+ * increment the existing counter.
+ *
+ * Note that weight-counter trees contain few nodes in mostly symmetric
+ * scenarios. For example, if all queues have the same weight, then the
+ * weight-counter tree for the queues may contain at most one node.
+ * This holds even if low_latency is on, because weight-raised queues
+ * are not inserted in the tree.
+ * In most scenarios, the rate at which nodes are created/destroyed
+ * should be low too.
+ */
+static void bfq_weights_tree_add(struct bfq_data *bfqd,
+				 struct bfq_entity *entity,
+				 struct rb_root *root)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+	/*
+	 * Do not insert if the entity is already associated with a
+	 * counter, which happens if:
+	 *   1) the entity is associated with a queue,
+	 *   2) a request arrival has caused the queue to become both
+	 *      non-weight-raised, and hence change its weight, and
+	 *      backlogged; in this respect, each of the two events
+	 *      causes an invocation of this function,
+	 *   3) this is the invocation of this function caused by the
+	 *      second event. This second invocation is actually useless,
+	 *      and we handle this fact by exiting immediately. More
+	 *      efficient or clearer solutions might possibly be adopted.
+	 */
+	if (entity->weight_counter)
+		return;
+
+	while (*new) {
+		struct bfq_weight_counter *__counter = container_of(*new,
+						struct bfq_weight_counter,
+						weights_node);
+		parent = *new;
+
+		if (entity->weight == __counter->weight) {
+			entity->weight_counter = __counter;
+			goto inc_counter;
+		}
+		if (entity->weight < __counter->weight)
+			new = &((*new)->rb_left);
+		else
+			new = &((*new)->rb_right);
+	}
+
+	entity->weight_counter = kzalloc(sizeof(struct bfq_weight_counter),
+					 GFP_ATOMIC);
+
+	/*
+	 * In the unlucky event of an allocation failure, we just
+	 * exit. This will cause the weight of entity to not be
+	 * considered in bfq_differentiated_weights, which, in its
+	 * turn, causes the scenario to be deemed wrongly symmetric in
+	 * case entity's weight would have been the only weight making
+	 * the scenario asymmetric. On the bright side, no unbalance
+	 * will however occur when entity becomes inactive again (the
+	 * invocation of this function is triggered by an activation
+	 * of entity). In fact, bfq_weights_tree_remove does nothing
+	 * if !entity->weight_counter.
+	 */
+	if (unlikely(!entity->weight_counter))
+		return;
+
+	entity->weight_counter->weight = entity->weight;
+	rb_link_node(&entity->weight_counter->weights_node, parent, new);
+	rb_insert_color(&entity->weight_counter->weights_node, root);
+
+inc_counter:
+	entity->weight_counter->num_active++;
+}
+
+/*
+ * Decrement the weight counter associated with the entity, and, if the
+ * counter reaches 0, remove the counter from the tree.
+ * See the comments to the function bfq_weights_tree_add() for considerations
+ * about overhead.
+ */
+static void bfq_weights_tree_remove(struct bfq_data *bfqd,
+				    struct bfq_entity *entity,
+				    struct rb_root *root)
+{
+	if (!entity->weight_counter)
+		return;
+
+	BUG_ON(RB_EMPTY_ROOT(root));
+	BUG_ON(entity->weight_counter->weight != entity->weight);
+
+	BUG_ON(!entity->weight_counter->num_active);
+	entity->weight_counter->num_active--;
+	if (entity->weight_counter->num_active > 0)
+		goto reset_entity_pointer;
+
+	rb_erase(&entity->weight_counter->weights_node, root);
+	kfree(entity->weight_counter);
+
+reset_entity_pointer:
+	entity->weight_counter = NULL;
+}
+
+/*
+ * 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);
+	BUG_ON(RB_EMPTY_NODE(&rq->rb_node));
+	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;
+
+	BUG_ON(list_empty(&bfqq->fifo));
+
+	/* Follow expired path, else get first next available. */
+	next = bfq_check_fifo(bfqq, last);
+	if (next) {
+		BUG_ON(next == last);
+		return next;
+	}
+
+	BUG_ON(RB_EMPTY_NODE(&last->rb_node));
+
+	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));
+}
+
+/* see the definition of bfq_async_charge_factor for details */
+static unsigned long bfq_serv_to_charge(struct request *rq,
+					struct bfq_queue *bfqq)
+{
+	if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1)
+		return blk_rq_sectors(rq);
+
+	/*
+	 * If there are no weight-raised queues, then amplify service
+	 * by just the async charge factor; otherwise amplify service
+	 * by twice the async charge factor, to further reduce latency
+	 * for weight-raised queues.
+	 */
+	if (bfqq->bfqd->wr_busy_queues == 0)
+		return blk_rq_sectors(rq) * bfq_async_charge_factor;
+
+	return blk_rq_sectors(rq) * 2 * bfq_async_charge_factor;
+}
+
+/**
+ * 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 bfq_service_tree *st = bfq_entity_service_tree(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;
+
+	BUG_ON(entity->tree != &st->active);
+	BUG_ON(entity == entity->sched_data->in_service_entity);
+
+	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 unsigned int bfq_wr_duration(struct bfq_data *bfqd)
+{
+	u64 dur;
+
+	if (bfqd->bfq_wr_max_time > 0)
+		return bfqd->bfq_wr_max_time;
+
+	dur = bfqd->RT_prod;
+	do_div(dur, bfqd->peak_rate);
+
+	/*
+	 * Limit duration between 3 and 13 seconds. Tests show that
+	 * higher values than 13 seconds often yield the opposite of
+	 * the desired result, i.e., worsen responsiveness by letting
+	 * non-interactive and non-soft-real-time applications
+	 * preserve weight raising for a too long time interval.
+	 *
+	 * On the other end, lower values than 3 seconds make it
+	 * difficult for most interactive tasks to complete their jobs
+	 * before weight-raising finishes.
+	 */
+	if (dur > msecs_to_jiffies(13000))
+		dur = msecs_to_jiffies(13000);
+	else if (dur < msecs_to_jiffies(3000))
+		dur = msecs_to_jiffies(3000);
+
+	return dur;
+}
+
+static void
+bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
+		      struct bfq_io_cq *bic, bool bfq_already_existing)
+{
+	unsigned int old_wr_coeff;
+	bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq);
+
+	if (bic->saved_idle_window)
+		bfq_mark_bfqq_idle_window(bfqq);
+	else
+		bfq_clear_bfqq_idle_window(bfqq);
+
+	if (bic->saved_IO_bound)
+		bfq_mark_bfqq_IO_bound(bfqq);
+	else
+		bfq_clear_bfqq_IO_bound(bfqq);
+
+	if (unlikely(busy))
+		old_wr_coeff = bfqq->wr_coeff;
+
+	bfqq->wr_coeff = bic->saved_wr_coeff;
+	bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt;
+	BUG_ON(time_is_after_jiffies(bfqq->wr_start_at_switch_to_srt));
+	bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish;
+	bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time;
+	BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish));
+
+	if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
+				   time_is_before_jiffies(bfqq->last_wr_start_finish +
+							  bfqq->wr_cur_max_time))) {
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+			     "resume state: switching off wr (%lu + %lu < %lu)",
+			     bfqq->last_wr_start_finish, bfqq->wr_cur_max_time,
+			     jiffies);
+
+		bfqq->wr_coeff = 1;
+	}
+
+	/* make sure weight will be updated, however we got here */
+	bfqq->entity.prio_changed = 1;
+
+	if (likely(!busy))
+		return;
+
+	if (old_wr_coeff == 1 && bfqq->wr_coeff > 1) {
+		bfqd->wr_busy_queues++;
+		BUG_ON(bfqd->wr_busy_queues > bfqd->busy_queues);
+	} else if (old_wr_coeff > 1 && bfqq->wr_coeff == 1) {
+		bfqd->wr_busy_queues--;
+		BUG_ON(bfqd->wr_busy_queues < 0);
+	}
+}
+
+static int bfqq_process_refs(struct bfq_queue *bfqq)
+{
+	int process_refs, io_refs;
+
+	lockdep_assert_held(bfqq->bfqd->queue->queue_lock);
+
+	io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE];
+	process_refs = bfqq->ref - io_refs - bfqq->entity.on_st;
+	BUG_ON(process_refs < 0);
+	return process_refs;
+}
+
+/* Empty burst list and add just bfqq (see comments to bfq_handle_burst) */
+static void bfq_reset_burst_list(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct bfq_queue *item;
+	struct hlist_node *n;
+
+	hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node)
+		hlist_del_init(&item->burst_list_node);
+	hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+	bfqd->burst_size = 1;
+	bfqd->burst_parent_entity = bfqq->entity.parent;
+}
+
+/* Add bfqq to the list of queues in current burst (see bfq_handle_burst) */
+static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	/* Increment burst size to take into account also bfqq */
+	bfqd->burst_size++;
+
+	bfq_log_bfqq(bfqd, bfqq, "add_to_burst %d", bfqd->burst_size);
+
+	BUG_ON(bfqd->burst_size > bfqd->bfq_large_burst_thresh);
+
+	if (bfqd->burst_size == bfqd->bfq_large_burst_thresh) {
+		struct bfq_queue *pos, *bfqq_item;
+		struct hlist_node *n;
+
+		/*
+		 * Enough queues have been activated shortly after each
+		 * other to consider this burst as large.
+		 */
+		bfqd->large_burst = true;
+		bfq_log_bfqq(bfqd, bfqq, "add_to_burst: large burst started");
+
+		/*
+		 * We can now mark all queues in the burst list as
+		 * belonging to a large burst.
+		 */
+		hlist_for_each_entry(bfqq_item, &bfqd->burst_list,
+				     burst_list_node) {
+			bfq_mark_bfqq_in_large_burst(bfqq_item);
+			bfq_log_bfqq(bfqd, bfqq_item, "marked in large burst");
+		}
+		bfq_mark_bfqq_in_large_burst(bfqq);
+		bfq_log_bfqq(bfqd, bfqq, "marked in large burst");
+
+		/*
+		 * From now on, and until the current burst finishes, any
+		 * new queue being activated shortly after the last queue
+		 * was inserted in the burst can be immediately marked as
+		 * belonging to a large burst. So the burst list is not
+		 * needed any more. Remove it.
+		 */
+		hlist_for_each_entry_safe(pos, n, &bfqd->burst_list,
+					  burst_list_node)
+			hlist_del_init(&pos->burst_list_node);
+	} else /*
+		* Burst not yet large: add bfqq to the burst list. Do
+		* not increment the ref counter for bfqq, because bfqq
+		* is removed from the burst list before freeing bfqq
+		* in put_queue.
+		*/
+		hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+}
+
+/*
+ * If many queues belonging to the same group happen to be created
+ * shortly after each other, then the processes associated with these
+ * queues have typically a common goal. In particular, bursts of queue
+ * creations are usually caused by services or applications that spawn
+ * many parallel threads/processes. Examples are systemd during boot,
+ * or git grep. To help these processes get their job done as soon as
+ * possible, it is usually better to not grant either weight-raising
+ * or device idling to their queues.
+ *
+ * In this comment we describe, firstly, the reasons why this fact
+ * holds, and, secondly, the next function, which implements the main
+ * steps needed to properly mark these queues so that they can then be
+ * treated in a different way.
+ *
+ * The above services or applications benefit mostly from a high
+ * throughput: the quicker the requests of the activated queues are
+ * cumulatively served, the sooner the target job of these queues gets
+ * completed. As a consequence, weight-raising any of these queues,
+ * which also implies idling the device for it, is almost always
+ * counterproductive. In most cases it just lowers throughput.
+ *
+ * On the other hand, a burst of queue creations may be caused also by
+ * the start of an application that does not consist of a lot of
+ * parallel I/O-bound threads. In fact, with a complex application,
+ * several short processes may need to be executed to start-up the
+ * application. In this respect, to start an application as quickly as
+ * possible, the best thing to do is in any case to privilege the I/O
+ * related to the application with respect to all other
+ * I/O. Therefore, the best strategy to start as quickly as possible
+ * an application that causes a burst of queue creations is to
+ * weight-raise all the queues created during the burst. This is the
+ * exact opposite of the best strategy for the other type of bursts.
+ *
+ * In the end, to take the best action for each of the two cases, the
+ * two types of bursts need to be distinguished. Fortunately, this
+ * seems relatively easy, by looking at the sizes of the bursts. In
+ * particular, we found a threshold such that only bursts with a
+ * larger size than that threshold are apparently caused by
+ * services or commands such as systemd or git grep. For brevity,
+ * hereafter we call just 'large' these bursts. BFQ *does not*
+ * weight-raise queues whose creation occurs in a large burst. In
+ * addition, for each of these queues BFQ performs or does not perform
+ * idling depending on which choice boosts the throughput more. The
+ * exact choice depends on the device and request pattern at
+ * hand.
+ *
+ * Unfortunately, false positives may occur while an interactive task
+ * is starting (e.g., an application is being started). The
+ * consequence is that the queues associated with the task do not
+ * enjoy weight raising as expected. Fortunately these false positives
+ * are very rare. They typically occur if some service happens to
+ * start doing I/O exactly when the interactive task starts.
+ *
+ * Turning back to the next function, it implements all the steps
+ * needed to detect the occurrence of a large burst and to properly
+ * mark all the queues belonging to it (so that they can then be
+ * treated in a different way). This goal is achieved by maintaining a
+ * "burst list" that holds, temporarily, the queues that belong to the
+ * burst in progress. The list is then used to mark these queues as
+ * belonging to a large burst if the burst does become large. The main
+ * steps are the following.
+ *
+ * . when the very first queue is created, the queue is inserted into the
+ *   list (as it could be the first queue in a possible burst)
+ *
+ * . if the current burst has not yet become large, and a queue Q that does
+ *   not yet belong to the burst is activated shortly after the last time
+ *   at which a new queue entered the burst list, then the function appends
+ *   Q to the burst list
+ *
+ * . if, as a consequence of the previous step, the burst size reaches
+ *   the large-burst threshold, then
+ *
+ *     . all the queues in the burst list are marked as belonging to a
+ *       large burst
+ *
+ *     . the burst list is deleted; in fact, the burst list already served
+ *       its purpose (keeping temporarily track of the queues in a burst,
+ *       so as to be able to mark them as belonging to a large burst in the
+ *       previous sub-step), and now is not needed any more
+ *
+ *     . the device enters a large-burst mode
+ *
+ * . if a queue Q that does not belong to the burst is created while
+ *   the device is in large-burst mode and shortly after the last time
+ *   at which a queue either entered the burst list or was marked as
+ *   belonging to the current large burst, then Q is immediately marked
+ *   as belonging to a large burst.
+ *
+ * . if a queue Q that does not belong to the burst is created a while
+ *   later, i.e., not shortly after, than the last time at which a queue
+ *   either entered the burst list or was marked as belonging to the
+ *   current large burst, then the current burst is deemed as finished and:
+ *
+ *        . the large-burst mode is reset if set
+ *
+ *        . the burst list is emptied
+ *
+ *        . Q is inserted in the burst list, as Q may be the first queue
+ *          in a possible new burst (then the burst list contains just Q
+ *          after this step).
+ */
+static void bfq_handle_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	/*
+	 * If bfqq is already in the burst list or is part of a large
+	 * burst, or finally has just been split, then there is
+	 * nothing else to do.
+	 */
+	if (!hlist_unhashed(&bfqq->burst_list_node) ||
+	    bfq_bfqq_in_large_burst(bfqq) ||
+	    time_is_after_eq_jiffies(bfqq->split_time +
+				     msecs_to_jiffies(10)))
+		return;
+
+	/*
+	 * If bfqq's creation happens late enough, or bfqq belongs to
+	 * a different group than the burst group, then the current
+	 * burst is finished, and related data structures must be
+	 * reset.
+	 *
+	 * In this respect, consider the special case where bfqq is
+	 * the very first queue created after BFQ is selected for this
+	 * device. In this case, last_ins_in_burst and
+	 * burst_parent_entity are not yet significant when we get
+	 * here. But it is easy to verify that, whether or not the
+	 * following condition is true, bfqq will end up being
+	 * inserted into the burst list. In particular the list will
+	 * happen to contain only bfqq. And this is exactly what has
+	 * to happen, as bfqq may be the first queue of the first
+	 * burst.
+	 */
+	if (time_is_before_jiffies(bfqd->last_ins_in_burst +
+	    bfqd->bfq_burst_interval) ||
+	    bfqq->entity.parent != bfqd->burst_parent_entity) {
+		bfqd->large_burst = false;
+		bfq_reset_burst_list(bfqd, bfqq);
+		bfq_log_bfqq(bfqd, bfqq,
+			"handle_burst: late activation or different group");
+		goto end;
+	}
+
+	/*
+	 * If we get here, then bfqq is being activated shortly after the
+	 * last queue. So, if the current burst is also large, we can mark
+	 * bfqq as belonging to this large burst immediately.
+	 */
+	if (bfqd->large_burst) {
+		bfq_log_bfqq(bfqd, bfqq, "handle_burst: marked in burst");
+		bfq_mark_bfqq_in_large_burst(bfqq);
+		goto end;
+	}
+
+	/*
+	 * If we get here, then a large-burst state has not yet been
+	 * reached, but bfqq is being activated shortly after the last
+	 * queue. Then we add bfqq to the burst.
+	 */
+	bfq_add_to_burst(bfqd, bfqq);
+end:
+	/*
+	 * At this point, bfqq either has been added to the current
+	 * burst or has caused the current burst to terminate and a
+	 * possible new burst to start. In particular, in the second
+	 * case, bfqq has become the first queue in the possible new
+	 * burst.  In both cases last_ins_in_burst needs to be moved
+	 * forward.
+	 */
+	bfqd->last_ins_in_burst = jiffies;
+
+}
+
+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 one of the two
+ * goals below.
+ *
+ * 1. 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:
+ *
+ * - BFQ_BFQQ_NO_MORE_REQUEST bfqq did not enjoy any device idling and
+ *   did not make it to issue a new request before its last request
+ *   was served;
+ *
+ * - BFQ_BFQQ_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.
+ *
+ * 2. Reduce latency. Even if timestamps are not backshifted to let
+ * the process associated with bfqq recover a service hole, bfqq may
+ * however happen to have, after being (re)activated, a lower finish
+ * timestamp than the in-service queue.  That is, the next budget of
+ * bfqq may have to be completed before the one of the in-service
+ * queue. If this is the case, then preempting the in-service queue
+ * allows this goal to be achieved, apart from the unpreemptible,
+ * outstanding requests mentioned above.
+ *
+ * Unfortunately, regardless of which of the above two goals one wants
+ * to achieve, service trees need first to be updated to know whether
+ * the in-service queue must be preempted. To have service trees
+ * correctly updated, the in-service queue must be expired and
+ * rescheduled, and bfqq must be scheduled too. This is one of the
+ * most costly operations (in future versions, the scheduling
+ * mechanism may be re-designed in such a way to make it possible to
+ * know whether preemption is needed without needing to update service
+ * trees). In addition, queue preemptions almost always cause random
+ * I/O, and thus loss of throughput. Because of these facts, the next
+ * function adopts the following simple scheme to avoid both costly
+ * operations and too frequent preemptions: it requests the expiration
+ * of the in-service queue (unconditionally) only for queues that need
+ * to recover a hole, or that either are weight-raised or deserve to
+ * be weight-raised.
+ */
+static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
+						struct bfq_queue *bfqq,
+						bool arrived_in_time,
+						bool wr_or_deserves_wr)
+{
+	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).
+		 */
+		BUG_ON(bfqq->max_budget < 0);
+		entity->budget = min_t(unsigned long,
+				       bfq_bfqq_budget_left(bfqq),
+				       bfqq->max_budget);
+
+		BUG_ON(entity->budget < 0);
+		return true;
+	}
+
+	BUG_ON(bfqq->max_budget < 0);
+	entity->budget = max_t(unsigned long, bfqq->max_budget,
+			       bfq_serv_to_charge(bfqq->next_rq, bfqq));
+	BUG_ON(entity->budget < 0);
+
+	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
+	return wr_or_deserves_wr;
+}
+
+static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
+					     struct bfq_queue *bfqq,
+					     unsigned int old_wr_coeff,
+					     bool wr_or_deserves_wr,
+					     bool interactive,
+					     bool in_burst,
+					     bool soft_rt)
+{
+	if (old_wr_coeff == 1 && wr_or_deserves_wr) {
+		/* start a weight-raising period */
+		if (interactive) {
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+		} else {
+			bfqq->wr_start_at_switch_to_srt = jiffies;
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff *
+				BFQ_SOFTRT_WEIGHT_FACTOR;
+			bfqq->wr_cur_max_time =
+				bfqd->bfq_wr_rt_max_time;
+		}
+		/*
+		 * If needed, further reduce budget to make sure it is
+		 * close to bfqq's backlog, so as to reduce the
+		 * scheduling-error component due to a too large
+		 * budget. Do not care about throughput consequences,
+		 * but only about latency. Finally, do not assign a
+		 * too small budget either, to avoid increasing
+		 * latency by causing too frequent expirations.
+		 */
+		bfqq->entity.budget = min_t(unsigned long,
+					    bfqq->entity.budget,
+					    2 * bfq_min_budget(bfqd));
+
+		bfq_log_bfqq(bfqd, bfqq,
+			     "wrais starting at %lu, rais_max_time %u",
+			     jiffies,
+			     jiffies_to_msecs(bfqq->wr_cur_max_time));
+	} else if (old_wr_coeff > 1) {
+		if (interactive) { /* update wr coeff and duration */
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+		} else if (in_burst) {
+			bfqq->wr_coeff = 1;
+			bfq_log_bfqq(bfqd, bfqq,
+				     "wrais ending at %lu, rais_max_time %u",
+				     jiffies,
+				     jiffies_to_msecs(bfqq->
+						      wr_cur_max_time));
+		} else if (soft_rt) {
+			/*
+			 * The application is now or still meeting the
+			 * requirements for being deemed soft rt.  We
+			 * can then correctly and safely (re)charge
+			 * the weight-raising duration for the
+			 * application with the weight-raising
+			 * duration for soft rt applications.
+			 *
+			 * In particular, doing this recharge now, i.e.,
+			 * before the weight-raising period for the
+			 * application finishes, reduces the probability
+			 * of the following negative scenario:
+			 * 1) the weight of a soft rt application is
+			 *    raised at startup (as for any newly
+			 *    created application),
+			 * 2) since the application is not interactive,
+			 *    at a certain time weight-raising is
+			 *    stopped for the application,
+			 * 3) at that time the application happens to
+			 *    still have pending requests, and hence
+			 *    is destined to not have a chance to be
+			 *    deemed soft rt before these requests are
+			 *    completed (see the comments to the
+			 *    function bfq_bfqq_softrt_next_start()
+			 *    for details on soft rt detection),
+			 * 4) these pending requests experience a high
+			 *    latency because the application is not
+			 *    weight-raised while they are pending.
+			 */
+			if (bfqq->wr_cur_max_time !=
+				bfqd->bfq_wr_rt_max_time) {
+				bfqq->wr_start_at_switch_to_srt =
+					bfqq->last_wr_start_finish;
+                BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish));
+
+				bfqq->wr_cur_max_time =
+					bfqd->bfq_wr_rt_max_time;
+				bfqq->wr_coeff = bfqd->bfq_wr_coeff *
+					BFQ_SOFTRT_WEIGHT_FACTOR;
+				bfq_log_bfqq(bfqd, bfqq,
+					     "switching to soft_rt wr");
+			} else
+				bfq_log_bfqq(bfqd, bfqq,
+					"moving forward soft_rt wr duration");
+			bfqq->last_wr_start_finish = jiffies;
+		}
+	}
+}
+
+static bool bfq_bfqq_idle_for_long_time(struct bfq_data *bfqd,
+					struct bfq_queue *bfqq)
+{
+	return bfqq->dispatched == 0 &&
+		time_is_before_jiffies(
+			bfqq->budget_timeout +
+			bfqd->bfq_wr_min_idle_time);
+}
+
+static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
+					     struct bfq_queue *bfqq,
+					     int old_wr_coeff,
+					     struct request *rq,
+					     bool *interactive)
+{
+	bool soft_rt, in_burst,	wr_or_deserves_wr,
+		bfqq_wants_to_preempt,
+		idle_for_long_time = bfq_bfqq_idle_for_long_time(bfqd, bfqq),
+		/*
+		 * 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() <=
+			RQ_BIC(rq)->ttime.last_end_request +
+			bfqd->bfq_slice_idle * 3;
+
+	bfq_log_bfqq(bfqd, bfqq,
+		     "bfq_add_request non-busy: "
+		     "jiffies %lu, in_time %d, idle_long %d busyw %d "
+		     "wr_coeff %u",
+		     jiffies, arrived_in_time,
+		     idle_for_long_time,
+		     bfq_bfqq_non_blocking_wait_rq(bfqq),
+		     old_wr_coeff);
+
+	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
+
+	BUG_ON(bfqq == bfqd->in_service_queue);
+	bfqg_stats_update_io_add(bfqq_group(RQ_BFQQ(rq)), bfqq, rq->cmd_flags);
+
+	/*
+	 * bfqq deserves to be weight-raised if:
+	 * - it is sync,
+	 * - it does not belong to a large burst,
+	 * - it has been idle for enough time or is soft real-time,
+	 * - is linked to a bfq_io_cq (it is not shared in any sense)
+	 */
+	in_burst = bfq_bfqq_in_large_burst(bfqq);
+	soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
+		!in_burst &&
+		time_is_before_jiffies(bfqq->soft_rt_next_start);
+	*interactive =
+		!in_burst &&
+		idle_for_long_time;
+	wr_or_deserves_wr = bfqd->low_latency &&
+		(bfqq->wr_coeff > 1 ||
+		 (bfq_bfqq_sync(bfqq) &&
+		  bfqq->bic && (*interactive || soft_rt)));
+
+	bfq_log_bfqq(bfqd, bfqq,
+		     "bfq_add_request: "
+		     "in_burst %d, "
+		     "soft_rt %d (next %lu), inter %d, bic %p",
+		     bfq_bfqq_in_large_burst(bfqq), soft_rt,
+		     bfqq->soft_rt_next_start,
+		     *interactive,
+		     bfqq->bic);
+
+	/*
+	 * Using the last flag, 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,
+						    wr_or_deserves_wr);
+
+	/*
+	 * If bfqq happened to be activated in a burst, but has been
+	 * idle for much more than an interactive queue, then we
+	 * assume that, in the overall I/O initiated in the burst, the
+	 * I/O associated with bfqq is finished. So bfqq does not need
+	 * to be treated as a queue belonging to a burst
+	 * anymore. Accordingly, we reset bfqq's in_large_burst flag
+	 * if set, and remove bfqq from the burst list if it's
+	 * there. We do not decrement burst_size, because the fact
+	 * that bfqq does not need to belong to the burst list any
+	 * more does not invalidate the fact that bfqq was created in
+	 * a burst.
+	 */
+	if (likely(!bfq_bfqq_just_created(bfqq)) &&
+	    idle_for_long_time &&
+	    time_is_before_jiffies(
+		    bfqq->budget_timeout +
+		    msecs_to_jiffies(10000))) {
+		hlist_del_init(&bfqq->burst_list_node);
+		bfq_clear_bfqq_in_large_burst(bfqq);
+	}
+
+	bfq_clear_bfqq_just_created(bfqq);
+
+	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_log_bfqq(bfqd, bfqq, "requests in time %d",
+			     bfqq->requests_within_timer);
+	}
+
+	if (bfqd->low_latency) {
+		if (unlikely(time_is_after_jiffies(bfqq->split_time)))
+			/* wraparound */
+			bfqq->split_time =
+				jiffies - bfqd->bfq_wr_min_idle_time - 1;
+
+		if (time_is_before_jiffies(bfqq->split_time +
+					   bfqd->bfq_wr_min_idle_time)) {
+			bfq_update_bfqq_wr_on_rq_arrival(bfqd, bfqq,
+							 old_wr_coeff,
+							 wr_or_deserves_wr,
+							 *interactive,
+							 in_burst,
+							 soft_rt);
+
+			if (old_wr_coeff != bfqq->wr_coeff)
+				bfqq->entity.prio_changed = 1;
+		}
+	}
+
+	bfqq->last_idle_bklogged = jiffies;
+	bfqq->service_from_backlogged = 0;
+	bfq_clear_bfqq_softrt_update(bfqq);
+
+	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 &&
+	    bfqd->in_service_queue->wr_coeff < bfqq->wr_coeff &&
+	    next_queue_may_preempt(bfqd)) {
+		struct bfq_queue *in_serv =
+			bfqd->in_service_queue;
+		BUG_ON(in_serv == bfqq);
+
+		bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
+				false, BFQ_BFQQ_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;
+	unsigned int old_wr_coeff = bfqq->wr_coeff;
+	bool interactive = false;
+
+	bfq_log_bfqq(bfqd, bfqq, "add_request: size %u %s",
+		     blk_rq_sectors(rq), rq_is_sync(rq) ? "S" : "A");
+
+	if (bfqq->wr_coeff > 1) /* queue is being weight-raised */
+		bfq_log_bfqq(bfqd, bfqq,
+			"raising period dur %u/%u msec, old coeff %u, w %d(%d)",
+			jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish),
+			jiffies_to_msecs(bfqq->wr_cur_max_time),
+			bfqq->wr_coeff,
+			bfqq->entity.weight, bfqq->entity.orig_weight);
+
+	bfqq->queued[rq_is_sync(rq)]++;
+	bfqd->queued++;
+
+	elv_rb_add(&bfqq->sort_list, rq);
+
+	/*
+	 * Check if this request is a better next-to-serve candidate.
+	 */
+	prev = bfqq->next_rq;
+	next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position);
+	BUG_ON(!next_rq);
+	bfqq->next_rq = next_rq;
+
+	/*
+	 * Adjust priority tree position, if next_rq changes.
+	 */
+	if (prev != bfqq->next_rq)
+		bfq_pos_tree_add_move(bfqd, bfqq);
+
+	if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */
+		bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, old_wr_coeff,
+						 rq, &interactive);
+	else {
+		if (bfqd->low_latency && old_wr_coeff == 1 && !rq_is_sync(rq) &&
+		    time_is_before_jiffies(
+				bfqq->last_wr_start_finish +
+				bfqd->bfq_wr_min_inter_arr_async)) {
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+
+			bfqd->wr_busy_queues++;
+			BUG_ON(bfqd->wr_busy_queues > bfqd->busy_queues);
+			bfqq->entity.prio_changed = 1;
+			bfq_log_bfqq(bfqd, bfqq,
+				     "non-idle wrais starting, "
+				     "wr_max_time %u wr_busy %d",
+				     jiffies_to_msecs(bfqq->wr_cur_max_time),
+				     bfqd->wr_busy_queues);
+		}
+		if (prev != bfqq->next_rq)
+			bfq_updated_next_req(bfqd, bfqq);
+	}
+
+	/*
+	 * Assign jiffies to last_wr_start_finish in the following
+	 * cases:
+	 *
+	 * . if bfqq is not going to be weight-raised, because, for
+	 *   non weight-raised queues, last_wr_start_finish stores the
+	 *   arrival time of the last request; as of now, this piece
+	 *   of information is used only for deciding whether to
+	 *   weight-raise async queues
+	 *
+	 * . if bfqq is not weight-raised, because, if bfqq is now
+	 *   switching to weight-raised, then last_wr_start_finish
+	 *   stores the time when weight-raising starts
+	 *
+	 * . if bfqq is interactive, because, regardless of whether
+	 *   bfqq is currently weight-raised, the weight-raising
+	 *   period must start or restart (this case is considered
+	 *   separately because it is not detected by the above
+	 *   conditions, if bfqq is already weight-raised)
+	 *
+	 * last_wr_start_finish has to be updated also if bfqq is soft
+	 * real-time, because the weight-raising period is constantly
+	 * restarted on idle-to-busy transitions for these queues, but
+	 * this is already done in bfq_bfqq_handle_idle_busy_switch if
+	 * needed.
+	 */
+	if (bfqd->low_latency &&
+		(old_wr_coeff == 1 || bfqq->wr_coeff == 1 || interactive))
+		bfqq->last_wr_start_finish = jiffies;
+}
+
+static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
+					  struct bio *bio)
+{
+	struct task_struct *tsk = current;
+	struct bfq_io_cq *bic;
+	struct bfq_queue *bfqq;
+
+	bic = bfq_bic_lookup(bfqd, tsk->io_context);
+	if (!bic)
+		return NULL;
+
+	bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf));
+	if (bfqq)
+		return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio));
+
+	return NULL;
+}
+
+static sector_t get_sdist(sector_t last_pos, struct request *rq)
+{
+	sector_t sdist = 0;
+
+	if (last_pos) {
+		if (last_pos < blk_rq_pos(rq))
+			sdist = blk_rq_pos(rq) - last_pos;
+		else
+			sdist = last_pos - blk_rq_pos(rq);
+	}
+
+	return sdist;
+}
+
+static void bfq_activate_request(struct request_queue *q, struct request *rq)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	bfqd->rq_in_driver++;
+}
+
+static void bfq_deactivate_request(struct request_queue *q, struct request *rq)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+
+	BUG_ON(bfqd->rq_in_driver == 0);
+	bfqd->rq_in_driver--;
+}
+
+static void bfq_remove_request(struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_data *bfqd = bfqq->bfqd;
+	const int sync = rq_is_sync(rq);
+
+	BUG_ON(bfqq->entity.service > bfqq->entity.budget &&
+	       bfqq == bfqd->in_service_queue);
+
+	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);
+	BUG_ON(bfqq->queued[sync] == 0);
+	bfqq->queued[sync]--;
+	bfqd->queued--;
+	elv_rb_del(&bfqq->sort_list, rq);
+
+	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		bfqq->next_rq = NULL;
+
+		BUG_ON(bfqq->entity.budget < 0);
+
+		if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) {
+			BUG_ON(bfqq->ref < 2); /* referred by rq and on tree */
+			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;
+		}
+
+		/*
+		 * Remove queue from request-position tree as it is empty.
+		 */
+		if (bfqq->pos_root) {
+			rb_erase(&bfqq->pos_node, bfqq->pos_root);
+			bfqq->pos_root = NULL;
+		}
+	}
+
+	if (rq->cmd_flags & REQ_META) {
+		BUG_ON(bfqq->meta_pending == 0);
+		bfqq->meta_pending--;
+	}
+	bfqg_stats_update_io_remove(bfqq_group(bfqq), rq->cmd_flags);
+}
+
+static enum elv_merge bfq_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);
+	if (__rq && elv_bio_merge_ok(__rq, bio)) {
+		*req = __rq;
+		return ELEVATOR_FRONT_MERGE;
+	}
+
+	return ELEVATOR_NO_MERGE;
+}
+
+static void bfq_merged_request(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);
+		BUG_ON(!next_rq);
+		bfqq->next_rq = next_rq;
+		/*
+		 * If next_rq changes, update both the queue's budget to
+		 * fit the new request and the queue's position in its
+		 * rq_pos_tree.
+		 */
+		if (prev != bfqq->next_rq) {
+			bfq_updated_next_req(bfqd, bfqq);
+			bfq_pos_tree_add_move(bfqd, bfqq);
+		}
+	}
+}
+
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+static void bfq_bio_merged(struct request_queue *q, struct request *req,
+			   struct bio *bio)
+{
+	bfqg_stats_update_io_merged(bfqq_group(RQ_BFQQ(req)), bio->bi_opf);
+}
+#endif
+
+static void bfq_merged_requests(struct request_queue *q, struct request *rq,
+				struct request *next)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next);
+
+	/*
+	 * 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(next);
+	bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
+}
+
+/* Must be called with bfqq != NULL */
+static void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
+{
+	BUG_ON(!bfqq);
+
+	if (bfq_bfqq_busy(bfqq)) {
+		bfqq->bfqd->wr_busy_queues--;
+		BUG_ON(bfqq->bfqd->wr_busy_queues < 0);
+	}
+	bfqq->wr_coeff = 1;
+	bfqq->wr_cur_max_time = 0;
+	bfqq->last_wr_start_finish = jiffies;
+	/*
+	 * Trigger a weight change on the next invocation of
+	 * __bfq_entity_update_weight_prio.
+	 */
+	bfqq->entity.prio_changed = 1;
+	bfq_log_bfqq(bfqq->bfqd, bfqq,
+		     "end_wr: wrais ending at %lu, rais_max_time %u",
+		     bfqq->last_wr_start_finish,
+		     jiffies_to_msecs(bfqq->wr_cur_max_time));
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "end_wr: wr_busy %d",
+		     bfqq->bfqd->wr_busy_queues);
+}
+
+static void bfq_end_wr_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++)
+			if (bfqg->async_bfqq[i][j])
+				bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]);
+	if (bfqg->async_idle_bfqq)
+		bfq_bfqq_end_wr(bfqg->async_idle_bfqq);
+}
+
+static void bfq_end_wr(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq;
+
+	spin_lock_irq(bfqd->queue->queue_lock);
+
+	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
+		bfq_bfqq_end_wr(bfqq);
+	list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list)
+		bfq_bfqq_end_wr(bfqq);
+	bfq_end_wr_async(bfqd);
+
+	spin_unlock_irq(bfqd->queue->queue_lock);
+}
+
+static sector_t bfq_io_struct_pos(void *io_struct, bool request)
+{
+	if (request)
+		return blk_rq_pos(io_struct);
+	else
+		return ((struct bio *)io_struct)->bi_iter.bi_sector;
+}
+
+static int bfq_rq_close_to_sector(void *io_struct, bool request,
+				  sector_t sector)
+{
+	return abs(bfq_io_struct_pos(io_struct, request) - sector) <=
+	       BFQQ_CLOSE_THR;
+}
+
+static struct bfq_queue *bfqq_find_close(struct bfq_data *bfqd,
+					 struct bfq_queue *bfqq,
+					 sector_t sector)
+{
+	struct rb_root *root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
+	struct rb_node *parent, *node;
+	struct bfq_queue *__bfqq;
+
+	if (RB_EMPTY_ROOT(root))
+		return NULL;
+
+	/*
+	 * First, if we find a request starting at the end of the last
+	 * request, choose it.
+	 */
+	__bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL);
+	if (__bfqq)
+		return __bfqq;
+
+	/*
+	 * If the exact sector wasn't found, the parent of the NULL leaf
+	 * will contain the closest sector (rq_pos_tree sorted by
+	 * next_request position).
+	 */
+	__bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+	if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+		return __bfqq;
+
+	if (blk_rq_pos(__bfqq->next_rq) < sector)
+		node = rb_next(&__bfqq->pos_node);
+	else
+		node = rb_prev(&__bfqq->pos_node);
+	if (!node)
+		return NULL;
+
+	__bfqq = rb_entry(node, struct bfq_queue, pos_node);
+	if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+		return __bfqq;
+
+	return NULL;
+}
+
+static struct bfq_queue *bfq_find_close_cooperator(struct bfq_data *bfqd,
+						   struct bfq_queue *cur_bfqq,
+						   sector_t sector)
+{
+	struct bfq_queue *bfqq;
+
+	/*
+	 * We shall notice if some of the queues are cooperating,
+	 * e.g., working closely on the same area of the device. In
+	 * that case, we can group them together and: 1) don't waste
+	 * time idling, and 2) serve the union of their requests in
+	 * the best possible order for throughput.
+	 */
+	bfqq = bfqq_find_close(bfqd, cur_bfqq, sector);
+	if (!bfqq || bfqq == cur_bfqq)
+		return NULL;
+
+	return bfqq;
+}
+
+static struct bfq_queue *
+bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+{
+	int process_refs, new_process_refs;
+	struct bfq_queue *__bfqq;
+
+	/*
+	 * If there are no process references on the new_bfqq, then it is
+	 * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
+	 * may have dropped their last reference (not just their last process
+	 * reference).
+	 */
+	if (!bfqq_process_refs(new_bfqq))
+		return NULL;
+
+	/* Avoid a circular list and skip interim queue merges. */
+	while ((__bfqq = new_bfqq->new_bfqq)) {
+		if (__bfqq == bfqq)
+			return NULL;
+		new_bfqq = __bfqq;
+	}
+
+	process_refs = bfqq_process_refs(bfqq);
+	new_process_refs = bfqq_process_refs(new_bfqq);
+	/*
+	 * If the process for the bfqq has gone away, there is no
+	 * sense in merging the queues.
+	 */
+	if (process_refs == 0 || new_process_refs == 0)
+		return NULL;
+
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
+		new_bfqq->pid);
+
+	/*
+	 * Merging is just a redirection: the requests of the process
+	 * owning one of the two queues are redirected to the other queue.
+	 * The latter queue, in its turn, is set as shared if this is the
+	 * first time that the requests of some process are redirected to
+	 * it.
+	 *
+	 * We redirect bfqq to new_bfqq and not the opposite, because we
+	 * are in the context of the process owning bfqq, hence we have
+	 * the io_cq of this process. So we can immediately configure this
+	 * io_cq to redirect the requests of the process to new_bfqq.
+	 *
+	 * NOTE, even if new_bfqq coincides with the in-service queue, the
+	 * io_cq of new_bfqq is not available, because, if the in-service
+	 * queue is shared, bfqd->in_service_bic may not point to the
+	 * io_cq of the in-service queue.
+	 * Redirecting the requests of the process owning bfqq to the
+	 * currently in-service queue is in any case the best option, as
+	 * we feed the in-service queue with new requests close to the
+	 * last request served and, by doing so, hopefully increase the
+	 * throughput.
+	 */
+	bfqq->new_bfqq = new_bfqq;
+	new_bfqq->ref += process_refs;
+	return new_bfqq;
+}
+
+static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq,
+					struct bfq_queue *new_bfqq)
+{
+	if (bfq_class_idle(bfqq) || bfq_class_idle(new_bfqq) ||
+	    (bfqq->ioprio_class != new_bfqq->ioprio_class))
+		return false;
+
+	/*
+	 * If either of the queues has already been detected as seeky,
+	 * then merging it with the other queue is unlikely to lead to
+	 * sequential I/O.
+	 */
+	if (BFQQ_SEEKY(bfqq) || BFQQ_SEEKY(new_bfqq))
+		return false;
+
+	/*
+	 * Interleaved I/O is known to be done by (some) applications
+	 * only for reads, so it does not make sense to merge async
+	 * queues.
+	 */
+	if (!bfq_bfqq_sync(bfqq) || !bfq_bfqq_sync(new_bfqq))
+		return false;
+
+	return true;
+}
+
+/*
+ * If this function returns true, then bfqq cannot be merged. The idea
+ * is that true cooperation happens very early after processes start
+ * to do I/O. Usually, late cooperations are just accidental false
+ * positives. In case bfqq is weight-raised, such false positives
+ * would evidently degrade latency guarantees for bfqq.
+ */
+static bool wr_from_too_long(struct bfq_queue *bfqq)
+{
+	return bfqq->wr_coeff > 1 &&
+		time_is_before_jiffies(bfqq->last_wr_start_finish +
+				       msecs_to_jiffies(100));
+}
+
+/*
+ * Attempt to schedule a merge of bfqq with the currently in-service
+ * queue or with a close queue among the scheduled queues.  Return
+ * NULL if no merge was scheduled, a pointer to the shared bfq_queue
+ * structure otherwise.
+ *
+ * The OOM queue is not allowed to participate to cooperation: in fact, since
+ * the requests temporarily redirected to the OOM queue could be redirected
+ * again to dedicated queues at any time, the state needed to correctly
+ * handle merging with the OOM queue would be quite complex and expensive
+ * to maintain. Besides, in such a critical condition as an out of memory,
+ * the benefits of queue merging may be little relevant, or even negligible.
+ *
+ * Weight-raised queues can be merged only if their weight-raising
+ * period has just started. In fact cooperating processes are usually
+ * started together. Thus, with this filter we avoid false positives
+ * that would jeopardize low-latency guarantees.
+ *
+ * WARNING: queue merging may impair fairness among non-weight raised
+ * queues, for at least two reasons: 1) the original weight of a
+ * merged queue may change during the merged state, 2) even being the
+ * weight the same, a merged queue may be bloated with many more
+ * requests than the ones produced by its originally-associated
+ * process.
+ */
+static struct bfq_queue *
+bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		     void *io_struct, bool request)
+{
+	struct bfq_queue *in_service_bfqq, *new_bfqq;
+
+	if (bfqq->new_bfqq)
+		return bfqq->new_bfqq;
+
+	if (io_struct && wr_from_too_long(bfqq) &&
+	    likely(bfqq != &bfqd->oom_bfqq))
+		bfq_log_bfqq(bfqd, bfqq,
+			     "would have looked for coop, but bfq%d wr",
+			bfqq->pid);
+
+	if (!io_struct ||
+	    wr_from_too_long(bfqq) ||
+	    unlikely(bfqq == &bfqd->oom_bfqq))
+		return NULL;
+
+	/* If there is only one backlogged queue, don't search. */
+	if (bfqd->busy_queues == 1)
+		return NULL;
+
+	in_service_bfqq = bfqd->in_service_queue;
+
+	if (in_service_bfqq && in_service_bfqq != bfqq &&
+	    bfqd->in_service_bic && wr_from_too_long(in_service_bfqq)
+	    && likely(in_service_bfqq == &bfqd->oom_bfqq))
+		bfq_log_bfqq(bfqd, bfqq,
+		"would have tried merge with in-service-queue, but wr");
+
+	if (!in_service_bfqq || in_service_bfqq == bfqq ||
+	    !bfqd->in_service_bic || wr_from_too_long(in_service_bfqq) ||
+	    unlikely(in_service_bfqq == &bfqd->oom_bfqq))
+		goto check_scheduled;
+
+	if (bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) &&
+	    bfqq->entity.parent == in_service_bfqq->entity.parent &&
+	    bfq_may_be_close_cooperator(bfqq, in_service_bfqq)) {
+		new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq);
+		if (new_bfqq)
+			return new_bfqq;
+	}
+	/*
+	 * Check whether there is a cooperator among currently scheduled
+	 * queues. The only thing we need is that the bio/request is not
+	 * NULL, as we need it to establish whether a cooperator exists.
+	 */
+check_scheduled:
+	new_bfqq = bfq_find_close_cooperator(bfqd, bfqq,
+			bfq_io_struct_pos(io_struct, request));
+
+	BUG_ON(new_bfqq && bfqq->entity.parent != new_bfqq->entity.parent);
+
+	if (new_bfqq && wr_from_too_long(new_bfqq) &&
+	    likely(new_bfqq != &bfqd->oom_bfqq) &&
+	    bfq_may_be_close_cooperator(bfqq, new_bfqq))
+		bfq_log_bfqq(bfqd, bfqq,
+			     "would have merged with bfq%d, but wr",
+			     new_bfqq->pid);
+
+	if (new_bfqq && !wr_from_too_long(new_bfqq) &&
+	    likely(new_bfqq != &bfqd->oom_bfqq) &&
+	    bfq_may_be_close_cooperator(bfqq, new_bfqq))
+		return bfq_setup_merge(bfqq, new_bfqq);
+
+	return NULL;
+}
+
+static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
+{
+	struct bfq_io_cq *bic = bfqq->bic;
+
+	/*
+	 * If !bfqq->bic, the queue is already shared or its requests
+	 * have already been redirected to a shared queue; both idle window
+	 * and weight raising state have already been saved. Do nothing.
+	 */
+	if (!bic)
+		return;
+
+	bic->saved_idle_window = bfq_bfqq_idle_window(bfqq);
+	bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
+	bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
+	bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
+	bic->saved_wr_coeff = bfqq->wr_coeff;
+	bic->saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt;
+	bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
+	bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
+	BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish));
+}
+
+static void bfq_get_bic_reference(struct bfq_queue *bfqq)
+{
+	/*
+	 * If bfqq->bic has a non-NULL value, the bic to which it belongs
+	 * is about to begin using a shared bfq_queue.
+	 */
+	if (bfqq->bic)
+		atomic_long_inc(&bfqq->bic->icq.ioc->refcount);
+}
+
+static void
+bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
+		struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+{
+	bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
+		     (unsigned long) new_bfqq->pid);
+	/* Save weight raising and idle window of the merged queues */
+	bfq_bfqq_save_state(bfqq);
+	bfq_bfqq_save_state(new_bfqq);
+	if (bfq_bfqq_IO_bound(bfqq))
+		bfq_mark_bfqq_IO_bound(new_bfqq);
+	bfq_clear_bfqq_IO_bound(bfqq);
+
+	/*
+	 * If bfqq is weight-raised, then let new_bfqq inherit
+	 * weight-raising. To reduce false positives, neglect the case
+	 * where bfqq has just been created, but has not yet made it
+	 * to be weight-raised (which may happen because EQM may merge
+	 * bfqq even before bfq_add_request is executed for the first
+	 * time for bfqq). Handling this case would however be very
+	 * easy, thanks to the flag just_created.
+	 */
+	if (new_bfqq->wr_coeff == 1 && bfqq->wr_coeff > 1) {
+		new_bfqq->wr_coeff = bfqq->wr_coeff;
+		new_bfqq->wr_cur_max_time = bfqq->wr_cur_max_time;
+		new_bfqq->last_wr_start_finish = bfqq->last_wr_start_finish;
+		new_bfqq->wr_start_at_switch_to_srt =
+			bfqq->wr_start_at_switch_to_srt;
+		if (bfq_bfqq_busy(new_bfqq)) {
+			bfqd->wr_busy_queues++;
+			BUG_ON(bfqd->wr_busy_queues > bfqd->busy_queues);
+		}
+
+		new_bfqq->entity.prio_changed = 1;
+		bfq_log_bfqq(bfqd, new_bfqq,
+			     "wr start after merge with %d, rais_max_time %u",
+			     bfqq->pid,
+			     jiffies_to_msecs(bfqq->wr_cur_max_time));
+	}
+
+	if (bfqq->wr_coeff > 1) { /* bfqq has given its wr to new_bfqq */
+		bfqq->wr_coeff = 1;
+		bfqq->entity.prio_changed = 1;
+		if (bfq_bfqq_busy(bfqq)) {
+			bfqd->wr_busy_queues--;
+			BUG_ON(bfqd->wr_busy_queues < 0);
+		}
+
+	}
+
+	bfq_log_bfqq(bfqd, new_bfqq, "merge_bfqqs: wr_busy %d",
+		     bfqd->wr_busy_queues);
+
+	/*
+	 * Grab a reference to the bic, to prevent it from being destroyed
+	 * before being possibly touched by a bfq_split_bfqq().
+	 */
+	bfq_get_bic_reference(bfqq);
+	bfq_get_bic_reference(new_bfqq);
+	/*
+	 * Merge queues (that is, let bic redirect its requests to new_bfqq)
+	 */
+	bic_set_bfqq(bic, new_bfqq, 1);
+	bfq_mark_bfqq_coop(new_bfqq);
+	/*
+	 * new_bfqq now belongs to at least two bics (it is a shared queue):
+	 * set new_bfqq->bic to NULL. bfqq either:
+	 * - does not belong to any bic any more, and hence bfqq->bic must
+	 *   be set to NULL, or
+	 * - is a queue whose owning bics have already been redirected to a
+	 *   different queue, hence the queue is destined to not belong to
+	 *   any bic soon and bfqq->bic is already NULL (therefore the next
+	 *   assignment causes no harm).
+	 */
+	new_bfqq->bic = NULL;
+	bfqq->bic = NULL;
+	/* release process reference to bfqq */
+	bfq_put_queue(bfqq);
+}
+
+static int 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_io_cq *bic;
+	struct bfq_queue *bfqq, *new_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.
+	 * Queue lock is held here.
+	 */
+	bic = bfq_bic_lookup(bfqd, current->io_context);
+	if (!bic)
+		return false;
+
+	bfqq = bic_to_bfqq(bic, is_sync);
+	/*
+	 * We take advantage of this function to perform an early merge
+	 * of the queues of possible cooperating processes.
+	 */
+	if (bfqq) {
+		new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
+		if (new_bfqq) {
+			bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq);
+			/*
+			 * If we get here, the bio will be queued in the
+			 * shared queue, i.e., new_bfqq, so use new_bfqq
+			 * to decide whether bio and rq can be merged.
+			 */
+			bfqq = new_bfqq;
+		}
+	}
+
+	return bfqq == RQ_BFQQ(rq);
+}
+
+static int bfq_allow_rq_merge(struct request_queue *q, struct request *rq,
+			      struct request *next)
+{
+	return RQ_BFQQ(rq) == RQ_BFQQ(next);
+}
+
+/*
+ * Set the maximum time for the in-service queue to consume its
+ * budget. This prevents seeky processes from lowering the throughput.
+ * In practice, a time-slice service scheme is used with seeky
+ * processes.
+ */
+static void bfq_set_budget_timeout(struct bfq_data *bfqd,
+				   struct bfq_queue *bfqq)
+{
+	unsigned int timeout_coeff;
+
+	if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time)
+		timeout_coeff = 1;
+	else
+		timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight;
+
+	bfqd->last_budget_start = ktime_get();
+
+	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));
+}
+
+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_must_alloc(bfqq);
+		bfq_clear_bfqq_fifo_expire(bfqq);
+
+		bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8;
+
+		BUG_ON(bfqq == bfqd->in_service_queue);
+		BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list));
+
+		if (time_is_before_jiffies(bfqq->last_wr_start_finish) &&
+		    bfqq->wr_coeff > 1 &&
+		    bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
+		    time_is_before_jiffies(bfqq->budget_timeout)) {
+			/*
+			 * For soft real-time queues, move the start
+			 * of the weight-raising period forward by the
+			 * time the queue has not received any
+			 * service. Otherwise, a relatively long
+			 * service delay is likely to cause the
+			 * weight-raising period of the queue to end,
+			 * because of the short duration of the
+			 * weight-raising period of a soft real-time
+			 * queue.  It is worth noting that this move
+			 * is not so dangerous for the other queues,
+			 * because soft real-time queues are not
+			 * greedy.
+			 *
+			 * To not add a further variable, we use the
+			 * overloaded field budget_timeout to
+			 * determine for how long the queue has not
+			 * received service, i.e., how much time has
+			 * elapsed since the queue expired. However,
+			 * this is a little imprecise, because
+			 * budget_timeout is set to jiffies if bfqq
+			 * not only expires, but also remains with no
+			 * request.
+			 */
+			if (time_after(bfqq->budget_timeout,
+				       bfqq->last_wr_start_finish))
+				bfqq->last_wr_start_finish +=
+					jiffies - bfqq->budget_timeout;
+			else
+				bfqq->last_wr_start_finish = jiffies;
+
+			if (time_is_after_jiffies(bfqq->last_wr_start_finish)) {
+			       pr_crit(
+			       "BFQ WARNING:last %lu budget %lu jiffies %lu",
+			       bfqq->last_wr_start_finish,
+			       bfqq->budget_timeout,
+			       jiffies);
+			       pr_crit("diff %lu", jiffies -
+				       max_t(unsigned long,
+					     bfqq->last_wr_start_finish,
+					     bfqq->budget_timeout));
+			       bfqq->last_wr_start_finish = jiffies;
+			}
+		}
+
+		bfq_set_budget_timeout(bfqd, bfqq);
+		bfq_log_bfqq(bfqd, bfqq,
+			     "set_in_service_queue, cur-budget = %d",
+			     bfqq->entity.budget);
+	} else
+		bfq_log(bfqd, "set_in_service_queue: NULL");
+
+	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;
+
+	BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
+
+	/* 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.
+	 *
+	 * To prevent processes with (partly) seeky workloads from
+	 * being too ill-treated, grant them a small fraction of the
+	 * assigned budget before reducing the waiting time to
+	 * BFQ_MIN_TT. This happened to help reduce latency.
+	 */
+	sl = bfqd->bfq_slice_idle;
+	/*
+	 * Unless the queue is being weight-raised or the scenario is
+	 * asymmetric, grant only minimum idle time if the queue
+	 * is seeky. A long idling is preserved for a weight-raised
+	 * queue, or, more in general, in an asymemtric scenario,
+	 * because a long idling is needed for guaranteeing to a queue
+	 * its reserved share of the throughput (in particular, it is
+	 * needed if the queue has a higher weight than some other
+	 * queue).
+	 */
+	if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
+	    bfq_symmetric_scenario(bfqd))
+		sl = min_t(u32, 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));
+	bfq_log(bfqd, "arm idle: %ld/%ld ms",
+		sl / NSEC_PER_MSEC, bfqd->bfq_slice_idle / NSEC_PER_MSEC);
+}
+
+/*
+ * In autotuning mode, max_budget is dynamically recomputed as the
+ * amount of sectors transferred in timeout at the estimated peak
+ * rate. This enables BFQ to utilize a full timeslice with a full
+ * budget, even if the in-service queue is served at peak rate. And
+ * this maximises throughput with sequential workloads.
+ */
+static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd)
+{
+	return (u64)bfqd->peak_rate * USEC_PER_MSEC *
+		jiffies_to_msecs(bfqd->bfq_timeout)>>BFQ_RATE_SHIFT;
+}
+
+/*
+ * Update parameters related to throughput and responsiveness, as a
+ * function of the estimated peak rate. See comments on
+ * bfq_calc_max_budget(), and on T_slow and T_fast arrays.
+ */
+static void update_thr_responsiveness_params(struct bfq_data *bfqd)
+{
+	int dev_type = blk_queue_nonrot(bfqd->queue);
+
+	if (bfqd->bfq_user_max_budget == 0) {
+		bfqd->bfq_max_budget =
+			bfq_calc_max_budget(bfqd);
+		BUG_ON(bfqd->bfq_max_budget < 0);
+		bfq_log(bfqd, "new max_budget = %d",
+			bfqd->bfq_max_budget);
+	}
+
+	if (bfqd->device_speed == BFQ_BFQD_FAST &&
+	    bfqd->peak_rate < device_speed_thresh[dev_type]) {
+		bfqd->device_speed = BFQ_BFQD_SLOW;
+		bfqd->RT_prod = R_slow[dev_type] *
+			T_slow[dev_type];
+	} else if (bfqd->device_speed == BFQ_BFQD_SLOW &&
+		   bfqd->peak_rate > device_speed_thresh[dev_type]) {
+		bfqd->device_speed = BFQ_BFQD_FAST;
+		bfqd->RT_prod = R_fast[dev_type] *
+			T_fast[dev_type];
+	}
+
+	bfq_log(bfqd,
+"dev_type %s dev_speed_class = %s (%llu sects/sec), thresh %llu setcs/sec",
+		dev_type == 0 ? "ROT" : "NONROT",
+		bfqd->device_speed == BFQ_BFQD_FAST ? "FAST" : "SLOW",
+		bfqd->device_speed == BFQ_BFQD_FAST ?
+		(USEC_PER_SEC*(u64)R_fast[dev_type])>>BFQ_RATE_SHIFT :
+		(USEC_PER_SEC*(u64)R_slow[dev_type])>>BFQ_RATE_SHIFT,
+		(USEC_PER_SEC*(u64)device_speed_thresh[dev_type])>>
+		BFQ_RATE_SHIFT);
+}
+
+static void bfq_reset_rate_computation(struct bfq_data *bfqd, struct request *rq)
+{
+	if (rq != NULL) { /* new rq dispatch now, reset accordingly */
+		bfqd->last_dispatch = bfqd->first_dispatch = ktime_get_ns() ;
+		bfqd->peak_rate_samples = 1;
+		bfqd->sequential_samples = 0;
+		bfqd->tot_sectors_dispatched = bfqd->last_rq_max_size =
+			blk_rq_sectors(rq);
+	} else /* no new rq dispatched, just reset the number of samples */
+		bfqd->peak_rate_samples = 0; /* full re-init on next disp. */
+
+	bfq_log(bfqd,
+		"reset_rate_computation at end, sample %u/%u tot_sects %llu",
+		bfqd->peak_rate_samples, bfqd->sequential_samples,
+		bfqd->tot_sectors_dispatched);
+}
+
+static void bfq_update_rate_reset(struct bfq_data *bfqd, struct request *rq)
+{
+	u32 rate, weight, divisor;
+
+	/*
+	 * For the convergence property to hold (see comments on
+	 * bfq_update_peak_rate()) and for the assessment to be
+	 * reliable, a minimum number of samples must be present, and
+	 * a minimum amount of time must have elapsed. If not so, do
+	 * not compute new rate. Just reset parameters, to get ready
+	 * for a new evaluation attempt.
+	 */
+	if (bfqd->peak_rate_samples < BFQ_RATE_MIN_SAMPLES ||
+	    bfqd->delta_from_first < BFQ_RATE_MIN_INTERVAL) {
+		bfq_log(bfqd,
+	"update_rate_reset: only resetting, delta_first %lluus samples %d",
+			bfqd->delta_from_first>>10, bfqd->peak_rate_samples);
+		goto reset_computation;
+	}
+
+	/*
+	 * If a new request completion has occurred after last
+	 * dispatch, then, to approximate the rate at which requests
+	 * have been served by the device, it is more precise to
+	 * extend the observation interval to the last completion.
+	 */
+	bfqd->delta_from_first =
+		max_t(u64, bfqd->delta_from_first,
+		      bfqd->last_completion - bfqd->first_dispatch);
+
+	BUG_ON(bfqd->delta_from_first == 0);
+	/*
+	 * Rate computed in sects/usec, and not sects/nsec, for
+	 * precision issues.
+	 */
+	rate = div64_ul(bfqd->tot_sectors_dispatched<<BFQ_RATE_SHIFT,
+			div_u64(bfqd->delta_from_first, NSEC_PER_USEC));
+
+	bfq_log(bfqd,
+"update_rate_reset: tot_sects %llu delta_first %lluus rate %llu sects/s (%d)",
+		bfqd->tot_sectors_dispatched, bfqd->delta_from_first>>10,
+		((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT),
+		rate > 20<<BFQ_RATE_SHIFT);
+
+	/*
+	 * Peak rate not updated if:
+	 * - the percentage of sequential dispatches is below 3/4 of the
+	 *   total, and rate is below the current estimated peak rate
+	 * - rate is unreasonably high (> 20M sectors/sec)
+	 */
+	if ((bfqd->sequential_samples < (3 * bfqd->peak_rate_samples)>>2 &&
+	     rate <= bfqd->peak_rate) ||
+		rate > 20<<BFQ_RATE_SHIFT) {
+		bfq_log(bfqd,
+		"update_rate_reset: goto reset, samples %u/%u rate/peak %llu/%llu",
+		bfqd->peak_rate_samples, bfqd->sequential_samples,
+		((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT),
+		((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT));
+		goto reset_computation;
+	} else {
+		bfq_log(bfqd,
+		"update_rate_reset: do update, samples %u/%u rate/peak %llu/%llu",
+		bfqd->peak_rate_samples, bfqd->sequential_samples,
+		((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT),
+		((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT));
+	}
+
+	/*
+	 * We have to update the peak rate, at last! To this purpose,
+	 * we use a low-pass filter. We compute the smoothing constant
+	 * of the filter as a function of the 'weight' of the new
+	 * measured rate.
+	 *
+	 * As can be seen in next formulas, we define this weight as a
+	 * quantity proportional to how sequential the workload is,
+	 * and to how long the observation time interval is.
+	 *
+	 * The weight runs from 0 to 8. The maximum value of the
+	 * weight, 8, yields the minimum value for the smoothing
+	 * constant. At this minimum value for the smoothing constant,
+	 * the measured rate contributes for half of the next value of
+	 * the estimated peak rate.
+	 *
+	 * So, the first step is to compute the weight as a function
+	 * of how sequential the workload is. Note that the weight
+	 * cannot reach 9, because bfqd->sequential_samples cannot
+	 * become equal to bfqd->peak_rate_samples, which, in its
+	 * turn, holds true because bfqd->sequential_samples is not
+	 * incremented for the first sample.
+	 */
+	weight = (9 * bfqd->sequential_samples) / bfqd->peak_rate_samples;
+
+	/*
+	 * Second step: further refine the weight as a function of the
+	 * duration of the observation interval.
+	 */
+	weight = min_t(u32, 8,
+		       div_u64(weight * bfqd->delta_from_first,
+			       BFQ_RATE_REF_INTERVAL));
+
+	/*
+	 * Divisor ranging from 10, for minimum weight, to 2, for
+	 * maximum weight.
+	 */
+	divisor = 10 - weight;
+	BUG_ON(divisor == 0);
+
+	/*
+	 * Finally, update peak rate:
+	 *
+	 * peak_rate = peak_rate * (divisor-1) / divisor  +  rate / divisor
+	 */
+	bfqd->peak_rate *= divisor-1;
+	bfqd->peak_rate /= divisor;
+	rate /= divisor; /* smoothing constant alpha = 1/divisor */
+
+	bfq_log(bfqd,
+		"update_rate_reset: divisor %d tmp_peak_rate %llu tmp_rate %u",
+		divisor,
+		((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT),
+		(u32)((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT));
+
+	BUG_ON(bfqd->peak_rate == 0);
+	BUG_ON(bfqd->peak_rate > 20<<BFQ_RATE_SHIFT);
+
+	bfqd->peak_rate += rate;
+	update_thr_responsiveness_params(bfqd);
+	BUG_ON(bfqd->peak_rate > 20<<BFQ_RATE_SHIFT);
+
+reset_computation:
+	bfq_reset_rate_computation(bfqd, rq);
+}
+
+/*
+ * Update the read/write peak rate (the main quantity used for
+ * auto-tuning, see update_thr_responsiveness_params()).
+ *
+ * It is not trivial to estimate the peak rate (correctly): because of
+ * the presence of sw and hw queues between the scheduler and the
+ * device components that finally serve I/O requests, it is hard to
+ * say exactly when a given dispatched request is served inside the
+ * device, and for how long. As a consequence, it is hard to know
+ * precisely at what rate a given set of requests is actually served
+ * by the device.
+ *
+ * On the opposite end, the dispatch time of any request is trivially
+ * available, and, from this piece of information, the "dispatch rate"
+ * of requests can be immediately computed. So, the idea in the next
+ * function is to use what is known, namely request dispatch times
+ * (plus, when useful, request completion times), to estimate what is
+ * unknown, namely in-device request service rate.
+ *
+ * The main issue is that, because of the above facts, the rate at
+ * which a certain set of requests is dispatched over a certain time
+ * interval can vary greatly with respect to the rate at which the
+ * same requests are then served. But, since the size of any
+ * intermediate queue is limited, and the service scheme is lossless
+ * (no request is silently dropped), the following obvious convergence
+ * property holds: the number of requests dispatched MUST become
+ * closer and closer to the number of requests completed as the
+ * observation interval grows. This is the key property used in
+ * the next function to estimate the peak service rate as a function
+ * of the observed dispatch rate. The function assumes to be invoked
+ * on every request dispatch.
+ */
+static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq)
+{
+	u64 now_ns = ktime_get_ns();
+
+	if (bfqd->peak_rate_samples == 0) { /* first dispatch */
+		bfq_log(bfqd,
+		"update_peak_rate: goto reset, samples %d",
+				bfqd->peak_rate_samples) ;
+		bfq_reset_rate_computation(bfqd, rq);
+		goto update_last_values; /* will add one sample */
+	}
+
+	/*
+	 * Device idle for very long: the observation interval lasting
+	 * up to this dispatch cannot be a valid observation interval
+	 * for computing a new peak rate (similarly to the late-
+	 * completion event in bfq_completed_request()). Go to
+	 * update_rate_and_reset to have the following three steps
+	 * taken:
+	 * - close the observation interval at the last (previous)
+	 *   request dispatch or completion
+	 * - compute rate, if possible, for that observation interval
+	 * - start a new observation interval with this dispatch
+	 */
+	if (now_ns - bfqd->last_dispatch > 100*NSEC_PER_MSEC &&
+	    bfqd->rq_in_driver == 0) {
+		bfq_log(bfqd,
+"update_peak_rate: jumping to updating&resetting delta_last %lluus samples %d",
+			(now_ns - bfqd->last_dispatch)>>10,
+			bfqd->peak_rate_samples) ;
+		goto update_rate_and_reset;
+	}
+
+	/* Update sampling information */
+	bfqd->peak_rate_samples++;
+
+	if ((bfqd->rq_in_driver > 0 ||
+		now_ns - bfqd->last_completion < BFQ_MIN_TT)
+	     && get_sdist(bfqd->last_position, rq) < BFQQ_SEEK_THR)
+		bfqd->sequential_samples++;
+
+	bfqd->tot_sectors_dispatched += blk_rq_sectors(rq);
+
+	/* Reset max observed rq size every 32 dispatches */
+	if (likely(bfqd->peak_rate_samples % 32))
+		bfqd->last_rq_max_size =
+			max_t(u32, blk_rq_sectors(rq), bfqd->last_rq_max_size);
+	else
+		bfqd->last_rq_max_size = blk_rq_sectors(rq);
+
+	bfqd->delta_from_first = now_ns - bfqd->first_dispatch;
+
+	bfq_log(bfqd,
+	"update_peak_rate: added samples %u/%u tot_sects %llu delta_first %lluus",
+		bfqd->peak_rate_samples, bfqd->sequential_samples,
+		bfqd->tot_sectors_dispatched,
+		bfqd->delta_from_first>>10);
+
+	/* Target observation interval not yet reached, go on sampling */
+	if (bfqd->delta_from_first < BFQ_RATE_REF_INTERVAL)
+		goto update_last_values;
+
+update_rate_and_reset:
+	bfq_update_rate_reset(bfqd, rq);
+update_last_values:
+	bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
+	bfqd->last_dispatch = now_ns;
+
+	bfq_log(bfqd,
+	"update_peak_rate: delta_first %lluus last_pos %llu peak_rate %llu",
+		(now_ns - bfqd->first_dispatch)>>10,
+		(unsigned long long) bfqd->last_position,
+		((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT));
+	bfq_log(bfqd,
+	"update_peak_rate: samples at end %d", bfqd->peak_rate_samples);
+}
+
+/*
+ * Move request from internal lists to the dispatch list of the request queue
+ */
+static void bfq_dispatch_insert(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, in a forced_dispatch, this prevents two counters related
+	 * to bfqq->dispatched to risk to be uselessly decremented if bfqq
+	 * is not in service, and then to be incremented again after
+	 * incrementing bfqq->dispatched.
+	 */
+	bfqq->dispatched++;
+	bfq_update_peak_rate(q->elevator->elevator_data, rq);
+
+	bfq_remove_request(rq);
+	elv_dispatch_sort(q, rq);
+}
+
+static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	BUG_ON(bfqq != bfqd->in_service_queue);
+
+	/*
+	 * If this bfqq is shared between multiple processes, check
+	 * to make sure that those processes are still issuing I/Os
+	 * within the mean seek distance. If not, it may be time to
+	 * break the queues apart again.
+	 */
+	if (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq))
+		bfq_mark_bfqq_split_coop(bfqq);
+
+	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		if (bfqq->dispatched == 0)
+			/*
+			 * Overloading budget_timeout field to store
+			 * the time at which the queue remains with no
+			 * backlog and no outstanding request; used by
+			 * the weight-raising mechanism.
+			 */
+			bfqq->budget_timeout = jiffies;
+
+		bfq_del_bfqq_busy(bfqd, bfqq, true);
+	} else {
+		bfq_requeue_bfqq(bfqd, bfqq);
+		/*
+		 * Resort priority tree of potential close cooperators.
+		 */
+		bfq_pos_tree_add_move(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;
+
+	BUG_ON(bfqq != bfqd->in_service_queue);
+
+	min_budget = bfq_min_budget(bfqd);
+
+	if (bfqq->wr_coeff == 1)
+		budget = bfqq->max_budget;
+	else /*
+	      * Use a constant, low budget for weight-raised queues,
+	      * to help achieve a low latency. Keep it slightly higher
+	      * than the minimum possible budget, to cause a little
+	      * bit fewer expirations.
+	      */
+		budget = 2 * min_budget;
+
+	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) && bfqq->wr_coeff == 1) {
+		switch (reason) {
+		/*
+		 * Caveat: in all the following cases we trade latency
+		 * for throughput.
+		 */
+		case BFQ_BFQQ_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 BFQ_BFQQ_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 BFQ_BFQQ_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 BFQ_BFQQ_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
+			 * BFQ_BFQQ_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 if (!bfq_bfqq_sync(bfqq))
+		/*
+		 * 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) {
+		BUG_ON(reason == BFQ_BFQQ_TOO_IDLE ||
+		       reason == BFQ_BFQQ_NO_MORE_REQUESTS);
+		bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget,
+					    bfq_serv_to_charge(next_rq, bfqq));
+		BUG_ON(!bfq_bfqq_busy(bfqq));
+		BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list));
+	}
+
+	bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %d",
+			next_rq ? blk_rq_sectors(next_rq) : 0,
+			bfqq->entity.budget);
+}
+
+/*
+ * Return true if the process associated with bfqq is "slow". The slow
+ * flag is used, in addition to the budget timeout, to reduce the
+ * amount of service provided to seeky processes, and thus reduce
+ * their chances to lower the throughput. More details in the comments
+ * on the function bfq_bfqq_expire().
+ *
+ * An important observation is in order: as discussed in the comments
+ * on the function bfq_update_peak_rate(), with devices with internal
+ * queues, it is hard if ever possible to know when and for how long
+ * an I/O request is processed by the device (apart from the trivial
+ * I/O pattern where a new request is dispatched only after the
+ * previous one has been completed). This makes it hard to evaluate
+ * the real rate at which the I/O requests of each bfq_queue are
+ * served.  In fact, for an I/O scheduler like BFQ, serving a
+ * bfq_queue means just dispatching its requests during its service
+ * slot (i.e., until the budget of the queue is exhausted, or the
+ * queue remains idle, or, finally, a timeout fires). But, during the
+ * service slot of a bfq_queue, around 100 ms at most, the device may
+ * be even still processing requests of bfq_queues served in previous
+ * service slots. On the opposite end, the requests of the in-service
+ * bfq_queue may be completed after the service slot of the queue
+ * finishes.
+ *
+ * Anyway, unless more sophisticated solutions are used
+ * (where possible), the sum of the sizes of the requests dispatched
+ * during the service slot of a bfq_queue is probably the only
+ * approximation available for the service received by the bfq_queue
+ * during its service slot. And this sum is the quantity used in this
+ * function to evaluate the I/O speed of a process.
+ */
+static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+				 bool compensate, enum bfqq_expiration reason,
+				 unsigned long *delta_ms)
+{
+	ktime_t delta_ktime;
+	u32 delta_usecs;
+	bool slow = BFQQ_SEEKY(bfqq); /* if delta too short, use seekyness */
+
+	if (!bfq_bfqq_sync(bfqq))
+		return false;
+
+	if (compensate)
+		delta_ktime = bfqd->last_idling_start;
+	else
+		delta_ktime = ktime_get();
+	delta_ktime = ktime_sub(delta_ktime, bfqd->last_budget_start);
+	delta_usecs = ktime_to_us(delta_ktime);
+
+	/* don't use too short time intervals */
+	if (delta_usecs < 1000) {
+		if (blk_queue_nonrot(bfqd->queue))
+			 /*
+			  * give same worst-case guarantees as idling
+			  * for seeky
+			  */
+			*delta_ms = BFQ_MIN_TT / NSEC_PER_MSEC;
+		else /* charge at least one seek */
+			*delta_ms = bfq_slice_idle / NSEC_PER_MSEC;
+
+		bfq_log(bfqd, "bfq_bfqq_is_slow: too short %u", delta_usecs);
+
+		return slow;
+	}
+
+	*delta_ms = delta_usecs / USEC_PER_MSEC;
+
+	/*
+	 * Use only long (> 20ms) intervals to filter out excessive
+	 * spikes in service rate estimation.
+	 */
+	if (delta_usecs > 20000) {
+		/*
+		 * Caveat for rotational devices: processes doing I/O
+		 * in the slower disk zones tend to be slow(er) even
+		 * if not seeky. In this respect, the estimated peak
+		 * rate is likely to be an average over the disk
+		 * surface. Accordingly, to not be too harsh with
+		 * unlucky processes, a process is deemed slow only if
+		 * its rate has been lower than half of the estimated
+		 * peak rate.
+		 */
+		slow = bfqq->entity.service < bfqd->bfq_max_budget / 2;
+		bfq_log(bfqd, "bfq_bfqq_is_slow: relative rate %d/%d",
+			bfqq->entity.service, bfqd->bfq_max_budget);
+	}
+
+	bfq_log_bfqq(bfqd, bfqq, "bfq_bfqq_is_slow: slow %d", slow);
+
+	return slow;
+}
+
+/*
+ * To be deemed as soft real-time, an application must meet two
+ * requirements. First, the application must not require an average
+ * bandwidth higher than the approximate bandwidth required to playback or
+ * record a compressed high-definition video.
+ * The next function is invoked on the completion of the last request of a
+ * batch, to compute the next-start time instant, soft_rt_next_start, such
+ * that, if the next request of the application does not arrive before
+ * soft_rt_next_start, then the above requirement on the bandwidth is met.
+ *
+ * The second requirement is that the request pattern of the application is
+ * isochronous, i.e., that, after issuing a request or a batch of requests,
+ * the application stops issuing new requests until all its pending requests
+ * have been completed. After that, the application may issue a new batch,
+ * and so on.
+ * For this reason the next function is invoked to compute
+ * soft_rt_next_start only for applications that meet this requirement,
+ * whereas soft_rt_next_start is set to infinity for applications that do
+ * not.
+ *
+ * Unfortunately, even a greedy application may happen to behave in an
+ * isochronous way if the CPU load is high. In fact, the application may
+ * stop issuing requests while the CPUs are busy serving other processes,
+ * then restart, then stop again for a while, and so on. In addition, if
+ * the disk achieves a low enough throughput with the request pattern
+ * issued by the application (e.g., because the request pattern is random
+ * and/or the device is slow), then the application may meet the above
+ * bandwidth requirement too. To prevent such a greedy application to be
+ * deemed as soft real-time, a further rule is used in the computation of
+ * soft_rt_next_start: soft_rt_next_start must be higher than the current
+ * time plus the maximum time for which the arrival of a request is waited
+ * for when a sync queue becomes idle, namely bfqd->bfq_slice_idle.
+ * This filters out greedy applications, as the latter issue instead their
+ * next request as soon as possible after the last one has been completed
+ * (in contrast, when a batch of requests is completed, a soft real-time
+ * application spends some time processing data).
+ *
+ * Unfortunately, the last filter may easily generate false positives if
+ * only bfqd->bfq_slice_idle is used as a reference time interval and one
+ * or both the following cases occur:
+ * 1) HZ is so low that the duration of a jiffy is comparable to or higher
+ *    than bfqd->bfq_slice_idle. This happens, e.g., on slow devices with
+ *    HZ=100.
+ * 2) jiffies, instead of increasing at a constant rate, may stop increasing
+ *    for a while, then suddenly 'jump' by several units to recover the lost
+ *    increments. This seems to happen, e.g., inside virtual machines.
+ * To address this issue, we do not use as a reference time interval just
+ * bfqd->bfq_slice_idle, but bfqd->bfq_slice_idle plus a few jiffies. In
+ * particular we add the minimum number of jiffies for which the filter
+ * seems to be quite precise also in embedded systems and KVM/QEMU virtual
+ * machines.
+ */
+static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
+						struct bfq_queue *bfqq)
+{
+	bfq_log_bfqq(bfqd, bfqq,
+"softrt_next_start: service_blkg %lu soft_rate %u sects/sec interval %u",
+		     bfqq->service_from_backlogged,
+		     bfqd->bfq_wr_max_softrt_rate,
+		     jiffies_to_msecs(HZ * bfqq->service_from_backlogged /
+				      bfqd->bfq_wr_max_softrt_rate));
+
+	return max(bfqq->last_idle_bklogged +
+		   HZ * bfqq->service_from_backlogged /
+		   bfqd->bfq_wr_max_softrt_rate,
+		   jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
+}
+
+/*
+ * Return the farthest future time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_greatest_from_now(void)
+{
+	return jiffies + MAX_JIFFY_OFFSET;
+}
+
+/*
+ * 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 bfqq does slow I/O (e.g., because it
+ * issues random requests), we charge bfqq with the time it has been
+ * in service instead of the service it has received (see
+ * bfq_bfqq_charge_time for details on how this goal is achieved). As
+ * a consequence, bfqq will typically get higher timestamps upon
+ * reactivation, and hence it will be rescheduled as if it had
+ * received more service than what it has actually received. In the
+ * end, bfqq receives less service in proportion to how slowly its
+ * associated process consumes its budgets (and hence how seriously it
+ * tends to lower the throughput). In addition, this time-charging
+ * strategy guarantees time fairness among slow processes. In
+ * contrast, if the process associated with bfqq is not slow, we
+ * charge bfqq exactly with the service it has received.
+ *
+ * Charging time to the first type of queues and the exact service to
+ * the other has the effect of using the WF2Q+ policy to schedule the
+ * former on a timeslice basis, without violating service domain
+ * guarantees among the latter.
+ */
+static void bfq_bfqq_expire(struct bfq_data *bfqd,
+			    struct bfq_queue *bfqq,
+			    bool compensate,
+			    enum bfqq_expiration reason)
+{
+	bool slow;
+	unsigned long delta = 0;
+	struct bfq_entity *entity = &bfqq->entity;
+	int ref;
+
+	BUG_ON(bfqq != bfqd->in_service_queue);
+
+	/*
+	 * Check whether the process is slow (see bfq_bfqq_is_slow).
+	 */
+	slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta);
+
+	/*
+	 * Increase service_from_backlogged before next statement,
+	 * because the possible next invocation of
+	 * bfq_bfqq_charge_time would likely inflate
+	 * entity->service. In contrast, service_from_backlogged must
+	 * contain real service, to enable the soft real-time
+	 * heuristic to correctly compute the bandwidth consumed by
+	 * bfqq.
+	 */
+	bfqq->service_from_backlogged += entity->service;
+
+	/*
+	 * As above explained, charge slow (typically seeky) and
+	 * timed-out queues with the time and not the service
+	 * received, to favor sequential workloads.
+	 *
+	 * Processes doing I/O in the slower disk zones will tend to
+	 * be slow(er) even if not seeky. Therefore, since the
+	 * estimated peak rate is actually an average over the disk
+	 * surface, these processes may timeout just for bad luck. To
+	 * avoid punishing them, do not charge time to processes that
+	 * succeeded in consuming at least 2/3 of their budget. This
+	 * allows BFQ to preserve enough elasticity to still perform
+	 * bandwidth, and not time, distribution with little unlucky
+	 * or quasi-sequential processes.
+	 */
+	if (bfqq->wr_coeff == 1 &&
+	    (slow ||
+	     (reason == BFQ_BFQQ_BUDGET_TIMEOUT &&
+	      bfq_bfqq_budget_left(bfqq) >=  entity->budget / 3)))
+		bfq_bfqq_charge_time(bfqd, bfqq, delta);
+
+	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
+
+	if (reason == BFQ_BFQQ_TOO_IDLE &&
+	    entity->service <= 2 * entity->budget / 10)
+		bfq_clear_bfqq_IO_bound(bfqq);
+
+	if (bfqd->low_latency && bfqq->wr_coeff == 1)
+		bfqq->last_wr_start_finish = jiffies;
+
+	if (bfqd->low_latency && bfqd->bfq_wr_max_softrt_rate > 0 &&
+	    RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		/*
+		 * If we get here, and there are no outstanding
+		 * requests, then the request pattern is isochronous
+		 * (see the comments on the function
+		 * bfq_bfqq_softrt_next_start()). Thus we can compute
+		 * soft_rt_next_start. If, instead, the queue still
+		 * has outstanding requests, then we have to wait for
+		 * the completion of all the outstanding requests to
+		 * discover whether the request pattern is actually
+		 * isochronous.
+		 */
+		BUG_ON(bfqd->busy_queues < 1);
+		if (bfqq->dispatched == 0) {
+			bfqq->soft_rt_next_start =
+				bfq_bfqq_softrt_next_start(bfqd, bfqq);
+			bfq_log_bfqq(bfqd, bfqq, "new soft_rt_next %lu",
+				     bfqq->soft_rt_next_start);
+		} else {
+			/*
+			 * The application is still waiting for the
+			 * completion of one or more requests:
+			 * prevent it from possibly being incorrectly
+			 * deemed as soft real-time by setting its
+			 * soft_rt_next_start to infinity. In fact,
+			 * without this assignment, the application
+			 * would be incorrectly deemed as soft
+			 * real-time if:
+			 * 1) it issued a new request before the
+			 *    completion of all its in-flight
+			 *    requests, and
+			 * 2) at that time, its soft_rt_next_start
+			 *    happened to be in the past.
+			 */
+			bfqq->soft_rt_next_start =
+				bfq_greatest_from_now();
+			/*
+			 * Schedule an update of soft_rt_next_start to when
+			 * the task may be discovered to be isochronous.
+			 */
+			bfq_mark_bfqq_softrt_update(bfqq);
+		}
+	}
+
+	bfq_log_bfqq(bfqd, bfqq,
+		"expire (%d, slow %d, num_disp %d, idle_win %d, weight %d)",
+		     reason, slow, bfqq->dispatched,
+		     bfq_bfqq_idle_window(bfqq), entity->weight);
+
+	/*
+	 * Increase, decrease or leave budget unchanged according to
+	 * reason.
+	 */
+	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
+	__bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
+	BUG_ON(bfqq->next_rq == NULL &&
+	       bfqq->entity.budget < bfqq->entity.service);
+	ref = bfqq->ref;
+	__bfq_bfqq_expire(bfqd, bfqq);
+
+	BUG_ON(ref > 1 &&
+	       !bfq_bfqq_busy(bfqq) && reason == BFQ_BFQQ_BUDGET_EXHAUSTED &&
+		!bfq_class_idle(bfqq));
+
+	/* mark bfqq as waiting a request only if a bic still points to it */
+	if (ref > 1 && !bfq_bfqq_busy(bfqq) &&
+	    reason != BFQ_BFQQ_BUDGET_TIMEOUT &&
+	    reason != BFQ_BFQQ_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)
+{
+	return time_is_before_eq_jiffies(bfqq->budget_timeout);
+}
+
+/*
+ * 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 that queue. As a consequence, since
+ * device idling plays a critical role for both throughput boosting
+ * and service guarantees, the return value of this function plays a
+ * critical role as well.
+ *
+ * In a nutshell, this function returns true only if idling is
+ * beneficial for throughput or, even if detrimental for throughput,
+ * idling is however necessary to preserve service guarantees (low
+ * latency, desired throughput distribution, ...). In particular, on
+ * NCQ-capable devices, this function tries to return false, so as to
+ * help keep the drives' internal queues full, whenever this helps the
+ * device boost the throughput without causing any service-guarantee
+ * issue.
+ *
+ * In more detail, the return value of this function is obtained by,
+ * first, computing a number of boolean variables that take into
+ * account throughput and service-guarantee issues, and, then,
+ * combining these variables in a logical expression. Most of the
+ * issues taken into account are not trivial. We discuss these issues
+ * while introducing the variables.
+ */
+static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
+{
+	struct bfq_data *bfqd = bfqq->bfqd;
+	bool idling_boosts_thr, idling_boosts_thr_without_issues,
+		idling_needed_for_service_guarantees,
+		asymmetric_scenario;
+
+	if (bfqd->strict_guarantees)
+		return true;
+
+	/*
+	 * The next variable takes into account the cases where idling
+	 * boosts the throughput.
+	 *
+	 * The value of the variable is computed considering, first, that
+	 * idling is virtually always beneficial for the throughput if:
+	 * (a) the device is not NCQ-capable, or
+	 * (b) regardless of the presence of NCQ, the device is rotational
+	 *     and the request pattern for bfqq is I/O-bound and sequential.
+	 *
+	 * Secondly, and in contrast to the above item (b), idling an
+	 * NCQ-capable flash-based device would not boost the
+	 * throughput even with sequential I/O; rather it would lower
+	 * the throughput in proportion to how fast the device
+	 * is. Accordingly, the next variable is true if any of the
+	 * above conditions (a) and (b) is true, and, in particular,
+	 * happens to be false if bfqd is an NCQ-capable flash-based
+	 * device.
+	 */
+	idling_boosts_thr = !bfqd->hw_tag ||
+		(!blk_queue_nonrot(bfqd->queue) && bfq_bfqq_IO_bound(bfqq) &&
+		 bfq_bfqq_idle_window(bfqq));
+
+	/*
+	 * The value of the next variable,
+	 * idling_boosts_thr_without_issues, is equal to that of
+	 * idling_boosts_thr, unless a special case holds. In this
+	 * special case, described below, idling may cause problems to
+	 * weight-raised queues.
+	 *
+	 * When the request pool is saturated (e.g., in the presence
+	 * of write hogs), if the processes associated with
+	 * non-weight-raised queues ask for requests at a lower rate,
+	 * then processes associated with weight-raised queues have a
+	 * higher probability to get a request from the pool
+	 * immediately (or at least soon) when they need one. Thus
+	 * they have a higher probability to actually get a fraction
+	 * of the device throughput proportional to their high
+	 * weight. This is especially true with NCQ-capable drives,
+	 * which enqueue several requests in advance, and further
+	 * reorder internally-queued requests.
+	 *
+	 * For this reason, we force to false the value of
+	 * idling_boosts_thr_without_issues if there are weight-raised
+	 * busy queues. In this case, and if bfqq is not weight-raised,
+	 * this guarantees that the device is not idled for bfqq (if,
+	 * instead, bfqq is weight-raised, then idling will be
+	 * guaranteed by another variable, see below). Combined with
+	 * the timestamping rules of BFQ (see [1] for details), this
+	 * behavior causes bfqq, and hence any sync non-weight-raised
+	 * queue, to get a lower number of requests served, and thus
+	 * to ask for a lower number of requests from the request
+	 * pool, before the busy weight-raised queues get served
+	 * again. This often mitigates starvation problems in the
+	 * presence of heavy write workloads and NCQ, thereby
+	 * guaranteeing a higher application and system responsiveness
+	 * in these hostile scenarios.
+	 */
+	idling_boosts_thr_without_issues = idling_boosts_thr &&
+		bfqd->wr_busy_queues == 0;
+
+	/*
+	 * There is then a case where idling must be performed not
+	 * for throughput concerns, but to preserve service
+	 * guarantees.
+	 *
+	 * To introduce this case, we can note that allowing the drive
+	 * to enqueue more than one request at a time, and hence
+	 * delegating de facto final scheduling decisions to the
+	 * drive's internal scheduler, entails loss of control on the
+	 * actual request service order. In particular, the critical
+	 * situation is when requests from different processes happen
+	 * to be present, at the same time, in the internal queue(s)
+	 * of the drive. In such a situation, the drive, by deciding
+	 * the service order of the internally-queued requests, does
+	 * determine also the actual throughput distribution among
+	 * these processes. But the drive typically has no notion or
+	 * concern about per-process throughput distribution, and
+	 * makes its decisions only on a per-request basis. Therefore,
+	 * the service distribution enforced by the drive's internal
+	 * scheduler is likely to coincide with the desired
+	 * device-throughput distribution only in a completely
+	 * symmetric scenario where:
+	 * (i)  each of these processes must get the same throughput as
+	 *      the others;
+	 * (ii) all these processes have the same I/O pattern
+	 *      (either sequential or random).
+	 * In fact, in such a scenario, the drive will tend to treat
+	 * the requests of each of these processes in about the same
+	 * way as the requests of the others, and thus to provide
+	 * each of these processes with about the same throughput
+	 * (which is exactly the desired throughput distribution). In
+	 * contrast, in any asymmetric scenario, device idling is
+	 * certainly needed to guarantee that bfqq receives its
+	 * assigned fraction of the device throughput (see [1] for
+	 * details).
+	 *
+	 * We address this issue by controlling, actually, only the
+	 * symmetry sub-condition (i), i.e., provided that
+	 * sub-condition (i) holds, idling is not performed,
+	 * regardless of whether sub-condition (ii) holds. In other
+	 * words, only if sub-condition (i) holds, then idling is
+	 * allowed, and the device tends to be prevented from queueing
+	 * many requests, possibly of several processes. The reason
+	 * for not controlling also sub-condition (ii) is that we
+	 * exploit preemption to preserve guarantees in case of
+	 * symmetric scenarios, even if (ii) does not hold, as
+	 * explained in the next two paragraphs.
+	 *
+	 * Even if a queue, say Q, is expired when it remains idle, Q
+	 * can still preempt the new in-service queue if the next
+	 * request of Q arrives soon (see the comments on
+	 * bfq_bfqq_update_budg_for_activation). If all queues and
+	 * groups have the same weight, this form of preemption,
+	 * combined with the hole-recovery heuristic described in the
+	 * comments on function bfq_bfqq_update_budg_for_activation,
+	 * are enough to preserve a correct bandwidth distribution in
+	 * the mid term, even without idling. In fact, even if not
+	 * idling allows the internal queues of the device to contain
+	 * many requests, and thus to reorder requests, we can rather
+	 * safely assume that the internal scheduler still preserves a
+	 * minimum of mid-term fairness. The motivation for using
+	 * preemption instead of idling is that, by not idling,
+	 * service guarantees are preserved without minimally
+	 * sacrificing throughput. In other words, both a high
+	 * throughput and its desired distribution are obtained.
+	 *
+	 * More precisely, this preemption-based, idleless approach
+	 * provides fairness in terms of IOPS, and not sectors per
+	 * second. This can be seen with a simple example. Suppose
+	 * that there are two queues with the same weight, but that
+	 * the first queue receives requests of 8 sectors, while the
+	 * second queue receives requests of 1024 sectors. In
+	 * addition, suppose that each of the two queues contains at
+	 * most one request at a time, which implies that each queue
+	 * always remains idle after it is served. Finally, after
+	 * remaining idle, each queue receives very quickly a new
+	 * request. It follows that the two queues are served
+	 * alternatively, preempting each other if needed. This
+	 * implies that, although both queues have the same weight,
+	 * the queue with large requests receives a service that is
+	 * 1024/8 times as high as the service received by the other
+	 * queue.
+	 *
+	 * On the other hand, device idling is performed, and thus
+	 * pure sector-domain guarantees are provided, for the
+	 * following queues, which are likely to need stronger
+	 * throughput guarantees: weight-raised queues, and queues
+	 * with a higher weight than other queues. When such queues
+	 * are active, sub-condition (i) is false, which triggers
+	 * device idling.
+	 *
+	 * According to the above considerations, the next variable is
+	 * true (only) if sub-condition (i) holds. To compute the
+	 * value of this variable, we not only use the return value of
+	 * the function bfq_symmetric_scenario(), but also check
+	 * whether bfqq is being weight-raised, because
+	 * bfq_symmetric_scenario() does not take into account also
+	 * weight-raised queues (see comments on
+	 * bfq_weights_tree_add()).
+	 *
+	 * As a side note, it is worth considering that the above
+	 * device-idling countermeasures may however fail in the
+	 * following unlucky scenario: if idling is (correctly)
+	 * disabled in a time period during which all symmetry
+	 * sub-conditions hold, and hence the device is allowed to
+	 * enqueue many requests, but at some later point in time some
+	 * sub-condition stops to hold, then it may become impossible
+	 * to let requests be served in the desired order until all
+	 * the requests already queued in the device have been served.
+	 */
+	asymmetric_scenario = bfqq->wr_coeff > 1 ||
+		!bfq_symmetric_scenario(bfqd);
+
+	/*
+	 * Finally, there is a case where maximizing throughput is the
+	 * best choice even if it may cause unfairness toward
+	 * bfqq. Such a case is when bfqq became active in a burst of
+	 * queue activations. Queues that became active during a large
+	 * burst benefit only from throughput, as discussed in the
+	 * comments on bfq_handle_burst. Thus, if bfqq became active
+	 * in a burst and not idling the device maximizes throughput,
+	 * then the device must no be idled, because not idling the
+	 * device provides bfqq and all other queues in the burst with
+	 * maximum benefit. Combining this and the above case, we can
+	 * now establish when idling is actually needed to preserve
+	 * service guarantees.
+	 */
+	idling_needed_for_service_guarantees =
+		asymmetric_scenario && !bfq_bfqq_in_large_burst(bfqq);
+
+	/*
+	 * We have now all 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 either boosts the throughput (without issues), or
+	 *    is necessary to preserve service guarantees.
+	 */
+	bfq_log_bfqq(bfqd, bfqq, "may_idle: sync %d idling_boosts_thr %d",
+		     bfq_bfqq_sync(bfqq), idling_boosts_thr);
+
+	bfq_log_bfqq(bfqd, bfqq,
+		     "may_idle: wr_busy %d boosts %d IO-bound %d guar %d",
+		     bfqd->wr_busy_queues,
+		     idling_boosts_thr_without_issues,
+		     bfq_bfqq_IO_bound(bfqq),
+		     idling_needed_for_service_guarantees);
+
+	return bfq_bfqq_sync(bfqq) &&
+		(idling_boosts_thr_without_issues ||
+		 idling_needed_for_service_guarantees);
+}
+
+/*
+ * 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 = BFQ_BFQQ_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) &&
+	    !hrtimer_active(&bfqd->idle_slice_timer) &&
+	    !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) {
+		BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list));
+
+		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 = BFQ_BFQQ_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)) {
+				BUG_ON(!hrtimer_active(&bfqd->idle_slice_timer));
+				/*
+				 * 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 (hrtimer_active(&bfqd->idle_slice_timer) ||
+	    (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) {
+		bfqq = NULL;
+		goto keep_queue;
+	}
+
+	reason = BFQ_BFQQ_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;
+}
+
+static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */
+		BUG_ON(bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
+		       time_is_after_jiffies(bfqq->last_wr_start_finish));
+
+		bfq_log_bfqq(bfqd, bfqq,
+			"raising period dur %u/%u msec, old coeff %u, w %d(%d)",
+			jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish),
+			jiffies_to_msecs(bfqq->wr_cur_max_time),
+			bfqq->wr_coeff,
+			bfqq->entity.weight, bfqq->entity.orig_weight);
+
+		BUG_ON(bfqq != bfqd->in_service_queue && entity->weight !=
+		       entity->orig_weight * bfqq->wr_coeff);
+		if (entity->prio_changed)
+			bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change");
+
+		/*
+		 * If the queue was activated in a burst, or too much
+		 * time has elapsed from the beginning of this
+		 * weight-raising period, then end weight raising.
+		 */
+		if (bfq_bfqq_in_large_burst(bfqq))
+			bfq_bfqq_end_wr(bfqq);
+		else if (time_is_before_jiffies(bfqq->last_wr_start_finish +
+					   bfqq->wr_cur_max_time)) {
+			if (bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time ||
+			time_is_before_jiffies(bfqq->wr_start_at_switch_to_srt +
+					bfq_wr_duration(bfqd)))
+				bfq_bfqq_end_wr(bfqq);
+			else {
+				/* switch back to interactive wr */
+				bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+				bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+				bfqq->last_wr_start_finish =
+					bfqq->wr_start_at_switch_to_srt;
+				BUG_ON(time_is_after_jiffies(
+					       bfqq->last_wr_start_finish));
+				bfqq->entity.prio_changed = 1;
+				bfq_log_bfqq(bfqd, bfqq,
+					"back to interactive wr");
+			}
+		}
+	}
+	/*
+	 * To improve latency (for this or other queues), immediately
+	 * update weight both if it must be raised and if it must be
+	 * lowered. Since, entity may be on some active tree here, and
+	 * might have a pending change of its ioprio class, invoke
+	 * next function with the last parameter unset (see the
+	 * comments on the function).
+	 */
+	if ((entity->weight > entity->orig_weight) != (bfqq->wr_coeff > 1))
+		__bfq_entity_update_weight_prio(bfq_entity_service_tree(entity),
+						entity, false);
+}
+
+/*
+ * Dispatch one request from bfqq, moving it to the request queue
+ * dispatch list.
+ */
+static int bfq_dispatch_request(struct bfq_data *bfqd,
+				struct bfq_queue *bfqq)
+{
+	int dispatched = 0;
+	struct request *rq = bfqq->next_rq;
+	unsigned long service_to_charge;
+
+	BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list));
+	BUG_ON(!rq);
+	service_to_charge = bfq_serv_to_charge(rq, bfqq);
+
+	BUG_ON(service_to_charge > bfq_bfqq_budget_left(bfqq));
+
+	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
+
+	bfq_bfqq_served(bfqq, service_to_charge);
+
+	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
+
+	bfq_dispatch_insert(bfqd->queue, rq);
+
+	/*
+	 * If weight raising has to terminate for bfqq, then next
+	 * function causes an immediate update of bfqq's weight,
+	 * without waiting for next activation. As a consequence, on
+	 * expiration, bfqq will be timestamped as if has never been
+	 * weight-raised during this service slot, even if it has
+	 * received part or even most of the service as a
+	 * weight-raised queue. This inflates bfqq's timestamps, which
+	 * is beneficial, as bfqq is then more willing to leave the
+	 * device immediately to possible other weight-raised queues.
+	 */
+	bfq_update_wr_data(bfqd, bfqq);
+
+	bfq_log_bfqq(bfqd, bfqq,
+			"dispatched %u sec req (%llu), budg left %d",
+			blk_rq_sectors(rq),
+			(unsigned long long) blk_rq_pos(rq),
+			bfq_bfqq_budget_left(bfqq));
+
+	dispatched++;
+
+	if (!bfqd->in_service_bic) {
+		atomic_long_inc(&RQ_BIC(rq)->icq.ioc->refcount);
+		bfqd->in_service_bic = RQ_BIC(rq);
+	}
+
+	if (bfqd->busy_queues > 1 && bfq_class_idle(bfqq))
+		goto expire;
+
+	return dispatched;
+
+expire:
+	bfq_bfqq_expire(bfqd, bfqq, false, BFQ_BFQQ_BUDGET_EXHAUSTED);
+	return dispatched;
+}
+
+static int __bfq_forced_dispatch_bfqq(struct bfq_queue *bfqq)
+{
+	int dispatched = 0;
+
+	while (bfqq->next_rq) {
+		bfq_dispatch_insert(bfqq->bfqd->queue, bfqq->next_rq);
+		dispatched++;
+	}
+
+	BUG_ON(!list_empty(&bfqq->fifo));
+	return dispatched;
+}
+
+/*
+ * Drain our current requests.
+ * Used for barriers and when switching io schedulers on-the-fly.
+ */
+static int bfq_forced_dispatch(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq, *n;
+	struct bfq_service_tree *st;
+	int dispatched = 0;
+
+	bfqq = bfqd->in_service_queue;
+	if (bfqq)
+		__bfq_bfqq_expire(bfqd, bfqq);
+
+	/*
+	 * Loop through classes, and be careful to leave the scheduler
+	 * in a consistent state, as feedback mechanisms and vtime
+	 * updates cannot be disabled during the process.
+	 */
+	list_for_each_entry_safe(bfqq, n, &bfqd->active_list, bfqq_list) {
+		st = bfq_entity_service_tree(&bfqq->entity);
+
+		dispatched += __bfq_forced_dispatch_bfqq(bfqq);
+
+		bfqq->max_budget = bfq_max_budget(bfqd);
+		bfq_forget_idle(st);
+	}
+
+	BUG_ON(bfqd->busy_queues != 0);
+
+	return dispatched;
+}
+
+static int bfq_dispatch_requests(struct request_queue *q, int force)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct bfq_queue *bfqq;
+
+	bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues);
+
+	if (bfqd->busy_queues == 0)
+		return 0;
+
+	if (unlikely(force))
+		return bfq_forced_dispatch(bfqd);
+
+	/*
+	 * 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)
+		return 0;
+
+	bfqq = bfq_select_queue(bfqd);
+	if (!bfqq)
+		return 0;
+
+	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
+
+	BUG_ON(bfq_bfqq_wait_request(bfqq));
+
+	if (!bfq_dispatch_request(bfqd, bfqq))
+		return 0;
+
+	bfq_log_bfqq(bfqd, bfqq, "dispatched %s request",
+			bfq_bfqq_sync(bfqq) ? "sync" : "async");
+
+	BUG_ON(bfqq->next_rq == NULL &&
+	       bfqq->entity.budget < bfqq->entity.service);
+	return 1;
+}
+
+/*
+ * 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.
+ *
+ * Queue 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_SQ_GROUP_IOSCHED
+	struct bfq_group *bfqg = bfqq_group(bfqq);
+#endif
+
+	BUG_ON(bfqq->ref <= 0);
+
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d", bfqq, bfqq->ref);
+	bfqq->ref--;
+	if (bfqq->ref)
+		return;
+
+	BUG_ON(rb_first(&bfqq->sort_list));
+	BUG_ON(bfqq->allocated[READ] + bfqq->allocated[WRITE] != 0);
+	BUG_ON(bfqq->entity.tree);
+	BUG_ON(bfq_bfqq_busy(bfqq));
+
+	if (bfq_bfqq_sync(bfqq))
+		/*
+		 * The fact that this queue is being destroyed does not
+		 * invalidate the fact that this queue may have been
+		 * activated during the current burst. As a consequence,
+		 * although the queue does not exist anymore, and hence
+		 * needs to be removed from the burst list if there,
+		 * the burst size has not to be decremented.
+		 */
+		hlist_del_init(&bfqq->burst_list_node);
+
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p freed", bfqq);
+
+	kmem_cache_free(bfq_pool, bfqq);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	bfqg_put(bfqg);
+#endif
+}
+
+static void bfq_put_cooperator(struct bfq_queue *bfqq)
+{
+	struct bfq_queue *__bfqq, *next;
+
+	/*
+	 * If this queue was scheduled to merge with another queue, be
+	 * sure to drop the reference taken on that queue (and others in
+	 * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs.
+	 */
+	__bfqq = bfqq->new_bfqq;
+	while (__bfqq) {
+		if (__bfqq == bfqq)
+			break;
+		next = __bfqq->new_bfqq;
+		bfq_put_queue(__bfqq);
+		__bfqq = next;
+	}
+}
+
+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_cooperator(bfqq);
+
+	bfq_put_queue(bfqq); /* release process reference */
+}
+
+static void bfq_init_icq(struct io_cq *icq)
+{
+	icq_to_bic(icq)->ttime.last_end_request = ktime_get_ns() - (1ULL<<32);
+}
+
+static void bfq_exit_icq(struct io_cq *icq)
+{
+	struct bfq_io_cq *bic = icq_to_bic(icq);
+	struct bfq_data *bfqd = bic_to_bfqd(bic);
+
+	if (bic_to_bfqq(bic, false)) {
+		bfq_exit_bfqq(bfqd, bic_to_bfqq(bic, false));
+		bic_set_bfqq(bic, NULL, false);
+	}
+
+	if (bic_to_bfqq(bic, true)) {
+		/*
+		 * If the bic is using a shared queue, put the reference
+		 * taken on the io_context when the bic started using a
+		 * shared bfq_queue.
+		 */
+		if (bfq_bfqq_coop(bic_to_bfqq(bic, true)))
+			put_io_context(icq->ioc);
+		bfq_exit_bfqq(bfqd, bic_to_bfqq(bic, true));
+		bic_set_bfqq(bic, NULL, true);
+	}
+}
+
+/*
+ * 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;
+
+	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);
+		BUG();
+	}
+
+	bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio);
+	bfqq->entity.prio_changed = 1;
+	bfq_log_bfqq(bfqq->bfqd, bfqq,
+		     "set_next_ioprio_data: bic_class %d prio %d class %d",
+		     ioprio_class, bfqq->new_ioprio, bfqq->new_ioprio_class);
+}
+
+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;
+	unsigned long uninitialized_var(flags);
+	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);
+		bfq_log_bfqq(bfqd, bfqq,
+			     "check_ioprio_change: bfqq %p %d",
+			     bfqq, bfqq->ref);
+	}
+
+	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);
+	INIT_HLIST_NODE(&bfqq->burst_list_node);
+	BUG_ON(!hlist_unhashed(&bfqq->burst_list_node));
+
+	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);
+		bfq_mark_bfqq_just_created(bfqq);
+	} else
+		bfq_clear_bfqq_sync(bfqq);
+	bfq_mark_bfqq_IO_bound(bfqq);
+
+	/* Tentative initial value to trade off between thr and lat */
+	bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3;
+	bfqq->pid = pid;
+
+	bfqq->wr_coeff = 1;
+	bfqq->last_wr_start_finish = jiffies;
+	bfqq->wr_start_at_switch_to_srt = bfq_smallest_from_now();
+	bfqq->budget_timeout = bfq_smallest_from_now();
+	bfqq->split_time = bfq_smallest_from_now();
+
+	/*
+	 * Set to the value for which bfqq will not be deemed as
+	 * soft rt when it becomes backlogged.
+	 */
+	bfqq->soft_rt_next_start = bfq_greatest_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:
+		BUG();
+	}
+}
+
+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_io_cq *bic)
+{
+	struct bfq_ttime *ttime = &bic->ttime;
+	u64 elapsed = ktime_get_ns() - bic->ttime.last_end_request;
+
+	elapsed = min_t(u64, elapsed, 2 * bfqd->bfq_slice_idle);
+
+	ttime->ttime_samples = (7*bic->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)
+{
+	bfqq->seek_history <<= 1;
+	bfqq->seek_history |=
+		get_sdist(bfqq->last_request_pos, rq) > 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;
+
+	/* Idle window just restored, statistics are meaningless. */
+	if (time_is_after_eq_jiffies(bfqq->split_time +
+				     bfqd->bfq_wr_min_idle_time))
+		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) &&
+			bfqq->wr_coeff == 1))
+		enable_idle = 0;
+	else if (bfq_sample_valid(bic->ttime.ttime_samples)) {
+		if (bic->ttime.ttime_mean > bfqd->bfq_slice_idle &&
+			bfqq->wr_coeff == 1)
+			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, bic);
+	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,
+					BFQ_BFQQ_BUDGET_TIMEOUT);
+
+		/*
+		 * Let the request rip immediately, or let a new queue be
+		 * selected if bfqq has just been expired.
+		 */
+		__blk_run_queue(bfqd->queue);
+	}
+}
+
+static void bfq_insert_request(struct request_queue *q, struct request *rq)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq;
+
+	assert_spin_locked(bfqd->queue->queue_lock);
+
+	/*
+	 * An unplug may trigger a requeue of a request from the device
+	 * driver: make sure we are in process context while trying to
+	 * merge two bfq_queues.
+	 */
+	if (!in_interrupt()) {
+		new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true);
+		if (new_bfqq) {
+			if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq)
+				new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1);
+			/*
+			 * Release the request's reference to the old bfqq
+			 * and make sure one is taken to the shared queue.
+			 */
+			new_bfqq->allocated[rq_data_dir(rq)]++;
+			bfqq->allocated[rq_data_dir(rq)]--;
+			new_bfqq->ref++;
+			bfq_clear_bfqq_just_created(bfqq);
+			if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
+				bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
+						bfqq, new_bfqq);
+			/*
+			 * rq is about to be enqueued into new_bfqq,
+			 * release rq reference on bfqq
+			 */
+			bfq_put_queue(bfqq);
+			rq->elv.priv[1] = new_bfqq;
+			bfqq = new_bfqq;
+		}
+	}
+
+	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_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 request_queue *q, struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_data *bfqd = bfqq->bfqd;
+	u64 now_ns;
+	u32 delta_us;
+
+	bfq_log_bfqq(bfqd, bfqq, "completed one req with %u sects left",
+		     blk_rq_sectors(rq));
+
+	assert_spin_locked(bfqd->queue->queue_lock);
+	bfq_update_hw_tag(bfqd);
+
+	BUG_ON(!bfqd->rq_in_driver);
+	BUG_ON(!bfqq->dispatched);
+	bfqd->rq_in_driver--;
+	bfqq->dispatched--;
+	bfqg_stats_update_completion(bfqq_group(bfqq),
+				     rq_start_time_ns(rq),
+				     rq_io_start_time_ns(rq),
+				     rq->cmd_flags);
+
+	if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) {
+		BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
+		/*
+		 * Set budget_timeout (which we overload to store the
+		 * time at which the queue remains with no backlog and
+		 * no outstanding request; used by the weight-raising
+		 * mechanism).
+		 */
+		bfqq->budget_timeout = jiffies;
+
+		bfq_weights_tree_remove(bfqd, &bfqq->entity,
+					&bfqd->queue_weights_tree);
+	}
+
+	now_ns = ktime_get_ns();
+
+	RQ_BIC(rq)->ttime.last_end_request = now_ns;
+
+	/*
+	 * Using us instead of ns, to get a reasonable precision in
+	 * computing rate in next check.
+	 */
+	delta_us = div_u64(now_ns - bfqd->last_completion, NSEC_PER_USEC);
+
+	bfq_log(bfqd, "rq_completed: delta %uus/%luus max_size %u rate %llu/%llu",
+		delta_us, BFQ_MIN_TT/NSEC_PER_USEC, bfqd->last_rq_max_size,
+		(USEC_PER_SEC*
+		(u64)((bfqd->last_rq_max_size<<BFQ_RATE_SHIFT)/delta_us))
+			>>BFQ_RATE_SHIFT,
+		(USEC_PER_SEC*(u64)(1UL<<(BFQ_RATE_SHIFT-10)))>>BFQ_RATE_SHIFT);
+
+	/*
+	 * If the request took rather long to complete, and, according
+	 * to the maximum request size recorded, this completion latency
+	 * implies that the request was certainly served at a very low
+	 * rate (less than 1M sectors/sec), then the whole observation
+	 * interval that lasts up to this time instant cannot be a
+	 * valid time interval for computing a new peak rate.  Invoke
+	 * bfq_update_rate_reset to have the following three steps
+	 * taken:
+	 * - close the observation interval at the last (previous)
+	 *   request dispatch or completion
+	 * - compute rate, if possible, for that observation interval
+	 * - reset to zero samples, which will trigger a proper
+	 *   re-initialization of the observation interval on next
+	 *   dispatch
+	 */
+	if (delta_us > BFQ_MIN_TT/NSEC_PER_USEC &&
+	   (bfqd->last_rq_max_size<<BFQ_RATE_SHIFT)/delta_us <
+			1UL<<(BFQ_RATE_SHIFT - 10))
+		bfq_update_rate_reset(bfqd, NULL);
+	bfqd->last_completion = now_ns;
+
+	/*
+	 * If we are waiting to discover whether the request pattern
+	 * of the task associated with the queue is actually
+	 * isochronous, and both requisites for this condition to hold
+	 * are now satisfied, then compute soft_rt_next_start (see the
+	 * comments on the function bfq_bfqq_softrt_next_start()). We
+	 * schedule this delayed check when bfqq expires, if it still
+	 * has in-flight requests.
+	 */
+	if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 &&
+	    RB_EMPTY_ROOT(&bfqq->sort_list))
+		bfqq->soft_rt_next_start =
+			bfq_bfqq_softrt_next_start(bfqd, bfqq);
+
+	/*
+	 * 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 (bfqq->dispatched == 0 && bfq_bfqq_must_idle(bfqq)) {
+			bfq_arm_slice_timer(bfqd);
+			goto out;
+		} else if (bfq_may_expire_for_budg_timeout(bfqq))
+			bfq_bfqq_expire(bfqd, bfqq, false,
+					BFQ_BFQQ_BUDGET_TIMEOUT);
+		else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
+			 (bfqq->dispatched == 0 ||
+			  !bfq_bfqq_may_idle(bfqq)))
+			bfq_bfqq_expire(bfqd, bfqq, false,
+					BFQ_BFQQ_NO_MORE_REQUESTS);
+	}
+
+	if (!bfqd->rq_in_driver)
+		bfq_schedule_dispatch(bfqd);
+
+out:
+	return;
+}
+
+static int __bfq_may_queue(struct bfq_queue *bfqq)
+{
+	if (bfq_bfqq_wait_request(bfqq) && bfq_bfqq_must_alloc(bfqq)) {
+		bfq_clear_bfqq_must_alloc(bfqq);
+		return ELV_MQUEUE_MUST;
+	}
+
+	return ELV_MQUEUE_MAY;
+}
+
+static int bfq_may_queue(struct request_queue *q, unsigned int op)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct task_struct *tsk = current;
+	struct bfq_io_cq *bic;
+	struct bfq_queue *bfqq;
+
+	/*
+	 * Don't force setup of a queue from here, as a call to may_queue
+	 * does not necessarily imply that a request actually will be
+	 * queued. So just lookup a possibly existing queue, or return
+	 * 'may queue' if that fails.
+	 */
+	bic = bfq_bic_lookup(bfqd, tsk->io_context);
+	if (!bic)
+		return ELV_MQUEUE_MAY;
+
+	bfqq = bic_to_bfqq(bic, op_is_sync(op));
+	if (bfqq)
+		return __bfq_may_queue(bfqq);
+
+	return ELV_MQUEUE_MAY;
+}
+
+/*
+ * Queue lock held here.
+ */
+static void bfq_put_request(struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+
+	if (bfqq) {
+		const int rw = rq_data_dir(rq);
+
+		BUG_ON(!bfqq->allocated[rw]);
+		bfqq->allocated[rw]--;
+
+		rq->elv.priv[0] = NULL;
+		rq->elv.priv[1] = NULL;
+
+		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_request %p, %d",
+			     bfqq, bfqq->ref);
+		bfq_put_queue(bfqq);
+	}
+}
+
+/*
+ * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
+ * was the last process referring to that bfqq.
+ */
+static struct bfq_queue *
+bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
+{
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");
+
+	put_io_context(bic->icq.ioc);
+
+	if (bfqq_process_refs(bfqq) == 1) {
+		bfqq->pid = current->pid;
+		bfq_clear_bfqq_coop(bfqq);
+		bfq_clear_bfqq_split_coop(bfqq);
+		return bfqq;
+	}
+
+	bic_set_bfqq(bic, NULL, 1);
+
+	bfq_put_cooperator(bfqq);
+
+	bfq_put_queue(bfqq);
+	return NULL;
+}
+
+/*
+ * Allocate bfq data structures associated with this request.
+ */
+static int bfq_set_request(struct request_queue *q, struct request *rq,
+			   struct bio *bio, gfp_t gfp_mask)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
+	const int rw = rq_data_dir(rq);
+	const int is_sync = rq_is_sync(rq);
+	struct bfq_queue *bfqq;
+	unsigned long flags;
+	bool bfqq_already_existing = false, split = false;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+
+	if (!bic)
+		goto queue_fail;
+
+	bfq_check_ioprio_change(bic, bio);
+
+	bfq_bic_update_cgroup(bic, bio);
+
+new_queue:
+	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);
+		BUG_ON(!hlist_unhashed(&bfqq->burst_list_node));
+
+		bic_set_bfqq(bic, bfqq, is_sync);
+		if (split && is_sync) {
+			bfq_log_bfqq(bfqd, bfqq,
+				     "set_request: was_in_list %d "
+				     "was_in_large_burst %d "
+				     "large burst in progress %d",
+				     bic->was_in_burst_list,
+				     bic->saved_in_large_burst,
+				     bfqd->large_burst);
+
+			if ((bic->was_in_burst_list && bfqd->large_burst) ||
+			    bic->saved_in_large_burst) {
+				bfq_log_bfqq(bfqd, bfqq,
+					     "set_request: marking in "
+					     "large burst");
+				bfq_mark_bfqq_in_large_burst(bfqq);
+			} else {
+				bfq_log_bfqq(bfqd, bfqq,
+					     "set_request: clearing in "
+					     "large burst");
+				bfq_clear_bfqq_in_large_burst(bfqq);
+				if (bic->was_in_burst_list)
+					hlist_add_head(&bfqq->burst_list_node,
+						       &bfqd->burst_list);
+			}
+			bfqq->split_time = jiffies;
+		}
+	} else {
+		/* If the queue was seeky for too long, break it apart. */
+		if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
+			bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
+
+			/* Update bic before losing reference to bfqq */
+			if (bfq_bfqq_in_large_burst(bfqq))
+				bic->saved_in_large_burst = true;
+
+			bfqq = bfq_split_bfqq(bic, bfqq);
+			split = true;
+			if (!bfqq)
+				goto new_queue;
+			else
+				bfqq_already_existing = true;
+		}
+	}
+
+	bfqq->allocated[rw]++;
+	bfqq->ref++;
+	bfq_log_bfqq(bfqd, bfqq, "set_request: bfqq %p, %d", bfqq, bfqq->ref);
+
+	rq->elv.priv[0] = bic;
+	rq->elv.priv[1] = bfqq;
+
+	/*
+	 * If a bfq_queue has only one process reference, it is owned
+	 * by only one bfq_io_cq: we can set the bic field of the
+	 * bfq_queue to the address of that structure. Also, if the
+	 * queue has just been split, mark a flag so that the
+	 * information is available to the other scheduler hooks.
+	 */
+	if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) {
+		bfqq->bic = bic;
+		if (split) {
+			/*
+			 * If the queue has just been split from a shared
+			 * queue, restore the idle window and the possible
+			 * weight raising period.
+			 */
+			bfq_bfqq_resume_state(bfqq, bfqd, bic,
+					      bfqq_already_existing);
+		}
+	}
+
+	if (unlikely(bfq_bfqq_just_created(bfqq)))
+		bfq_handle_burst(bfqd, bfqq);
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	return 0;
+
+queue_fail:
+	bfq_schedule_dispatch(bfqd);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	return 1;
+}
+
+static void bfq_kick_queue(struct work_struct *work)
+{
+	struct bfq_data *bfqd =
+		container_of(work, struct bfq_data, unplug_work);
+	struct request_queue *q = bfqd->queue;
+
+	spin_lock_irq(q->queue_lock);
+	__blk_run_queue(q);
+	spin_unlock_irq(q->queue_lock);
+}
+
+/*
+ * 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;
+	unsigned long flags;
+	enum bfqq_expiration reason;
+
+	spin_lock_irqsave(bfqd->queue->queue_lock, flags);
+
+	bfqq = bfqd->in_service_queue;
+	/*
+	 * Theoretical race here: the in-service queue can be NULL or
+	 * different from the queue that was idling if the timer handler
+	 * spins on the queue_lock and 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_log_bfqq(bfqd, bfqq, "slice_timer expired");
+		bfq_clear_bfqq_wait_request(bfqq);
+
+		if (bfq_bfqq_budget_timeout(bfqq))
+			/*
+			 * Also here the queue can be safely expired
+			 * for budget timeout without wasting
+			 * guarantees
+			 */
+			reason = BFQ_BFQQ_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 = BFQ_BFQQ_TOO_IDLE;
+		else
+			goto schedule_dispatch;
+
+		bfq_bfqq_expire(bfqd, bfqq, true, reason);
+	}
+
+schedule_dispatch:
+	bfq_schedule_dispatch(bfqd);
+
+	spin_unlock_irqrestore(bfqd->queue->queue_lock, flags);
+	return HRTIMER_NORESTART;
+}
+
+static void bfq_shutdown_timer_wq(struct bfq_data *bfqd)
+{
+	hrtimer_cancel(&bfqd->idle_slice_timer);
+	cancel_work_sync(&bfqd->unplug_work);
+}
+
+static void __bfq_put_async_bfqq(struct bfq_data *bfqd,
+				 struct bfq_queue **bfqq_ptr)
+{
+	struct bfq_group *root_group = bfqd->root_group;
+	struct bfq_queue *bfqq = *bfqq_ptr;
+
+	bfq_log(bfqd, "put_async_bfqq: %p", bfqq);
+	if (bfqq) {
+		bfq_bfqq_move(bfqd, bfqq, 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 request_queue *q = bfqd->queue;
+	struct bfq_queue *bfqq, *n;
+
+	bfq_shutdown_timer_wq(bfqd);
+
+	spin_lock_irq(q->queue_lock);
+
+	BUG_ON(bfqd->in_service_queue);
+	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
+		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
+
+	spin_unlock_irq(q->queue_lock);
+
+	bfq_shutdown_timer_wq(bfqd);
+
+	BUG_ON(hrtimer_active(&bfqd->idle_slice_timer));
+
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	blkcg_deactivate_policy(q, &blkcg_policy_bfq);
+#else
+	bfq_put_async_queues(bfqd, bfqd->root_group);
+	kfree(bfqd->root_group);
+#endif
+
+	kfree(bfqd);
+}
+
+static void bfq_init_root_group(struct bfq_group *root_group,
+				struct bfq_data *bfqd)
+{
+	int i;
+
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	root_group->entity.parent = NULL;
+	root_group->my_entity = NULL;
+	root_group->bfqd = bfqd;
+#endif
+	root_group->rq_pos_tree = RB_ROOT;
+	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;
+
+	/*
+	 * 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);
+
+	/* oom_bfqq does not participate to bursts */
+	bfq_clear_bfqq_just_created(&bfqd->oom_bfqq);
+	/*
+	 * 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;
+
+	spin_lock_irq(q->queue_lock);
+	q->elevator = eq;
+	spin_unlock_irq(q->queue_lock);
+
+	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);
+
+	hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
+	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
+
+	bfqd->queue_weights_tree = RB_ROOT;
+	bfqd->group_weights_tree = RB_ROOT;
+
+	INIT_WORK(&bfqd->unplug_work, bfq_kick_queue);
+
+	INIT_LIST_HEAD(&bfqd->active_list);
+	INIT_LIST_HEAD(&bfqd->idle_list);
+	INIT_HLIST_HEAD(&bfqd->burst_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;
+
+	bfqd->bfq_large_burst_thresh = 8;
+	bfqd->bfq_burst_interval = msecs_to_jiffies(180);
+
+	bfqd->low_latency = true;
+
+	/*
+	 * Trade-off between responsiveness and fairness.
+	 */
+	bfqd->bfq_wr_coeff = 30;
+	bfqd->bfq_wr_rt_max_time = msecs_to_jiffies(300);
+	bfqd->bfq_wr_max_time = 0;
+	bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000);
+	bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500);
+	bfqd->bfq_wr_max_softrt_rate = 7000; /*
+					      * Approximate rate required
+					      * to playback or record a
+					      * high-definition compressed
+					      * video.
+					      */
+	bfqd->wr_busy_queues = 0;
+
+	/*
+	 * Begin by assuming, optimistically, that the device is a
+	 * high-speed one, and that its peak rate is equal to 2/3 of
+	 * the highest reference rate.
+	 */
+	bfqd->RT_prod = R_fast[blk_queue_nonrot(bfqd->queue)] *
+			T_fast[blk_queue_nonrot(bfqd->queue)];
+	bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
+	bfqd->device_speed = BFQ_BFQD_FAST;
+
+	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;
+}
+
+static ssize_t bfq_wr_max_time_show(struct elevator_queue *e, char *page)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+
+	return sprintf(page, "%d\n", bfqd->bfq_wr_max_time > 0 ?
+		       jiffies_to_msecs(bfqd->bfq_wr_max_time) :
+		       jiffies_to_msecs(bfq_wr_duration(bfqd)));
+}
+
+static ssize_t bfq_weights_show(struct elevator_queue *e, char *page)
+{
+	struct bfq_queue *bfqq;
+	struct bfq_data *bfqd = e->elevator_data;
+	ssize_t num_char = 0;
+
+	num_char += sprintf(page + num_char, "Tot reqs queued %d\n\n",
+			    bfqd->queued);
+
+	spin_lock_irq(bfqd->queue->queue_lock);
+
+	num_char += sprintf(page + num_char, "Active:\n");
+	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) {
+		num_char += sprintf(page + num_char,
+				    "pid%d: weight %hu, nr_queued %d %d, ",
+				    bfqq->pid,
+				    bfqq->entity.weight,
+				    bfqq->queued[0],
+				    bfqq->queued[1]);
+		num_char += sprintf(page + num_char,
+				    "dur %d/%u\n",
+				    jiffies_to_msecs(
+					    jiffies -
+					    bfqq->last_wr_start_finish),
+				    jiffies_to_msecs(bfqq->wr_cur_max_time));
+	}
+
+	num_char += sprintf(page + num_char, "Idle:\n");
+	list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) {
+		num_char += sprintf(page + num_char,
+				    "pid%d: weight %hu, dur %d/%u\n",
+				    bfqq->pid,
+				    bfqq->entity.weight,
+				    jiffies_to_msecs(jiffies -
+						     bfqq->last_wr_start_finish),
+				    jiffies_to_msecs(bfqq->wr_cur_max_time));
+	}
+
+	spin_unlock_irq(bfqd->queue->queue_lock);
+
+	return num_char;
+}
+
+#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);
+SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0);
+SHOW_FUNCTION(bfq_wr_coeff_show, bfqd->bfq_wr_coeff, 0);
+SHOW_FUNCTION(bfq_wr_rt_max_time_show, bfqd->bfq_wr_rt_max_time, 1);
+SHOW_FUNCTION(bfq_wr_min_idle_time_show, bfqd->bfq_wr_min_idle_time, 1);
+SHOW_FUNCTION(bfq_wr_min_inter_arr_async_show, bfqd->bfq_wr_min_inter_arr_async,
+	1);
+SHOW_FUNCTION(bfq_wr_max_softrt_rate_show, bfqd->bfq_wr_max_softrt_rate, 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);
+STORE_FUNCTION(bfq_wr_coeff_store, &bfqd->bfq_wr_coeff, 1, INT_MAX, 0);
+STORE_FUNCTION(bfq_wr_max_time_store, &bfqd->bfq_wr_max_time, 0, INT_MAX, 1);
+STORE_FUNCTION(bfq_wr_rt_max_time_store, &bfqd->bfq_wr_rt_max_time, 0, INT_MAX,
+		1);
+STORE_FUNCTION(bfq_wr_min_idle_time_store, &bfqd->bfq_wr_min_idle_time, 0,
+		INT_MAX, 1);
+STORE_FUNCTION(bfq_wr_min_inter_arr_async_store,
+		&bfqd->bfq_wr_min_inter_arr_async, 0, INT_MAX, 1);
+STORE_FUNCTION(bfq_wr_max_softrt_rate_store, &bfqd->bfq_wr_max_softrt_rate, 0,
+		INT_MAX, 0);
+#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
+
+/* do nothing for the moment */
+static ssize_t bfq_weights_store(struct elevator_queue *e,
+				    const char *page, size_t count)
+{
+	return count;
+}
+
+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_calc_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_calc_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;
+}
+
+static ssize_t bfq_low_latency_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 (__data == 0 && bfqd->low_latency != 0)
+		bfq_end_wr(bfqd);
+	bfqd->low_latency = __data;
+
+	return ret;
+}
+
+#define BFQ_ATTR(name) \
+	__ATTR(name, S_IRUGO|S_IWUSR, 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),
+	BFQ_ATTR(low_latency),
+	BFQ_ATTR(wr_coeff),
+	BFQ_ATTR(wr_max_time),
+	BFQ_ATTR(wr_rt_max_time),
+	BFQ_ATTR(wr_min_idle_time),
+	BFQ_ATTR(wr_min_inter_arr_async),
+	BFQ_ATTR(wr_max_softrt_rate),
+	BFQ_ATTR(weights),
+	__ATTR_NULL
+};
+
+static struct elevator_type iosched_bfq = {
+	.ops.sq = {
+		.elevator_merge_fn =		bfq_merge,
+		.elevator_merged_fn =		bfq_merged_request,
+		.elevator_merge_req_fn =	bfq_merged_requests,
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+		.elevator_bio_merged_fn =	bfq_bio_merged,
+#endif
+		.elevator_allow_bio_merge_fn =	bfq_allow_bio_merge,
+		.elevator_allow_rq_merge_fn =	bfq_allow_rq_merge,
+		.elevator_dispatch_fn =		bfq_dispatch_requests,
+		.elevator_add_req_fn =		bfq_insert_request,
+		.elevator_activate_req_fn =	bfq_activate_request,
+		.elevator_deactivate_req_fn =	bfq_deactivate_request,
+		.elevator_completed_req_fn =	bfq_completed_request,
+		.elevator_former_req_fn =	elv_rb_former_request,
+		.elevator_latter_req_fn =	elv_rb_latter_request,
+		.elevator_init_icq_fn =		bfq_init_icq,
+		.elevator_exit_icq_fn =		bfq_exit_icq,
+		.elevator_set_req_fn =		bfq_set_request,
+		.elevator_put_req_fn =		bfq_put_request,
+		.elevator_may_queue_fn =	bfq_may_queue,
+		.elevator_init_fn =		bfq_init_queue,
+		.elevator_exit_fn =		bfq_exit_queue,
+	},
+	.icq_size =		sizeof(struct bfq_io_cq),
+	.icq_align =		__alignof__(struct bfq_io_cq),
+	.elevator_attrs =	bfq_attrs,
+	.elevator_name =	"bfq-sq",
+	.elevator_owner =	THIS_MODULE,
+};
+
+#ifdef CONFIG_BFQ_SQ_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;
+	char msg[60] = "BFQ I/O-scheduler: v8r12";
+
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	ret = blkcg_policy_register(&blkcg_policy_bfq);
+	if (ret)
+		return ret;
+#endif
+
+	ret = -ENOMEM;
+	if (bfq_slab_setup())
+		goto err_pol_unreg;
+
+	/*
+	 * Times to load large popular applications for the typical
+	 * systems installed on the reference devices (see the
+	 * comments before the definitions of the next two
+	 * arrays). Actually, we use slightly slower values, as the
+	 * estimated peak rate tends to be smaller than the actual
+	 * peak rate.  The reason for this last fact is that estimates
+	 * are computed over much shorter time intervals than the long
+	 * intervals typically used for benchmarking. Why? First, to
+	 * adapt more quickly to variations. Second, because an I/O
+	 * scheduler cannot rely on a peak-rate-evaluation workload to
+	 * be run for a long time.
+	 */
+	T_slow[0] = msecs_to_jiffies(3500); /* actually 4 sec */
+	T_slow[1] = msecs_to_jiffies(6000); /* actually 6.5 sec */
+	T_fast[0] = msecs_to_jiffies(7000); /* actually 8 sec */
+	T_fast[1] = msecs_to_jiffies(2500); /* actually 3 sec */
+
+	/*
+	 * Thresholds that determine the switch between speed classes
+	 * (see the comments before the definition of the array
+	 * device_speed_thresh). These thresholds are biased towards
+	 * transitions to the fast class. This is safer than the
+	 * opposite bias. In fact, a wrong transition to the slow
+	 * class results in short weight-raising periods, because the
+	 * speed of the device then tends to be higher that the
+	 * reference peak rate. On the opposite end, a wrong
+	 * transition to the fast class tends to increase
+	 * weight-raising periods, because of the opposite reason.
+	 */
+	device_speed_thresh[0] = (4 * R_slow[0]) / 3;
+	device_speed_thresh[1] = (4 * R_slow[1]) / 3;
+
+	ret = elv_register(&iosched_bfq);
+	if (ret)
+		goto err_pol_unreg;
+
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	strcat(msg, " (with cgroups support)");
+#endif
+	pr_info("%s", msg);
+
+	return 0;
+
+err_pol_unreg:
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	blkcg_policy_unregister(&blkcg_policy_bfq);
+#endif
+	return ret;
+}
+
+static void __exit bfq_exit(void)
+{
+	elv_unregister(&iosched_bfq);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	blkcg_policy_unregister(&blkcg_policy_bfq);
+#endif
+	bfq_slab_kill();
+}
+
+module_init(bfq_init);
+module_exit(bfq_exit);
+
+MODULE_AUTHOR("Arianna Avanzini, Fabio Checconi, Paolo Valente");
+MODULE_LICENSE("GPL");
diff --git a/block/bfq.h b/block/bfq.h
new file mode 100644
index 000000000000..f5751ea59d98
--- /dev/null
+++ b/block/bfq.h
@@ -0,0 +1,948 @@
+/*
+ * BFQ v8r12 for 4.11.0: data structures and common functions prototypes.
+ *
+ * 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) 2015 Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2017 Paolo Valente <paolo.valente@linaro.org>
+ */
+
+#ifndef _BFQ_H
+#define _BFQ_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
+
+/*
+ * Soft real-time applications are extremely more latency sensitive
+ * than interactive ones. Over-raise the weight of the former to
+ * privilege them against the latter.
+ */
+#define BFQ_SOFTRT_WEIGHT_FACTOR	100
+
+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;
+
+	struct bfq_entity *first_idle;	/* idle entity with minimum F_i */
+	struct bfq_entity *last_idle;	/* idle entity with maximum F_i */
+
+	u64 vtime; /* scheduler virtual time */
+	/* 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 {
+	struct bfq_entity *in_service_entity;  /* entity in service */
+	/* head-of-the-line entity in the scheduler (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_weight_counter - counter of the number of all active entities
+ *                             with a given weight.
+ */
+struct bfq_weight_counter {
+	unsigned int weight; /* weight of the entities this counter refers to */
+	unsigned int num_active; /* nr of active entities with this weight */
+	/*
+	 * Weights tree member (see bfq_data's @queue_weights_tree and
+	 * @group_weights_tree)
+	 */
+	struct rb_node weights_node;
+};
+
+/**
+ * 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 {
+	struct rb_node rb_node; /* service_tree member */
+	/* pointer to the weight counter associated with this entity */
+	struct bfq_weight_counter *weight_counter;
+
+	/*
+	 * 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;
+
+	u64 finish; /* B-WF2Q+ finish timestamp (aka F_i) */
+	u64 start;  /* B-WF2Q+ start timestamp (aka S_i) */
+
+	/* 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;
+
+	unsigned int weight;	 /* weight of the queue */
+	unsigned int new_weight; /* next weight if a change is in progress */
+
+	/* original weight, used to implement weight boosting */
+	unsigned 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_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 or shared  between  cooperating
+ * processes. @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;
+
+	/*
+	 * Shared bfq_queue if queue is cooperating with one or more
+	 * other queues.
+	 */
+	struct bfq_queue *new_bfqq;
+	/* request-position tree member (see bfq_group's @rq_pos_tree) */
+	struct rb_node pos_node;
+	/* request-position tree root (see bfq_group's @rq_pos_tree) */
+	struct rb_root *pos_root;
+
+	/* 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 sync and async requests currently allocated */
+	int allocated[2];
+	/* 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;
+
+	unsigned int flags; /* status flags.*/
+
+	/* node for active/idle bfqq list inside parent bfqd */
+	struct list_head bfqq_list;
+
+	/* bit vector: a 1 for each seeky requests in history */
+	u32 seek_history;
+
+	/* node for the device's burst list */
+	struct hlist_node burst_list_node;
+
+	/* 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;
+
+	/*
+	 * Pointer to the bfq_io_cq owning the bfq_queue, set to %NULL
+	 * if the queue is shared.
+	 */
+	struct bfq_io_cq *bic;
+
+	/* current maximum weight-raising time for this queue */
+	unsigned long wr_cur_max_time;
+	/*
+	 * Minimum time instant such that, only if a new request is
+	 * enqueued after this time instant in an idle @bfq_queue with
+	 * no outstanding requests, then the task associated with the
+	 * queue it is deemed as soft real-time (see the comments on
+	 * the function bfq_bfqq_softrt_next_start())
+	 */
+	unsigned long soft_rt_next_start;
+	/*
+	 * Start time of the current weight-raising period if
+	 * the @bfq-queue is being weight-raised, otherwise
+	 * finish time of the last weight-raising period.
+	 */
+	unsigned long last_wr_start_finish;
+	/* factor by which the weight of this queue is multiplied */
+	unsigned int wr_coeff;
+	/*
+	 * Time of the last transition of the @bfq_queue from idle to
+	 * backlogged.
+	 */
+	unsigned long last_idle_bklogged;
+	/*
+	 * Cumulative service received from the @bfq_queue since the
+	 * last transition from idle to backlogged.
+	 */
+	unsigned long service_from_backlogged;
+	/*
+	 * Value of wr start time when switching to soft rt
+	 */
+	unsigned long wr_start_at_switch_to_srt;
+
+	unsigned long split_time; /* time of last split */
+};
+
+/**
+ * struct bfq_ttime - per process thinktime stats.
+ */
+struct bfq_ttime {
+	u64 last_end_request; /* completion time of last request */
+
+	u64 ttime_total; /* total process thinktime */
+	unsigned long ttime_samples; /* number of thinktime samples */
+	u64 ttime_mean; /* average process thinktime */
+
+};
+
+/**
+ * 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];
+	/* associated @bfq_ttime struct */
+	struct bfq_ttime ttime;
+	/* per (request_queue, blkcg) ioprio */
+	int ioprio;
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	uint64_t blkcg_serial_nr; /* the current blkcg serial */
+#endif
+
+	/*
+	 * Snapshot of the idle window before merging; taken to
+	 * remember this value while the queue is merged, so as to be
+	 * able to restore it in case of split.
+	 */
+	bool saved_idle_window;
+	/*
+	 * Same purpose as the previous two fields for the I/O bound
+	 * classification of a queue.
+	 */
+	bool saved_IO_bound;
+
+	/*
+	 * Same purpose as the previous fields for the value of the
+	 * field keeping the queue's belonging to a large burst
+	 */
+	bool saved_in_large_burst;
+	/*
+	 * True if the queue belonged to a burst list before its merge
+	 * with another cooperating queue.
+	 */
+	bool was_in_burst_list;
+
+	/*
+	 * Similar to previous fields: save wr information.
+	 */
+	unsigned long saved_wr_coeff;
+	unsigned long saved_last_wr_start_finish;
+	unsigned long saved_wr_start_at_switch_to_srt;
+	unsigned int saved_wr_cur_max_time;
+};
+
+enum bfq_device_speed {
+	BFQ_BFQD_FAST,
+	BFQ_BFQD_SLOW,
+};
+
+/**
+ * struct bfq_data - per-device data structure.
+ *
+ * All the fields are protected by the @queue lock.
+ */
+struct bfq_data {
+	/* request queue for the device */
+	struct request_queue *queue;
+
+	/* root bfq_group for the device */
+	struct bfq_group *root_group;
+
+	/*
+	 * rbtree of weight counters of @bfq_queues, sorted by
+	 * weight. Used to keep track of whether all @bfq_queues have
+	 * the same weight. The tree contains one counter for each
+	 * distinct weight associated to some active and not
+	 * weight-raised @bfq_queue (see the comments to the functions
+	 * bfq_weights_tree_[add|remove] for further details).
+	 */
+	struct rb_root queue_weights_tree;
+	/*
+	 * rbtree of non-queue @bfq_entity weight counters, sorted by
+	 * weight. Used to keep track of whether all @bfq_groups have
+	 * the same weight. The tree contains one counter for each
+	 * distinct weight associated to some active @bfq_group (see
+	 * the comments to the functions bfq_weights_tree_[add|remove]
+	 * for further details).
+	 */
+	struct rb_root group_weights_tree;
+
+	/*
+	 * Number of bfq_queues containing requests (including the
+	 * queue in service, even if it is idling).
+	 */
+	int busy_queues;
+	/* number of weight-raised busy @bfq_queues */
+	int wr_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;
+	/* delayed work to restart dispatching on the request queue */
+	struct work_struct unplug_work;
+
+	/* 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;
+
+	/* time of last request completion (ns) */
+	u64 last_completion;
+
+	/* time of first rq dispatch in current observation interval (ns) */
+	u64 first_dispatch;
+	/* time of last rq dispatch in current observation interval (ns) */
+	u64 last_dispatch;
+
+	/* beginning of the last budget */
+	ktime_t last_budget_start;
+	/* beginning of the last idle slice */
+	ktime_t last_idling_start;
+
+	/* number of samples in current observation interval */
+	int peak_rate_samples;
+	/* num of samples of seq dispatches in current observation interval */
+	u32 sequential_samples;
+	/* total num of sectors transferred in current observation interval */
+	u64 tot_sectors_dispatched;
+	/* max rq size seen during current observation interval (sectors) */
+	u32 last_rq_max_size;
+	/* time elapsed from first dispatch in current observ. interval (us) */
+	u64 delta_from_first;
+	/* current estimate of device peak rate */
+	u32 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;
+
+	/*
+	 * Last time at which a queue entered the current burst of
+	 * queues being activated shortly after each other; for more
+	 * details about this and the following parameters related to
+	 * a burst of activations, see the comments on the function
+	 * bfq_handle_burst.
+	 */
+	unsigned long last_ins_in_burst;
+	/*
+	 * Reference time interval used to decide whether a queue has
+	 * been activated shortly after @last_ins_in_burst.
+	 */
+	unsigned long bfq_burst_interval;
+	/* number of queues in the current burst of queue activations */
+	int burst_size;
+
+	/* common parent entity for the queues in the burst */
+	struct bfq_entity *burst_parent_entity;
+	/* Maximum burst size above which the current queue-activation
+	 * burst is deemed as 'large'.
+	 */
+	unsigned long bfq_large_burst_thresh;
+	/* true if a large queue-activation burst is in progress */
+	bool large_burst;
+	/*
+	 * Head of the burst list (as for the above fields, more
+	 * details in the comments on the function bfq_handle_burst).
+	 */
+	struct hlist_head burst_list;
+
+	/* if set to true, low-latency heuristics are enabled */
+	bool low_latency;
+	/*
+	 * Maximum factor by which the weight of a weight-raised queue
+	 * is multiplied.
+	 */
+	unsigned int bfq_wr_coeff;
+	/* maximum duration of a weight-raising period (jiffies) */
+	unsigned int bfq_wr_max_time;
+
+	/* Maximum weight-raising duration for soft real-time processes */
+	unsigned int bfq_wr_rt_max_time;
+	/*
+	 * Minimum idle period after which weight-raising may be
+	 * reactivated for a queue (in jiffies).
+	 */
+	unsigned int bfq_wr_min_idle_time;
+	/*
+	 * Minimum period between request arrivals after which
+	 * weight-raising may be reactivated for an already busy async
+	 * queue (in jiffies).
+	 */
+	unsigned long bfq_wr_min_inter_arr_async;
+
+	/* Max service-rate for a soft real-time queue, in sectors/sec */
+	unsigned int bfq_wr_max_softrt_rate;
+	/*
+	 * Cached value of the product R*T, used for computing the
+	 * maximum duration of weight raising automatically.
+	 */
+	u64 RT_prod;
+	/* device-speed class for the low-latency heuristic */
+	enum bfq_device_speed device_speed;
+
+	/* fallback dummy bfqq for extreme OOM conditions */
+	struct bfq_queue oom_bfqq;
+};
+
+enum bfqq_state_flags {
+	BFQ_BFQQ_FLAG_just_created = 0,	/* queue just allocated */
+	BFQ_BFQQ_FLAG_busy,		/* has requests or is in service */
+	BFQ_BFQQ_FLAG_wait_request,	/* waiting for a request */
+	BFQ_BFQQ_FLAG_non_blocking_wait_rq, /*
+					     * waiting for a request
+					     * without idling the device
+					     */
+	BFQ_BFQQ_FLAG_must_alloc,	/* must be allowed rq alloc */
+	BFQ_BFQQ_FLAG_fifo_expire,	/* FIFO checked in this slice */
+	BFQ_BFQQ_FLAG_idle_window,	/* slice idling enabled */
+	BFQ_BFQQ_FLAG_sync,		/* synchronous queue */
+	BFQ_BFQQ_FLAG_IO_bound,		/*
+					 * bfqq has timed-out at least once
+					 * having consumed at most 2/10 of
+					 * its budget
+					 */
+	BFQ_BFQQ_FLAG_in_large_burst,	/*
+					 * bfqq activated in a large burst,
+					 * see comments to bfq_handle_burst.
+					 */
+	BFQ_BFQQ_FLAG_softrt_update,	/*
+					 * may need softrt-next-start
+					 * update
+					 */
+	BFQ_BFQQ_FLAG_coop,		/* bfqq is shared */
+	BFQ_BFQQ_FLAG_split_coop	/* shared bfqq will be split */
+};
+
+#define BFQ_BFQQ_FNS(name)						\
+static void bfq_mark_bfqq_##name(struct bfq_queue *bfqq)		\
+{									\
+	(bfqq)->flags |= (1 << BFQ_BFQQ_FLAG_##name);			\
+}									\
+static void bfq_clear_bfqq_##name(struct bfq_queue *bfqq)		\
+{									\
+	(bfqq)->flags &= ~(1 << BFQ_BFQQ_FLAG_##name);			\
+}									\
+static int bfq_bfqq_##name(const struct bfq_queue *bfqq)		\
+{									\
+	return ((bfqq)->flags & (1 << BFQ_BFQQ_FLAG_##name)) != 0;	\
+}
+
+BFQ_BFQQ_FNS(just_created);
+BFQ_BFQQ_FNS(busy);
+BFQ_BFQQ_FNS(wait_request);
+BFQ_BFQQ_FNS(non_blocking_wait_rq);
+BFQ_BFQQ_FNS(must_alloc);
+BFQ_BFQQ_FNS(fifo_expire);
+BFQ_BFQQ_FNS(idle_window);
+BFQ_BFQQ_FNS(sync);
+BFQ_BFQQ_FNS(IO_bound);
+BFQ_BFQQ_FNS(in_large_burst);
+BFQ_BFQQ_FNS(coop);
+BFQ_BFQQ_FNS(split_coop);
+BFQ_BFQQ_FNS(softrt_update);
+#undef BFQ_BFQQ_FNS
+
+/* Logging facilities. */
+#ifdef CONFIG_BFQ_REDIRECT_TO_CONSOLE
+
+static const char *checked_dev_name(const struct device *dev)
+{
+	static const char nodev[] = "nodev";
+
+	if (dev)
+		return dev_name(dev);
+
+	return nodev;
+}
+
+#ifdef CONFIG_BFQ_SQ_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];						\
+									\
+	assert_spin_locked((bfqd)->queue->queue_lock);			\
+	blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
+	pr_crit("%s bfq%d%c %s " fmt "\n", 				\
+		checked_dev_name((bfqd)->queue->backing_dev_info->dev),	\
+		(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));		\
+	pr_crit("%s %s " fmt "\n",					\
+	checked_dev_name((bfqd)->queue->backing_dev_info->dev),		\
+	__pbuf, ##args);						\
+} while (0)
+
+#else /* CONFIG_BFQ_SQ_GROUP_IOSCHED */
+
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...)				\
+	pr_crit("%s bfq%d%c " fmt "\n",					\
+		checked_dev_name((bfqd)->queue->backing_dev_info->dev),	\
+		(bfqq)->pid, bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
+		##args)
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)		do {} while (0)
+
+#endif /* CONFIG_BFQ_SQ_GROUP_IOSCHED */
+
+#define bfq_log(bfqd, fmt, args...) \
+	pr_crit("%s bfq " fmt "\n",					\
+		checked_dev_name((bfqd)->queue->backing_dev_info->dev),	\
+		##args)
+
+#else /* CONFIG_BFQ_REDIRECT_TO_CONSOLE */
+#ifdef CONFIG_BFQ_SQ_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];						\
+									\
+	assert_spin_locked((bfqd)->queue->queue_lock);			\
+	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_SQ_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_SQ_GROUP_IOSCHED */
+
+#define bfq_log(bfqd, fmt, args...) \
+	blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)
+#endif /* CONFIG_BFQ_REDIRECT_TO_CONSOLE */
+
+/* Expiration reasons. */
+enum bfqq_expiration {
+	BFQ_BFQQ_TOO_IDLE = 0,		/*
+					 * queue has been idling for
+					 * too long
+					 */
+	BFQ_BFQQ_BUDGET_TIMEOUT,	/* budget took too long to be used */
+	BFQ_BFQQ_BUDGET_EXHAUSTED,	/* budget consumed */
+	BFQ_BFQQ_NO_MORE_REQUESTS,	/* the queue has no more requests */
+	BFQ_BFQQ_PREEMPTED		/* preemption in progress */
+};
+
+
+struct bfqg_stats {
+#ifdef CONFIG_BFQ_SQ_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
+};
+
+#ifdef CONFIG_BFQ_SQ_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 int 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.
+ * @active_entities: number of active entities belonging to the group;
+ *                   unused for the root group. Used to know whether there
+ *                   are groups with more than one active @bfq_entity
+ *                   (see the comments to the function
+ *                   bfq_bfqq_may_idle()).
+ * @rq_pos_tree: rbtree sorted by next_request position, used when
+ *               determining if two or more queues have interleaving
+ *               requests (see bfq_find_close_cooperator()).
+ *
+ * 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;
+
+	int active_entities;
+
+	struct rb_root rq_pos_tree;
+
+	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;
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	unsigned int idx = bfq_class_idx(entity);
+
+	BUG_ON(idx >= BFQ_IOPRIO_CLASSES);
+	BUG_ON(sched_data == NULL);
+
+	if (bfqq)
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+			     "entity_service_tree %p %d",
+			     sched_data->service_tree + idx, idx);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	else {
+		struct bfq_group *bfqg =
+			container_of(entity, struct bfq_group, entity);
+
+		bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
+			     "entity_service_tree %p %d",
+			     sched_data->service_tree + idx, idx);
+	}
+#endif
+	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;
+}
+
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+
+static struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
+{
+	struct bfq_entity *group_entity = bfqq->entity.parent;
+
+	if (!group_entity)
+		group_entity = &bfqq->bfqd->root_group->entity;
+
+	return container_of(group_entity, struct bfq_group, entity);
+}
+
+#else
+
+static struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
+{
+	return bfqq->bfqd->root_group;
+}
+
+#endif
+
+static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio);
+static void bfq_put_queue(struct bfq_queue *bfqq);
+static void bfq_dispatch_insert(struct request_queue *q, struct request *rq);
+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_end_wr_async_queues(struct bfq_data *bfqd,
+				    struct bfq_group *bfqg);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
+#endif
+static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+
+#endif /* _BFQ_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8da66379f7ea..bf000c58644b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -54,7 +54,7 @@ struct blk_stat_callback;
  * Maximum number of blkcg policies allowed to be registered concurrently.
  * Defined here to simplify include dependency.
  */
-#define BLKCG_MAX_POLS		3
+#define BLKCG_MAX_POLS		4
 
