aboutsummaryrefslogtreecommitdiffstats
path: root/block/cfq-iosched.c
blob: a8437042e28a59d83c6d8218fbfa90097738540d (plain) (blame)
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
/*
 *  CFQ, or complete fairness queueing, disk scheduler.
 *
 *  Based on ideas from a previously unfinished io
 *  scheduler (round robin per-process disk scheduling) and Andrea Arcangeli.
 *
 *  Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
 */
#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/hash.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>

/*
 * tunables
 */
static const int cfq_quantum = 4;		/* max queue in one round of service */
static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
static const int cfq_back_max = 16 * 1024;	/* maximum backwards seek, in KiB */
static const int cfq_back_penalty = 2;		/* penalty of a backwards seek */

static const int cfq_slice_sync = HZ / 10;
static int cfq_slice_async = HZ / 25;
static const int cfq_slice_async_rq = 2;
static int cfq_slice_idle = HZ / 125;

/*
 * grace period before allowing idle class to get disk access
 */
#define CFQ_IDLE_GRACE		(HZ / 10)

/*
 * below this threshold, we consider thinktime immediate
 */
#define CFQ_MIN_TT		(2)

#define CFQ_SLICE_SCALE		(5)

#define CFQ_KEY_ASYNC		(0)

/*
 * for the hash of cfqq inside the cfqd
 */
#define CFQ_QHASH_SHIFT		6
#define CFQ_QHASH_ENTRIES	(1 << CFQ_QHASH_SHIFT)

#define RQ_CIC(rq)		((struct cfq_io_context*)(rq)->elevator_private)
#define RQ_CFQQ(rq)		((rq)->elevator_private2)

static struct kmem_cache *cfq_pool;
static struct kmem_cache *cfq_ioc_pool;

static DEFINE_PER_CPU(unsigned long, ioc_count);
static struct completion *ioc_gone;

#define CFQ_PRIO_LISTS		IOPRIO_BE_NR
#define cfq_class_idle(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
#define cfq_class_rt(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_RT)

#define ASYNC			(0)
#define SYNC			(1)

#define cfq_cfqq_sync(cfqq)	((cfqq)->key != CFQ_KEY_ASYNC)

#define sample_valid(samples)	((samples) > 80)

/*
 * Most of our rbtree usage is for sorting with min extraction, so
 * if we cache the leftmost node we don't have to walk down the tree
 * to find it. Idea borrowed from Ingo Molnars CFS scheduler. We should
 * move this into the elevator for the rq sorting as well.
 */
struct cfq_rb_root {
	struct rb_root rb;
	struct rb_node *left;
};
#define CFQ_RB_ROOT	(struct cfq_rb_root) { RB_ROOT, NULL, }

/*
 * Per block device queue structure
 */
struct cfq_data {
	request_queue_t *queue;

	/*
	 * rr list of queues with requests and the count of them
	 */
	struct cfq_rb_root service_tree;
	unsigned int busy_queues;

	/*
	 * cfqq lookup hash
	 */
	struct hlist_head *cfq_hash;

	int rq_in_driver;
	int hw_tag;

	/*
	 * idle window management
	 */
	struct timer_list idle_slice_timer;
	struct work_struct unplug_work;

	struct cfq_queue *active_queue;
	struct cfq_io_context *active_cic;
	unsigned int dispatch_slice;

	struct timer_list idle_class_timer;

	sector_t last_position;
	unsigned long last_end_request;

	/*
	 * tunables, see top of file
	 */
	unsigned int cfq_quantum;
	unsigned int cfq_fifo_expire[2];
	unsigned int cfq_back_penalty;
	unsigned int cfq_back_max;
	unsigned int cfq_slice[2];
	unsigned int cfq_slice_async_rq;
	unsigned int cfq_slice_idle;

	struct list_head cic_list;

	sector_t new_seek_mean;
	u64 new_seek_total;
};

/*
 * Per process-grouping structure
 */
struct cfq_queue {
	/* reference count */
	atomic_t ref;
	/* parent cfq_data */
	struct cfq_data *cfqd;
	/* cfqq lookup hash */
	struct hlist_node cfq_hash;
	/* hash key */
	unsigned int key;
	/* service_tree member */
	struct rb_node rb_node;
	/* service_tree key */
	unsigned long rb_key;
	/* sorted list of pending requests */
	struct rb_root sort_list;
	/* if fifo isn't expired, next request to serve */
	struct request *next_rq;
	/* requests queued in sort_list */
	int queued[2];
	/* currently allocated requests */
	int allocated[2];
	/* pending metadata requests */
	int meta_pending;
	/* fifo list of requests in sort_list */
	struct list_head fifo;

	unsigned long slice_end;
	long slice_resid;

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

	/* io prio of this group */
	unsigned short ioprio, org_ioprio;
	unsigned short ioprio_class, org_ioprio_class;

	/* various state flags, see below */
	unsigned int flags;

	sector_t last_request_pos;
};

enum cfqq_state_flags {
	CFQ_CFQQ_FLAG_on_rr = 0,	/* on round-robin busy list */
	CFQ_CFQQ_FLAG_wait_request,	/* waiting for a request */
	CFQ_CFQQ_FLAG_must_alloc,	/* must be allowed rq alloc */
	CFQ_CFQQ_FLAG_must_alloc_slice,	/* per-slice must_alloc flag */
	CFQ_CFQQ_FLAG_must_dispatch,	/* must dispatch, even if expired */
	CFQ_CFQQ_FLAG_fifo_expire,	/* FIFO checked in this slice */
	CFQ_CFQQ_FLAG_idle_window,	/* slice idling enabled */
	CFQ_CFQQ_FLAG_prio_changed,	/* task priority has changed */
	CFQ_CFQQ_FLAG_queue_new,	/* queue never been serviced */
	CFQ_CFQQ_FLAG_slice_new,	/* no requests dispatched in slice */
};

#define CFQ_CFQQ_FNS(name)						\
static inline void cfq_mark_cfqq_##name(struct cfq_queue *cfqq)		\
{									\
	cfqq->flags |= (1 << CFQ_CFQQ_FLAG_##name);			\
}									\
static inline void cfq_clear_cfqq_##name(struct cfq_queue *cfqq)	\
{									\
	cfqq->flags &= ~(1 << CFQ_CFQQ_FLAG_##name);			\
}									\
static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq)		\
{									\
	return (cfqq->flags & (1 << CFQ_CFQQ_FLAG_##name)) != 0;	\
}

CFQ_CFQQ_FNS(on_rr);
CFQ_CFQQ_FNS(wait_request);
CFQ_CFQQ_FNS(must_alloc);
CFQ_CFQQ_FNS(must_alloc_slice);
CFQ_CFQQ_FNS(must_dispatch);
CFQ_CFQQ_FNS(fifo_expire);
CFQ_CFQQ_FNS(idle_window);
CFQ_CFQQ_FNS(prio_changed);
CFQ_CFQQ_FNS(queue_new);
CFQ_CFQQ_FNS(slice_new);
#undef CFQ_CFQQ_FNS

static struct cfq_queue *cfq_find_cfq_hash(struct cfq_data *, unsigned int, unsigned short);
static void cfq_dispatch_insert(request_queue_t *, struct request *);
static struct cfq_queue *cfq_get_queue(struct cfq_data *, unsigned int, struct task_struct *, gfp_t);

/*
 * scheduler run of queue, if there are requests pending and no one in the
 * driver that will restart queueing
 */
static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
{
	if (cfqd->busy_queues)
		kblockd_schedule_work(&cfqd->unplug_work);
}

static int cfq_queue_empty(request_queue_t *q)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;

	return !cfqd->busy_queues;
}

static inline pid_t cfq_queue_pid(struct task_struct *task, int rw, int is_sync)
{
	/*
	 * Use the per-process queue, for read requests and syncronous writes
	 */
	if (!(rw & REQ_RW) || is_sync)
		return task->pid;

	return CFQ_KEY_ASYNC;
}

/*
 * Scale schedule slice based on io priority. Use the sync time slice only
 * if a queue is marked sync and has sync io queued. A sync queue with async
 * io only, should not get full sync slice length.
 */
static inline int cfq_prio_slice(struct cfq_data *cfqd, int sync,
				 unsigned short prio)
{
	const int base_slice = cfqd->cfq_slice[sync];

	WARN_ON(prio >= IOPRIO_BE_NR);

	return base_slice + (base_slice/CFQ_SLICE_SCALE * (4 - prio));
}

static inline int
cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
}

static inline void
cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	cfqq->slice_end = cfq_prio_to_slice(cfqd, cfqq) + jiffies;
}

/*
 * We need to wrap this check in cfq_cfqq_slice_new(), since ->slice_end
 * isn't valid until the first request from the dispatch is activated
 * and the slice time set.
 */
static inline int cfq_slice_used(struct cfq_queue *cfqq)
{
	if (cfq_cfqq_slice_new(cfqq))
		return 0;
	if (time_before(jiffies, cfqq->slice_end))
		return 0;

	return 1;
}

/*
 * Lifted from AS - choose which of rq1 and rq2 that is best served now.
 * We choose the request that is closest to the head right now. Distance
 * behind the head is penalized and only allowed to a certain extent.
 */
static struct request *
cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2)
{
	sector_t last, s1, s2, d1 = 0, d2 = 0;
	unsigned long back_max;
#define CFQ_RQ1_WRAP	0x01 /* request 1 wraps */
#define CFQ_RQ2_WRAP	0x02 /* request 2 wraps */
	unsigned wrap = 0; /* bit mask: requests behind the disk head? */

	if (rq1 == NULL || rq1 == rq2)
		return rq2;
	if (rq2 == NULL)
		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 (rq_is_meta(rq1) && !rq_is_meta(rq2))
		return rq1;
	else if (rq_is_meta(rq2) && !rq_is_meta(rq1))
		return rq2;

	s1 = rq1->sector;
	s2 = rq2->sector;

	last = cfqd->last_position;

	/*
	 * by definition, 1KiB is 2 sectors
	 */
	back_max = cfqd->cfq_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) * cfqd->cfq_back_penalty;
	else
		wrap |= CFQ_RQ1_WRAP;

	if (s2 >= last)
		d2 = s2 - last;
	else if (s2 + back_max >= last)
		d2 = (last - s2) * cfqd->cfq_back_penalty;
	else
		wrap |= CFQ_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;
		else {
			if (s1 >= s2)
				return rq1;
			else
				return rq2;
		}

	case CFQ_RQ2_WRAP:
		return rq1;
	case CFQ_RQ1_WRAP:
		return rq2;
	case (CFQ_RQ1_WRAP|CFQ_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;
	}
}

/*
 * The below is leftmost cache rbtree addon
 */
static struct rb_node *cfq_rb_first(struct cfq_rb_root *root)
{
	if (!root->left)
		root->left = rb_first(&root->rb);

	return root->left;
}

static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root)
{
	if (root->left == n)
		root->left = NULL;

	rb_erase(n, &root->rb);
	RB_CLEAR_NODE(n);
}

/*
 * would be nice to take fifo expire time into account as well
 */
static struct request *
cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		  struct request *last)
{
	struct rb_node *rbnext = rb_next(&last->rb_node);
	struct rb_node *rbprev = rb_prev(&last->rb_node);
	struct request *next = NULL, *prev = NULL;

	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(&cfqq->sort_list);
		if (rbnext && rbnext != &last->rb_node)
			next = rb_entry_rq(rbnext);
	}

	return cfq_choose_req(cfqd, next, prev);
}

static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
				      struct cfq_queue *cfqq)
{
	/*
	 * just an approximation, should be ok.
	 */
	return (cfqd->busy_queues - 1) * (cfq_prio_slice(cfqd, 1, 0) -
		       cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio));
}

/*
 * The cfqd->service_tree holds all pending cfq_queue's that have
 * requests waiting to be processed. It is sorted in the order that
 * we will service the queues.
 */
static void cfq_service_tree_add(struct cfq_data *cfqd,
				    struct cfq_queue *cfqq, int add_front)
{
	struct rb_node **p = &cfqd->service_tree.rb.rb_node;
	struct rb_node *parent = NULL;
	unsigned long rb_key;
	int left;

	if (!add_front) {
		rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies;
		rb_key += cfqq->slice_resid;
		cfqq->slice_resid = 0;
	} else
		rb_key = 0;

	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
		/*
		 * same position, nothing more to do
		 */
		if (rb_key == cfqq->rb_key)
			return;

		cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree);
	}

	left = 1;
	while (*p) {
		struct cfq_queue *__cfqq;
		struct rb_node **n;

		parent = *p;
		__cfqq = rb_entry(parent, struct cfq_queue, rb_node);

		/*
		 * sort RT queues first, we always want to give
		 * preference to them. IDLE queues goes to the back.
		 * after that, sort on the next service time.
		 */
		if (cfq_class_rt(cfqq) > cfq_class_rt(__cfqq))
			n = &(*p)->rb_left;
		else if (cfq_class_rt(cfqq) < cfq_class_rt(__cfqq))
			n = &(*p)->rb_right;
		else if (cfq_class_idle(cfqq) < cfq_class_idle(__cfqq))
			n = &(*p)->rb_left;
		else if (cfq_class_idle(cfqq) > cfq_class_idle(__cfqq))
			n = &(*p)->rb_right;
		else if (rb_key < __cfqq->rb_key)
			n = &(*p)->rb_left;
		else
			n = &(*p)->rb_right;

		if (n == &(*p)->rb_right)
			left = 0;

		p = n;
	}

	if (left)
		cfqd->service_tree.left = &cfqq->rb_node;

	cfqq->rb_key = rb_key;
	rb_link_node(&cfqq->rb_node, parent, p);
	rb_insert_color(&cfqq->rb_node, &cfqd->service_tree.rb);
}

/*
 * Update cfqq's position in the service tree.
 */
static void cfq_resort_rr_list(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	/*
	 * Resorting requires the cfqq to be on the RR list already.
	 */
	if (cfq_cfqq_on_rr(cfqq))
		cfq_service_tree_add(cfqd, cfqq, 0);
}

/*
 * add to busy list of queues for service, trying to be fair in ordering
 * the pending list according to last request service
 */
static inline void
cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	BUG_ON(cfq_cfqq_on_rr(cfqq));
	cfq_mark_cfqq_on_rr(cfqq);
	cfqd->busy_queues++;

	cfq_resort_rr_list(cfqd, cfqq);
}

/*
 * Called when the cfqq no longer has requests pending, remove it from
 * the service tree.
 */
static inline void
cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	BUG_ON(!cfq_cfqq_on_rr(cfqq));
	cfq_clear_cfqq_on_rr(cfqq);

	if (!RB_EMPTY_NODE(&cfqq->rb_node))
		cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree);

	BUG_ON(!cfqd->busy_queues);
	cfqd->busy_queues--;
}

/*
 * rb tree support functions
 */
static inline void cfq_del_rq_rb(struct request *rq)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);
	struct cfq_data *cfqd = cfqq->cfqd;
	const int sync = rq_is_sync(rq);

	BUG_ON(!cfqq->queued[sync]);
	cfqq->queued[sync]--;

	elv_rb_del(&cfqq->sort_list, rq);

	if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list))
		cfq_del_cfqq_rr(cfqd, cfqq);
}

static void cfq_add_rq_rb(struct request *rq)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);
	struct cfq_data *cfqd = cfqq->cfqd;
	struct request *__alias;

	cfqq->queued[rq_is_sync(rq)]++;

	/*
	 * looks a little odd, but the first insert might return an alias.
	 * if that happens, put the alias on the dispatch list
	 */
	while ((__alias = elv_rb_add(&cfqq->sort_list, rq)) != NULL)
		cfq_dispatch_insert(cfqd->queue, __alias);

	if (!cfq_cfqq_on_rr(cfqq))
		cfq_add_cfqq_rr(cfqd, cfqq);

	/*
	 * check if this request is a better next-serve candidate
	 */
	cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq);
	BUG_ON(!cfqq->next_rq);
}

static inline void
cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq)
{
	elv_rb_del(&cfqq->sort_list, rq);
	cfqq->queued[rq_is_sync(rq)]--;
	cfq_add_rq_rb(rq);
}

static struct request *
cfq_find_rq_fmerge(struct cfq_data *cfqd, struct bio *bio)
{
	struct task_struct *tsk = current;
	pid_t key = cfq_queue_pid(tsk, bio_data_dir(bio), bio_sync(bio));
	struct cfq_queue *cfqq;

	cfqq = cfq_find_cfq_hash(cfqd, key, tsk->ioprio);
	if (cfqq) {
		sector_t sector = bio->bi_sector + bio_sectors(bio);

		return elv_rb_find(&cfqq->sort_list, sector);
	}

	return NULL;
}

static void cfq_activate_request(request_queue_t *q, struct request *rq)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;

	cfqd->rq_in_driver++;