 typedef void (rq_end_io_fn)(struct request *, blk_status_t);
 

From 9916fed6c89c61a2b26053be04501784570bbec8 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Thu, 20 Jul 2017 10:46:39 +0200
Subject: [PATCH 02/51] Add extra checks related to entity scheduling

- extra checks related to ioprioi-class changes
- specific check on st->idle in __bfq_requeue_entity

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-sched.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/block/bfq-sched.c b/block/bfq-sched.c
index ac8991bca9fa..5ddf9af4261e 100644
--- a/block/bfq-sched.c
+++ b/block/bfq-sched.c
@@ -812,6 +812,7 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
 		}
 #endif
 
+		BUG_ON(entity->tree && update_class_too);
 		BUG_ON(old_st->wsum < entity->weight);
 		old_st->wsum -= entity->weight;
 
@@ -883,8 +884,10 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
 
 		new_st->wsum += entity->weight;
 
-		if (new_st != old_st)
+		if (new_st != old_st) {
+			BUG_ON(!update_class_too);
 			entity->start = new_st->vtime;
+		}
 	}
 
 	return new_st;
@@ -993,6 +996,7 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
 	 * tree, then it is safe to invoke next function with the last
 	 * parameter set (see the comments on the function).
 	 */
+	BUG_ON(entity->tree);
 	st = __bfq_entity_update_weight_prio(st, entity, true);
 	bfq_calc_finish(entity, entity->budget);
 
@@ -1113,9 +1117,11 @@ static void __bfq_activate_entity(struct bfq_entity *entity,
 		 * check for that.
 		 */
 		bfq_idle_extract(st, entity);
+		BUG_ON(entity->tree);
 		entity->start = bfq_gt(min_vstart, entity->finish) ?
 			min_vstart : entity->finish;
 	} else {
+		BUG_ON(entity->tree);
 		/*
 		 * The finish time of the entity may be invalid, and
 		 * it is in the past for sure, otherwise the queue
@@ -1203,6 +1209,7 @@ static void __bfq_requeue_entity(struct bfq_entity *entity)
 		 */
 		bfq_calc_finish(entity, entity->service);
 		entity->start = entity->finish;
+		BUG_ON(entity->tree && entity->tree == &st->idle);
 		BUG_ON(entity->tree && entity->tree != &st->active);
 		/*
 		 * In addition, if the entity had more than one child

From 8f5b2c25dcbe31dda524e85b921b3aa1fe11d111 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Fri, 21 Jul 2017 12:08:57 +0200
Subject: [PATCH 03/51] block, bfq: reset in_service_entity if it becomes idle

BFQ implements hierarchical scheduling by representing each group of
queues with a generic parent entity. For each parent entity, BFQ
maintains an in_service_entity pointer: if one of the child entities
happens to be in service, in_service_entity points to it.  The
resetting of these pointers happens only on queue expirations: when
the in-service queue is expired, i.e., stops to be the queue in
service, BFQ resets all in_service_entity pointers along the
parent-entity path from this queue to the root entity.