	/*
	 * If the depth is larger 1, it really could be queueing. But lets
	 * make the mark a little higher - idling could still be good for
	 * low queueing, and a low queueing number could also just indicate
	 * a SCSI mid layer like behaviour where limit+1 is often seen.
	 */
	if (!cfqd->hw_tag && cfqd->rq_in_driver > 4)
		cfqd->hw_tag = 1;

	cfqd->last_position = rq->hard_sector + rq->hard_nr_sectors;
}

static void cfq_deactivate_request(request_queue_t *q, struct request *rq)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;

	WARN_ON(!cfqd->rq_in_driver);
	cfqd->rq_in_driver--;
}

static void cfq_remove_request(struct request *rq)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);

	if (cfqq->next_rq == rq)
		cfqq->next_rq = cfq_find_next_rq(cfqq->cfqd, cfqq, rq);

	list_del_init(&rq->queuelist);
	cfq_del_rq_rb(rq);

	if (rq_is_meta(rq)) {
		WARN_ON(!cfqq->meta_pending);
		cfqq->meta_pending--;
	}
}

static int cfq_merge(request_queue_t *q, struct request **req, struct bio *bio)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct request *__rq;

	__rq = cfq_find_rq_fmerge(cfqd, bio);
	if (__rq && elv_rq_merge_ok(__rq, bio)) {
		*req = __rq;
		return ELEVATOR_FRONT_MERGE;
	}

	return ELEVATOR_NO_MERGE;
}

static void cfq_merged_request(request_queue_t *q, struct request *req,
			       int type)
{
	if (type == ELEVATOR_FRONT_MERGE) {
		struct cfq_queue *cfqq = RQ_CFQQ(req);

		cfq_reposition_rq_rb(cfqq, req);
	}
}

static void
cfq_merged_requests(request_queue_t *q, struct request *rq,
		    struct request *next)
{
	/*
	 * reposition in fifo if next is older than rq
	 */
	if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
	    time_before(next->start_time, rq->start_time))
		list_move(&rq->queuelist, &next->queuelist);

	cfq_remove_request(next);
}

static int cfq_allow_merge(request_queue_t *q, struct request *rq,
			   struct bio *bio)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	const int rw = bio_data_dir(bio);
	struct cfq_queue *cfqq;
	pid_t key;

	/*
	 * Disallow merge of a sync bio into an async request.
	 */
	if ((bio_data_dir(bio) == READ || bio_sync(bio)) && !rq_is_sync(rq))
		return 0;

	/*
	 * Lookup the cfqq that this bio will be queued with. Allow
	 * merge only if rq is queued there.
	 */
	key = cfq_queue_pid(current, rw, bio_sync(bio));
	cfqq = cfq_find_cfq_hash(cfqd, key, current->ioprio);

	if (cfqq == RQ_CFQQ(rq))
		return 1;

	return 0;
}

static inline void
__cfq_set_active_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	if (cfqq) {
		/*
		 * stop potential idle class queues waiting service
		 */
		del_timer(&cfqd->idle_class_timer);

		cfqq->slice_end = 0;
		cfq_clear_cfqq_must_alloc_slice(cfqq);
		cfq_clear_cfqq_fifo_expire(cfqq);
		cfq_mark_cfqq_slice_new(cfqq);
		cfq_clear_cfqq_queue_new(cfqq);
	}

	cfqd->active_queue = cfqq;
}

/*
 * current cfqq expired its slice (or was too idle), select new one
 */
static void
__cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		    int preempted, int timed_out)
{
	if (cfq_cfqq_wait_request(cfqq))
		del_timer(&cfqd->idle_slice_timer);

	cfq_clear_cfqq_must_dispatch(cfqq);
	cfq_clear_cfqq_wait_request(cfqq);

	/*
	 * store what was left of this slice, if the queue idled out
	 * or was preempted
	 */
	if (timed_out && !cfq_cfqq_slice_new(cfqq))
		cfqq->slice_resid = cfqq->slice_end - jiffies;

	cfq_resort_rr_list(cfqd, cfqq);

	if (cfqq == cfqd->active_queue)
		cfqd->active_queue = NULL;

	if (cfqd->active_cic) {
		put_io_context(cfqd->active_cic->ioc);
		cfqd->active_cic = NULL;
	}

	cfqd->dispatch_slice = 0;
}

static inline void cfq_slice_expired(struct cfq_data *cfqd, int preempted,
				     int timed_out)
{
	struct cfq_queue *cfqq = cfqd->active_queue;

	if (cfqq)
		__cfq_slice_expired(cfqd, cfqq, preempted, timed_out);
}

/*
 * Get next queue for service. Unless we have a queue preemption,
 * we'll simply select the first cfqq in the service tree.
 */
static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
{
	struct cfq_queue *cfqq;
	struct rb_node *n;

	if (RB_EMPTY_ROOT(&cfqd->service_tree.rb))
		return NULL;

	n = cfq_rb_first(&cfqd->service_tree);
	cfqq = rb_entry(n, struct cfq_queue, rb_node);

	if (cfq_class_idle(cfqq)) {
		unsigned long end;

		/*
		 * if we have idle queues and no rt or be queues had
		 * pending requests, either allow immediate service if
		 * the grace period has passed or arm the idle grace
		 * timer
		 */
		end = cfqd->last_end_request + CFQ_IDLE_GRACE;
		if (time_before(jiffies, end)) {
			mod_timer(&cfqd->idle_class_timer, end);
			cfqq = NULL;
		}
	}

	return cfqq;
}

/*
 * Get and set a new active queue for service.
 */
static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd)
{
	struct cfq_queue *cfqq;

	cfqq = cfq_get_next_queue(cfqd);
	__cfq_set_active_queue(cfqd, cfqq);
	return cfqq;
}

static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
					  struct request *rq)
{
	if (rq->sector >= cfqd->last_position)
		return rq->sector - cfqd->last_position;
	else
		return cfqd->last_position - rq->sector;
}

static inline int cfq_rq_close(struct cfq_data *cfqd, struct request *rq)
{
	struct cfq_io_context *cic = cfqd->active_cic;

	if (!sample_valid(cic->seek_samples))
		return 0;

	return cfq_dist_from_last(cfqd, rq) <= cic->seek_mean;
}

static int cfq_close_cooperator(struct cfq_data *cfq_data,
				struct cfq_queue *cfqq)
{
	/*
	 * We should notice if some of the queues are cooperating, eg
	 * working closely on the same area of the disk. In that case,
	 * we can group them together and don't waste time idling.
	 */
	return 0;
}

#define CIC_SEEKY(cic) ((cic)->seek_mean > (8 * 1024))

static void cfq_arm_slice_timer(struct cfq_data *cfqd)
{
	struct cfq_queue *cfqq = cfqd->active_queue;
	struct cfq_io_context *cic;
	unsigned long sl;

	WARN_ON(!RB_EMPTY_ROOT(&cfqq->sort_list));
	WARN_ON(cfq_cfqq_slice_new(cfqq));

	/*
	 * idle is disabled, either manually or by past process history
	 */
	if (!cfqd->cfq_slice_idle || !cfq_cfqq_idle_window(cfqq))
		return;

	/*
	 * task has exited, don't wait
	 */
	cic = cfqd->active_cic;
	if (!cic || !cic->ioc->task)
		return;

	/*
	 * See if this prio level has a good candidate
	 */
	if (cfq_close_cooperator(cfqd, cfqq) &&
	    (sample_valid(cic->ttime_samples) && cic->ttime_mean > 2))
		return;

	cfq_mark_cfqq_must_dispatch(cfqq);
	cfq_mark_cfqq_wait_request(cfqq);

	/*
	 * we don't want to idle for seeks, but we do want to allow
	 * fair distribution of slice time for a process doing back-to-back
	 * seeks. so allow a little bit of time for him to submit a new rq
	 */
	sl = cfqd->cfq_slice_idle;
	if (sample_valid(cic->seek_samples) && CIC_SEEKY(cic))
		sl = min(sl, msecs_to_jiffies(CFQ_MIN_TT));

	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
}

/*
 * Move request from internal lists to the request queue dispatch list.
 */
static void cfq_dispatch_insert(request_queue_t *q, struct request *rq)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);

	cfq_remove_request(rq);
	cfqq->dispatched++;
	elv_dispatch_sort(q, rq);
}

/*
 * return expired entry, or NULL to just start from scratch in rbtree
 */
static inline struct request *cfq_check_fifo(struct cfq_queue *cfqq)
{
	struct cfq_data *cfqd = cfqq->cfqd;
	struct request *rq;
	int fifo;

	if (cfq_cfqq_fifo_expire(cfqq))
		return NULL;

	cfq_mark_cfqq_fifo_expire(cfqq);

	if (list_empty(&cfqq->fifo))
		return NULL;

	fifo = cfq_cfqq_sync(cfqq);
	rq = rq_entry_fifo(cfqq->fifo.next);

	if (time_before(jiffies, rq->start_time + cfqd->cfq_fifo_expire[fifo]))
		return NULL;

	return rq;
}

static inline int
cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	const int base_rq = cfqd->cfq_slice_async_rq;

	WARN_ON(cfqq->ioprio >= IOPRIO_BE_NR);

	return 2 * (base_rq + base_rq * (CFQ_PRIO_LISTS - 1 - cfqq->ioprio));
}

/*
 * Select a queue for service. If we have a current active queue,
 * check whether to continue servicing it, or retrieve and set a new one.
 */
static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
{
	struct cfq_queue *cfqq;

	cfqq = cfqd->active_queue;
	if (!cfqq)
		goto new_queue;

	/*
	 * The active queue has run out of time, expire it and select new.
	 */
	if (cfq_slice_used(cfqq))
		goto expire;

	/*
	 * The active queue has requests and isn't expired, allow it to
	 * dispatch.
	 */
	if (!RB_EMPTY_ROOT(&cfqq->sort_list))
		goto keep_queue;

	/*
	 * No requests pending. If the active queue still has requests in
	 * flight or is idling for a new request, allow either of these
	 * conditions to happen (or time out) before selecting a new queue.
	 */
	if (cfqq->dispatched || timer_pending(&cfqd->idle_slice_timer)) {
		cfqq = NULL;
		goto keep_queue;
	}

expire:
	cfq_slice_expired(cfqd, 0, 0);
new_queue:
	cfqq = cfq_set_active_queue(cfqd);
keep_queue:
	return cfqq;
}

/*
 * Dispatch some requests from cfqq, moving them to the request queue
 * dispatch list.
 */
static int
__cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq,
			int max_dispatch)
{
	int dispatched = 0;

	BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));

	do {
		struct request *rq;

		/*
		 * follow expired path, else get first next available
		 */
		if ((rq = cfq_check_fifo(cfqq)) == NULL)
			rq = cfqq->next_rq;

		/*
		 * finally, insert request into driver dispatch list
		 */
		cfq_dispatch_insert(cfqd->queue, rq);

		cfqd->dispatch_slice++;
		dispatched++;

		if (!cfqd->active_cic) {
			atomic_inc(&RQ_CIC(rq)->ioc->refcount);
			cfqd->active_cic = RQ_CIC(rq);
		}

		if (RB_EMPTY_ROOT(&cfqq->sort_list))
			break;

	} while (dispatched < max_dispatch);

	/*
	 * expire an async queue immediately if it has used up its slice. idle
	 * queue always expire after 1 dispatch round.
	 */
	if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
	    cfqd->dispatch_slice >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
	    cfq_class_idle(cfqq))) {
		cfqq->slice_end = jiffies + 1;
		cfq_slice_expired(cfqd, 0, 0);
	}

	return dispatched;
}

static inline int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq)
{
	int dispatched = 0;

	while (cfqq->next_rq) {
		cfq_dispatch_insert(cfqq->cfqd->queue, cfqq->next_rq);
		dispatched++;
	}

	BUG_ON(!list_empty(&cfqq->fifo));
	return dispatched;
}

/*
 * Drain our current requests. Used for barriers and when switching
 * io schedulers on-the-fly.
 */
static int cfq_forced_dispatch(struct cfq_data *cfqd)
{
	int dispatched = 0;
	struct rb_node *n;

	while ((n = cfq_rb_first(&cfqd->service_tree)) != NULL) {
		struct cfq_queue *cfqq = rb_entry(n, struct cfq_queue, rb_node);

		dispatched += __cfq_forced_dispatch_cfqq(cfqq);
	}

	cfq_slice_expired(cfqd, 0, 0);

	BUG_ON(cfqd->busy_queues);

	return dispatched;
}

static int cfq_dispatch_requests(request_queue_t *q, int force)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct cfq_queue *cfqq;
	int dispatched;

	if (!cfqd->busy_queues)
		return 0;

	if (unlikely(force))
		return cfq_forced_dispatch(cfqd);

	dispatched = 0;
	while ((cfqq = cfq_select_queue(cfqd)) != NULL) {
		int max_dispatch;

		if (cfqd->busy_queues > 1) {
			/*
			 * So we have dispatched before in this round, if the
			 * next queue has idling enabled (must be sync), don't
			 * allow it service until the previous have completed.
			 */
			if (cfqd->rq_in_driver && cfq_cfqq_idle_window(cfqq) &&
			    dispatched)
				break;
			if (cfqq->dispatched >= cfqd->cfq_quantum)
				break;
		}

		cfq_clear_cfqq_must_dispatch(cfqq);
		cfq_clear_cfqq_wait_request(cfqq);
		del_timer(&cfqd->idle_slice_timer);

		max_dispatch = cfqd->cfq_quantum;
		if (cfq_class_idle(cfqq))
			max_dispatch = 1;

		dispatched += __cfq_dispatch_requests(cfqd, cfqq, max_dispatch);
	}

	return dispatched;
}

/*
 * 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.
 */
static void cfq_put_queue(struct cfq_queue *cfqq)
{
	struct cfq_data *cfqd = cfqq->cfqd;

	BUG_ON(atomic_read(&cfqq->ref) <= 0);

	if (!atomic_dec_and_test(&cfqq->ref))
		return;

	BUG_ON(rb_first(&cfqq->sort_list));
	BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
	BUG_ON(cfq_cfqq_on_rr(cfqq));

	if (unlikely(cfqd->active_queue == cfqq)) {
		__cfq_slice_expired(cfqd, cfqq, 0, 0);
		cfq_schedule_dispatch(cfqd);
	}

	/*
	 * it's on the empty list and still hashed
	 */
	hlist_del(&cfqq->cfq_hash);
	kmem_cache_free(cfq_pool, cfqq);
}

static struct cfq_queue *
__cfq_find_cfq_hash(struct cfq_data *cfqd, unsigned int key, unsigned int prio,
		    const int hashval)
{
	struct hlist_head *hash_list = &cfqd->cfq_hash[hashval];
	struct hlist_node *entry;
	struct cfq_queue *__cfqq;

	hlist_for_each_entry(__cfqq, entry, hash_list, cfq_hash) {
		const unsigned short __p = IOPRIO_PRIO_VALUE(__cfqq->org_ioprio_class, __cfqq->org_ioprio);

		if (__cfqq->key == key && (__p == prio || !prio))
			return __cfqq;
	}

	return NULL;
}

static struct cfq_queue *
cfq_find_cfq_hash(struct cfq_data *cfqd, unsigned int key, unsigned short prio)
{
	return __cfq_find_cfq_hash(cfqd, key, prio, hash_long(key, CFQ_QHASH_SHIFT));
}

static void cfq_free_io_context(struct io_context *ioc)
{
	struct cfq_io_context *__cic;
	struct rb_node *n;
	int freed = 0;

	while ((n = rb_first(&ioc->cic_root)) != NULL) {
		__cic = rb_entry(n, struct cfq_io_context, rb_node);
		rb_erase(&__cic->rb_node, &ioc->cic_root);
		kmem_cache_free(cfq_ioc_pool, __cic);
		freed++;
	}

	elv_ioc_count_mod(ioc_count, -freed);

	if (ioc_gone && !elv_ioc_count_read(ioc_count))
		complete(ioc_gone);
}

static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	if (unlikely(cfqq == cfqd->active_queue)) {
		__cfq_slice_expired(cfqd, cfqq, 0, 0);
		cfq_schedule_dispatch(cfqd);
	}

	cfq_put_queue(cfqq);
}

static void __cfq_exit_single_io_context(struct cfq_data *cfqd,
					 struct cfq_io_context *cic)
{
	list_del_init(&cic->queue_list);
	smp_wmb();
	cic->key = NULL;

	if (cic->cfqq[ASYNC]) {
		cfq_exit_cfqq(cfqd, cic->cfqq[ASYNC]);
		cic->cfqq[ASYNC] = NULL;
	}

	if (cic->cfqq[SYNC]) {
		cfq_exit_cfqq(cfqd, cic->cfqq[SYNC]);
		cic->cfqq[SYNC] = NULL;
	}
}

static void cfq_exit_single_io_context(struct cfq_io_context *cic)
{
	struct cfq_data *cfqd = cic->key;

	if (cfqd) {
		request_queue_t *q = cfqd->queue;

		spin_lock_irq(q->queue_lock);
		__cfq_exit_single_io_context(cfqd, cic);
		spin_unlock_irq(q->queue_lock);
	}
}