Functions handling the scheduling of entities assume, naturally, that
in-service entities are active, i.e., have pending I/O requests (or,
as a special case, even if they have no pending requests, they are
expected to receive a new request very soon, with the scheduler idling
the storage device while waiting for such an event). Unfortunately,
the above resetting scheme of the in_service_entity pointers may cause
this assumption to be violated.  For example, the in-service queue may
happen to remain without requests because of a request merge. In this
case the queue does become idle, and all related data structures are
updated accordingly. But in_service_entity still points to the queue
in the parent entity. This inconsistency may even propagate to
higher-level parent entities, if they happen to become idle as well,
as a consequence of the leaf queue becoming idle. For this queue and
parent entities, scheduling functions have an undefined behaviour,
and, as reported, may easily lead to kernel crashes or hangs.

This commit addresses this issue by simply resetting the
in_service_entity field also when it is detected to point to an entity
becoming idle (regardless of why the entity becomes idle).

Reported-by: Laurentiu Nicola <lnicola@dend.ro>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Laurentiu Nicola <lnicola@dend.ro>
---
 block/bfq-sched.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/block/bfq-sched.c b/block/bfq-sched.c
index 5ddf9af4261e..a07a06eb5c72 100644
--- a/block/bfq-sched.c
+++ b/block/bfq-sched.c
@@ -1336,8 +1336,10 @@ static bool __bfq_deactivate_entity(struct bfq_entity *entity,
 
 	BUG_ON(is_in_service && entity->tree && entity->tree != &st->active);
 
-	if (is_in_service)
+	if (is_in_service) {
 		bfq_calc_finish(entity, entity->service);
+		sd->in_service_entity = NULL;
+	}
 
 	if (entity->tree == &st->active)
 		bfq_active_extract(st, entity);

From 600ea668e2d340c95724bcf981d88812d6900342 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Fri, 28 Jul 2017 21:09:51 +0200
Subject: [PATCH 04/51] block, bfq: consider also in_service_entity to state
 whether an entity is active

Groups of BFQ queues are represented by generic entities in BFQ. When
a queue belonging to a parent entity is deactivated, the parent entity
may need to be deactivated too, in case the deactivated queue was the
only active queue for the parent entity. This deactivation may need to
be propagated upwards if the entity belongs, in its turn, to a further
higher-level entity, and so on. In particular, the upward propagation
of deactivation stops at the first parent entity that remains active
even if one of its child entities has been deactivated.

To decide whether the last non-deactivation condition holds for a
parent entity, BFQ checks whether the field next_in_service is still
not NULL for the parent entity, after the deactivation of one of its
child entity. If it is not NULL, then there are certainly other active
entities in the parent entity, and deactivations can stop.

Unfortunately, this check misses a corner case: if in_service_entity
is not NULL, then next_in_service may happen to be NULL, although the
parent entity is evidently active. This happens if: 1) the entity
pointed by in_service_entity is the only active entity in the parent
entity, and 2) according to the definition of next_in_service, the
in_service_entity cannot be considered as next_in_service. See the
comments on the definition of next_in_service for details on this
second point.

Hitting the above corner case causes crashes.

To address this issue, this commit:
1) Extends the above check on only next_in_service to controlling both
next_in_service and in_service_entity (if any of them is not NULL,
then no further deactivation is performed)
2) Improves the (important) comments on how next_in_service is defined
and updated; in particular it fixes a few rather obscure paragraphs

Reported-by: Eric Wheeler <bfq-sched@lists.ewheeler.net>
Reported-by: Rick Yiu <rick_yiu@htc.com>
Reported-by: Tom X Nguyen <tom81094@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Eric Wheeler <bfq-sched@lists.ewheeler.net>
Tested-by: Rick Yiu <rick_yiu@htc.com>
Tested-by: Laurentiu Nicola <lnicola@dend.ro>
Tested-by: Tom X Nguyen <tom81094@gmail.com>
---
 block/bfq-sched.c | 140 ++++++++++++++++++++++++++++++------------------------
 block/bfq.h       |  23 +++++++--
 2 files changed, 95 insertions(+), 68 deletions(-)

diff --git a/block/bfq-sched.c b/block/bfq-sched.c
index a07a06eb5c72..5c0f9290a79c 100644
--- a/block/bfq-sched.c
+++ b/block/bfq-sched.c
@@ -196,21 +196,23 @@ static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
 
 /*
  * This function tells whether entity stops being a candidate for next
- * service, according to the following logic.
+ * service, according to the restrictive definition of the field
+ * next_in_service. In particular, this function is invoked for an
+ * entity that is about to be set in service.
  *
- * 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.
+ * If entity is a queue, then the entity is no longer a candidate for
+ * next service according to the that definition, because entity is
+ * about to become the in-service queue. This function then returns
+ * true if entity is a queue.
  *
- * In contrast, the entity could stil be a candidate for next service
- * if it is not a queue, and has more than one child. In fact, even if
- * one of its children is about to be set in service, other children
- * may still be the next to serve. As a consequence, a non-queue
- * entity is not a candidate for next-service only if it has only one
- * child. And only if this condition holds, then the function returns
- * true for a non-queue entity.
+ * In contrast, entity could still be a candidate for next service if
+ * it is not a queue, and has more than one active child. In fact,
+ * even if one of its children is about to be set in service, other
+ * active children may still be the next to serve, for the parent
+ * entity, even according to the above definition. As a consequence, a
+ * non-queue entity is not a candidate for next-service only if it has
+ * only one active child. And only if this condition holds, then this
+ * function returns true for a non-queue entity.
  */
 static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
 {
@@ -223,6 +225,18 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
 
 	BUG_ON(bfqg == ((struct bfq_data *)(bfqg->bfqd))->root_group);
 	BUG_ON(bfqg->active_entities == 0);
+	/*
+	 * The field active_entities does not always contain the
+	 * actual number of active children entities: it happens to
+	 * not account for the in-service entity in case the latter is
+	 * removed from its active tree (which may get done after
+	 * invoking the function bfq_no_longer_next_in_service in
+	 * bfq_get_next_queue). Fortunately, here, i.e., while
+	 * bfq_no_longer_next_in_service is not yet completed in
+	 * bfq_get_next_queue, bfq_active_extract has not yet been
+	 * invoked, and thus active_entities still coincides with the
+	 * actual number of active entities.
+	 */
 	if (bfqg->active_entities == 1)
 		return true;
 
@@ -1089,7 +1103,7 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
  * 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
+ * inserts entity into its active tree, ater possibly extracting it
  * from its idle tree.
  */
 static void __bfq_activate_entity(struct bfq_entity *entity,
@@ -1213,7 +1227,7 @@ static void __bfq_requeue_entity(struct bfq_entity *entity)
 		BUG_ON(entity->tree && entity->tree != &st->active);
 		/*
 		 * In addition, if the entity had more than one child
-		 * when set in service, then was not extracted from
+		 * when set in service, then it 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
@@ -1221,9 +1235,8 @@ static void __bfq_requeue_entity(struct bfq_entity *entity)
 		 * 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.
+		 * 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);
@@ -1270,9 +1283,9 @@ static void __bfq_activate_requeue_entity(struct bfq_entity *entity,
 
 
 /**
- * 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.
+ * bfq_activate_requeue_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
@@ -1308,9 +1321,9 @@ static void bfq_activate_requeue_entity(struct bfq_entity *entity,
  * @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
+ * Deactivates an entity, independently of 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
+ * from that tree, and if necessary and allowed, puts it into the idle
  * tree.
  */
 static bool __bfq_deactivate_entity(struct bfq_entity *entity,
@@ -1359,7 +1372,7 @@ static bool __bfq_deactivate_entity(struct bfq_entity *entity,
 /**
  * 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
+ * @ins_into_idle_tree: true if the entity can be put into the idle tree
  */
 static void bfq_deactivate_entity(struct bfq_entity *entity,
 				  bool ins_into_idle_tree,
@@ -1406,16 +1419,29 @@ static void bfq_deactivate_entity(struct bfq_entity *entity,
 			 */
 			bfq_update_next_in_service(sd, NULL);
 
-		if (sd->next_in_service) {
+		if (sd->next_in_service || sd->in_service_entity) {
 			/*
-			 * 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.
+			 * The parent entity is still active, because
+			 * either next_in_service or in_service_entity
+			 * 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.
+			 *
+			 * NOTE If in_service_entity is not NULL, then
+			 * next_in_service may happen to be NULL,
+			 * although the parent entity is evidently
+			 * active. This happens if 1) the entity
+			 * pointed by in_service_entity is the only
+			 * active entity in the parent entity, and 2)
+			 * according to the definition of
+			 * next_in_service, the in_service_entity
+			 * cannot be considered as
+			 * next_in_service. See the comments on the
+			 * definition of next_in_service for details.
 			 */
 			BUG_ON(sd->next_in_service == entity);
+			BUG_ON(sd->in_service_entity == entity);
 			break;
 		}
 
@@ -1806,45 +1832,33 @@ static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
 
 		/*
 		 * 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.
+		 * service, then it must be extracted from its active
+		 * tree, so as to make sure that it won't be
+		 * considered when computing next_in_service. See the
+		 * comments on the function
+		 * bfq_no_longer_next_in_service() for details.
 		 */
 		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.
+		 * Even if entity is not to be extracted according to
+		 * the above check, a descendant entity may get
+		 * extracted in one of the next iterations of this
+		 * loop. Such an event could cause a change in
+		 * next_in_service for the level of the descendant
+		 * entity, and thus possibly back to this level.
 		 *
-		 * 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.
+		 * However, we cannot perform the resulting needed
+		 * update of next_in_service for this level before the
+		 * end of the whole 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.
 		 */
 
 		/* Log some information */
diff --git a/block/bfq.h b/block/bfq.h
index f5751ea59d98..ebd9688b9f61 100644
--- a/block/bfq.h
+++ b/block/bfq.h
@@ -68,17 +68,30 @@ struct bfq_service_tree {
  *
  * 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.
+ * intermediate queue in a hierarchical setup.
  *
  * 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.
+ *
+ * The schedule is implemented by the service trees, plus the field
+ * @next_in_service, which points to the entity on the active trees
+ * that will be served next, if 1) no changes in the schedule occurs
+ * before the current in-service entity is expired, 2) the in-service
+ * queue becomes idle when it expires, and 3) if the entity pointed by
+ * in_service_entity is not a queue, then the in-service child entity
+ * of the entity pointed by in_service_entity becomes idle on
+ * expiration. This peculiar definition allows for the following
+ * optimization, not yet exploited: while a given entity is still in
+ * service, we already know which is the best candidate for next
+ * service among the other active entitities in the same parent
+ * entity. We can then quickly compare the timestamps of the
+ * in-service entity with those of such best candidate.
+ *
+ * All the fields are protected by the queue lock of the containing
+ * bfqd.
  */
 struct bfq_sched_data {
 	struct bfq_entity *in_service_entity;  /* entity in service */

From 6b5effd10bc6711a862e7cbd7cd2dd0146defa01 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Thu, 4 May 2017 10:53:43 +0200
Subject: [PATCH 05/51] block, bfq: improve and refactor throughput-boosting
 logic

When a queue associated with a process remains empty, there are cases
where throughput gets boosted if the device is idled to await the
arrival of a new I/O request for that queue. Currently, BFQ assumes
that one of these cases is when the device has no internal queueing
(regardless of the properties of the I/O being served). Unfortunately,
this condition has proved to be too general. So, this commit refines it
as "the device has no internal queueing and is rotational".

This refinement provides a significant throughput boost with random
I/O, on flash-based storage without internal queueing. For example, on
a HiKey board, throughput increases by up to 125%, growing, e.g., from
6.9MB/s to 15.6MB/s with two or three random readers in parallel.

This commit also refactors the code related to device idling, for the
following reason. Finding the change that provides the above large
improvement has been slightly more difficult than it had to be,
because the logic that decides whether to idle the device is still
scattered across three functions. Almost all of the logic is in the
function bfq_bfqq_may_idle, but (1) part of the decision is made in
bfq_update_idle_window, and (2) the function bfq_bfqq_must_idle may
switch off idling regardless of the output of bfq_bfqq_may_idle. In
addition, both bfq_update_idle_window and bfq_bfqq_must_idle make
their decisions as a function of parameters that are used, for similar
purposes, also in bfq_bfqq_may_idle. This commit addresses this issue
by moving all the logic into bfq_bfqq_may_idle.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Luca Miccio <lucmiccio@gmail.com>
---
 block/bfq-sq-iosched.c | 141 +++++++++++++++++++++++++++----------------------
 block/bfq.h            |  12 ++---
 2 files changed, 83 insertions(+), 70 deletions(-)

diff --git a/block/bfq-sq-iosched.c b/block/bfq-sq-iosched.c
index 65e7c7e77f3c..30d019fc67e0 100644
--- a/block/bfq-sq-iosched.c
+++ b/block/bfq-sq-iosched.c
@@ -684,10 +684,10 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 	unsigned int old_wr_coeff;
 	bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq);
 
-	if (bic->saved_idle_window)
-		bfq_mark_bfqq_idle_window(bfqq);
+	if (bic->saved_has_short_ttime)
+		bfq_mark_bfqq_has_short_ttime(bfqq);
 	else
-		bfq_clear_bfqq_idle_window(bfqq);
+		bfq_clear_bfqq_has_short_ttime(bfqq);
 
 	if (bic->saved_IO_bound)
 		bfq_mark_bfqq_IO_bound(bfqq);
@@ -2047,7 +2047,7 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	if (!bic)
 		return;
 
-	bic->saved_idle_window = bfq_bfqq_idle_window(bfqq);
+	bic->saved_has_short_ttime = bfq_bfqq_has_short_ttime(bfqq);
 	bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
 	bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
 	bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
@@ -3214,9 +3214,9 @@ static void bfq_bfqq_expire(struct bfq_data *bfqd,
 	}
 
 	bfq_log_bfqq(bfqd, bfqq,
-		"expire (%d, slow %d, num_disp %d, idle_win %d, weight %d)",
+		"expire (%d, slow %d, num_disp %d, short_ttime %d, weight %d)",
 		     reason, slow, bfqq->dispatched,
-		     bfq_bfqq_idle_window(bfqq), entity->weight);
+		     bfq_bfqq_has_short_ttime(bfqq), entity->weight);
 
 	/*
 	 * Increase, decrease or leave budget unchanged according to
@@ -3298,7 +3298,10 @@ static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
 static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
 {
 	struct bfq_data *bfqd = bfqq->bfqd;
-	bool idling_boosts_thr, idling_boosts_thr_without_issues,
+	bool rot_without_queueing =
+		!blk_queue_nonrot(bfqd->queue) && !bfqd->hw_tag,
+		bfqq_sequential_and_IO_bound,
+		idling_boosts_thr, idling_boosts_thr_without_issues,
 		idling_needed_for_service_guarantees,
 		asymmetric_scenario;
 
@@ -3306,27 +3309,44 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
 		return true;
 
 	/*
+	 * Idling is performed only if slice_idle > 0. In addition, we
+	 * do not idle if
+	 * (a) bfqq is async
+	 * (b) bfqq is in the idle io prio class: in this case we do
+	 * not idle because we want to minimize the bandwidth that
+	 * queues in this class can steal to higher-priority queues
+	 */
+	if (bfqd->bfq_slice_idle == 0 || !bfq_bfqq_sync(bfqq) ||
+	   bfq_class_idle(bfqq))
+		return false;
+
+	bfqq_sequential_and_IO_bound = !BFQQ_SEEKY(bfqq) &&
+		bfq_bfqq_IO_bound(bfqq) && bfq_bfqq_has_short_ttime(bfqq);
+	/*
 	 * The next variable takes into account the cases where idling
 	 * boosts the throughput.
 	 *
 	 * The value of the variable is computed considering, first, that
 	 * idling is virtually always beneficial for the throughput if:
-	 * (a) the device is not NCQ-capable, or
-	 * (b) regardless of the presence of NCQ, the device is rotational
-	 *     and the request pattern for bfqq is I/O-bound and sequential.
+	 * (a) the device is not NCQ-capable and rotational, or
+	 * (b) regardless of the presence of NCQ, the device is rotational and
+	 *     the request pattern for bfqq is I/O-bound and sequential, or
+	 * (c) regardless of whether it is rotational, the device is
+	 *     not NCQ-capable and the request pattern for bfqq is
+	 *     I/O-bound and sequential.
 	 *
 	 * Secondly, and in contrast to the above item (b), idling an
 	 * NCQ-capable flash-based device would not boost the
 	 * throughput even with sequential I/O; rather it would lower
 	 * the throughput in proportion to how fast the device
 	 * is. Accordingly, the next variable is true if any of the
-	 * above conditions (a) and (b) is true, and, in particular,
-	 * happens to be false if bfqd is an NCQ-capable flash-based
-	 * device.
+	 * above conditions (a), (b) or (c) is true, and, in
+	 * particular, happens to be false if bfqd is an NCQ-capable
+	 * flash-based device.
 	 */
-	idling_boosts_thr = !bfqd->hw_tag ||
-		(!blk_queue_nonrot(bfqd->queue) && bfq_bfqq_IO_bound(bfqq) &&
-		 bfq_bfqq_idle_window(bfqq));
+	idling_boosts_thr = rot_without_queueing ||
+		((!blk_queue_nonrot(bfqd->queue) || !bfqd->hw_tag) &&
+		 bfqq_sequential_and_IO_bound);
 
 	/*
 	 * The value of the next variable,
@@ -3497,12 +3517,10 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
 		asymmetric_scenario && !bfq_bfqq_in_large_burst(bfqq);
 
 	/*
-	 * We have now all 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 either boosts the throughput (without issues), or
-	 *    is necessary to preserve service guarantees.
+	 * We have now all the components we need to compute the
+	 * return value of the function, which is true only if idling
+	 * either boosts the throughput (without issues), or is
+	 * necessary to preserve service guarantees.
 	 */
 	bfq_log_bfqq(bfqd, bfqq, "may_idle: sync %d idling_boosts_thr %d",
 		     bfq_bfqq_sync(bfqq), idling_boosts_thr);
@@ -3514,9 +3532,8 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
 		     bfq_bfqq_IO_bound(bfqq),
 		     idling_needed_for_service_guarantees);
 
-	return bfq_bfqq_sync(bfqq) &&
-		(idling_boosts_thr_without_issues ||
-		 idling_needed_for_service_guarantees);
+	return idling_boosts_thr_without_issues ||
+		idling_needed_for_service_guarantees;
 }
 
 /*
@@ -3532,10 +3549,7 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
  */
 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);
+	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_may_idle(bfqq);
 }
 
 /*
@@ -3994,7 +4008,6 @@ static void bfq_set_next_ioprio_data(struct bfq_queue *bfqq,
 	case IOPRIO_CLASS_IDLE:
 		bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE;
 		bfqq->new_ioprio = 7;
-		bfq_clear_bfqq_idle_window(bfqq);
 		break;
 	}
 
@@ -4058,8 +4071,14 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		bfq_set_next_ioprio_data(bfqq, bic);
 
 	if (is_sync) {
+		/*
+		 * No need to mark as has_short_ttime if in
+		 * idle_class, because no device idling is performed
+		 * for queues in idle class
+		 */
 		if (!bfq_class_idle(bfqq))
-			bfq_mark_bfqq_idle_window(bfqq);
+			/* tentatively mark as has_short_ttime */
+			bfq_mark_bfqq_has_short_ttime(bfqq);
 		bfq_mark_bfqq_sync(bfqq);
 		bfq_mark_bfqq_just_created(bfqq);
 	} else
@@ -4195,18 +4214,19 @@ bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		 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)
+static void bfq_update_has_short_ttime(struct bfq_data *bfqd,
+				       struct bfq_queue *bfqq,
+				       struct bfq_io_cq *bic)
 {
-	int enable_idle;
+	bool has_short_ttime = true;
 
-	/* Don't idle for async or idle io prio class. */
-	if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq))
+	/*
+	 * No need to update has_short_ttime if bfqq is async or in
+	 * idle io prio class, or if bfq_slice_idle is zero, because
+	 * no device idling is performed for bfqq in this case.
+	 */
+	if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq) ||
+	    bfqd->bfq_slice_idle == 0)
 		return;
 
 	/* Idle window just restored, statistics are meaningless. */
@@ -4214,27 +4234,22 @@ static void bfq_update_idle_window(struct bfq_data *bfqd,
 				     bfqd->bfq_wr_min_idle_time))
 		return;
 
-	enable_idle = bfq_bfqq_idle_window(bfqq);
-
+	/* Think time is infinite if no process is linked to
+	 * bfqq. Otherwise check average think time to
+	 * decide whether to mark as has_short_ttime
+	 */
 	if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
-	    bfqd->bfq_slice_idle == 0 ||
-		(bfqd->hw_tag && BFQQ_SEEKY(bfqq) &&
-			bfqq->wr_coeff == 1))
-		enable_idle = 0;
-	else if (bfq_sample_valid(bic->ttime.ttime_samples)) {
-		if (bic->ttime.ttime_mean > bfqd->bfq_slice_idle &&
-			bfqq->wr_coeff == 1)
-			enable_idle = 0;
-		else
-			enable_idle = 1;
-	}
-	bfq_log_bfqq(bfqd, bfqq, "update_idle_window: enable_idle %d",
-		enable_idle);
+	    (bfq_sample_valid(bic->ttime.ttime_samples) &&
+	     bic->ttime.ttime_mean > bfqd->bfq_slice_idle))
+		has_short_ttime = false;
+
+	bfq_log_bfqq(bfqd, bfqq, "update_has_short_ttime: has_short_ttime %d",
+		has_short_ttime);
 
-	if (enable_idle)
-		bfq_mark_bfqq_idle_window(bfqq);
+	if (has_short_ttime)
+		bfq_mark_bfqq_has_short_ttime(bfqq);
 	else
-		bfq_clear_bfqq_idle_window(bfqq);
+		bfq_clear_bfqq_has_short_ttime(bfqq);
 }
 
 /*
@@ -4250,14 +4265,12 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		bfqq->meta_pending++;
 
 	bfq_update_io_thinktime(bfqd, bic);
+	bfq_update_has_short_ttime(bfqd, bfqq, bic);
 	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));
+		     "rq_enqueued: has_short_ttime=%d (seeky %d)",
+		     bfq_bfqq_has_short_ttime(bfqq), BFQQ_SEEKY(bfqq));
 
 	bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
 
diff --git a/block/bfq.h b/block/bfq.h
index ebd9688b9f61..34fc4697fd89 100644
--- a/block/bfq.h
+++ b/block/bfq.h
@@ -349,11 +349,11 @@ struct bfq_io_cq {
 #endif
 
 	/*
-	 * Snapshot of the idle window before merging; taken to
-	 * remember this value while the queue is merged, so as to be
-	 * able to restore it in case of split.
+	 * Snapshot of the has_short_time flag before merging; taken
+	 * to remember its value while the queue is merged, so as to
+	 * be able to restore it in case of split.
 	 */
-	bool saved_idle_window;
+	bool saved_has_short_ttime;
 	/*
 	 * Same purpose as the previous two fields for the I/O bound
 	 * classification of a queue.
@@ -610,7 +610,7 @@ enum bfqq_state_flags {
 					     */
 	BFQ_BFQQ_FLAG_must_alloc,	/* must be allowed rq alloc */
 	BFQ_BFQQ_FLAG_fifo_expire,	/* FIFO checked in this slice */
-	BFQ_BFQQ_FLAG_idle_window,	/* slice idling enabled */
+	BFQ_BFQQ_FLAG_has_short_ttime,	/* queue has a short think time */
 	BFQ_BFQQ_FLAG_sync,		/* synchronous queue */
 	BFQ_BFQQ_FLAG_IO_bound,		/*
 					 * bfqq has timed-out at least once
@@ -649,7 +649,7 @@ BFQ_BFQQ_FNS(wait_request);
 BFQ_BFQQ_FNS(non_blocking_wait_rq);
 BFQ_BFQQ_FNS(must_alloc);
 BFQ_BFQQ_FNS(fifo_expire);
-BFQ_BFQQ_FNS(idle_window);
+BFQ_BFQQ_FNS(has_short_ttime);
 BFQ_BFQQ_FNS(sync);
 BFQ_BFQQ_FNS(IO_bound);
 BFQ_BFQQ_FNS(in_large_burst);

From b5e746fa99d961a5642cffb27c19a77e8b638007 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Mon, 19 Dec 2016 16:59:33 +0100
Subject: [PATCH 06/51] FIRST BFQ-MQ COMMIT: Copy bfq-sq-iosched.c as
 bfq-mq-iosched.c

This commit introduces bfq-mq-iosched.c, the main source file that
will contain the code of bfq for blk-mq. I name tentatively
bfq-mq this version of bfq.

For the moment, the file bfq-mq-iosched.c is just a copy of
bfq-sq-iosched.c, i.e, of the main source file of bfq for blk.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c | 5392 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 5392 insertions(+)
 create mode 100644 block/bfq-mq-iosched.c