/*
 * The process that ioc belongs to has exited, we need to clean up
 * and put the internal structures we have that belongs to that process.
 */
static void cfq_exit_io_context(struct io_context *ioc)
{
	struct cfq_io_context *__cic;
	struct rb_node *n;

	/*
	 * put the reference this task is holding to the various queues
	 */

	n = rb_first(&ioc->cic_root);
	while (n != NULL) {
		__cic = rb_entry(n, struct cfq_io_context, rb_node);

		cfq_exit_single_io_context(__cic);
		n = rb_next(n);
	}
}

static struct cfq_io_context *
cfq_alloc_io_context(struct cfq_data *cfqd, gfp_t gfp_mask)
{
	struct cfq_io_context *cic;

	cic = kmem_cache_alloc_node(cfq_ioc_pool, gfp_mask, cfqd->queue->node);
	if (cic) {
		memset(cic, 0, sizeof(*cic));
		cic->last_end_request = jiffies;
		INIT_LIST_HEAD(&cic->queue_list);
		cic->dtor = cfq_free_io_context;
		cic->exit = cfq_exit_io_context;
		elv_ioc_count_inc(ioc_count);
	}

	return cic;
}

static void cfq_init_prio_data(struct cfq_queue *cfqq)
{
	struct task_struct *tsk = current;
	int ioprio_class;

	if (!cfq_cfqq_prio_changed(cfqq))
		return;

	ioprio_class = IOPRIO_PRIO_CLASS(tsk->ioprio);
	switch (ioprio_class) {
		default:
			printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
		case IOPRIO_CLASS_NONE:
			/*
			 * no prio set, place us in the middle of the BE classes
			 */
			cfqq->ioprio = task_nice_ioprio(tsk);
			cfqq->ioprio_class = IOPRIO_CLASS_BE;
			break;
		case IOPRIO_CLASS_RT:
			cfqq->ioprio = task_ioprio(tsk);
			cfqq->ioprio_class = IOPRIO_CLASS_RT;
			break;
		case IOPRIO_CLASS_BE:
			cfqq->ioprio = task_ioprio(tsk);
			cfqq->ioprio_class = IOPRIO_CLASS_BE;
			break;
		case IOPRIO_CLASS_IDLE:
			cfqq->ioprio_class = IOPRIO_CLASS_IDLE;
			cfqq->ioprio = 7;
			cfq_clear_cfqq_idle_window(cfqq);
			break;
	}

	/*
	 * keep track of original prio settings in case we have to temporarily
	 * elevate the priority of this queue
	 */
	cfqq->org_ioprio = cfqq->ioprio;
	cfqq->org_ioprio_class = cfqq->ioprio_class;
	cfq_clear_cfqq_prio_changed(cfqq);
}

static inline void changed_ioprio(struct cfq_io_context *cic)
{
	struct cfq_data *cfqd = cic->key;
	struct cfq_queue *cfqq;
	unsigned long flags;

	if (unlikely(!cfqd))
		return;

	spin_lock_irqsave(cfqd->queue->queue_lock, flags);

	cfqq = cic->cfqq[ASYNC];
	if (cfqq) {
		struct cfq_queue *new_cfqq;
		new_cfqq = cfq_get_queue(cfqd, CFQ_KEY_ASYNC, cic->ioc->task,
					 GFP_ATOMIC);
		if (new_cfqq) {
			cic->cfqq[ASYNC] = new_cfqq;
			cfq_put_queue(cfqq);
		}
	}

	cfqq = cic->cfqq[SYNC];
	if (cfqq)
		cfq_mark_cfqq_prio_changed(cfqq);

	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
}

static void cfq_ioc_set_ioprio(struct io_context *ioc)
{
	struct cfq_io_context *cic;
	struct rb_node *n;

	ioc->ioprio_changed = 0;

	n = rb_first(&ioc->cic_root);
	while (n != NULL) {
		cic = rb_entry(n, struct cfq_io_context, rb_node);

		changed_ioprio(cic);
		n = rb_next(n);
	}
}

static struct cfq_queue *
cfq_get_queue(struct cfq_data *cfqd, unsigned int key, struct task_struct *tsk,
	      gfp_t gfp_mask)
{
	const int hashval = hash_long(key, CFQ_QHASH_SHIFT);
	struct cfq_queue *cfqq, *new_cfqq = NULL;
	unsigned short ioprio;

retry:
	ioprio = tsk->ioprio;
	cfqq = __cfq_find_cfq_hash(cfqd, key, ioprio, hashval);

	if (!cfqq) {
		if (new_cfqq) {
			cfqq = new_cfqq;
			new_cfqq = NULL;
		} else if (gfp_mask & __GFP_WAIT) {
			/*
			 * Inform the allocator of the fact that we will
			 * just repeat this allocation if it fails, to allow
			 * the allocator to do whatever it needs to attempt to
			 * free memory.
			 */
			spin_unlock_irq(cfqd->queue->queue_lock);
			new_cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask|__GFP_NOFAIL, cfqd->queue->node);
			spin_lock_irq(cfqd->queue->queue_lock);
			goto retry;
		} else {
			cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask, cfqd->queue->node);
			if (!cfqq)
				goto out;
		}

		memset(cfqq, 0, sizeof(*cfqq));

		INIT_HLIST_NODE(&cfqq->cfq_hash);
		RB_CLEAR_NODE(&cfqq->rb_node);
		INIT_LIST_HEAD(&cfqq->fifo);

		cfqq->key = key;
		hlist_add_head(&cfqq->cfq_hash, &cfqd->cfq_hash[hashval]);
		atomic_set(&cfqq->ref, 0);
		cfqq->cfqd = cfqd;

		if (key != CFQ_KEY_ASYNC)
			cfq_mark_cfqq_idle_window(cfqq);

		cfq_mark_cfqq_prio_changed(cfqq);
		cfq_mark_cfqq_queue_new(cfqq);
		cfq_init_prio_data(cfqq);
	}

	if (new_cfqq)
		kmem_cache_free(cfq_pool, new_cfqq);

	atomic_inc(&cfqq->ref);
out:
	WARN_ON((gfp_mask & __GFP_WAIT) && !cfqq);
	return cfqq;
}

/*
 * We drop cfq io contexts lazily, so we may find a dead one.
 */
static void
cfq_drop_dead_cic(struct io_context *ioc, struct cfq_io_context *cic)
{
	WARN_ON(!list_empty(&cic->queue_list));
	rb_erase(&cic->rb_node, &ioc->cic_root);
	kmem_cache_free(cfq_ioc_pool, cic);
	elv_ioc_count_dec(ioc_count);
}

static struct cfq_io_context *
cfq_cic_rb_lookup(struct cfq_data *cfqd, struct io_context *ioc)
{
	struct rb_node *n;
	struct cfq_io_context *cic;
	void *k, *key = cfqd;

restart:
	n = ioc->cic_root.rb_node;
	while (n) {
		cic = rb_entry(n, struct cfq_io_context, rb_node);
		/* ->key must be copied to avoid race with cfq_exit_queue() */
		k = cic->key;
		if (unlikely(!k)) {
			cfq_drop_dead_cic(ioc, cic);
			goto restart;
		}

		if (key < k)
			n = n->rb_left;
		else if (key > k)
			n = n->rb_right;
		else
			return cic;
	}

	return NULL;
}

static inline void
cfq_cic_link(struct cfq_data *cfqd, struct io_context *ioc,
	     struct cfq_io_context *cic)
{
	struct rb_node **p;
	struct rb_node *parent;
	struct cfq_io_context *__cic;
	unsigned long flags;
	void *k;

	cic->ioc = ioc;
	cic->key = cfqd;

restart:
	parent = NULL;
	p = &ioc->cic_root.rb_node;
	while (*p) {
		parent = *p;
		__cic = rb_entry(parent, struct cfq_io_context, rb_node);
		/* ->key must be copied to avoid race with cfq_exit_queue() */
		k = __cic->key;
		if (unlikely(!k)) {
			cfq_drop_dead_cic(ioc, __cic);
			goto restart;
		}

		if (cic->key < k)
			p = &(*p)->rb_left;
		else if (cic->key > k)
			p = &(*p)->rb_right;
		else
			BUG();
	}

	rb_link_node(&cic->rb_node, parent, p);
	rb_insert_color(&cic->rb_node, &ioc->cic_root);

	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
	list_add(&cic->queue_list, &cfqd->cic_list);
	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
}

/*
 * Setup general io context and cfq io context. There can be several cfq
 * io contexts per general io context, if this process is doing io to more
 * than one device managed by cfq.
 */
static struct cfq_io_context *
cfq_get_io_context(struct cfq_data *cfqd, gfp_t gfp_mask)
{
	struct io_context *ioc = NULL;
	struct cfq_io_context *cic;

	might_sleep_if(gfp_mask & __GFP_WAIT);

	ioc = get_io_context(gfp_mask, cfqd->queue->node);
	if (!ioc)
		return NULL;

	cic = cfq_cic_rb_lookup(cfqd, ioc);
	if (cic)
		goto out;

	cic = cfq_alloc_io_context(cfqd, gfp_mask);
	if (cic == NULL)
		goto err;

	cfq_cic_link(cfqd, ioc, cic);
out:
	smp_read_barrier_depends();
	if (unlikely(ioc->ioprio_changed))
		cfq_ioc_set_ioprio(ioc);

	return cic;
err:
	put_io_context(ioc);
	return NULL;
}

static void
cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_io_context *cic)
{
	unsigned long elapsed = jiffies - cic->last_end_request;
	unsigned long ttime = min(elapsed, 2UL * cfqd->cfq_slice_idle);

	cic->ttime_samples = (7*cic->ttime_samples + 256) / 8;
	cic->ttime_total = (7*cic->ttime_total + 256*ttime) / 8;
	cic->ttime_mean = (cic->ttime_total + 128) / cic->ttime_samples;
}

static void
cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic,
		       struct request *rq)
{
	sector_t sdist;
	u64 total;

	if (cic->last_request_pos < rq->sector)
		sdist = rq->sector - cic->last_request_pos;
	else
		sdist = cic->last_request_pos - rq->sector;

	if (!cic->seek_samples) {
		cfqd->new_seek_total = (7*cic->seek_total + (u64)256*sdist) / 8;
		cfqd->new_seek_mean = cfqd->new_seek_total / 256;
	}

	/*
	 * Don't allow the seek distance to get too large from the
	 * odd fragment, pagein, etc
	 */
	if (cic->seek_samples <= 60) /* second&third seek */
		sdist = min(sdist, (cic->seek_mean * 4) + 2*1024*1024);
	else
		sdist = min(sdist, (cic->seek_mean * 4)	+ 2*1024*64);

	cic->seek_samples = (7*cic->seek_samples + 256) / 8;
	cic->seek_total = (7*cic->seek_total + (u64)256*sdist) / 8;
	total = cic->seek_total + (cic->seek_samples/2);
	do_div(total, cic->seek_samples);
	cic->seek_mean = (sector_t)total;
}

/*
 * Disable idle window if the process thinks too long or seeks so much that
 * it doesn't matter
 */
static void
cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		       struct cfq_io_context *cic)
{
	int enable_idle = cfq_cfqq_idle_window(cfqq);

	if (!cic->ioc->task || !cfqd->cfq_slice_idle ||
	    (cfqd->hw_tag && CIC_SEEKY(cic)))
		enable_idle = 0;
	else if (sample_valid(cic->ttime_samples)) {
		if (cic->ttime_mean > cfqd->cfq_slice_idle)
			enable_idle = 0;
		else
			enable_idle = 1;
	}

	if (enable_idle)
		cfq_mark_cfqq_idle_window(cfqq);
	else
		cfq_clear_cfqq_idle_window(cfqq);
}

/*
 * Check if new_cfqq should preempt the currently active queue. Return 0 for
 * no or if we aren't sure, a 1 will cause a preempt.
 */
static int
cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
		   struct request *rq)
{
	struct cfq_queue *cfqq;

	cfqq = cfqd->active_queue;
	if (!cfqq)
		return 0;

	if (cfq_slice_used(cfqq))
		return 1;

	if (cfq_class_idle(new_cfqq))
		return 0;

	if (cfq_class_idle(cfqq))
		return 1;

	/*
	 * if the new request is sync, but the currently running queue is
	 * not, let the sync request have priority.
	 */
	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
		return 1;

	/*
	 * So both queues are sync. Let the new request get disk time if
	 * it's a metadata request and the current queue is doing regular IO.
	 */
	if (rq_is_meta(rq) && !cfqq->meta_pending)
		return 1;

	if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
		return 0;

	/*
	 * if this request is as-good as one we would expect from the
	 * current cfqq, let it preempt
	 */
	if (cfq_rq_close(cfqd, rq))
		return 1;

	return 0;
}

/*
 * cfqq preempts the active queue. if we allowed preempt with no slice left,
 * let it have half of its nominal slice.
 */
static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	cfq_slice_expired(cfqd, 1, 1);

	/*
	 * Put the new queue at the front of the of the current list,
	 * so we know that it will be selected next.
	 */
	BUG_ON(!cfq_cfqq_on_rr(cfqq));

	cfq_service_tree_add(cfqd, cfqq, 1);

	cfqq->slice_end = 0;
	cfq_mark_cfqq_slice_new(cfqq);
}

/*
 * Called when a new fs request (rq) is added (to cfqq). Check if there's
 * something we should do about it
 */
static void
cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		struct request *rq)
{
	struct cfq_io_context *cic = RQ_CIC(rq);

	if (rq_is_meta(rq))
		cfqq->meta_pending++;

	cfq_update_io_thinktime(cfqd, cic);
	cfq_update_io_seektime(cfqd, cic, rq);
	cfq_update_idle_window(cfqd, cfqq, cic);

	cic->last_request_pos = rq->sector + rq->nr_sectors;
	cfqq->last_request_pos = cic->last_request_pos;

	if (cfqq == cfqd->active_queue) {
		/*
		 * if we are waiting for a request for this queue, let it rip
		 * immediately and flag that we must not expire this queue
		 * just now
		 */
		if (cfq_cfqq_wait_request(cfqq)) {
			cfq_mark_cfqq_must_dispatch(cfqq);
			del_timer(&cfqd->idle_slice_timer);
			blk_start_queueing(cfqd->queue);
		}
	} else if (cfq_should_preempt(cfqd, cfqq, rq)) {
		/*
		 * not the active queue - expire current slice if it is
		 * idle and has expired it's mean thinktime or this new queue
		 * has some old slice time left and is of higher priority
		 */
		cfq_preempt_queue(cfqd, cfqq);
		cfq_mark_cfqq_must_dispatch(cfqq);
		blk_start_queueing(cfqd->queue);
	}
}

static void cfq_insert_request(request_queue_t *q, struct request *rq)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct cfq_queue *cfqq = RQ_CFQQ(rq);

	cfq_init_prio_data(cfqq);

	cfq_add_rq_rb(rq);

	list_add_tail(&rq->queuelist, &cfqq->fifo);

	cfq_rq_enqueued(cfqd, cfqq, rq);
}

static void cfq_completed_request(request_queue_t *q, struct request *rq)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);
	struct cfq_data *cfqd = cfqq->cfqd;
	const int sync = rq_is_sync(rq);
	unsigned long now;

	now = jiffies;

	WARN_ON(!cfqd->rq_in_driver);
	WARN_ON(!cfqq->dispatched);
	cfqd->rq_in_driver--;
	cfqq->dispatched--;

	if (!cfq_class_idle(cfqq))
		cfqd->last_end_request = now;

	if (sync)
		RQ_CIC(rq)->last_end_request = now;