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
new file mode 100644
index 000000000000..30d019fc67e0
--- /dev/null
+++ b/block/bfq-mq-iosched.c
@@ -0,0 +1,5392 @@
+/*
+ * 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) 2015 Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2017 Paolo Valente <paolo.valente@linaro.org>
+ *
+ * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ
+ * file.
+ *
+ * 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 and usage 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. 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.
+ *
+ * NOTE: if the main or only goal, with a given device, is to achieve
+ * the maximum-possible throughput at all times, then do switch off
+ * all low-latency heuristics for that device, by setting low_latency
+ * to 0.
+ *
+ * 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+, that is described in [2], together with
+ * H-WF2Q+, while the augmented tree used 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
+ *
+ * http://algogroup.unimo.it/people/paolo/disk_sched/bf1-v1-suite-results.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/jiffies.h>
+#include <linux/rbtree.h>
+#include <linux/ioprio.h>
+#include "blk.h"
+#include "bfq.h"
+
+/* 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, 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 u32 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);
+
+/*
+ * Async to sync throughput distribution is controlled as follows:
+ * when an async request is served, the entity is charged the number
+ * of sectors of the request, multiplied by the factor below
+ */
+static const int bfq_async_charge_factor = 10;
+
+/* 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 ns), 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 number of samples required to perform peak-rate update */
+#define BFQ_RATE_MIN_SAMPLES	32
+/* Min observation time interval required to perform a peak-rate update (ns) */
+#define BFQ_RATE_MIN_INTERVAL	(300*NSEC_PER_MSEC)
+/* Target observation time interval for a peak-rate update (ns) */
+#define BFQ_RATE_REF_INTERVAL	NSEC_PER_SEC
+
+/* Shift used for peak rate fixed precision calculations. */
+#define BFQ_RATE_SHIFT		16
+
+/*
+ * By default, BFQ computes the duration of the weight raising for
+ * interactive applications automatically, using the following formula:
+ * duration = (R / r) * T, where r is the peak rate of the device, and
+ * R and T are two reference parameters.
+ * In particular, R is the peak rate of the reference device (see below),
+ * and T is a reference time: given the systems that are likely to be
+ * installed on the reference device according to its speed class, T is
+ * about the maximum time needed, under BFQ and while reading two files in
+ * parallel, to load typical large applications on these systems.
+ * In practice, the slower/faster the device at hand is, the more/less it
+ * takes to load applications with respect to the reference device.
+ * Accordingly, the longer/shorter BFQ grants weight raising to interactive
+ * applications.
+ *
+ * BFQ uses four different reference pairs (R, T), depending on:
+ * . whether the device is rotational or non-rotational;
+ * . whether the device is slow, such as old or portable HDDs, as well as
+ *   SD cards, or fast, such as newer HDDs and SSDs.
+ *
+ * The device's speed class is dynamically (re)detected in
+ * bfq_update_peak_rate() every time the estimated peak rate is updated.
+ *
+ * In the following definitions, R_slow[0]/R_fast[0] and
+ * T_slow[0]/T_fast[0] are the reference values for a slow/fast
+ * rotational device, whereas R_slow[1]/R_fast[1] and
+ * T_slow[1]/T_fast[1] are the reference values for a slow/fast
+ * non-rotational device. Finally, device_speed_thresh are the
+ * thresholds used to switch between speed classes. The reference
+ * rates are not the actual peak rates of the devices used as a
+ * reference, but slightly lower values. The reason for using these
+ * slightly lower values is that the peak-rate estimator tends to
+ * yield slightly lower values than the actual peak rate (it can yield
+ * the actual peak rate only if there is only one process doing I/O,
+ * and the process does sequential I/O).
+ *
+ * Both the reference peak rates and the thresholds are measured in
+ * sectors/usec, left-shifted by BFQ_RATE_SHIFT.
+ */
+static int R_slow[2] = {1000, 10700};
+static int R_fast[2] = {14000, 33000};
+/*
+ * To improve readability, a conversion function is used to initialize the
+ * following arrays, which entails that they can be initialized only in a
+ * function.
+ */
+static int T_slow[2];
+static int T_fast[2];
+static int device_speed_thresh[2];
+
+#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])
+
+static void bfq_schedule_dispatch(struct bfq_data *bfqd);
+
+#include "bfq-ioc.c"
+#include "bfq-sched.c"
+#include "bfq-cgroup-included.c"
+
+#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)
+
+/*
+ * 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");
+		kblockd_schedule_work(&bfqd->unplug_work);
+	}
+}
+
+/*
+ * 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;
+	}
+}
+
+static struct bfq_queue *
+bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
+		     sector_t sector, struct rb_node **ret_parent,
+		     struct rb_node ***rb_link)
+{
+	struct rb_node **p, *parent;
+	struct bfq_queue *bfqq = NULL;
+
+	parent = NULL;
+	p = &root->rb_node;
+	while (*p) {
+		struct rb_node **n;
+
+		parent = *p;
+		bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+
+		/*
+		 * Sort strictly based on sector. Smallest to the left,
+		 * largest to the right.
+		 */
+		if (sector > blk_rq_pos(bfqq->next_rq))
+			n = &(*p)->rb_right;
+		else if (sector < blk_rq_pos(bfqq->next_rq))
+			n = &(*p)->rb_left;
+		else
+			break;
+		p = n;
+		bfqq = NULL;
+	}
+
+	*ret_parent = parent;
+	if (rb_link)
+		*rb_link = p;
+
+	bfq_log(bfqd, "rq_pos_tree_lookup %llu: returning %d",
+		(unsigned long long) sector,
+		bfqq ? bfqq->pid : 0);
+
+	return bfqq;
+}
+
+static void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct rb_node **p, *parent;
+	struct bfq_queue *__bfqq;
+
+	if (bfqq->pos_root) {
+		rb_erase(&bfqq->pos_node, bfqq->pos_root);
+		bfqq->pos_root = NULL;
+	}
+
+	if (bfq_class_idle(bfqq))
+		return;
+	if (!bfqq->next_rq)
+		return;
+
+	bfqq->pos_root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
+	__bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root,
+			blk_rq_pos(bfqq->next_rq), &parent, &p);
+	if (!__bfqq) {
+		rb_link_node(&bfqq->pos_node, parent, p);
+		rb_insert_color(&bfqq->pos_node, bfqq->pos_root);
+	} else
+		bfqq->pos_root = NULL;
+}
+
+/*
+ * Tell whether there are active queues or groups with differentiated weights.
+ */
+static bool bfq_differentiated_weights(struct bfq_data *bfqd)
+{
+	/*
+	 * For weights to differ, at least one of the trees must contain
+	 * at least two nodes.
+	 */
+	return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
+		(bfqd->queue_weights_tree.rb_node->rb_left ||
+		 bfqd->queue_weights_tree.rb_node->rb_right)
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	       ) ||
+	       (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) &&
+		(bfqd->group_weights_tree.rb_node->rb_left ||
+		 bfqd->group_weights_tree.rb_node->rb_right)
+#endif
+	       );
+}
+
+/*
+ * The following function returns true if every queue must receive the
+ * same share of the throughput (this condition is used when deciding
+ * whether idling may be disabled, see the comments in the function
+ * bfq_bfqq_may_idle()).
+ *
+ * Such a scenario occurs when:
+ * 1) all active queues have the same weight,
+ * 2) all active groups at the same level in the groups tree have the same
+ *    weight,
+ * 3) all active groups at the same level in the groups tree have the same
+ *    number of children.
+ *
+ * Unfortunately, keeping the necessary state for evaluating exactly the
+ * above symmetry conditions would be quite complex and time-consuming.
+ * Therefore this function evaluates, instead, the following stronger
+ * sub-conditions, for which it is much easier to maintain the needed
+ * state:
+ * 1) all active queues have the same weight,
+ * 2) all active groups have the same weight,
+ * 3) all active groups have at most one active child each.
+ * In particular, the last two conditions are always true if hierarchical
+ * support and the cgroups interface are not enabled, thus no state needs
+ * to be maintained in this case.
+ */
+static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
+{
+	return !bfq_differentiated_weights(bfqd);
+}
+
+/*
+ * If the weight-counter tree passed as input contains no counter for
+ * the weight of the input entity, then add that counter; otherwise just
+ * increment the existing counter.
+ *
+ * Note that weight-counter trees contain few nodes in mostly symmetric
+ * scenarios. For example, if all queues have the same weight, then the
+ * weight-counter tree for the queues may contain at most one node.
+ * This holds even if low_latency is on, because weight-raised queues
+ * are not inserted in the tree.
+ * In most scenarios, the rate at which nodes are created/destroyed
+ * should be low too.
+ */
+static void bfq_weights_tree_add(struct bfq_data *bfqd,
+				 struct bfq_entity *entity,
+				 struct rb_root *root)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+	/*
+	 * Do not insert if the entity is already associated with a
+	 * counter, which happens if:
+	 *   1) the entity is associated with a queue,
+	 *   2) a request arrival has caused the queue to become both
+	 *      non-weight-raised, and hence change its weight, and
+	 *      backlogged; in this respect, each of the two events
+	 *      causes an invocation of this function,
+	 *   3) this is the invocation of this function caused by the
+	 *      second event. This second invocation is actually useless,
+	 *      and we handle this fact by exiting immediately. More
+	 *      efficient or clearer solutions might possibly be adopted.
+	 */
+	if (entity->weight_counter)
+		return;
+
+	while (*new) {
+		struct bfq_weight_counter *__counter = container_of(*new,
+						struct bfq_weight_counter,
+						weights_node);
+		parent = *new;
+
+		if (entity->weight == __counter->weight) {
+			entity->weight_counter = __counter;
+			goto inc_counter;
+		}
+		if (entity->weight < __counter->weight)
+			new = &((*new)->rb_left);
+		else
+			new = &((*new)->rb_right);
+	}
+
+	entity->weight_counter = kzalloc(sizeof(struct bfq_weight_counter),
+					 GFP_ATOMIC);
+
+	/*
+	 * In the unlucky event of an allocation failure, we just
+	 * exit. This will cause the weight of entity to not be
+	 * considered in bfq_differentiated_weights, which, in its
+	 * turn, causes the scenario to be deemed wrongly symmetric in
+	 * case entity's weight would have been the only weight making
+	 * the scenario asymmetric. On the bright side, no unbalance
+	 * will however occur when entity becomes inactive again (the
+	 * invocation of this function is triggered by an activation
+	 * of entity). In fact, bfq_weights_tree_remove does nothing
+	 * if !entity->weight_counter.
+	 */
+	if (unlikely(!entity->weight_counter))
+		return;
+
+	entity->weight_counter->weight = entity->weight;
+	rb_link_node(&entity->weight_counter->weights_node, parent, new);
+	rb_insert_color(&entity->weight_counter->weights_node, root);
+
+inc_counter:
+	entity->weight_counter->num_active++;
+}
+
+/*
+ * Decrement the weight counter associated with the entity, and, if the
+ * counter reaches 0, remove the counter from the tree.
+ * See the comments to the function bfq_weights_tree_add() for considerations
+ * about overhead.
+ */
+static void bfq_weights_tree_remove(struct bfq_data *bfqd,
+				    struct bfq_entity *entity,
+				    struct rb_root *root)
+{
+	if (!entity->weight_counter)
+		return;
+
+	BUG_ON(RB_EMPTY_ROOT(root));
+	BUG_ON(entity->weight_counter->weight != entity->weight);
+
+	BUG_ON(!entity->weight_counter->num_active);
+	entity->weight_counter->num_active--;
+	if (entity->weight_counter->num_active > 0)
+		goto reset_entity_pointer;
+
+	rb_erase(&entity->weight_counter->weights_node, root);
+	kfree(entity->weight_counter);
+
+reset_entity_pointer:
+	entity->weight_counter = NULL;
+}
+
+/*
+ * 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);
+	BUG_ON(RB_EMPTY_NODE(&rq->rb_node));
+	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;
+
+	BUG_ON(list_empty(&bfqq->fifo));
+
+	/* Follow expired path, else get first next available. */
+	next = bfq_check_fifo(bfqq, last);
+	if (next) {
+		BUG_ON(next == last);
+		return next;
+	}
+
+	BUG_ON(RB_EMPTY_NODE(&last->rb_node));
+
+	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));
+}
+
+/* see the definition of bfq_async_charge_factor for details */
+static unsigned long bfq_serv_to_charge(struct request *rq,
+					struct bfq_queue *bfqq)
+{
+	if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1)
+		return blk_rq_sectors(rq);
+
+	/*
+	 * If there are no weight-raised queues, then amplify service
+	 * by just the async charge factor; otherwise amplify service
+	 * by twice the async charge factor, to further reduce latency
+	 * for weight-raised queues.
+	 */
+	if (bfqq->bfqd->wr_busy_queues == 0)
+		return blk_rq_sectors(rq) * bfq_async_charge_factor;
+
+	return blk_rq_sectors(rq) * 2 * bfq_async_charge_factor;
+}
+
+/**
+ * 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 bfq_service_tree *st = bfq_entity_service_tree(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;
+
+	BUG_ON(entity->tree != &st->active);
+	BUG_ON(entity == entity->sched_data->in_service_entity);
+
+	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 unsigned int bfq_wr_duration(struct bfq_data *bfqd)
+{
+	u64 dur;
+
+	if (bfqd->bfq_wr_max_time > 0)
+		return bfqd->bfq_wr_max_time;
+
+	dur = bfqd->RT_prod;
+	do_div(dur, bfqd->peak_rate);
+
+	/*
+	 * Limit duration between 3 and 13 seconds. Tests show that
+	 * higher values than 13 seconds often yield the opposite of
+	 * the desired result, i.e., worsen responsiveness by letting
+	 * non-interactive and non-soft-real-time applications
+	 * preserve weight raising for a too long time interval.
+	 *
+	 * On the other end, lower values than 3 seconds make it
+	 * difficult for most interactive tasks to complete their jobs
+	 * before weight-raising finishes.
+	 */
+	if (dur > msecs_to_jiffies(13000))
+		dur = msecs_to_jiffies(13000);
+	else if (dur < msecs_to_jiffies(3000))
+		dur = msecs_to_jiffies(3000);
+
+	return dur;
+}
+
+static void
+bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
+		      struct bfq_io_cq *bic, bool bfq_already_existing)
+{
+	unsigned int old_wr_coeff;
+	bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq);
+
+	if (bic->saved_has_short_ttime)
+		bfq_mark_bfqq_has_short_ttime(bfqq);
+	else
+		bfq_clear_bfqq_has_short_ttime(bfqq);
+
+	if (bic->saved_IO_bound)
+		bfq_mark_bfqq_IO_bound(bfqq);
+	else
+		bfq_clear_bfqq_IO_bound(bfqq);
+
+	if (unlikely(busy))
+		old_wr_coeff = bfqq->wr_coeff;
+
+	bfqq->wr_coeff = bic->saved_wr_coeff;
+	bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt;
+	BUG_ON(time_is_after_jiffies(bfqq->wr_start_at_switch_to_srt));
+	bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish;
+	bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time;
+	BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish));
+
+	if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
+				   time_is_before_jiffies(bfqq->last_wr_start_finish +
+							  bfqq->wr_cur_max_time))) {
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+			     "resume state: switching off wr (%lu + %lu < %lu)",
+			     bfqq->last_wr_start_finish, bfqq->wr_cur_max_time,
+			     jiffies);
+
+		bfqq->wr_coeff = 1;
+	}
+
+	/* make sure weight will be updated, however we got here */
+	bfqq->entity.prio_changed = 1;
+
+	if (likely(!busy))
+		return;
+
+	if (old_wr_coeff == 1 && bfqq->wr_coeff > 1) {
+		bfqd->wr_busy_queues++;
+		BUG_ON(bfqd->wr_busy_queues > bfqd->busy_queues);
+	} else if (old_wr_coeff > 1 && bfqq->wr_coeff == 1) {
+		bfqd->wr_busy_queues--;
+		BUG_ON(bfqd->wr_busy_queues < 0);
+	}
+}
+
+static int bfqq_process_refs(struct bfq_queue *bfqq)
+{
+	int process_refs, io_refs;
+
+	lockdep_assert_held(bfqq->bfqd->queue->queue_lock);
+
+	io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE];
+	process_refs = bfqq->ref - io_refs - bfqq->entity.on_st;
+	BUG_ON(process_refs < 0);
+	return process_refs;
+}
+
+/* Empty burst list and add just bfqq (see comments to bfq_handle_burst) */
+static void bfq_reset_burst_list(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct bfq_queue *item;
+	struct hlist_node *n;
+
+	hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node)
+		hlist_del_init(&item->burst_list_node);
+	hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+	bfqd->burst_size = 1;
+	bfqd->burst_parent_entity = bfqq->entity.parent;
+}
+
+/* Add bfqq to the list of queues in current burst (see bfq_handle_burst) */
+static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	/* Increment burst size to take into account also bfqq */
+	bfqd->burst_size++;
+
+	bfq_log_bfqq(bfqd, bfqq, "add_to_burst %d", bfqd->burst_size);
+
+	BUG_ON(bfqd->burst_size > bfqd->bfq_large_burst_thresh);
+
+	if (bfqd->burst_size == bfqd->bfq_large_burst_thresh) {
+		struct bfq_queue *pos, *bfqq_item;
+		struct hlist_node *n;
+
+		/*
+		 * Enough queues have been activated shortly after each
+		 * other to consider this burst as large.
+		 */
+		bfqd->large_burst = true;
+		bfq_log_bfqq(bfqd, bfqq, "add_to_burst: large burst started");
+
+		/*
+		 * We can now mark all queues in the burst list as
+		 * belonging to a large burst.
+		 */
+		hlist_for_each_entry(bfqq_item, &bfqd->burst_list,
+				     burst_list_node) {
+			bfq_mark_bfqq_in_large_burst(bfqq_item);
+			bfq_log_bfqq(bfqd, bfqq_item, "marked in large burst");
+		}
+		bfq_mark_bfqq_in_large_burst(bfqq);
+		bfq_log_bfqq(bfqd, bfqq, "marked in large burst");
+
+		/*
+		 * From now on, and until the current burst finishes, any
+		 * new queue being activated shortly after the last queue
+		 * was inserted in the burst can be immediately marked as
+		 * belonging to a large burst. So the burst list is not
+		 * needed any more. Remove it.
+		 */
+		hlist_for_each_entry_safe(pos, n, &bfqd->burst_list,
+					  burst_list_node)
+			hlist_del_init(&pos->burst_list_node);
+	} else /*
+		* Burst not yet large: add bfqq to the burst list. Do
+		* not increment the ref counter for bfqq, because bfqq
+		* is removed from the burst list before freeing bfqq
+		* in put_queue.
+		*/
+		hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+}
+
+/*
+ * If many queues belonging to the same group happen to be created
+ * shortly after each other, then the processes associated with these
+ * queues have typically a common goal. In particular, bursts of queue
+ * creations are usually caused by services or applications that spawn
+ * many parallel threads/processes. Examples are systemd during boot,
+ * or git grep. To help these processes get their job done as soon as
+ * possible, it is usually better to not grant either weight-raising
+ * or device idling to their queues.
+ *
+ * In this comment we describe, firstly, the reasons why this fact
+ * holds, and, secondly, the next function, which implements the main
+ * steps needed to properly mark these queues so that they can then be
+ * treated in a different way.
+ *
+ * The above services or applications benefit mostly from a high
+ * throughput: the quicker the requests of the activated queues are
+ * cumulatively served, the sooner the target job of these queues gets
+ * completed. As a consequence, weight-raising any of these queues,
+ * which also implies idling the device for it, is almost always
+ * counterproductive. In most cases it just lowers throughput.
+ *
+ * On the other hand, a burst of queue creations may be caused also by
+ * the start of an application that does not consist of a lot of
+ * parallel I/O-bound threads. In fact, with a complex application,
+ * several short processes may need to be executed to start-up the
+ * application. In this respect, to start an application as quickly as
+ * possible, the best thing to do is in any case to privilege the I/O
+ * related to the application with respect to all other
+ * I/O. Therefore, the best strategy to start as quickly as possible
+ * an application that causes a burst of queue creations is to
+ * weight-raise all the queues created during the burst. This is the
+ * exact opposite of the best strategy for the other type of bursts.
+ *
+ * In the end, to take the best action for each of the two cases, the
+ * two types of bursts need to be distinguished. Fortunately, this
+ * seems relatively easy, by looking at the sizes of the bursts. In
+ * particular, we found a threshold such that only bursts with a
+ * larger size than that threshold are apparently caused by
+ * services or commands such as systemd or git grep. For brevity,
+ * hereafter we call just 'large' these bursts. BFQ *does not*
+ * weight-raise queues whose creation occurs in a large burst. In
+ * addition, for each of these queues BFQ performs or does not perform
+ * idling depending on which choice boosts the throughput more. The
+ * exact choice depends on the device and request pattern at
+ * hand.
+ *
+ * Unfortunately, false positives may occur while an interactive task
+ * is starting (e.g., an application is being started). The
+ * consequence is that the queues associated with the task do not
+ * enjoy weight raising as expected. Fortunately these false positives
+ * are very rare. They typically occur if some service happens to
+ * start doing I/O exactly when the interactive task starts.
+ *
+ * Turning back to the next function, it implements all the steps
+ * needed to detect the occurrence of a large burst and to properly
+ * mark all the queues belonging to it (so that they can then be
+ * treated in a different way). This goal is achieved by maintaining a
+ * "burst list" that holds, temporarily, the queues that belong to the
+ * burst in progress. The list is then used to mark these queues as
+ * belonging to a large burst if the burst does become large. The main
+ * steps are the following.
+ *
+ * . when the very first queue is created, the queue is inserted into the
+ *   list (as it could be the first queue in a possible burst)
+ *
+ * . if the current burst has not yet become large, and a queue Q that does
+ *   not yet belong to the burst is activated shortly after the last time
+ *   at which a new queue entered the burst list, then the function appends
+ *   Q to the burst list
+ *
+ * . if, as a consequence of the previous step, the burst size reaches
+ *   the large-burst threshold, then
+ *
+ *     . all the queues in the burst list are marked as belonging to a
+ *       large burst
+ *
+ *     . the burst list is deleted; in fact, the burst list already served
+ *       its purpose (keeping temporarily track of the queues in a burst,
+ *       so as to be able to mark them as belonging to a large burst in the
+ *       previous sub-step), and now is not needed any more
+ *
+ *     . the device enters a large-burst mode
+ *
+ * . if a queue Q that does not belong to the burst is created while
+ *   the device is in large-burst mode and shortly after the last time
+ *   at which a queue either entered the burst list or was marked as
+ *   belonging to the current large burst, then Q is immediately marked
+ *   as belonging to a large burst.
+ *
+ * . if a queue Q that does not belong to the burst is created a while
+ *   later, i.e., not shortly after, than the last time at which a queue
+ *   either entered the burst list or was marked as belonging to the
+ *   current large burst, then the current burst is deemed as finished and:
+ *
+ *        . the large-burst mode is reset if set
+ *
+ *        . the burst list is emptied
+ *
+ *        . Q is inserted in the burst list, as Q may be the first queue
+ *          in a possible new burst (then the burst list contains just Q
+ *          after this step).
+ */
+static void bfq_handle_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	/*
+	 * If bfqq is already in the burst list or is part of a large
+	 * burst, or finally has just been split, then there is
+	 * nothing else to do.
+	 */
+	if (!hlist_unhashed(&bfqq->burst_list_node) ||
+	    bfq_bfqq_in_large_burst(bfqq) ||
+	    time_is_after_eq_jiffies(bfqq->split_time +
+				     msecs_to_jiffies(10)))
+		return;
+
+	/*
+	 * If bfqq's creation happens late enough, or bfqq belongs to
+	 * a different group than the burst group, then the current
+	 * burst is finished, and related data structures must be
+	 * reset.
+	 *
+	 * In this respect, consider the special case where bfqq is
+	 * the very first queue created after BFQ is selected for this
+	 * device. In this case, last_ins_in_burst and
+	 * burst_parent_entity are not yet significant when we get
+	 * here. But it is easy to verify that, whether or not the
+	 * following condition is true, bfqq will end up being
+	 * inserted into the burst list. In particular the list will
+	 * happen to contain only bfqq. And this is exactly what has
+	 * to happen, as bfqq may be the first queue of the first
+	 * burst.
+	 */
+	if (time_is_before_jiffies(bfqd->last_ins_in_burst +
+	    bfqd->bfq_burst_interval) ||
+	    bfqq->entity.parent != bfqd->burst_parent_entity) {
+		bfqd->large_burst = false;
+		bfq_reset_burst_list(bfqd, bfqq);
+		bfq_log_bfqq(bfqd, bfqq,
+			"handle_burst: late activation or different group");
+		goto end;
+	}
+
+	/*
+	 * If we get here, then bfqq is being activated shortly after the
+	 * last queue. So, if the current burst is also large, we can mark
+	 * bfqq as belonging to this large burst immediately.
+	 */
+	if (bfqd->large_burst) {
+		bfq_log_bfqq(bfqd, bfqq, "handle_burst: marked in burst");
+		bfq_mark_bfqq_in_large_burst(bfqq);
+		goto end;
+	}
+
+	/*
+	 * If we get here, then a large-burst state has not yet been
+	 * reached, but bfqq is being activated shortly after the last
+	 * queue. Then we add bfqq to the burst.
+	 */
+	bfq_add_to_burst(bfqd, bfqq);
+end:
+	/*
+	 * At this point, bfqq either has been added to the current
+	 * burst or has caused the current burst to terminate and a
+	 * possible new burst to start. In particular, in the second
+	 * case, bfqq has become the first queue in the possible new
+	 * burst.  In both cases last_ins_in_burst needs to be moved
+	 * forward.
+	 */
+	bfqd->last_ins_in_burst = jiffies;
+
+}
+
+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 one of the two
+ * goals below.
+ *
+ * 1. 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:
+ *
+ * - BFQ_BFQQ_NO_MORE_REQUEST bfqq did not enjoy any device idling and
+ *   did not make it to issue a new request before its last request
+ *   was served;
+ *
+ * - BFQ_BFQQ_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.
+ *
+ * 2. Reduce latency. Even if timestamps are not backshifted to let
+ * the process associated with bfqq recover a service hole, bfqq may
+ * however happen to have, after being (re)activated, a lower finish
+ * timestamp than the in-service queue.  That is, the next budget of
+ * bfqq may have to be completed before the one of the in-service
+ * queue. If this is the case, then preempting the in-service queue
+ * allows this goal to be achieved, apart from the unpreemptible,
+ * outstanding requests mentioned above.
+ *
+ * Unfortunately, regardless of which of the above two goals one wants
+ * to achieve, service trees need first to be updated to know whether
+ * the in-service queue must be preempted. To have service trees
+ * correctly updated, the in-service queue must be expired and
+ * rescheduled, and bfqq must be scheduled too. This is one of the
+ * most costly operations (in future versions, the scheduling
+ * mechanism may be re-designed in such a way to make it possible to
+ * know whether preemption is needed without needing to update service
+ * trees). In addition, queue preemptions almost always cause random
+ * I/O, and thus loss of throughput. Because of these facts, the next
+ * function adopts the following simple scheme to avoid both costly
+ * operations and too frequent preemptions: it requests the expiration
+ * of the in-service queue (unconditionally) only for queues that need
+ * to recover a hole, or that either are weight-raised or deserve to
+ * be weight-raised.
+ */
+static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
+						struct bfq_queue *bfqq,
+						bool arrived_in_time,
+						bool wr_or_deserves_wr)
+{
+	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).
+		 */
+		BUG_ON(bfqq->max_budget < 0);
+		entity->budget = min_t(unsigned long,
+				       bfq_bfqq_budget_left(bfqq),
+				       bfqq->max_budget);
+
+		BUG_ON(entity->budget < 0);
+		return true;
+	}
+
+	BUG_ON(bfqq->max_budget < 0);
+	entity->budget = max_t(unsigned long, bfqq->max_budget,
+			       bfq_serv_to_charge(bfqq->next_rq, bfqq));
+	BUG_ON(entity->budget < 0);
+
+	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
+	return wr_or_deserves_wr;
+}
+
+static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
+					     struct bfq_queue *bfqq,
+					     unsigned int old_wr_coeff,
+					     bool wr_or_deserves_wr,
+					     bool interactive,
+					     bool in_burst,
+					     bool soft_rt)
+{
+	if (old_wr_coeff == 1 && wr_or_deserves_wr) {
+		/* start a weight-raising period */
+		if (interactive) {
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+		} else {
+			bfqq->wr_start_at_switch_to_srt = jiffies;
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff *
+				BFQ_SOFTRT_WEIGHT_FACTOR;
+			bfqq->wr_cur_max_time =
+				bfqd->bfq_wr_rt_max_time;
+		}
+		/*
+		 * If needed, further reduce budget to make sure it is
+		 * close to bfqq's backlog, so as to reduce the
+		 * scheduling-error component due to a too large
+		 * budget. Do not care about throughput consequences,
+		 * but only about latency. Finally, do not assign a
+		 * too small budget either, to avoid increasing
+		 * latency by causing too frequent expirations.
+		 */
+		bfqq->entity.budget = min_t(unsigned long,
+					    bfqq->entity.budget,
+					    2 * bfq_min_budget(bfqd));
+
+		bfq_log_bfqq(bfqd, bfqq,
+			     "wrais starting at %lu, rais_max_time %u",
+			     jiffies,
+			     jiffies_to_msecs(bfqq->wr_cur_max_time));
+	} else if (old_wr_coeff > 1) {
+		if (interactive) { /* update wr coeff and duration */
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+		} else if (in_burst) {
+			bfqq->wr_coeff = 1;
+			bfq_log_bfqq(bfqd, bfqq,
+				     "wrais ending at %lu, rais_max_time %u",
+				     jiffies,
+				     jiffies_to_msecs(bfqq->
+						      wr_cur_max_time));
+		} else if (soft_rt) {
+			/*
+			 * The application is now or still meeting the
+			 * requirements for being deemed soft rt.  We
+			 * can then correctly and safely (re)charge
+			 * the weight-raising duration for the
+			 * application with the weight-raising
+			 * duration for soft rt applications.
+			 *
+			 * In particular, doing this recharge now, i.e.,
+			 * before the weight-raising period for the
+			 * application finishes, reduces the probability
+			 * of the following negative scenario:
+			 * 1) the weight of a soft rt application is
+			 *    raised at startup (as for any newly
+			 *    created application),
+			 * 2) since the application is not interactive,
+			 *    at a certain time weight-raising is
+			 *    stopped for the application,
+			 * 3) at that time the application happens to
+			 *    still have pending requests, and hence
+			 *    is destined to not have a chance to be
+			 *    deemed soft rt before these requests are
+			 *    completed (see the comments to the
+			 *    function bfq_bfqq_softrt_next_start()
+			 *    for details on soft rt detection),
+			 * 4) these pending requests experience a high
+			 *    latency because the application is not
+			 *    weight-raised while they are pending.
+			 */
+			if (bfqq->wr_cur_max_time !=
+				bfqd->bfq_wr_rt_max_time) {
+				bfqq->wr_start_at_switch_to_srt =
+					bfqq->last_wr_start_finish;
+                BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish));
+
+				bfqq->wr_cur_max_time =
+					bfqd->bfq_wr_rt_max_time;
+				bfqq->wr_coeff = bfqd->bfq_wr_coeff *
+					BFQ_SOFTRT_WEIGHT_FACTOR;
+				bfq_log_bfqq(bfqd, bfqq,
+					     "switching to soft_rt wr");
+			} else
+				bfq_log_bfqq(bfqd, bfqq,
+					"moving forward soft_rt wr duration");
+			bfqq->last_wr_start_finish = jiffies;
+		}
+	}
+}
+
+static bool bfq_bfqq_idle_for_long_time(struct bfq_data *bfqd,
+					struct bfq_queue *bfqq)
+{
+	return bfqq->dispatched == 0 &&
+		time_is_before_jiffies(
+			bfqq->budget_timeout +
+			bfqd->bfq_wr_min_idle_time);
+}
+
+static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
+					     struct bfq_queue *bfqq,
+					     int old_wr_coeff,
+					     struct request *rq,
+					     bool *interactive)
+{
+	bool soft_rt, in_burst,	wr_or_deserves_wr,
+		bfqq_wants_to_preempt,
+		idle_for_long_time = bfq_bfqq_idle_for_long_time(bfqd, bfqq),
+		/*
+		 * 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() <=
+			RQ_BIC(rq)->ttime.last_end_request +
+			bfqd->bfq_slice_idle * 3;
+
+	bfq_log_bfqq(bfqd, bfqq,
+		     "bfq_add_request non-busy: "
+		     "jiffies %lu, in_time %d, idle_long %d busyw %d "
+		     "wr_coeff %u",
+		     jiffies, arrived_in_time,
+		     idle_for_long_time,
+		     bfq_bfqq_non_blocking_wait_rq(bfqq),
+		     old_wr_coeff);
+
+	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
+
+	BUG_ON(bfqq == bfqd->in_service_queue);
+	bfqg_stats_update_io_add(bfqq_group(RQ_BFQQ(rq)), bfqq, rq->cmd_flags);
+
+	/*
+	 * bfqq deserves to be weight-raised if:
+	 * - it is sync,
+	 * - it does not belong to a large burst,
+	 * - it has been idle for enough time or is soft real-time,
+	 * - is linked to a bfq_io_cq (it is not shared in any sense)
+	 */
+	in_burst = bfq_bfqq_in_large_burst(bfqq);
+	soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
+		!in_burst &&
+		time_is_before_jiffies(bfqq->soft_rt_next_start);
+	*interactive =
+		!in_burst &&
+		idle_for_long_time;
+	wr_or_deserves_wr = bfqd->low_latency &&
+		(bfqq->wr_coeff > 1 ||
+		 (bfq_bfqq_sync(bfqq) &&
+		  bfqq->bic && (*interactive || soft_rt)));
+
+	bfq_log_bfqq(bfqd, bfqq,
+		     "bfq_add_request: "
+		     "in_burst %d, "
+		     "soft_rt %d (next %lu), inter %d, bic %p",
+		     bfq_bfqq_in_large_burst(bfqq), soft_rt,
+		     bfqq->soft_rt_next_start,
+		     *interactive,
+		     bfqq->bic);
+
+	/*
+	 * Using the last flag, 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,
+						    wr_or_deserves_wr);
+
+	/*
+	 * If bfqq happened to be activated in a burst, but has been
+	 * idle for much more than an interactive queue, then we
+	 * assume that, in the overall I/O initiated in the burst, the
+	 * I/O associated with bfqq is finished. So bfqq does not need
+	 * to be treated as a queue belonging to a burst
+	 * anymore. Accordingly, we reset bfqq's in_large_burst flag
+	 * if set, and remove bfqq from the burst list if it's
+	 * there. We do not decrement burst_size, because the fact
+	 * that bfqq does not need to belong to the burst list any
+	 * more does not invalidate the fact that bfqq was created in
+	 * a burst.
+	 */
+	if (likely(!bfq_bfqq_just_created(bfqq)) &&
+	    idle_for_long_time &&
+	    time_is_before_jiffies(
+		    bfqq->budget_timeout +
+		    msecs_to_jiffies(10000))) {
+		hlist_del_init(&bfqq->burst_list_node);
+		bfq_clear_bfqq_in_large_burst(bfqq);
+	}
+
+	bfq_clear_bfqq_just_created(bfqq);
+
+	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_log_bfqq(bfqd, bfqq, "requests in time %d",
+			     bfqq->requests_within_timer);
+	}
+
+	if (bfqd->low_latency) {
+		if (unlikely(time_is_after_jiffies(bfqq->split_time)))
+			/* wraparound */
+			bfqq->split_time =
+				jiffies - bfqd->bfq_wr_min_idle_time - 1;
+
+		if (time_is_before_jiffies(bfqq->split_time +
+					   bfqd->bfq_wr_min_idle_time)) {
+			bfq_update_bfqq_wr_on_rq_arrival(bfqd, bfqq,
+							 old_wr_coeff,
+							 wr_or_deserves_wr,
+							 *interactive,
+							 in_burst,
+							 soft_rt);
+
+			if (old_wr_coeff != bfqq->wr_coeff)
+				bfqq->entity.prio_changed = 1;
+		}
+	}
+
+	bfqq->last_idle_bklogged = jiffies;
+	bfqq->service_from_backlogged = 0;
+	bfq_clear_bfqq_softrt_update(bfqq);
+
+	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 &&
+	    bfqd->in_service_queue->wr_coeff < bfqq->wr_coeff &&
+	    next_queue_may_preempt(bfqd)) {
+		struct bfq_queue *in_serv =
+			bfqd->in_service_queue;
+		BUG_ON(in_serv == bfqq);
+
+		bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
+				false, BFQ_BFQQ_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;
+	unsigned int old_wr_coeff = bfqq->wr_coeff;
+	bool interactive = false;
+
+	bfq_log_bfqq(bfqd, bfqq, "add_request: size %u %s",
+		     blk_rq_sectors(rq), rq_is_sync(rq) ? "S" : "A");
+
+	if (bfqq->wr_coeff > 1) /* queue is being weight-raised */
+		bfq_log_bfqq(bfqd, bfqq,
+			"raising period dur %u/%u msec, old coeff %u, w %d(%d)",
+			jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish),
+			jiffies_to_msecs(bfqq->wr_cur_max_time),
+			bfqq->wr_coeff,
+			bfqq->entity.weight, bfqq->entity.orig_weight);
+
+	bfqq->queued[rq_is_sync(rq)]++;
+	bfqd->queued++;
+
+	elv_rb_add(&bfqq->sort_list, rq);
+
+	/*
+	 * Check if this request is a better next-to-serve candidate.
+	 */
+	prev = bfqq->next_rq;
+	next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position);
+	BUG_ON(!next_rq);
+	bfqq->next_rq = next_rq;
+
+	/*
+	 * Adjust priority tree position, if next_rq changes.
+	 */
+	if (prev != bfqq->next_rq)
+		bfq_pos_tree_add_move(bfqd, bfqq);
+
+	if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */
+		bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, old_wr_coeff,
+						 rq, &interactive);
+	else {
+		if (bfqd->low_latency && old_wr_coeff == 1 && !rq_is_sync(rq) &&
+		    time_is_before_jiffies(
+				bfqq->last_wr_start_finish +
+				bfqd->bfq_wr_min_inter_arr_async)) {
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+
+			bfqd->wr_busy_queues++;
+			BUG_ON(bfqd->wr_busy_queues > bfqd->busy_queues);
+			bfqq->entity.prio_changed = 1;
+			bfq_log_bfqq(bfqd, bfqq,
+				     "non-idle wrais starting, "
+				     "wr_max_time %u wr_busy %d",
+				     jiffies_to_msecs(bfqq->wr_cur_max_time),
+				     bfqd->wr_busy_queues);
+		}
+		if (prev != bfqq->next_rq)
+			bfq_updated_next_req(bfqd, bfqq);
+	}
+
+	/*
+	 * Assign jiffies to last_wr_start_finish in the following
+	 * cases:
+	 *
+	 * . if bfqq is not going to be weight-raised, because, for
+	 *   non weight-raised queues, last_wr_start_finish stores the
+	 *   arrival time of the last request; as of now, this piece
+	 *   of information is used only for deciding whether to
+	 *   weight-raise async queues
+	 *
+	 * . if bfqq is not weight-raised, because, if bfqq is now
+	 *   switching to weight-raised, then last_wr_start_finish
+	 *   stores the time when weight-raising starts
+	 *
+	 * . if bfqq is interactive, because, regardless of whether
+	 *   bfqq is currently weight-raised, the weight-raising
+	 *   period must start or restart (this case is considered
+	 *   separately because it is not detected by the above
+	 *   conditions, if bfqq is already weight-raised)
+	 *
+	 * last_wr_start_finish has to be updated also if bfqq is soft
+	 * real-time, because the weight-raising period is constantly
+	 * restarted on idle-to-busy transitions for these queues, but
+	 * this is already done in bfq_bfqq_handle_idle_busy_switch if
+	 * needed.
+	 */
+	if (bfqd->low_latency &&
+		(old_wr_coeff == 1 || bfqq->wr_coeff == 1 || interactive))
+		bfqq->last_wr_start_finish = jiffies;
+}
+
+static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
+					  struct bio *bio)
+{
+	struct task_struct *tsk = current;
+	struct bfq_io_cq *bic;
+	struct bfq_queue *bfqq;
+
+	bic = bfq_bic_lookup(bfqd, tsk->io_context);
+	if (!bic)
+		return NULL;
+
+	bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf));
+	if (bfqq)
+		return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio));
+
+	return NULL;
+}
+
+static sector_t get_sdist(sector_t last_pos, struct request *rq)
+{
+	sector_t sdist = 0;
+
+	if (last_pos) {
+		if (last_pos < blk_rq_pos(rq))
+			sdist = blk_rq_pos(rq) - last_pos;
+		else
+			sdist = last_pos - blk_rq_pos(rq);
+	}
+
+	return sdist;
+}
+
+static void bfq_activate_request(struct request_queue *q, struct request *rq)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	bfqd->rq_in_driver++;
+}
+
+static void bfq_deactivate_request(struct request_queue *q, struct request *rq)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+
+	BUG_ON(bfqd->rq_in_driver == 0);
+	bfqd->rq_in_driver--;
+}
+
+static void bfq_remove_request(struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_data *bfqd = bfqq->bfqd;
+	const int sync = rq_is_sync(rq);
+
+	BUG_ON(bfqq->entity.service > bfqq->entity.budget &&
+	       bfqq == bfqd->in_service_queue);
+
+	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);
+	BUG_ON(bfqq->queued[sync] == 0);
+	bfqq->queued[sync]--;
+	bfqd->queued--;
+	elv_rb_del(&bfqq->sort_list, rq);
+
+	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		bfqq->next_rq = NULL;
+
+		BUG_ON(bfqq->entity.budget < 0);
+
+		if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) {
+			BUG_ON(bfqq->ref < 2); /* referred by rq and on tree */
+			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;
+		}
+
+		/*
+		 * Remove queue from request-position tree as it is empty.
+		 */
+		if (bfqq->pos_root) {
+			rb_erase(&bfqq->pos_node, bfqq->pos_root);
+			bfqq->pos_root = NULL;
+		}
+	}
+
+	if (rq->cmd_flags & REQ_META) {
+		BUG_ON(bfqq->meta_pending == 0);
+		bfqq->meta_pending--;
+	}
+	bfqg_stats_update_io_remove(bfqq_group(bfqq), rq->cmd_flags);
+}
+
+static enum elv_merge bfq_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);
+	if (__rq && elv_bio_merge_ok(__rq, bio)) {
+		*req = __rq;
+		return ELEVATOR_FRONT_MERGE;
+	}
+
+	return ELEVATOR_NO_MERGE;
+}
+
+static void bfq_merged_request(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);
+		BUG_ON(!next_rq);
+		bfqq->next_rq = next_rq;
+		/*
+		 * If next_rq changes, update both the queue's budget to
+		 * fit the new request and the queue's position in its
+		 * rq_pos_tree.
+		 */
+		if (prev != bfqq->next_rq) {
+			bfq_updated_next_req(bfqd, bfqq);
+			bfq_pos_tree_add_move(bfqd, bfqq);
+		}
+	}
+}
+
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+static void bfq_bio_merged(struct request_queue *q, struct request *req,
+			   struct bio *bio)
+{
+	bfqg_stats_update_io_merged(bfqq_group(RQ_BFQQ(req)), bio->bi_opf);
+}
+#endif
+
+static void bfq_merged_requests(struct request_queue *q, struct request *rq,
+				struct request *next)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next);
+
+	/*
+	 * 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(next);
+	bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
+}
+
+/* Must be called with bfqq != NULL */
+static void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
+{
+	BUG_ON(!bfqq);
+
+	if (bfq_bfqq_busy(bfqq)) {
+		bfqq->bfqd->wr_busy_queues--;
+		BUG_ON(bfqq->bfqd->wr_busy_queues < 0);
+	}
+	bfqq->wr_coeff = 1;
+	bfqq->wr_cur_max_time = 0;
+	bfqq->last_wr_start_finish = jiffies;
+	/*
+	 * Trigger a weight change on the next invocation of
+	 * __bfq_entity_update_weight_prio.
+	 */
+	bfqq->entity.prio_changed = 1;
+	bfq_log_bfqq(bfqq->bfqd, bfqq,
+		     "end_wr: wrais ending at %lu, rais_max_time %u",
+		     bfqq->last_wr_start_finish,
+		     jiffies_to_msecs(bfqq->wr_cur_max_time));
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "end_wr: wr_busy %d",
+		     bfqq->bfqd->wr_busy_queues);
+}
+
+static void bfq_end_wr_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++)
+			if (bfqg->async_bfqq[i][j])
+				bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]);
+	if (bfqg->async_idle_bfqq)
+		bfq_bfqq_end_wr(bfqg->async_idle_bfqq);
+}
+
+static void bfq_end_wr(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq;
+
+	spin_lock_irq(bfqd->queue->queue_lock);
+
+	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
+		bfq_bfqq_end_wr(bfqq);
+	list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list)
+		bfq_bfqq_end_wr(bfqq);
+	bfq_end_wr_async(bfqd);
+
+	spin_unlock_irq(bfqd->queue->queue_lock);
+}
+
+static sector_t bfq_io_struct_pos(void *io_struct, bool request)
+{
+	if (request)
+		return blk_rq_pos(io_struct);
+	else
+		return ((struct bio *)io_struct)->bi_iter.bi_sector;
+}
+
+static int bfq_rq_close_to_sector(void *io_struct, bool request,
+				  sector_t sector)
+{
+	return abs(bfq_io_struct_pos(io_struct, request) - sector) <=
+	       BFQQ_CLOSE_THR;
+}
+
+static struct bfq_queue *bfqq_find_close(struct bfq_data *bfqd,
+					 struct bfq_queue *bfqq,
+					 sector_t sector)
+{
+	struct rb_root *root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
+	struct rb_node *parent, *node;
+	struct bfq_queue *__bfqq;
+
+	if (RB_EMPTY_ROOT(root))
+		return NULL;
+
+	/*
+	 * First, if we find a request starting at the end of the last
+	 * request, choose it.
+	 */
+	__bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL);
+	if (__bfqq)
+		return __bfqq;
+
+	/*
+	 * If the exact sector wasn't found, the parent of the NULL leaf
+	 * will contain the closest sector (rq_pos_tree sorted by
+	 * next_request position).
+	 */
+	__bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+	if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+		return __bfqq;
+
+	if (blk_rq_pos(__bfqq->next_rq) < sector)
+		node = rb_next(&__bfqq->pos_node);
+	else
+		node = rb_prev(&__bfqq->pos_node);
+	if (!node)
+		return NULL;
+
+	__bfqq = rb_entry(node, struct bfq_queue, pos_node);
+	if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+		return __bfqq;
+
+	return NULL;
+}
+
+static struct bfq_queue *bfq_find_close_cooperator(struct bfq_data *bfqd,
+						   struct bfq_queue *cur_bfqq,
+						   sector_t sector)
+{
+	struct bfq_queue *bfqq;
+
+	/*
+	 * We shall notice if some of the queues are cooperating,
+	 * e.g., working closely on the same area of the device. In
+	 * that case, we can group them together and: 1) don't waste
+	 * time idling, and 2) serve the union of their requests in
+	 * the best possible order for throughput.
+	 */
+	bfqq = bfqq_find_close(bfqd, cur_bfqq, sector);
+	if (!bfqq || bfqq == cur_bfqq)
+		return NULL;
+
+	return bfqq;
+}
+
+static struct bfq_queue *
+bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+{
+	int process_refs, new_process_refs;
+	struct bfq_queue *__bfqq;
+
+	/*
+	 * If there are no process references on the new_bfqq, then it is
+	 * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
+	 * may have dropped their last reference (not just their last process
+	 * reference).
+	 */
+	if (!bfqq_process_refs(new_bfqq))
+		return NULL;
+
+	/* Avoid a circular list and skip interim queue merges. */
+	while ((__bfqq = new_bfqq->new_bfqq)) {
+		if (__bfqq == bfqq)
+			return NULL;
+		new_bfqq = __bfqq;
+	}
+
+	process_refs = bfqq_process_refs(bfqq);
+	new_process_refs = bfqq_process_refs(new_bfqq);
+	/*
+	 * If the process for the bfqq has gone away, there is no
+	 * sense in merging the queues.
+	 */
+	if (process_refs == 0 || new_process_refs == 0)
+		return NULL;
+
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
+		new_bfqq->pid);
+
+	/*
+	 * Merging is just a redirection: the requests of the process
+	 * owning one of the two queues are redirected to the other queue.
+	 * The latter queue, in its turn, is set as shared if this is the
+	 * first time that the requests of some process are redirected to
+	 * it.
+	 *
+	 * We redirect bfqq to new_bfqq and not the opposite, because we
+	 * are in the context of the process owning bfqq, hence we have
+	 * the io_cq of this process. So we can immediately configure this
+	 * io_cq to redirect the requests of the process to new_bfqq.
+	 *
+	 * NOTE, even if new_bfqq coincides with the in-service queue, the
+	 * io_cq of new_bfqq is not available, because, if the in-service
+	 * queue is shared, bfqd->in_service_bic may not point to the
+	 * io_cq of the in-service queue.
+	 * Redirecting the requests of the process owning bfqq to the
+	 * currently in-service queue is in any case the best option, as
+	 * we feed the in-service queue with new requests close to the
+	 * last request served and, by doing so, hopefully increase the
+	 * throughput.
+	 */
+	bfqq->new_bfqq = new_bfqq;
+	new_bfqq->ref += process_refs;
+	return new_bfqq;
+}
+
+static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq,
+					struct bfq_queue *new_bfqq)
+{
+	if (bfq_class_idle(bfqq) || bfq_class_idle(new_bfqq) ||
+	    (bfqq->ioprio_class != new_bfqq->ioprio_class))
+		return false;
+
+	/*
+	 * If either of the queues has already been detected as seeky,
+	 * then merging it with the other queue is unlikely to lead to
+	 * sequential I/O.
+	 */
+	if (BFQQ_SEEKY(bfqq) || BFQQ_SEEKY(new_bfqq))
+		return false;
+
+	/*
+	 * Interleaved I/O is known to be done by (some) applications
+	 * only for reads, so it does not make sense to merge async
+	 * queues.
+	 */
+	if (!bfq_bfqq_sync(bfqq) || !bfq_bfqq_sync(new_bfqq))
+		return false;
+
+	return true;
+}
+
+/*
+ * If this function returns true, then bfqq cannot be merged. The idea
+ * is that true cooperation happens very early after processes start
+ * to do I/O. Usually, late cooperations are just accidental false
+ * positives. In case bfqq is weight-raised, such false positives
+ * would evidently degrade latency guarantees for bfqq.
+ */
+static bool wr_from_too_long(struct bfq_queue *bfqq)
+{
+	return bfqq->wr_coeff > 1 &&
+		time_is_before_jiffies(bfqq->last_wr_start_finish +
+				       msecs_to_jiffies(100));
+}
+
+/*
+ * Attempt to schedule a merge of bfqq with the currently in-service
+ * queue or with a close queue among the scheduled queues.  Return
+ * NULL if no merge was scheduled, a pointer to the shared bfq_queue
+ * structure otherwise.
+ *
+ * The OOM queue is not allowed to participate to cooperation: in fact, since
+ * the requests temporarily redirected to the OOM queue could be redirected
+ * again to dedicated queues at any time, the state needed to correctly
+ * handle merging with the OOM queue would be quite complex and expensive
+ * to maintain. Besides, in such a critical condition as an out of memory,
+ * the benefits of queue merging may be little relevant, or even negligible.
+ *
+ * Weight-raised queues can be merged only if their weight-raising
+ * period has just started. In fact cooperating processes are usually
+ * started together. Thus, with this filter we avoid false positives
+ * that would jeopardize low-latency guarantees.
+ *
+ * WARNING: queue merging may impair fairness among non-weight raised
+ * queues, for at least two reasons: 1) the original weight of a
+ * merged queue may change during the merged state, 2) even being the
+ * weight the same, a merged queue may be bloated with many more
+ * requests than the ones produced by its originally-associated
+ * process.
+ */
+static struct bfq_queue *
+bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		     void *io_struct, bool request)
+{
+	struct bfq_queue *in_service_bfqq, *new_bfqq;
+
+	if (bfqq->new_bfqq)
+		return bfqq->new_bfqq;
+
+	if (io_struct && wr_from_too_long(bfqq) &&
+	    likely(bfqq != &bfqd->oom_bfqq))
+		bfq_log_bfqq(bfqd, bfqq,
+			     "would have looked for coop, but bfq%d wr",
+			bfqq->pid);
+
+	if (!io_struct ||
+	    wr_from_too_long(bfqq) ||
+	    unlikely(bfqq == &bfqd->oom_bfqq))
+		return NULL;
+
+	/* If there is only one backlogged queue, don't search. */
+	if (bfqd->busy_queues == 1)
+		return NULL;
+
+	in_service_bfqq = bfqd->in_service_queue;
+
+	if (in_service_bfqq && in_service_bfqq != bfqq &&
+	    bfqd->in_service_bic && wr_from_too_long(in_service_bfqq)
+	    && likely(in_service_bfqq == &bfqd->oom_bfqq))
+		bfq_log_bfqq(bfqd, bfqq,
+		"would have tried merge with in-service-queue, but wr");
+
+	if (!in_service_bfqq || in_service_bfqq == bfqq ||
+	    !bfqd->in_service_bic || wr_from_too_long(in_service_bfqq) ||
+	    unlikely(in_service_bfqq == &bfqd->oom_bfqq))
+		goto check_scheduled;
+
+	if (bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) &&
+	    bfqq->entity.parent == in_service_bfqq->entity.parent &&
+	    bfq_may_be_close_cooperator(bfqq, in_service_bfqq)) {
+		new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq);
+		if (new_bfqq)
+			return new_bfqq;
+	}
+	/*
+	 * Check whether there is a cooperator among currently scheduled
+	 * queues. The only thing we need is that the bio/request is not
+	 * NULL, as we need it to establish whether a cooperator exists.
+	 */
+check_scheduled:
+	new_bfqq = bfq_find_close_cooperator(bfqd, bfqq,
+			bfq_io_struct_pos(io_struct, request));
+
+	BUG_ON(new_bfqq && bfqq->entity.parent != new_bfqq->entity.parent);
+
+	if (new_bfqq && wr_from_too_long(new_bfqq) &&
+	    likely(new_bfqq != &bfqd->oom_bfqq) &&
+	    bfq_may_be_close_cooperator(bfqq, new_bfqq))
+		bfq_log_bfqq(bfqd, bfqq,
+			     "would have merged with bfq%d, but wr",
+			     new_bfqq->pid);
+
+	if (new_bfqq && !wr_from_too_long(new_bfqq) &&
+	    likely(new_bfqq != &bfqd->oom_bfqq) &&
+	    bfq_may_be_close_cooperator(bfqq, new_bfqq))
+		return bfq_setup_merge(bfqq, new_bfqq);
+
+	return NULL;
+}
+
+static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
+{
+	struct bfq_io_cq *bic = bfqq->bic;
+
+	/*
+	 * If !bfqq->bic, the queue is already shared or its requests
+	 * have already been redirected to a shared queue; both idle window
+	 * and weight raising state have already been saved. Do nothing.
+	 */
+	if (!bic)
+		return;
+
+	bic->saved_has_short_ttime = bfq_bfqq_has_short_ttime(bfqq);
+	bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
+	bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
+	bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
+	bic->saved_wr_coeff = bfqq->wr_coeff;
+	bic->saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt;
+	bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
+	bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
+	BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish));
+}
+
+static void bfq_get_bic_reference(struct bfq_queue *bfqq)
+{
+	/*
+	 * If bfqq->bic has a non-NULL value, the bic to which it belongs
+	 * is about to begin using a shared bfq_queue.
+	 */
+	if (bfqq->bic)
+		atomic_long_inc(&bfqq->bic->icq.ioc->refcount);
+}
+
+static void
+bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
+		struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+{
+	bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
+		     (unsigned long) new_bfqq->pid);
+	/* Save weight raising and idle window of the merged queues */
+	bfq_bfqq_save_state(bfqq);
+	bfq_bfqq_save_state(new_bfqq);
+	if (bfq_bfqq_IO_bound(bfqq))
+		bfq_mark_bfqq_IO_bound(new_bfqq);
+	bfq_clear_bfqq_IO_bound(bfqq);
+
+	/*
+	 * If bfqq is weight-raised, then let new_bfqq inherit
+	 * weight-raising. To reduce false positives, neglect the case
+	 * where bfqq has just been created, but has not yet made it
+	 * to be weight-raised (which may happen because EQM may merge
+	 * bfqq even before bfq_add_request is executed for the first
+	 * time for bfqq). Handling this case would however be very
+	 * easy, thanks to the flag just_created.
+	 */
+	if (new_bfqq->wr_coeff == 1 && bfqq->wr_coeff > 1) {
+		new_bfqq->wr_coeff = bfqq->wr_coeff;
+		new_bfqq->wr_cur_max_time = bfqq->wr_cur_max_time;
+		new_bfqq->last_wr_start_finish = bfqq->last_wr_start_finish;
+		new_bfqq->wr_start_at_switch_to_srt =
+			bfqq->wr_start_at_switch_to_srt;
+		if (bfq_bfqq_busy(new_bfqq)) {
+			bfqd->wr_busy_queues++;
+			BUG_ON(bfqd->wr_busy_queues > bfqd->busy_queues);
+		}
+
+		new_bfqq->entity.prio_changed = 1;
+		bfq_log_bfqq(bfqd, new_bfqq,
+			     "wr start after merge with %d, rais_max_time %u",
+			     bfqq->pid,
+			     jiffies_to_msecs(bfqq->wr_cur_max_time));
+	}
+
+	if (bfqq->wr_coeff > 1) { /* bfqq has given its wr to new_bfqq */
+		bfqq->wr_coeff = 1;
+		bfqq->entity.prio_changed = 1;
+		if (bfq_bfqq_busy(bfqq)) {
+			bfqd->wr_busy_queues--;
+			BUG_ON(bfqd->wr_busy_queues < 0);
+		}
+
+	}
+
+	bfq_log_bfqq(bfqd, new_bfqq, "merge_bfqqs: wr_busy %d",
+		     bfqd->wr_busy_queues);
+
+	/*
+	 * Grab a reference to the bic, to prevent it from being destroyed
+	 * before being possibly touched by a bfq_split_bfqq().
+	 */
+	bfq_get_bic_reference(bfqq);
+	bfq_get_bic_reference(new_bfqq);
+	/*
+	 * Merge queues (that is, let bic redirect its requests to new_bfqq)
+	 */
+	bic_set_bfqq(bic, new_bfqq, 1);
+	bfq_mark_bfqq_coop(new_bfqq);
+	/*
+	 * new_bfqq now belongs to at least two bics (it is a shared queue):
+	 * set new_bfqq->bic to NULL. bfqq either:
+	 * - does not belong to any bic any more, and hence bfqq->bic must
+	 *   be set to NULL, or
+	 * - is a queue whose owning bics have already been redirected to a
+	 *   different queue, hence the queue is destined to not belong to
+	 *   any bic soon and bfqq->bic is already NULL (therefore the next
+	 *   assignment causes no harm).
+	 */
+	new_bfqq->bic = NULL;
+	bfqq->bic = NULL;
+	/* release process reference to bfqq */
+	bfq_put_queue(bfqq);
+}
+
+static int 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_io_cq *bic;
+	struct bfq_queue *bfqq, *new_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.
+	 * Queue lock is held here.
+	 */
+	bic = bfq_bic_lookup(bfqd, current->io_context);
+	if (!bic)
+		return false;
+
+	bfqq = bic_to_bfqq(bic, is_sync);
+	/*
+	 * We take advantage of this function to perform an early merge
+	 * of the queues of possible cooperating processes.
+	 */
+	if (bfqq) {
+		new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
+		if (new_bfqq) {
+			bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq);
+			/*
+			 * If we get here, the bio will be queued in the
+			 * shared queue, i.e., new_bfqq, so use new_bfqq
+			 * to decide whether bio and rq can be merged.
+			 */
+			bfqq = new_bfqq;
+		}
+	}
+
+	return bfqq == RQ_BFQQ(rq);
+}
+
+static int bfq_allow_rq_merge(struct request_queue *q, struct request *rq,
+			      struct request *next)
+{
+	return RQ_BFQQ(rq) == RQ_BFQQ(next);
+}
+
+/*
+ * Set the maximum time for the in-service queue to consume its
+ * budget. This prevents seeky processes from lowering the throughput.
+ * In practice, a time-slice service scheme is used with seeky
+ * processes.
+ */
+static void bfq_set_budget_timeout(struct bfq_data *bfqd,
+				   struct bfq_queue *bfqq)
+{
+	unsigned int timeout_coeff;
+
+	if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time)
+		timeout_coeff = 1;
+	else
+		timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight;
+
+	bfqd->last_budget_start = ktime_get();
+
+	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));
+}
+
+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_must_alloc(bfqq);
+		bfq_clear_bfqq_fifo_expire(bfqq);
+
+		bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8;
+
+		BUG_ON(bfqq == bfqd->in_service_queue);
+		BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list));
+
+		if (time_is_before_jiffies(bfqq->last_wr_start_finish) &&
+		    bfqq->wr_coeff > 1 &&
+		    bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
+		    time_is_before_jiffies(bfqq->budget_timeout)) {
+			/*
+			 * For soft real-time queues, move the start
+			 * of the weight-raising period forward by the
+			 * time the queue has not received any
+			 * service. Otherwise, a relatively long
+			 * service delay is likely to cause the
+			 * weight-raising period of the queue to end,
+			 * because of the short duration of the
+			 * weight-raising period of a soft real-time
+			 * queue.  It is worth noting that this move
+			 * is not so dangerous for the other queues,
+			 * because soft real-time queues are not
+			 * greedy.
+			 *
+			 * To not add a further variable, we use the
+			 * overloaded field budget_timeout to
+			 * determine for how long the queue has not
+			 * received service, i.e., how much time has
+			 * elapsed since the queue expired. However,
+			 * this is a little imprecise, because
+			 * budget_timeout is set to jiffies if bfqq
+			 * not only expires, but also remains with no
+			 * request.
+			 */
+			if (time_after(bfqq->budget_timeout,
+				       bfqq->last_wr_start_finish))
+				bfqq->last_wr_start_finish +=
+					jiffies - bfqq->budget_timeout;
+			else
+				bfqq->last_wr_start_finish = jiffies;
+
+			if (time_is_after_jiffies(bfqq->last_wr_start_finish)) {
+			       pr_crit(
+			       "BFQ WARNING:last %lu budget %lu jiffies %lu",
+			       bfqq->last_wr_start_finish,
+			       bfqq->budget_timeout,
+			       jiffies);
+			       pr_crit("diff %lu", jiffies -
+				       max_t(unsigned long,
+					     bfqq->last_wr_start_finish,
+					     bfqq->budget_timeout));
+			       bfqq->last_wr_start_finish = jiffies;
+			}
+		}
+
+		bfq_set_budget_timeout(bfqd, bfqq);
+		bfq_log_bfqq(bfqd, bfqq,
+			     "set_in_service_queue, cur-budget = %d",
+			     bfqq->entity.budget);
+	} else
+		bfq_log(bfqd, "set_in_service_queue: NULL");
+
+	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;
+
+	BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
+
+	/* 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.
+	 *
+	 * To prevent processes with (partly) seeky workloads from
+	 * being too ill-treated, grant them a small fraction of the
+	 * assigned budget before reducing the waiting time to
+	 * BFQ_MIN_TT. This happened to help reduce latency.
+	 */
+	sl = bfqd->bfq_slice_idle;
+	/*
+	 * Unless the queue is being weight-raised or the scenario is
+	 * asymmetric, grant only minimum idle time if the queue
+	 * is seeky. A long idling is preserved for a weight-raised
+	 * queue, or, more in general, in an asymemtric scenario,
+	 * because a long idling is needed for guaranteeing to a queue
+	 * its reserved share of the throughput (in particular, it is
+	 * needed if the queue has a higher weight than some other
+	 * queue).
+	 */
+	if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
+	    bfq_symmetric_scenario(bfqd))
+		sl = min_t(u32, 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));
+	bfq_log(bfqd, "arm idle: %ld/%ld ms",
+		sl / NSEC_PER_MSEC, bfqd->bfq_slice_idle / NSEC_PER_MSEC);
+}
+
+/*
+ * In autotuning mode, max_budget is dynamically recomputed as the
+ * amount of sectors transferred in timeout at the estimated peak
+ * rate. This enables BFQ to utilize a full timeslice with a full
+ * budget, even if the in-service queue is served at peak rate. And
+ * this maximises throughput with sequential workloads.
+ */
+static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd)
+{
+	return (u64)bfqd->peak_rate * USEC_PER_MSEC *
+		jiffies_to_msecs(bfqd->bfq_timeout)>>BFQ_RATE_SHIFT;
+}
+
+/*
+ * Update parameters related to throughput and responsiveness, as a
+ * function of the estimated peak rate. See comments on
+ * bfq_calc_max_budget(), and on T_slow and T_fast arrays.
+ */
+static void update_thr_responsiveness_params(struct bfq_data *bfqd)
+{
+	int dev_type = blk_queue_nonrot(bfqd->queue);
+
+	if (bfqd->bfq_user_max_budget == 0) {
+		bfqd->bfq_max_budget =
+			bfq_calc_max_budget(bfqd);
+		BUG_ON(bfqd->bfq_max_budget < 0);
+		bfq_log(bfqd, "new max_budget = %d",
+			bfqd->bfq_max_budget);
+	}
+
+	if (bfqd->device_speed == BFQ_BFQD_FAST &&
+	    bfqd->peak_rate < device_speed_thresh[dev_type]) {
+		bfqd->device_speed = BFQ_BFQD_SLOW;
+		bfqd->RT_prod = R_slow[dev_type] *
+			T_slow[dev_type];
+	} else if (bfqd->device_speed == BFQ_BFQD_SLOW &&
+		   bfqd->peak_rate > device_speed_thresh[dev_type]) {
+		bfqd->device_speed = BFQ_BFQD_FAST;
+		bfqd->RT_prod = R_fast[dev_type] *
+			T_fast[dev_type];
+	}
+
+	bfq_log(bfqd,
+"dev_type %s dev_speed_class = %s (%llu sects/sec), thresh %llu setcs/sec",
+		dev_type == 0 ? "ROT" : "NONROT",
+		bfqd->device_speed == BFQ_BFQD_FAST ? "FAST" : "SLOW",
+		bfqd->device_speed == BFQ_BFQD_FAST ?
+		(USEC_PER_SEC*(u64)R_fast[dev_type])>>BFQ_RATE_SHIFT :
+		(USEC_PER_SEC*(u64)R_slow[dev_type])>>BFQ_RATE_SHIFT,
+		(USEC_PER_SEC*(u64)device_speed_thresh[dev_type])>>
+		BFQ_RATE_SHIFT);
+}
+
+static void bfq_reset_rate_computation(struct bfq_data *bfqd, struct request *rq)
+{
+	if (rq != NULL) { /* new rq dispatch now, reset accordingly */
+		bfqd->last_dispatch = bfqd->first_dispatch = ktime_get_ns() ;
+		bfqd->peak_rate_samples = 1;
+		bfqd->sequential_samples = 0;
+		bfqd->tot_sectors_dispatched = bfqd->last_rq_max_size =
+			blk_rq_sectors(rq);
+	} else /* no new rq dispatched, just reset the number of samples */
+		bfqd->peak_rate_samples = 0; /* full re-init on next disp. */
+
+	bfq_log(bfqd,
+		"reset_rate_computation at end, sample %u/%u tot_sects %llu",
+		bfqd->peak_rate_samples, bfqd->sequential_samples,
+		bfqd->tot_sectors_dispatched);
+}
+
+static void bfq_update_rate_reset(struct bfq_data *bfqd, struct request *rq)
+{
+	u32 rate, weight, divisor;
+
+	/*
+	 * For the convergence property to hold (see comments on
+	 * bfq_update_peak_rate()) and for the assessment to be
+	 * reliable, a minimum number of samples must be present, and
+	 * a minimum amount of time must have elapsed. If not so, do
+	 * not compute new rate. Just reset parameters, to get ready
+	 * for a new evaluation attempt.
+	 */
+	if (bfqd->peak_rate_samples < BFQ_RATE_MIN_SAMPLES ||
+	    bfqd->delta_from_first < BFQ_RATE_MIN_INTERVAL) {
+		bfq_log(bfqd,
+	"update_rate_reset: only resetting, delta_first %lluus samples %d",
+			bfqd->delta_from_first>>10, bfqd->peak_rate_samples);
+		goto reset_computation;
+	}
+
+	/*
+	 * If a new request completion has occurred after last
+	 * dispatch, then, to approximate the rate at which requests
+	 * have been served by the device, it is more precise to
+	 * extend the observation interval to the last completion.
+	 */
+	bfqd->delta_from_first =
+		max_t(u64, bfqd->delta_from_first,
+		      bfqd->last_completion - bfqd->first_dispatch);
+
+	BUG_ON(bfqd->delta_from_first == 0);
+	/*
+	 * Rate computed in sects/usec, and not sects/nsec, for
+	 * precision issues.
+	 */
+	rate = div64_ul(bfqd->tot_sectors_dispatched<<BFQ_RATE_SHIFT,
+			div_u64(bfqd->delta_from_first, NSEC_PER_USEC));
+
+	bfq_log(bfqd,
+"update_rate_reset: tot_sects %llu delta_first %lluus rate %llu sects/s (%d)",
+		bfqd->tot_sectors_dispatched, bfqd->delta_from_first>>10,
+		((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT),
+		rate > 20<<BFQ_RATE_SHIFT);
+
+	/*
+	 * Peak rate not updated if:
+	 * - the percentage of sequential dispatches is below 3/4 of the
+	 *   total, and rate is below the current estimated peak rate
+	 * - rate is unreasonably high (> 20M sectors/sec)
+	 */
+	if ((bfqd->sequential_samples < (3 * bfqd->peak_rate_samples)>>2 &&
+	     rate <= bfqd->peak_rate) ||
+		rate > 20<<BFQ_RATE_SHIFT) {
+		bfq_log(bfqd,
+		"update_rate_reset: goto reset, samples %u/%u rate/peak %llu/%llu",
+		bfqd->peak_rate_samples, bfqd->sequential_samples,
+		((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT),
+		((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT));
+		goto reset_computation;
+	} else {
+		bfq_log(bfqd,
+		"update_rate_reset: do update, samples %u/%u rate/peak %llu/%llu",
+		bfqd->peak_rate_samples, bfqd->sequential_samples,
+		((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT),
+		((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT));
+	}
+
+	/*
+	 * We have to update the peak rate, at last! To this purpose,
+	 * we use a low-pass filter. We compute the smoothing constant
+	 * of the filter as a function of the 'weight' of the new
+	 * measured rate.
+	 *
+	 * As can be seen in next formulas, we define this weight as a
+	 * quantity proportional to how sequential the workload is,
+	 * and to how long the observation time interval is.
+	 *
+	 * The weight runs from 0 to 8. The maximum value of the
+	 * weight, 8, yields the minimum value for the smoothing
+	 * constant. At this minimum value for the smoothing constant,
+	 * the measured rate contributes for half of the next value of
+	 * the estimated peak rate.
+	 *
+	 * So, the first step is to compute the weight as a function
+	 * of how sequential the workload is. Note that the weight
+	 * cannot reach 9, because bfqd->sequential_samples cannot
+	 * become equal to bfqd->peak_rate_samples, which, in its
+	 * turn, holds true because bfqd->sequential_samples is not
+	 * incremented for the first sample.
+	 */
+	weight = (9 * bfqd->sequential_samples) / bfqd->peak_rate_samples;
+
+	/*
+	 * Second step: further refine the weight as a function of the
+	 * duration of the observation interval.
+	 */
+	weight = min_t(u32, 8,
+		       div_u64(weight * bfqd->delta_from_first,
+			       BFQ_RATE_REF_INTERVAL));
+
+	/*
+	 * Divisor ranging from 10, for minimum weight, to 2, for
+	 * maximum weight.
+	 */
+	divisor = 10 - weight;
+	BUG_ON(divisor == 0);
+
+	/*
+	 * Finally, update peak rate:
+	 *
+	 * peak_rate = peak_rate * (divisor-1) / divisor  +  rate / divisor
+	 */
+	bfqd->peak_rate *= divisor-1;
+	bfqd->peak_rate /= divisor;
+	rate /= divisor; /* smoothing constant alpha = 1/divisor */
+
+	bfq_log(bfqd,
+		"update_rate_reset: divisor %d tmp_peak_rate %llu tmp_rate %u",
+		divisor,
+		((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT),
+		(u32)((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT));
+
+	BUG_ON(bfqd->peak_rate == 0);
+	BUG_ON(bfqd->peak_rate > 20<<BFQ_RATE_SHIFT);
+
+	bfqd->peak_rate += rate;
+	update_thr_responsiveness_params(bfqd);
+	BUG_ON(bfqd->peak_rate > 20<<BFQ_RATE_SHIFT);
+
+reset_computation:
+	bfq_reset_rate_computation(bfqd, rq);
+}
+
+/*
+ * Update the read/write peak rate (the main quantity used for
+ * auto-tuning, see update_thr_responsiveness_params()).
+ *
+ * It is not trivial to estimate the peak rate (correctly): because of
+ * the presence of sw and hw queues between the scheduler and the
+ * device components that finally serve I/O requests, it is hard to
+ * say exactly when a given dispatched request is served inside the
+ * device, and for how long. As a consequence, it is hard to know
+ * precisely at what rate a given set of requests is actually served
+ * by the device.
+ *
+ * On the opposite end, the dispatch time of any request is trivially
+ * available, and, from this piece of information, the "dispatch rate"
+ * of requests can be immediately computed. So, the idea in the next
+ * function is to use what is known, namely request dispatch times
+ * (plus, when useful, request completion times), to estimate what is
+ * unknown, namely in-device request service rate.
+ *
+ * The main issue is that, because of the above facts, the rate at
+ * which a certain set of requests is dispatched over a certain time
+ * interval can vary greatly with respect to the rate at which the
+ * same requests are then served. But, since the size of any
+ * intermediate queue is limited, and the service scheme is lossless
+ * (no request is silently dropped), the following obvious convergence
+ * property holds: the number of requests dispatched MUST become
+ * closer and closer to the number of requests completed as the
+ * observation interval grows. This is the key property used in
+ * the next function to estimate the peak service rate as a function
+ * of the observed dispatch rate. The function assumes to be invoked
+ * on every request dispatch.
+ */
+static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq)
+{
+	u64 now_ns = ktime_get_ns();
+
+	if (bfqd->peak_rate_samples == 0) { /* first dispatch */
+		bfq_log(bfqd,
+		"update_peak_rate: goto reset, samples %d",
+				bfqd->peak_rate_samples) ;
+		bfq_reset_rate_computation(bfqd, rq);
+		goto update_last_values; /* will add one sample */
+	}
+
+	/*
+	 * Device idle for very long: the observation interval lasting
+	 * up to this dispatch cannot be a valid observation interval
+	 * for computing a new peak rate (similarly to the late-
+	 * completion event in bfq_completed_request()). Go to
+	 * update_rate_and_reset to have the following three steps
+	 * taken:
+	 * - close the observation interval at the last (previous)
+	 *   request dispatch or completion
+	 * - compute rate, if possible, for that observation interval
+	 * - start a new observation interval with this dispatch
+	 */
+	if (now_ns - bfqd->last_dispatch > 100*NSEC_PER_MSEC &&
+	    bfqd->rq_in_driver == 0) {
+		bfq_log(bfqd,
+"update_peak_rate: jumping to updating&resetting delta_last %lluus samples %d",
+			(now_ns - bfqd->last_dispatch)>>10,
+			bfqd->peak_rate_samples) ;
+		goto update_rate_and_reset;
+	}
+
+	/* Update sampling information */
+	bfqd->peak_rate_samples++;
+
+	if ((bfqd->rq_in_driver > 0 ||
+		now_ns - bfqd->last_completion < BFQ_MIN_TT)
+	     && get_sdist(bfqd->last_position, rq) < BFQQ_SEEK_THR)
+		bfqd->sequential_samples++;
+
+	bfqd->tot_sectors_dispatched += blk_rq_sectors(rq);
+
+	/* Reset max observed rq size every 32 dispatches */
+	if (likely(bfqd->peak_rate_samples % 32))
+		bfqd->last_rq_max_size =
+			max_t(u32, blk_rq_sectors(rq), bfqd->last_rq_max_size);
+	else
+		bfqd->last_rq_max_size = blk_rq_sectors(rq);
+
+	bfqd->delta_from_first = now_ns - bfqd->first_dispatch;
+
+	bfq_log(bfqd,
+	"update_peak_rate: added samples %u/%u tot_sects %llu delta_first %lluus",
+		bfqd->peak_rate_samples, bfqd->sequential_samples,
+		bfqd->tot_sectors_dispatched,
+		bfqd->delta_from_first>>10);
+
+	/* Target observation interval not yet reached, go on sampling */
+	if (bfqd->delta_from_first < BFQ_RATE_REF_INTERVAL)
+		goto update_last_values;
+
+update_rate_and_reset:
+	bfq_update_rate_reset(bfqd, rq);
+update_last_values:
+	bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
+	bfqd->last_dispatch = now_ns;
+
+	bfq_log(bfqd,
+	"update_peak_rate: delta_first %lluus last_pos %llu peak_rate %llu",
+		(now_ns - bfqd->first_dispatch)>>10,
+		(unsigned long long) bfqd->last_position,
+		((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT));
+	bfq_log(bfqd,
+	"update_peak_rate: samples at end %d", bfqd->peak_rate_samples);
+}
+
+/*
+ * Move request from internal lists to the dispatch list of the request queue
+ */
+static void bfq_dispatch_insert(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, in a forced_dispatch, this prevents two counters related
+	 * to bfqq->dispatched to risk to be uselessly decremented if bfqq
+	 * is not in service, and then to be incremented again after
+	 * incrementing bfqq->dispatched.
+	 */
+	bfqq->dispatched++;
+	bfq_update_peak_rate(q->elevator->elevator_data, rq);
+
+	bfq_remove_request(rq);
+	elv_dispatch_sort(q, rq);
+}
+
+static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	BUG_ON(bfqq != bfqd->in_service_queue);
+
+	/*
+	 * If this bfqq is shared between multiple processes, check
+	 * to make sure that those processes are still issuing I/Os
+	 * within the mean seek distance. If not, it may be time to
+	 * break the queues apart again.
+	 */
+	if (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq))
+		bfq_mark_bfqq_split_coop(bfqq);
+
+	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		if (bfqq->dispatched == 0)
+			/*
+			 * Overloading budget_timeout field to store
+			 * the time at which the queue remains with no
+			 * backlog and no outstanding request; used by
+			 * the weight-raising mechanism.
+			 */
+			bfqq->budget_timeout = jiffies;
+
+		bfq_del_bfqq_busy(bfqd, bfqq, true);
+	} else {
+		bfq_requeue_bfqq(bfqd, bfqq);
+		/*
+		 * Resort priority tree of potential close cooperators.
+		 */
+		bfq_pos_tree_add_move(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;
+
+	BUG_ON(bfqq != bfqd->in_service_queue);
+
+	min_budget = bfq_min_budget(bfqd);
+
+	if (bfqq->wr_coeff == 1)
+		budget = bfqq->max_budget;
+	else /*
+	      * Use a constant, low budget for weight-raised queues,
+	      * to help achieve a low latency. Keep it slightly higher
+	      * than the minimum possible budget, to cause a little
+	      * bit fewer expirations.
+	      */
+		budget = 2 * min_budget;
+
+	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) && bfqq->wr_coeff == 1) {
+		switch (reason) {
+		/*
+		 * Caveat: in all the following cases we trade latency
+		 * for throughput.
+		 */
+		case BFQ_BFQQ_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 BFQ_BFQQ_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 BFQ_BFQQ_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 BFQ_BFQQ_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
+			 * BFQ_BFQQ_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 if (!bfq_bfqq_sync(bfqq))
+		/*
+		 * 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) {
+		BUG_ON(reason == BFQ_BFQQ_TOO_IDLE ||
+		       reason == BFQ_BFQQ_NO_MORE_REQUESTS);
+		bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget,
+					    bfq_serv_to_charge(next_rq, bfqq));
+		BUG_ON(!bfq_bfqq_busy(bfqq));
+		BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list));
+	}
+
+	bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %d",
+			next_rq ? blk_rq_sectors(next_rq) : 0,
+			bfqq->entity.budget);
+}
+
+/*
+ * Return true if the process associated with bfqq is "slow". The slow
+ * flag is used, in addition to the budget timeout, to reduce the
+ * amount of service provided to seeky processes, and thus reduce
+ * their chances to lower the throughput. More details in the comments
+ * on the function bfq_bfqq_expire().
+ *
+ * An important observation is in order: as discussed in the comments
+ * on the function bfq_update_peak_rate(), with devices with internal
+ * queues, it is hard if ever possible to know when and for how long
+ * an I/O request is processed by the device (apart from the trivial
+ * I/O pattern where a new request is dispatched only after the
+ * previous one has been completed). This makes it hard to evaluate
+ * the real rate at which the I/O requests of each bfq_queue are
+ * served.  In fact, for an I/O scheduler like BFQ, serving a
+ * bfq_queue means just dispatching its requests during its service
+ * slot (i.e., until the budget of the queue is exhausted, or the
+ * queue remains idle, or, finally, a timeout fires). But, during the
+ * service slot of a bfq_queue, around 100 ms at most, the device may
+ * be even still processing requests of bfq_queues served in previous
+ * service slots. On the opposite end, the requests of the in-service
+ * bfq_queue may be completed after the service slot of the queue
+ * finishes.
+ *
+ * Anyway, unless more sophisticated solutions are used
+ * (where possible), the sum of the sizes of the requests dispatched
+ * during the service slot of a bfq_queue is probably the only
+ * approximation available for the service received by the bfq_queue
+ * during its service slot. And this sum is the quantity used in this
+ * function to evaluate the I/O speed of a process.
+ */
+static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+				 bool compensate, enum bfqq_expiration reason,
+				 unsigned long *delta_ms)
+{
+	ktime_t delta_ktime;
+	u32 delta_usecs;
+	bool slow = BFQQ_SEEKY(bfqq); /* if delta too short, use seekyness */
+
+	if (!bfq_bfqq_sync(bfqq))
+		return false;
+
+	if (compensate)
+		delta_ktime = bfqd->last_idling_start;
+	else
+		delta_ktime = ktime_get();
+	delta_ktime = ktime_sub(delta_ktime, bfqd->last_budget_start);
+	delta_usecs = ktime_to_us(delta_ktime);
+
+	/* don't use too short time intervals */
+	if (delta_usecs < 1000) {
+		if (blk_queue_nonrot(bfqd->queue))
+			 /*
+			  * give same worst-case guarantees as idling
+			  * for seeky
+			  */
+			*delta_ms = BFQ_MIN_TT / NSEC_PER_MSEC;
+		else /* charge at least one seek */
+			*delta_ms = bfq_slice_idle / NSEC_PER_MSEC;
+
+		bfq_log(bfqd, "bfq_bfqq_is_slow: too short %u", delta_usecs);
+
+		return slow;
+	}
+
+	*delta_ms = delta_usecs / USEC_PER_MSEC;
+
+	/*
+	 * Use only long (> 20ms) intervals to filter out excessive
+	 * spikes in service rate estimation.
+	 */
+	if (delta_usecs > 20000) {
+		/*
+		 * Caveat for rotational devices: processes doing I/O
+		 * in the slower disk zones tend to be slow(er) even
+		 * if not seeky. In this respect, the estimated peak
+		 * rate is likely to be an average over the disk
+		 * surface. Accordingly, to not be too harsh with
+		 * unlucky processes, a process is deemed slow only if
+		 * its rate has been lower than half of the estimated
+		 * peak rate.
+		 */
+		slow = bfqq->entity.service < bfqd->bfq_max_budget / 2;
+		bfq_log(bfqd, "bfq_bfqq_is_slow: relative rate %d/%d",
+			bfqq->entity.service, bfqd->bfq_max_budget);
+	}
+
+	bfq_log_bfqq(bfqd, bfqq, "bfq_bfqq_is_slow: slow %d", slow);
+
+	return slow;
+}
+
+/*
+ * To be deemed as soft real-time, an application must meet two
+ * requirements. First, the application must not require an average
+ * bandwidth higher than the approximate bandwidth required to playback or
+ * record a compressed high-definition video.
+ * The next function is invoked on the completion of the last request of a
+ * batch, to compute the next-start time instant, soft_rt_next_start, such
+ * that, if the next request of the application does not arrive before
+ * soft_rt_next_start, then the above requirement on the bandwidth is met.
+ *
+ * The second requirement is that the request pattern of the application is
+ * isochronous, i.e., that, after issuing a request or a batch of requests,
+ * the application stops issuing new requests until all its pending requests
+ * have been completed. After that, the application may issue a new batch,
+ * and so on.
+ * For this reason the next function is invoked to compute
+ * soft_rt_next_start only for applications that meet this requirement,
+ * whereas soft_rt_next_start is set to infinity for applications that do
+ * not.
+ *
+ * Unfortunately, even a greedy application may happen to behave in an
+ * isochronous way if the CPU load is high. In fact, the application may
+ * stop issuing requests while the CPUs are busy serving other processes,
+ * then restart, then stop again for a while, and so on. In addition, if
+ * the disk achieves a low enough throughput with the request pattern
+ * issued by the application (e.g., because the request pattern is random
+ * and/or the device is slow), then the application may meet the above
+ * bandwidth requirement too. To prevent such a greedy application to be
+ * deemed as soft real-time, a further rule is used in the computation of
+ * soft_rt_next_start: soft_rt_next_start must be higher than the current
+ * time plus the maximum time for which the arrival of a request is waited
+ * for when a sync queue becomes idle, namely bfqd->bfq_slice_idle.
+ * This filters out greedy applications, as the latter issue instead their
+ * next request as soon as possible after the last one has been completed
+ * (in contrast, when a batch of requests is completed, a soft real-time
+ * application spends some time processing data).
+ *
+ * Unfortunately, the last filter may easily generate false positives if
+ * only bfqd->bfq_slice_idle is used as a reference time interval and one
+ * or both the following cases occur:
+ * 1) HZ is so low that the duration of a jiffy is comparable to or higher
+ *    than bfqd->bfq_slice_idle. This happens, e.g., on slow devices with
+ *    HZ=100.
+ * 2) jiffies, instead of increasing at a constant rate, may stop increasing
+ *    for a while, then suddenly 'jump' by several units to recover the lost
+ *    increments. This seems to happen, e.g., inside virtual machines.
+ * To address this issue, we do not use as a reference time interval just
+ * bfqd->bfq_slice_idle, but bfqd->bfq_slice_idle plus a few jiffies. In
+ * particular we add the minimum number of jiffies for which the filter
+ * seems to be quite precise also in embedded systems and KVM/QEMU virtual
+ * machines.
+ */
+static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
+						struct bfq_queue *bfqq)
+{
+	bfq_log_bfqq(bfqd, bfqq,
+"softrt_next_start: service_blkg %lu soft_rate %u sects/sec interval %u",
+		     bfqq->service_from_backlogged,
+		     bfqd->bfq_wr_max_softrt_rate,
+		     jiffies_to_msecs(HZ * bfqq->service_from_backlogged /
+				      bfqd->bfq_wr_max_softrt_rate));
+
+	return max(bfqq->last_idle_bklogged +
+		   HZ * bfqq->service_from_backlogged /
+		   bfqd->bfq_wr_max_softrt_rate,
+		   jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
+}
+
+/*
+ * Return the farthest future time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_greatest_from_now(void)
+{
+	return jiffies + MAX_JIFFY_OFFSET;
+}
+
+/*
+ * 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 bfqq does slow I/O (e.g., because it
+ * issues random requests), we charge bfqq with the time it has been
+ * in service instead of the service it has received (see
+ * bfq_bfqq_charge_time for details on how this goal is achieved). As
+ * a consequence, bfqq will typically get higher timestamps upon
+ * reactivation, and hence it will be rescheduled as if it had
+ * received more service than what it has actually received. In the
+ * end, bfqq receives less service in proportion to how slowly its
+ * associated process consumes its budgets (and hence how seriously it
+ * tends to lower the throughput). In addition, this time-charging
+ * strategy guarantees time fairness among slow processes. In
+ * contrast, if the process associated with bfqq is not slow, we
+ * charge bfqq exactly with the service it has received.
+ *
+ * Charging time to the first type of queues and the exact service to
+ * the other has the effect of using the WF2Q+ policy to schedule the
+ * former on a timeslice basis, without violating service domain
+ * guarantees among the latter.
+ */
+static void bfq_bfqq_expire(struct bfq_data *bfqd,
+			    struct bfq_queue *bfqq,
+			    bool compensate,
+			    enum bfqq_expiration reason)
+{
+	bool slow;
+	unsigned long delta = 0;
+	struct bfq_entity *entity = &bfqq->entity;
+	int ref;
+
+	BUG_ON(bfqq != bfqd->in_service_queue);
+
+	/*
+	 * Check whether the process is slow (see bfq_bfqq_is_slow).
+	 */
+	slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta);
+
+	/*
+	 * Increase service_from_backlogged before next statement,
+	 * because the possible next invocation of
+	 * bfq_bfqq_charge_time would likely inflate
+	 * entity->service. In contrast, service_from_backlogged must
+	 * contain real service, to enable the soft real-time
+	 * heuristic to correctly compute the bandwidth consumed by
+	 * bfqq.
+	 */
+	bfqq->service_from_backlogged += entity->service;
+
+	/*
+	 * As above explained, charge slow (typically seeky) and
+	 * timed-out queues with the time and not the service
+	 * received, to favor sequential workloads.
+	 *
+	 * Processes doing I/O in the slower disk zones will tend to
+	 * be slow(er) even if not seeky. Therefore, since the
+	 * estimated peak rate is actually an average over the disk
+	 * surface, these processes may timeout just for bad luck. To
+	 * avoid punishing them, do not charge time to processes that
+	 * succeeded in consuming at least 2/3 of their budget. This
+	 * allows BFQ to preserve enough elasticity to still perform
+	 * bandwidth, and not time, distribution with little unlucky
+	 * or quasi-sequential processes.
+	 */
+	if (bfqq->wr_coeff == 1 &&
+	    (slow ||
+	     (reason == BFQ_BFQQ_BUDGET_TIMEOUT &&
+	      bfq_bfqq_budget_left(bfqq) >=  entity->budget / 3)))
+		bfq_bfqq_charge_time(bfqd, bfqq, delta);
+
+	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
+
+	if (reason == BFQ_BFQQ_TOO_IDLE &&
+	    entity->service <= 2 * entity->budget / 10)
+		bfq_clear_bfqq_IO_bound(bfqq);
+
+	if (bfqd->low_latency && bfqq->wr_coeff == 1)
+		bfqq->last_wr_start_finish = jiffies;
+
+	if (bfqd->low_latency && bfqd->bfq_wr_max_softrt_rate > 0 &&
+	    RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		/*
+		 * If we get here, and there are no outstanding
+		 * requests, then the request pattern is isochronous
+		 * (see the comments on the function
+		 * bfq_bfqq_softrt_next_start()). Thus we can compute
+		 * soft_rt_next_start. If, instead, the queue still
+		 * has outstanding requests, then we have to wait for
+		 * the completion of all the outstanding requests to
+		 * discover whether the request pattern is actually
+		 * isochronous.
+		 */
+		BUG_ON(bfqd->busy_queues < 1);
+		if (bfqq->dispatched == 0) {
+			bfqq->soft_rt_next_start =
+				bfq_bfqq_softrt_next_start(bfqd, bfqq);
+			bfq_log_bfqq(bfqd, bfqq, "new soft_rt_next %lu",
+				     bfqq->soft_rt_next_start);
+		} else {
+			/*
+			 * The application is still waiting for the
+			 * completion of one or more requests:
+			 * prevent it from possibly being incorrectly
+			 * deemed as soft real-time by setting its
+			 * soft_rt_next_start to infinity. In fact,
+			 * without this assignment, the application
+			 * would be incorrectly deemed as soft
+			 * real-time if:
+			 * 1) it issued a new request before the
+			 *    completion of all its in-flight
+			 *    requests, and
+			 * 2) at that time, its soft_rt_next_start
+			 *    happened to be in the past.
+			 */
+			bfqq->soft_rt_next_start =
+				bfq_greatest_from_now();
+			/*
+			 * Schedule an update of soft_rt_next_start to when
+			 * the task may be discovered to be isochronous.
+			 */
+			bfq_mark_bfqq_softrt_update(bfqq);
+		}
+	}
+
+	bfq_log_bfqq(bfqd, bfqq,
+		"expire (%d, slow %d, num_disp %d, short_ttime %d, weight %d)",
+		     reason, slow, bfqq->dispatched,
+		     bfq_bfqq_has_short_ttime(bfqq), entity->weight);
+
+	/*
+	 * Increase, decrease or leave budget unchanged according to
+	 * reason.
+	 */
+	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
+	__bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
+	BUG_ON(bfqq->next_rq == NULL &&
+	       bfqq->entity.budget < bfqq->entity.service);
+	ref = bfqq->ref;
+	__bfq_bfqq_expire(bfqd, bfqq);
+
+	BUG_ON(ref > 1 &&
+	       !bfq_bfqq_busy(bfqq) && reason == BFQ_BFQQ_BUDGET_EXHAUSTED &&
+		!bfq_class_idle(bfqq));
+
+	/* mark bfqq as waiting a request only if a bic still points to it */
+	if (ref > 1 && !bfq_bfqq_busy(bfqq) &&
+	    reason != BFQ_BFQQ_BUDGET_TIMEOUT &&
+	    reason != BFQ_BFQQ_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)
+{
+	return time_is_before_eq_jiffies(bfqq->budget_timeout);
+}
+
+/*
+ * 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 that queue. As a consequence, since
+ * device idling plays a critical role for both throughput boosting
+ * and service guarantees, the return value of this function plays a
+ * critical role as well.
+ *
+ * In a nutshell, this function returns true only if idling is
+ * beneficial for throughput or, even if detrimental for throughput,
+ * idling is however necessary to preserve service guarantees (low
+ * latency, desired throughput distribution, ...). In particular, on
+ * NCQ-capable devices, this function tries to return false, so as to
+ * help keep the drives' internal queues full, whenever this helps the
+ * device boost the throughput without causing any service-guarantee
+ * issue.
+ *
+ * In more detail, the return value of this function is obtained by,
+ * first, computing a number of boolean variables that take into
+ * account throughput and service-guarantee issues, and, then,
+ * combining these variables in a logical expression. Most of the
+ * issues taken into account are not trivial. We discuss these issues
+ * while introducing the variables.
+ */
+static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
+{
+	struct bfq_data *bfqd = bfqq->bfqd;
+	bool rot_without_queueing =
+		!blk_queue_nonrot(bfqd->queue) && !bfqd->hw_tag,
+		bfqq_sequential_and_IO_bound,
+		idling_boosts_thr, idling_boosts_thr_without_issues,
+		idling_needed_for_service_guarantees,
+		asymmetric_scenario;
+
+	if (bfqd->strict_guarantees)
+		return true;
+
+	/*
+	 * Idling is performed only if slice_idle > 0. In addition, we
+	 * do not idle if
+	 * (a) bfqq is async
+	 * (b) bfqq is in the idle io prio class: in this case we do
+	 * not idle because we want to minimize the bandwidth that
+	 * queues in this class can steal to higher-priority queues
+	 */
+	if (bfqd->bfq_slice_idle == 0 || !bfq_bfqq_sync(bfqq) ||
+	   bfq_class_idle(bfqq))
+		return false;
+
+	bfqq_sequential_and_IO_bound = !BFQQ_SEEKY(bfqq) &&
+		bfq_bfqq_IO_bound(bfqq) && bfq_bfqq_has_short_ttime(bfqq);
+	/*
+	 * The next variable takes into account the cases where idling
+	 * boosts the throughput.
+	 *
+	 * The value of the variable is computed considering, first, that
+	 * idling is virtually always beneficial for the throughput if:
+	 * (a) the device is not NCQ-capable and rotational, or
+	 * (b) regardless of the presence of NCQ, the device is rotational and
+	 *     the request pattern for bfqq is I/O-bound and sequential, or
+	 * (c) regardless of whether it is rotational, the device is
+	 *     not NCQ-capable and the request pattern for bfqq is
+	 *     I/O-bound and sequential.
+	 *
+	 * Secondly, and in contrast to the above item (b), idling an
+	 * NCQ-capable flash-based device would not boost the
+	 * throughput even with sequential I/O; rather it would lower
+	 * the throughput in proportion to how fast the device
+	 * is. Accordingly, the next variable is true if any of the
+	 * above conditions (a), (b) or (c) is true, and, in
+	 * particular, happens to be false if bfqd is an NCQ-capable
+	 * flash-based device.
+	 */
+	idling_boosts_thr = rot_without_queueing ||
+		((!blk_queue_nonrot(bfqd->queue) || !bfqd->hw_tag) &&
+		 bfqq_sequential_and_IO_bound);
+
+	/*
+	 * The value of the next variable,
+	 * idling_boosts_thr_without_issues, is equal to that of
+	 * idling_boosts_thr, unless a special case holds. In this
+	 * special case, described below, idling may cause problems to
+	 * weight-raised queues.
+	 *
+	 * When the request pool is saturated (e.g., in the presence
+	 * of write hogs), if the processes associated with
+	 * non-weight-raised queues ask for requests at a lower rate,
+	 * then processes associated with weight-raised queues have a
+	 * higher probability to get a request from the pool
+	 * immediately (or at least soon) when they need one. Thus
+	 * they have a higher probability to actually get a fraction
+	 * of the device throughput proportional to their high
+	 * weight. This is especially true with NCQ-capable drives,
+	 * which enqueue several requests in advance, and further
+	 * reorder internally-queued requests.
+	 *
+	 * For this reason, we force to false the value of
+	 * idling_boosts_thr_without_issues if there are weight-raised
+	 * busy queues. In this case, and if bfqq is not weight-raised,
+	 * this guarantees that the device is not idled for bfqq (if,
+	 * instead, bfqq is weight-raised, then idling will be
+	 * guaranteed by another variable, see below). Combined with
+	 * the timestamping rules of BFQ (see [1] for details), this
+	 * behavior causes bfqq, and hence any sync non-weight-raised
+	 * queue, to get a lower number of requests served, and thus
+	 * to ask for a lower number of requests from the request
+	 * pool, before the busy weight-raised queues get served
+	 * again. This often mitigates starvation problems in the
+	 * presence of heavy write workloads and NCQ, thereby
+	 * guaranteeing a higher application and system responsiveness
+	 * in these hostile scenarios.
+	 */
+	idling_boosts_thr_without_issues = idling_boosts_thr &&
+		bfqd->wr_busy_queues == 0;
+
+	/*
+	 * There is then a case where idling must be performed not
+	 * for throughput concerns, but to preserve service
+	 * guarantees.
+	 *
+	 * To introduce this case, we can note that allowing the drive
+	 * to enqueue more than one request at a time, and hence
+	 * delegating de facto final scheduling decisions to the
+	 * drive's internal scheduler, entails loss of control on the
+	 * actual request service order. In particular, the critical
+	 * situation is when requests from different processes happen
+	 * to be present, at the same time, in the internal queue(s)
+	 * of the drive. In such a situation, the drive, by deciding
+	 * the service order of the internally-queued requests, does
+	 * determine also the actual throughput distribution among
+	 * these processes. But the drive typically has no notion or
+	 * concern about per-process throughput distribution, and
+	 * makes its decisions only on a per-request basis. Therefore,
+	 * the service distribution enforced by the drive's internal
+	 * scheduler is likely to coincide with the desired
+	 * device-throughput distribution only in a completely
+	 * symmetric scenario where:
+	 * (i)  each of these processes must get the same throughput as
+	 *      the others;
+	 * (ii) all these processes have the same I/O pattern
+	 *      (either sequential or random).
+	 * In fact, in such a scenario, the drive will tend to treat
+	 * the requests of each of these processes in about the same
+	 * way as the requests of the others, and thus to provide
+	 * each of these processes with about the same throughput
+	 * (which is exactly the desired throughput distribution). In
+	 * contrast, in any asymmetric scenario, device idling is
+	 * certainly needed to guarantee that bfqq receives its
+	 * assigned fraction of the device throughput (see [1] for
+	 * details).
+	 *
+	 * We address this issue by controlling, actually, only the
+	 * symmetry sub-condition (i), i.e., provided that
+	 * sub-condition (i) holds, idling is not performed,
+	 * regardless of whether sub-condition (ii) holds. In other
+	 * words, only if sub-condition (i) holds, then idling is
+	 * allowed, and the device tends to be prevented from queueing
+	 * many requests, possibly of several processes. The reason
+	 * for not controlling also sub-condition (ii) is that we
+	 * exploit preemption to preserve guarantees in case of
+	 * symmetric scenarios, even if (ii) does not hold, as
+	 * explained in the next two paragraphs.
+	 *
+	 * Even if a queue, say Q, is expired when it remains idle, Q
+	 * can still preempt the new in-service queue if the next
+	 * request of Q arrives soon (see the comments on
+	 * bfq_bfqq_update_budg_for_activation). If all queues and
+	 * groups have the same weight, this form of preemption,
+	 * combined with the hole-recovery heuristic described in the
+	 * comments on function bfq_bfqq_update_budg_for_activation,
+	 * are enough to preserve a correct bandwidth distribution in
+	 * the mid term, even without idling. In fact, even if not
+	 * idling allows the internal queues of the device to contain
+	 * many requests, and thus to reorder requests, we can rather
+	 * safely assume that the internal scheduler still preserves a
+	 * minimum of mid-term fairness. The motivation for using
+	 * preemption instead of idling is that, by not idling,
+	 * service guarantees are preserved without minimally
+	 * sacrificing throughput. In other words, both a high
+	 * throughput and its desired distribution are obtained.
+	 *
+	 * More precisely, this preemption-based, idleless approach
+	 * provides fairness in terms of IOPS, and not sectors per
+	 * second. This can be seen with a simple example. Suppose
+	 * that there are two queues with the same weight, but that
+	 * the first queue receives requests of 8 sectors, while the
+	 * second queue receives requests of 1024 sectors. In
+	 * addition, suppose that each of the two queues contains at
+	 * most one request at a time, which implies that each queue
+	 * always remains idle after it is served. Finally, after
+	 * remaining idle, each queue receives very quickly a new
+	 * request. It follows that the two queues are served
+	 * alternatively, preempting each other if needed. This
+	 * implies that, although both queues have the same weight,
+	 * the queue with large requests receives a service that is
+	 * 1024/8 times as high as the service received by the other
+	 * queue.
+	 *
+	 * On the other hand, device idling is performed, and thus
+	 * pure sector-domain guarantees are provided, for the
+	 * following queues, which are likely to need stronger
+	 * throughput guarantees: weight-raised queues, and queues
+	 * with a higher weight than other queues. When such queues
+	 * are active, sub-condition (i) is false, which triggers
+	 * device idling.
+	 *
+	 * According to the above considerations, the next variable is
+	 * true (only) if sub-condition (i) holds. To compute the
+	 * value of this variable, we not only use the return value of
+	 * the function bfq_symmetric_scenario(), but also check
+	 * whether bfqq is being weight-raised, because
+	 * bfq_symmetric_scenario() does not take into account also
+	 * weight-raised queues (see comments on
+	 * bfq_weights_tree_add()).
+	 *
+	 * As a side note, it is worth considering that the above
+	 * device-idling countermeasures may however fail in the
+	 * following unlucky scenario: if idling is (correctly)
+	 * disabled in a time period during which all symmetry
+	 * sub-conditions hold, and hence the device is allowed to
+	 * enqueue many requests, but at some later point in time some
+	 * sub-condition stops to hold, then it may become impossible
+	 * to let requests be served in the desired order until all
+	 * the requests already queued in the device have been served.
+	 */
+	asymmetric_scenario = bfqq->wr_coeff > 1 ||
+		!bfq_symmetric_scenario(bfqd);
+
+	/*
+	 * Finally, there is a case where maximizing throughput is the
+	 * best choice even if it may cause unfairness toward
+	 * bfqq. Such a case is when bfqq became active in a burst of
+	 * queue activations. Queues that became active during a large
+	 * burst benefit only from throughput, as discussed in the
+	 * comments on bfq_handle_burst. Thus, if bfqq became active
+	 * in a burst and not idling the device maximizes throughput,
+	 * then the device must no be idled, because not idling the
+	 * device provides bfqq and all other queues in the burst with
+	 * maximum benefit. Combining this and the above case, we can
+	 * now establish when idling is actually needed to preserve
+	 * service guarantees.
+	 */
+	idling_needed_for_service_guarantees =
+		asymmetric_scenario && !bfq_bfqq_in_large_burst(bfqq);
+
+	/*
+	 * We have now all the components we need to compute the
+	 * return value of the function, which is true only if idling
+	 * either boosts the throughput (without issues), or is
+	 * necessary to preserve service guarantees.
+	 */
+	bfq_log_bfqq(bfqd, bfqq, "may_idle: sync %d idling_boosts_thr %d",
+		     bfq_bfqq_sync(bfqq), idling_boosts_thr);
+
+	bfq_log_bfqq(bfqd, bfqq,
+		     "may_idle: wr_busy %d boosts %d IO-bound %d guar %d",
+		     bfqd->wr_busy_queues,
+		     idling_boosts_thr_without_issues,
+		     bfq_bfqq_IO_bound(bfqq),
+		     idling_needed_for_service_guarantees);
+
+	return idling_boosts_thr_without_issues ||
+		idling_needed_for_service_guarantees;
+}
+
+/*
+ * 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)
+{
+	return RB_EMPTY_ROOT(&bfqq->sort_list) && 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 = BFQ_BFQQ_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) &&
+	    !hrtimer_active(&bfqd->idle_slice_timer) &&
+	    !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) {
+		BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list));
+
+		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 = BFQ_BFQQ_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)) {
+				BUG_ON(!hrtimer_active(&bfqd->idle_slice_timer));
+				/*
+				 * 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 (hrtimer_active(&bfqd->idle_slice_timer) ||
+	    (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) {
+		bfqq = NULL;
+		goto keep_queue;
+	}
+
+	reason = BFQ_BFQQ_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;
+}
+
+static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */
+		BUG_ON(bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
+		       time_is_after_jiffies(bfqq->last_wr_start_finish));
+
+		bfq_log_bfqq(bfqd, bfqq,
+			"raising period dur %u/%u msec, old coeff %u, w %d(%d)",
+			jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish),
+			jiffies_to_msecs(bfqq->wr_cur_max_time),
+			bfqq->wr_coeff,
+			bfqq->entity.weight, bfqq->entity.orig_weight);
+
+		BUG_ON(bfqq != bfqd->in_service_queue && entity->weight !=
+		       entity->orig_weight * bfqq->wr_coeff);
+		if (entity->prio_changed)
+			bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change");
+
+		/*
+		 * If the queue was activated in a burst, or too much
+		 * time has elapsed from the beginning of this
+		 * weight-raising period, then end weight raising.
+		 */
+		if (bfq_bfqq_in_large_burst(bfqq))
+			bfq_bfqq_end_wr(bfqq);
+		else if (time_is_before_jiffies(bfqq->last_wr_start_finish +
+					   bfqq->wr_cur_max_time)) {
+			if (bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time ||
+			time_is_before_jiffies(bfqq->wr_start_at_switch_to_srt +
+					bfq_wr_duration(bfqd)))
+				bfq_bfqq_end_wr(bfqq);
+			else {
+				/* switch back to interactive wr */
+				bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+				bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+				bfqq->last_wr_start_finish =
+					bfqq->wr_start_at_switch_to_srt;
+				BUG_ON(time_is_after_jiffies(
+					       bfqq->last_wr_start_finish));
+				bfqq->entity.prio_changed = 1;
+				bfq_log_bfqq(bfqd, bfqq,
+					"back to interactive wr");
+			}
+		}
+	}
+	/*
+	 * To improve latency (for this or other queues), immediately
+	 * update weight both if it must be raised and if it must be
+	 * lowered. Since, entity may be on some active tree here, and
+	 * might have a pending change of its ioprio class, invoke
+	 * next function with the last parameter unset (see the
+	 * comments on the function).
+	 */
+	if ((entity->weight > entity->orig_weight) != (bfqq->wr_coeff > 1))
+		__bfq_entity_update_weight_prio(bfq_entity_service_tree(entity),
+						entity, false);
+}
+
+/*
+ * Dispatch one request from bfqq, moving it to the request queue
+ * dispatch list.
+ */
+static int bfq_dispatch_request(struct bfq_data *bfqd,
+				struct bfq_queue *bfqq)
+{
+	int dispatched = 0;
+	struct request *rq = bfqq->next_rq;
+	unsigned long service_to_charge;
+
+	BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list));
+	BUG_ON(!rq);
+	service_to_charge = bfq_serv_to_charge(rq, bfqq);
+
+	BUG_ON(service_to_charge > bfq_bfqq_budget_left(bfqq));
+
+	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
+
+	bfq_bfqq_served(bfqq, service_to_charge);
+
+	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
+
+	bfq_dispatch_insert(bfqd->queue, rq);
+
+	/*
+	 * If weight raising has to terminate for bfqq, then next
+	 * function causes an immediate update of bfqq's weight,
+	 * without waiting for next activation. As a consequence, on
+	 * expiration, bfqq will be timestamped as if has never been
+	 * weight-raised during this service slot, even if it has
+	 * received part or even most of the service as a
+	 * weight-raised queue. This inflates bfqq's timestamps, which
+	 * is beneficial, as bfqq is then more willing to leave the
+	 * device immediately to possible other weight-raised queues.
+	 */
+	bfq_update_wr_data(bfqd, bfqq);
+
+	bfq_log_bfqq(bfqd, bfqq,
+			"dispatched %u sec req (%llu), budg left %d",
+			blk_rq_sectors(rq),
+			(unsigned long long) blk_rq_pos(rq),
+			bfq_bfqq_budget_left(bfqq));
+
+	dispatched++;
+
+	if (!bfqd->in_service_bic) {
+		atomic_long_inc(&RQ_BIC(rq)->icq.ioc->refcount);
+		bfqd->in_service_bic = RQ_BIC(rq);
+	}
+
+	if (bfqd->busy_queues > 1 && bfq_class_idle(bfqq))
+		goto expire;
+
+	return dispatched;
+
+expire:
+	bfq_bfqq_expire(bfqd, bfqq, false, BFQ_BFQQ_BUDGET_EXHAUSTED);
+	return dispatched;
+}
+
+static int __bfq_forced_dispatch_bfqq(struct bfq_queue *bfqq)
+{
+	int dispatched = 0;
+
+	while (bfqq->next_rq) {
+		bfq_dispatch_insert(bfqq->bfqd->queue, bfqq->next_rq);
+		dispatched++;
+	}
+
+	BUG_ON(!list_empty(&bfqq->fifo));
+	return dispatched;
+}
+
+/*
+ * Drain our current requests.
+ * Used for barriers and when switching io schedulers on-the-fly.
+ */
+static int bfq_forced_dispatch(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq, *n;
+	struct bfq_service_tree *st;
+	int dispatched = 0;
+
+	bfqq = bfqd->in_service_queue;
+	if (bfqq)
+		__bfq_bfqq_expire(bfqd, bfqq);
+
+	/*
+	 * Loop through classes, and be careful to leave the scheduler
+	 * in a consistent state, as feedback mechanisms and vtime
+	 * updates cannot be disabled during the process.
+	 */
+	list_for_each_entry_safe(bfqq, n, &bfqd->active_list, bfqq_list) {
+		st = bfq_entity_service_tree(&bfqq->entity);
+
+		dispatched += __bfq_forced_dispatch_bfqq(bfqq);
+
+		bfqq->max_budget = bfq_max_budget(bfqd);
+		bfq_forget_idle(st);
+	}
+
+	BUG_ON(bfqd->busy_queues != 0);
+
+	return dispatched;
+}
+
+static int bfq_dispatch_requests(struct request_queue *q, int force)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct bfq_queue *bfqq;
+
+	bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues);
+
+	if (bfqd->busy_queues == 0)
+		return 0;
+
+	if (unlikely(force))
+		return bfq_forced_dispatch(bfqd);
+
+	/*
+	 * 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)
+		return 0;
+
+	bfqq = bfq_select_queue(bfqd);
+	if (!bfqq)
+		return 0;
+
+	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
+
+	BUG_ON(bfq_bfqq_wait_request(bfqq));
+
+	if (!bfq_dispatch_request(bfqd, bfqq))
+		return 0;
+
+	bfq_log_bfqq(bfqd, bfqq, "dispatched %s request",
+			bfq_bfqq_sync(bfqq) ? "sync" : "async");
+
+	BUG_ON(bfqq->next_rq == NULL &&
+	       bfqq->entity.budget < bfqq->entity.service);
+	return 1;
+}
+
+/*
+ * 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.
+ *
+ * Queue 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_SQ_GROUP_IOSCHED
+	struct bfq_group *bfqg = bfqq_group(bfqq);
+#endif
+
+	BUG_ON(bfqq->ref <= 0);
+
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d", bfqq, bfqq->ref);
+	bfqq->ref--;
+	if (bfqq->ref)
+		return;
+
+	BUG_ON(rb_first(&bfqq->sort_list));
+	BUG_ON(bfqq->allocated[READ] + bfqq->allocated[WRITE] != 0);
+	BUG_ON(bfqq->entity.tree);
+	BUG_ON(bfq_bfqq_busy(bfqq));
+
+	if (bfq_bfqq_sync(bfqq))
+		/*
+		 * The fact that this queue is being destroyed does not
+		 * invalidate the fact that this queue may have been
+		 * activated during the current burst. As a consequence,
+		 * although the queue does not exist anymore, and hence
+		 * needs to be removed from the burst list if there,
+		 * the burst size has not to be decremented.
+		 */
+		hlist_del_init(&bfqq->burst_list_node);
+
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p freed", bfqq);
+
+	kmem_cache_free(bfq_pool, bfqq);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	bfqg_put(bfqg);
+#endif
+}
+
+static void bfq_put_cooperator(struct bfq_queue *bfqq)
+{
+	struct bfq_queue *__bfqq, *next;
+
+	/*
+	 * If this queue was scheduled to merge with another queue, be
+	 * sure to drop the reference taken on that queue (and others in
+	 * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs.
+	 */
+	__bfqq = bfqq->new_bfqq;
+	while (__bfqq) {
+		if (__bfqq == bfqq)
+			break;
+		next = __bfqq->new_bfqq;
+		bfq_put_queue(__bfqq);
+		__bfqq = next;
+	}
+}
+
+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_cooperator(bfqq);
+
+	bfq_put_queue(bfqq); /* release process reference */
+}
+
+static void bfq_init_icq(struct io_cq *icq)
+{
+	icq_to_bic(icq)->ttime.last_end_request = ktime_get_ns() - (1ULL<<32);
+}
+
+static void bfq_exit_icq(struct io_cq *icq)
+{
+	struct bfq_io_cq *bic = icq_to_bic(icq);
+	struct bfq_data *bfqd = bic_to_bfqd(bic);
+
+	if (bic_to_bfqq(bic, false)) {
+		bfq_exit_bfqq(bfqd, bic_to_bfqq(bic, false));
+		bic_set_bfqq(bic, NULL, false);
+	}
+
+	if (bic_to_bfqq(bic, true)) {
+		/*
+		 * If the bic is using a shared queue, put the reference
+		 * taken on the io_context when the bic started using a
+		 * shared bfq_queue.
+		 */
+		if (bfq_bfqq_coop(bic_to_bfqq(bic, true)))
+			put_io_context(icq->ioc);
+		bfq_exit_bfqq(bfqd, bic_to_bfqq(bic, true));
+		bic_set_bfqq(bic, NULL, true);
+	}
+}
+
+/*
+ * 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;
+
+	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;
+		break;
+	}
+
+	if (bfqq->new_ioprio >= IOPRIO_BE_NR) {
+		pr_crit("bfq_set_next_ioprio_data: new_ioprio %d\n",
+			bfqq->new_ioprio);
+		BUG();
+	}
+
+	bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio);
+	bfqq->entity.prio_changed = 1;
+	bfq_log_bfqq(bfqq->bfqd, bfqq,
+		     "set_next_ioprio_data: bic_class %d prio %d class %d",
+		     ioprio_class, bfqq->new_ioprio, bfqq->new_ioprio_class);
+}
+
+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;
+	unsigned long uninitialized_var(flags);
+	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);
+		bfq_log_bfqq(bfqd, bfqq,
+			     "check_ioprio_change: bfqq %p %d",
+			     bfqq, bfqq->ref);
+	}
+
+	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);
+	INIT_HLIST_NODE(&bfqq->burst_list_node);
+	BUG_ON(!hlist_unhashed(&bfqq->burst_list_node));
+
+	bfqq->ref = 0;
+	bfqq->bfqd = bfqd;
+
+	if (bic)
+		bfq_set_next_ioprio_data(bfqq, bic);
+
+	if (is_sync) {
+		/*
+		 * No need to mark as has_short_ttime if in
+		 * idle_class, because no device idling is performed
+		 * for queues in idle class
+		 */
+		if (!bfq_class_idle(bfqq))
+			/* tentatively mark as has_short_ttime */
+			bfq_mark_bfqq_has_short_ttime(bfqq);
+		bfq_mark_bfqq_sync(bfqq);
+		bfq_mark_bfqq_just_created(bfqq);
+	} else
+		bfq_clear_bfqq_sync(bfqq);
+	bfq_mark_bfqq_IO_bound(bfqq);
+
+	/* Tentative initial value to trade off between thr and lat */
+	bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3;
+	bfqq->pid = pid;
+
+	bfqq->wr_coeff = 1;
+	bfqq->last_wr_start_finish = jiffies;
+	bfqq->wr_start_at_switch_to_srt = bfq_smallest_from_now();
+	bfqq->budget_timeout = bfq_smallest_from_now();
+	bfqq->split_time = bfq_smallest_from_now();
+
+	/*
+	 * Set to the value for which bfqq will not be deemed as
+	 * soft rt when it becomes backlogged.
+	 */
+	bfqq->soft_rt_next_start = bfq_greatest_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:
+		BUG();
+	}
+}
+
+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_io_cq *bic)
+{
+	struct bfq_ttime *ttime = &bic->ttime;
+	u64 elapsed = ktime_get_ns() - bic->ttime.last_end_request;
+
+	elapsed = min_t(u64, elapsed, 2 * bfqd->bfq_slice_idle);
+
+	ttime->ttime_samples = (7*bic->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)
+{
+	bfqq->seek_history <<= 1;
+	bfqq->seek_history |=
+		get_sdist(bfqq->last_request_pos, rq) > BFQQ_SEEK_THR &&
+		(!blk_queue_nonrot(bfqd->queue) ||
+		 blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT);
+}
+
+static void bfq_update_has_short_ttime(struct bfq_data *bfqd,
+				       struct bfq_queue *bfqq,
+				       struct bfq_io_cq *bic)
+{
+	bool has_short_ttime = true;
+
+	/*
+	 * No need to update has_short_ttime if bfqq is async or in
+	 * idle io prio class, or if bfq_slice_idle is zero, because
+	 * no device idling is performed for bfqq in this case.
+	 */
+	if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq) ||
+	    bfqd->bfq_slice_idle == 0)
+		return;
+
+	/* Idle window just restored, statistics are meaningless. */
+	if (time_is_after_eq_jiffies(bfqq->split_time +
+				     bfqd->bfq_wr_min_idle_time))
+		return;
+
+	/* Think time is infinite if no process is linked to
+	 * bfqq. Otherwise check average think time to
+	 * decide whether to mark as has_short_ttime
+	 */
+	if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
+	    (bfq_sample_valid(bic->ttime.ttime_samples) &&
+	     bic->ttime.ttime_mean > bfqd->bfq_slice_idle))
+		has_short_ttime = false;
+
+	bfq_log_bfqq(bfqd, bfqq, "update_has_short_ttime: has_short_ttime %d",
+		has_short_ttime);
+
+	if (has_short_ttime)
+		bfq_mark_bfqq_has_short_ttime(bfqq);
+	else
+		bfq_clear_bfqq_has_short_ttime(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, bic);
+	bfq_update_has_short_ttime(bfqd, bfqq, bic);
+	bfq_update_io_seektime(bfqd, bfqq, rq);
+
+	bfq_log_bfqq(bfqd, bfqq,
+		     "rq_enqueued: has_short_ttime=%d (seeky %d)",
+		     bfq_bfqq_has_short_ttime(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,
+					BFQ_BFQQ_BUDGET_TIMEOUT);
+
+		/*
+		 * Let the request rip immediately, or let a new queue be
+		 * selected if bfqq has just been expired.
+		 */
+		__blk_run_queue(bfqd->queue);
+	}
+}
+
+static void bfq_insert_request(struct request_queue *q, struct request *rq)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq;
+
+	assert_spin_locked(bfqd->queue->queue_lock);
+
+	/*
+	 * An unplug may trigger a requeue of a request from the device
+	 * driver: make sure we are in process context while trying to
+	 * merge two bfq_queues.
+	 */
+	if (!in_interrupt()) {
+		new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true);
+		if (new_bfqq) {
+			if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq)
+				new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1);
+			/*
+			 * Release the request's reference to the old bfqq
+			 * and make sure one is taken to the shared queue.
+			 */
+			new_bfqq->allocated[rq_data_dir(rq)]++;
+			bfqq->allocated[rq_data_dir(rq)]--;
+			new_bfqq->ref++;
+			bfq_clear_bfqq_just_created(bfqq);
+			if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
+				bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
+						bfqq, new_bfqq);
+			/*
+			 * rq is about to be enqueued into new_bfqq,
+			 * release rq reference on bfqq
+			 */
+			bfq_put_queue(bfqq);
+			rq->elv.priv[1] = new_bfqq;
+			bfqq = new_bfqq;
+		}
+	}
+
+	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_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 request_queue *q, struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_data *bfqd = bfqq->bfqd;
+	u64 now_ns;
+	u32 delta_us;
+
+	bfq_log_bfqq(bfqd, bfqq, "completed one req with %u sects left",
+		     blk_rq_sectors(rq));
+
+	assert_spin_locked(bfqd->queue->queue_lock);
+	bfq_update_hw_tag(bfqd);
+
+	BUG_ON(!bfqd->rq_in_driver);
+	BUG_ON(!bfqq->dispatched);
+	bfqd->rq_in_driver--;
+	bfqq->dispatched--;
+	bfqg_stats_update_completion(bfqq_group(bfqq),
+				     rq_start_time_ns(rq),
+				     rq_io_start_time_ns(rq),
+				     rq->cmd_flags);
+
+	if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) {
+		BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
+		/*
+		 * Set budget_timeout (which we overload to store the
+		 * time at which the queue remains with no backlog and
+		 * no outstanding request; used by the weight-raising
+		 * mechanism).
+		 */
+		bfqq->budget_timeout = jiffies;
+
+		bfq_weights_tree_remove(bfqd, &bfqq->entity,
+					&bfqd->queue_weights_tree);
+	}
+
+	now_ns = ktime_get_ns();
+
+	RQ_BIC(rq)->ttime.last_end_request = now_ns;
+
+	/*
+	 * Using us instead of ns, to get a reasonable precision in
+	 * computing rate in next check.
+	 */
+	delta_us = div_u64(now_ns - bfqd->last_completion, NSEC_PER_USEC);
+
+	bfq_log(bfqd, "rq_completed: delta %uus/%luus max_size %u rate %llu/%llu",
+		delta_us, BFQ_MIN_TT/NSEC_PER_USEC, bfqd->last_rq_max_size,
+		(USEC_PER_SEC*
+		(u64)((bfqd->last_rq_max_size<<BFQ_RATE_SHIFT)/delta_us))
+			>>BFQ_RATE_SHIFT,
+		(USEC_PER_SEC*(u64)(1UL<<(BFQ_RATE_SHIFT-10)))>>BFQ_RATE_SHIFT);
+
+	/*
+	 * If the request took rather long to complete, and, according
+	 * to the maximum request size recorded, this completion latency
+	 * implies that the request was certainly served at a very low
+	 * rate (less than 1M sectors/sec), then the whole observation
+	 * interval that lasts up to this time instant cannot be a
+	 * valid time interval for computing a new peak rate.  Invoke
+	 * bfq_update_rate_reset to have the following three steps
+	 * taken:
+	 * - close the observation interval at the last (previous)
+	 *   request dispatch or completion
+	 * - compute rate, if possible, for that observation interval
+	 * - reset to zero samples, which will trigger a proper
+	 *   re-initialization of the observation interval on next
+	 *   dispatch
+	 */
+	if (delta_us > BFQ_MIN_TT/NSEC_PER_USEC &&
+	   (bfqd->last_rq_max_size<<BFQ_RATE_SHIFT)/delta_us <
+			1UL<<(BFQ_RATE_SHIFT - 10))
+		bfq_update_rate_reset(bfqd, NULL);
+	bfqd->last_completion = now_ns;
+
+	/*
+	 * If we are waiting to discover whether the request pattern
+	 * of the task associated with the queue is actually
+	 * isochronous, and both requisites for this condition to hold
+	 * are now satisfied, then compute soft_rt_next_start (see the
+	 * comments on the function bfq_bfqq_softrt_next_start()). We
+	 * schedule this delayed check when bfqq expires, if it still
+	 * has in-flight requests.
+	 */
+	if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 &&
+	    RB_EMPTY_ROOT(&bfqq->sort_list))
+		bfqq->soft_rt_next_start =
+			bfq_bfqq_softrt_next_start(bfqd, bfqq);
+
+	/*
+	 * 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 (bfqq->dispatched == 0 && bfq_bfqq_must_idle(bfqq)) {
+			bfq_arm_slice_timer(bfqd);
+			goto out;
+		} else if (bfq_may_expire_for_budg_timeout(bfqq))
+			bfq_bfqq_expire(bfqd, bfqq, false,
+					BFQ_BFQQ_BUDGET_TIMEOUT);
+		else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
+			 (bfqq->dispatched == 0 ||
+			  !bfq_bfqq_may_idle(bfqq)))
+			bfq_bfqq_expire(bfqd, bfqq, false,
+					BFQ_BFQQ_NO_MORE_REQUESTS);
+	}
+
+	if (!bfqd->rq_in_driver)
+		bfq_schedule_dispatch(bfqd);
+
+out:
+	return;
+}
+
+static int __bfq_may_queue(struct bfq_queue *bfqq)
+{
+	if (bfq_bfqq_wait_request(bfqq) && bfq_bfqq_must_alloc(bfqq)) {
+		bfq_clear_bfqq_must_alloc(bfqq);
+		return ELV_MQUEUE_MUST;
+	}
+
+	return ELV_MQUEUE_MAY;
+}
+
+static int bfq_may_queue(struct request_queue *q, unsigned int op)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct task_struct *tsk = current;
+	struct bfq_io_cq *bic;
+	struct bfq_queue *bfqq;
+
+	/*
+	 * Don't force setup of a queue from here, as a call to may_queue
+	 * does not necessarily imply that a request actually will be
+	 * queued. So just lookup a possibly existing queue, or return
+	 * 'may queue' if that fails.
+	 */
+	bic = bfq_bic_lookup(bfqd, tsk->io_context);
+	if (!bic)
+		return ELV_MQUEUE_MAY;
+
+	bfqq = bic_to_bfqq(bic, op_is_sync(op));
+	if (bfqq)
+		return __bfq_may_queue(bfqq);
+
+	return ELV_MQUEUE_MAY;
+}
+
+/*
+ * Queue lock held here.
+ */
+static void bfq_put_request(struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+
+	if (bfqq) {
+		const int rw = rq_data_dir(rq);
+
+		BUG_ON(!bfqq->allocated[rw]);
+		bfqq->allocated[rw]--;
+
+		rq->elv.priv[0] = NULL;
+		rq->elv.priv[1] = NULL;
+
+		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_request %p, %d",
+			     bfqq, bfqq->ref);
+		bfq_put_queue(bfqq);
+	}
+}
+
+/*
+ * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
+ * was the last process referring to that bfqq.
+ */
+static struct bfq_queue *
+bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
+{
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");
+
+	put_io_context(bic->icq.ioc);
+
+	if (bfqq_process_refs(bfqq) == 1) {
+		bfqq->pid = current->pid;
+		bfq_clear_bfqq_coop(bfqq);
+		bfq_clear_bfqq_split_coop(bfqq);
+		return bfqq;
+	}
+
+	bic_set_bfqq(bic, NULL, 1);
+
+	bfq_put_cooperator(bfqq);
+
+	bfq_put_queue(bfqq);
+	return NULL;
+}
+
+/*
+ * Allocate bfq data structures associated with this request.
+ */
+static int bfq_set_request(struct request_queue *q, struct request *rq,
+			   struct bio *bio, gfp_t gfp_mask)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
+	const int rw = rq_data_dir(rq);
+	const int is_sync = rq_is_sync(rq);
+	struct bfq_queue *bfqq;
+	unsigned long flags;
+	bool bfqq_already_existing = false, split = false;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+
+	if (!bic)
+		goto queue_fail;
+
+	bfq_check_ioprio_change(bic, bio);
+
+	bfq_bic_update_cgroup(bic, bio);
+
+new_queue:
+	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);
+		BUG_ON(!hlist_unhashed(&bfqq->burst_list_node));
+
+		bic_set_bfqq(bic, bfqq, is_sync);
+		if (split && is_sync) {
+			bfq_log_bfqq(bfqd, bfqq,
+				     "set_request: was_in_list %d "
+				     "was_in_large_burst %d "
+				     "large burst in progress %d",
+				     bic->was_in_burst_list,
+				     bic->saved_in_large_burst,
+				     bfqd->large_burst);
+
+			if ((bic->was_in_burst_list && bfqd->large_burst) ||
+			    bic->saved_in_large_burst) {
+				bfq_log_bfqq(bfqd, bfqq,
+					     "set_request: marking in "
+					     "large burst");
+				bfq_mark_bfqq_in_large_burst(bfqq);
+			} else {
+				bfq_log_bfqq(bfqd, bfqq,
+					     "set_request: clearing in "
+					     "large burst");
+				bfq_clear_bfqq_in_large_burst(bfqq);
+				if (bic->was_in_burst_list)
+					hlist_add_head(&bfqq->burst_list_node,
+						       &bfqd->burst_list);
+			}
+			bfqq->split_time = jiffies;
+		}
+	} else {
+		/* If the queue was seeky for too long, break it apart. */
+		if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
+			bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
+
+			/* Update bic before losing reference to bfqq */
+			if (bfq_bfqq_in_large_burst(bfqq))
+				bic->saved_in_large_burst = true;
+
+			bfqq = bfq_split_bfqq(bic, bfqq);
+			split = true;
+			if (!bfqq)
+				goto new_queue;
+			else
+				bfqq_already_existing = true;
+		}
+	}
+
+	bfqq->allocated[rw]++;
+	bfqq->ref++;
+	bfq_log_bfqq(bfqd, bfqq, "set_request: bfqq %p, %d", bfqq, bfqq->ref);
+
+	rq->elv.priv[0] = bic;
+	rq->elv.priv[1] = bfqq;
+
+	/*
+	 * If a bfq_queue has only one process reference, it is owned
+	 * by only one bfq_io_cq: we can set the bic field of the
+	 * bfq_queue to the address of that structure. Also, if the
+	 * queue has just been split, mark a flag so that the
+	 * information is available to the other scheduler hooks.
+	 */
+	if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) {
+		bfqq->bic = bic;
+		if (split) {
+			/*
+			 * If the queue has just been split from a shared
+			 * queue, restore the idle window and the possible
+			 * weight raising period.
+			 */
+			bfq_bfqq_resume_state(bfqq, bfqd, bic,
+					      bfqq_already_existing);
+		}
+	}
+
+	if (unlikely(bfq_bfqq_just_created(bfqq)))
+		bfq_handle_burst(bfqd, bfqq);
+
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	return 0;
+
+queue_fail:
+	bfq_schedule_dispatch(bfqd);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	return 1;
+}
+
+static void bfq_kick_queue(struct work_struct *work)
+{
+	struct bfq_data *bfqd =
+		container_of(work, struct bfq_data, unplug_work);
+	struct request_queue *q = bfqd->queue;
+
+	spin_lock_irq(q->queue_lock);
+	__blk_run_queue(q);
+	spin_unlock_irq(q->queue_lock);
+}
+
+/*
+ * 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;
+	unsigned long flags;
+	enum bfqq_expiration reason;
+
+	spin_lock_irqsave(bfqd->queue->queue_lock, flags);
+
+	bfqq = bfqd->in_service_queue;
+	/*
+	 * Theoretical race here: the in-service queue can be NULL or
+	 * different from the queue that was idling if the timer handler
+	 * spins on the queue_lock and 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_log_bfqq(bfqd, bfqq, "slice_timer expired");
+		bfq_clear_bfqq_wait_request(bfqq);
+
+		if (bfq_bfqq_budget_timeout(bfqq))
+			/*
+			 * Also here the queue can be safely expired
+			 * for budget timeout without wasting
+			 * guarantees
+			 */
+			reason = BFQ_BFQQ_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 = BFQ_BFQQ_TOO_IDLE;
+		else
+			goto schedule_dispatch;
+
+		bfq_bfqq_expire(bfqd, bfqq, true, reason);
+	}
+
+schedule_dispatch:
+	bfq_schedule_dispatch(bfqd);
+
+	spin_unlock_irqrestore(bfqd->queue->queue_lock, flags);
+	return HRTIMER_NORESTART;
+}
+
+static void bfq_shutdown_timer_wq(struct bfq_data *bfqd)
+{
+	hrtimer_cancel(&bfqd->idle_slice_timer);
+	cancel_work_sync(&bfqd->unplug_work);
+}
+
+static void __bfq_put_async_bfqq(struct bfq_data *bfqd,
+				 struct bfq_queue **bfqq_ptr)
+{
+	struct bfq_group *root_group = bfqd->root_group;
+	struct bfq_queue *bfqq = *bfqq_ptr;
+
+	bfq_log(bfqd, "put_async_bfqq: %p", bfqq);
+	if (bfqq) {
+		bfq_bfqq_move(bfqd, bfqq, 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 request_queue *q = bfqd->queue;
+	struct bfq_queue *bfqq, *n;
+
+	bfq_shutdown_timer_wq(bfqd);
+
+	spin_lock_irq(q->queue_lock);
+
+	BUG_ON(bfqd->in_service_queue);
+	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
+		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
+
+	spin_unlock_irq(q->queue_lock);
+
+	bfq_shutdown_timer_wq(bfqd);
+
+	BUG_ON(hrtimer_active(&bfqd->idle_slice_timer));
+
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	blkcg_deactivate_policy(q, &blkcg_policy_bfq);
+#else
+	bfq_put_async_queues(bfqd, bfqd->root_group);
+	kfree(bfqd->root_group);
+#endif
+
+	kfree(bfqd);
+}
+
+static void bfq_init_root_group(struct bfq_group *root_group,
+				struct bfq_data *bfqd)
+{
+	int i;
+
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	root_group->entity.parent = NULL;
+	root_group->my_entity = NULL;
+	root_group->bfqd = bfqd;
+#endif
+	root_group->rq_pos_tree = RB_ROOT;
+	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;
+
+	/*
+	 * 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);
+
+	/* oom_bfqq does not participate to bursts */
+	bfq_clear_bfqq_just_created(&bfqd->oom_bfqq);
+	/*
+	 * 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;
+
+	spin_lock_irq(q->queue_lock);
+	q->elevator = eq;
+	spin_unlock_irq(q->queue_lock);
+
+	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);
+
+	hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
+	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
+
+	bfqd->queue_weights_tree = RB_ROOT;
+	bfqd->group_weights_tree = RB_ROOT;
+
+	INIT_WORK(&bfqd->unplug_work, bfq_kick_queue);
+
+	INIT_LIST_HEAD(&bfqd->active_list);
+	INIT_LIST_HEAD(&bfqd->idle_list);
+	INIT_HLIST_HEAD(&bfqd->burst_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;
+
+	bfqd->bfq_large_burst_thresh = 8;
+	bfqd->bfq_burst_interval = msecs_to_jiffies(180);
+
+	bfqd->low_latency = true;
+
+	/*
+	 * Trade-off between responsiveness and fairness.
+	 */
+	bfqd->bfq_wr_coeff = 30;
+	bfqd->bfq_wr_rt_max_time = msecs_to_jiffies(300);
+	bfqd->bfq_wr_max_time = 0;
+	bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000);
+	bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500);
+	bfqd->bfq_wr_max_softrt_rate = 7000; /*
+					      * Approximate rate required
+					      * to playback or record a
+					      * high-definition compressed
+					      * video.
+					      */
+	bfqd->wr_busy_queues = 0;
+
+	/*
+	 * Begin by assuming, optimistically, that the device is a
+	 * high-speed one, and that its peak rate is equal to 2/3 of
+	 * the highest reference rate.
+	 */
+	bfqd->RT_prod = R_fast[blk_queue_nonrot(bfqd->queue)] *
+			T_fast[blk_queue_nonrot(bfqd->queue)];
+	bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
+	bfqd->device_speed = BFQ_BFQD_FAST;
+
+	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;
+}
+
+static ssize_t bfq_wr_max_time_show(struct elevator_queue *e, char *page)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+
+	return sprintf(page, "%d\n", bfqd->bfq_wr_max_time > 0 ?
+		       jiffies_to_msecs(bfqd->bfq_wr_max_time) :
+		       jiffies_to_msecs(bfq_wr_duration(bfqd)));
+}
+
+static ssize_t bfq_weights_show(struct elevator_queue *e, char *page)
+{
+	struct bfq_queue *bfqq;
+	struct bfq_data *bfqd = e->elevator_data;
+	ssize_t num_char = 0;
+
+	num_char += sprintf(page + num_char, "Tot reqs queued %d\n\n",
+			    bfqd->queued);
+
+	spin_lock_irq(bfqd->queue->queue_lock);
+
+	num_char += sprintf(page + num_char, "Active:\n");
+	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) {
+		num_char += sprintf(page + num_char,
+				    "pid%d: weight %hu, nr_queued %d %d, ",
+				    bfqq->pid,
+				    bfqq->entity.weight,
+				    bfqq->queued[0],
+				    bfqq->queued[1]);
+		num_char += sprintf(page + num_char,
+				    "dur %d/%u\n",
+				    jiffies_to_msecs(
+					    jiffies -
+					    bfqq->last_wr_start_finish),
+				    jiffies_to_msecs(bfqq->wr_cur_max_time));
+	}
+
+	num_char += sprintf(page + num_char, "Idle:\n");
+	list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) {
+		num_char += sprintf(page + num_char,
+				    "pid%d: weight %hu, dur %d/%u\n",
+				    bfqq->pid,
+				    bfqq->entity.weight,
+				    jiffies_to_msecs(jiffies -
+						     bfqq->last_wr_start_finish),
+				    jiffies_to_msecs(bfqq->wr_cur_max_time));
+	}
+
+	spin_unlock_irq(bfqd->queue->queue_lock);
+
+	return num_char;
+}
+
+#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);
+SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0);
+SHOW_FUNCTION(bfq_wr_coeff_show, bfqd->bfq_wr_coeff, 0);
+SHOW_FUNCTION(bfq_wr_rt_max_time_show, bfqd->bfq_wr_rt_max_time, 1);
+SHOW_FUNCTION(bfq_wr_min_idle_time_show, bfqd->bfq_wr_min_idle_time, 1);
+SHOW_FUNCTION(bfq_wr_min_inter_arr_async_show, bfqd->bfq_wr_min_inter_arr_async,
+	1);
+SHOW_FUNCTION(bfq_wr_max_softrt_rate_show, bfqd->bfq_wr_max_softrt_rate, 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);
+STORE_FUNCTION(bfq_wr_coeff_store, &bfqd->bfq_wr_coeff, 1, INT_MAX, 0);
+STORE_FUNCTION(bfq_wr_max_time_store, &bfqd->bfq_wr_max_time, 0, INT_MAX, 1);
+STORE_FUNCTION(bfq_wr_rt_max_time_store, &bfqd->bfq_wr_rt_max_time, 0, INT_MAX,
+		1);
+STORE_FUNCTION(bfq_wr_min_idle_time_store, &bfqd->bfq_wr_min_idle_time, 0,
+		INT_MAX, 1);
+STORE_FUNCTION(bfq_wr_min_inter_arr_async_store,
+		&bfqd->bfq_wr_min_inter_arr_async, 0, INT_MAX, 1);
+STORE_FUNCTION(bfq_wr_max_softrt_rate_store, &bfqd->bfq_wr_max_softrt_rate, 0,
+		INT_MAX, 0);
+#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
+
+/* do nothing for the moment */
+static ssize_t bfq_weights_store(struct elevator_queue *e,
+				    const char *page, size_t count)
+{
+	return count;
+}
+
+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_calc_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_calc_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;
+}
+
+static ssize_t bfq_low_latency_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 (__data == 0 && bfqd->low_latency != 0)
+		bfq_end_wr(bfqd);
+	bfqd->low_latency = __data;
+
+	return ret;
+}
+
+#define BFQ_ATTR(name) \
+	__ATTR(name, S_IRUGO|S_IWUSR, 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),
+	BFQ_ATTR(low_latency),
+	BFQ_ATTR(wr_coeff),
+	BFQ_ATTR(wr_max_time),
+	BFQ_ATTR(wr_rt_max_time),
+	BFQ_ATTR(wr_min_idle_time),
+	BFQ_ATTR(wr_min_inter_arr_async),
+	BFQ_ATTR(wr_max_softrt_rate),
+	BFQ_ATTR(weights),
+	__ATTR_NULL
+};
+
+static struct elevator_type iosched_bfq = {
+	.ops.sq = {
+		.elevator_merge_fn =		bfq_merge,
+		.elevator_merged_fn =		bfq_merged_request,
+		.elevator_merge_req_fn =	bfq_merged_requests,
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+		.elevator_bio_merged_fn =	bfq_bio_merged,
+#endif
+		.elevator_allow_bio_merge_fn =	bfq_allow_bio_merge,
+		.elevator_allow_rq_merge_fn =	bfq_allow_rq_merge,
+		.elevator_dispatch_fn =		bfq_dispatch_requests,
+		.elevator_add_req_fn =		bfq_insert_request,
+		.elevator_activate_req_fn =	bfq_activate_request,
+		.elevator_deactivate_req_fn =	bfq_deactivate_request,
+		.elevator_completed_req_fn =	bfq_completed_request,
+		.elevator_former_req_fn =	elv_rb_former_request,
+		.elevator_latter_req_fn =	elv_rb_latter_request,
+		.elevator_init_icq_fn =		bfq_init_icq,
+		.elevator_exit_icq_fn =		bfq_exit_icq,
+		.elevator_set_req_fn =		bfq_set_request,
+		.elevator_put_req_fn =		bfq_put_request,
+		.elevator_may_queue_fn =	bfq_may_queue,
+		.elevator_init_fn =		bfq_init_queue,
+		.elevator_exit_fn =		bfq_exit_queue,
+	},
+	.icq_size =		sizeof(struct bfq_io_cq),
+	.icq_align =		__alignof__(struct bfq_io_cq),
+	.elevator_attrs =	bfq_attrs,
+	.elevator_name =	"bfq-sq",
+	.elevator_owner =	THIS_MODULE,
+};
+
+#ifdef CONFIG_BFQ_SQ_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;
+	char msg[60] = "BFQ I/O-scheduler: v8r12";
+
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	ret = blkcg_policy_register(&blkcg_policy_bfq);
+	if (ret)
+		return ret;
+#endif
+
+	ret = -ENOMEM;
+	if (bfq_slab_setup())
+		goto err_pol_unreg;
+
+	/*
+	 * Times to load large popular applications for the typical
+	 * systems installed on the reference devices (see the
+	 * comments before the definitions of the next two
+	 * arrays). Actually, we use slightly slower values, as the
+	 * estimated peak rate tends to be smaller than the actual
+	 * peak rate.  The reason for this last fact is that estimates
+	 * are computed over much shorter time intervals than the long
+	 * intervals typically used for benchmarking. Why? First, to
+	 * adapt more quickly to variations. Second, because an I/O
+	 * scheduler cannot rely on a peak-rate-evaluation workload to
+	 * be run for a long time.
+	 */
+	T_slow[0] = msecs_to_jiffies(3500); /* actually 4 sec */
+	T_slow[1] = msecs_to_jiffies(6000); /* actually 6.5 sec */
+	T_fast[0] = msecs_to_jiffies(7000); /* actually 8 sec */
+	T_fast[1] = msecs_to_jiffies(2500); /* actually 3 sec */
+
+	/*
+	 * Thresholds that determine the switch between speed classes
+	 * (see the comments before the definition of the array
+	 * device_speed_thresh). These thresholds are biased towards
+	 * transitions to the fast class. This is safer than the
+	 * opposite bias. In fact, a wrong transition to the slow
+	 * class results in short weight-raising periods, because the
+	 * speed of the device then tends to be higher that the
+	 * reference peak rate. On the opposite end, a wrong
+	 * transition to the fast class tends to increase
+	 * weight-raising periods, because of the opposite reason.
+	 */
+	device_speed_thresh[0] = (4 * R_slow[0]) / 3;
+	device_speed_thresh[1] = (4 * R_slow[1]) / 3;
+
+	ret = elv_register(&iosched_bfq);
+	if (ret)
+		goto err_pol_unreg;
+
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	strcat(msg, " (with cgroups support)");
+#endif
+	pr_info("%s", msg);
+
+	return 0;
+
+err_pol_unreg:
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	blkcg_policy_unregister(&blkcg_policy_bfq);
+#endif
+	return ret;
+}
+
+static void __exit bfq_exit(void)
+{
+	elv_unregister(&iosched_bfq);
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+	blkcg_policy_unregister(&blkcg_policy_bfq);
+#endif
+	bfq_slab_kill();
+}
+
+module_init(bfq_init);
+module_exit(bfq_exit);
+
+MODULE_AUTHOR("Arianna Avanzini, Fabio Checconi, Paolo Valente");
+MODULE_LICENSE("GPL");