	/*
	 * If this is the active queue, check if it needs to be expired,
	 * or if we want to idle in case it has no pending requests.
	 */
	if (cfqd->active_queue == cfqq) {
		if (cfq_cfqq_slice_new(cfqq)) {
			cfq_set_prio_slice(cfqd, cfqq);
			cfq_clear_cfqq_slice_new(cfqq);
		}
		if (cfq_slice_used(cfqq))
			cfq_slice_expired(cfqd, 0, 1);
		else if (sync && RB_EMPTY_ROOT(&cfqq->sort_list))
			cfq_arm_slice_timer(cfqd);
	}

	if (!cfqd->rq_in_driver)
		cfq_schedule_dispatch(cfqd);
}

/*
 * we temporarily boost lower priority queues if they are holding fs exclusive
 * resources. they are boosted to normal prio (CLASS_BE/4)
 */
static void cfq_prio_boost(struct cfq_queue *cfqq)
{
	if (has_fs_excl()) {
		/*
		 * boost idle prio on transactions that would lock out other
		 * users of the filesystem
		 */
		if (cfq_class_idle(cfqq))
			cfqq->ioprio_class = IOPRIO_CLASS_BE;
		if (cfqq->ioprio > IOPRIO_NORM)
			cfqq->ioprio = IOPRIO_NORM;
	} else {
		/*
		 * check if we need to unboost the queue
		 */
		if (cfqq->ioprio_class != cfqq->org_ioprio_class)
			cfqq->ioprio_class = cfqq->org_ioprio_class;
		if (cfqq->ioprio != cfqq->org_ioprio)
			cfqq->ioprio = cfqq->org_ioprio;
	}
}

static inline int __cfq_may_queue(struct cfq_queue *cfqq)
{
	if ((cfq_cfqq_wait_request(cfqq) || cfq_cfqq_must_alloc(cfqq)) &&
	    !cfq_cfqq_must_alloc_slice(cfqq)) {
		cfq_mark_cfqq_must_alloc_slice(cfqq);
		return ELV_MQUEUE_MUST;
	}

	return ELV_MQUEUE_MAY;
}

static int cfq_may_queue(request_queue_t *q, int rw)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct task_struct *tsk = current;
	struct cfq_queue *cfqq;
	unsigned int key;

	key = cfq_queue_pid(tsk, rw, rw & REQ_RW_SYNC);

	/*
	 * 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
	 */
	cfqq = cfq_find_cfq_hash(cfqd, key, tsk->ioprio);
	if (cfqq) {
		cfq_init_prio_data(cfqq);
		cfq_prio_boost(cfqq);

		return __cfq_may_queue(cfqq);
	}

	return ELV_MQUEUE_MAY;
}

/*
 * queue lock held here
 */
static void cfq_put_request(struct request *rq)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);

	if (cfqq) {
		const int rw = rq_data_dir(rq);

		BUG_ON(!cfqq->allocated[rw]);
		cfqq->allocated[rw]--;

		put_io_context(RQ_CIC(rq)->ioc);

		rq->elevator_private = NULL;
		rq->elevator_private2 = NULL;

		cfq_put_queue(cfqq);
	}
}

/*
 * Allocate cfq data structures associated with this request.
 */
static int
cfq_set_request(request_queue_t *q, struct request *rq, gfp_t gfp_mask)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct task_struct *tsk = current;
	struct cfq_io_context *cic;
	const int rw = rq_data_dir(rq);
	const int is_sync = rq_is_sync(rq);
	pid_t key = cfq_queue_pid(tsk, rw, is_sync);
	struct cfq_queue *cfqq;
	unsigned long flags;

	might_sleep_if(gfp_mask & __GFP_WAIT);

	cic = cfq_get_io_context(cfqd, gfp_mask);

	spin_lock_irqsave(q->queue_lock, flags);

	if (!cic)
		goto queue_fail;

	if (!cic->cfqq[is_sync]) {
		cfqq = cfq_get_queue(cfqd, key, tsk, gfp_mask);
		if (!cfqq)
			goto queue_fail;

		cic->cfqq[is_sync] = cfqq;
	} else
		cfqq = cic->cfqq[is_sync];

	cfqq->allocated[rw]++;
	cfq_clear_cfqq_must_alloc(cfqq);
	atomic_inc(&cfqq->ref);

	spin_unlock_irqrestore(q->queue_lock, flags);

	rq->elevator_private = cic;
	rq->elevator_private2 = cfqq;
	return 0;

queue_fail:
	if (cic)
		put_io_context(cic->ioc);

	cfq_schedule_dispatch(cfqd);
	spin_unlock_irqrestore(q->queue_lock, flags);
	return 1;
}

static void cfq_kick_queue(struct work_struct *work)
{
	struct cfq_data *cfqd =
		container_of(work, struct cfq_data, unplug_work);
	request_queue_t *q = cfqd->queue;
	unsigned long flags;

	spin_lock_irqsave(q->queue_lock, flags);
	blk_start_queueing(q);
	spin_unlock_irqrestore(q->queue_lock, flags);
}

/*
 * Timer running if the active_queue is currently idling inside its time slice
 */
static void cfq_idle_slice_timer(unsigned long data)
{
	struct cfq_data *cfqd = (struct cfq_data *) data;
	struct cfq_queue *cfqq;
	unsigned long flags;
	int timed_out = 1;

	spin_lock_irqsave(cfqd->queue->queue_lock, flags);

	if ((cfqq = cfqd->active_queue) != NULL) {
		timed_out = 0;

		/*
		 * expired
		 */
		if (cfq_slice_used(cfqq))
			goto expire;

		/*
		 * only expire and reinvoke request handler, if there are
		 * other queues with pending requests
		 */
		if (!cfqd->busy_queues)
			goto out_cont;

		/*
		 * not expired and it has a request pending, let it dispatch
		 */
		if (!RB_EMPTY_ROOT(&cfqq->sort_list)) {
			cfq_mark_cfqq_must_dispatch(cfqq);
			goto out_kick;
		}
	}
expire:
	cfq_slice_expired(cfqd, 0, timed_out);
out_kick:
	cfq_schedule_dispatch(cfqd);
out_cont:
	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
}

/*
 * Timer running if an idle class queue is waiting for service
 */
static void cfq_idle_class_timer(unsigned long data)
{
	struct cfq_data *cfqd = (struct cfq_data *) data;
	unsigned long flags, end;

	spin_lock_irqsave(cfqd->queue->queue_lock, flags);

	/*
	 * race with a non-idle queue, reset timer
	 */
	end = cfqd->last_end_request + CFQ_IDLE_GRACE;
	if (!time_after_eq(jiffies, end))
		mod_timer(&cfqd->idle_class_timer, end);
	else
		cfq_schedule_dispatch(cfqd);

	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
}

static void cfq_shutdown_timer_wq(struct cfq_data *cfqd)
{
	del_timer_sync(&cfqd->idle_slice_timer);
	del_timer_sync(&cfqd->idle_class_timer);
	blk_sync_queue(cfqd->queue);
}

static void cfq_exit_queue(elevator_t *e)
{
	struct cfq_data *cfqd = e->elevator_data;
	request_queue_t *q = cfqd->queue;

	cfq_shutdown_timer_wq(cfqd);

	spin_lock_irq(q->queue_lock);

	if (cfqd->active_queue)
		__cfq_slice_expired(cfqd, cfqd->active_queue, 0, 0);

	while (!list_empty(&cfqd->cic_list)) {
		struct cfq_io_context *cic = list_entry(cfqd->cic_list.next,
							struct cfq_io_context,
							queue_list);

		__cfq_exit_single_io_context(cfqd, cic);
	}

	spin_unlock_irq(q->queue_lock);

	cfq_shutdown_timer_wq(cfqd);

	kfree(cfqd->cfq_hash);
	kfree(cfqd);
}

static void *cfq_init_queue(request_queue_t *q)
{
	struct cfq_data *cfqd;
	int i;

	cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL, q->node);
	if (!cfqd)
		return NULL;

	memset(cfqd, 0, sizeof(*cfqd));

	cfqd->service_tree = CFQ_RB_ROOT;
	INIT_LIST_HEAD(&cfqd->cic_list);

	cfqd->cfq_hash = kmalloc_node(sizeof(struct hlist_head) * CFQ_QHASH_ENTRIES, GFP_KERNEL, q->node);
	if (!cfqd->cfq_hash)
		goto out_free;

	for (i = 0; i < CFQ_QHASH_ENTRIES; i++)
		INIT_HLIST_HEAD(&cfqd->cfq_hash[i]);

	cfqd->queue = q;

	init_timer(&cfqd->idle_slice_timer);
	cfqd->idle_slice_timer.function = cfq_idle_slice_timer;
	cfqd->idle_slice_timer.data = (unsigned long) cfqd;

	init_timer(&cfqd->idle_class_timer);
	cfqd->idle_class_timer.function = cfq_idle_class_timer;
	cfqd->idle_class_timer.data = (unsigned long) cfqd;

	INIT_WORK(&cfqd->unplug_work, cfq_kick_queue);

	cfqd->cfq_quantum = cfq_quantum;
	cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0];
	cfqd->cfq_fifo_expire[1] = cfq_fifo_expire[1];
	cfqd->cfq_back_max = cfq_back_max;
	cfqd->cfq_back_penalty = cfq_back_penalty;
	cfqd->cfq_slice[0] = cfq_slice_async;
	cfqd->cfq_slice[1] = cfq_slice_sync;
	cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
	cfqd->cfq_slice_idle = cfq_slice_idle;

	return cfqd;
out_free:
	kfree(cfqd);
	return NULL;
}

static void cfq_slab_kill(void)
{
	if (cfq_pool)
		kmem_cache_destroy(cfq_pool);
	if (cfq_ioc_pool)
		kmem_cache_destroy(cfq_ioc_pool);
}

static int __init cfq_slab_setup(void)
{
	cfq_pool = kmem_cache_create("cfq_pool", sizeof(struct cfq_queue), 0, 0,
					NULL, NULL);
	if (!cfq_pool)
		goto fail;

	cfq_ioc_pool = kmem_cache_create("cfq_ioc_pool",
			sizeof(struct cfq_io_context), 0, 0, NULL, NULL);
	if (!cfq_ioc_pool)
		goto fail;

	return 0;
fail:
	cfq_slab_kill();
	return -ENOMEM;
}

/*
 * sysfs parts below -->
 */
static ssize_t
cfq_var_show(unsigned int var, char *page)
{
	return sprintf(page, "%d\n", var);
}

static ssize_t
cfq_var_store(unsigned int *var, const char *page, size_t count)
{
	char *p = (char *) page;

	*var = simple_strtoul(p, &p, 10);
	return count;
}

#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
static ssize_t __FUNC(elevator_t *e, char *page)			\
{									\
	struct cfq_data *cfqd = e->elevator_data;			\
	unsigned int __data = __VAR;					\
	if (__CONV)							\
		__data = jiffies_to_msecs(__data);			\
	return cfq_var_show(__data, (page));				\
}
SHOW_FUNCTION(cfq_quantum_show, cfqd->cfq_quantum, 0);
SHOW_FUNCTION(cfq_fifo_expire_sync_show, cfqd->cfq_fifo_expire[1], 1);
SHOW_FUNCTION(cfq_fifo_expire_async_show, cfqd->cfq_fifo_expire[0], 1);
SHOW_FUNCTION(cfq_back_seek_max_show, cfqd->cfq_back_max, 0);
SHOW_FUNCTION(cfq_back_seek_penalty_show, cfqd->cfq_back_penalty, 0);
SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_idle, 1);
SHOW_FUNCTION(cfq_slice_sync_show, cfqd->cfq_slice[1], 1);
SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1);
SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0);
#undef SHOW_FUNCTION

#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
static ssize_t __FUNC(elevator_t *e, const char *page, size_t count)	\
{									\
	struct cfq_data *cfqd = e->elevator_data;			\
	unsigned int __data;						\
	int ret = cfq_var_store(&__data, (page), count);		\
	if (__data < (MIN))						\
		__data = (MIN);						\
	else if (__data > (MAX))					\
		__data = (MAX);						\
	if (__CONV)							\
		*(__PTR) = msecs_to_jiffies(__data);			\
	else								\
		*(__PTR) = __data;					\
	return ret;							\
}
STORE_FUNCTION(cfq_quantum_store, &cfqd->cfq_quantum, 1, UINT_MAX, 0);
STORE_FUNCTION(cfq_fifo_expire_sync_store, &cfqd->cfq_fifo_expire[1], 1, UINT_MAX, 1);
STORE_FUNCTION(cfq_fifo_expire_async_store, &cfqd->cfq_fifo_expire[0], 1, UINT_MAX, 1);
STORE_FUNCTION(cfq_back_seek_max_store, &cfqd->cfq_back_max, 0, UINT_MAX, 0);
STORE_FUNCTION(cfq_back_seek_penalty_store, &cfqd->cfq_back_penalty, 1, UINT_MAX, 0);
STORE_FUNCTION(cfq_slice_idle_store, &cfqd->cfq_slice_idle, 0, UINT_MAX, 1);
STORE_FUNCTION(cfq_slice_sync_store, &cfqd->cfq_slice[1], 1, UINT_MAX, 1);
STORE_FUNCTION(cfq_slice_async_store, &cfqd->cfq_slice[0], 1, UINT_MAX, 1);
STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1, UINT_MAX, 0);
#undef STORE_FUNCTION

#define CFQ_ATTR(name) \
	__ATTR(name, S_IRUGO|S_IWUSR, cfq_##name##_show, cfq_##name##_store)

static struct elv_fs_entry cfq_attrs[] = {
	CFQ_ATTR(quantum),
	CFQ_ATTR(fifo_expire_sync),
	CFQ_ATTR(fifo_expire_async),
	CFQ_ATTR(back_seek_max),
	CFQ_ATTR(back_seek_penalty),
	CFQ_ATTR(slice_sync),
	CFQ_ATTR(slice_async),
	CFQ_ATTR(slice_async_rq),
	CFQ_ATTR(slice_idle),
	__ATTR_NULL
};

static struct elevator_type iosched_cfq = {
	.ops = {
		.elevator_merge_fn = 		cfq_merge,
		.elevator_merged_fn =		cfq_merged_request,
		.elevator_merge_req_fn =	cfq_merged_requests,
		.elevator_allow_merge_fn =	cfq_allow_merge,
		.elevator_dispatch_fn =		cfq_dispatch_requests,
		.elevator_add_req_fn =		cfq_insert_request,
		.elevator_activate_req_fn =	cfq_activate_request,
		.elevator_deactivate_req_fn =	cfq_deactivate_request,
		.elevator_queue_empty_fn =	cfq_queue_empty,
		.elevator_completed_req_fn =	cfq_completed_request,
		.elevator_former_req_fn =	elv_rb_former_request,
		.elevator_latter_req_fn =	elv_rb_latter_request,
		.elevator_set_req_fn =		cfq_set_request,
		.elevator_put_req_fn =		cfq_put_request,
		.elevator_may_queue_fn =	cfq_may_queue,
		.elevator_init_fn =		cfq_init_queue,
		.elevator_exit_fn =		cfq_exit_queue,
		.trim =				cfq_free_io_context,
	},
	.elevator_attrs =	cfq_attrs,
	.elevator_name =	"cfq",
	.elevator_owner =	THIS_MODULE,
};

static int __init cfq_init(void)
{
	int ret;

	/*
	 * could be 0 on HZ < 1000 setups
	 */
	if (!cfq_slice_async)
		cfq_slice_async = 1;
	if (!cfq_slice_idle)
		cfq_slice_idle = 1;

	if (cfq_slab_setup())
		return -ENOMEM;

	ret = elv_register(&iosched_cfq);
	if (ret)
		cfq_slab_kill();

	return ret;
}

static void __exit cfq_exit(void)
{
	DECLARE_COMPLETION_ONSTACK(all_gone);
	elv_unregister(&iosched_cfq);
	ioc_gone = &all_gone;
	/* ioc_gone's update must be visible before reading ioc_count */
	smp_wmb();
	if (elv_ioc_count_read(ioc_count))
		wait_for_completion(ioc_gone);
	synchronize_rcu();
	cfq_slab_kill();
}

module_init(cfq_init);
module_exit(cfq_exit);

MODULE_AUTHOR("Jens Axboe");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Completely Fair Queueing IO scheduler");