From e24d2e6461479dbd13d58be2dc44b23b5e24487c Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Mon, 19 Dec 2016 17:13:39 +0100
Subject: [PATCH 07/51] Add config and build bits for bfq-mq-iosched

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/Kconfig.iosched       | 10 +++++++++
 block/Makefile              |  1 +
 block/bfq-cgroup-included.c |  4 ++--
 block/bfq-mq-iosched.c      | 25 ++++++++++++-----------
 block/bfq-sched.c           | 50 ++++++++++++++++++++++-----------------------
 block/bfq-sq-iosched.c      | 24 +++++++++++-----------
 block/bfq.h                 | 36 +++++++++++++++++++++-----------
 8 files changed, 88 insertions(+), 64 deletions(-)

diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 9e3f4c2f7390..2d94af3d8b0a 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -96,6 +96,16 @@ config DEFAULT_IOSCHED
 	default "bfq-sq" if DEFAULT_BFQ_SQ
 	default "noop" if DEFAULT_NOOP
 
+config MQ_IOSCHED_BFQ
+	tristate "BFQ-MQ I/O Scheduler"
+	default y
+	---help---
+	BFQ I/O scheduler for BLK-MQ. BFQ-MQ distributes bandwidth
+	among all processes according to their weights, regardless of
+	the device parameters and with any workload. It also
+	guarantees a low latency to interactive and soft real-time
+	applications.  Details in Documentation/block/bfq-iosched.txt
+
 config MQ_IOSCHED_DEADLINE
 	tristate "MQ deadline I/O scheduler"
 	default y
diff --git a/block/Makefile b/block/Makefile
index 59026b425791..a571329c23f0 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_MQ_IOSCHED_KYBER)	+= kyber-iosched.o
 bfq-y				:= bfq-iosched.o bfq-wf2q.o bfq-cgroup.o
 obj-$(CONFIG_IOSCHED_BFQ)	+= bfq.o
 obj-$(CONFIG_IOSCHED_BFQ_SQ)	+= bfq-sq-iosched.o
+obj-$(CONFIG_MQ_IOSCHED_BFQ)	+= bfq-mq-iosched.o
 
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
diff --git a/block/bfq-cgroup-included.c b/block/bfq-cgroup-included.c
index af7c216a3540..9c483b658179 100644
--- a/block/bfq-cgroup-included.c
+++ b/block/bfq-cgroup-included.c
@@ -15,7 +15,7 @@
  * file.
  */
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 
 /* bfqg stats flags */
 enum bfqg_stats_flags {
@@ -1116,7 +1116,7 @@ static struct cftype bfq_blkg_files[] = {
 	{} /* terminate */
 };
 
-#else /* CONFIG_BFQ_SQ_GROUP_IOSCHED */
+#else /* BFQ_GROUP_IOSCHED_ENABLED */
 
 static inline void bfqg_stats_update_io_add(struct bfq_group *bfqg,
 			struct bfq_queue *bfqq, unsigned int op) { }
diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 30d019fc67e0..e88e00f1e0a7 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -82,6 +82,7 @@
 #include <linux/rbtree.h>
 #include <linux/ioprio.h>
 #include "blk.h"
+#undef CONFIG_BFQ_GROUP_IOSCHED /* cgroups support not yet functional */
 #include "bfq.h"
 
 /* Expiration time of sync (0) and async (1) requests, in ns. */
@@ -387,7 +388,7 @@ static bool bfq_differentiated_weights(struct bfq_data *bfqd)
 	return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
 		(bfqd->queue_weights_tree.rb_node->rb_left ||
 		 bfqd->queue_weights_tree.rb_node->rb_right)
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	       ) ||
 	       (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) &&
 		(bfqd->group_weights_tree.rb_node->rb_left ||
@@ -1672,7 +1673,7 @@ static void bfq_merged_request(struct request_queue *q, struct request *req,
 	}
 }
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 static void bfq_bio_merged(struct request_queue *q, struct request *req,
 			   struct bio *bio)
 {
@@ -3879,7 +3880,7 @@ static int bfq_dispatch_requests(struct request_queue *q, int force)
  */
 static void bfq_put_queue(struct bfq_queue *bfqq)
 {
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	struct bfq_group *bfqg = bfqq_group(bfqq);
 #endif
 
@@ -3909,7 +3910,7 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
 	bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p freed", bfqq);
 
 	kmem_cache_free(bfq_pool, bfqq);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	bfqg_put(bfqg);
 #endif
 }
@@ -4835,7 +4836,7 @@ static void bfq_exit_queue(struct elevator_queue *e)
 
 	BUG_ON(hrtimer_active(&bfqd->idle_slice_timer));
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	blkcg_deactivate_policy(q, &blkcg_policy_bfq);
 #else
 	bfq_put_async_queues(bfqd, bfqd->root_group);
@@ -4850,7 +4851,7 @@ static void bfq_init_root_group(struct bfq_group *root_group,
 {
 	int i;
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	root_group->entity.parent = NULL;
 	root_group->my_entity = NULL;
 	root_group->bfqd = bfqd;
@@ -5265,7 +5266,7 @@ static struct elevator_type iosched_bfq = {
 		.elevator_merge_fn =		bfq_merge,
 		.elevator_merged_fn =		bfq_merged_request,
 		.elevator_merge_req_fn =	bfq_merged_requests,
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 		.elevator_bio_merged_fn =	bfq_bio_merged,
 #endif
 		.elevator_allow_bio_merge_fn =	bfq_allow_bio_merge,
@@ -5292,7 +5293,7 @@ static struct elevator_type iosched_bfq = {
 	.elevator_owner =	THIS_MODULE,
 };
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 static struct blkcg_policy blkcg_policy_bfq = {
 	.dfl_cftypes		= bfq_blkg_files,
 	.legacy_cftypes		= bfq_blkcg_legacy_files,
@@ -5315,7 +5316,7 @@ static int __init bfq_init(void)
 	int ret;
 	char msg[60] = "BFQ I/O-scheduler: v8r12";
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	ret = blkcg_policy_register(&blkcg_policy_bfq);
 	if (ret)
 		return ret;
@@ -5362,7 +5363,7 @@ static int __init bfq_init(void)
 	if (ret)
 		goto err_pol_unreg;
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	strcat(msg, " (with cgroups support)");
 #endif
 	pr_info("%s", msg);
@@ -5370,7 +5371,7 @@ static int __init bfq_init(void)
 	return 0;
 
 err_pol_unreg:
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	blkcg_policy_unregister(&blkcg_policy_bfq);
 #endif
 	return ret;
@@ -5379,7 +5380,7 @@ static int __init bfq_init(void)
 static void __exit bfq_exit(void)
 {
 	elv_unregister(&iosched_bfq);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	blkcg_policy_unregister(&blkcg_policy_bfq);
 #endif
 	bfq_slab_kill();
diff --git a/block/bfq-sched.c b/block/bfq-sched.c
index 5c0f9290a79c..b54a638186e3 100644
--- a/block/bfq-sched.c
+++ b/block/bfq-sched.c
@@ -136,7 +136,7 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 	if (bfqq)
 		bfq_log_bfqq(bfqq->bfqd, bfqq,
 			     "update_next_in_service: chosen this queue");
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	else {
 		struct bfq_group *bfqg =
 			container_of(next_in_service,
@@ -149,7 +149,7 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 	return parent_sched_may_change;
 }
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 /* both next loops stop at one of the child entities of the root group */
 #define for_each_entity(entity)				\
 	for (; entity ; entity = entity->parent)
@@ -243,7 +243,7 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
 	return false;
 }
 
-#else /* CONFIG_BFQ_SQ_GROUP_IOSCHED */
+#else /* BFQ_GROUP_IOSCHED_ENABLED */
 #define for_each_entity(entity)	\
 	for (; entity ; entity = NULL)
 
@@ -260,7 +260,7 @@ static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
 	return true;
 }
 
-#endif /* CONFIG_BFQ_SQ_GROUP_IOSCHED */
+#endif /* BFQ_GROUP_IOSCHED_ENABLED */
 
 /*
  * Shift for timestamp calculations.  This actually limits the maximum
@@ -323,7 +323,7 @@ static void bfq_calc_finish(struct bfq_entity *entity, unsigned long service)
 		bfq_log_bfqq(bfqq->bfqd, bfqq,
 			"calc_finish: start %llu, finish %llu, delta %llu",
 			start, finish, delta);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	} else {
 		struct bfq_group *bfqg =
 			container_of(entity, struct bfq_group, entity);
@@ -473,7 +473,7 @@ static void bfq_update_active_node(struct rb_node *node)
 		bfq_log_bfqq(bfqq->bfqd, bfqq,
 			     "update_active_node: new min_start %llu",
 			     ((entity->min_start>>10)*1000)>>12);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	} else {
 		struct bfq_group *bfqg =
 			container_of(entity, struct bfq_group, entity);
@@ -540,7 +540,7 @@ static void bfq_active_insert(struct bfq_service_tree *st,
 {
 	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
 	struct rb_node *node = &entity->rb_node;
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	struct bfq_sched_data *sd = NULL;
 	struct bfq_group *bfqg = NULL;
 	struct bfq_data *bfqd = NULL;
@@ -555,7 +555,7 @@ static void bfq_active_insert(struct bfq_service_tree *st,
 
 	bfq_update_active_tree(node);
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	sd = entity->sched_data;
 	bfqg = container_of(sd, struct bfq_group, sched_data);
 	BUG_ON(!bfqg);
@@ -563,7 +563,7 @@ static void bfq_active_insert(struct bfq_service_tree *st,
 #endif
 	if (bfqq)
 		list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	else { /* bfq_group */
 		BUG_ON(!bfqd);
 		bfq_weights_tree_add(bfqd, entity, &bfqd->group_weights_tree);
@@ -652,7 +652,7 @@ static void bfq_active_extract(struct bfq_service_tree *st,
 {
 	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
 	struct rb_node *node;
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	struct bfq_sched_data *sd = NULL;
 	struct bfq_group *bfqg = NULL;
 	struct bfq_data *bfqd = NULL;
@@ -664,7 +664,7 @@ static void bfq_active_extract(struct bfq_service_tree *st,
 	if (node)
 		bfq_update_active_tree(node);
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	sd = entity->sched_data;
 	bfqg = container_of(sd, struct bfq_group, sched_data);
 	BUG_ON(!bfqg);
@@ -672,7 +672,7 @@ static void bfq_active_extract(struct bfq_service_tree *st,
 #endif
 	if (bfqq)
 		list_del(&bfqq->bfqq_list);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	else { /* bfq_group */
 		BUG_ON(!bfqd);
 		bfq_weights_tree_remove(bfqd, entity,
@@ -809,14 +809,14 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
 		unsigned int prev_weight, new_weight;
 		struct bfq_data *bfqd = NULL;
 		struct rb_root *root;
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 		struct bfq_sched_data *sd;
 		struct bfq_group *bfqg;
 #endif
 
 		if (bfqq)
 			bfqd = bfqq->bfqd;
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 		else {
 			sd = entity->my_sched_data;
 			bfqg = container_of(sd, struct bfq_group, sched_data);
@@ -907,7 +907,7 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
 	return new_st;
 }
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 static void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
 #endif
 
@@ -936,7 +936,7 @@ static void bfq_bfqq_served(struct bfq_queue *bfqq, int served)
 		st->vtime += bfq_delta(served, st->wsum);
 		bfq_forget_idle(st);
 	}
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	bfqg_stats_set_start_empty_time(bfqq_group(bfqq));
 #endif
 	st = bfq_entity_service_tree(&bfqq->entity);
@@ -1060,7 +1060,7 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
 			bfq_log_bfqq(bfqq->bfqd, bfqq,
 				     "__activate_entity: new queue finish %llu",
 				     ((entity->finish>>10)*1000)>>12);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 		} else {
 			struct bfq_group *bfqg =
 				container_of(entity, struct bfq_group, entity);
@@ -1078,7 +1078,7 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
 		bfq_log_bfqq(bfqq->bfqd, bfqq,
 			"__activate_entity: queue %seligible in st %p",
 			     entity->start <= st->vtime ? "" : "non ", st);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	} else {
 		struct bfq_group *bfqg =
 			container_of(entity, struct bfq_group, entity);
@@ -1153,7 +1153,7 @@ static void __bfq_activate_entity(struct bfq_entity *entity,
 
 		BUG_ON(entity->on_st && bfqq);
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 		if (entity->on_st && !bfqq) {
 			struct bfq_group *bfqg =
 				container_of(entity, struct bfq_group,
@@ -1485,7 +1485,7 @@ static void bfq_deactivate_entity(struct bfq_entity *entity,
 		if (bfqq)
 			bfq_log_bfqq(bfqq->bfqd, bfqq,
 				     "invoking udpdate_next for this queue");
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 		else {
 			struct bfq_group *bfqg =
 				container_of(entity,
@@ -1525,7 +1525,7 @@ static u64 bfq_calc_vtime_jump(struct bfq_service_tree *st)
 			bfq_log_bfqq(bfqq->bfqd, bfqq,
 				     "calc_vtime_jump: new value %llu",
 				     root_entity->min_start);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 		else {
 			struct bfq_group *bfqg =
 				container_of(root_entity, struct bfq_group,
@@ -1661,7 +1661,7 @@ __bfq_lookup_next_entity(struct bfq_service_tree *st, bool in_service
 			     "__lookup_next: start %llu vtime %llu st %p",
 			     ((entity->start>>10)*1000)>>12,
 			     ((new_vtime>>10)*1000)>>12, st);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	else {
 		struct bfq_group *bfqg =
 			container_of(entity, struct bfq_group, entity);
@@ -1735,7 +1735,7 @@ static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd)
 	if (bfqq)
 		bfq_log_bfqq(bfqq->bfqd, bfqq, "chosen from st %p %d",
 			     st + class_idx, class_idx);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	else {
 		struct bfq_group *bfqg =
 			container_of(entity, struct bfq_group, entity);
@@ -1777,7 +1777,7 @@ static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
 	 */
 	sd = &bfqd->root_group->sched_data;
 	for (; sd ; sd = entity->my_sched_data) {
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 		if (entity) {
 			struct bfq_group *bfqg =
 				container_of(entity, struct bfq_group, entity);
@@ -1867,7 +1867,7 @@ static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
 			bfq_log_bfqq(bfqd, bfqq,
 			     "get_next_queue: this queue, finish %llu",
 				(((entity->finish>>10)*1000)>>10)>>2);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 		else {
 			struct bfq_group *bfqg =
 				container_of(entity, struct bfq_group, entity);
diff --git a/block/bfq-sq-iosched.c b/block/bfq-sq-iosched.c
index 30d019fc67e0..25da0d1c0622 100644
--- a/block/bfq-sq-iosched.c
+++ b/block/bfq-sq-iosched.c
@@ -387,7 +387,7 @@ static bool bfq_differentiated_weights(struct bfq_data *bfqd)
 	return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
 		(bfqd->queue_weights_tree.rb_node->rb_left ||
 		 bfqd->queue_weights_tree.rb_node->rb_right)
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	       ) ||
 	       (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) &&
 		(bfqd->group_weights_tree.rb_node->rb_left ||
@@ -1672,7 +1672,7 @@ static void bfq_merged_request(struct request_queue *q, struct request *req,
 	}
 }
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 static void bfq_bio_merged(struct request_queue *q, struct request *req,
 			   struct bio *bio)
 {
@@ -3879,7 +3879,7 @@ static int bfq_dispatch_requests(struct request_queue *q, int force)
  */
 static void bfq_put_queue(struct bfq_queue *bfqq)
 {
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	struct bfq_group *bfqg = bfqq_group(bfqq);
 #endif
 
@@ -3909,7 +3909,7 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
 	bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p freed", bfqq);
 
 	kmem_cache_free(bfq_pool, bfqq);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	bfqg_put(bfqg);
 #endif
 }
@@ -4835,7 +4835,7 @@ static void bfq_exit_queue(struct elevator_queue *e)
 
 	BUG_ON(hrtimer_active(&bfqd->idle_slice_timer));
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	blkcg_deactivate_policy(q, &blkcg_policy_bfq);
 #else
 	bfq_put_async_queues(bfqd, bfqd->root_group);
@@ -4850,7 +4850,7 @@ static void bfq_init_root_group(struct bfq_group *root_group,
 {
 	int i;
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	root_group->entity.parent = NULL;
 	root_group->my_entity = NULL;
 	root_group->bfqd = bfqd;
@@ -5265,7 +5265,7 @@ static struct elevator_type iosched_bfq = {
 		.elevator_merge_fn =		bfq_merge,
 		.elevator_merged_fn =		bfq_merged_request,
 		.elevator_merge_req_fn =	bfq_merged_requests,
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 		.elevator_bio_merged_fn =	bfq_bio_merged,
 #endif
 		.elevator_allow_bio_merge_fn =	bfq_allow_bio_merge,
@@ -5292,7 +5292,7 @@ static struct elevator_type iosched_bfq = {
 	.elevator_owner =	THIS_MODULE,
 };
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 static struct blkcg_policy blkcg_policy_bfq = {
 	.dfl_cftypes		= bfq_blkg_files,
 	.legacy_cftypes		= bfq_blkcg_legacy_files,
@@ -5315,7 +5315,7 @@ static int __init bfq_init(void)
 	int ret;
 	char msg[60] = "BFQ I/O-scheduler: v8r12";
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	ret = blkcg_policy_register(&blkcg_policy_bfq);
 	if (ret)
 		return ret;
@@ -5362,7 +5362,7 @@ static int __init bfq_init(void)
 	if (ret)
 		goto err_pol_unreg;
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	strcat(msg, " (with cgroups support)");
 #endif
 	pr_info("%s", msg);
@@ -5370,7 +5370,7 @@ static int __init bfq_init(void)
 	return 0;
 
 err_pol_unreg:
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	blkcg_policy_unregister(&blkcg_policy_bfq);
 #endif
 	return ret;
@@ -5379,7 +5379,7 @@ static int __init bfq_init(void)
 static void __exit bfq_exit(void)
 {
 	elv_unregister(&iosched_bfq);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	blkcg_policy_unregister(&blkcg_policy_bfq);
 #endif
 	bfq_slab_kill();
diff --git a/block/bfq.h b/block/bfq.h
index 34fc4697fd89..53954d1b87f8 100644
--- a/block/bfq.h
+++ b/block/bfq.h
@@ -19,6 +19,18 @@
 #include <linux/hrtimer.h>
 #include <linux/blk-cgroup.h>
 
+/*
+ * Define an alternative macro to compile cgroups support. This is one
+ * of the steps needed to let bfq-mq share the files bfq-sched.c and
+ * bfq-cgroup.c with bfq-sq. For bfq-mq, the macro
+ * BFQ_GROUP_IOSCHED_ENABLED will be defined as a function of whether
+ * the configuration option CONFIG_BFQ_MQ_GROUP_IOSCHED, and not
+ * CONFIG_BFQ_GROUP_IOSCHED, is defined.
+ */
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#define BFQ_GROUP_IOSCHED_ENABLED
+#endif
+
 #define BFQ_IOPRIO_CLASSES	3
 #define BFQ_CL_IDLE_TIMEOUT	(HZ/5)
 
@@ -344,7 +356,7 @@ struct bfq_io_cq {
 	struct bfq_ttime ttime;
 	/* per (request_queue, blkcg) ioprio */
 	int ioprio;
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	uint64_t blkcg_serial_nr; /* the current blkcg serial */
 #endif
 
@@ -671,7 +683,7 @@ static const char *checked_dev_name(const struct device *dev)
 	return nodev;
 }
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 static struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 
@@ -696,7 +708,7 @@ static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 	__pbuf, ##args);						\
 } while (0)
 
-#else /* CONFIG_BFQ_SQ_GROUP_IOSCHED */
+#else /* BFQ_GROUP_IOSCHED_ENABLED */
 
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...)				\
 	pr_crit("%s bfq%d%c " fmt "\n",					\
@@ -705,7 +717,7 @@ static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 		##args)
 #define bfq_log_bfqg(bfqd, bfqg, fmt, args...)		do {} while (0)
 
-#endif /* CONFIG_BFQ_SQ_GROUP_IOSCHED */
+#endif /* BFQ_GROUP_IOSCHED_ENABLED */
 
 #define bfq_log(bfqd, fmt, args...) \
 	pr_crit("%s bfq " fmt "\n",					\
@@ -713,7 +725,7 @@ static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 		##args)
 
 #else /* CONFIG_BFQ_REDIRECT_TO_CONSOLE */
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 static struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 
@@ -735,7 +747,7 @@ static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 	blk_add_trace_msg((bfqd)->queue, "%s " fmt, __pbuf, ##args);	\
 } while (0)
 
-#else /* CONFIG_BFQ_SQ_GROUP_IOSCHED */
+#else /* BFQ_GROUP_IOSCHED_ENABLED */
 
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	\
 	blk_add_trace_msg((bfqd)->queue, "bfq%d%c " fmt, (bfqq)->pid,	\
@@ -743,7 +755,7 @@ static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 				##args)
 #define bfq_log_bfqg(bfqd, bfqg, fmt, args...)		do {} while (0)
 
-#endif /* CONFIG_BFQ_SQ_GROUP_IOSCHED */
+#endif /* BFQ_GROUP_IOSCHED_ENABLED */
 
 #define bfq_log(bfqd, fmt, args...) \
 	blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)
@@ -763,7 +775,7 @@ enum bfqq_expiration {
 
 
 struct bfqg_stats {
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	/* number of ios merged */
 	struct blkg_rwstat		merged;
 	/* total time spent on device in ns, may not be accurate w/ queueing */
@@ -794,7 +806,7 @@ struct bfqg_stats {
 #endif
 };
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 /*
  * struct bfq_group_data - per-blkcg storage for the blkio subsystem.
  *
@@ -895,7 +907,7 @@ bfq_entity_service_tree(struct bfq_entity *entity)
 		bfq_log_bfqq(bfqq->bfqd, bfqq,
 			     "entity_service_tree %p %d",
 			     sched_data->service_tree + idx, idx);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	else {
 		struct bfq_group *bfqg =
 			container_of(entity, struct bfq_group, entity);
@@ -924,7 +936,7 @@ static struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
 	return bic->icq.q->elevator->elevator_data;
 }
 
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 
 static struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
 {
@@ -953,7 +965,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
 				       struct bfq_io_cq *bic);
 static void bfq_end_wr_async_queues(struct bfq_data *bfqd,
 				    struct bfq_group *bfqg);
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
 #endif
 static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);

From add91dbd756cf8ca3aa3add9a19eef742d5fca6b Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Fri, 20 Jan 2017 09:18:25 +0100
Subject: [PATCH 08/51] Increase max policies for io controller

To let bfq-mq policy be plugged too (however cgroups
suppport is not yet functional in bfq-mq).

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 include/linux/blkdev.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index bf000c58644b..10f892ca585d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -54,7 +54,7 @@ struct blk_stat_callback;
  * Maximum number of blkcg policies allowed to be registered concurrently.
  * Defined here to simplify include dependency.
  */
-#define BLKCG_MAX_POLS		4
+#define BLKCG_MAX_POLS		5
 
 typedef void (rq_end_io_fn)(struct request *, blk_status_t);
 

From 2c39a1d9ab4516d44e01e96f19f578b927e7f2e9 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Mon, 19 Dec 2016 18:11:33 +0100
Subject: [PATCH 09/51] Copy header file bfq.h as bfq-mq.h

This commit introduces the header file bfq-mq.h, that will play
for bfq-mq-iosched.c the same role that bfq.h plays for bfq-iosched.c.

For the moment, the file bfq-mq.h is just a copy of bfq.h.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c |   2 +-
 block/bfq-mq.h         | 973 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 974 insertions(+), 1 deletion(-)
 create mode 100644 block/bfq-mq.h

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index e88e00f1e0a7..d1125aee658c 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -83,7 +83,7 @@
 #include <linux/ioprio.h>
 #include "blk.h"
 #undef CONFIG_BFQ_GROUP_IOSCHED /* cgroups support not yet functional */
-#include "bfq.h"
+#include "bfq-mq.h"
 
 /* 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 };
diff --git a/block/bfq-mq.h b/block/bfq-mq.h
new file mode 100644
index 000000000000..53954d1b87f8
--- /dev/null
+++ b/block/bfq-mq.h
@@ -0,0 +1,973 @@
+/*
+ * BFQ v8r12 for 4.11.0: data structures and common functions prototypes.
+ *
+ * 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) 2015 Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2017 Paolo Valente <paolo.valente@linaro.org>
+ */
+
+#ifndef _BFQ_H
+#define _BFQ_H
+
+#include <linux/blktrace_api.h>
+#include <linux/hrtimer.h>
+#include <linux/blk-cgroup.h>
+
+/*
+ * Define an alternative macro to compile cgroups support. This is one
+ * of the steps needed to let bfq-mq share the files bfq-sched.c and
+ * bfq-cgroup.c with bfq-sq. For bfq-mq, the macro
+ * BFQ_GROUP_IOSCHED_ENABLED will be defined as a function of whether
+ * the configuration option CONFIG_BFQ_MQ_GROUP_IOSCHED, and not
+ * CONFIG_BFQ_GROUP_IOSCHED, is defined.
+ */
+#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+#define BFQ_GROUP_IOSCHED_ENABLED
+#endif
+
+#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
+
+/*
+ * Soft real-time applications are extremely more latency sensitive
+ * than interactive ones. Over-raise the weight of the former to
+ * privilege them against the latter.
+ */
+#define BFQ_SOFTRT_WEIGHT_FACTOR	100
+
+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;
+
+	struct bfq_entity *first_idle;	/* idle entity with minimum F_i */
+	struct bfq_entity *last_idle;	/* idle entity with maximum F_i */
+
+	u64 vtime; /* scheduler virtual time */
+	/* 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 in a hierarchical setup.
+ *
+ * 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+.
+ *
+ * The schedule is implemented by the service trees, plus the field
+ * @next_in_service, which points to the entity on the active trees
+ * that will be served next, if 1) no changes in the schedule occurs
+ * before the current in-service entity is expired, 2) the in-service
+ * queue becomes idle when it expires, and 3) if the entity pointed by
+ * in_service_entity is not a queue, then the in-service child entity
+ * of the entity pointed by in_service_entity becomes idle on
+ * expiration. This peculiar definition allows for the following
+ * optimization, not yet exploited: while a given entity is still in
+ * service, we already know which is the best candidate for next
+ * service among the other active entitities in the same parent
+ * entity. We can then quickly compare the timestamps of the
+ * in-service entity with those of such best candidate.
+ *
+ * All the fields are protected by the queue lock of the containing
+ * bfqd.
+ */
+struct bfq_sched_data {
+	struct bfq_entity *in_service_entity;  /* entity in service */
+	/* head-of-the-line entity in the scheduler (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_weight_counter - counter of the number of all active entities
+ *                             with a given weight.
+ */
+struct bfq_weight_counter {
+	unsigned int weight; /* weight of the entities this counter refers to */
+	unsigned int num_active; /* nr of active entities with this weight */
+	/*
+	 * Weights tree member (see bfq_data's @queue_weights_tree and
+	 * @group_weights_tree)
+	 */
+	struct rb_node weights_node;
+};
+
+/**
+ * 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 {
+	struct rb_node rb_node; /* service_tree member */
+	/* pointer to the weight counter associated with this entity */
+	struct bfq_weight_counter *weight_counter;
+
+	/*
+	 * 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;
+
+	u64 finish; /* B-WF2Q+ finish timestamp (aka F_i) */
+	u64 start;  /* B-WF2Q+ start timestamp (aka S_i) */
+
+	/* 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;
+
+	unsigned int weight;	 /* weight of the queue */
+	unsigned int new_weight; /* next weight if a change is in progress */
+
+	/* original weight, used to implement weight boosting */
+	unsigned 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_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 or shared  between  cooperating
+ * processes. @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;
+
+	/*
+	 * Shared bfq_queue if queue is cooperating with one or more
+	 * other queues.
+	 */
+	struct bfq_queue *new_bfqq;
+	/* request-position tree member (see bfq_group's @rq_pos_tree) */
+	struct rb_node pos_node;
+	/* request-position tree root (see bfq_group's @rq_pos_tree) */
+	struct rb_root *pos_root;
+
+	/* 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 sync and async requests currently allocated */
+	int allocated[2];
+	/* 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;
+
+	unsigned int flags; /* status flags.*/
+
+	/* node for active/idle bfqq list inside parent bfqd */
+	struct list_head bfqq_list;
+
+	/* bit vector: a 1 for each seeky requests in history */
+	u32 seek_history;
+
+	/* node for the device's burst list */
+	struct hlist_node burst_list_node;
+
+	/* 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;
+
+	/*
+	 * Pointer to the bfq_io_cq owning the bfq_queue, set to %NULL
+	 * if the queue is shared.
+	 */
+	struct bfq_io_cq *bic;
+
+	/* current maximum weight-raising time for this queue */
+	unsigned long wr_cur_max_time;
+	/*
+	 * Minimum time instant such that, only if a new request is
+	 * enqueued after this time instant in an idle @bfq_queue with
+	 * no outstanding requests, then the task associated with the
+	 * queue it is deemed as soft real-time (see the comments on
+	 * the function bfq_bfqq_softrt_next_start())
+	 */
+	unsigned long soft_rt_next_start;
+	/*
+	 * Start time of the current weight-raising period if
+	 * the @bfq-queue is being weight-raised, otherwise
+	 * finish time of the last weight-raising period.
+	 */
+	unsigned long last_wr_start_finish;
+	/* factor by which the weight of this queue is multiplied */
+	unsigned int wr_coeff;
+	/*
+	 * Time of the last transition of the @bfq_queue from idle to
+	 * backlogged.
+	 */
+	unsigned long last_idle_bklogged;
+	/*
+	 * Cumulative service received from the @bfq_queue since the
+	 * last transition from idle to backlogged.
+	 */
+	unsigned long service_from_backlogged;
+	/*
+	 * Value of wr start time when switching to soft rt
+	 */
+	unsigned long wr_start_at_switch_to_srt;
+
+	unsigned long split_time; /* time of last split */
+};
+
+/**
+ * struct bfq_ttime - per process thinktime stats.
+ */
+struct bfq_ttime {
+	u64 last_end_request; /* completion time of last request */
+
+	u64 ttime_total; /* total process thinktime */
+	unsigned long ttime_samples; /* number of thinktime samples */
+	u64 ttime_mean; /* average process thinktime */
+
+};
+
+/**
+ * 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];
+	/* associated @bfq_ttime struct */
+	struct bfq_ttime ttime;
+	/* per (request_queue, blkcg) ioprio */
+	int ioprio;
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+	uint64_t blkcg_serial_nr; /* the current blkcg serial */
+#endif
+
+	/*
+	 * Snapshot of the has_short_time flag before merging; taken
+	 * to remember its value while the queue is merged, so as to
+	 * be able to restore it in case of split.
+	 */
+	bool saved_has_short_ttime;
+	/*
+	 * Same purpose as the previous two fields for the I/O bound
+	 * classification of a queue.
+	 */
+	bool saved_IO_bound;
+
+	/*
+	 * Same purpose as the previous fields for the value of the
+	 * field keeping the queue's belonging to a large burst
+	 */
+	bool saved_in_large_burst;
+	/*
+	 * True if the queue belonged to a burst list before its merge
+	 * with another cooperating queue.
+	 */
+	bool was_in_burst_list;
+
+	/*
+	 * Similar to previous fields: save wr information.
+	 */
+	unsigned long saved_wr_coeff;
+	unsigned long saved_last_wr_start_finish;
+	unsigned long saved_wr_start_at_switch_to_srt;
+	unsigned int saved_wr_cur_max_time;
+};
+
+enum bfq_device_speed {
+	BFQ_BFQD_FAST,
+	BFQ_BFQD_SLOW,
+};
+
+/**
+ * struct bfq_data - per-device data structure.
+ *
+ * All the fields are protected by the @queue lock.
+ */
+struct bfq_data {
+	/* request queue for the device */
+	struct request_queue *queue;
+
+	/* root bfq_group for the device */
+	struct bfq_group *root_group;
+
+	/*
+	 * rbtree of weight counters of @bfq_queues, sorted by
+	 * weight. Used to keep track of whether all @bfq_queues have
+	 * the same weight. The tree contains one counter for each
+	 * distinct weight associated to some active and not
+	 * weight-raised @bfq_queue (see the comments to the functions
+	 * bfq_weights_tree_[add|remove] for further details).
+	 */
+	struct rb_root queue_weights_tree;
+	/*
+	 * rbtree of non-queue @bfq_entity weight counters, sorted by
+	 * weight. Used to keep track of whether all @bfq_groups have
+	 * the same weight. The tree contains one counter for each
+	 * distinct weight associated to some active @bfq_group (see
+	 * the comments to the functions bfq_weights_tree_[add|remove]
+	 * for further details).
+	 */
+	struct rb_root group_weights_tree;
+
+	/*
+	 * Number of bfq_queues containing requests (including the
+	 * queue in service, even if it is idling).
+	 */
+	int busy_queues;
+	/* number of weight-raised busy @bfq_queues */
+	int wr_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;
+	/* delayed work to restart dispatching on the request queue */
+	struct work_struct unplug_work;
+
+	/* 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;
+
+	/* time of last request completion (ns) */
+	u64 last_completion;
+
+	/* time of first rq dispatch in current observation interval (ns) */
+	u64 first_dispatch;
+	/* time of last rq dispatch in current observation interval (ns) */
+	u64 last_dispatch;
+
+	/* beginning of the last budget */
+	ktime_t last_budget_start;
+	/* beginning of the last idle slice */
+	ktime_t last_idling_start;
+
+	/* number of samples in current observation interval */
+	int peak_rate_samples;
+	/* num of samples of seq dispatches in current observation interval */
+	u32 sequential_samples;
+	/* total num of sectors transferred in current observation interval */
+	u64 tot_sectors_dispatched;
+	/* max rq size seen during current observation interval (sectors) */
+	u32 last_rq_max_size;
+	/* time elapsed from first dispatch in current observ. interval (us) */
+	u64 delta_from_first;
+	/* current estimate of device peak rate */
+	u32 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;
+
+	/*
+	 * Last time at which a queue entered the current burst of
+	 * queues being activated shortly after each other; for more
+	 * details about this and the following parameters related to
+	 * a burst of activations, see the comments on the function
+	 * bfq_handle_burst.
+	 */
+	unsigned long last_ins_in_burst;
+	/*
+	 * Reference time interval used to decide whether a queue has
+	 * been activated shortly after @last_ins_in_burst.
+	 */
+	unsigned long bfq_burst_interval;
+	/* number of queues in the current burst of queue activations */
+	int burst_size;
+
+	/* common parent entity for the queues in the burst */
+	struct bfq_entity *burst_parent_entity;
+	/* Maximum burst size above which the current queue-activation
+	 * burst is deemed as 'large'.
+	 */
+	unsigned long bfq_large_burst_thresh;
+	/* true if a large queue-activation burst is in progress */
+	bool large_burst;
+	/*
+	 * Head of the burst list (as for the above fields, more
+	 * details in the comments on the function bfq_handle_burst).
+	 */
+	struct hlist_head burst_list;
+
+	/* if set to true, low-latency heuristics are enabled */
+	bool low_latency;
+	/*
+	 * Maximum factor by which the weight of a weight-raised queue
+	 * is multiplied.
+	 */
+	unsigned int bfq_wr_coeff;
+	/* maximum duration of a weight-raising period (jiffies) */
+	unsigned int bfq_wr_max_time;
+
+	/* Maximum weight-raising duration for soft real-time processes */
+	unsigned int bfq_wr_rt_max_time;
+	/*
+	 * Minimum idle period after which weight-raising may be
+	 * reactivated for a queue (in jiffies).
+	 */
+	unsigned int bfq_wr_min_idle_time;
+	/*
+	 * Minimum period between request arrivals after which
+	 * weight-raising may be reactivated for an already busy async
+	 * queue (in jiffies).
+	 */
+	unsigned long bfq_wr_min_inter_arr_async;
+
+	/* Max service-rate for a soft real-time queue, in sectors/sec */
+	unsigned int bfq_wr_max_softrt_rate;
+	/*
+	 * Cached value of the product R*T, used for computing the
+	 * maximum duration of weight raising automatically.
+	 */
+	u64 RT_prod;
+	/* device-speed class for the low-latency heuristic */
+	enum bfq_device_speed device_speed;
+
+	/* fallback dummy bfqq for extreme OOM conditions */
+	struct bfq_queue oom_bfqq;
+};
+
+enum bfqq_state_flags {
+	BFQ_BFQQ_FLAG_just_created = 0,	/* queue just allocated */
+	BFQ_BFQQ_FLAG_busy,		/* has requests or is in service */
+	BFQ_BFQQ_FLAG_wait_request,	/* waiting for a request */
+	BFQ_BFQQ_FLAG_non_blocking_wait_rq, /*
+					     * waiting for a request
+					     * without idling the device
+					     */
+	BFQ_BFQQ_FLAG_must_alloc,	/* must be allowed rq alloc */
+	BFQ_BFQQ_FLAG_fifo_expire,	/* FIFO checked in this slice */
+	BFQ_BFQQ_FLAG_has_short_ttime,	/* queue has a short think time */
+	BFQ_BFQQ_FLAG_sync,		/* synchronous queue */
+	BFQ_BFQQ_FLAG_IO_bound,		/*
+					 * bfqq has timed-out at least once
+					 * having consumed at most 2/10 of
+					 * its budget
+					 */
+	BFQ_BFQQ_FLAG_in_large_burst,	/*
+					 * bfqq activated in a large burst,
+					 * see comments to bfq_handle_burst.
+					 */
+	BFQ_BFQQ_FLAG_softrt_update,	/*
+					 * may need softrt-next-start
+					 * update
+					 */
+	BFQ_BFQQ_FLAG_coop,		/* bfqq is shared */
+	BFQ_BFQQ_FLAG_split_coop	/* shared bfqq will be split */
+};
+
+#define BFQ_BFQQ_FNS(name)						\
+static void bfq_mark_bfqq_##name(struct bfq_queue *bfqq)		\
+{									\
+	(bfqq)->flags |= (1 << BFQ_BFQQ_FLAG_##name);			\
+}									\
+static void bfq_clear_bfqq_##name(struct bfq_queue *bfqq)		\
+{									\
+	(bfqq)->flags &= ~(1 << BFQ_BFQQ_FLAG_##name);			\
+}									\
+static int bfq_bfqq_##name(const struct bfq_queue *bfqq)		\
+{									\
+	return ((bfqq)->flags & (1 << BFQ_BFQQ_FLAG_##name)) != 0;	\
+}
+
+BFQ_BFQQ_FNS(just_created);
+BFQ_BFQQ_FNS(busy);
+BFQ_BFQQ_FNS(wait_request);
+BFQ_BFQQ_FNS(non_blocking_wait_rq);
+BFQ_BFQQ_FNS(must_alloc);
+BFQ_BFQQ_FNS(fifo_expire);
+BFQ_BFQQ_FNS(has_short_ttime);
+BFQ_BFQQ_FNS(sync);
+BFQ_BFQQ_FNS(IO_bound);
+BFQ_BFQQ_FNS(in_large_burst);
+BFQ_BFQQ_FNS(coop);
+BFQ_BFQQ_FNS(split_coop);
+BFQ_BFQQ_FNS(softrt_update);
+#undef BFQ_BFQQ_FNS
+
+/* Logging facilities. */
+#ifdef CONFIG_BFQ_REDIRECT_TO_CONSOLE
+
+static const char *checked_dev_name(const struct device *dev)
+{
+	static const char nodev[] = "nodev";
+
+	if (dev)
+		return dev_name(dev);
+
+	return nodev;
+}
+
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+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];						\
+									\
+	assert_spin_locked((bfqd)->queue->queue_lock);			\
+	blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
+	pr_crit("%s bfq%d%c %s " fmt "\n", 				\
+		checked_dev_name((bfqd)->queue->backing_dev_info->dev),	\
+		(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));		\
+	pr_crit("%s %s " fmt "\n",					\
+	checked_dev_name((bfqd)->queue->backing_dev_info->dev),		\
+	__pbuf, ##args);						\
+} while (0)
+
+#else /* BFQ_GROUP_IOSCHED_ENABLED */
+
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...)				\
+	pr_crit("%s bfq%d%c " fmt "\n",					\
+		checked_dev_name((bfqd)->queue->backing_dev_info->dev),	\
+		(bfqq)->pid, bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
+		##args)
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)		do {} while (0)
+
+#endif /* BFQ_GROUP_IOSCHED_ENABLED */
+
+#define bfq_log(bfqd, fmt, args...) \
+	pr_crit("%s bfq " fmt "\n",					\
+		checked_dev_name((bfqd)->queue->backing_dev_info->dev),	\
+		##args)
+
+#else /* CONFIG_BFQ_REDIRECT_TO_CONSOLE */
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+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];						\
+									\
+	assert_spin_locked((bfqd)->queue->queue_lock);			\
+	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 /* BFQ_GROUP_IOSCHED_ENABLED */
+
+#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 /* BFQ_GROUP_IOSCHED_ENABLED */
+
+#define bfq_log(bfqd, fmt, args...) \
+	blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)
+#endif /* CONFIG_BFQ_REDIRECT_TO_CONSOLE */
+
+/* Expiration reasons. */
+enum bfqq_expiration {
+	BFQ_BFQQ_TOO_IDLE = 0,		/*
+					 * queue has been idling for
+					 * too long
+					 */
+	BFQ_BFQQ_BUDGET_TIMEOUT,	/* budget took too long to be used */
+	BFQ_BFQQ_BUDGET_EXHAUSTED,	/* budget consumed */
+	BFQ_BFQQ_NO_MORE_REQUESTS,	/* the queue has no more requests */
+	BFQ_BFQQ_PREEMPTED		/* preemption in progress */
+};
+
+
+struct bfqg_stats {
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+	/* 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
+};
+
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+/*
+ * 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 int 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.
+ * @active_entities: number of active entities belonging to the group;
+ *                   unused for the root group. Used to know whether there
+ *                   are groups with more than one active @bfq_entity
+ *                   (see the comments to the function
+ *                   bfq_bfqq_may_idle()).
+ * @rq_pos_tree: rbtree sorted by next_request position, used when
+ *               determining if two or more queues have interleaving
+ *               requests (see bfq_find_close_cooperator()).
+ *
+ * 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;
+
+	int active_entities;
+
+	struct rb_root rq_pos_tree;
+
+	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;
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	unsigned int idx = bfq_class_idx(entity);
+
+	BUG_ON(idx >= BFQ_IOPRIO_CLASSES);
+	BUG_ON(sched_data == NULL);
+
+	if (bfqq)
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+			     "entity_service_tree %p %d",
+			     sched_data->service_tree + idx, idx);
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+	else {
+		struct bfq_group *bfqg =
+			container_of(entity, struct bfq_group, entity);
+
+		bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
+			     "entity_service_tree %p %d",
+			     sched_data->service_tree + idx, idx);
+	}
+#endif
+	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;
+}
+
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+
+static struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
+{
+	struct bfq_entity *group_entity = bfqq->entity.parent;
+
+	if (!group_entity)
+		group_entity = &bfqq->bfqd->root_group->entity;
+
+	return container_of(group_entity, struct bfq_group, entity);
+}
+
+#else
+
+static struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
+{
+	return bfqq->bfqd->root_group;
+}
+
+#endif
+
+static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio);
+static void bfq_put_queue(struct bfq_queue *bfqq);
+static void bfq_dispatch_insert(struct request_queue *q, struct request *rq);
+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_end_wr_async_queues(struct bfq_data *bfqd,
+				    struct bfq_group *bfqg);
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
+#endif
+static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+
+#endif /* _BFQ_H */

From 0bd96428e086fd28800efdf5f0a5f62869af6e30 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Sat, 21 Jan 2017 12:41:14 +0100
Subject: [PATCH 10/51] Move thinktime from bic to bfqq

Prep change to make it possible to protect this field with a
scheduler lock.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c | 28 ++++++++++++++--------------
 block/bfq-mq.h         | 30 ++++++++++++++++--------------
 2 files changed, 30 insertions(+), 28 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index d1125aee658c..65f5dfb79417 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -698,6 +698,7 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 	if (unlikely(busy))
 		old_wr_coeff = bfqq->wr_coeff;
 
+	bfqq->ttime = bic->saved_ttime;
 	bfqq->wr_coeff = bic->saved_wr_coeff;
 	bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt;
 	BUG_ON(time_is_after_jiffies(bfqq->wr_start_at_switch_to_srt));
@@ -1287,7 +1288,7 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
 		 * details on the usage of the next variable.
 		 */
 		arrived_in_time =  ktime_get_ns() <=
-			RQ_BIC(rq)->ttime.last_end_request +
+			bfqq->ttime.last_end_request +
 			bfqd->bfq_slice_idle * 3;
 
 	bfq_log_bfqq(bfqd, bfqq,
@@ -2048,6 +2049,7 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	if (!bic)
 		return;
 
+	bic->saved_ttime = bfqq->ttime;
 	bic->saved_has_short_ttime = bfq_bfqq_has_short_ttime(bfqq);
 	bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
 	bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
@@ -3948,11 +3950,6 @@ static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 	bfq_put_queue(bfqq); /* release process reference */
 }
 
-static void bfq_init_icq(struct io_cq *icq)
-{
-	icq_to_bic(icq)->ttime.last_end_request = ktime_get_ns() - (1ULL<<32);
-}
-
 static void bfq_exit_icq(struct io_cq *icq)
 {
 	struct bfq_io_cq *bic = icq_to_bic(icq);
@@ -4084,6 +4081,9 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		bfq_mark_bfqq_just_created(bfqq);
 	} else
 		bfq_clear_bfqq_sync(bfqq);
+
+	bfqq->ttime.last_end_request = ktime_get_ns() - (1ULL<<32);
+
 	bfq_mark_bfqq_IO_bound(bfqq);
 
 	/* Tentative initial value to trade off between thr and lat */
@@ -4191,14 +4191,14 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
 }
 
 static void bfq_update_io_thinktime(struct bfq_data *bfqd,
-				    struct bfq_io_cq *bic)
+				    struct bfq_queue *bfqq)
 {
-	struct bfq_ttime *ttime = &bic->ttime;
-	u64 elapsed = ktime_get_ns() - bic->ttime.last_end_request;
+	struct bfq_ttime *ttime = &bfqq->ttime;
+	u64 elapsed = ktime_get_ns() - bfqq->ttime.last_end_request;
 
 	elapsed = min_t(u64, elapsed, 2 * bfqd->bfq_slice_idle);
 
-	ttime->ttime_samples = (7*bic->ttime.ttime_samples + 256) / 8;
+	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);
@@ -4240,8 +4240,8 @@ static void bfq_update_has_short_ttime(struct bfq_data *bfqd,
 	 * decide whether to mark as has_short_ttime
 	 */
 	if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
-	    (bfq_sample_valid(bic->ttime.ttime_samples) &&
-	     bic->ttime.ttime_mean > bfqd->bfq_slice_idle))
+	    (bfq_sample_valid(bfqq->ttime.ttime_samples) &&
+	     bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle))
 		has_short_ttime = false;
 
 	bfq_log_bfqq(bfqd, bfqq, "update_has_short_ttime: has_short_ttime %d",
@@ -4265,7 +4265,7 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	if (rq->cmd_flags & REQ_META)
 		bfqq->meta_pending++;
 
-	bfq_update_io_thinktime(bfqd, bic);
+	bfq_update_io_thinktime(bfqd, bfqq);
 	bfq_update_has_short_ttime(bfqd, bfqq, bic);
 	bfq_update_io_seektime(bfqd, bfqq, rq);
 
@@ -4436,7 +4436,7 @@ static void bfq_completed_request(struct request_queue *q, struct request *rq)
 
 	now_ns = ktime_get_ns();
 
-	RQ_BIC(rq)->ttime.last_end_request = now_ns;
+	bfqq->ttime.last_end_request = now_ns;
 
 	/*
 	 * Using us instead of ns, to get a reasonable precision in
diff --git a/block/bfq-mq.h b/block/bfq-mq.h
index 53954d1b87f8..0f51f270469c 100644
--- a/block/bfq-mq.h
+++ b/block/bfq-mq.h
@@ -210,6 +210,18 @@ struct bfq_entity {
 struct bfq_group;
 
 /**
+ * struct bfq_ttime - per process thinktime stats.
+ */
+struct bfq_ttime {
+	u64 last_end_request; /* completion time of last request */
+
+	u64 ttime_total; /* total process thinktime */
+	unsigned long ttime_samples; /* number of thinktime samples */
+	u64 ttime_mean; /* average process thinktime */
+
+};
+
+/**
  * struct bfq_queue - leaf schedulable entity.
  *
  * A bfq_queue is a leaf request queue; it can be associated with an
@@ -270,6 +282,9 @@ struct bfq_queue {
 	/* 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;
 
@@ -333,18 +348,6 @@ struct bfq_queue {
 };
 
 /**
- * struct bfq_ttime - per process thinktime stats.
- */
-struct bfq_ttime {
-	u64 last_end_request; /* completion time of last request */
-
-	u64 ttime_total; /* total process thinktime */
-	unsigned long ttime_samples; /* number of thinktime samples */
-	u64 ttime_mean; /* average process thinktime */
-
-};
-
-/**
  * struct bfq_io_cq - per (request_queue, io_context) structure.
  */
 struct bfq_io_cq {
@@ -352,8 +355,6 @@ struct bfq_io_cq {
 	struct io_cq icq; /* must be the first member */
 	/* array of two process queues, the sync and the async */
 	struct bfq_queue *bfqq[2];
-	/* associated @bfq_ttime struct */
-	struct bfq_ttime ttime;
 	/* per (request_queue, blkcg) ioprio */
 	int ioprio;
 #ifdef BFQ_GROUP_IOSCHED_ENABLED
@@ -390,6 +391,7 @@ struct bfq_io_cq {
 	unsigned long saved_last_wr_start_finish;
 	unsigned long saved_wr_start_at_switch_to_srt;
 	unsigned int saved_wr_cur_max_time;
+	struct bfq_ttime saved_ttime;
 };
 
 enum bfq_device_speed {

From 351a9aea7c0c9c30edacdbf2a3c0d089470de1e8 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Wed, 18 Jan 2017 11:42:22 +0100
Subject: [PATCH 11/51] Embed bfq-ioc.c and add locking on request queue

The version of bfq-ioc.c for bfq-iosched.c is not correct any more for
bfq-mq, because, in bfq-mq, the request queue lock is not being held
when bfq_bic_lookup is invoked. That function must then take that look
on its own. This commit removes the inclusion of bfq-ioc.c, copies the
content of bfq-ioc.c into bfq-mq-iosched.c, and adds the grabbing of
the lock.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c | 39 ++++++++++++++++++++++++++++++++++++---
 1 file changed, 36 insertions(+), 3 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 65f5dfb79417..756a618d5902 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -195,7 +195,39 @@ static int device_speed_thresh[2];
 
 static void bfq_schedule_dispatch(struct bfq_data *bfqd);
 
-#include "bfq-ioc.c"
+/**
+ * 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) {
+		struct bfq_io_cq *icq;
+
+		spin_lock_irq(q->queue_lock);
+		icq = icq_to_bic(ioc_lookup_icq(ioc, q));
+		spin_unlock_irq(q->queue_lock);
+
+		return icq;
+	}
+
+	return NULL;
+}
+
 #include "bfq-sched.c"
 #include "bfq-cgroup-included.c"
 
@@ -1520,13 +1552,14 @@ static void bfq_add_request(struct request *rq)
 }
 
 static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
-					  struct bio *bio)
+					  struct bio *bio,
+					  struct request_queue *q)
 {
 	struct task_struct *tsk = current;
 	struct bfq_io_cq *bic;
 	struct bfq_queue *bfqq;
 
-	bic = bfq_bic_lookup(bfqd, tsk->io_context);
+	bic = bfq_bic_lookup(bfqd, tsk->io_context, q);
 	if (!bic)
 		return NULL;
 

From ed0d64e27b2308813a2a846139e405e0479f0849 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Tue, 20 Dec 2016 09:07:19 +0100
Subject: [PATCH 12/51] Modify interface and operation to comply with
 blk-mq-sched

As for modifications of the operation, the major changes are the introduction
of a scheduler lock, and the moving to deferred work of the body of the hook
exit_icq. The latter change has been made to avoid deadlocks caused by the
combination of the following facts: 1) such a body  takes the scheduler lock,
and, if not deferred, 2) it does so from inside the exit_icq hook, which is
invoked with the queue lock held, and 3) there is at least one code path,
namely that starting from bfq_bio_merge, which takes these locks in the
opposite order.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-cgroup-included.c |   4 -
 block/bfq-mq-iosched.c      | 695 ++++++++++++++++++++++++--------------------
 block/bfq-mq.h              |  35 +--
 3 files changed, 394 insertions(+), 340 deletions(-)

diff --git a/block/bfq-cgroup-included.c b/block/bfq-cgroup-included.c
index 9c483b658179..8a73de76f32b 100644
--- a/block/bfq-cgroup-included.c
+++ b/block/bfq-cgroup-included.c
@@ -472,8 +472,6 @@ static struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
 	struct bfq_group *bfqg, *parent;
 	struct bfq_entity *entity;
 
-	assert_spin_locked(bfqd->queue->queue_lock);
-
 	bfqg = bfq_lookup_bfqg(bfqd, blkcg);
 
 	if (unlikely(!bfqg))
@@ -602,8 +600,6 @@ static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
 	struct bfq_group *bfqg;
 	struct bfq_entity *entity;
 
-	lockdep_assert_held(bfqd->queue->queue_lock);
-
 	bfqg = bfq_find_set_group(bfqd, blkcg);
 
 	if (unlikely(!bfqg))
diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 756a618d5902..c963d92a32c2 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -81,7 +81,13 @@
 #include <linux/jiffies.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"
 #undef CONFIG_BFQ_GROUP_IOSCHED /* cgroups support not yet functional */
 #include "bfq-mq.h"
 
@@ -193,8 +199,6 @@ static int device_speed_thresh[2];
 #define RQ_BIC(rq)		((struct bfq_io_cq *) (rq)->elv.priv[0])
 #define RQ_BFQQ(rq)		((rq)->elv.priv[1])
 
-static void bfq_schedule_dispatch(struct bfq_data *bfqd);
-
 /**
  * icq_to_bic - convert iocontext queue structure to bfq_io_cq.
  * @icq: the iocontext queue.
@@ -216,11 +220,12 @@ static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
 					struct request_queue *q)
 {
 	if (ioc) {
+		unsigned long flags;
 		struct bfq_io_cq *icq;
 
-		spin_lock_irq(q->queue_lock);
+		spin_lock_irqsave(q->queue_lock, flags);
 		icq = icq_to_bic(ioc_lookup_icq(ioc, q));
-		spin_unlock_irq(q->queue_lock);
+		spin_unlock_irqrestore(q->queue_lock, flags);
 
 		return icq;
 	}
@@ -244,7 +249,7 @@ static void bfq_schedule_dispatch(struct bfq_data *bfqd)
 {
 	if (bfqd->queued != 0) {
 		bfq_log(bfqd, "schedule dispatch");
-		kblockd_schedule_work(&bfqd->unplug_work);
+		blk_mq_run_hw_queues(bfqd->queue, true);
 	}
 }
 
@@ -768,9 +773,7 @@ static int bfqq_process_refs(struct bfq_queue *bfqq)
 {
 	int process_refs, io_refs;
 
-	lockdep_assert_held(bfqq->bfqd->queue->queue_lock);
-
-	io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE];
+	io_refs = bfqq->allocated;
 	process_refs = bfqq->ref - io_refs - bfqq->entity.on_st;
 	BUG_ON(process_refs < 0);
 	return process_refs;
@@ -1584,6 +1587,7 @@ static sector_t get_sdist(sector_t last_pos, struct request *rq)
 	return sdist;
 }
 
+#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;
@@ -1597,8 +1601,10 @@ static void bfq_deactivate_request(struct request_queue *q, struct request *rq)
 	BUG_ON(bfqd->rq_in_driver == 0);
 	bfqd->rq_in_driver--;
 }
+#endif
 
-static void bfq_remove_request(struct request *rq)
+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;
@@ -1619,6 +1625,10 @@ static void bfq_remove_request(struct request *rq)
 	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;
 
@@ -1659,13 +1669,36 @@ static void bfq_remove_request(struct request *rq)
 	bfqg_stats_update_io_remove(bfqq_group(bfqq), rq->cmd_flags);
 }
 
-static enum elv_merge bfq_merge(struct request_queue *q, struct request **req,
-				struct bio *bio)
+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;
+	bool ret;
+
+	spin_lock_irq(&bfqd->lock);
+	ret = blk_mq_sched_try_merge(q, bio, &free);
+
+	/*
+	 * XXX Not yet freeing without lock held, to avoid an
+	 * inconsistency with respect to the lock-protected invocation
+	 * of blk_mq_sched_try_insert_merge in bfq_bio_merge. Waiting
+	 * for clarifications from Jens.
+	 */
+	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);
+	__rq = bfq_find_rq_fmerge(bfqd, bio, q);
 	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
 		return ELEVATOR_FRONT_MERGE;
@@ -1674,7 +1707,7 @@ static enum elv_merge bfq_merge(struct request_queue *q, struct request **req,
 	return ELEVATOR_NO_MERGE;
 }
 
-static void bfq_merged_request(struct request_queue *q, struct request *req,
+static void bfq_request_merged(struct request_queue *q, struct request *req,
 			       enum elv_merge type)
 {
 	if (type == ELEVATOR_FRONT_MERGE &&
@@ -1689,6 +1722,8 @@ static void bfq_merged_request(struct request_queue *q, struct request *req,
 		/* Reposition request in its sort_list */
 		elv_rb_del(&bfqq->sort_list, req);
 		elv_rb_add(&bfqq->sort_list, req);
+
+		spin_lock_irq(&bfqd->lock);
 		/* Choose next request to be served for bfqq */
 		prev = bfqq->next_rq;
 		next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req,
@@ -1704,22 +1739,19 @@ static void bfq_merged_request(struct request_queue *q, struct request *req,
 			bfq_updated_next_req(bfqd, bfqq);
 			bfq_pos_tree_add_move(bfqd, bfqq);
 		}
+		spin_unlock_irq(&bfqd->lock);
 	}
 }
 
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
-static void bfq_bio_merged(struct request_queue *q, struct request *req,
-			   struct bio *bio)
-{
-	bfqg_stats_update_io_merged(bfqq_group(RQ_BFQQ(req)), bio->bi_opf);
-}
-#endif
-
-static void bfq_merged_requests(struct request_queue *q, struct request *rq,
+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
@@ -1740,7 +1772,10 @@ static void bfq_merged_requests(struct request_queue *q, struct request *rq,
 	if (bfqq->next_rq == next)
 		bfqq->next_rq = rq;
 
-	bfq_remove_request(next);
+	bfq_remove_request(q, next);
+
+	spin_unlock_irq(&bfqq->bfqd->lock);
+end:
 	bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
 }
 
@@ -1786,7 +1821,7 @@ static void bfq_end_wr(struct bfq_data *bfqd)
 {
 	struct bfq_queue *bfqq;
 
-	spin_lock_irq(bfqd->queue->queue_lock);
+	spin_lock_irq(&bfqd->lock);
 
 	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
 		bfq_bfqq_end_wr(bfqq);
@@ -1794,7 +1829,7 @@ static void bfq_end_wr(struct bfq_data *bfqd)
 		bfq_bfqq_end_wr(bfqq);
 	bfq_end_wr_async(bfqd);
 
-	spin_unlock_irq(bfqd->queue->queue_lock);
+	spin_unlock_irq(&bfqd->lock);
 }
 
 static sector_t bfq_io_struct_pos(void *io_struct, bool request)
@@ -2184,8 +2219,8 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 	bfq_put_queue(bfqq);
 }
 
-static int bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
-			       struct bio *bio)
+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);
@@ -2203,7 +2238,7 @@ static int bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
 	 * merge only if rq is queued there.
 	 * Queue lock is held here.
 	 */
-	bic = bfq_bic_lookup(bfqd, current->io_context);
+	bic = bfq_bic_lookup(bfqd, current->io_context, q);
 	if (!bic)
 		return false;
 
@@ -2228,12 +2263,6 @@ static int bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
 	return bfqq == RQ_BFQQ(rq);
 }
 
-static int bfq_allow_rq_merge(struct request_queue *q, struct request *rq,
-			      struct request *next)
-{
-	return RQ_BFQQ(rq) == RQ_BFQQ(next);
-}
-
 /*
  * Set the maximum time for the in-service queue to consume its
  * budget. This prevents seeky processes from lowering the throughput.
@@ -2264,7 +2293,6 @@ static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
 {
 	if (bfqq) {
 		bfqg_stats_update_avg_queue_size(bfqq_group(bfqq));
-		bfq_mark_bfqq_must_alloc(bfqq);
 		bfq_clear_bfqq_fifo_expire(bfqq);
 
 		bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8;
@@ -2703,27 +2731,28 @@ static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq)
 }
 
 /*
- * Move request from internal lists to the dispatch list of the request queue
+ * Remove request from internal lists.
  */
-static void bfq_dispatch_insert(struct request_queue *q, struct request *rq)
+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, in a forced_dispatch, this prevents two counters related
-	 * to bfqq->dispatched to risk to be uselessly decremented if bfqq
-	 * is not in service, and then to be incremented again after
-	 * incrementing bfqq->dispatched.
+	 * 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_update_peak_rate(q->elevator->elevator_data, rq);
 
-	bfq_remove_request(rq);
-	elv_dispatch_sort(q, rq);
+	bfq_remove_request(q, rq);
 }
 
 static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
@@ -3605,7 +3634,7 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
 	bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
 
 	if (bfq_may_expire_for_budg_timeout(bfqq) &&
-	    !hrtimer_active(&bfqd->idle_slice_timer) &&
+	    !bfq_bfqq_wait_request(bfqq) &&
 	    !bfq_bfqq_must_idle(bfqq))
 		goto expire;
 
@@ -3641,7 +3670,6 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
 			 * arrives.
 			 */
 			if (bfq_bfqq_wait_request(bfqq)) {
-				BUG_ON(!hrtimer_active(&bfqd->idle_slice_timer));
 				/*
 				 * If we get here: 1) at least a new request
 				 * has arrived but we have not disabled the
@@ -3668,7 +3696,7 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
 	 * for a new request, or has requests waiting for a completion and
 	 * may idle after their completion, then keep it anyway.
 	 */
-	if (hrtimer_active(&bfqd->idle_slice_timer) ||
+	if (bfq_bfqq_wait_request(bfqq) ||
 	    (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) {
 		bfqq = NULL;
 		goto keep_queue;
@@ -3753,13 +3781,11 @@ static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 }
 
 /*
- * Dispatch one request from bfqq, moving it to the request queue
- * dispatch list.
+ * Dispatch next request from bfqq.
  */
-static int bfq_dispatch_request(struct bfq_data *bfqd,
-				struct bfq_queue *bfqq)
+static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
+						 struct bfq_queue *bfqq)
 {
-	int dispatched = 0;
 	struct request *rq = bfqq->next_rq;
 	unsigned long service_to_charge;
 
@@ -3775,7 +3801,7 @@ static int bfq_dispatch_request(struct bfq_data *bfqd,
 
 	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
 
-	bfq_dispatch_insert(bfqd->queue, rq);
+	bfq_dispatch_remove(bfqd->queue, rq);
 
 	/*
 	 * If weight raising has to terminate for bfqq, then next
@@ -3791,86 +3817,61 @@ static int bfq_dispatch_request(struct bfq_data *bfqd,
 	bfq_update_wr_data(bfqd, bfqq);
 
 	bfq_log_bfqq(bfqd, bfqq,
-			"dispatched %u sec req (%llu), budg left %d",
+	     "dispatched %u sec req (%llu), budg left %d, new disp_nr %d",
 			blk_rq_sectors(rq),
 			(unsigned long long) blk_rq_pos(rq),
-			bfq_bfqq_budget_left(bfqq));
-
-	dispatched++;
+		     bfq_bfqq_budget_left(bfqq),
+		     bfqq->dispatched);
 
 	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 dispatched;
+	return rq;
 
 expire:
 	bfq_bfqq_expire(bfqd, bfqq, false, BFQ_BFQQ_BUDGET_EXHAUSTED);
-	return dispatched;
-}
-
-static int __bfq_forced_dispatch_bfqq(struct bfq_queue *bfqq)
-{
-	int dispatched = 0;
-
-	while (bfqq->next_rq) {
-		bfq_dispatch_insert(bfqq->bfqd->queue, bfqq->next_rq);
-		dispatched++;
-	}
-
-	BUG_ON(!list_empty(&bfqq->fifo));
-	return dispatched;
+	return rq;
 }
 
-/*
- * Drain our current requests.
- * Used for barriers and when switching io schedulers on-the-fly.
- */
-static int bfq_forced_dispatch(struct bfq_data *bfqd)
+static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
 {
-	struct bfq_queue *bfqq, *n;
-	struct bfq_service_tree *st;
-	int dispatched = 0;
-
-	bfqq = bfqd->in_service_queue;
-	if (bfqq)
-		__bfq_bfqq_expire(bfqd, bfqq);
+	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 
 	/*
-	 * Loop through classes, and be careful to leave the scheduler
-	 * in a consistent state, as feedback mechanisms and vtime
-	 * updates cannot be disabled during the process.
+	 * Avoiding lock: a race on bfqd->busy_queues should cause at
+	 * most a call to dispatch for nothing
 	 */
-	list_for_each_entry_safe(bfqq, n, &bfqd->active_list, bfqq_list) {
-		st = bfq_entity_service_tree(&bfqq->entity);
-
-		dispatched += __bfq_forced_dispatch_bfqq(bfqq);
-
-		bfqq->max_budget = bfq_max_budget(bfqd);
-		bfq_forget_idle(st);
-	}
-
-	BUG_ON(bfqd->busy_queues != 0);
-
-	return dispatched;
+	return !list_empty_careful(&bfqd->dispatch) ||
+		bfqd->busy_queues > 0;
 }
 
-static int bfq_dispatch_requests(struct request_queue *q, int force)
+static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 {
-	struct bfq_data *bfqd = q->elevator->elevator_data;
-	struct bfq_queue *bfqq;
+	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);
+		goto exit;
+	}
 
 	bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues);
 
 	if (bfqd->busy_queues == 0)
-		return 0;
-
-	if (unlikely(force))
-		return bfq_forced_dispatch(bfqd);
+		goto exit;
 
 	/*
 	 * Force device to serve one request at a time if
@@ -3885,25 +3886,39 @@ static int bfq_dispatch_requests(struct request_queue *q, int force)
 	 * throughput.
 	 */
 	if (bfqd->strict_guarantees && bfqd->rq_in_driver > 0)
-		return 0;
+		goto exit;
 
 	bfqq = bfq_select_queue(bfqd);
 	if (!bfqq)
-		return 0;
+		goto exit;
 
 	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
 
 	BUG_ON(bfq_bfqq_wait_request(bfqq));
 
-	if (!bfq_dispatch_request(bfqd, bfqq))
-		return 0;
-
-	bfq_log_bfqq(bfqd, bfqq, "dispatched %s request",
-			bfq_bfqq_sync(bfqq) ? "sync" : "async");
+	rq = bfq_dispatch_rq_from_bfqq(bfqd, bfqq);
 
 	BUG_ON(bfqq->next_rq == NULL &&
 	       bfqq->entity.budget < bfqq->entity.service);
-	return 1;
+exit:
+	if (rq) {
+		rq->rq_flags |= RQF_STARTED;
+		bfqd->rq_in_driver++;
+	}
+
+	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;
 }
 
 /*
@@ -3921,13 +3936,14 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
 
 	BUG_ON(bfqq->ref <= 0);
 
-	bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d", bfqq, bfqq->ref);
+	if (bfqq->bfqd)
+		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d", bfqq, bfqq->ref);
+
 	bfqq->ref--;
 	if (bfqq->ref)
 		return;
 
 	BUG_ON(rb_first(&bfqq->sort_list));
-	BUG_ON(bfqq->allocated[READ] + bfqq->allocated[WRITE] != 0);
 	BUG_ON(bfqq->entity.tree);
 	BUG_ON(bfq_bfqq_busy(bfqq));
 
@@ -3942,7 +3958,8 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
 		 */
 		hlist_del_init(&bfqq->burst_list_node);
 
-	bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p freed", bfqq);
+	if (bfqq->bfqd)
+		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p freed", bfqq);
 
 	kmem_cache_free(bfq_pool, bfqq);
 #ifdef BFQ_GROUP_IOSCHED_ENABLED
@@ -3983,29 +4000,52 @@ static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 	bfq_put_queue(bfqq); /* release process reference */
 }
 
-static void bfq_exit_icq(struct io_cq *icq)
+static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
 {
-	struct bfq_io_cq *bic = icq_to_bic(icq);
-	struct bfq_data *bfqd = bic_to_bfqd(bic);
+	struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);
+	struct bfq_data *bfqd;
 
-	if (bic_to_bfqq(bic, false)) {
-		bfq_exit_bfqq(bfqd, bic_to_bfqq(bic, false));
-		bic_set_bfqq(bic, NULL, false);
-	}
+	if (bfqq)
+		bfqd = bfqq->bfqd; /* NULL if scheduler already exited */
 
-	if (bic_to_bfqq(bic, true)) {
+	if (bfqq && bfqd) {
+		spin_lock_irq(&bfqd->lock);
 		/*
 		 * If the bic is using a shared queue, put the reference
 		 * taken on the io_context when the bic started using a
 		 * shared bfq_queue.
 		 */
-		if (bfq_bfqq_coop(bic_to_bfqq(bic, true)))
-			put_io_context(icq->ioc);
-		bfq_exit_bfqq(bfqd, bic_to_bfqq(bic, true));
-		bic_set_bfqq(bic, NULL, true);
+		if (is_sync && bfq_bfqq_coop(bfqq))
+			put_io_context(bic->icq.ioc);
+		bfq_exit_bfqq(bfqd, bfqq);
+		bic_set_bfqq(bic, NULL, is_sync);
+		spin_unlock_irq(&bfqd->lock);
 	}
 }
 
+static void bfq_exit_icq_body(struct work_struct *work)
+{
+	struct bfq_io_cq *bic =
+		container_of(work, struct bfq_io_cq, exit_icq_work);
+
+	bfq_exit_icq_bfqq(bic, true);
+	bfq_exit_icq_bfqq(bic, false);
+}
+
+static void bfq_init_icq(struct io_cq *icq)
+{
+	struct bfq_io_cq *bic = icq_to_bic(icq);
+
+	INIT_WORK(&bic->exit_icq_work, bfq_exit_icq_body);
+}
+
+static void bfq_exit_icq(struct io_cq *icq)
+{
+	struct bfq_io_cq *bic = icq_to_bic(icq);
+
+	kblockd_schedule_work(&bic->exit_icq_work);
+}
+
 /*
  * Update the entity prio values; note that the new values will not
  * be used until the next (re)activation.
@@ -4015,6 +4055,10 @@ static void bfq_set_next_ioprio_data(struct bfq_queue *bfqq,
 {
 	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) {
@@ -4095,6 +4139,8 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	INIT_HLIST_NODE(&bfqq->burst_list_node);
 	BUG_ON(!hlist_unhashed(&bfqq->burst_list_node));
 
+	spin_lock_init(&bfqq->lock);
+
 	bfqq->ref = 0;
 	bfqq->bfqd = bfqd;
 
@@ -4351,22 +4397,13 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		if (budget_timeout)
 			bfq_bfqq_expire(bfqd, bfqq, false,
 					BFQ_BFQQ_BUDGET_TIMEOUT);
-
-		/*
-		 * Let the request rip immediately, or let a new queue be
-		 * selected if bfqq has just been expired.
-		 */
-		__blk_run_queue(bfqd->queue);
 	}
 }
 
-static void bfq_insert_request(struct request_queue *q, struct request *rq)
+static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 {
-	struct bfq_data *bfqd = q->elevator->elevator_data;
 	struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq;
 
-	assert_spin_locked(bfqd->queue->queue_lock);
-
 	/*
 	 * An unplug may trigger a requeue of a request from the device
 	 * driver: make sure we are in process context while trying to
@@ -4381,8 +4418,8 @@ static void bfq_insert_request(struct request_queue *q, struct request *rq)
 			 * Release the request's reference to the old bfqq
 			 * and make sure one is taken to the shared queue.
 			 */
-			new_bfqq->allocated[rq_data_dir(rq)]++;
-			bfqq->allocated[rq_data_dir(rq)]--;
+			new_bfqq->allocated++;
+			bfqq->allocated--;
 			new_bfqq->ref++;
 			bfq_clear_bfqq_just_created(bfqq);
 			if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
@@ -4406,6 +4443,55 @@ static void bfq_insert_request(struct request_queue *q, struct request *rq)
 	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))
+		goto done;
+	spin_unlock_irq(&bfqd->lock);
+
+	blk_mq_sched_request_inserted(rq);
+
+	spin_lock_irq(&bfqd->lock);
+	if (at_head || blk_rq_is_passthrough(rq)) {
+		struct bfq_queue *bfqq = RQ_BFQQ(rq);
+
+		if (at_head)
+			list_add(&rq->queuelist, &bfqd->dispatch);
+		else
+			list_add_tail(&rq->queuelist, &bfqd->dispatch);
+
+		if (bfqq)
+			bfqq->dispatched++;
+	} else {
+		__bfq_insert_request(bfqd, rq);
+
+		if (rq_mergeable(rq)) {
+			elv_rqhash_add(q, rq);
+			if (!q->last_merge)
+				q->last_merge = rq;
+		}
+	}
+done:
+	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,
@@ -4431,27 +4517,17 @@ static void bfq_update_hw_tag(struct bfq_data *bfqd)
 	bfqd->hw_tag_samples = 0;
 }
 
-static void bfq_completed_request(struct request_queue *q, struct request *rq)
+static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 {
-	struct bfq_queue *bfqq = RQ_BFQQ(rq);
-	struct bfq_data *bfqd = bfqq->bfqd;
 	u64 now_ns;
 	u32 delta_us;
 
-	bfq_log_bfqq(bfqd, bfqq, "completed one req with %u sects left",
-		     blk_rq_sectors(rq));
-
-	assert_spin_locked(bfqd->queue->queue_lock);
 	bfq_update_hw_tag(bfqd);
 
 	BUG_ON(!bfqd->rq_in_driver);
 	BUG_ON(!bfqq->dispatched);
 	bfqd->rq_in_driver--;
 	bfqq->dispatched--;
-	bfqg_stats_update_completion(bfqq_group(bfqq),
-				     rq_start_time_ns(rq),
-				     rq_io_start_time_ns(rq),
-				     rq->cmd_flags);
 
 	if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) {
 		BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
@@ -4477,7 +4553,8 @@ static void bfq_completed_request(struct request_queue *q, struct request *rq)
 	 */
 	delta_us = div_u64(now_ns - bfqd->last_completion, NSEC_PER_USEC);
 
-	bfq_log(bfqd, "rq_completed: delta %uus/%luus max_size %u rate %llu/%llu",
+	bfq_log_bfqq(bfqd, bfqq,
+		"rq_completed: delta %uus/%luus max_size %u rate %llu/%llu",
 		delta_us, BFQ_MIN_TT/NSEC_PER_USEC, bfqd->last_rq_max_size,
 		(USEC_PER_SEC*
 		(u64)((bfqd->last_rq_max_size<<BFQ_RATE_SHIFT)/delta_us))
@@ -4527,7 +4604,7 @@ static void bfq_completed_request(struct request_queue *q, struct request *rq)
 	if (bfqd->in_service_queue == bfqq) {
 		if (bfqq->dispatched == 0 && bfq_bfqq_must_idle(bfqq)) {
 			bfq_arm_slice_timer(bfqd);
-			goto out;
+			return;
 		} else if (bfq_may_expire_for_budg_timeout(bfqq))
 			bfq_bfqq_expire(bfqd, bfqq, false,
 					BFQ_BFQQ_BUDGET_TIMEOUT);
@@ -4537,68 +4614,55 @@ static void bfq_completed_request(struct request_queue *q, struct request *rq)
 			bfq_bfqq_expire(bfqd, bfqq, false,
 					BFQ_BFQQ_NO_MORE_REQUESTS);
 	}
-
-	if (!bfqd->rq_in_driver)
-		bfq_schedule_dispatch(bfqd);
-
-out:
-	return;
 }
 
-static int __bfq_may_queue(struct bfq_queue *bfqq)
+static void bfq_put_rq_priv_body(struct bfq_queue *bfqq)
 {
-	if (bfq_bfqq_wait_request(bfqq) && bfq_bfqq_must_alloc(bfqq)) {
-		bfq_clear_bfqq_must_alloc(bfqq);
-		return ELV_MQUEUE_MUST;
-	}
+	bfqq->allocated--;
 
-	return ELV_MQUEUE_MAY;
+	bfq_put_queue(bfqq);
 }
 
-static int bfq_may_queue(struct request_queue *q, unsigned int op)
+static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
 {
-	struct bfq_data *bfqd = q->elevator->elevator_data;
-	struct task_struct *tsk = current;
-	struct bfq_io_cq *bic;
-	struct bfq_queue *bfqq;
-
-	/*
-	 * Don't force setup of a queue from here, as a call to may_queue
-	 * does not necessarily imply that a request actually will be
-	 * queued. So just lookup a possibly existing queue, or return
-	 * 'may queue' if that fails.
-	 */
-	bic = bfq_bic_lookup(bfqd, tsk->io_context);
-	if (!bic)
-		return ELV_MQUEUE_MAY;
-
-	bfqq = bic_to_bfqq(bic, op_is_sync(op));
-	if (bfqq)
-		return __bfq_may_queue(bfqq);
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_data *bfqd = bfqq->bfqd;
 
-	return ELV_MQUEUE_MAY;
-}
+	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);
 
-/*
- * Queue lock held here.
- */
-static void bfq_put_request(struct request *rq)
-{
-	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	if (likely(rq->rq_flags & RQF_STARTED)) {
+		unsigned long flags;
 
-	if (bfqq) {
-		const int rw = rq_data_dir(rq);
+		spin_lock_irqsave(&bfqd->lock, flags);
 
-		BUG_ON(!bfqq->allocated[rw]);
-		bfqq->allocated[rw]--;
+		bfq_completed_request(bfqq, bfqd);
+		bfq_put_rq_priv_body(bfqq);
 
-		rq->elv.priv[0] = NULL;
-		rq->elv.priv[1] = NULL;
+		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.
+		 * Fortunately, this situation occurs only in process
+		 * context, so taking the scheduler lock does not
+		 * cause any deadlock, even if other locks are already
+		 * (correctly) held by this process.
+		 */
 
-		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_request %p, %d",
-			     bfqq, bfqq->ref);
-		bfq_put_queue(bfqq);
+		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;
 }
 
 /*
@@ -4630,18 +4694,16 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
 /*
  * Allocate bfq data structures associated with this request.
  */
-static int bfq_set_request(struct request_queue *q, struct request *rq,
-			   struct bio *bio, gfp_t gfp_mask)
+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 rw = rq_data_dir(rq);
 	const int is_sync = rq_is_sync(rq);
 	struct bfq_queue *bfqq;
-	unsigned long flags;
 	bool bfqq_already_existing = false, split = false;
 
-	spin_lock_irqsave(q->queue_lock, flags);
+	spin_lock_irq(&bfqd->lock);
 
 	if (!bic)
 		goto queue_fail;
@@ -4661,7 +4723,7 @@ static int bfq_set_request(struct request_queue *q, struct request *rq,
 		bic_set_bfqq(bic, bfqq, is_sync);
 		if (split && is_sync) {
 			bfq_log_bfqq(bfqd, bfqq,
-				     "set_request: was_in_list %d "
+				     "get_request: was_in_list %d "
 				     "was_in_large_burst %d "
 				     "large burst in progress %d",
 				     bic->was_in_burst_list,
@@ -4671,12 +4733,12 @@ static int bfq_set_request(struct request_queue *q, struct request *rq,
 			if ((bic->was_in_burst_list && bfqd->large_burst) ||
 			    bic->saved_in_large_burst) {
 				bfq_log_bfqq(bfqd, bfqq,
-					     "set_request: marking in "
+					     "get_request: marking in "
 					     "large burst");
 				bfq_mark_bfqq_in_large_burst(bfqq);
 			} else {
 				bfq_log_bfqq(bfqd, bfqq,
-					     "set_request: clearing in "
+					     "get_request: clearing in "
 					     "large burst");
 				bfq_clear_bfqq_in_large_burst(bfqq);
 				if (bic->was_in_burst_list)
@@ -4703,9 +4765,12 @@ static int bfq_set_request(struct request_queue *q, struct request *rq,
 		}
 	}
 
-	bfqq->allocated[rw]++;
+	bfqq->allocated++;
+	bfq_log_bfqq(bfqq->bfqd, bfqq,
+		     "get_request: new allocated %d", bfqq->allocated);
+
 	bfqq->ref++;
-	bfq_log_bfqq(bfqd, bfqq, "set_request: bfqq %p, %d", bfqq, bfqq->ref);
+	bfq_log_bfqq(bfqd, bfqq, "get_request: bfqq %p, %d", bfqq, bfqq->ref);
 
 	rq->elv.priv[0] = bic;
 	rq->elv.priv[1] = bfqq;
@@ -4733,26 +4798,53 @@ static int bfq_set_request(struct request_queue *q, struct request *rq,
 	if (unlikely(bfq_bfqq_just_created(bfqq)))
 		bfq_handle_burst(bfqd, bfqq);
 
-	spin_unlock_irqrestore(q->queue_lock, flags);
+	spin_unlock_irq(&bfqd->lock);
 
 	return 0;
 
 queue_fail:
-	bfq_schedule_dispatch(bfqd);
-	spin_unlock_irqrestore(q->queue_lock, flags);
+	spin_unlock_irq(&bfqd->lock);
 
 	return 1;
 }
 
-static void bfq_kick_queue(struct work_struct *work)
+static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
 {
-	struct bfq_data *bfqd =
-		container_of(work, struct bfq_data, unplug_work);
-	struct request_queue *q = bfqd->queue;
+	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);
 
-	spin_lock_irq(q->queue_lock);
-	__blk_run_queue(q);
-	spin_unlock_irq(q->queue_lock);
+	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 = BFQ_BFQQ_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 = BFQ_BFQQ_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);
 }
 
 /*
@@ -4763,59 +4855,22 @@ 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;
-	unsigned long flags;
-	enum bfqq_expiration reason;
-
-	spin_lock_irqsave(bfqd->queue->queue_lock, flags);
+	struct bfq_queue *bfqq = bfqd->in_service_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 the timer handler
-	 * spins on the queue_lock and 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.
+	 * 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_log_bfqq(bfqd, bfqq, "slice_timer expired");
-		bfq_clear_bfqq_wait_request(bfqq);
-
-		if (bfq_bfqq_budget_timeout(bfqq))
-			/*
-			 * Also here the queue can be safely expired
-			 * for budget timeout without wasting
-			 * guarantees
-			 */
-			reason = BFQ_BFQQ_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 = BFQ_BFQQ_TOO_IDLE;
-		else
-			goto schedule_dispatch;
-
-		bfq_bfqq_expire(bfqd, bfqq, true, reason);
-	}
-
-schedule_dispatch:
-	bfq_schedule_dispatch(bfqd);
+	if (bfqq)
+		bfq_idle_slice_timer_body(bfqq);
 
-	spin_unlock_irqrestore(bfqd->queue->queue_lock, flags);
 	return HRTIMER_NORESTART;
 }
 
-static void bfq_shutdown_timer_wq(struct bfq_data *bfqd)
-{
-	hrtimer_cancel(&bfqd->idle_slice_timer);
-	cancel_work_sync(&bfqd->unplug_work);
-}
-
 static void __bfq_put_async_bfqq(struct bfq_data *bfqd,
 				 struct bfq_queue **bfqq_ptr)
 {
@@ -4852,28 +4907,40 @@ static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
 static void bfq_exit_queue(struct elevator_queue *e)
 {
 	struct bfq_data *bfqd = e->elevator_data;
-	struct request_queue *q = bfqd->queue;
 	struct bfq_queue *bfqq, *n;
 
-	bfq_shutdown_timer_wq(bfqd);
-
-	spin_lock_irq(q->queue_lock);
+	hrtimer_cancel(&bfqd->idle_slice_timer);
 
 	BUG_ON(bfqd->in_service_queue);
-	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
-		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
 
-	spin_unlock_irq(q->queue_lock);
+	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list) {
+		if (bfqq->bic) /* bfqqs without bic are handled below */
+			cancel_work_sync(&bfqq->bic->exit_icq_work);
+	}
+
+	spin_lock_irq(&bfqd->lock);
+	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list) {
+		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
+		/*
+		 * Make sure that deferred exit_icq_work completes
+		 * without errors for bfq_queues without bic
+		 */
+		if (!bfqq->bic)
+			bfqq->bfqd = NULL;
+	}
+	spin_unlock_irq(&bfqd->lock);
 
-	bfq_shutdown_timer_wq(bfqd);
+	hrtimer_cancel(&bfqd->idle_slice_timer);
 
 	BUG_ON(hrtimer_active(&bfqd->idle_slice_timer));
 
 #ifdef BFQ_GROUP_IOSCHED_ENABLED
-	blkcg_deactivate_policy(q, &blkcg_policy_bfq);
+	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);
@@ -4934,10 +5001,6 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 
 	bfqd->queue = q;
 
-	spin_lock_irq(q->queue_lock);
-	q->elevator = eq;
-	spin_unlock_irq(q->queue_lock);
-
 	bfqd->root_group = bfq_create_group_hierarchy(bfqd, q->node);
 	if (!bfqd->root_group)
 		goto out_free;
@@ -4951,8 +5014,6 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	bfqd->queue_weights_tree = RB_ROOT;
 	bfqd->group_weights_tree = RB_ROOT;
 
-	INIT_WORK(&bfqd->unplug_work, bfq_kick_queue);
-
 	INIT_LIST_HEAD(&bfqd->active_list);
 	INIT_LIST_HEAD(&bfqd->idle_list);
 	INIT_HLIST_HEAD(&bfqd->burst_list);
@@ -5001,6 +5062,11 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
 	bfqd->device_speed = BFQ_BFQD_FAST;
 
+	spin_lock_init(&bfqd->lock);
+	INIT_LIST_HEAD(&bfqd->dispatch);
+
+	q->elevator = eq;
+
 	return 0;
 
 out_free:
@@ -5057,7 +5123,7 @@ static ssize_t bfq_weights_show(struct elevator_queue *e, char *page)
 	num_char += sprintf(page + num_char, "Tot reqs queued %d\n\n",
 			    bfqd->queued);
 
-	spin_lock_irq(bfqd->queue->queue_lock);
+	spin_lock_irq(&bfqd->lock);
 
 	num_char += sprintf(page + num_char, "Active:\n");
 	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) {
@@ -5086,7 +5152,7 @@ static ssize_t bfq_weights_show(struct elevator_queue *e, char *page)
 				    jiffies_to_msecs(bfqq->wr_cur_max_time));
 	}
 
-	spin_unlock_irq(bfqd->queue->queue_lock);
+	spin_unlock_irq(&bfqd->lock);
 
 	return num_char;
 }
@@ -5294,35 +5360,31 @@ static struct elv_fs_entry bfq_attrs[] = {
 	__ATTR_NULL
 };
 
-static struct elevator_type iosched_bfq = {
-	.ops.sq = {
-		.elevator_merge_fn =		bfq_merge,
-		.elevator_merged_fn =		bfq_merged_request,
-		.elevator_merge_req_fn =	bfq_merged_requests,
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
-		.elevator_bio_merged_fn =	bfq_bio_merged,
-#endif
-		.elevator_allow_bio_merge_fn =	bfq_allow_bio_merge,
-		.elevator_allow_rq_merge_fn =	bfq_allow_rq_merge,
-		.elevator_dispatch_fn =		bfq_dispatch_requests,
-		.elevator_add_req_fn =		bfq_insert_request,
-		.elevator_activate_req_fn =	bfq_activate_request,
-		.elevator_deactivate_req_fn =	bfq_deactivate_request,
-		.elevator_completed_req_fn =	bfq_completed_request,
-		.elevator_former_req_fn =	elv_rb_former_request,
-		.elevator_latter_req_fn =	elv_rb_latter_request,
-		.elevator_init_icq_fn =		bfq_init_icq,
-		.elevator_exit_icq_fn =		bfq_exit_icq,
-		.elevator_set_req_fn =		bfq_set_request,
-		.elevator_put_req_fn =		bfq_put_request,
-		.elevator_may_queue_fn =	bfq_may_queue,
-		.elevator_init_fn =		bfq_init_queue,
-		.elevator_exit_fn =		bfq_exit_queue,
+static struct elevator_type iosched_bfq_mq = {
+	.ops.mq = {
+		.get_rq_priv		= bfq_get_rq_private,
+		.put_rq_priv		= bfq_put_rq_private,
+		.init_icq		= bfq_init_icq,
+		.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-sq",
+	.elevator_name =	"bfq-mq",
 	.elevator_owner =	THIS_MODULE,
 };
 
@@ -5392,7 +5454,7 @@ static int __init bfq_init(void)
 	device_speed_thresh[0] = (4 * R_slow[0]) / 3;
 	device_speed_thresh[1] = (4 * R_slow[1]) / 3;
 
-	ret = elv_register(&iosched_bfq);
+	ret = elv_register(&iosched_bfq_mq);
 	if (ret)
 		goto err_pol_unreg;
 
@@ -5412,8 +5474,8 @@ static int __init bfq_init(void)
 
 static void __exit bfq_exit(void)
 {
-	elv_unregister(&iosched_bfq);
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+	elv_unregister(&iosched_bfq_mq);
+#ifdef CONFIG_BFQ_GROUP_ENABLED
 	blkcg_policy_unregister(&blkcg_policy_bfq);
 #endif
 	bfq_slab_kill();
@@ -5422,5 +5484,6 @@ static void __exit bfq_exit(void)
 module_init(bfq_init);
 module_exit(bfq_exit);
 
-MODULE_AUTHOR("Arianna Avanzini, Fabio Checconi, Paolo Valente");
+MODULE_AUTHOR("Paolo Valente");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MQ Budget Fair Queueing I/O Scheduler");
diff --git a/block/bfq-mq.h b/block/bfq-mq.h
index 0f51f270469c..c3fcd5ebd735 100644
--- a/block/bfq-mq.h
+++ b/block/bfq-mq.h
@@ -19,15 +19,8 @@
 #include <linux/hrtimer.h>
 #include <linux/blk-cgroup.h>
 
-/*
- * Define an alternative macro to compile cgroups support. This is one
- * of the steps needed to let bfq-mq share the files bfq-sched.c and
- * bfq-cgroup.c with bfq-sq. For bfq-mq, the macro
- * BFQ_GROUP_IOSCHED_ENABLED will be defined as a function of whether
- * the configuration option CONFIG_BFQ_MQ_GROUP_IOSCHED, and not
- * CONFIG_BFQ_GROUP_IOSCHED, is defined.
- */
-#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED
+/* see comments on CONFIG_BFQ_GROUP_IOSCHED in bfq.h */
+#ifdef CONFIG_BFQ_MQ_GROUP_IOSCHED
 #define BFQ_GROUP_IOSCHED_ENABLED
 #endif
 
@@ -259,8 +252,8 @@ struct bfq_queue {
 	struct request *next_rq;
 	/* number of sync and async requests queued */
 	int queued[2];
-	/* number of sync and async requests currently allocated */
-	int allocated[2];
+	/* number of requests currently allocated */
+	int allocated;
 	/* number of pending metadata requests */
 	int meta_pending;
 	/* fifo list of requests in sort_list */
@@ -345,6 +338,8 @@ struct bfq_queue {
 	unsigned long wr_start_at_switch_to_srt;
 
 	unsigned long split_time; /* time of last split */
+
+	spinlock_t lock;
 };
 
 /**
@@ -361,6 +356,9 @@ struct bfq_io_cq {
 	uint64_t blkcg_serial_nr; /* the current blkcg serial */
 #endif
 
+	/* delayed work to exec the body of the the exit_icq handler */
+	struct work_struct exit_icq_work;
+
 	/*
 	 * Snapshot of the has_short_time flag before merging; taken
 	 * to remember its value while the queue is merged, so as to
@@ -402,11 +400,13 @@ enum bfq_device_speed {
 /**
  * struct bfq_data - per-device data structure.
  *
- * All the fields are protected by the @queue lock.
+ * All the fields are protected by @lock.
  */
 struct bfq_data {
-	/* request queue for the device */
+	/* device request queue */
 	struct request_queue *queue;
+	/* dispatch queue */
+	struct list_head dispatch;
 
 	/* root bfq_group for the device */
 	struct bfq_group *root_group;
@@ -460,8 +460,6 @@ struct bfq_data {
 	 * the queue in service.
 	 */
 	struct hrtimer idle_slice_timer;
-	/* delayed work to restart dispatching on the request queue */
-	struct work_struct unplug_work;
 
 	/* bfq_queue in service */
 	struct bfq_queue *in_service_queue;
@@ -612,6 +610,8 @@ struct bfq_data {
 
 	/* fallback dummy bfqq for extreme OOM conditions */
 	struct bfq_queue oom_bfqq;
+
+	spinlock_t lock;
 };
 
 enum bfqq_state_flags {
@@ -622,7 +622,6 @@ enum bfqq_state_flags {
 					     * waiting for a request
 					     * without idling the device
 					     */
-	BFQ_BFQQ_FLAG_must_alloc,	/* must be allowed rq alloc */
 	BFQ_BFQQ_FLAG_fifo_expire,	/* FIFO checked in this slice */
 	BFQ_BFQQ_FLAG_has_short_ttime,	/* queue has a short think time */
 	BFQ_BFQQ_FLAG_sync,		/* synchronous queue */
@@ -661,7 +660,6 @@ BFQ_BFQQ_FNS(just_created);
 BFQ_BFQQ_FNS(busy);
 BFQ_BFQQ_FNS(wait_request);
 BFQ_BFQQ_FNS(non_blocking_wait_rq);
-BFQ_BFQQ_FNS(must_alloc);
 BFQ_BFQQ_FNS(fifo_expire);
 BFQ_BFQQ_FNS(has_short_ttime);
 BFQ_BFQQ_FNS(sync);
@@ -692,7 +690,6 @@ static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	do {			\
 	char __pbuf[128];						\
 									\
-	assert_spin_locked((bfqd)->queue->queue_lock);			\
 	blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
 	pr_crit("%s bfq%d%c %s " fmt "\n", 				\
 		checked_dev_name((bfqd)->queue->backing_dev_info->dev),	\
@@ -734,7 +731,6 @@ static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	do {			\
 	char __pbuf[128];						\
 									\
-	assert_spin_locked((bfqd)->queue->queue_lock);			\
 	blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
 	blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, \
 			  (bfqq)->pid,			  \
@@ -961,7 +957,6 @@ static struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
 
 static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio);
 static void bfq_put_queue(struct bfq_queue *bfqq);
-static void bfq_dispatch_insert(struct request_queue *q, struct request *rq);
 static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
 				       struct bio *bio, bool is_sync,
 				       struct bfq_io_cq *bic);

From bde5235de2241502c1c00337bd51c96d9b60b6df Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Fri, 3 Mar 2017 08:52:40 +0100
Subject: [PATCH 13/51] Add checks and extra log messages - Part I

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c | 112 +++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 109 insertions(+), 3 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index c963d92a32c2..40eadb3f7073 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -773,6 +773,8 @@ static int bfqq_process_refs(struct bfq_queue *bfqq)
 {
 	int process_refs, io_refs;
 
+	lockdep_assert_held(&bfqq->bfqd->lock);
+
 	io_refs = bfqq->allocated;
 	process_refs = bfqq->ref - io_refs - bfqq->entity.on_st;
 	BUG_ON(process_refs < 0);
@@ -1483,6 +1485,8 @@ static void bfq_add_request(struct request *rq)
 	bfqq->queued[rq_is_sync(rq)]++;
 	bfqd->queued++;
 
+	BUG_ON(!RQ_BFQQ(rq));
+	BUG_ON(RQ_BFQQ(rq) != bfqq);
 	elv_rb_add(&bfqq->sort_list, rq);
 
 	/*
@@ -1491,6 +1495,8 @@ static void bfq_add_request(struct request *rq)
 	prev = bfqq->next_rq;
 	next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position);
 	BUG_ON(!next_rq);
+	BUG_ON(!RQ_BFQQ(next_rq));
+	BUG_ON(RQ_BFQQ(next_rq) != bfqq);
 	bfqq->next_rq = next_rq;
 
 	/*
@@ -1615,6 +1621,19 @@ static void bfq_remove_request(struct request_queue *q,
 
 	if (bfqq->next_rq == rq) {
 		bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq);
+		if (bfqq->next_rq && !RQ_BFQQ(bfqq->next_rq)) {
+			pr_crit("no bfqq! for next rq %p bfqq %p\n",
+				bfqq->next_rq, bfqq);
+		}
+
+		BUG_ON(bfqq->next_rq && !RQ_BFQQ(bfqq->next_rq));
+		if (bfqq->next_rq && RQ_BFQQ(bfqq->next_rq) != bfqq) {
+			pr_crit(
+			"wrong bfqq! for next rq %p, rq_bfqq %p bfqq %p\n",
+			bfqq->next_rq, RQ_BFQQ(bfqq->next_rq), bfqq);
+		}
+		BUG_ON(bfqq->next_rq && RQ_BFQQ(bfqq->next_rq) != bfqq);
+
 		bfq_updated_next_req(bfqd, bfqq);
 	}
 
@@ -1701,6 +1720,8 @@ static int bfq_request_merge(struct request_queue *q, struct request **req,
 	__rq = bfq_find_rq_fmerge(bfqd, bio, q);
 	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
+		bfq_log(bfqd, "request_merge: req %p", __rq);
+
 		return ELEVATOR_FRONT_MERGE;
 	}
 
@@ -1721,6 +1742,8 @@ static void bfq_request_merged(struct request_queue *q, struct request *req,
 
 		/* Reposition request in its sort_list */
 		elv_rb_del(&bfqq->sort_list, req);
+		BUG_ON(!RQ_BFQQ(req));
+		BUG_ON(RQ_BFQQ(req) != bfqq);
 		elv_rb_add(&bfqq->sort_list, req);
 
 		spin_lock_irq(&bfqd->lock);
@@ -1729,7 +1752,13 @@ static void bfq_request_merged(struct request_queue *q, struct request *req,
 		next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req,
 					 bfqd->last_position);
 		BUG_ON(!next_rq);
+
 		bfqq->next_rq = next_rq;
+
+		bfq_log_bfqq(bfqd, bfqq,
+			"requests_merged: req %p prev %p next_rq %p bfqq %p",
+			     req, prev, next_rq, bfqq);
+
 		/*
 		 * If next_rq changes, update both the queue's budget to
 		 * fit the new request and the queue's position in its
@@ -1748,8 +1777,16 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
 {
 	struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next);
 
+	BUG_ON(!RQ_BFQQ(rq));
+	BUG_ON(!RQ_BFQQ(next));
+
 	if (!RB_EMPTY_NODE(&rq->rb_node))
 		goto end;
+
+	bfq_log_bfqq(bfqq->bfqd, bfqq,
+		     "requests_merged: rq %p next %p bfqq %p next_bfqq %p",
+		     rq, next, bfqq, next_bfqq);
+
 	spin_lock_irq(&bfqq->bfqd->lock);
 
 	/*
@@ -3847,6 +3884,9 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
 {
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 
+	bfq_log(bfqd, "has_work, dispatch_non_empty %d busy_queues %d",
+		!list_empty_careful(&bfqd->dispatch), bfqd->busy_queues > 0);
+
 	/*
 	 * Avoiding lock: a race on bfqd->busy_queues should cause at
 	 * most a call to dispatch for nothing
@@ -3865,6 +3905,8 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 		rq = list_first_entry(&bfqd->dispatch, struct request,
 				      queuelist);
 		list_del_init(&rq->queuelist);
+		bfq_log(bfqd,
+			"dispatch requests: picked %p from dispatch list", rq);
 		goto exit;
 	}
 
@@ -3904,7 +3946,20 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	if (rq) {
 		rq->rq_flags |= RQF_STARTED;
 		bfqd->rq_in_driver++;
-	}
+		if (bfqq)
+			bfq_log_bfqq(bfqd, bfqq,
+				"dispatched %s request %p, rq_in_driver %d",
+				     bfq_bfqq_sync(bfqq) ? "sync" : "async",
+				     rq,
+				     bfqd->rq_in_driver);
+		else
+			bfq_log(bfqd,
+		"dispatched request %p from dispatch list, rq_in_driver %d",
+				rq, bfqd->rq_in_driver);
+	} else
+		bfq_log(bfqd,
+		"returned NULL request, rq_in_driver %d",
+			bfqd->rq_in_driver);
 
 	return rq;
 }
@@ -3944,6 +3999,7 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
 		return;
 
 	BUG_ON(rb_first(&bfqq->sort_list));
+	BUG_ON(bfqq->allocated != 0);
 	BUG_ON(bfqq->entity.tree);
 	BUG_ON(bfq_bfqq_busy(bfqq));
 
@@ -4043,6 +4099,7 @@ static void bfq_exit_icq(struct io_cq *icq)
 {
 	struct bfq_io_cq *bic = icq_to_bic(icq);
 
+	BUG_ON(!bic);
 	kblockd_schedule_work(&bic->exit_icq_work);
 }
 
@@ -4057,6 +4114,7 @@ static void bfq_set_next_ioprio_data(struct bfq_queue *bfqq,
 	int ioprio_class;
 	struct bfq_data *bfqd = bfqq->bfqd;
 
+	WARN_ON(!bfqd);
 	if (!bfqd)
 		return;
 
@@ -4404,6 +4462,10 @@ static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 {
 	struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq;
 
+	assert_spin_locked(&bfqd->lock);
+
+	bfq_log_bfqq(bfqd, bfqq, "__insert_req: rq %p bfqq %p", rq, bfqq);
+
 	/*
 	 * An unplug may trigger a requeue of a request from the device
 	 * driver: make sure we are in process context while trying to
@@ -4420,6 +4482,12 @@ static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 			 */
 			new_bfqq->allocated++;
 			bfqq->allocated--;
+			bfq_log_bfqq(bfqd, bfqq,
+		     "insert_request: new allocated %d", bfqq->allocated);
+			bfq_log_bfqq(bfqd, new_bfqq,
+		     "insert_request: new_bfqq new allocated %d",
+				     bfqq->allocated);
+
 			new_bfqq->ref++;
 			bfq_clear_bfqq_just_created(bfqq);
 			if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
@@ -4529,6 +4597,10 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 	bfqd->rq_in_driver--;
 	bfqq->dispatched--;
 
+	bfq_log_bfqq(bfqd, bfqq,
+		     "completed_requests: new disp %d, new rq_in_driver %d",
+		     bfqq->dispatched, bfqd->rq_in_driver);
+
 	if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) {
 		BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
 		/*
@@ -4618,6 +4690,9 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 
 static void bfq_put_rq_priv_body(struct bfq_queue *bfqq)
 {
+	bfq_log_bfqq(bfqq->bfqd, bfqq,
+		     "put_request_body: allocated %d", bfqq->allocated);
+	BUG_ON(!bfqq->allocated);
 	bfqq->allocated--;
 
 	bfq_put_queue(bfqq);
@@ -4625,8 +4700,27 @@ static void bfq_put_rq_priv_body(struct bfq_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;
+	struct bfq_queue *bfqq;
+	struct bfq_data *bfqd;
+	struct bfq_io_cq *bic;
+
+	BUG_ON(!rq);
+	bfqq = RQ_BFQQ(rq);
+	BUG_ON(!bfqq);
+
+	bic = RQ_BIC(rq);
+	BUG_ON(!bic);
+
+	bfqd = bfqq->bfqd;
+	BUG_ON(!bfqd);
+
+	BUG_ON(rq->rq_flags & RQF_QUEUED);
+	BUG_ON(!(rq->rq_flags & RQF_ELVPRIV));
+
+	bfq_log_bfqq(bfqd, bfqq,
+		     "putting rq %p with %u sects left, STARTED %d",
+		     rq, blk_rq_sectors(rq),
+		     rq->rq_flags & RQF_STARTED);
 
 	if (rq->rq_flags & RQF_STARTED)
 		bfqg_stats_update_completion(bfqq_group(bfqq),
@@ -4634,6 +4728,8 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
 					     rq_io_start_time_ns(rq),
 					     rq->cmd_flags);
 
+	BUG_ON(blk_rq_sectors(rq) == 0 && !(rq->rq_flags & RQF_STARTED));
+
 	if (likely(rq->rq_flags & RQF_STARTED)) {
 		unsigned long flags;
 
@@ -4655,7 +4751,9 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
 		 * cause any deadlock, even if other locks are already
 		 * (correctly) held by this process.
 		 */
+		BUG_ON(in_interrupt());
 
+		assert_spin_locked(&bfqd->lock);
 		if (!RB_EMPTY_NODE(&rq->rb_node))
 			bfq_remove_request(q, rq);
 		bfq_put_rq_priv_body(bfqq);
@@ -4814,7 +4912,9 @@ static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
 	enum bfqq_expiration reason;
 	unsigned long flags;
 
+	BUG_ON(!bfqd);
 	spin_lock_irqsave(&bfqd->lock, flags);
+	bfq_log_bfqq(bfqd, bfqq, "handling slice_timer expiration");
 	bfq_clear_bfqq_wait_request(bfqq);
 
 	if (bfqq != bfqd->in_service_queue) {
@@ -4857,6 +4957,8 @@ static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer)
 					     idle_slice_timer);
 	struct bfq_queue *bfqq = bfqd->in_service_queue;
 
+	bfq_log(bfqd, "slice_timer expired");
+
 	/*
 	 * Theoretical race here: the in-service queue can be NULL or
 	 * different from the queue that was idling if a new request
@@ -4909,9 +5011,12 @@ static void bfq_exit_queue(struct elevator_queue *e)
 	struct bfq_data *bfqd = e->elevator_data;
 	struct bfq_queue *bfqq, *n;
 
+	bfq_log(bfqd, "exit_queue: starting ...");
+
 	hrtimer_cancel(&bfqd->idle_slice_timer);
 
 	BUG_ON(bfqd->in_service_queue);
+	BUG_ON(!list_empty(&bfqd->active_list));
 
 	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list) {
 		if (bfqq->bic) /* bfqqs without bic are handled below */
@@ -4943,6 +5048,7 @@ static void bfq_exit_queue(struct elevator_queue *e)
 	spin_unlock_irq(&bfqd->lock);
 #endif
 
+	bfq_log(bfqd, "exit_queue: finished ...");
 	kfree(bfqd);
 }
 

From 7f59486861e368d25f59d4136cf8e51a75b7edf9 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Thu, 9 Feb 2017 10:36:27 +0100
Subject: [PATCH 14/51] Add lock check in bfq_allow_bio_merge

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 40eadb3f7073..21b876aeba16 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -2279,6 +2279,7 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
 	if (!bic)
 		return false;
 
+	assert_spin_locked(&bfqd->lock);
 	bfqq = bic_to_bfqq(bic, is_sync);
 	/*
 	 * We take advantage of this function to perform an early merge

From a2dd19a4d95cf401268c144c79ce549c7fc4bbca Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Tue, 7 Feb 2017 15:14:29 +0100
Subject: [PATCH 15/51] bfq-mq: execute exit_icq operations immediately

Exploting Omar's patch that removes the taking of the queue lock in
put_io_context_active, this patch moves back the operation of the bfq_exit_icq
hook from a deferred work to the body of the function.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c | 34 +++-------------------------------
 block/bfq-mq.h         |  3 ---
 2 files changed, 3 insertions(+), 34 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 21b876aeba16..1deb79a47181 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -4080,28 +4080,13 @@ static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
 	}
 }
 
-static void bfq_exit_icq_body(struct work_struct *work)
-{
-	struct bfq_io_cq *bic =
-		container_of(work, struct bfq_io_cq, exit_icq_work);
-
-	bfq_exit_icq_bfqq(bic, true);
-	bfq_exit_icq_bfqq(bic, false);
-}
-
-static void bfq_init_icq(struct io_cq *icq)
-{
-	struct bfq_io_cq *bic = icq_to_bic(icq);
-
-	INIT_WORK(&bic->exit_icq_work, bfq_exit_icq_body);
-}
-
 static void bfq_exit_icq(struct io_cq *icq)
 {
 	struct bfq_io_cq *bic = icq_to_bic(icq);
 
 	BUG_ON(!bic);
-	kblockd_schedule_work(&bic->exit_icq_work);
+	bfq_exit_icq_bfqq(bic, true);
+	bfq_exit_icq_bfqq(bic, false);
 }
 
 /*
@@ -5019,21 +5004,9 @@ static void bfq_exit_queue(struct elevator_queue *e)
 	BUG_ON(bfqd->in_service_queue);
 	BUG_ON(!list_empty(&bfqd->active_list));
 
-	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list) {
-		if (bfqq->bic) /* bfqqs without bic are handled below */
-			cancel_work_sync(&bfqq->bic->exit_icq_work);
-	}
-
 	spin_lock_irq(&bfqd->lock);
-	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list) {
+	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
 		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
-		/*
-		 * Make sure that deferred exit_icq_work completes
-		 * without errors for bfq_queues without bic
-		 */
-		if (!bfqq->bic)
-			bfqq->bfqd = NULL;
-	}
 	spin_unlock_irq(&bfqd->lock);
 
 	hrtimer_cancel(&bfqd->idle_slice_timer);
@@ -5471,7 +5444,6 @@ static struct elevator_type iosched_bfq_mq = {
 	.ops.mq = {
 		.get_rq_priv		= bfq_get_rq_private,
 		.put_rq_priv		= bfq_put_rq_private,
-		.init_icq		= bfq_init_icq,
 		.exit_icq		= bfq_exit_icq,
 		.insert_requests	= bfq_insert_requests,
 		.dispatch_request	= bfq_dispatch_request,
diff --git a/block/bfq-mq.h b/block/bfq-mq.h
index c3fcd5ebd735..23744b246db6 100644
--- a/block/bfq-mq.h
+++ b/block/bfq-mq.h
@@ -356,9 +356,6 @@ struct bfq_io_cq {
 	uint64_t blkcg_serial_nr; /* the current blkcg serial */
 #endif
 
-	/* delayed work to exec the body of the the exit_icq handler */
-	struct work_struct exit_icq_work;
-
 	/*
 	 * Snapshot of the has_short_time flag before merging; taken
 	 * to remember its value while the queue is merged, so as to

From ab7e78a0ff095101de74e700f8743295a500bb20 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Tue, 21 Feb 2017 10:26:22 +0100
Subject: [PATCH 16/51] Unnest request-queue and ioc locks from scheduler locks

In some bio-merging functions, the request-queue lock needs to be
taken, to lookup for the bic associated with the process that issued
the bio that may need to be merged. In addition, put_io_context must
be invoked in some other functions, and put_io_context may cause the
lock of the involved ioc to be taken. In both cases, these extra
request-queue or ioc locks are taken, or might be taken, while the
scheduler lock is being held. In this respect, there are other code
paths, in part external to bfq-mq, in which the same locks are taken
(nested) in the opposite order, i.e., it is the scheduler lock to be
taken while the request-queue or the ioc lock is being held.  This
leads to circular deadlocks.

This commit addresses this issue by modifying the logic of the above
functions, so as to let the lookup and put_io_context be performed,
and thus the extra locks be taken, outside the critical sections
protected by the scheduler lock.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-cgroup-included.c |   9 ++
 block/bfq-mq-iosched.c      | 264 ++++++++++++++++++++++++++++----------------
 block/bfq-mq.h              |  25 ++++-
 block/bfq-sched.c           |  11 ++
 4 files changed, 213 insertions(+), 96 deletions(-)

diff --git a/block/bfq-cgroup-included.c b/block/bfq-cgroup-included.c
index 8a73de76f32b..cf59eeb7f08e 100644
--- a/block/bfq-cgroup-included.c
+++ b/block/bfq-cgroup-included.c
@@ -716,6 +716,9 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 	struct bfq_group *bfqg;
 	struct bfq_data *bfqd;
 	struct bfq_entity *entity;
+#ifdef BFQ_MQ
+	unsigned long flags;
+#endif
 	int i;
 
 	BUG_ON(!pd);
@@ -729,6 +732,9 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 	if (!entity) /* root group */
 		return;
 
+#ifdef BFQ_MQ
+	spin_lock_irqsave(&bfqd->lock, flags);
+#endif
 	/*
 	 * Empty all service_trees belonging to this group before
 	 * deactivating the group itself.
@@ -766,6 +772,9 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 	__bfq_deactivate_entity(entity, false);
 	bfq_put_async_queues(bfqd, bfqg);
 
+#ifdef BFQ_MQ
+	bfq_unlock_put_ioc_restore(bfqd, flags);
+#endif
 	/*
 	 * @blkg is going offline and will be ignored by
 	 * blkg_[rw]stat_recursive_sum().  Transfer stats to the parent so
diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 1deb79a47181..69ef3761c95d 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -233,6 +233,7 @@ static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
 	return NULL;
 }
 
+#define BFQ_MQ
 #include "bfq-sched.c"
 #include "bfq-cgroup-included.c"
 
@@ -1564,15 +1565,9 @@ static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
 					  struct bio *bio,
 					  struct request_queue *q)
 {
-	struct task_struct *tsk = current;
-	struct bfq_io_cq *bic;
-	struct bfq_queue *bfqq;
+	struct bfq_queue *bfqq = bfqd->bio_bfqq;
 
-	bic = bfq_bic_lookup(bfqd, tsk->io_context, q);
-	if (!bic)
-		return NULL;
 
-	bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf));
 	if (bfqq)
 		return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio));
 
@@ -1693,9 +1688,26 @@ 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;
+	/* Set next flag just for testing purposes */
+	bfqd->bio_bfqq_set = true;
+
 	ret = blk_mq_sched_try_merge(q, bio, &free);
 
 	/*
@@ -1706,6 +1718,7 @@ static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
 	 */
 	if (free)
 		blk_mq_free_request(free);
+	bfqd->bio_bfqq_set = false;
 	spin_unlock_irq(&bfqd->lock);
 
 	return ret;
@@ -2261,8 +2274,7 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
 {
 	struct bfq_data *bfqd = q->elevator->elevator_data;
 	bool is_sync = op_is_sync(bio->bi_opf);
-	struct bfq_io_cq *bic;
-	struct bfq_queue *bfqq, *new_bfqq;
+	struct bfq_queue *bfqq = bfqd->bio_bfqq, *new_bfqq;
 
 	/*
 	 * Disallow merge of a sync bio into an async request.
@@ -2273,31 +2285,40 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
 	/*
 	 * Lookup the bfqq that this bio will be queued with. Allow
 	 * merge only if rq is queued there.
-	 * Queue lock is held here.
 	 */
-	bic = bfq_bic_lookup(bfqd, current->io_context, q);
-	if (!bic)
+	if (!bfqq)
 		return false;
 
-	assert_spin_locked(&bfqd->lock);
-	bfqq = bic_to_bfqq(bic, is_sync);
 	/*
 	 * We take advantage of this function to perform an early merge
 	 * of the queues of possible cooperating processes.
 	 */
-	if (bfqq) {
-		new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
-		if (new_bfqq) {
-			bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq);
-			/*
-			 * If we get here, the bio will be queued in the
-			 * shared queue, i.e., new_bfqq, so use new_bfqq
-			 * to decide whether bio and rq can be merged.
-			 */
-			bfqq = new_bfqq;
-		}
-	}
+	new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
+	if (new_bfqq) {
+		/*
+		 * bic still points to bfqq, then it has not yet been
+		 * redirected to some other bfq_queue, and a queue
+		 * merge beween bfqq and new_bfqq can be safely
+		 * fulfillled, i.e., bic can be redirected to new_bfqq
+		 * and bfqq can be put.
+		 */
+		bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq,
+				new_bfqq);
+		/*
+		 * If we get here, bio will be queued into new_queue,
+		 * so use new_bfqq to decide whether bio and rq can be
+		 * merged.
+		 */
+		bfqq = new_bfqq;
 
+		/*
+		 * Change also bqfd->bio_bfqq, as
+		 * bfqd->bio_bic now points to new_bfqq, and
+		 * this function may be invoked again (and then may
+		 * use again bqfd->bio_bfqq).
+		 */
+		bfqd->bio_bfqq = bfqq;
+	}
 	return bfqq == RQ_BFQQ(rq);
 }
 
@@ -3965,14 +3986,43 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	return rq;
 }
 
+/*
+ * Next two functions release bfqd->lock and put the io context
+ * pointed by bfqd->ioc_to_put. This delayed put is used to not risk
+ * to take an ioc->lock while the scheduler lock is being held.
+ */
+static void bfq_unlock_put_ioc(struct bfq_data *bfqd)
+{
+	struct io_context *ioc_to_put = bfqd->ioc_to_put;
+
+	bfqd->ioc_to_put = NULL;
+	spin_unlock_irq(&bfqd->lock);
+
+	if (ioc_to_put)
+		put_io_context(ioc_to_put);
+}
+
+static void bfq_unlock_put_ioc_restore(struct bfq_data *bfqd,
+				       unsigned long flags)
+{
+	struct io_context *ioc_to_put = bfqd->ioc_to_put;
+
+	bfqd->ioc_to_put = NULL;
+	spin_unlock_irqrestore(&bfqd->lock, flags);
+
+	if (ioc_to_put)
+		put_io_context(ioc_to_put);
+}
+
 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);
+	bfq_unlock_put_ioc(bfqd);
 
 	return rq;
 }
@@ -3981,7 +4031,7 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
  * 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.
  *
- * Queue lock must be held here. Recall not to use bfqq after calling
+ * 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)
@@ -4066,17 +4116,23 @@ static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
 		bfqd = bfqq->bfqd; /* NULL if scheduler already exited */
 
 	if (bfqq && bfqd) {
-		spin_lock_irq(&bfqd->lock);
+		unsigned long flags;
+
+		spin_lock_irqsave(&bfqd->lock, flags);
 		/*
-		 * If the bic is using a shared queue, put the reference
-		 * taken on the io_context when the bic started using a
-		 * shared bfq_queue.
+		 * If the bic is using a shared queue, put the
+		 * reference taken on the io_context when the bic
+		 * started using a shared bfq_queue. This put cannot
+		 * make ioc->ref_count reach 0, then no ioc->lock
+		 * risks to be taken (leading to possible deadlock
+		 * scenarios).
 		 */
 		if (is_sync && bfq_bfqq_coop(bfqq))
 			put_io_context(bic->icq.ioc);
+
 		bfq_exit_bfqq(bfqd, bfqq);
 		bic_set_bfqq(bic, NULL, is_sync);
-		spin_unlock_irq(&bfqd->lock);
+		bfq_unlock_put_ioc_restore(bfqd, flags);
 	}
 }
 
@@ -4183,8 +4239,6 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	INIT_HLIST_NODE(&bfqq->burst_list_node);
 	BUG_ON(!hlist_unhashed(&bfqq->burst_list_node));
 
-	spin_lock_init(&bfqq->lock);
-
 	bfqq->ref = 0;
 	bfqq->bfqd = bfqd;
 
@@ -4476,6 +4530,14 @@ static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 
 			new_bfqq->ref++;
 			bfq_clear_bfqq_just_created(bfqq);
+			/*
+			 * If the bic associated with the process
+			 * issuing this request still points to bfqq
+			 * (and thus has not been already redirected
+			 * to new_bfqq or even some other bfq_queue),
+			 * then complete the merge and redirect it to
+			 * new_bfqq.
+			 */
 			if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
 				bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
 						bfqq, new_bfqq);
@@ -4498,14 +4560,17 @@ static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 }
 
 static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
-			      bool at_head)
+			       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))
-		goto done;
+	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);
@@ -4530,8 +4595,8 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 				q->last_merge = rq;
 		}
 	}
-done:
-	spin_unlock_irq(&bfqd->lock);
+
+	bfq_unlock_put_ioc(bfqd);
 }
 
 static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
@@ -4724,7 +4789,7 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
 		bfq_completed_request(bfqq, bfqd);
 		bfq_put_rq_priv_body(bfqq);
 
-		spin_unlock_irqrestore(&bfqd->lock, flags);
+		bfq_unlock_put_ioc_restore(bfqd, flags);
 	} else {
 		/*
 		 * Request rq may be still/already in the scheduler,
@@ -4732,10 +4797,10 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
 		 * 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.
-		 * Fortunately, this situation occurs only in process
-		 * context, so taking the scheduler lock does not
-		 * cause any deadlock, even if other locks are already
-		 * (correctly) held by this process.
+		 * 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.
 		 */
 		BUG_ON(in_interrupt());
 
@@ -4758,8 +4823,6 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
 {
 	bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");
 
-	put_io_context(bic->icq.ioc);
-
 	if (bfqq_process_refs(bfqq) == 1) {
 		bfqq->pid = current->pid;
 		bfq_clear_bfqq_coop(bfqq);
@@ -4775,6 +4838,41 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
 	return NULL;
 }
 
+static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
+						   struct bfq_io_cq *bic,
+						   struct bio *bio,
+						   bool split, bool is_sync,
+						   bool *new_queue)
+{
+	struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);
+
+	if (likely(bfqq && bfqq != &bfqd->oom_bfqq))
+		return bfqq;
+
+	if (new_queue)
+		*new_queue = true;
+
+	if (bfqq)
+		bfq_put_queue(bfqq);
+	bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);
+
+	bic_set_bfqq(bic, bfqq, is_sync);
+	if (split && is_sync) {
+		if ((bic->was_in_burst_list && bfqd->large_burst) ||
+		    bic->saved_in_large_burst)
+			bfq_mark_bfqq_in_large_burst(bfqq);
+		else {
+			bfq_clear_bfqq_in_large_burst(bfqq);
+			if (bic->was_in_burst_list)
+				hlist_add_head(&bfqq->burst_list_node,
+					       &bfqd->burst_list);
+		}
+		bfqq->split_time = jiffies;
+	}
+
+	return bfqq;
+}
+
 /*
  * Allocate bfq data structures associated with this request.
  */
@@ -4786,6 +4884,7 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 	const int is_sync = rq_is_sync(rq);
 	struct bfq_queue *bfqq;
 	bool bfqq_already_existing = false, split = false;
+	bool new_queue = false;
 
 	spin_lock_irq(&bfqd->lock);
 
@@ -4796,42 +4895,10 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 
 	bfq_bic_update_cgroup(bic, bio);
 
-new_queue:
-	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);
-		BUG_ON(!hlist_unhashed(&bfqq->burst_list_node));
+	bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync,
+					 &new_queue);
 
-		bic_set_bfqq(bic, bfqq, is_sync);
-		if (split && is_sync) {
-			bfq_log_bfqq(bfqd, bfqq,
-				     "get_request: was_in_list %d "
-				     "was_in_large_burst %d "
-				     "large burst in progress %d",
-				     bic->was_in_burst_list,
-				     bic->saved_in_large_burst,
-				     bfqd->large_burst);
-
-			if ((bic->was_in_burst_list && bfqd->large_burst) ||
-			    bic->saved_in_large_burst) {
-				bfq_log_bfqq(bfqd, bfqq,
-					     "get_request: marking in "
-					     "large burst");
-				bfq_mark_bfqq_in_large_burst(bfqq);
-			} else {
-				bfq_log_bfqq(bfqd, bfqq,
-					     "get_request: clearing in "
-					     "large burst");
-				bfq_clear_bfqq_in_large_burst(bfqq);
-				if (bic->was_in_burst_list)
-					hlist_add_head(&bfqq->burst_list_node,
-						       &bfqd->burst_list);
-			}
-			bfqq->split_time = jiffies;
-		}
-	} else {
+	if (unlikely(!new_queue)) {
 		/* If the queue was seeky for too long, break it apart. */
 		if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
 			bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
@@ -4841,9 +4908,19 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 				bic->saved_in_large_burst = true;
 
 			bfqq = bfq_split_bfqq(bic, bfqq);
-			split = true;
+			/*
+			 * A reference to bic->icq.ioc needs to be
+			 * released after a queue split. Do not do it
+			 * immediately, to not risk to possibly take
+			 * an ioc->lock while holding the scheduler
+			 * lock.
+			 */
+			bfqd->ioc_to_put = bic->icq.ioc;
+
 			if (!bfqq)
-				goto new_queue;
+				bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,
+								 true, is_sync,
+								 NULL);
 			else
 				bfqq_already_existing = true;
 		}
@@ -4861,18 +4938,17 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 
 	/*
 	 * If a bfq_queue has only one process reference, it is owned
-	 * by only one bfq_io_cq: we can set the bic field of the
-	 * bfq_queue to the address of that structure. Also, if the
-	 * queue has just been split, mark a flag so that the
-	 * information is available to the other scheduler hooks.
+	 * by only this bic: we can then set bfqq->bic = bic. in
+	 * addition, if the queue has also just been split, we have to
+	 * resume its state.
 	 */
 	if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) {
 		bfqq->bic = bic;
-		if (split) {
+		if (bfqd->ioc_to_put) { /* if true, then there has been a split */
 			/*
-			 * If the queue has just been split from a shared
-			 * queue, restore the idle window and the possible
-			 * weight raising period.
+			 * The queue has just been split from a shared
+			 * queue: restore the idle window and the
+			 * possible weight raising period.
 			 */
 			bfq_bfqq_resume_state(bfqq, bfqd, bic,
 					      bfqq_already_existing);
@@ -4882,7 +4958,7 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 	if (unlikely(bfq_bfqq_just_created(bfqq)))
 		bfq_handle_burst(bfqd, bfqq);
 
-	spin_unlock_irq(&bfqd->lock);
+	bfq_unlock_put_ioc(bfqd);
 
 	return 0;
 
@@ -4929,7 +5005,7 @@ static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
 	bfq_bfqq_expire(bfqd, bfqq, true, reason);
 
 schedule_dispatch:
-	spin_unlock_irqrestore(&bfqd->lock, flags);
+	bfq_unlock_put_ioc_restore(bfqd, flags);
 	bfq_schedule_dispatch(bfqd);
 }
 
diff --git a/block/bfq-mq.h b/block/bfq-mq.h
index 23744b246db6..bd83f1c02573 100644
--- a/block/bfq-mq.h
+++ b/block/bfq-mq.h
@@ -338,8 +338,6 @@ struct bfq_queue {
 	unsigned long wr_start_at_switch_to_srt;
 
 	unsigned long split_time; /* time of last split */
-
-	spinlock_t lock;
 };
 
 /**
@@ -609,6 +607,29 @@ struct bfq_data {
 	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;
+	/* Extra flag used only for TESTING */
+	bool bio_bfqq_set;
+
+	/*
+	 * io context to put right after bfqd->lock is released. This
+	 * filed is used to perform put_io_context, when needed, to
+	 * after the scheduler lock has been released, and thus
+	 * prevent an ioc->lock from being possibly taken while the
+	 * scheduler lock is being held.
+	 */
+	struct io_context *ioc_to_put;
 };
 
 enum bfqq_state_flags {
diff --git a/block/bfq-sched.c b/block/bfq-sched.c
index b54a638186e3..a5c8b4acd33c 100644
--- a/block/bfq-sched.c
+++ b/block/bfq-sched.c
@@ -1905,7 +1905,18 @@ static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
 	struct bfq_entity *entity = in_serv_entity;
 
 	if (bfqd->in_service_bic) {
+#ifdef BFQ_MQ
+		/*
+		 * Schedule the release of a reference to
+		 * bfqd->in_service_bic->icq.ioc to right after the
+		 * scheduler lock is released. This ioc is not
+		 * released immediately, to not risk to possibly take
+		 * an ioc->lock while holding the scheduler lock.
+		 */
+		bfqd->ioc_to_put = bfqd->in_service_bic->icq.ioc;
+#else
 		put_io_context(bfqd->in_service_bic->icq.ioc);
+#endif
 		bfqd->in_service_bic = NULL;
 	}
 

From 84cc7140cb4f0574710625f51abbb076a1dd2920 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Fri, 3 Mar 2017 09:31:14 +0100
Subject: [PATCH 17/51] Add checks and extra log messages - Part II

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c | 42 ++++++++++++++++++++++++++++++++++++++++--
 block/bfq-sched.c      |  1 +
 2 files changed, 41 insertions(+), 2 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 69ef3761c95d..5707d42b160d 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -1567,6 +1567,7 @@ static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
 {
 	struct bfq_queue *bfqq = bfqd->bio_bfqq;
 
+	BUG_ON(!bfqd->bio_bfqq_set);
 
 	if (bfqq)
 		return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio));
@@ -1719,6 +1720,7 @@ static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
 	if (free)
 		blk_mq_free_request(free);
 	bfqd->bio_bfqq_set = false;
+	BUG_ON(bfqd->ioc_to_put);
 	spin_unlock_irq(&bfqd->lock);
 
 	return ret;
@@ -1781,6 +1783,7 @@ static void bfq_request_merged(struct request_queue *q, struct request *req,
 			bfq_updated_next_req(bfqd, bfqq);
 			bfq_pos_tree_add_move(bfqd, bfqq);
 		}
+		BUG_ON(bfqd->ioc_to_put);
 		spin_unlock_irq(&bfqd->lock);
 	}
 }
@@ -1824,6 +1827,7 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
 
 	bfq_remove_request(q, next);
 
+	BUG_ON(bfqq->bfqd->ioc_to_put);
 	spin_unlock_irq(&bfqq->bfqd->lock);
 end:
 	bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
@@ -2195,9 +2199,11 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 {
 	bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
 		     (unsigned long) new_bfqq->pid);
+	BUG_ON(bfqq->bic && bfqq->bic == new_bfqq->bic);
 	/* Save weight raising and idle window of the merged queues */
 	bfq_bfqq_save_state(bfqq);
 	bfq_bfqq_save_state(new_bfqq);
+
 	if (bfq_bfqq_IO_bound(bfqq))
 		bfq_mark_bfqq_IO_bound(new_bfqq);
 	bfq_clear_bfqq_IO_bound(bfqq);
@@ -2276,6 +2282,7 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
 	bool is_sync = op_is_sync(bio->bi_opf);
 	struct bfq_queue *bfqq = bfqd->bio_bfqq, *new_bfqq;
 
+	assert_spin_locked(&bfqd->lock);
 	/*
 	 * Disallow merge of a sync bio into an async request.
 	 */
@@ -2286,6 +2293,7 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
 	 * Lookup the bfqq that this bio will be queued with. Allow
 	 * merge only if rq is queued there.
 	 */
+	BUG_ON(!bfqd->bio_bfqq_set);
 	if (!bfqq)
 		return false;
 
@@ -2294,6 +2302,7 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
 	 * of the queues of possible cooperating processes.
 	 */
 	new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
+	BUG_ON(new_bfqq == bfqq);
 	if (new_bfqq) {
 		/*
 		 * bic still points to bfqq, then it has not yet been
@@ -4040,6 +4049,8 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
 	struct bfq_group *bfqg = bfqq_group(bfqq);
 #endif
 
+	assert_spin_locked(&bfqq->bfqd->lock);
+
 	BUG_ON(bfqq->ref <= 0);
 
 	if (bfqq->bfqd)
@@ -4119,6 +4130,7 @@ static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
 		unsigned long flags;
 
 		spin_lock_irqsave(&bfqd->lock, flags);
+		BUG_ON(bfqd->ioc_to_put);
 		/*
 		 * If the bic is using a shared queue, put the
 		 * reference taken on the io_context when the bic
@@ -4567,10 +4579,12 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	spin_lock_irq(&bfqd->lock);
 	if (blk_mq_sched_try_insert_merge(q, rq)) {
+		BUG_ON(bfqd->ioc_to_put);
 		spin_unlock_irq(&bfqd->lock);
 		return;
 	}
 
+	BUG_ON(bfqd->ioc_to_put);
 	spin_unlock_irq(&bfqd->lock);
 
 	blk_mq_sched_request_inserted(rq);
@@ -4785,6 +4799,7 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
 		unsigned long flags;
 
 		spin_lock_irqsave(&bfqd->lock, flags);
+		BUG_ON(bfqd->ioc_to_put);
 
 		bfq_completed_request(bfqq, bfqd);
 		bfq_put_rq_priv_body(bfqq);
@@ -4855,13 +4870,28 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
 	if (bfqq)
 		bfq_put_queue(bfqq);
 	bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);
+	BUG_ON(!hlist_unhashed(&bfqq->burst_list_node));
 
 	bic_set_bfqq(bic, bfqq, is_sync);
 	if (split && is_sync) {
+		bfq_log_bfqq(bfqd, bfqq,
+			     "get_request: was_in_list %d "
+			     "was_in_large_burst %d "
+			     "large burst in progress %d",
+			     bic->was_in_burst_list,
+			     bic->saved_in_large_burst,
+			     bfqd->large_burst);
+
 		if ((bic->was_in_burst_list && bfqd->large_burst) ||
-		    bic->saved_in_large_burst)
+		    bic->saved_in_large_burst) {
+			bfq_log_bfqq(bfqd, bfqq,
+				     "get_request: marking in "
+				     "large burst");
 			bfq_mark_bfqq_in_large_burst(bfqq);
-		else {
+		} else {
+			bfq_log_bfqq(bfqd, bfqq,
+				     "get_request: clearing in "
+				     "large burst");
 			bfq_clear_bfqq_in_large_burst(bfqq);
 			if (bic->was_in_burst_list)
 				hlist_add_head(&bfqq->burst_list_node,
@@ -4897,10 +4927,12 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 
 	bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync,
 					 &new_queue);
+	BUG_ON(bfqd->ioc_to_put);
 
 	if (unlikely(!new_queue)) {
 		/* If the queue was seeky for too long, break it apart. */
 		if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
+			BUG_ON(!is_sync);
 			bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
 
 			/* Update bic before losing reference to bfqq */
@@ -4923,6 +4955,9 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 								 NULL);
 			else
 				bfqq_already_existing = true;
+
+			BUG_ON(!bfqq);
+			BUG_ON(bfqq == &bfqd->oom_bfqq);
 		}
 	}
 
@@ -4976,6 +5011,8 @@ static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
 
 	BUG_ON(!bfqd);
 	spin_lock_irqsave(&bfqd->lock, flags);
+	BUG_ON(bfqd->ioc_to_put);
+
 	bfq_log_bfqq(bfqd, bfqq, "handling slice_timer expiration");
 	bfq_clear_bfqq_wait_request(bfqq);
 
@@ -5083,6 +5120,7 @@ static void bfq_exit_queue(struct elevator_queue *e)
 	spin_lock_irq(&bfqd->lock);
 	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
 		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
+	BUG_ON(bfqd->ioc_to_put);
 	spin_unlock_irq(&bfqd->lock);
 
 	hrtimer_cancel(&bfqd->idle_slice_timer);
diff --git a/block/bfq-sched.c b/block/bfq-sched.c
index a5c8b4acd33c..85e59eeb3569 100644
--- a/block/bfq-sched.c
+++ b/block/bfq-sched.c
@@ -1906,6 +1906,7 @@ static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
 
 	if (bfqd->in_service_bic) {
 #ifdef BFQ_MQ
+		BUG_ON(bfqd->ioc_to_put);
 		/*
 		 * Schedule the release of a reference to
 		 * bfqd->in_service_bic->icq.ioc to right after the

From 3d54cb804f1db2e08ce4a6cc335868538542f587 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Wed, 22 Feb 2017 11:30:01 +0100
Subject: [PATCH 18/51] Fix unbalanced increment of rq_in_driver

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c | 52 +++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 43 insertions(+), 9 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 5707d42b160d..9cbcb8d43d81 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -3936,9 +3936,45 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 		rq = list_first_entry(&bfqd->dispatch, struct request,
 				      queuelist);
 		list_del_init(&rq->queuelist);
+
 		bfq_log(bfqd,
 			"dispatch requests: picked %p from dispatch list", rq);
-		goto exit;
+		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);
@@ -3973,10 +4009,12 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 
 	BUG_ON(bfqq->next_rq == NULL &&
 	       bfqq->entity.budget < bfqq->entity.service);
-exit:
+
 	if (rq) {
-		rq->rq_flags |= RQF_STARTED;
+	inc_in_driver_start_rq:
 		bfqd->rq_in_driver++;
+	start_rq:
+		rq->rq_flags |= RQF_STARTED;
 		if (bfqq)
 			bfq_log_bfqq(bfqd, bfqq,
 				"dispatched %s request %p, rq_in_driver %d",
@@ -3992,6 +4030,7 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 		"returned NULL request, rq_in_driver %d",
 			bfqd->rq_in_driver);
 
+exit:
 	return rq;
 }
 
@@ -4591,15 +4630,10 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	spin_lock_irq(&bfqd->lock);
 	if (at_head || blk_rq_is_passthrough(rq)) {
-		struct bfq_queue *bfqq = RQ_BFQQ(rq);
-
 		if (at_head)
 			list_add(&rq->queuelist, &bfqd->dispatch);
 		else
 			list_add_tail(&rq->queuelist, &bfqd->dispatch);
-
-		if (bfqq)
-			bfqq->dispatched++;
 	} else {
 		__bfq_insert_request(bfqd, rq);
 
@@ -4966,7 +5000,7 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 		     "get_request: new allocated %d", bfqq->allocated);
 
 	bfqq->ref++;
-	bfq_log_bfqq(bfqd, bfqq, "get_request: bfqq %p, %d", bfqq, 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;

From 7ba977d696b239569b4cd233aebc99e136ecf487 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Fri, 3 Mar 2017 09:39:35 +0100
Subject: [PATCH 19/51] Add checks and extra log messages - Part III

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 9cbcb8d43d81..24b529a2edc7 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -4630,10 +4630,21 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	spin_lock_irq(&bfqd->lock);
 	if (at_head || blk_rq_is_passthrough(rq)) {
+		struct bfq_queue *bfqq = RQ_BFQQ(rq);
+
 		if (at_head)
 			list_add(&rq->queuelist, &bfqd->dispatch);
 		else
 			list_add_tail(&rq->queuelist, &bfqd->dispatch);
+
+		if (bfqq)
+			bfq_log_bfqq(bfqd, bfqq,
+				     "insert_request %p in disp: at_head %d",
+				     rq, at_head);
+		else
+			bfq_log(bfqd,
+				"insert_request %p in disp: at_head %d",
+				rq, at_head);
 	} else {
 		__bfq_insert_request(bfqd, rq);
 

From c94e47b2908600b8ba89f84b0ac7febddd313141 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Fri, 17 Feb 2017 14:28:02 +0100
Subject: [PATCH 20/51] TESTING: Check wrong invocation of merge and
 put_rq_priv functions

Check that merge functions are not invoked on requests queued in the
dispatch queue, and that neither put_rq_private is invoked on these
requests if, in addition, they have not passed through get_rq_private.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c | 22 ++++++++++++++++++++++
 include/linux/blkdev.h |  2 ++
 2 files changed, 24 insertions(+)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 24b529a2edc7..b4d40bb712d2 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -1746,6 +1746,8 @@ static int bfq_request_merge(struct request_queue *q, struct request **req,
 static void bfq_request_merged(struct request_queue *q, struct request *req,
 			       enum elv_merge type)
 {
+	BUG_ON(req->rq_flags & RQF_DISP_LIST);
+
 	if (type == ELEVATOR_FRONT_MERGE &&
 	    rb_prev(&req->rb_node) &&
 	    blk_rq_pos(req) <
@@ -1795,6 +1797,8 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
 
 	BUG_ON(!RQ_BFQQ(rq));
 	BUG_ON(!RQ_BFQQ(next));
+	BUG_ON(rq->rq_flags & RQF_DISP_LIST);
+	BUG_ON(next->rq_flags & RQF_DISP_LIST);
 
 	if (!RB_EMPTY_NODE(&rq->rb_node))
 		goto end;
@@ -3936,6 +3940,7 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 		rq = list_first_entry(&bfqd->dispatch, struct request,
 				      queuelist);
 		list_del_init(&rq->queuelist);
+		rq->rq_flags &= ~RQF_DISP_LIST;
 
 		bfq_log(bfqd,
 			"dispatch requests: picked %p from dispatch list", rq);
@@ -3950,6 +3955,17 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 			 */
 			bfqq->dispatched++;
 
+			/*
+			 * TESTING: reset DISP_LIST flag, because: 1)
+			 * this rq this request has passed through
+			 * get_rq_private, 2) then it will have
+			 * put_rq_private invoked on it, and 3) in
+			 * put_rq_private we use this flag to check
+			 * that put_rq_private is not invoked on
+			 * requests for which get_rq_private has been
+			 * invoked.
+			 */
+			rq->rq_flags &= ~RQF_DISP_LIST;
 			goto inc_in_driver_start_rq;
 		}
 
@@ -4637,6 +4653,7 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		else
 			list_add_tail(&rq->queuelist, &bfqd->dispatch);
 
+		rq->rq_flags |= RQF_DISP_LIST;
 		if (bfqq)
 			bfq_log_bfqq(bfqd, bfqq,
 				     "insert_request %p in disp: at_head %d",
@@ -4824,6 +4841,10 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
 	bfqd = bfqq->bfqd;
 	BUG_ON(!bfqd);
 
+	if (rq->rq_flags & RQF_DISP_LIST) {
+		pr_crit("putting disp rq %p for %d", rq, bfqq->pid);
+		BUG();
+	}
 	BUG_ON(rq->rq_flags & RQF_QUEUED);
 	BUG_ON(!(rq->rq_flags & RQF_ELVPRIV));
 
@@ -5015,6 +5036,7 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 
 	rq->elv.priv[0] = bic;
 	rq->elv.priv[1] = bfqq;
+	rq->rq_flags &= ~RQF_DISP_LIST;
 
 	/*
 	 * If a bfq_queue has only one process reference, it is owned
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 10f892ca585d..0048e59e6d07 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -121,6 +121,8 @@ typedef __u32 __bitwise req_flags_t;
 /* Look at ->special_vec for the actual data payload instead of the
    bio chain. */
 #define RQF_SPECIAL_PAYLOAD	((__force req_flags_t)(1 << 18))
+/* DEBUG: rq in bfq-mq dispatch list */
+#define RQF_DISP_LIST	((__force req_flags_t)(1 << 19))
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \

From 49206f9052d13c96d49dbc36c612bed41b2d6552 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Sat, 25 Feb 2017 17:38:05 +0100
Subject: [PATCH 21/51] Complete support for cgroups

This commit completes cgroups support for bfq-mq. In particular, it deals with
a sort of circular dependency introduced in blk-mq: the function
blkcg_activate_policy, invoked during scheduler initialization, triggers the
invocation of the has_work scheduler hook (before the init function is
finished). To adress this issue, this commit moves the invocation of
blkcg_activate_policy after the initialization of all the fields that could be
initialized before invoking blkcg_activate_policy itself. This enables has_work
to correctly return false, and thus to prevent the blk-mq stack from invoking
further scheduler hooks before the init function is finished.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/Kconfig.iosched  |   9 +++++
 block/bfq-mq-iosched.c | 108 ++++++++++++++++++++++++++++---------------------
 block/bfq-mq.h         |   2 +-
 3 files changed, 72 insertions(+), 47 deletions(-)

diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 2d94af3d8b0a..299a6861fb90 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -106,6 +106,15 @@ config MQ_IOSCHED_BFQ
 	guarantees a low latency to interactive and soft real-time
 	applications.  Details in Documentation/block/bfq-iosched.txt
 
+config MQ_BFQ_GROUP_IOSCHED
+	bool "BFQ-MQ hierarchical scheduling support"
+	depends on MQ_IOSCHED_BFQ && BLK_CGROUP
+	default n
+	---help---
+
+	Enable hierarchical scheduling in BFQ-MQ, using the blkio
+	(cgroups-v1) or io (cgroups-v2) controller.
+
 config MQ_IOSCHED_DEADLINE
 	tristate "MQ deadline I/O scheduler"
 	default y
diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index b4d40bb712d2..02a1e7fd0ea4 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -88,7 +88,6 @@
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
 #include "blk-mq-sched.h"
-#undef CONFIG_BFQ_GROUP_IOSCHED /* cgroups support not yet functional */
 #include "bfq-mq.h"
 
 /* Expiration time of sync (0) and async (1) requests, in ns. */
@@ -233,15 +232,6 @@ static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
 	return NULL;
 }
 
-#define BFQ_MQ
-#include "bfq-sched.c"
-#include "bfq-cgroup-included.c"
-
-#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)
-
 /*
  * Scheduler run of queue, if there are requests pending and no one in the
  * driver that will restart queueing.
@@ -255,6 +245,43 @@ static void bfq_schedule_dispatch(struct bfq_data *bfqd)
 }
 
 /*
+ * Next two functions release bfqd->lock and put the io context
+ * pointed by bfqd->ioc_to_put. This delayed put is used to not risk
+ * to take an ioc->lock while the scheduler lock is being held.
+ */
+static void bfq_unlock_put_ioc(struct bfq_data *bfqd)
+{
+	struct io_context *ioc_to_put = bfqd->ioc_to_put;
+
+	bfqd->ioc_to_put = NULL;
+	spin_unlock_irq(&bfqd->lock);
+
+	if (ioc_to_put)
+		put_io_context(ioc_to_put);
+}
+
+static void bfq_unlock_put_ioc_restore(struct bfq_data *bfqd,
+				       unsigned long flags)
+{
+	struct io_context *ioc_to_put = bfqd->ioc_to_put;
+
+	bfqd->ioc_to_put = NULL;
+	spin_unlock_irqrestore(&bfqd->lock, flags);
+
+	if (ioc_to_put)
+		put_io_context(ioc_to_put);
+}
+
+#define BFQ_MQ
+#include "bfq-sched.c"
+#include "bfq-cgroup-included.c"
+
+#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.
@@ -4050,34 +4077,6 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	return rq;
 }
 
-/*
- * Next two functions release bfqd->lock and put the io context
- * pointed by bfqd->ioc_to_put. This delayed put is used to not risk
- * to take an ioc->lock while the scheduler lock is being held.
- */
-static void bfq_unlock_put_ioc(struct bfq_data *bfqd)
-{
-	struct io_context *ioc_to_put = bfqd->ioc_to_put;
-
-	bfqd->ioc_to_put = NULL;
-	spin_unlock_irq(&bfqd->lock);
-
-	if (ioc_to_put)
-		put_io_context(ioc_to_put);
-}
-
-static void bfq_unlock_put_ioc_restore(struct bfq_data *bfqd,
-				       unsigned long flags)
-{
-	struct io_context *ioc_to_put = bfqd->ioc_to_put;
-
-	bfqd->ioc_to_put = NULL;
-	spin_unlock_irqrestore(&bfqd->lock, flags);
-
-	if (ioc_to_put)
-		put_io_context(ioc_to_put);
-}
-
 static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 {
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
@@ -5239,6 +5238,10 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	}
 	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
@@ -5261,12 +5264,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	bfqd->oom_bfqq.entity.prio_changed = 1;
 
 	bfqd->queue = q;
-
-	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);
+	INIT_LIST_HEAD(&bfqd->dispatch);
 
 	hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_REL);
@@ -5324,9 +5322,27 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	bfqd->device_speed = BFQ_BFQD_FAST;
 
 	spin_lock_init(&bfqd->lock);
-	INIT_LIST_HEAD(&bfqd->dispatch);
 
-	q->elevator = eq;
+	/*
+	 * 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;
 
diff --git a/block/bfq-mq.h b/block/bfq-mq.h
index bd83f1c02573..2c81c02bccc4 100644
--- a/block/bfq-mq.h
+++ b/block/bfq-mq.h
@@ -20,7 +20,7 @@
 #include <linux/blk-cgroup.h>
 
 /* see comments on CONFIG_BFQ_GROUP_IOSCHED in bfq.h */
-#ifdef CONFIG_BFQ_MQ_GROUP_IOSCHED
+#ifdef CONFIG_MQ_BFQ_GROUP_IOSCHED
 #define BFQ_GROUP_IOSCHED_ENABLED
 #endif
 

From 62d12db23ce14d2716b5cff7d2635fbc817b96d0 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Fri, 17 Mar 2017 06:15:18 +0100
Subject: [PATCH 22/51] Remove all get and put of I/O contexts

When a bfq queue is set in service and when it is merged, a reference
to the I/O context associated with the queue is taken. This reference
is then released when the queue is deselected from service or
split. More precisely, the release of the reference is postponed to
when the scheduler lock is released, to avoid nesting between the
scheduler and the I/O-context lock. In fact, such nesting would lead
to deadlocks, because of other code paths that take the same locks in
the opposite order. This postponing of I/O-context releases does
complicate code.

This commit addresses this issue by modifying involved operations in
such a way to not need to get the above I/O-context references any
more. Then it also removes any get and release of these references.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-cgroup-included.c |   2 +-
 block/bfq-mq-iosched.c      | 127 ++++++++------------------------------------
 block/bfq-mq.h              |  11 ----
 block/bfq-sched.c           |  17 ------
 4 files changed, 22 insertions(+), 135 deletions(-)

diff --git a/block/bfq-cgroup-included.c b/block/bfq-cgroup-included.c
index cf59eeb7f08e..dfacca799b5e 100644
--- a/block/bfq-cgroup-included.c
+++ b/block/bfq-cgroup-included.c
@@ -773,7 +773,7 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 	bfq_put_async_queues(bfqd, bfqg);
 
 #ifdef BFQ_MQ
-	bfq_unlock_put_ioc_restore(bfqd, flags);
+	spin_unlock_irqrestore(&bfqd->lock, flags);
 #endif
 	/*
 	 * @blkg is going offline and will be ignored by
diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 02a1e7fd0ea4..8e7589d3280f 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -244,34 +244,6 @@ static void bfq_schedule_dispatch(struct bfq_data *bfqd)
 	}
 }
 
-/*
- * Next two functions release bfqd->lock and put the io context
- * pointed by bfqd->ioc_to_put. This delayed put is used to not risk
- * to take an ioc->lock while the scheduler lock is being held.
- */
-static void bfq_unlock_put_ioc(struct bfq_data *bfqd)
-{
-	struct io_context *ioc_to_put = bfqd->ioc_to_put;
-
-	bfqd->ioc_to_put = NULL;
-	spin_unlock_irq(&bfqd->lock);
-
-	if (ioc_to_put)
-		put_io_context(ioc_to_put);
-}
-
-static void bfq_unlock_put_ioc_restore(struct bfq_data *bfqd,
-				       unsigned long flags)
-{
-	struct io_context *ioc_to_put = bfqd->ioc_to_put;
-
-	bfqd->ioc_to_put = NULL;
-	spin_unlock_irqrestore(&bfqd->lock, flags);
-
-	if (ioc_to_put)
-		put_io_context(ioc_to_put);
-}
-
 #define BFQ_MQ
 #include "bfq-sched.c"
 #include "bfq-cgroup-included.c"
@@ -1747,7 +1719,6 @@ static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
 	if (free)
 		blk_mq_free_request(free);
 	bfqd->bio_bfqq_set = false;
-	BUG_ON(bfqd->ioc_to_put);
 	spin_unlock_irq(&bfqd->lock);
 
 	return ret;
@@ -1812,7 +1783,6 @@ static void bfq_request_merged(struct request_queue *q, struct request *req,
 			bfq_updated_next_req(bfqd, bfqq);
 			bfq_pos_tree_add_move(bfqd, bfqq);
 		}
-		BUG_ON(bfqd->ioc_to_put);
 		spin_unlock_irq(&bfqd->lock);
 	}
 }
@@ -1858,7 +1828,6 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
 
 	bfq_remove_request(q, next);
 
-	BUG_ON(bfqq->bfqd->ioc_to_put);
 	spin_unlock_irq(&bfqq->bfqd->lock);
 end:
 	bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
@@ -2035,20 +2004,18 @@ bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
 	 * first time that the requests of some process are redirected to
 	 * it.
 	 *
-	 * We redirect bfqq to new_bfqq and not the opposite, because we
-	 * are in the context of the process owning bfqq, hence we have
-	 * the io_cq of this process. So we can immediately configure this
-	 * io_cq to redirect the requests of the process to new_bfqq.
+	 * We redirect bfqq to new_bfqq and not the opposite, because
+	 * we are in the context of the process owning bfqq, thus we
+	 * have the io_cq of this process. So we can immediately
+	 * configure this io_cq to redirect the requests of the
+	 * process to new_bfqq. In contrast, the io_cq of new_bfqq is
+	 * not available any more (new_bfqq->bic == NULL).
 	 *
-	 * NOTE, even if new_bfqq coincides with the in-service queue, the
-	 * io_cq of new_bfqq is not available, because, if the in-service
-	 * queue is shared, bfqd->in_service_bic may not point to the
-	 * io_cq of the in-service queue.
-	 * Redirecting the requests of the process owning bfqq to the
-	 * currently in-service queue is in any case the best option, as
-	 * we feed the in-service queue with new requests close to the
-	 * last request served and, by doing so, hopefully increase the
-	 * throughput.
+	 * Anyway, even in case new_bfqq coincides with the in-service
+	 * queue, redirecting requests the in-service queue is the
+	 * best option, as we feed the in-service queue with new
+	 * requests close to the last request served and, by doing so,
+	 * are likely to increase the throughput.
 	 */
 	bfqq->new_bfqq = new_bfqq;
 	new_bfqq->ref += process_refs;
@@ -2147,13 +2114,13 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	in_service_bfqq = bfqd->in_service_queue;
 
 	if (in_service_bfqq && in_service_bfqq != bfqq &&
-	    bfqd->in_service_bic && wr_from_too_long(in_service_bfqq)
+	    wr_from_too_long(in_service_bfqq)
 	    && likely(in_service_bfqq == &bfqd->oom_bfqq))
 		bfq_log_bfqq(bfqd, bfqq,
 		"would have tried merge with in-service-queue, but wr");
 
-	if (!in_service_bfqq || in_service_bfqq == bfqq ||
-	    !bfqd->in_service_bic || wr_from_too_long(in_service_bfqq) ||
+	if (!in_service_bfqq || in_service_bfqq == bfqq
+	    || wr_from_too_long(in_service_bfqq) ||
 	    unlikely(in_service_bfqq == &bfqd->oom_bfqq))
 		goto check_scheduled;
 
@@ -2214,16 +2181,6 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish));
 }
 
-static void bfq_get_bic_reference(struct bfq_queue *bfqq)
-{
-	/*
-	 * If bfqq->bic has a non-NULL value, the bic to which it belongs
-	 * is about to begin using a shared bfq_queue.
-	 */
-	if (bfqq->bic)
-		atomic_long_inc(&bfqq->bic->icq.ioc->refcount);
-}
-
 static void
 bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 		struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
@@ -2280,12 +2237,6 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 		     bfqd->wr_busy_queues);
 
 	/*
-	 * Grab a reference to the bic, to prevent it from being destroyed
-	 * before being possibly touched by a bfq_split_bfqq().
-	 */
-	bfq_get_bic_reference(bfqq);
-	bfq_get_bic_reference(new_bfqq);
-	/*
 	 * Merge queues (that is, let bic redirect its requests to new_bfqq)
 	 */
 	bic_set_bfqq(bic, new_bfqq, 1);
@@ -2472,16 +2423,10 @@ static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd)
 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;
 
 	BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
 
-	/* 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);
 
 	/*
@@ -3922,11 +3867,6 @@ static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
 		     bfq_bfqq_budget_left(bfqq),
 		     bfqq->dispatched);
 
-	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
@@ -4085,7 +4025,7 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	spin_lock_irq(&bfqd->lock);
 
 	rq = __bfq_dispatch_request(hctx);
-	bfq_unlock_put_ioc(bfqd);
+	spin_unlock_irq(&bfqd->lock);
 
 	return rq;
 }
@@ -4184,21 +4124,10 @@ static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
 		unsigned long flags;
 
 		spin_lock_irqsave(&bfqd->lock, flags);
-		BUG_ON(bfqd->ioc_to_put);
-		/*
-		 * If the bic is using a shared queue, put the
-		 * reference taken on the io_context when the bic
-		 * started using a shared bfq_queue. This put cannot
-		 * make ioc->ref_count reach 0, then no ioc->lock
-		 * risks to be taken (leading to possible deadlock
-		 * scenarios).
-		 */
-		if (is_sync && bfq_bfqq_coop(bfqq))
-			put_io_context(bic->icq.ioc);
 
 		bfq_exit_bfqq(bfqd, bfqq);
 		bic_set_bfqq(bic, NULL, is_sync);
-		bfq_unlock_put_ioc_restore(bfqd, flags);
+		spin_unlock_irqrestore(&bfqd->lock, flags);
 	}
 }
 
@@ -4633,12 +4562,10 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	spin_lock_irq(&bfqd->lock);
 	if (blk_mq_sched_try_insert_merge(q, rq)) {
-		BUG_ON(bfqd->ioc_to_put);
 		spin_unlock_irq(&bfqd->lock);
 		return;
 	}
 
-	BUG_ON(bfqd->ioc_to_put);
 	spin_unlock_irq(&bfqd->lock);
 
 	blk_mq_sched_request_inserted(rq);
@@ -4671,7 +4598,7 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		}
 	}
 
-	bfq_unlock_put_ioc(bfqd);
+	spin_unlock_irq(&bfqd->lock);
 }
 
 static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
@@ -4864,12 +4791,11 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
 		unsigned long flags;
 
 		spin_lock_irqsave(&bfqd->lock, flags);
-		BUG_ON(bfqd->ioc_to_put);
 
 		bfq_completed_request(bfqq, bfqd);
 		bfq_put_rq_priv_body(bfqq);
 
-		bfq_unlock_put_ioc_restore(bfqd, flags);
+		spin_unlock_irqrestore(&bfqd->lock, flags);
 	} else {
 		/*
 		 * Request rq may be still/already in the scheduler,
@@ -4992,7 +4918,6 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 
 	bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync,
 					 &new_queue);
-	BUG_ON(bfqd->ioc_to_put);
 
 	if (unlikely(!new_queue)) {
 		/* If the queue was seeky for too long, break it apart. */
@@ -5005,14 +4930,6 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 				bic->saved_in_large_burst = true;
 
 			bfqq = bfq_split_bfqq(bic, bfqq);
-			/*
-			 * A reference to bic->icq.ioc needs to be
-			 * released after a queue split. Do not do it
-			 * immediately, to not risk to possibly take
-			 * an ioc->lock while holding the scheduler
-			 * lock.
-			 */
-			bfqd->ioc_to_put = bic->icq.ioc;
 
 			if (!bfqq)
 				bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,
@@ -5045,7 +4962,7 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 	 */
 	if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) {
 		bfqq->bic = bic;
-		if (bfqd->ioc_to_put) { /* if true, then there has been a split */
+		if (split) {
 			/*
 			 * The queue has just been split from a shared
 			 * queue: restore the idle window and the
@@ -5059,7 +4976,7 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 	if (unlikely(bfq_bfqq_just_created(bfqq)))
 		bfq_handle_burst(bfqd, bfqq);
 
-	bfq_unlock_put_ioc(bfqd);
+	spin_unlock_irq(&bfqd->lock);
 
 	return 0;
 
@@ -5077,7 +4994,6 @@ static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
 
 	BUG_ON(!bfqd);
 	spin_lock_irqsave(&bfqd->lock, flags);
-	BUG_ON(bfqd->ioc_to_put);
 
 	bfq_log_bfqq(bfqd, bfqq, "handling slice_timer expiration");
 	bfq_clear_bfqq_wait_request(bfqq);
@@ -5108,7 +5024,7 @@ static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
 	bfq_bfqq_expire(bfqd, bfqq, true, reason);
 
 schedule_dispatch:
-	bfq_unlock_put_ioc_restore(bfqd, flags);
+	spin_unlock_irqrestore(&bfqd->lock, flags);
 	bfq_schedule_dispatch(bfqd);
 }
 
@@ -5186,7 +5102,6 @@ static void bfq_exit_queue(struct elevator_queue *e)
 	spin_lock_irq(&bfqd->lock);
 	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
 		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
-	BUG_ON(bfqd->ioc_to_put);
 	spin_unlock_irq(&bfqd->lock);
 
 	hrtimer_cancel(&bfqd->idle_slice_timer);
diff --git a/block/bfq-mq.h b/block/bfq-mq.h
index 2c81c02bccc4..36ee24a87dda 100644
--- a/block/bfq-mq.h
+++ b/block/bfq-mq.h
@@ -458,8 +458,6 @@ struct bfq_data {
 
 	/* 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;
@@ -621,15 +619,6 @@ struct bfq_data {
 	struct bfq_queue *bio_bfqq;
 	/* Extra flag used only for TESTING */
 	bool bio_bfqq_set;
-
-	/*
-	 * io context to put right after bfqd->lock is released. This
-	 * filed is used to perform put_io_context, when needed, to
-	 * after the scheduler lock has been released, and thus
-	 * prevent an ioc->lock from being possibly taken while the
-	 * scheduler lock is being held.
-	 */
-	struct io_context *ioc_to_put;
 };
 
 enum bfqq_state_flags {
diff --git a/block/bfq-sched.c b/block/bfq-sched.c
index 85e59eeb3569..9c4e6797d8c9 100644
--- a/block/bfq-sched.c
+++ b/block/bfq-sched.c
@@ -1904,23 +1904,6 @@ static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
 	struct bfq_entity *in_serv_entity = &in_serv_bfqq->entity;
 	struct bfq_entity *entity = in_serv_entity;
 
-	if (bfqd->in_service_bic) {
-#ifdef BFQ_MQ
-		BUG_ON(bfqd->ioc_to_put);
-		/*
-		 * Schedule the release of a reference to
-		 * bfqd->in_service_bic->icq.ioc to right after the
-		 * scheduler lock is released. This ioc is not
-		 * released immediately, to not risk to possibly take
-		 * an ioc->lock while holding the scheduler lock.
-		 */
-		bfqd->ioc_to_put = bfqd->in_service_bic->icq.ioc;
-#else
-		put_io_context(bfqd->in_service_bic->icq.ioc);
-#endif
-		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;

From 1521ad11f8684cf0a1b7249249cd406fee50da6d Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Wed, 29 Mar 2017 18:41:46 +0200
Subject: [PATCH 23/51] BUGFIX: Remove unneeded and deadlock-causing lock in
 request_merged

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 8e7589d3280f..bb046335ff4f 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -1761,7 +1761,6 @@ static void bfq_request_merged(struct request_queue *q, struct request *req,
 		BUG_ON(RQ_BFQQ(req) != bfqq);
 		elv_rb_add(&bfqq->sort_list, req);
 
-		spin_lock_irq(&bfqd->lock);
 		/* Choose next request to be served for bfqq */
 		prev = bfqq->next_rq;
 		next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req,
@@ -1783,7 +1782,6 @@ static void bfq_request_merged(struct request_queue *q, struct request *req,
 			bfq_updated_next_req(bfqd, bfqq);
 			bfq_pos_tree_add_move(bfqd, bfqq);
 		}
-		spin_unlock_irq(&bfqd->lock);
 	}
 }
 

From 9136b4c953918ea937254c57cfb787b55b5bc2c6 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Wed, 29 Mar 2017 18:55:30 +0200
Subject: [PATCH 24/51] Fix wrong unlikely

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index bb046335ff4f..3ae9bd424b3f 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -4917,7 +4917,7 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 	bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync,
 					 &new_queue);
 
-	if (unlikely(!new_queue)) {
+	if (likely(!new_queue)) {
 		/* If the queue was seeky for too long, break it apart. */
 		if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
 			BUG_ON(!is_sync);

From 8e05f722f19645f2278f6962368ca3b7c2a81c9c Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Fri, 12 May 2017 09:51:18 +0200
Subject: [PATCH 25/51] Change cgroup params prefix to bfq-mq for bfq-mq

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-cgroup-included.c | 54 ++++++++++++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 23 deletions(-)

diff --git a/block/bfq-cgroup-included.c b/block/bfq-cgroup-included.c
index dfacca799b5e..9e9b0a09e26f 100644
--- a/block/bfq-cgroup-included.c
+++ b/block/bfq-cgroup-included.c
@@ -995,9 +995,15 @@ bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
 	return blkg_to_bfqg(bfqd->queue->root_blkg);
 }
 
+#ifdef BFQ_MQ
+#define BFQ_CGROUP_FNAME(param) "bfq-mq."#param
+#else
+#define BFQ_CGROUP_FNAME(param) "bfq."#param
+#endif
+
 static struct cftype bfq_blkcg_legacy_files[] = {
 	{
-		.name = "bfq.weight",
+		.name = BFQ_CGROUP_FNAME(weight),
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = bfq_io_show_weight,
 		.write_u64 = bfq_io_set_weight_legacy,
@@ -1005,106 +1011,106 @@ static struct cftype bfq_blkcg_legacy_files[] = {
 
 	/* statistics, covers only the tasks in the bfqg */
 	{
-		.name = "bfq.time",
+		.name = BFQ_CGROUP_FNAME(time),
 		.private = offsetof(struct bfq_group, stats.time),
 		.seq_show = bfqg_print_stat,
 	},
 	{
-		.name = "bfq.sectors",
+		.name = BFQ_CGROUP_FNAME(sectors),
 		.seq_show = bfqg_print_stat_sectors,
 	},
 	{
-		.name = "bfq.io_service_bytes",
+		.name = BFQ_CGROUP_FNAME(io_service_bytes),
 		.private = (unsigned long)&blkcg_policy_bfq,
 		.seq_show = blkg_print_stat_bytes,
 	},
 	{
-		.name = "bfq.io_serviced",
+		.name = BFQ_CGROUP_FNAME(io_serviced),
 		.private = (unsigned long)&blkcg_policy_bfq,
 		.seq_show = blkg_print_stat_ios,
 	},
 	{
-		.name = "bfq.io_service_time",
+		.name = BFQ_CGROUP_FNAME(io_service_time),
 		.private = offsetof(struct bfq_group, stats.service_time),
 		.seq_show = bfqg_print_rwstat,
 	},
 	{
-		.name = "bfq.io_wait_time",
+		.name = BFQ_CGROUP_FNAME(io_wait_time),
 		.private = offsetof(struct bfq_group, stats.wait_time),
 		.seq_show = bfqg_print_rwstat,
 	},
 	{
-		.name = "bfq.io_merged",
+		.name = BFQ_CGROUP_FNAME(io_merged),
 		.private = offsetof(struct bfq_group, stats.merged),
 		.seq_show = bfqg_print_rwstat,
 	},
 	{
-		.name = "bfq.io_queued",
+		.name = BFQ_CGROUP_FNAME(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",
+		.name = BFQ_CGROUP_FNAME(time_recursive),
 		.private = offsetof(struct bfq_group, stats.time),
 		.seq_show = bfqg_print_stat_recursive,
 	},
 	{
-		.name = "bfq.sectors_recursive",
+		.name = BFQ_CGROUP_FNAME(sectors_recursive),
 		.seq_show = bfqg_print_stat_sectors_recursive,
 	},
 	{
-		.name = "bfq.io_service_bytes_recursive",
+		.name = BFQ_CGROUP_FNAME(io_service_bytes_recursive),
 		.private = (unsigned long)&blkcg_policy_bfq,
 		.seq_show = blkg_print_stat_bytes_recursive,
 	},
 	{
-		.name = "bfq.io_serviced_recursive",
+		.name = BFQ_CGROUP_FNAME(io_serviced_recursive),
 		.private = (unsigned long)&blkcg_policy_bfq,
 		.seq_show = blkg_print_stat_ios_recursive,
 	},
 	{
-		.name = "bfq.io_service_time_recursive",
+		.name = BFQ_CGROUP_FNAME(io_service_time_recursive),
 		.private = offsetof(struct bfq_group, stats.service_time),
 		.seq_show = bfqg_print_rwstat_recursive,
 	},
 	{
-		.name = "bfq.io_wait_time_recursive",
+		.name = BFQ_CGROUP_FNAME(io_wait_time_recursive),
 		.private = offsetof(struct bfq_group, stats.wait_time),
 		.seq_show = bfqg_print_rwstat_recursive,
 	},
 	{
-		.name = "bfq.io_merged_recursive",
+		.name = BFQ_CGROUP_FNAME(io_merged_recursive),
 		.private = offsetof(struct bfq_group, stats.merged),
 		.seq_show = bfqg_print_rwstat_recursive,
 	},
 	{
-		.name = "bfq.io_queued_recursive",
+		.name = BFQ_CGROUP_FNAME(io_queued_recursive),
 		.private = offsetof(struct bfq_group, stats.queued),
 		.seq_show = bfqg_print_rwstat_recursive,
 	},
 	{
-		.name = "bfq.avg_queue_size",
+		.name = BFQ_CGROUP_FNAME(avg_queue_size),
 		.seq_show = bfqg_print_avg_queue_size,
 	},
 	{
-		.name = "bfq.group_wait_time",
+		.name = BFQ_CGROUP_FNAME(group_wait_time),
 		.private = offsetof(struct bfq_group, stats.group_wait_time),
 		.seq_show = bfqg_print_stat,
 	},
 	{
-		.name = "bfq.idle_time",
+		.name = BFQ_CGROUP_FNAME(idle_time),
 		.private = offsetof(struct bfq_group, stats.idle_time),
 		.seq_show = bfqg_print_stat,
 	},
 	{
-		.name = "bfq.empty_time",
+		.name = BFQ_CGROUP_FNAME(empty_time),
 		.private = offsetof(struct bfq_group, stats.empty_time),
 		.seq_show = bfqg_print_stat,
 	},
 	{
-		.name = "bfq.dequeue",
+		.name = BFQ_CGROUP_FNAME(dequeue),
 		.private = offsetof(struct bfq_group, stats.dequeue),
 		.seq_show = bfqg_print_stat,
 	},
@@ -1113,7 +1119,7 @@ static struct cftype bfq_blkcg_legacy_files[] = {
 
 static struct cftype bfq_blkg_files[] = {
 	{
-		.name = "bfq.weight",
+		.name = BFQ_CGROUP_FNAME(weight),
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = bfq_io_show_weight,
 		.write = bfq_io_set_weight,
@@ -1121,6 +1127,8 @@ static struct cftype bfq_blkg_files[] = {
 	{} /* terminate */
 };
 
+#undef BFQ_CGROUP_FNAME
+
 #else /* BFQ_GROUP_IOSCHED_ENABLED */
 
 static inline void bfqg_stats_update_io_add(struct bfq_group *bfqg,

From abdf7565dadbb00e78be5f4fb2cc9b157649840e Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Fri, 12 May 2017 11:56:13 +0200
Subject: [PATCH 26/51] Add tentative extra tests on groups, reqs and queues

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-cgroup-included.c | 1 +
 block/bfq-mq-iosched.c      | 5 +++++
 include/linux/blkdev.h      | 2 ++
 3 files changed, 8 insertions(+)

diff --git a/block/bfq-cgroup-included.c b/block/bfq-cgroup-included.c
index 9e9b0a09e26f..72107ad12220 100644
--- a/block/bfq-cgroup-included.c
+++ b/block/bfq-cgroup-included.c
@@ -412,6 +412,7 @@ static void bfq_pd_init(struct blkg_policy_data *pd)
 	BUG_ON(!blkg);
 	bfqg = blkg_to_bfqg(blkg);
 	bfqd = blkg->q->elevator->elevator_data;
+	BUG_ON(bfqg == bfqd->root_group);
 	entity = &bfqg->entity;
 	d = blkcg_to_bfqgd(blkg->blkcg);
 
diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 3ae9bd424b3f..a9e3406fef06 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -4494,6 +4494,7 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 {
 	struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq;
+	BUG_ON(!bfqq);
 
 	assert_spin_locked(&bfqd->lock);
 
@@ -4587,6 +4588,9 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 				"insert_request %p in disp: at_head %d",
 				rq, at_head);
 	} else {
+		BUG_ON(!(rq->rq_flags & RQF_GOT));
+		rq->rq_flags &= ~RQF_GOT;
+
 		__bfq_insert_request(bfqd, rq);
 
 		if (rq_mergeable(rq)) {
@@ -4974,6 +4978,7 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 	if (unlikely(bfq_bfqq_just_created(bfqq)))
 		bfq_handle_burst(bfqd, bfqq);
 
+	rq->rq_flags |= RQF_GOT;
 	spin_unlock_irq(&bfqd->lock);
 
 	return 0;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0048e59e6d07..9ae814743095 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -123,6 +123,8 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_SPECIAL_PAYLOAD	((__force req_flags_t)(1 << 18))
 /* DEBUG: rq in bfq-mq dispatch list */
 #define RQF_DISP_LIST	((__force req_flags_t)(1 << 19))
+/* DEBUG: rq had get_rq_private executed on it */
+#define RQF_GOT	((__force req_flags_t)(1 << 20))
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \

From 9e1c1514bc947c4e04502331372b1cc58459d8d1 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Mon, 15 May 2017 22:25:03 +0200
Subject: [PATCH 27/51] block, bfq-mq: access and cache blkg data only when
 safe

In blk-cgroup, operations on blkg objects are protected with the
request_queue lock. This is no more the lock that protects
I/O-scheduler operations in blk-mq. In fact, the latter are now
protected with a finer-grained per-scheduler-instance lock. As a
consequence, although blkg lookups are also rcu-protected, blk-mq I/O
schedulers may see inconsistent data when they access blkg and
blkg-related objects. BFQ does access these objects, and does incur
this problem, in the following case.

The blkg_lookup performed in bfq_get_queue, being protected (only)
through rcu, may happen to return the address of a copy of the
original blkg. If this is the case, then the blkg_get performed in
bfq_get_queue, to pin down the blkg, is useless: it does not prevent
blk-cgroup code from destroying both the original blkg and all objects
directly or indirectly referred by the copy of the blkg. BFQ accesses
these objects, which typically causes a crash for NULL-pointer
dereference of memory-protection violation.

Some additional protection mechanism should be added to blk-cgroup to
address this issue. In the meantime, this commit provides a quick
temporary fix for BFQ: cache (when safe) blkg data that might
disappear right after a blkg_lookup.

In particular, this commit exploits the following facts to achieve its
goal without introducing further locks.  Destroy operations on a blkg
invoke, as a first step, hooks of the scheduler associated with the
blkg. And these hooks are executed with bfqd->lock held for BFQ. As a
consequence, for any blkg associated with the request queue an
instance of BFQ is attached to, we are guaranteed that such a blkg is
not destroyed, and that all the pointers it contains are consistent,
while that instance is holding its bfqd->lock. A blkg_lookup performed
with bfqd->lock held then returns a fully consistent blkg, which
remains consistent until this lock is held. In more detail, this holds
even if the returned blkg is a copy of the original one.

Finally, also the object describing a group inside BFQ needs to be
protected from destruction on the blkg_free of the original blkg
(which invokes bfq_pd_free). This commit adds private refcounting for
this object, to let it disappear only after no bfq_queue refers to it
any longer.

This commit also removes or updates some stale comments on locking
issues related to blk-cgroup operations.

Reported-by: Tomas Konir <tomas.konir@gmail.com>
Reported-by: Lee Tibbert <lee.tibbert@gmail.com>
Reported-by: Marco Piazza <mpiazza@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Tomas Konir <tomas.konir@gmail.com>
Tested-by: Lee Tibbert <lee.tibbert@gmail.com>
Tested-by: Marco Piazza <mpiazza@gmail.com>
---
 block/bfq-cgroup-included.c | 149 ++++++++++++++++++++++++++++++++++++++++----
 block/bfq-mq-iosched.c      |   2 +-
 block/bfq-mq.h              |  26 +++-----
 3 files changed, 148 insertions(+), 29 deletions(-)

diff --git a/block/bfq-cgroup-included.c b/block/bfq-cgroup-included.c
index 72107ad12220..d903393ee78a 100644
--- a/block/bfq-cgroup-included.c
+++ b/block/bfq-cgroup-included.c
@@ -43,7 +43,11 @@ BFQG_FLAG_FNS(idling)
 BFQG_FLAG_FNS(empty)
 #undef BFQG_FLAG_FNS
 
+#ifdef BFQ_MQ
+/* This should be called with the scheduler lock held. */
+#else
 /* This should be called with the queue_lock held. */
+#endif
 static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
 {
 	unsigned long long now;
@@ -58,7 +62,11 @@ static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
 	bfqg_stats_clear_waiting(stats);
 }
 
+#ifdef BFQ_MQ
+/* This should be called with the scheduler lock held. */
+#else
 /* This should be called with the queue_lock held. */
+#endif
 static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
 						 struct bfq_group *curr_bfqg)
 {
@@ -72,7 +80,11 @@ static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
 	bfqg_stats_mark_waiting(stats);
 }
 
+#ifdef BFQ_MQ
+/* This should be called with the scheduler lock held. */
+#else
 /* This should be called with the queue_lock held. */
+#endif
 static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
 {
 	unsigned long long now;
@@ -198,14 +210,43 @@ static struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
 
 static void bfqg_get(struct bfq_group *bfqg)
 {
-	return blkg_get(bfqg_to_blkg(bfqg));
+#ifdef BFQ_MQ
+	bfqg->ref++;
+#else
+	blkg_get(bfqg_to_blkg(bfqg));
+#endif
 }
 
 static void bfqg_put(struct bfq_group *bfqg)
 {
-	return blkg_put(bfqg_to_blkg(bfqg));
+#ifdef BFQ_MQ
+	bfqg->ref--;
+
+	BUG_ON(bfqg->ref < 0);
+	if (bfqg->ref == 0)
+		kfree(bfqg);
+#else
+	blkg_put(bfqg_to_blkg(bfqg));
+#endif
+}
+
+#ifdef BFQ_MQ
+static void bfqg_and_blkg_get(struct bfq_group *bfqg)
+{
+	/* see comments in bfq_bic_update_cgroup for why refcounting bfqg */
+	bfqg_get(bfqg);
+
+	blkg_get(bfqg_to_blkg(bfqg));
 }
 
+static void bfqg_and_blkg_put(struct bfq_group *bfqg)
+{
+	bfqg_put(bfqg);
+
+	blkg_put(bfqg_to_blkg(bfqg));
+}
+#endif
+
 static void bfqg_stats_update_io_add(struct bfq_group *bfqg,
 				     struct bfq_queue *bfqq,
 				     unsigned int op)
@@ -310,7 +351,15 @@ static void bfq_init_entity(struct bfq_entity *entity,
 	if (bfqq) {
 		bfqq->ioprio = bfqq->new_ioprio;
 		bfqq->ioprio_class = bfqq->new_ioprio_class;
+#ifdef BFQ_MQ
+		/*
+		 * Make sure that bfqg and its associated blkg do not
+		 * disappear before entity.
+		 */
+		bfqg_and_blkg_get(bfqg);
+#else
 		bfqg_get(bfqg);
+#endif
 	}
 	entity->parent = bfqg->my_entity; /* NULL for root group */
 	entity->sched_data = &bfqg->sched_data;
@@ -397,6 +446,10 @@ static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node)
 		return NULL;
 	}
 
+#ifdef BFQ_MQ
+	/* see comments in bfq_bic_update_cgroup for why refcounting */
+	bfqg_get(bfqg);
+#endif
 	return &bfqg->pd;
 }
 
@@ -432,7 +485,11 @@ 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);
+#ifdef BFQ_MQ
+	bfqg_put(bfqg);
+#else
+	kfree(bfqg);
+#endif
 }
 
 static void bfq_pd_reset_stats(struct blkg_policy_data *pd)
@@ -516,9 +573,16 @@ static void bfq_bfqq_expire(struct bfq_data *bfqd,
  * 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.
  *
+#ifdef BFQ_MQ
+ * Must be called under the scheduler lock, to make sure that the blkg
+ * owning @bfqg does not disappear (see comments in
+ * bfq_bic_update_cgroup on guaranteeing the consistency of blkg
+ * objects).
+#else
  * 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()).
+#endif
  */
 static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 			  struct bfq_group *bfqg)
@@ -555,16 +619,20 @@ static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		       entity->tree);
 		bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
 	}
+#ifdef BFQ_MQ
+	bfqg_and_blkg_put(bfqq_group(bfqq));
+#else
 	bfqg_put(bfqq_group(bfqq));
+#endif
 
-	/*
-	 * 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;
+#ifdef BFQ_MQ
+	/* pin down bfqg and its associated blkg  */
+	bfqg_and_blkg_get(bfqg);
+#else
 	bfqg_get(bfqg);
+#endif
 
 	BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_busy(bfqq));
 	if (bfq_bfqq_busy(bfqq)) {
@@ -585,8 +653,14 @@ static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
  * @bic: the bic to move.
  * @blkcg: the blk-cgroup to move to.
  *
+#ifdef BFQ_MQ
+ * Move bic to blkcg, assuming that bfqd->lock is held; which makes
+ * sure that the reference to cgroup is valid across the call (see
+ * comments in bfq_bic_update_cgroup on this issue)
+#else
  * 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.
+#endif
  *
  * NOTE: an alternative approach might have been to store the current
  * cgroup in bfqq and getting a reference to it, reducing the lookup
@@ -645,6 +719,59 @@ static void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
 		goto out;
 
 	bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio));
+#ifdef BFQ_MQ
+	/*
+	 * Update blkg_path for bfq_log_* functions. We cache this
+	 * path, and update it here, for the following
+	 * reasons. Operations on blkg objects in blk-cgroup are
+	 * protected with the request_queue lock, and not with the
+	 * lock that protects the instances of this scheduler
+	 * (bfqd->lock). This exposes BFQ to the following sort of
+	 * race.
+	 *
+	 * The blkg_lookup performed in bfq_get_queue, protected
+	 * through rcu, may happen to return the address of a copy of
+	 * the original blkg. If this is the case, then the
+	 * bfqg_and_blkg_get performed in bfq_get_queue, to pin down
+	 * the blkg, is useless: it does not prevent blk-cgroup code
+	 * from destroying both the original blkg and all objects
+	 * directly or indirectly referred by the copy of the
+	 * blkg.
+	 *
+	 * On the bright side, destroy operations on a blkg invoke, as
+	 * a first step, hooks of the scheduler associated with the
+	 * blkg. And these hooks are executed with bfqd->lock held for
+	 * BFQ. As a consequence, for any blkg associated with the
+	 * request queue this instance of the scheduler is attached
+	 * to, we are guaranteed that such a blkg is not destroyed, and
+	 * that all the pointers it contains are consistent, while we
+	 * are holding bfqd->lock. A blkg_lookup performed with
+	 * bfqd->lock held then returns a fully consistent blkg, which
+	 * remains consistent until this lock is held.
+	 *
+	 * Thanks to the last fact, and to the fact that: (1) bfqg has
+	 * been obtained through a blkg_lookup in the above
+	 * assignment, and (2) bfqd->lock is being held, here we can
+	 * safely use the policy data for the involved blkg (i.e., the
+	 * field bfqg->pd) to get to the blkg associated with bfqg,
+	 * and then we can safely use any field of blkg. After we
+	 * release bfqd->lock, even just getting blkg through this
+	 * bfqg may cause dangling references to be traversed, as
+	 * bfqg->pd may not exist any more.
+	 *
+	 * In view of the above facts, here we cache, in the bfqg, any
+	 * blkg data we may need for this bic, and for its associated
+	 * bfq_queue. As of now, we need to cache only the path of the
+	 * blkg, which is used in the bfq_log_* functions.
+	 *
+	 * Finally, note that bfqg itself needs to be protected from
+	 * destruction on the blkg_free of the original blkg (which
+	 * invokes bfq_pd_free). We use an additional private
+	 * refcounter for bfqg, to let it disappear only after no
+	 * bfq_queue refers to it any longer.
+	 */
+	blkg_path(bfqg_to_blkg(bfqg), bfqg->blkg_path, sizeof(bfqg->blkg_path));
+#endif
 	bic->blkcg_serial_nr = serial_nr;
 out:
 	rcu_read_unlock();
@@ -682,8 +809,6 @@ static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
  * @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,
@@ -736,6 +861,7 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 #ifdef BFQ_MQ
 	spin_lock_irqsave(&bfqd->lock, flags);
 #endif
+
 	/*
 	 * Empty all service_trees belonging to this group before
 	 * deactivating the group itself.
@@ -746,8 +872,7 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 		/*
 		 * 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.
+		 * cgroup from the one being destroyed now.
 		 */
 		bfq_flush_idle_tree(st);
 
diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index a9e3406fef06..4eb668eeacdc 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -4073,7 +4073,7 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
 
 	kmem_cache_free(bfq_pool, bfqq);
 #ifdef BFQ_GROUP_IOSCHED_ENABLED
-	bfqg_put(bfqg);
+	bfqg_and_blkg_put(bfqg);
 #endif
 }
 
diff --git a/block/bfq-mq.h b/block/bfq-mq.h
index 36ee24a87dda..77ab0f22ed22 100644
--- a/block/bfq-mq.h
+++ b/block/bfq-mq.h
@@ -695,23 +695,17 @@ 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)); \
 	pr_crit("%s bfq%d%c %s " fmt "\n", 				\
 		checked_dev_name((bfqd)->queue->backing_dev_info->dev),	\
 		(bfqq)->pid,						\
 		bfq_bfqq_sync((bfqq)) ? 'S' : 'A',			\
-		__pbuf, ##args);					\
+		bfqq_group(bfqq)->blkg_path, ##args);			\
 } while (0)
 
 #define bfq_log_bfqg(bfqd, bfqg, fmt, args...)	do {			\
-	char __pbuf[128];						\
-									\
-	blkg_path(bfqg_to_blkg(bfqg), __pbuf, sizeof(__pbuf));		\
 	pr_crit("%s %s " fmt "\n",					\
 	checked_dev_name((bfqd)->queue->backing_dev_info->dev),		\
-	__pbuf, ##args);						\
+	bfqg->blkg_path, ##args);					\
 } while (0)
 
 #else /* BFQ_GROUP_IOSCHED_ENABLED */
@@ -736,20 +730,14 @@ 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);				\
+			  bfqq_group(bfqq)->blkg_path, ##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);	\
+	blk_add_trace_msg((bfqd)->queue, "%s " fmt, bfqg->blkg_path, ##args);\
 } while (0)
 
 #else /* BFQ_GROUP_IOSCHED_ENABLED */
@@ -860,6 +848,12 @@ struct bfq_group {
 	/* must be the first member */
 	struct blkg_policy_data pd;
 
+	/* cached path for this blkg (see comments in bfq_bic_update_cgroup) */
+	char blkg_path[128];
+
+	/* reference counter (see comments in bfq_bic_update_cgroup) */
+	int ref;
+
 	struct bfq_entity entity;
 	struct bfq_sched_data sched_data;
 

From c9137b749aceef6c2dde88e99b2fc978d5952e76 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Sat, 17 Jun 2017 11:18:11 +0200
Subject: [PATCH 28/51] bfq-mq: fix macro name in conditional invocation of
 policy_unregister

This commit fixes the name of the macro in the conditional group that
invokes blkcg_policy_unregister in bfq_exit for bfq-mq. Because of
this error, blkcg_policy_unregister was never invoked.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 4eb668eeacdc..bc1de3f70ea8 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -5669,7 +5669,7 @@ static int __init bfq_init(void)
 static void __exit bfq_exit(void)
 {
 	elv_unregister(&iosched_bfq_mq);
-#ifdef CONFIG_BFQ_GROUP_ENABLED
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 	blkcg_policy_unregister(&blkcg_policy_bfq);
 #endif
 	bfq_slab_kill();

From c7ceb37496f63b2dba4d06946ab85ec97b87bfb5 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Wed, 5 Jul 2017 11:48:17 +0200
Subject: [PATCH 29/51] Port of "blk-mq-sched: unify request finished methods"

No need to have two different callouts of bfq vs kyber.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bfq-mq-iosched.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index bc1de3f70ea8..2598602a0b10 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -4753,7 +4753,7 @@ static void bfq_put_rq_priv_body(struct bfq_queue *bfqq)
 	bfq_put_queue(bfqq);
 }
 
-static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
+static void bfq_finish_request(struct request *rq)
 {
 	struct bfq_queue *bfqq;
 	struct bfq_data *bfqd;
@@ -4814,7 +4814,7 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
 
 		assert_spin_locked(&bfqd->lock);
 		if (!RB_EMPTY_NODE(&rq->rb_node))
-			bfq_remove_request(q, rq);
+			bfq_remove_request(rq->q, rq);
 		bfq_put_rq_priv_body(bfqq);
 	}
 
@@ -5558,7 +5558,7 @@ static struct elv_fs_entry bfq_attrs[] = {
 static struct elevator_type iosched_bfq_mq = {
 	.ops.mq = {
 		.get_rq_priv		= bfq_get_rq_private,
-		.put_rq_priv		= bfq_put_rq_private,
+		.finish_request         = bfq_finish_request,
 		.exit_icq		= bfq_exit_icq,
 		.insert_requests	= bfq_insert_requests,
 		.dispatch_request	= bfq_dispatch_request,

From 12bef026fe114ab5e2e284772ddc52a8be83fdbc Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Wed, 5 Jul 2017 11:54:57 +0200
Subject: [PATCH 30/51] Port of "bfq-iosched: fix NULL ioc check in
 bfq_get_rq_private"

icq_to_bic is a container_of operation, so we need to check for NULL
before it.  Also move the check outside the spinlock while we're at
it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bfq-mq-iosched.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 2598602a0b10..c57774a60911 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -4903,16 +4903,17 @@ 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);
+	struct bfq_io_cq *bic;
 	const int is_sync = rq_is_sync(rq);
 	struct bfq_queue *bfqq;
 	bool bfqq_already_existing = false, split = false;
 	bool new_queue = false;
 
-	spin_lock_irq(&bfqd->lock);
+	if (!rq->elv.icq)
+		return 1;
+	bic = icq_to_bic(rq->elv.icq);
 
-	if (!bic)
-		goto queue_fail;
+	spin_lock_irq(&bfqd->lock);
 
 	bfq_check_ioprio_change(bic, bio);
 
@@ -4980,13 +4981,7 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 
 	rq->rq_flags |= RQF_GOT;
 	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)

From 633e5711347df1bf4ca935fd0aa9118a0054f75d Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Wed, 5 Jul 2017 12:02:16 +0200
Subject: [PATCH 31/51] Port of "blk-mq-sched: unify request prepare methods"

This patch makes sure we always allocate requests in the core blk-mq
code and use a common prepare_request method to initialize them for
both mq I/O schedulers.  For Kyber and additional limit_depth method
is added that is called before allocating the request.

Also because none of the intializations can really fail the new method
does not return an error - instead the bfq finish method is hardened
to deal with the no-IOC case.

Last but not least this removes the abuse of RQF_QUEUE by the blk-mq
scheduling code as RQF_ELFPRIV is all that is needed now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bfq-mq-iosched.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index c57774a60911..49ffca1ad6e7 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -4760,6 +4760,10 @@ static void bfq_finish_request(struct request *rq)
 	struct bfq_io_cq *bic;
 
 	BUG_ON(!rq);
+
+	if (!rq->elv.icq)
+		return;
+
 	bfqq = RQ_BFQQ(rq);
 	BUG_ON(!bfqq);
 
@@ -4899,9 +4903,9 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
 /*
  * Allocate bfq data structures associated with this request.
  */
-static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
-			      struct bio *bio)
+static void bfq_prepare_request(struct request *rq, struct bio *bio)
 {
+	struct request_queue *q = rq->q;
 	struct bfq_data *bfqd = q->elevator->elevator_data;
 	struct bfq_io_cq *bic;
 	const int is_sync = rq_is_sync(rq);
@@ -4910,7 +4914,7 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 	bool new_queue = false;
 
 	if (!rq->elv.icq)
-		return 1;
+		return;
 	bic = icq_to_bic(rq->elv.icq);
 
 	spin_lock_irq(&bfqd->lock);
@@ -4981,7 +4985,6 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 
 	rq->rq_flags |= RQF_GOT;
 	spin_unlock_irq(&bfqd->lock);
-	return 0;
 }
 
 static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
@@ -5552,7 +5555,7 @@ static struct elv_fs_entry bfq_attrs[] = {
 
 static struct elevator_type iosched_bfq_mq = {
 	.ops.mq = {
-		.get_rq_priv		= bfq_get_rq_private,
+		.prepare_request        = bfq_prepare_request,
 		.finish_request         = bfq_finish_request,
 		.exit_icq		= bfq_exit_icq,
 		.insert_requests	= bfq_insert_requests,

From 5a321acfce282c3e58ac63582faf6f928ad17f27 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Wed, 5 Jul 2017 12:43:22 +0200
Subject: [PATCH 32/51] Add list of bfq instances to documentation

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 Documentation/block/bfq-iosched.txt | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt
index 3d6951d63489..8ce6b9a9bacd 100644
--- a/Documentation/block/bfq-iosched.txt
+++ b/Documentation/block/bfq-iosched.txt
@@ -11,6 +11,15 @@ controllers), BFQ's main features are:
   groups (switching back to time distribution when needed to keep
   throughput high).
 
+If bfq-mq patches have been applied, then the following three
+instances of BFQ are available (otherwise only the first instance):
+- bfq: mainline version of BFQ, for blk-mq
+- bfq-mq: development version of BFQ for blk-mq; this version contains
+   also all latest features not yet landed in mainline, plus many
+   safety checks
+- bfq: BFQ for legacy blk; also this version contains both latest
+   features and safety checks
+
 In its default configuration, BFQ privileges latency over
 throughput. So, when needed for achieving a lower latency, BFQ builds
 schedules that may lead to a lower throughput. If your main or only
@@ -27,7 +36,7 @@ sequential I/O (e.g., 8-12 GB/s if I/O requests are 256 KB large), and
 to 120-200 MB/s with 4KB random I/O. BFQ is currently being tested on
 multi-queue devices too.
 
-The table of contents follow. Impatients can just jump to Section 3.
+The table of contents follows. Impatients can just jump to Section 3.
 
 CONTENTS
 

From 9f2e5b27227fd9254cc258572dc2d4531838c30b Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Wed, 5 Jul 2017 16:28:00 +0200
Subject: [PATCH 33/51] bfq-sq: fix prefix of names of cgroups parameters

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 Documentation/block/bfq-iosched.txt | 12 +++++++-----
 block/bfq-cgroup-included.c         |  2 +-
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt
index 8ce6b9a9bacd..965d82f94db9 100644
--- a/Documentation/block/bfq-iosched.txt
+++ b/Documentation/block/bfq-iosched.txt
@@ -503,10 +503,12 @@ To get proportional sharing of bandwidth with BFQ for a given device,
 BFQ must of course be the active scheduler for that device.
 
 Within each group directory, the names of the files associated with
-BFQ-specific cgroup parameters and stats begin with the "bfq."
-prefix. So, with cgroups-v1 or cgroups-v2, the full prefix for
-BFQ-specific files is "blkio.bfq." or "io.bfq." For example, the group
-parameter to set the weight of a group with BFQ is blkio.bfq.weight
+BFQ-specific cgroup parameters and stats begin with the "bfq.",
+"bfq-sq." or "bfq-mq." prefix, depending on which instance of bfq you
+want to use. So, with cgroups-v1 or cgroups-v2, the full prefix for
+BFQ-specific files is "blkio.bfqX." or "io.bfqX.", where X can be ""
+(i.e., null string), "-sq" or "-mq". For example, the group parameter
+to set the weight of a group with the mainline BFQ is blkio.bfq.weight
 or io.bfq.weight.
 
 Parameters to set
@@ -514,7 +516,7 @@ Parameters to set
 
 For each group, there is only the following parameter to set.
 
-weight (namely blkio.bfq.weight or io.bfq-weight): the weight of the
+weight (namely blkio.bfqX.weight or io.bfqX.weight): the weight of the
 group inside its parent. Available values: 1..10000 (default 100). The
 linear mapping between ioprio and weights, described at the beginning
 of the tunable section, is still valid, but all weights higher than
diff --git a/block/bfq-cgroup-included.c b/block/bfq-cgroup-included.c
index d903393ee78a..631e53d9150d 100644
--- a/block/bfq-cgroup-included.c
+++ b/block/bfq-cgroup-included.c
@@ -1124,7 +1124,7 @@ bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
 #ifdef BFQ_MQ
 #define BFQ_CGROUP_FNAME(param) "bfq-mq."#param
 #else
-#define BFQ_CGROUP_FNAME(param) "bfq."#param
+#define BFQ_CGROUP_FNAME(param) "bfq-sq."#param
 #endif
 
 static struct cftype bfq_blkcg_legacy_files[] = {

From 92b42df8166939ccf26aa450125b5b575cf6d505 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Wed, 5 Jul 2017 21:08:32 +0200
Subject: [PATCH 34/51] Add to documentation that bfq-mq and bfq-sq contain
 last fixes too

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 Documentation/block/bfq-iosched.txt | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt
index 965d82f94db9..0e59f1c9d30e 100644
--- a/Documentation/block/bfq-iosched.txt
+++ b/Documentation/block/bfq-iosched.txt
@@ -15,10 +15,10 @@ If bfq-mq patches have been applied, then the following three
 instances of BFQ are available (otherwise only the first instance):
 - bfq: mainline version of BFQ, for blk-mq
 - bfq-mq: development version of BFQ for blk-mq; this version contains
-   also all latest features not yet landed in mainline, plus many
+   also all latest features and fixes not yet landed in mainline, plus many
    safety checks
-- bfq: BFQ for legacy blk; also this version contains both latest
-   features and safety checks
+- bfq: BFQ for legacy blk; also this version contains latest features
+   and fixes, as well as safety checks
 
 In its default configuration, BFQ privileges latency over
 throughput. So, when needed for achieving a lower latency, BFQ builds

From 7f9bdd433b848d4f53c167258bf4d0b3f1ae1923 Mon Sep 17 00:00:00 2001
From: Lee Tibbert <lee.tibbert@gmail.com>
Date: Wed, 19 Jul 2017 10:28:32 -0400
Subject: [PATCH 35/51] Improve most frequently used no-logging path

This patch originated as a fix for compiler unused-variable warnings
issued when compiling bfq-mq with logging disabled (both
CONFIG_BLK_DEV_IO_TRACE and CONFIG_BFQ_REDIRECT_TO_CONSOLE
undefined).

It turns out to also have benefits for the bfq-sq path as well.

In most performance sensitive production builds blktrace_api logging
will probably be turned off, so it is worth making the no-logging path
compile without warnings. Any performance benefit is a bonus.

Thank you to T. B. on the bfq-iosched@googlegroups.com list
for ((void) (bfqq)) simplification/suggestion/improvement. All bugs
and unclear descriptions are my own doing.

The discussion below is based on the gcc compiler with optimization
level of at least 02.  Lower optimization levels are unlikely to
remove no-op instruction equivalents.

Provide three improvements in this likely case.

  1) Fix multiple occurrences of an unused-variable warning
     issued when compiling bfq-mq with no logging. The warning
     occurred each time the bfq_log_bfqg macro was expanded inside
     a code block such as the following snippet from
     block/bfq-sched.c, line 139 and few following, lightly edited for
     indentation in order to pass checkpatch.pl maximum line lengths.

else {
     struct bfq_group *bfqg =
             container_of(next_in_service,
                     struct bfq_group, entity);

     bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
             "update_next_in_service: chosen this entity");
     }

     Previously bfq-mq.h expanded bfq_log_bfqg to blk_add_trace_msg.
     When both bfq console logging and blktrace_api logging are
     disabled, include/linux/blktrace_api expands to
     do { } while (0), leaving the code block local variable unused.

     bfq_log_bfqq() had similar behavior but is never called with
     a potentially unused variable. This patch fixes that macro for
     consistency.

     bfq-sq.h (single queue) with blktrace_api enabled, and the bfq
     console logging macros have code paths which not trigger this
     warning.

     kernel.org (4.12 & 4.13) bfq (bfq-iosched.h) could trigger
     the warning but no code does so now. This patch fixes
     bfq-iosched.h for consistency.

     The style above enables a software engineering approach where
     complex expressions are moved to a local variable before the
     bfq_log* call.  This makes it easier to read the expression and
     use breakpoints to verify it. bfq-mq uses this approach in
     several places.

     New bfq_log* macros are provided for the no-logging case.
     I touch only the second argument, because current code never
     uses the local variable approach with the first or other
     arguments. I tried to balance consistency with simplicity.

  2) For bfq-sq, reduce to zero, the number of instructions executed
     when no logging is configured. No sense marshaling arguments
     which are never going to be used.

     On a trial V8R11 builds, this reduced the size of bfq-iosched.o
     by 14.3 KiB. The size went from 70304 to 55664 bytes.

     bfq-mq and kernel.org bfq code size does not change because
     existing macros already optimize to zero bytes when not logging.
     The current changes maintains consistency with the bfq-sq path
     and makes the bfq-mq & bfq no-logging paths resistant to future
     logging path macro changes which might cause generated code.

  3) Slightly reduce compile time of all bfq variants by including
     blktrace_api.h only when it will be used.

Signed-off-by: Lee Tibbert <lee.tibbert@gmail.com>
---
 block/bfq-mq.h | 18 +++++++++++++++++-
 block/bfq.h    | 18 +++++++++++++++++-
 2 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/block/bfq-mq.h b/block/bfq-mq.h
index 77ab0f22ed22..7ed2cc29be57 100644
--- a/block/bfq-mq.h
+++ b/block/bfq-mq.h
@@ -15,7 +15,6 @@
 #ifndef _BFQ_H
 #define _BFQ_H
 
-#include <linux/blktrace_api.h>
 #include <linux/hrtimer.h>
 #include <linux/blk-cgroup.h>
 
@@ -725,6 +724,21 @@ static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 		##args)
 
 #else /* CONFIG_BFQ_REDIRECT_TO_CONSOLE */
+
+#if !defined(CONFIG_BLK_DEV_IO_TRACE)
+
+/* Avoid possible "unused-variable" warning. See commit message. */
+
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	((void) (bfqq))
+
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)	((void) (bfqg))
+
+#define bfq_log(bfqd, fmt, args...)		do {} while (0)
+
+#else /* CONFIG_BLK_DEV_IO_TRACE */
+
+#include <linux/blktrace_api.h>
+
 #ifdef BFQ_GROUP_IOSCHED_ENABLED
 static struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
@@ -752,6 +766,8 @@ static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 
 #define bfq_log(bfqd, fmt, args...) \
 	blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)
+
+#endif /* CONFIG_BLK_DEV_IO_TRACE */
 #endif /* CONFIG_BFQ_REDIRECT_TO_CONSOLE */
 
 /* Expiration reasons. */
diff --git a/block/bfq.h b/block/bfq.h
index 53954d1b87f8..15d326f466b7 100644
--- a/block/bfq.h
+++ b/block/bfq.h
@@ -15,7 +15,6 @@
 #ifndef _BFQ_H
 #define _BFQ_H
 
-#include <linux/blktrace_api.h>
 #include <linux/hrtimer.h>
 #include <linux/blk-cgroup.h>
 
@@ -725,6 +724,21 @@ static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 		##args)
 
 #else /* CONFIG_BFQ_REDIRECT_TO_CONSOLE */
+
+#if !defined(CONFIG_BLK_DEV_IO_TRACE)
+
+/* Avoid possible "unused-variable" warning. See commit message. */
+
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	((void) (bfqq))
+
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)	((void) (bfqg))
+
+#define bfq_log(bfqd, fmt, args...)		do {} while (0)
+
+#else /* CONFIG_BLK_DEV_IO_TRACE */
+
+#include <linux/blktrace_api.h>
+
 #ifdef BFQ_GROUP_IOSCHED_ENABLED
 static struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
@@ -759,6 +773,8 @@ static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 
 #define bfq_log(bfqd, fmt, args...) \
 	blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)
+
+#endif /* CONFIG_BLK_DEV_IO_TRACE */
 #endif /* CONFIG_BFQ_REDIRECT_TO_CONSOLE */
 
 /* Expiration reasons. */

From f11a0e751e741bf94c6a48234824d50b3c0100ad Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Wed, 9 Aug 2017 16:40:39 +0200
Subject: [PATCH 36/51] bfq-sq: fix commit "Remove all get and put of I/O
 contexts" in branch bfq-mq

The commit "Remove all get and put of I/O contexts" erroneously removed
the reset of the field in_service_bic for bfq-sq. This commit re-adds
that missing reset.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-sched.c      | 7 +++++++
 block/bfq-sq-iosched.c | 1 +
 2 files changed, 8 insertions(+)

diff --git a/block/bfq-sched.c b/block/bfq-sched.c
index 9c4e6797d8c9..7425824c26b8 100644
--- a/block/bfq-sched.c
+++ b/block/bfq-sched.c
@@ -1904,6 +1904,13 @@ static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
 	struct bfq_entity *in_serv_entity = &in_serv_bfqq->entity;
 	struct bfq_entity *entity = in_serv_entity;
 
+#ifndef BFQ_MQ
+	if (bfqd->in_service_bic) {
+		put_io_context(bfqd->in_service_bic->icq.ioc);
+		bfqd->in_service_bic = NULL;
+	}
+#endif
+
 	bfq_clear_bfqq_wait_request(in_serv_bfqq);
 	hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
 	bfqd->in_service_queue = NULL;
diff --git a/block/bfq-sq-iosched.c b/block/bfq-sq-iosched.c
index 25da0d1c0622..e1960bf149d8 100644
--- a/block/bfq-sq-iosched.c
+++ b/block/bfq-sq-iosched.c
@@ -3765,6 +3765,7 @@ static int bfq_dispatch_request(struct bfq_data *bfqd,
 	if (!bfqd->in_service_bic) {
 		atomic_long_inc(&RQ_BIC(rq)->icq.ioc->refcount);
 		bfqd->in_service_bic = RQ_BIC(rq);
+		BUG_ON(!bfqd->in_service_bic);
 	}
 
 	if (bfqd->busy_queues > 1 && bfq_class_idle(bfqq))

From eceae5457530df8598557767d7be258ca9384de4 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Wed, 9 Aug 2017 22:29:01 +0200
Subject: [PATCH 37/51] bfq-sq-mq: make lookup_next_entity push up vtime on
 expirations

To provide a very smooth service, bfq starts to serve a bfq_queue
only if the queue is 'eligible', i.e., if the same queue would
have started to be served in the ideal, perfectly fair system that
bfq simulates internally. This is obtained by associating each
queue with a virtual start time, and by computing a special system
virtual time quantity: a queue is eligible only if the system
virtual time has reached the virtual start time of the
queue. Finally, bfq guarantees that, when a new queue must be set
in service, there is always at least one eligible entity for each
active parent entity in the scheduler. To provide this guarantee,
the function __bfq_lookup_next_entity pushes up, for each parent
entity on which it is invoked, the system virtual time to the
minimum among the virtual start times of the entities in the
active tree for the parent entity (more precisely, the push up
occurs if the system virtual time happens to be lower than all
such virtual start times).

There is however a circumstance in which __bfq_lookup_next_entity
cannot push up the system virtual time for a parent entity, even
if the system virtual time is lower than the virtual start times
of all the child entities in the active tree. It happens if one of
the child entities is in service. In fact, in such a case, there
is already an eligible entity, the in-service one, even if it may
not be not present in the active tree (because in-service entities
may be removed from the active tree).

Unfortunately, in the last re-design of the
hierarchical-scheduling engine, the reset of the pointer to the
in-service entity for a given parent entity--reset to be done as a
consequence of the expiration of the in-service entity--always
happens after the function __bfq_lookup_next_entity has been
invoked. This causes the function to think that there is still an
entity in service for the parent entity, and then that the system
virtual time cannot be pushed up, even if actually such a
no-more-in-service entity has already been properly reinserted
into the active tree (or in some other tree if no more
active). Yet, the system virtual time *had* to be pushed up, to be
ready to correctly choose the next queue to serve. Because of the
lack of this push up, bfq may wrongly set in service a queue that
had been speculatively pre-computed as the possible
next-in-service queue, but that would no more be the one to serve
after the expiration and the reinsertion into the active trees of
the previously in-service entities.

This commit addresses this issue by making
__bfq_lookup_next_entity properly push up the system virtual time
if an expiration is occurring.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c |  4 +--
 block/bfq-sched.c      | 77 ++++++++++++++++++++++++++++++++------------------
 block/bfq-sq-iosched.c |  4 +--
 3 files changed, 53 insertions(+), 32 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 49ffca1ad6e7..b5c848650375 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -682,7 +682,7 @@ static void bfq_updated_next_req(struct bfq_data *bfqd,
 		entity->budget = new_budget;
 		bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu",
 					 new_budget);
-		bfq_requeue_bfqq(bfqd, bfqq);
+		bfq_requeue_bfqq(bfqd, bfqq, false);
 	}
 }
 
@@ -2822,7 +2822,7 @@ static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 
 		bfq_del_bfqq_busy(bfqd, bfqq, true);
 	} else {
-		bfq_requeue_bfqq(bfqd, bfqq);
+		bfq_requeue_bfqq(bfqd, bfqq, true);
 		/*
 		 * Resort priority tree of potential close cooperators.
 		 */
diff --git a/block/bfq-sched.c b/block/bfq-sched.c
index 7425824c26b8..f3001af37256 100644
--- a/block/bfq-sched.c
+++ b/block/bfq-sched.c
@@ -33,7 +33,8 @@ static struct bfq_entity *bfq_root_active_entity(struct rb_root *tree)
 	return rb_entry(node, struct bfq_entity, rb_node);
 }
 
-static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd);
+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
+						 bool expiration);
 
 static bool bfq_update_parent_budget(struct bfq_entity *next_in_service);
 
@@ -43,6 +44,8 @@ static bool bfq_update_parent_budget(struct bfq_entity *next_in_service);
  * @new_entity: if not NULL, pointer to the entity whose activation,
  *		requeueing or repositionig triggered the invocation of
  *		this function.
+ * @expiration: id true, this function is being invoked after the
+ *		expiration of the in-service entity
  *
  * This function is called to update sd->next_in_service, which, in
  * its turn, may change as a consequence of the insertion or
@@ -61,7 +64,8 @@ static bool bfq_update_parent_budget(struct bfq_entity *next_in_service);
  * entity.
  */
 static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
-				       struct bfq_entity *new_entity)
+				       struct bfq_entity *new_entity,
+				       bool expiration)
 {
 	struct bfq_entity *next_in_service = sd->next_in_service;
 	struct bfq_queue *bfqq;
@@ -120,7 +124,7 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 		if (replace_next)
 			next_in_service = new_entity;
 	} else /* invoked because of a deactivation: lookup needed */
-		next_in_service = bfq_lookup_next_entity(sd);
+		next_in_service = bfq_lookup_next_entity(sd, expiration);
 
 	if (next_in_service) {
 		parent_sched_may_change = !sd->next_in_service ||
@@ -1291,10 +1295,12 @@ static void __bfq_activate_requeue_entity(struct bfq_entity *entity,
  * @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
+ * @expiration: true if this function is being invoked in the expiration path
+ *		of the in-service queue
  */
 static void bfq_activate_requeue_entity(struct bfq_entity *entity,
 					bool non_blocking_wait_rq,
-					bool requeue)
+					bool requeue, bool expiration)
 {
 	struct bfq_sched_data *sd;
 
@@ -1307,7 +1313,8 @@ static void bfq_activate_requeue_entity(struct bfq_entity *entity,
 		       RB_EMPTY_ROOT(&(sd->service_tree+1)->active) &&
 		       RB_EMPTY_ROOT(&(sd->service_tree+2)->active));
 
-		if (!bfq_update_next_in_service(sd, entity) && !requeue) {
+		if (!bfq_update_next_in_service(sd, entity, expiration) &&
+		    !requeue) {
 			BUG_ON(!sd->next_in_service);
 			break;
 		}
@@ -1373,6 +1380,8 @@ static bool __bfq_deactivate_entity(struct bfq_entity *entity,
  * 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 into the idle tree
+ * @expiration: true if this function is being invoked in the expiration path
+ *		of the in-service queue
  */
 static void bfq_deactivate_entity(struct bfq_entity *entity,
 				  bool ins_into_idle_tree,
@@ -1417,7 +1426,7 @@ static void bfq_deactivate_entity(struct bfq_entity *entity,
 			 * then, since entity has just been
 			 * deactivated, a new one must be found.
 			 */
-			bfq_update_next_in_service(sd, NULL);
+			bfq_update_next_in_service(sd, NULL, expiration);
 
 		if (sd->next_in_service || sd->in_service_entity) {
 			/*
@@ -1495,7 +1504,7 @@ static void bfq_deactivate_entity(struct bfq_entity *entity,
 				     "invoking udpdate_next for this entity");
 		}
 #endif
-		if (!bfq_update_next_in_service(sd, entity) &&
+		if (!bfq_update_next_in_service(sd, entity, expiration) &&
 		    !expiration)
 			/*
 			 * next_in_service unchanged or not causing
@@ -1524,7 +1533,7 @@ static u64 bfq_calc_vtime_jump(struct bfq_service_tree *st)
 		if (bfqq)
 			bfq_log_bfqq(bfqq->bfqd, bfqq,
 				     "calc_vtime_jump: new value %llu",
-				     root_entity->min_start);
+				     ((root_entity->min_start>>10)*1000)>>12);
 #ifdef BFQ_GROUP_IOSCHED_ENABLED
 		else {
 			struct bfq_group *bfqg =
@@ -1533,7 +1542,7 @@ static u64 bfq_calc_vtime_jump(struct bfq_service_tree *st)
 
 			bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
 				     "calc_vtime_jump: new value %llu",
-				     root_entity->min_start);
+				     ((root_entity->min_start>>10)*1000)>>12);
 		}
 #endif
 		return root_entity->min_start;
@@ -1615,17 +1624,9 @@ static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st,
  * 3) is idle.
  */
 static struct bfq_entity *
-__bfq_lookup_next_entity(struct bfq_service_tree *st, bool in_service
-#if 0
-			 , bool force
-#endif
-	)
+__bfq_lookup_next_entity(struct bfq_service_tree *st, bool in_service)
 {
-	struct bfq_entity *entity
-#if 0
-		, *new_next_in_service = NULL
-#endif
-		;
+	struct bfq_entity *entity;
 	u64 new_vtime;
 	struct bfq_queue *bfqq;
 
@@ -1667,8 +1668,9 @@ __bfq_lookup_next_entity(struct bfq_service_tree *st, bool in_service
 			container_of(entity, struct bfq_group, entity);
 
 		bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
-			     "__lookup_next: start %llu vtime %llu st %p",
+			     "__lookup_next: start %llu vtime %llu (%llu) st %p",
 			     ((entity->start>>10)*1000)>>12,
+			     ((st->vtime>>10)*1000)>>12,
 			     ((new_vtime>>10)*1000)>>12, st);
 	}
 #endif
@@ -1681,12 +1683,14 @@ __bfq_lookup_next_entity(struct bfq_service_tree *st, bool in_service
 /**
  * bfq_lookup_next_entity - return the first eligible entity in @sd.
  * @sd: the sched_data.
+ * @expiration: true if we are on the expiration path of the in-service queue
  *
  * 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.
+ * for sd, and we need to know what is the new next entity to serve
+ * after this change.
  */
-static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd)
+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
+						 bool expiration)
 {
 	struct bfq_service_tree *st = sd->service_tree;
 	struct bfq_service_tree *idle_class_st = st + (BFQ_IOPRIO_CLASSES - 1);
@@ -1716,8 +1720,24 @@ static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd)
 	 * class, unless the idle class needs to be served.
 	 */
 	for (; class_idx < BFQ_IOPRIO_CLASSES; class_idx++) {
+		/*
+		 * If expiration is true, then bfq_lookup_next_entity
+		 * is being invoked as a part of the expiration path
+		 * of the in-service queue. In this case, even if
+		 * sd->in_service_entity is not NULL,
+		 * sd->in_service_entiy at this point is actually not
+		 * in service any more, and, if needed, has already
+		 * been properly queued or requeued into the right
+		 * tree. The reason why sd->in_service_entity is still
+		 * not NULL here, even if expiration is true, is that
+		 * sd->in_service_entiy is reset as a last step in the
+		 * expiration path. So, if expiration is true, tell
+		 * __bfq_lookup_next_entity that there is no
+		 * sd->in_service_entity.
+		 */
 		entity = __bfq_lookup_next_entity(st + class_idx,
-						  sd->in_service_entity);
+						  sd->in_service_entity &&
+						  !expiration);
 
 		if (entity)
 			break;
@@ -1891,7 +1911,7 @@ static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
 	for_each_entity(entity) {
 		struct bfq_sched_data *sd = entity->sched_data;
 
-		if(!bfq_update_next_in_service(sd, NULL))
+		if (!bfq_update_next_in_service(sd, NULL, false))
 			break;
 	}
 
@@ -1951,16 +1971,17 @@ static void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 	       entity->on_st);
 
 	bfq_activate_requeue_entity(entity, bfq_bfqq_non_blocking_wait_rq(bfqq),
-				    false);
+				    false, false);
 	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
 }
 
-static void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+static void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			     bool expiration)
 {
 	struct bfq_entity *entity = &bfqq->entity;
 
 	bfq_activate_requeue_entity(entity, false,
-				    bfqq == bfqd->in_service_queue);
+				    bfqq == bfqd->in_service_queue, expiration);
 }
 
 static void bfqg_stats_update_dequeue(struct bfq_group *bfqg);
diff --git a/block/bfq-sq-iosched.c b/block/bfq-sq-iosched.c
index e1960bf149d8..42393ab889a9 100644
--- a/block/bfq-sq-iosched.c
+++ b/block/bfq-sq-iosched.c
@@ -644,7 +644,7 @@ static void bfq_updated_next_req(struct bfq_data *bfqd,
 		entity->budget = new_budget;
 		bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu",
 					 new_budget);
-		bfq_requeue_bfqq(bfqd, bfqq);
+		bfq_requeue_bfqq(bfqd, bfqq, false);
 	}
 }
 
@@ -2715,7 +2715,7 @@ static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 
 		bfq_del_bfqq_busy(bfqd, bfqq, true);
 	} else {
-		bfq_requeue_bfqq(bfqd, bfqq);
+		bfq_requeue_bfqq(bfqd, bfqq, true);
 		/*
 		 * Resort priority tree of potential close cooperators.
 		 */

From ee9f95b24e1d88ffba4845981c2a4684aefd0245 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Wed, 9 Aug 2017 22:53:00 +0200
Subject: [PATCH 38/51] bfq-sq-mq: remove direct switch to an entity in higher
 class

If the function bfq_update_next_in_service is invoked as a consequence
of the activation or requeueing of an entity, say E, and finds out
that E belongs to a higher-priority class than that of the current
next-in-service entity, then it sets next_in_service directly to
E. But this may lead to anomalous schedules, because E may happen not
be eligible for service, because its virtual start time is higher than
the system virtual time for its service tree.

This commit addresses this issue by simply removing this direct
switch.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-sched.c | 19 +++++--------------
 1 file changed, 5 insertions(+), 14 deletions(-)

diff --git a/block/bfq-sched.c b/block/bfq-sched.c
index f3001af37256..b1a59088db88 100644
--- a/block/bfq-sched.c
+++ b/block/bfq-sched.c
@@ -76,9 +76,8 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 	 * 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
+	 * just-modified entity 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.
@@ -94,9 +93,8 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 
 		/*
 		 * 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.
+		 * entity, then compare timestamps to decide whether
+		 * to replace sd->service_tree with new_entity.
 		 */
 		if (next_in_service) {
 			unsigned int new_entity_class_idx =
@@ -104,10 +102,6 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 			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)
@@ -115,10 +109,7 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 				 !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);
+					new_entity->finish));
 		}
 
 		if (replace_next)

From a3fdc5af40537355b68c1f0d3997c5a5fb54b9ce Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Thu, 10 Aug 2017 08:15:50 +0200
Subject: [PATCH 39/51] bfq-sq-mq: guarantee update_next_in_service always
 returns an eligible entity

If the function bfq_update_next_in_service is invoked as a consequence
of the activation or requeueing of an entity, say E, then it doesn't
invoke bfq_lookup_next_entity to get the next-in-service entity. In
contrast, it follows a shorter path: if E happens to be eligible (see
commit "bfq-sq-mq: make lookup_next_entity push up vtime on
expirations" for details on eligibility) and to have a lower virtual
finish time than the current candidate as next-in-service entity, then
E directly becomes the next-in-service entity. Unfortunately, there is
a corner case for which this shorter path makes
bfq_update_next_in_service choose a non eligible entity: it occurs if
both E and the current next-in-service entity happen to be non
eligible when bfq_update_next_in_service is invoked. In this case, E
is not set as next-in-service, and, since bfq_lookup_next_entity is
not invoked, the state of the parent entity is not updated so as to
end up with an eligible entity as the proper next-in-service entity.

In this respect, next-in-service is actually allowed to be non
eligible while some queue is in service: since no system-virtual-time
push-up can be performed in that case (see again commit "bfq-sq-mq:
make lookup_next_entity push up vtime on expirations" for details),
next-in-service is chosen, speculatively, as a function of the
possible value that the system virtual time may get after a push
up. But the correctness of the schedule breaks if next-in-service is
still a non eligible entity when it is time to set in service the next
entity. Unfortunately, this may happen in the above corner case.

This commit fixes this problem by making bfq_update_next_in_service
invoke bfq_lookup_next_entity not only if the above shorter path
cannot be taken, but also if the shorter path is taken but fails to
yield an eligible next-in-service entity.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-sched.c | 38 ++++++++++++++++++++++++++++----------
 1 file changed, 28 insertions(+), 10 deletions(-)

diff --git a/block/bfq-sched.c b/block/bfq-sched.c
index b1a59088db88..e4a2553a2d2c 100644
--- a/block/bfq-sched.c
+++ b/block/bfq-sched.c
@@ -70,6 +70,7 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 	struct bfq_entity *next_in_service = sd->next_in_service;
 	struct bfq_queue *bfqq;
 	bool parent_sched_may_change = false;
+	bool change_without_lookup = false;
 
 	/*
 	 * If this update is triggered by the activation, requeueing
@@ -89,7 +90,7 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 		 * set to true, and left as true if
 		 * sd->next_in_service is NULL.
 		 */
-		bool replace_next = true;
+		change_without_lookup = true;
 
 		/*
 		 * If there is already a next_in_service candidate
@@ -102,7 +103,7 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 			struct bfq_service_tree *st =
 				sd->service_tree + new_entity_class_idx;
 
-			replace_next =
+			change_without_lookup =
 				(new_entity_class_idx ==
 				 bfq_class_idx(next_in_service)
 				 &&
@@ -112,15 +113,32 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 					new_entity->finish));
 		}
 
-		if (replace_next)
+		if (change_without_lookup) {
 			next_in_service = new_entity;
-	} else /* invoked because of a deactivation: lookup needed */
+			bfqq = bfq_entity_to_bfqq(next_in_service);
+
+			if (bfqq)
+				bfq_log_bfqq(bfqq->bfqd, bfqq,
+				"update_next_in_service: chose without lookup");
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+			else {
+				struct bfq_group *bfqg =
+					container_of(next_in_service,
+						     struct bfq_group, entity);
+
+				bfq_log_bfqg((struct bfq_data*)bfqg->bfqd, bfqg,
+				"update_next_in_service: chose without lookup");
+			}
+#endif
+		}
+	}
+
+	if (!change_without_lookup) /* lookup needed */
 		next_in_service = bfq_lookup_next_entity(sd, expiration);
 
-	if (next_in_service) {
+	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;
 
@@ -1053,7 +1071,7 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
 
 		if (bfqq) {
 			bfq_log_bfqq(bfqq->bfqd, bfqq,
-				     "__activate_entity: new queue finish %llu",
+				     "update_fin_time_enqueue: new queue finish %llu",
 				     ((entity->finish>>10)*1000)>>12);
 #ifdef BFQ_GROUP_IOSCHED_ENABLED
 		} else {
@@ -1061,7 +1079,7 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
 				container_of(entity, struct bfq_group, entity);
 
 			bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
-				     "__activate_entity: new group finish %llu",
+				     "update_fin_time_enqueue: new group finish %llu",
 				     ((entity->finish>>10)*1000)>>12);
 #endif
 		}
@@ -1071,7 +1089,7 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
 
 	if (bfqq) {
 		bfq_log_bfqq(bfqq->bfqd, bfqq,
-			"__activate_entity: queue %seligible in st %p",
+			"update_fin_time_enqueue: queue %seligible in st %p",
 			     entity->start <= st->vtime ? "" : "non ", st);
 #ifdef BFQ_GROUP_IOSCHED_ENABLED
 	} else {
@@ -1079,7 +1097,7 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
 			container_of(entity, struct bfq_group, entity);
 
 		bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg,
-			"__activate_entity: group %seligible in st %p",
+			"update_fin_time_enqueue: group %seligible in st %p",
 			     entity->start <= st->vtime ? "" : "non ", st);
 #endif
 	}

From 6565e4d1aac029b6f0a5d86a4c6ef38608838eac Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Thu, 31 Aug 2017 19:24:26 +0200
Subject: [PATCH 40/51] doc, block, bfq: fix some typos and stale sentences

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Reviewed-by: Jeremy Hickman <jeremywh7@gmail.com>
Reviewed-by: Laurentiu Nicola <lnicola@dend.ro>
---
 Documentation/block/bfq-iosched.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt
index 0e59f1c9d30e..dcfe15523da3 100644
--- a/Documentation/block/bfq-iosched.txt
+++ b/Documentation/block/bfq-iosched.txt
@@ -17,7 +17,7 @@ instances of BFQ are available (otherwise only the first instance):
 - bfq-mq: development version of BFQ for blk-mq; this version contains
    also all latest features and fixes not yet landed in mainline, plus many
    safety checks
-- bfq: BFQ for legacy blk; also this version contains latest features
+- bfq-sq: BFQ for legacy blk; also this version contains latest features
    and fixes, as well as safety checks
 
 In its default configuration, BFQ privileges latency over

From 261ee8cc9f43e03d790a07184f0bcaa504ee6737 Mon Sep 17 00:00:00 2001
From: Luca Miccio <lucmiccio@gmail.com>
Date: Wed, 13 Sep 2017 12:03:56 +0200
Subject: [PATCH 41/51] bfq-mq, bfq-sq: Disable writeback throttling

Similarly to CFQ, BFQ has its write-throttling heuristics, and it
is better not to combine them with further write-throttling
heuristics of a different nature.
So this commit disables write-back throttling for a device if BFQ
is used as I/O scheduler for that device.

Signed-off-by: Luca Miccio <lucmiccio@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
---
 block/bfq-mq-iosched.c | 2 ++
 block/bfq-sq-iosched.c | 7 +++++++
 2 files changed, 9 insertions(+)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index b5c848650375..7d27d5b3befb 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -89,6 +89,7 @@
 #include "blk-mq-tag.h"
 #include "blk-mq-sched.h"
 #include "bfq-mq.h"
+#include "blk-wbt.h"
 
 /* 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 };
@@ -5260,6 +5261,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	bfq_init_root_group(bfqd->root_group, bfqd);
 	bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group);
 
+	wbt_disable_default(q);
 	return 0;
 
 out_free:
diff --git a/block/bfq-sq-iosched.c b/block/bfq-sq-iosched.c
index 42393ab889a9..6fdc3b1d5bb8 100644
--- a/block/bfq-sq-iosched.c
+++ b/block/bfq-sq-iosched.c
@@ -83,6 +83,7 @@
 #include <linux/ioprio.h>
 #include "blk.h"
 #include "bfq.h"
+#include "blk-wbt.h"
 
 /* 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 };
@@ -4976,6 +4977,11 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	return -ENOMEM;
 }
 
+static void bfq_registered_queue(struct request_queue *q)
+{
+	wbt_disable_default(q);
+}
+
 static void bfq_slab_kill(void)
 {
 	kmem_cache_destroy(bfq_pool);
@@ -5285,6 +5291,7 @@ static struct elevator_type iosched_bfq = {
 		.elevator_may_queue_fn =	bfq_may_queue,
 		.elevator_init_fn =		bfq_init_queue,
 		.elevator_exit_fn =		bfq_exit_queue,
+		.elevator_registered_fn =	bfq_registered_queue,
 	},
 	.icq_size =		sizeof(struct bfq_io_cq),
 	.icq_align =		__alignof__(struct bfq_io_cq),

From 40ea0aed088791da27fcfa51f3b64d1f96b0d06e Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Tue, 12 Sep 2017 16:45:53 +0200
Subject: [PATCH 42/51] bfq-mq, bfq-sq: fix wrong init of saved start time for
 weight raising

This commit fixes a bug that causes bfq to fail to guarantee a high
responsiveness on some drives, if there is heavy random read+write I/O
in the background. More precisely, such a failure allowed this bug to
be found [1], but the bug may well cause other yet unreported
anomalies.

BFQ raises the weight of the bfq_queues associated with soft real-time
applications, to privilege the I/O, and thus reduce latency, for these
applications. This mechanism is named soft-real-time weight raising in
BFQ. A soft real-time period may happen to be nested into an
interactive weight raising period, i.e., it may happen that, when a
bfq_queue switches to a soft real-time weight-raised state, the
bfq_queue is already being weight-raised because deemed interactive
too. In this case, BFQ saves in a special variable
wr_start_at_switch_to_srt, the time instant when the interactive
weight-raising period started for the bfq_queue, i.e., the time
instant when BFQ started to deem the bfq_queue interactive. This value
is then used to check whether the interactive weight-raising period
would still be in progress when the soft real-time weight-raising
period ends.  If so, interactive weight raising is restored for the
bfq_queue. This restore is useful, in particular, because it prevents
bfq_queues from losing their interactive weight raising prematurely,
as a consequence of spurious, short-lived soft real-time
weight-raising periods caused by wrong detections as soft real-time.

If, instead, a bfq_queue switches to soft-real-time weight raising
while it *is not* already in an interactive weight-raising period,
then the variable wr_start_at_switch_to_srt has no meaning during the
following soft real-time weight-raising period. Unfortunately the
handling of this case is wrong in BFQ: not only the variable is not
flagged somehow as meaningless, but it is also set to the time when
the switch to soft real-time weight-raising occurs. This may cause an
interactive weight-raising period to be considered mistakenly as still
in progress, and thus a spurious interactive weight-raising period to
start for the bfq_queue, at the end of the soft-real-time
weight-raising period. In particular the spurious interactive
weight-raising period will be considered as still in progress, if the
soft-real-time weight-raising period does not last very long. The
bfq_queue will then be wrongly privileged and, if I/O bound, will
unjustly steal bandwidth to truly interactive or soft real-time
bfq_queues, harming responsiveness and low latency.

This commit fixes this issue by just setting wr_start_at_switch_to_srt
to minus infinity (farthest past time instant according to jiffies
macros): when the soft-real-time weight-raising period ends, certainly
no interactive weight-raising period will be considered as still in
progress.

[1] Background I/O Type: Random - Background I/O mix: Reads and writes
- Application to start: LibreOffice Writer in
http://www.phoronix.com/scan.php?page=news_item&px=Linux-4.13-IO-Laptop

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Angelo Ruocco <angeloruocco90@gmail.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Tested-by: Lee Tibbert <lee.tibbert@gmail.com>
Tested-by: Mirko Montanari <mirkomontanari91@gmail.com>
---
 block/bfq-mq-iosched.c | 50 +++++++++++++++++++++++++++++++-------------------
 block/bfq-sq-iosched.c | 50 +++++++++++++++++++++++++++++++-------------------
 2 files changed, 62 insertions(+), 38 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 7d27d5b3befb..f378519b6d33 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -1204,6 +1204,24 @@ static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
 	return wr_or_deserves_wr;
 }
 
+/*
+ * Return the farthest future time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_greatest_from_now(void)
+{
+	return jiffies + MAX_JIFFY_OFFSET;
+}
+
+/*
+ * Return the farthest past time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_smallest_from_now(void)
+{
+	return jiffies - MAX_JIFFY_OFFSET;
+}
+
 static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
 					     struct bfq_queue *bfqq,
 					     unsigned int old_wr_coeff,
@@ -1218,7 +1236,19 @@ static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
 			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
 			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
 		} else {
-			bfqq->wr_start_at_switch_to_srt = jiffies;
+			/*
+			 * No interactive weight raising in progress
+			 * here: assign minus infinity to
+			 * wr_start_at_switch_to_srt, to make sure
+			 * that, at the end of the soft-real-time
+			 * weight raising periods that is starting
+			 * now, no interactive weight-raising period
+			 * may be wrongly considered as still in
+			 * progress (and thus actually started by
+			 * mistake).
+			 */
+			bfqq->wr_start_at_switch_to_srt =
+				bfq_smallest_from_now();
 			bfqq->wr_coeff = bfqd->bfq_wr_coeff *
 				BFQ_SOFTRT_WEIGHT_FACTOR;
 			bfqq->wr_cur_max_time =
@@ -3174,24 +3204,6 @@ static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
 		   jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
 }
 
-/*
- * Return the farthest future time instant according to jiffies
- * macros.
- */
-static unsigned long bfq_greatest_from_now(void)
-{
-	return jiffies + MAX_JIFFY_OFFSET;
-}
-
-/*
- * 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.
diff --git a/block/bfq-sq-iosched.c b/block/bfq-sq-iosched.c
index 6fdc3b1d5bb8..f4654436cd55 100644
--- a/block/bfq-sq-iosched.c
+++ b/block/bfq-sq-iosched.c
@@ -1165,6 +1165,24 @@ static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
 	return wr_or_deserves_wr;
 }
 
+/*
+ * Return the farthest future time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_greatest_from_now(void)
+{
+	return jiffies + MAX_JIFFY_OFFSET;
+}
+
+/*
+ * Return the farthest past time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_smallest_from_now(void)
+{
+	return jiffies - MAX_JIFFY_OFFSET;
+}
+
 static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
 					     struct bfq_queue *bfqq,
 					     unsigned int old_wr_coeff,
@@ -1179,7 +1197,19 @@ static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
 			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
 			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
 		} else {
-			bfqq->wr_start_at_switch_to_srt = jiffies;
+			/*
+			 * No interactive weight raising in progress
+			 * here: assign minus infinity to
+			 * wr_start_at_switch_to_srt, to make sure
+			 * that, at the end of the soft-real-time
+			 * weight raising periods that is starting
+			 * now, no interactive weight-raising period
+			 * may be wrongly considered as still in
+			 * progress (and thus actually started by
+			 * mistake).
+			 */
+			bfqq->wr_start_at_switch_to_srt =
+				bfq_smallest_from_now();
 			bfqq->wr_coeff = bfqd->bfq_wr_coeff *
 				BFQ_SOFTRT_WEIGHT_FACTOR;
 			bfqq->wr_cur_max_time =
@@ -3067,24 +3097,6 @@ static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
 		   jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
 }
 
-/*
- * Return the farthest future time instant according to jiffies
- * macros.
- */
-static unsigned long bfq_greatest_from_now(void)
-{
-	return jiffies + MAX_JIFFY_OFFSET;
-}
-
-/*
- * 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.

From 9dbea44b6f721baeff35b9fdf628ec55fe00e09d Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Thu, 14 Sep 2017 05:12:58 -0400
Subject: [PATCH 43/51] Fix commit "Unnest request-queue and ioc locks from
 scheduler locks"

The commit "Unnest request-queue and ioc locks from scheduler locks"
mistakenly removed the setting of the split flag in function
bfq_prepare_request. This commit puts this missing instruction back in
its place.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 block/bfq-mq-iosched.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index f378519b6d33..288078e68a2a 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -744,6 +744,12 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 	bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time;
 	BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish));
 
+	bfq_log_bfqq(bfqq->bfqd, bfqq,
+		     "[%s] bic %p wr_coeff %d start_finish %lu max_time %lu",
+		     __func__,
+		     bic, bfqq->wr_coeff, bfqq->last_wr_start_finish,
+		     bfqq->wr_cur_max_time);
+
 	if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
 				   time_is_before_jiffies(bfqq->last_wr_start_finish +
 							  bfqq->wr_cur_max_time))) {
@@ -2208,6 +2214,11 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
 	bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
 	BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish));
+	bfq_log_bfqq(bfqq->bfqd, bfqq,
+		     "[%s] bic %p wr_coeff %d start_finish %lu max_time %lu",
+		     __func__,
+		     bic, bfqq->wr_coeff, bfqq->last_wr_start_finish,
+		     bfqq->wr_cur_max_time);
 }
 
 static void
@@ -4950,6 +4961,7 @@ static void bfq_prepare_request(struct request *rq, struct bio *bio)
 				bic->saved_in_large_burst = true;
 
 			bfqq = bfq_split_bfqq(bic, bfqq);
+			split = true;
 
 			if (!bfqq)
 				bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,

From d4ebb2a66a23dc183792088c521f2be2193b56db Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Fri, 15 Sep 2017 01:53:51 -0400
Subject: [PATCH 44/51] bfq-sq, bfq-mq: check and switch back to interactive wr
 also on queue split

As already explained in the message of commit "bfq-mq, bfq-sq: fix
wrong init of saved start time for weight raising", if a soft
real-time weight-raising period happens to be nested in a larger
interactive weight-raising period, then BFQ restores the interactive
weight raising at the end of the soft real-time weight raising. In
particular, BFQ checks whether the latter has ended only on request
dispatches.

Unfortunately, the above scheme fails to restore interactive weight
raising in the following corner case: if a bfq_queue, say Q,
1) Is merged with another bfq_queue while it is in a nested soft
real-time weight-raising period. The weight-raising state of Q is
then saved, and not considered any longer until a split occurs.
2) Is split from the other bfq_queue(s) at a time instant when its
soft real-time weight raising is already finished.
On the split, while resuming the previous, soft real-time
weight-raised state of the bfq_queue Q, BFQ checks whether the
current soft real-time weight-raising period is actually over. If so,
BFQ switches weight raising off for Q, *without* checking whether the
soft real-time period was actually nested in a non-yet-finished
interactive weight-raising period.

This commit addresses this issue by adding the above missing check in
bfq_queue splits, and restoring interactive weight raising if needed.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Angelo Ruocco <angeloruocco90@gmail.com>
Tested-by: Mirko Montanari <mirkomontanari91@gmail.com>
---
 block/bfq-mq-iosched.c | 29 +++++++++++++++++++++--------
 block/bfq-sq-iosched.c | 35 +++++++++++++++++++++++++++--------
 2 files changed, 48 insertions(+), 16 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 288078e68a2a..6130a95c6497 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -716,6 +716,15 @@ static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
 	return dur;
 }
 
+/* switch back from soft real-time to interactive weight raising */
+static void switch_back_to_interactive_wr(struct bfq_queue *bfqq,
+					  struct bfq_data *bfqd)
+{
+	bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+	bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+	bfqq->last_wr_start_finish = bfqq->wr_start_at_switch_to_srt;
+}
+
 static void
 bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 		      struct bfq_io_cq *bic, bool bfq_already_existing)
@@ -753,12 +762,20 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 	if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
 				   time_is_before_jiffies(bfqq->last_wr_start_finish +
 							  bfqq->wr_cur_max_time))) {
-		bfq_log_bfqq(bfqq->bfqd, bfqq,
+		if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
+		    !bfq_bfqq_in_large_burst(bfqq) &&
+		    time_is_after_eq_jiffies(bfqq->wr_start_at_switch_to_srt +
+					     bfq_wr_duration(bfqd))) {
+			switch_back_to_interactive_wr(bfqq, bfqd);
+			bfq_log_bfqq(bfqq->bfqd, bfqq,
+			     "resume state: switching back to interactive");
+		} else {
+			bfqq->wr_coeff = 1;
+			bfq_log_bfqq(bfqq->bfqd, bfqq,
 			     "resume state: switching off wr (%lu + %lu < %lu)",
 			     bfqq->last_wr_start_finish, bfqq->wr_cur_max_time,
 			     jiffies);
-
-		bfqq->wr_coeff = 1;
+		}
 	}
 
 	/* make sure weight will be updated, however we got here */
@@ -3820,11 +3837,7 @@ static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 					bfq_wr_duration(bfqd)))
 				bfq_bfqq_end_wr(bfqq);
 			else {
-				/* switch back to interactive wr */
-				bfqq->wr_coeff = bfqd->bfq_wr_coeff;
-				bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
-				bfqq->last_wr_start_finish =
-					bfqq->wr_start_at_switch_to_srt;
+				switch_back_to_interactive_wr(bfqq, bfqd);
 				BUG_ON(time_is_after_jiffies(
 					       bfqq->last_wr_start_finish));
 				bfqq->entity.prio_changed = 1;
diff --git a/block/bfq-sq-iosched.c b/block/bfq-sq-iosched.c
index f4654436cd55..e07d5d1c0d40 100644
--- a/block/bfq-sq-iosched.c
+++ b/block/bfq-sq-iosched.c
@@ -678,6 +678,15 @@ static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
 	return dur;
 }
 
+/* switch back from soft real-time to interactive weight raising */
+static void switch_back_to_interactive_wr(struct bfq_queue *bfqq,
+					  struct bfq_data *bfqd)
+{
+	bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+	bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+	bfqq->last_wr_start_finish = bfqq->wr_start_at_switch_to_srt;
+}
+
 static void
 bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 		      struct bfq_io_cq *bic, bool bfq_already_existing)
@@ -705,15 +714,29 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 	bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time;
 	BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish));
 
+	bfq_log_bfqq(bfqq->bfqd, bfqq,
+		     "[%s] bic %p wr_coeff %d start_finish %lu max_time %lu",
+		     __func__,
+		     bic, bfqq->wr_coeff, bfqq->last_wr_start_finish,
+		     bfqq->wr_cur_max_time);
+
 	if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
 				   time_is_before_jiffies(bfqq->last_wr_start_finish +
 							  bfqq->wr_cur_max_time))) {
-		bfq_log_bfqq(bfqq->bfqd, bfqq,
+		if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
+		    !bfq_bfqq_in_large_burst(bfqq) &&
+		    time_is_after_eq_jiffies(bfqq->wr_start_at_switch_to_srt +
+					     bfq_wr_duration(bfqd))) {
+			switch_back_to_interactive_wr(bfqq, bfqd);
+			bfq_log_bfqq(bfqq->bfqd, bfqq,
+			     "resume state: switching back to interactive");
+		} else {
+			bfqq->wr_coeff = 1;
+			bfq_log_bfqq(bfqq->bfqd, bfqq,
 			     "resume state: switching off wr (%lu + %lu < %lu)",
 			     bfqq->last_wr_start_finish, bfqq->wr_cur_max_time,
 			     jiffies);
-
-		bfqq->wr_coeff = 1;
+		}
 	}
 
 	/* make sure weight will be updated, however we got here */
@@ -3703,11 +3726,7 @@ static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 					bfq_wr_duration(bfqd)))
 				bfq_bfqq_end_wr(bfqq);
 			else {
-				/* switch back to interactive wr */
-				bfqq->wr_coeff = bfqd->bfq_wr_coeff;
-				bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
-				bfqq->last_wr_start_finish =
-					bfqq->wr_start_at_switch_to_srt;
+				switch_back_to_interactive_wr(bfqq, bfqd);
 				BUG_ON(time_is_after_jiffies(
 					       bfqq->last_wr_start_finish));
 				bfqq->entity.prio_changed = 1;

From 9eaec0c3a2d675763b09da81c9117a9c43bce942 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Fri, 15 Sep 2017 04:58:33 -0400
Subject: [PATCH 45/51] bfq-sq, bfq-mq: let early-merged queues be
 weight-raised on split too

A just-created bfq_queue, say Q, may happen to be merged with another
bfq_queue on the very first invocation of the function
__bfq_insert_request. In such a case, even if Q would clearly deserve
interactive weight raising (as it has just been created), the function
bfq_add_request does not make it to be invoked for Q, and thus to
activate weight raising for Q. As a consequence, when the state of Q
is saved for a possible future restore, after a split of Q from the
other bfq_queue(s), such a state happens to be (unjustly)
non-weight-raised. Then the bfq_queue will not enjoy any weight
raising on the split, even if should still be in an interactive
weight-raising period when the split occurs.

This commit solves this problem as follows, for a just-created
bfq_queue that is being early-merged: it stores directly, in the saved
state of the bfq_queue, the weight-raising state that would have been
assigned to the bfq_queue if not early-merged.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Angelo Ruocco <angeloruocco90@gmail.com>
Tested-by: Mirko Montanari <mirkomontanari91@gmail.com>
---
 block/bfq-mq-iosched.c | 28 +++++++++++++++++++++++-----
 block/bfq-sq-iosched.c | 28 +++++++++++++++++++++++-----
 2 files changed, 46 insertions(+), 10 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 6130a95c6497..af84e506e897 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -2226,10 +2226,27 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
 	bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
 	bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
-	bic->saved_wr_coeff = bfqq->wr_coeff;
-	bic->saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt;
-	bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
-	bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
+	if (unlikely(bfq_bfqq_just_created(bfqq) &&
+		     !bfq_bfqq_in_large_burst(bfqq))) {
+		/*
+		 * bfqq being merged ritgh after being created: bfqq
+		 * would have deserved interactive weight raising, but
+		 * did not make it to be set in a weight-raised state,
+		 * because of this early merge.  Store directly the
+		 * weight-raising state that would have been assigned
+		 * to bfqq, so that to avoid that bfqq unjustly fails
+		 * to enjoy weight raising if split soon.
+		 */
+		bic->saved_wr_coeff = bfqq->bfqd->bfq_wr_coeff;
+		bic->saved_wr_cur_max_time = bfq_wr_duration(bfqq->bfqd);
+		bic->saved_last_wr_start_finish = jiffies;
+	} else {
+		bic->saved_wr_coeff = bfqq->wr_coeff;
+		bic->saved_wr_start_at_switch_to_srt =
+			bfqq->wr_start_at_switch_to_srt;
+		bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
+		bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
+	}
 	BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish));
 	bfq_log_bfqq(bfqq->bfqd, bfqq,
 		     "[%s] bic %p wr_coeff %d start_finish %lu max_time %lu",
@@ -4560,7 +4577,6 @@ static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 				     bfqq->allocated);
 
 			new_bfqq->ref++;
-			bfq_clear_bfqq_just_created(bfqq);
 			/*
 			 * If the bic associated with the process
 			 * issuing this request still points to bfqq
@@ -4572,6 +4588,8 @@ static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 			if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
 				bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
 						bfqq, new_bfqq);
+
+			bfq_clear_bfqq_just_created(bfqq);
 			/*
 			 * rq is about to be enqueued into new_bfqq,
 			 * release rq reference on bfqq
diff --git a/block/bfq-sq-iosched.c b/block/bfq-sq-iosched.c
index e07d5d1c0d40..0c48f527fe3f 100644
--- a/block/bfq-sq-iosched.c
+++ b/block/bfq-sq-iosched.c
@@ -2105,10 +2105,27 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
 	bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
 	bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
-	bic->saved_wr_coeff = bfqq->wr_coeff;
-	bic->saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt;
-	bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
-	bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
+	if (unlikely(bfq_bfqq_just_created(bfqq) &&
+		     !bfq_bfqq_in_large_burst(bfqq))) {
+		/*
+		 * bfqq being merged ritgh after being created: bfqq
+		 * would have deserved interactive weight raising, but
+		 * did not make it to be set in a weight-raised state,
+		 * because of this early merge.	Store directly the
+		 * weight-raising state that would have been assigned
+		 * to bfqq, so that to avoid that bfqq unjustly fails
+		 * to enjoy weight raising if split soon.
+		 */
+		bic->saved_wr_coeff = bfqq->bfqd->bfq_wr_coeff;
+		bic->saved_wr_cur_max_time = bfq_wr_duration(bfqq->bfqd);
+		bic->saved_last_wr_start_finish = jiffies;
+	} else {
+		bic->saved_wr_coeff = bfqq->wr_coeff;
+		bic->saved_wr_start_at_switch_to_srt =
+			bfqq->wr_start_at_switch_to_srt;
+		bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
+		bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
+	}
 	BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish));
 }
 
@@ -4383,10 +4400,11 @@ static void bfq_insert_request(struct request_queue *q, struct request *rq)
 			new_bfqq->allocated[rq_data_dir(rq)]++;
 			bfqq->allocated[rq_data_dir(rq)]--;
 			new_bfqq->ref++;
-			bfq_clear_bfqq_just_created(bfqq);
 			if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
 				bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
 						bfqq, new_bfqq);
+
+			bfq_clear_bfqq_just_created(bfqq);
 			/*
 			 * rq is about to be enqueued into new_bfqq,
 			 * release rq reference on bfqq

From cb05150675095cb97ab22e4955eb82e4fe2e9dbe Mon Sep 17 00:00:00 2001
From: omcira <omcira@gmail.com>
Date: Mon, 18 Sep 2017 10:49:48 +0200
Subject: [PATCH 46/51] bfq-sq, bfq-mq: decrease burst size when queues in
 burst exit

If many queues belonging to the same group happen to be created
shortly after each other, then the concurrent processes associated
with these queues have typically a common goal, and they get it done
as soon as possible if not hampered by device idling.  Examples are
processes spawned by git grep, or by systemd during boot. As for
device idling, this mechanism is currently necessary for weight
raising to succeed in its goal: privileging I/O.  In view of these
facts, BFQ does not provide the above queues with either weight
raising or device idling.

On the other hand, a burst of queue creations may be caused also by
the start-up of a complex application. In this case, these queues need
usually to be served one after the other, and as quickly as possible,
to maximise responsiveness. Therefore, in this case the best strategy
is to weight-raise all the queues created during the burst, i.e., the
exact opposite of the strategy for the above case.

To distinguish between the two cases, BFQ uses an empirical burst-size
threshold, found through extensive tests and monitoring of daily
usage. Only large bursts, i.e., burst with a size above this
threshold, are considered as generated by a high number of parallel
processes. In this respect, upstart-based boot proved to be rather
hard to detect as generating a large burst of queue creations, because
with upstart most of the queues created in a burst exit *before* the
next queues in the same burst are created. To address this issue, I
changed the burst-detection mechanism so as to not decrease the size
of the current burst even if one of the queues in the burst is
eliminated.

Unfortunately, this missing decrease causes false positives on very
fast systems: on the start-up of a complex application, such as
libreoffice writer, so many queues are created, served and exited
shortly after each other, that a large burst of queue creations is
wrongly detected as occurring. These false positives just disappear if
the size of a burst is decreased when one of the queues in the burst
exits. This commit restores the missing burst-size decrease, relying
of the fact that upstart is apparently unlikely to be used on systems
running this and future versions of the kernel.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Mauro Andreolini <mauro.andreolini@unimore.it>
Signed-off-by: Angelo Ruocco <angeloruocco90@gmail.com>
Tested-by: Mirko Montanari <mirkomontanari91@gmail.com>
---
 block/bfq-mq-iosched.c | 12 +++---------
 block/bfq-sq-iosched.c | 12 +++---------
 2 files changed, 6 insertions(+), 18 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index af84e506e897..6e413d7236ce 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -4111,16 +4111,10 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
 	BUG_ON(bfqq->entity.tree);
 	BUG_ON(bfq_bfqq_busy(bfqq));
 
-	if (bfq_bfqq_sync(bfqq))
-		/*
-		 * The fact that this queue is being destroyed does not
-		 * invalidate the fact that this queue may have been
-		 * activated during the current burst. As a consequence,
-		 * although the queue does not exist anymore, and hence
-		 * needs to be removed from the burst list if there,
-		 * the burst size has not to be decremented.
-		 */
+	if (bfq_bfqq_sync(bfqq) && !hlist_unhashed(&bfqq->burst_list_node)) {
 		hlist_del_init(&bfqq->burst_list_node);
+		bfqq->bfqd->burst_size--;
+	}
 
 	if (bfqq->bfqd)
 		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p freed", bfqq);
diff --git a/block/bfq-sq-iosched.c b/block/bfq-sq-iosched.c
index 0c48f527fe3f..93034dd7b801 100644
--- a/block/bfq-sq-iosched.c
+++ b/block/bfq-sq-iosched.c
@@ -3945,16 +3945,10 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
 	BUG_ON(bfqq->entity.tree);
 	BUG_ON(bfq_bfqq_busy(bfqq));
 
-	if (bfq_bfqq_sync(bfqq))
-		/*
-		 * The fact that this queue is being destroyed does not
-		 * invalidate the fact that this queue may have been
-		 * activated during the current burst. As a consequence,
-		 * although the queue does not exist anymore, and hence
-		 * needs to be removed from the burst list if there,
-		 * the burst size has not to be decremented.
-		 */
+	if (bfq_bfqq_sync(bfqq) && !hlist_unhashed(&bfqq->burst_list_node)) {
 		hlist_del_init(&bfqq->burst_list_node);
+		bfqq->bfqd->burst_size--;
+	}
 
 	bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p freed", bfqq);
 

From 60de7307d5e3ed7f272f12c900f631bdfe114db2 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Fri, 6 Oct 2017 19:35:38 +0200
Subject: [PATCH 47/51] bfq-sq, bfq-mq: fix unbalanced decrements of burst size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The commit "bfq-sq, bfq-mq: decrease burst size when queues in burst
exit" introduced the decrement of burst_size on the removal of a
bfq_queue from the burst list. Unfortunately, this decrement can
happen to be performed even when burst size is already equal to 0,
because of unbalanced decrements. A description follows of the cause
of these unbalanced decrements, namely a wrong assumption, and of the
way how this wrong assumption leads to unbalanced decrements.

The wrong assumption is that a bfq_queue can exit only if the process
associated with the bfq_queue has exited. This is false, because a
bfq_queue, say Q, may exit also as a consequence of a merge with
another bfq_queue. In this case, Q exits because the I/O of its
associated process has been redirected to another bfq_queue.

The decrement unbalance occurs because Q may then be re-created after
a split, and added back to the current burst list, *without*
incrementing burst_size. burst_size is not incremented because Q is
not a new bfq_queue added to the burst list, but a bfq_queue only
temporarily removed from the list, and, before the commit "bfq-sq,
bfq-mq: decrease burst size when queues in burst exit", burst_size was
not decremented when Q was removed.

This commit addresses this issue by just checking whether the exiting
bfq_queue is a merged bfq_queue, and, in that case, not decrementing
burst_size. Unfortunately, this still leaves room for unbalanced
decrements, in the following rarer case: on a split, the bfq_queue
happens to be inserted into a different burst list than that it was
removed from when merged. If this happens, the number of elements in
the new burst list becomes higher than burst_size (by one). When the
bfq_queue then exits, it is of course not in a merged state any
longer, thus burst_size is decremented, which results in an unbalanced
decrement.  To handle this sporadic, unlucky case in a simple way,
this commit also checks that burst_size is larger than 0 before
decrementing it.

Finally, this commit removes an useless, extra check: the check that
the bfq_queue is sync, performed before checking whether the bfq_queue
is in the burst list. This extra check is redundant, because only sync
bfq_queues can be inserted into the burst list.

Reported-by: Philip Müller <philm@manjaro.org>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Angelo Ruocco <angeloruocco90@gmail.com>
Tested-by: Philip Müller <philm@manjaro.org>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Tested-by: Lee Tibbert <lee.tibbert@gmail.com>
---
 block/bfq-mq-iosched.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++--
 block/bfq-sq-iosched.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 114 insertions(+), 4 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 6e413d7236ce..816bac6cdd3d 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -4111,9 +4111,36 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
 	BUG_ON(bfqq->entity.tree);
 	BUG_ON(bfq_bfqq_busy(bfqq));
 
-	if (bfq_bfqq_sync(bfqq) && !hlist_unhashed(&bfqq->burst_list_node)) {
+	if (!hlist_unhashed(&bfqq->burst_list_node)) {
 		hlist_del_init(&bfqq->burst_list_node);
-		bfqq->bfqd->burst_size--;
+		/*
+		 * Decrement also burst size after the removal, if the
+		 * process associated with bfqq is exiting, and thus
+		 * does not contribute to the burst any longer. This
+		 * decrement helps filter out false positives of large
+		 * bursts, when some short-lived process (often due to
+		 * the execution of commands by some service) happens
+		 * to start and exit while a complex application is
+		 * starting, and thus spawning several processes that
+		 * do I/O (and that *must not* be treated as a large
+		 * burst, see comments on bfq_handle_burst).
+		 *
+		 * In particular, the decrement is performed only if:
+		 * 1) bfqq is not a merged queue, because, if it is,
+		 * then this free of bfqq is not triggered by the exit
+		 * of the process bfqq is associated with, but exactly
+		 * by the fact that bfqq has just been merged.
+		 * 2) burst_size is greater than 0, to handle
+		 * unbalanced decrements. Unbalanced decrements may
+		 * happen in te following case: bfqq is inserted into
+		 * the current burst list--without incrementing
+		 * bust_size--because of a split, but the current
+		 * burst list is not the burst list bfqq belonged to
+		 * (see comments on the case of a split in
+		 * bfq_set_request).
+		 */
+		if (bfqq->bic && bfqq->bfqd->burst_size > 0)
+			bfqq->bfqd->burst_size--;
 	}
 
 	if (bfqq->bfqd)
@@ -4940,6 +4967,34 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
 				     "large burst");
 			bfq_clear_bfqq_in_large_burst(bfqq);
 			if (bic->was_in_burst_list)
+				/*
+				 * If bfqq was in the current
+				 * burst list before being
+				 * merged, then we have to add
+				 * it back. And we do not need
+				 * to increase burst_size, as
+				 * we did not decrement
+				 * burst_size when we removed
+				 * bfqq from the burst list as
+				 * a consequence of a merge
+				 * (see comments in
+				 * bfq_put_queue). In this
+				 * respect, it would be rather
+				 * costly to know whether the
+				 * current burst list is still
+				 * the same burst list from
+				 * which bfqq was removed on
+				 * the merge. To avoid this
+				 * cost, if bfqq was in a
+				 * burst list, then we add
+				 * bfqq to the current burst
+				 * list without any further
+				 * check. This can cause
+				 * inappropriate insertions,
+				 * but rarely enough to not
+				 * harm the detection of large
+				 * bursts significantly.
+				 */
 				hlist_add_head(&bfqq->burst_list_node,
 					       &bfqd->burst_list);
 		}
diff --git a/block/bfq-sq-iosched.c b/block/bfq-sq-iosched.c
index 93034dd7b801..4bbd7f4c0154 100644
--- a/block/bfq-sq-iosched.c
+++ b/block/bfq-sq-iosched.c
@@ -3945,9 +3945,36 @@ static void bfq_put_queue(struct bfq_queue *bfqq)
 	BUG_ON(bfqq->entity.tree);
 	BUG_ON(bfq_bfqq_busy(bfqq));
 
-	if (bfq_bfqq_sync(bfqq) && !hlist_unhashed(&bfqq->burst_list_node)) {
+	if (!hlist_unhashed(&bfqq->burst_list_node)) {
 		hlist_del_init(&bfqq->burst_list_node);
-		bfqq->bfqd->burst_size--;
+		/*
+		 * Decrement also burst size after the removal, if the
+		 * process associated with bfqq is exiting, and thus
+		 * does not contribute to the burst any longer. This
+		 * decrement helps filter out false positives of large
+		 * bursts, when some short-lived process (often due to
+		 * the execution of commands by some service) happens
+		 * to start and exit while a complex application is
+		 * starting, and thus spawning several processes that
+		 * do I/O (and that *must not* be treated as a large
+		 * burst, see comments on bfq_handle_burst).
+		 *
+		 * In particular, the decrement is performed only if:
+		 * 1) bfqq is not a merged queue, because, if it is,
+		 * then this free of bfqq is not triggered by the exit
+		 * of the process bfqq is associated with, but exactly
+		 * by the fact that bfqq has just been merged.
+		 * 2) burst_size is greater than 0, to handle
+		 * unbalanced decrements. Unbalanced decrements may
+		 * happen in te following case: bfqq is inserted into
+		 * the current burst list--without incrementing
+		 * bust_size--because of a split, but the current
+		 * burst list is not the burst list bfqq belonged to
+		 * (see comments on the case of a split in
+		 * bfq_set_request).
+		 */
+		if (bfqq->bic && bfqq->bfqd->burst_size > 0)
+			bfqq->bfqd->burst_size--;
 	}
 
 	bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p freed", bfqq);
@@ -4691,6 +4718,34 @@ static int bfq_set_request(struct request_queue *q, struct request *rq,
 					     "large burst");
 				bfq_clear_bfqq_in_large_burst(bfqq);
 				if (bic->was_in_burst_list)
+					/*
+					 * If bfqq was in the current
+					 * burst list before being
+					 * merged, then we have to add
+					 * it back. And we do not need
+					 * to increase burst_size, as
+					 * we did not decrement
+					 * burst_size when we removed
+					 * bfqq from the burst list as
+					 * a consequence of a merge
+					 * (see comments in
+					 * bfq_put_queue). In this
+					 * respect, it would be rather
+					 * costly to know whether the
+					 * current burst list is still
+					 * the same burst list from
+					 * which bfqq was removed on
+					 * the merge. To avoid this
+					 * cost, if bfqq was in a
+					 * burst list, then we add
+					 * bfqq to the current burst
+					 * list without any further
+					 * check. This can cause
+					 * inappropriate insertions,
+					 * but rarely enough to not
+					 * harm the detection of large
+					 * bursts significantly.
+					 */
 					hlist_add_head(&bfqq->burst_list_node,
 						       &bfqd->burst_list);
 			}

From 09adbd0f46f4ba395964b35bf611b7cc3dd84b4d Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Mon, 30 Oct 2017 16:50:50 +0100
Subject: [PATCH 48/51] doc, block, bfq-mq: update max IOPS sustainable with
 BFQ

We have investigated more deeply the performance of BFQ, in terms of
number of IOPS that can be processed by the CPU when BFQ is used as
I/O scheduler. In more detail, using the script [1], we have measured
the number of IOPS reached on top of a null block device configured
with zero latency, as a function of the workload (sequential read,
sequential write, random read, random write) and of the system (we
considered desktops, laptops and embedded systems).

Basing on the resulting figures, with this commit we update the
current, conservative IOPS range reported in BFQ documentation. In
particular, the documentation now reports, for each of three different
systems, the lowest number of IOPS obtained for that system with the
above test (namely, the value obtained with the workload leading to
the lowest IOPS).

[1] https://github.com/Algodev-github/IOSpeed

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Luca Miccio <lucmiccio@gmail.com>
---
 Documentation/block/bfq-iosched.txt | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt
index dcfe15523da3..595ff7a5ff34 100644
--- a/Documentation/block/bfq-iosched.txt
+++ b/Documentation/block/bfq-iosched.txt
@@ -29,12 +29,19 @@ for that device, by setting low_latency to 0. See Section 3 for
 details on how to configure BFQ for the desired tradeoff between
 latency and throughput, or on how to maximize throughput.
 
-On average CPUs, the current version of BFQ can handle devices
-performing at most ~30K IOPS; at most ~50 KIOPS on faster CPUs. As a
-reference, 30-50 KIOPS correspond to very high bandwidths with
-sequential I/O (e.g., 8-12 GB/s if I/O requests are 256 KB large), and
-to 120-200 MB/s with 4KB random I/O. BFQ is currently being tested on
-multi-queue devices too.
+BFQ has a non-null overhead, which limits the maximum IOPS that the
+CPU can process for a device scheduled with BFQ. To give an idea of
+the limits on slow or average CPUs, here are BFQ limits for three
+different CPUs, on, respectively, an average laptop, an old desktop,
+and a cheap embedded system, in case full hierarchical support is
+enabled (i.e., CONFIG_BFQ_SQ_GROUP_IOSCHED is set for bfq-sq, or
+CONFIG_MQ_BFQ_GROUP_IOSCHED is set for bfq-mq, or, finally,
+CONFIG_BFQ_GROUP_IOSCHED is set for bfq):
+- Intel i7-4850HQ: 250 KIOPS
+- AMD A8-3850: 170 KIOPS
+- ARM CortexTM-A53 Octa-core: 45 KIOPS
+
+BFQ works for multi-queue devices too (bfq and bfq-mq instances).
 
 The table of contents follows. Impatients can just jump to Section 3.
 

From be94f97b577dc587593185224a7718aa59ac43f7 Mon Sep 17 00:00:00 2001
From: Luca Miccio <lucmiccio@gmail.com>
Date: Tue, 31 Oct 2017 09:50:11 +0100
Subject: [PATCH 49/51] block, bfq-mq: add missing invocations of
 bfqg_stats_update_io_add/remove

bfqg_stats_update_io_add and bfqg_stats_update_io_remove are to be
invoked, respectively, when an I/O request enters and when an I/O
request exits the scheduler. Unfortunately, bfq-mq does not fully comply
with this scheme, because it does not invoke these functions for
requests that are inserted into or extracted from its priority
dispatch list. This commit fixes this mistake.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Luca Miccio <lucmiccio@gmail.com>
---
 block/bfq-mq-iosched.c | 24 +++++++++++++++++++-----
 1 file changed, 19 insertions(+), 5 deletions(-)

diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index 816bac6cdd3d..fbf28804c220 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -1394,7 +1394,6 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
 	BUG_ON(bfqq->entity.budget < bfqq->entity.service);
 
 	BUG_ON(bfqq == bfqd->in_service_queue);
-	bfqg_stats_update_io_add(bfqq_group(RQ_BFQQ(rq)), bfqq, rq->cmd_flags);
 
 	/*
 	 * bfqq deserves to be weight-raised if:
@@ -1734,7 +1733,6 @@ static void bfq_remove_request(struct request_queue *q,
 		BUG_ON(bfqq->meta_pending == 0);
 		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)
@@ -1879,6 +1877,7 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
 		bfqq->next_rq = rq;
 
 	bfq_remove_request(q, next);
+	bfqg_stats_update_io_remove(bfqq_group(bfqq), next->cmd_flags);
 
 	spin_unlock_irq(&bfqq->bfqd->lock);
 end:
@@ -4077,6 +4076,10 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	spin_lock_irq(&bfqd->lock);
 
 	rq = __bfq_dispatch_request(hctx);
+	if (rq && RQ_BFQQ(rq))
+		bfqg_stats_update_io_remove(bfqq_group(RQ_BFQQ(rq)),
+					    rq->cmd_flags);
+
 	spin_unlock_irq(&bfqd->lock);
 
 	return rq;
@@ -4634,6 +4637,7 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 {
 	struct request_queue *q = hctx->queue;
 	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
 
 	spin_lock_irq(&bfqd->lock);
 	if (blk_mq_sched_try_insert_merge(q, rq)) {
@@ -4647,8 +4651,6 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	spin_lock_irq(&bfqd->lock);
 	if (at_head || blk_rq_is_passthrough(rq)) {
-		struct bfq_queue *bfqq = RQ_BFQQ(rq);
-
 		if (at_head)
 			list_add(&rq->queuelist, &bfqd->dispatch);
 		else
@@ -4668,6 +4670,12 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		rq->rq_flags &= ~RQF_GOT;
 
 		__bfq_insert_request(bfqd, rq);
+		/*
+		 * Update bfqq, because, if a queue merge has occurred
+		 * in __bfq_insert_request, then rq has been
+		 * redirected into a new queue.
+		 */
+		bfqq = RQ_BFQQ(rq);
 
 		if (rq_mergeable(rq)) {
 			elv_rqhash_add(q, rq);
@@ -4676,6 +4684,9 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		}
 	}
 
+	if (bfqq)
+		bfqg_stats_update_io_add(bfqq_group(bfqq), bfqq, rq->cmd_flags);
+
 	spin_unlock_irq(&bfqd->lock);
 }
 
@@ -4893,8 +4904,11 @@ static void bfq_finish_request(struct request *rq)
 		BUG_ON(in_interrupt());
 
 		assert_spin_locked(&bfqd->lock);
-		if (!RB_EMPTY_NODE(&rq->rb_node))
+		if (!RB_EMPTY_NODE(&rq->rb_node)) {
 			bfq_remove_request(rq->q, rq);
+			bfqg_stats_update_io_remove(bfqq_group(bfqq),
+						    rq->cmd_flags);
+		}
 		bfq_put_rq_priv_body(bfqq);
 	}
 

From 8659a1549d2bf241129a0f7c90429bddd9c2bc53 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Wed, 8 Nov 2017 19:07:40 +0100
Subject: [PATCH 50/51] block, bfq-mq: update blkio stats outside the scheduler
 lock

bfq-mq invokes various blkg_*stats_* functions to update the statistics
contained in the special files blkio.bfq-mq.* in the blkio controller
groups, i.e., the I/O accounting related to the proportional-share
policy provided by bfq-mq. The execution of these functions takes a
considerable percentage, about 40%, of the total per-request execution
time of bfq-mq (i.e., of the sum of the execution time of all the bfq-mq
functions that have to be executed to process an I/O request from its
creation to its destruction).  This reduces the request-processing
rate sustainable by bfq-mq noticeably, even on a multicore CPU. In fact,
the bfq-mq functions that invoke blkg_*stats_* functions cannot be
executed in parallel with the rest of the code of bfq-mq, because
both are executed under the same same per-device scheduler lock.

To reduce this slowdown, this commit moves, wherever possible, the
invocation of these functions (more precisely, of the bfq-mq functions
that invoke blkg_*stats_* functions) outside the critical sections
protected by the scheduler lock.

With this change, and with all blkio.bfq-mq.* statistics enabled, the
throughput grows, e.g., from 250 to 310 KIOPS (+25%) on an Intel
i7-4850HQ, in case of 8 threads doing random I/O in parallel on
null_blk, with the latter configured with 0 latency. We obtained the
same or higher throughput boosts, up to +30%, with other processors
(some figures are reported in the documentation). For our tests, we
used the script [1], with which our results can be easily reproduced.

NOTE. This commit still protects the invocation of blkg_*stats_*
functions with the request_queue lock, because the group these
functions are invoked on may otherwise disappear before or while these
functions are executed.  Fortunately, tests without even this lock
show, by difference, that the serialization caused by this lock has a
little impact (at most ~5% of throughput reduction).

[1] https://github.com/Algodev-github/IOSpeed

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Luca Miccio <lucmiccio@gmail.com>
---
 Documentation/block/bfq-iosched.txt |  18 ++++--
 block/bfq-mq-iosched.c              | 112 +++++++++++++++++++++++++++++++-----
 block/bfq-sched.c                   |   2 +
 3 files changed, 112 insertions(+), 20 deletions(-)

diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt
index 595ff7a5ff34..c816c595082d 100644
--- a/Documentation/block/bfq-iosched.txt
+++ b/Documentation/block/bfq-iosched.txt
@@ -31,16 +31,22 @@ latency and throughput, or on how to maximize throughput.
 
 BFQ has a non-null overhead, which limits the maximum IOPS that the
 CPU can process for a device scheduled with BFQ. To give an idea of
-the limits on slow or average CPUs, here are BFQ limits for three
-different CPUs, on, respectively, an average laptop, an old desktop,
-and a cheap embedded system, in case full hierarchical support is
-enabled (i.e., CONFIG_BFQ_SQ_GROUP_IOSCHED is set for bfq-sq, or
-CONFIG_MQ_BFQ_GROUP_IOSCHED is set for bfq-mq, or, finally,
-CONFIG_BFQ_GROUP_IOSCHED is set for bfq):
+the limits on slow or average CPUs, here are, first, the limits of
+bfq-sq for three different CPUs, on, respectively, an average laptop,
+an old desktop, and a cheap embedded system, in case full hierarchical
+support is enabled (i.e., CONFIG_BFQ_SQ_GROUP_IOSCHED is set):
 - Intel i7-4850HQ: 250 KIOPS
 - AMD A8-3850: 170 KIOPS
 - ARM CortexTM-A53 Octa-core: 45 KIOPS
 
+bfq-mq and bfq instances reach, instead, a higher sustainable
+throughput. Their limits, on the same systems as above, are, with full
+hierarchical support enabled (i.e., CONFIG_MQ_BFQ_GROUP_IOSCHED set
+for bfq-mq, or CONFIG_BFQ_GROUP_IOSCHED set for bfq):
+- Intel i7-4850HQ: 310 KIOPS
+- AMD A8-3850: 200 KIOPS
+- ARM CortexTM-A53 Octa-core: 56 KIOPS
+
 BFQ works for multi-queue devices too (bfq and bfq-mq instances).
 
 The table of contents follows. Impatients can just jump to Section 3.
diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index fbf28804c220..ab3b83d612c2 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -1822,7 +1822,7 @@ static void bfq_request_merged(struct request_queue *q, struct request *req,
 		bfqq->next_rq = next_rq;
 
 		bfq_log_bfqq(bfqd, bfqq,
-			"requests_merged: req %p prev %p next_rq %p bfqq %p",
+			"request_merged: req %p prev %p next_rq %p bfqq %p",
 			     req, prev, next_rq, bfqq);
 
 		/*
@@ -2415,7 +2415,6 @@ 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_clear_bfqq_fifo_expire(bfqq);
 
 		bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8;
@@ -3784,7 +3783,6 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
 				 */
 				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;
 		}
@@ -4072,16 +4070,67 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 {
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 	struct request *rq;
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+	struct bfq_queue *in_serv_queue, *bfqq;
+	bool waiting_rq, idle_timer_disabled;
+#endif
 
 	spin_lock_irq(&bfqd->lock);
 
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+	in_serv_queue = bfqd->in_service_queue;
+	waiting_rq = in_serv_queue && bfq_bfqq_wait_request(in_serv_queue);
+
 	rq = __bfq_dispatch_request(hctx);
-	if (rq && RQ_BFQQ(rq))
-		bfqg_stats_update_io_remove(bfqq_group(RQ_BFQQ(rq)),
-					    rq->cmd_flags);
 
+	idle_timer_disabled =
+		waiting_rq && !bfq_bfqq_wait_request(in_serv_queue);
+
+#else
+	rq = __bfq_dispatch_request(hctx);
+#endif
 	spin_unlock_irq(&bfqd->lock);
 
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+	bfqq = rq ? RQ_BFQQ(rq) : NULL;
+	if (!idle_timer_disabled && !bfqq)
+		return rq;
+
+	/*
+	 * rq and bfqq are guaranteed to exist until this function
+	 * ends, for the following reasons. First, rq can be
+	 * dispatched to the device, and then can be completed and
+	 * freed, only after this function ends. Second, rq cannot be
+	 * merged (and thus freed because of a merge) any longer,
+	 * because it has already started. Thus rq cannot be freed
+	 * before this function ends, and, since rq has a reference to
+	 * bfqq, the same guarantee holds for bfqq too.
+	 *
+	 * In addition, the following queue lock guarantees that
+	 * bfqq_group(bfqq) exists as well.
+	 */
+	spin_lock_irq(hctx->queue->queue_lock);
+	if (idle_timer_disabled)
+		/*
+		 * Since the idle timer has been disabled,
+		 * in_serv_queue contained some request when
+		 * __bfq_dispatch_request was invoked above, which
+		 * implies that rq was picked exactly from
+		 * in_serv_queue. Thus in_serv_queue == bfqq, and is
+		 * therefore guaranteed to exist because of the above
+		 * arguments.
+		 */
+		bfqg_stats_update_idle_time(bfqq_group(in_serv_queue));
+	if (bfqq) {
+		struct bfq_group *bfqg = bfqq_group(bfqq);
+
+		bfqg_stats_update_avg_queue_size(bfqg);
+		bfqg_stats_set_start_empty_time(bfqg);
+		bfqg_stats_update_io_remove(bfqg, rq->cmd_flags);
+	}
+	spin_unlock_irq(hctx->queue->queue_lock);
+#endif
+
 	return rq;
 }
 
@@ -4200,7 +4249,6 @@ static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
 		unsigned long flags;
 
 		spin_lock_irqsave(&bfqd->lock, flags);
-
 		bfq_exit_bfqq(bfqd, bfqq);
 		bic_set_bfqq(bic, NULL, is_sync);
 		spin_unlock_irqrestore(&bfqd->lock, flags);
@@ -4554,7 +4602,6 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		 */
 		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
@@ -4569,9 +4616,11 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	}
 }
 
-static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
+/* returns true if it causes the idle timer to be disabled */
+static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 {
 	struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq;
+	bool waiting, idle_timer_disabled = false;
 	BUG_ON(!bfqq);
 
 	assert_spin_locked(&bfqd->lock);
@@ -4624,12 +4673,16 @@ static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 		}
 	}
 
+	waiting = bfqq && bfq_bfqq_wait_request(bfqq);
 	bfq_add_request(rq);
+	idle_timer_disabled = waiting && !bfq_bfqq_wait_request(bfqq);
 
 	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);
+
+	return idle_timer_disabled;
 }
 
 static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
@@ -4638,6 +4691,10 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	struct request_queue *q = hctx->queue;
 	struct bfq_data *bfqd = q->elevator->elevator_data;
 	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+	bool idle_timer_disabled = false;
+	unsigned int cmd_flags;
+#endif
 
 	spin_lock_irq(&bfqd->lock);
 	if (blk_mq_sched_try_insert_merge(q, rq)) {
@@ -4669,13 +4726,17 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		BUG_ON(!(rq->rq_flags & RQF_GOT));
 		rq->rq_flags &= ~RQF_GOT;
 
-		__bfq_insert_request(bfqd, rq);
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+		idle_timer_disabled = __bfq_insert_request(bfqd, rq);
 		/*
 		 * Update bfqq, because, if a queue merge has occurred
 		 * in __bfq_insert_request, then rq has been
 		 * redirected into a new queue.
 		 */
 		bfqq = RQ_BFQQ(rq);
+#else
+		__bfq_insert_request(bfqd, rq);
+#endif
 
 		if (rq_mergeable(rq)) {
 			elv_rqhash_add(q, rq);
@@ -4683,11 +4744,34 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 				q->last_merge = rq;
 		}
 	}
-
-	if (bfqq)
-		bfqg_stats_update_io_add(bfqq_group(bfqq), bfqq, rq->cmd_flags);
-
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+	/*
+	 * Cache cmd_flags before releasing scheduler lock, because rq
+	 * may disappear afterwards (for example, because of a request
+	 * merge).
+	 */
+	cmd_flags = rq->cmd_flags;
+#endif
 	spin_unlock_irq(&bfqd->lock);
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+	if (!bfqq)
+		return;
+	/*
+	 * bfqq still exists, because it can disappear only after
+	 * either it is merged with another queue, or the process it
+	 * is associated with exits. But both actions must be taken by
+	 * the same process currently executing this flow of
+	 * instruction.
+	 *
+	 * In addition, the following queue lock guarantees that
+	 * bfqq_group(bfqq) exists as well.
+	 */
+	spin_lock_irq(q->queue_lock);
+	bfqg_stats_update_io_add(bfqq_group(bfqq), bfqq, cmd_flags);
+	if (idle_timer_disabled)
+		bfqg_stats_update_idle_time(bfqq_group(bfqq));
+	spin_unlock_irq(q->queue_lock);
+#endif
 }
 
 static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
diff --git a/block/bfq-sched.c b/block/bfq-sched.c
index e4a2553a2d2c..616c0692335a 100644
--- a/block/bfq-sched.c
+++ b/block/bfq-sched.c
@@ -949,9 +949,11 @@ static void bfq_bfqq_served(struct bfq_queue *bfqq, int served)
 		st->vtime += bfq_delta(served, st->wsum);
 		bfq_forget_idle(st);
 	}
+#ifndef BFQ_MQ
 #ifdef BFQ_GROUP_IOSCHED_ENABLED
 	bfqg_stats_set_start_empty_time(bfqq_group(bfqq));
 #endif
+#endif
 	st = bfq_entity_service_tree(&bfqq->entity);
 	bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %d secs, vtime %llu on %p",
 		     served,  ((st->vtime>>10)*1000)>>12, st);

From abdfb33a3325df55ec0261fd824ca61ddac13575 Mon Sep 17 00:00:00 2001
From: Luca Miccio <lucmiccio@gmail.com>
Date: Wed, 8 Nov 2017 19:07:41 +0100
Subject: [PATCH 51/51] block, bfq-sq, bfq-mq: move debug blkio stats behind
 CONFIG_DEBUG_BLK_CGROUP

BFQ (both bfq-mq and bfq-sq) currently creates, and updates, its own
instance of the whole set of blkio statistics that cfq creates. Yet,
from the comments of Tejun Heo in [1], it turned out that most of
these statistics are meant/useful only for debugging. This commit
makes BFQ create the latter, debugging statistics only if the option
CONFIG_DEBUG_BLK_CGROUP is set.

By doing so, this commit also enables BFQ to enjoy a high perfomance
boost. The reason is that, if CONFIG_DEBUG_BLK_CGROUP is not set, then
BFQ has to update far fewer statistics, and, in particular, not the
heaviest to update.  To give an idea of the benefits, if
CONFIG_DEBUG_BLK_CGROUP is not set, then, on an Intel i7-4850HQ, and
with 8 threads doing random I/O in parallel on null_blk (configured
with 0 latency), the throughput of bfq-mq grows from 310 to 400 KIOPS
(+30%). We have measured similar or even much higher boosts with other
CPUs: e.g., +45% with an ARM CortexTM-A53 Octa-core. Our results have
been obtained and can be reproduced very easily with the script in [1].

[1] https://www.spinics.net/lists/linux-block/msg18943.html

Reported-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Luca Miccio <lucmiccio@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
---
 Documentation/block/bfq-iosched.txt |  59 ++++++++++---
 block/bfq-cgroup-included.c         | 163 ++++++++++++++++++++----------------
 block/bfq-mq-iosched.c              |  14 ++--
 block/bfq-mq.h                      |   4 +-
 block/bfq.h                         |   4 +-
 5 files changed, 147 insertions(+), 97 deletions(-)

diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt
index c816c595082d..30ef2dba85ad 100644
--- a/Documentation/block/bfq-iosched.txt
+++ b/Documentation/block/bfq-iosched.txt
@@ -29,24 +29,41 @@ for that device, by setting low_latency to 0. See Section 3 for
 details on how to configure BFQ for the desired tradeoff between
 latency and throughput, or on how to maximize throughput.
 
-BFQ has a non-null overhead, which limits the maximum IOPS that the
-CPU can process for a device scheduled with BFQ. To give an idea of
-the limits on slow or average CPUs, here are, first, the limits of
-bfq-sq for three different CPUs, on, respectively, an average laptop,
+BFQ has a non-null overhead, which limits the maximum IOPS that a CPU
+can process for a device scheduled with BFQ. To give an idea of the
+limits on slow or average CPUs, here are, first, the limits of bfq-mq
+and bfq for three different CPUs, on, respectively, an average laptop,
 an old desktop, and a cheap embedded system, in case full hierarchical
-support is enabled (i.e., CONFIG_BFQ_SQ_GROUP_IOSCHED is set):
-- Intel i7-4850HQ: 250 KIOPS
-- AMD A8-3850: 170 KIOPS
-- ARM CortexTM-A53 Octa-core: 45 KIOPS
-
-bfq-mq and bfq instances reach, instead, a higher sustainable
-throughput. Their limits, on the same systems as above, are, with full
-hierarchical support enabled (i.e., CONFIG_MQ_BFQ_GROUP_IOSCHED set
-for bfq-mq, or CONFIG_BFQ_GROUP_IOSCHED set for bfq):
+support is enabled (i.e., CONFIG_MQ_BFQ_GROUP_IOSCHED is set for
+bfq-mq, or CONFIG_BFQ_GROUP_IOSCHED is set for bfq), but
+CONFIG_DEBUG_BLK_CGROUP is not set (Section 4-2):
+- Intel i7-4850HQ: 400 KIOPS
+- AMD A8-3850: 250 KIOPS
+- ARM CortexTM-A53 Octa-core: 80 KIOPS
+
+As for bfq-sq, it cannot reach the above IOPS, because of the
+inherent, lower parallelism of legacy blk and of the components within
+it (including bfq-sq itself). In particular, results with
+CONFIG_DEBUG_BLK_CGROUP unset are rather fluctuating. The limits
+reported below for the case CONFIG_DEBUG_BLK_CGROUP set will however
+provide a lower bound to the limits of bfq-sq.
+
+Turning back to bfq-mq and bfq, If CONFIG_DEBUG_BLK_CGROUP is set (and
+of course full hierarchical support is enabled), then the sustainable
+throughput with bfq-mq and bfq decreases, because all blkio.bfq*
+statistics are created and updated (Section 4-2).  For bfq-mq and bfq,
+this leads to the following maximum sustainable throughputs, on the
+same systems as above:
 - Intel i7-4850HQ: 310 KIOPS
 - AMD A8-3850: 200 KIOPS
 - ARM CortexTM-A53 Octa-core: 56 KIOPS
 
+Finally, if CONFIG_DEBUG_BLK_CGROUP is set (and full hierarchical
+support is enabled), then bfq-sq exhibits the following limits:
+- Intel i7-4850HQ: 250 KIOPS
+- AMD A8-3850: 170 KIOPS
+- ARM CortexTM-A53 Octa-core: 45 KIOPS
+
 BFQ works for multi-queue devices too (bfq and bfq-mq instances).
 
 The table of contents follows. Impatients can just jump to Section 3.
@@ -524,6 +541,22 @@ BFQ-specific files is "blkio.bfqX." or "io.bfqX.", where X can be ""
 to set the weight of a group with the mainline BFQ is blkio.bfq.weight
 or io.bfq.weight.
 
+As for cgroups-v1 (blkio controller), the exact set of stat files
+created, and kept up-to-date by bfq*, depends on whether
+CONFIG_DEBUG_BLK_CGROUP is set. If it is set, then bfq* creates all
+the stat files documented in
+Documentation/cgroup-v1/blkio-controller.txt. If, instead,
+CONFIG_DEBUG_BLK_CGROUP is not set, then bfq* creates only the files
+blkio.bfq*.io_service_bytes
+blkio.bfq*.io_service_bytes_recursive
+blkio.bfq*.io_serviced
+blkio.bfq*.io_serviced_recursive
+
+The value of CONFIG_DEBUG_BLK_CGROUP greatly influences the maximum
+throughput sustainable with bfq*, because updating the blkio.bfq*
+stats is rather costly, especially for some of the stats enabled by
+CONFIG_DEBUG_BLK_CGROUP.
+
 Parameters to set
 -----------------
 
diff --git a/block/bfq-cgroup-included.c b/block/bfq-cgroup-included.c
index 631e53d9150d..562b0ce581a7 100644
--- a/block/bfq-cgroup-included.c
+++ b/block/bfq-cgroup-included.c
@@ -15,7 +15,7 @@
  * file.
  */
 
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+#if defined(BFQ_GROUP_IOSCHED_ENABLED) && defined(CONFIG_DEBUG_BLK_CGROUP)
 
 /* bfqg stats flags */
 enum bfqg_stats_flags {
@@ -155,6 +155,63 @@ static void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg)
 	bfqg_stats_update_group_wait_time(stats);
 }
 
+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);
+}
+
+#else /* BFQ_GROUP_IOSCHED_ENABLED && CONFIG_DEBUG_BLK_CGROUP */
+
+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) { }
+
+#endif /* BFQ_GROUP_IOSCHED_ENABLED && CONFIG_DEBUG_BLK_CGROUP */
+
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
 static struct blkcg_policy blkcg_policy_bfq;
 
 /*
@@ -247,44 +304,10 @@ static void bfqg_and_blkg_put(struct bfq_group *bfqg)
 }
 #endif
 
-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)
 {
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	/* queued stats shouldn't be cleared */
 	blkg_rwstat_reset(&stats->merged);
 	blkg_rwstat_reset(&stats->service_time);
@@ -296,6 +319,7 @@ static void bfqg_stats_reset(struct bfqg_stats *stats)
 	blkg_stat_reset(&stats->group_wait_time);
 	blkg_stat_reset(&stats->idle_time);
 	blkg_stat_reset(&stats->empty_time);
+#endif
 }
 
 /* @to += @from */
@@ -304,6 +328,7 @@ static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from)
 	if (!to || !from)
 		return;
 
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	/* queued stats shouldn't be cleared */
 	blkg_rwstat_add_aux(&to->merged, &from->merged);
 	blkg_rwstat_add_aux(&to->service_time, &from->service_time);
@@ -316,6 +341,7 @@ static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from)
 	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);
+#endif
 }
 
 /*
@@ -367,6 +393,7 @@ static void bfq_init_entity(struct bfq_entity *entity,
 
 static void bfqg_stats_exit(struct bfqg_stats *stats)
 {
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	blkg_rwstat_exit(&stats->merged);
 	blkg_rwstat_exit(&stats->service_time);
 	blkg_rwstat_exit(&stats->wait_time);
@@ -378,10 +405,12 @@ static void bfqg_stats_exit(struct bfqg_stats *stats)
 	blkg_stat_exit(&stats->group_wait_time);
 	blkg_stat_exit(&stats->idle_time);
 	blkg_stat_exit(&stats->empty_time);
+#endif
 }
 
 static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
 {
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	if (blkg_rwstat_init(&stats->merged, gfp) ||
 	    blkg_rwstat_init(&stats->service_time, gfp) ||
 	    blkg_rwstat_init(&stats->wait_time, gfp) ||
@@ -396,6 +425,7 @@ static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
 		bfqg_stats_exit(stats);
 		return -ENOMEM;
 	}
+#endif
 
 	return 0;
 }
@@ -1003,6 +1033,7 @@ static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
 	return bfq_io_set_weight_legacy(of_css(of), NULL, weight);
 }
 
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 static int bfqg_print_stat(struct seq_file *sf, void *v)
 {
 	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
@@ -1108,6 +1139,7 @@ static int bfqg_print_avg_queue_size(struct seq_file *sf, void *v)
 			  0, false);
 	return 0;
 }
+#endif /* CONFIG_DEBUG_BLK_CGROUP */
 
 static struct bfq_group *
 bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
@@ -1137,15 +1169,6 @@ static struct cftype bfq_blkcg_legacy_files[] = {
 
 	/* statistics, covers only the tasks in the bfqg */
 	{
-		.name = BFQ_CGROUP_FNAME(time),
-		.private = offsetof(struct bfq_group, stats.time),
-		.seq_show = bfqg_print_stat,
-	},
-	{
-		.name = BFQ_CGROUP_FNAME(sectors),
-		.seq_show = bfqg_print_stat_sectors,
-	},
-	{
 		.name = BFQ_CGROUP_FNAME(io_service_bytes),
 		.private = (unsigned long)&blkcg_policy_bfq,
 		.seq_show = blkg_print_stat_bytes,
@@ -1155,6 +1178,16 @@ static struct cftype bfq_blkcg_legacy_files[] = {
 		.private = (unsigned long)&blkcg_policy_bfq,
 		.seq_show = blkg_print_stat_ios,
 	},
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+	{
+		.name = BFQ_CGROUP_FNAME(time),
+		.private = offsetof(struct bfq_group, stats.time),
+		.seq_show = bfqg_print_stat,
+	},
+	{
+		.name = BFQ_CGROUP_FNAME(sectors),
+		.seq_show = bfqg_print_stat_sectors,
+	},
 	{
 		.name = BFQ_CGROUP_FNAME(io_service_time),
 		.private = offsetof(struct bfq_group, stats.service_time),
@@ -1175,18 +1208,10 @@ static struct cftype bfq_blkcg_legacy_files[] = {
 		.private = offsetof(struct bfq_group, stats.queued),
 		.seq_show = bfqg_print_rwstat,
 	},
+#endif /* CONFIG_DEBUG_BLK_CGROUP */
 
 	/* the same statictics which cover the bfqg and its descendants */
 	{
-		.name = BFQ_CGROUP_FNAME(time_recursive),
-		.private = offsetof(struct bfq_group, stats.time),
-		.seq_show = bfqg_print_stat_recursive,
-	},
-	{
-		.name = BFQ_CGROUP_FNAME(sectors_recursive),
-		.seq_show = bfqg_print_stat_sectors_recursive,
-	},
-	{
 		.name = BFQ_CGROUP_FNAME(io_service_bytes_recursive),
 		.private = (unsigned long)&blkcg_policy_bfq,
 		.seq_show = blkg_print_stat_bytes_recursive,
@@ -1196,6 +1221,16 @@ static struct cftype bfq_blkcg_legacy_files[] = {
 		.private = (unsigned long)&blkcg_policy_bfq,
 		.seq_show = blkg_print_stat_ios_recursive,
 	},
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+	{
+		.name = BFQ_CGROUP_FNAME(time_recursive),
+		.private = offsetof(struct bfq_group, stats.time),
+		.seq_show = bfqg_print_stat_recursive,
+	},
+	{
+		.name = BFQ_CGROUP_FNAME(sectors_recursive),
+		.seq_show = bfqg_print_stat_sectors_recursive,
+	},
 	{
 		.name = BFQ_CGROUP_FNAME(io_service_time_recursive),
 		.private = offsetof(struct bfq_group, stats.service_time),
@@ -1240,6 +1275,7 @@ static struct cftype bfq_blkcg_legacy_files[] = {
 		.private = offsetof(struct bfq_group, stats.dequeue),
 		.seq_show = bfqg_print_stat,
 	},
+#endif	/* CONFIG_DEBUG_BLK_CGROUP */
 	{ }	/* terminate */
 };
 
@@ -1257,25 +1293,6 @@ static struct cftype bfq_blkg_files[] = {
 
 #else /* BFQ_GROUP_IOSCHED_ENABLED */
 
-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) {}
 
diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c
index ab3b83d612c2..0c09609a6099 100644
--- a/block/bfq-mq-iosched.c
+++ b/block/bfq-mq-iosched.c
@@ -4070,14 +4070,14 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 {
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 	struct request *rq;
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+#if defined(BFQ_GROUP_IOSCHED_ENABLED) &&  defined(CONFIG_DEBUG_BLK_CGROUP)
 	struct bfq_queue *in_serv_queue, *bfqq;
 	bool waiting_rq, idle_timer_disabled;
 #endif
 
 	spin_lock_irq(&bfqd->lock);
 
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+#if defined(BFQ_GROUP_IOSCHED_ENABLED) &&  defined(CONFIG_DEBUG_BLK_CGROUP)
 	in_serv_queue = bfqd->in_service_queue;
 	waiting_rq = in_serv_queue && bfq_bfqq_wait_request(in_serv_queue);
 
@@ -4091,7 +4091,7 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 #endif
 	spin_unlock_irq(&bfqd->lock);
 
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+#if defined(BFQ_GROUP_IOSCHED_ENABLED) &&  defined(CONFIG_DEBUG_BLK_CGROUP)
 	bfqq = rq ? RQ_BFQQ(rq) : NULL;
 	if (!idle_timer_disabled && !bfqq)
 		return rq;
@@ -4691,7 +4691,7 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	struct request_queue *q = hctx->queue;
 	struct bfq_data *bfqd = q->elevator->elevator_data;
 	struct bfq_queue *bfqq = RQ_BFQQ(rq);
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+#if defined(BFQ_GROUP_IOSCHED_ENABLED) &&  defined(CONFIG_DEBUG_BLK_CGROUP)
 	bool idle_timer_disabled = false;
 	unsigned int cmd_flags;
 #endif
@@ -4726,7 +4726,7 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		BUG_ON(!(rq->rq_flags & RQF_GOT));
 		rq->rq_flags &= ~RQF_GOT;
 
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+#if defined(BFQ_GROUP_IOSCHED_ENABLED) &&  defined(CONFIG_DEBUG_BLK_CGROUP)
 		idle_timer_disabled = __bfq_insert_request(bfqd, rq);
 		/*
 		 * Update bfqq, because, if a queue merge has occurred
@@ -4744,7 +4744,7 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 				q->last_merge = rq;
 		}
 	}
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+#if defined(BFQ_GROUP_IOSCHED_ENABLED) &&  defined(CONFIG_DEBUG_BLK_CGROUP)
 	/*
 	 * Cache cmd_flags before releasing scheduler lock, because rq
 	 * may disappear afterwards (for example, because of a request
@@ -4753,7 +4753,7 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	cmd_flags = rq->cmd_flags;
 #endif
 	spin_unlock_irq(&bfqd->lock);
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+#if defined(BFQ_GROUP_IOSCHED_ENABLED) &&  defined(CONFIG_DEBUG_BLK_CGROUP)
 	if (!bfqq)
 		return;
 	/*
diff --git a/block/bfq-mq.h b/block/bfq-mq.h
index 7ed2cc29be57..1cb05bb853d2 100644
--- a/block/bfq-mq.h
+++ b/block/bfq-mq.h
@@ -784,7 +784,7 @@ enum bfqq_expiration {
 
 
 struct bfqg_stats {
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+#if defined(BFQ_GROUP_IOSCHED_ENABLED) &&  defined(CONFIG_DEBUG_BLK_CGROUP)
 	/* number of ios merged */
 	struct blkg_rwstat		merged;
 	/* total time spent on device in ns, may not be accurate w/ queueing */
@@ -812,7 +812,7 @@ struct bfqg_stats {
 	uint64_t			start_idle_time;
 	uint64_t			start_empty_time;
 	uint16_t			flags;
-#endif
+#endif /* BFQ_GROUP_IOSCHED_ENABLED && CONFIG_DEBUG_BLK_CGROUP */
 };
 
 #ifdef BFQ_GROUP_IOSCHED_ENABLED
diff --git a/block/bfq.h b/block/bfq.h
index 15d326f466b7..47cd4d5a8c32 100644
--- a/block/bfq.h
+++ b/block/bfq.h
@@ -791,7 +791,7 @@ enum bfqq_expiration {
 
 
 struct bfqg_stats {
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+#if defined(BFQ_GROUP_IOSCHED_ENABLED) &&  defined(CONFIG_DEBUG_BLK_CGROUP)
 	/* number of ios merged */
 	struct blkg_rwstat		merged;
 	/* total time spent on device in ns, may not be accurate w/ queueing */
@@ -819,7 +819,7 @@ struct bfqg_stats {
 	uint64_t			start_idle_time;
 	uint64_t			start_empty_time;
 	uint16_t			flags;
-#endif
+#endif /* BFQ_GROUP_IOSCHED_ENABLED && CONFIG_DEBUG_BLK_CGROUP */
 };
 
 #ifdef BFQ_GROUP_IOSCHED_ENABLED