summaryrefslogtreecommitdiffstats
path: root/block/blk-core.c
blob: 177ddcf356e6a2cf3dca8b86d5985c3461addade (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
/*
 * Copyright (C) 1991, 1992 Linus Torvalds
 * Copyright (C) 1994,      Karl Keyte: Added support for disk statistics
 * Elevator latency, (C) 2000  Andrea Arcangeli <andrea@suse.de> SuSE
 * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de>
 * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au>
 *	-  July2000
 * bio rewrite, highmem i/o, etc, Jens Axboe <axboe@suse.de> - may 2001
 */

/*
 * This handles all read/write requests to block devices
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/kernel_stat.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/completion.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/fault-inject.h>
#include <linux/list_sort.h>
#include <linux/delay.h>
#include <linux/ratelimit.h>

#define CREATE_TRACE_POINTS
#include <trace/events/block.h>

#include "blk.h"
#include "blk-cgroup.h"

EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);

DEFINE_IDA(blk_queue_ida);

/*
 * For the allocated request tables
 */
static struct kmem_cache *request_cachep;

/*
 * For queue allocation
 */
struct kmem_cache *blk_requestq_cachep;

/*
 * Controlling structure to kblockd
 */
static struct workqueue_struct *kblockd_workqueue;

static void drive_stat_acct(struct request *rq, int new_io)
{
	struct hd_struct *part;
	int rw = rq_data_dir(rq);
	int cpu;

	if (!blk_do_io_stat(rq))
		return;

	cpu = part_stat_lock();

	if (!new_io) {
		part = rq->part;
		part_stat_inc(cpu, part, merges[rw]);
	} else {
		part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
		if (!hd_struct_try_get(part)) {
			/*
			 * The partition is already being removed,
			 * the request will be accounted on the disk only
			 *
			 * We take a reference on disk->part0 although that
			 * partition will never be deleted, so we can treat
			 * it as any other partition.
			 */
			part = &rq->rq_disk->part0;
			hd_struct_get(part);
		}
		part_round_stats(cpu, part);
		part_inc_in_flight(part, rw);
		rq->part = part;
	}

	part_stat_unlock();
}

void blk_queue_congestion_threshold(struct request_queue *q)
{
	int nr;

	nr = q->nr_requests - (q->nr_requests / 8) + 1;
	if (nr > q->nr_requests)
		nr = q->nr_requests;
	q->nr_congestion_on = nr;

	nr = q->nr_requests - (q->nr_requests / 8) - (q->nr_requests / 16) - 1;
	if (nr < 1)
		nr = 1;
	q->nr_congestion_off = nr;
}

/**
 * blk_get_backing_dev_info - get the address of a queue's backing_dev_info
 * @bdev:	device
 *
 * Locates the passed device's request queue and returns the address of its
 * backing_dev_info
 *
 * Will return NULL if the request queue cannot be located.
 */
struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
{
	struct backing_dev_info *ret = NULL;
	struct request_queue *q = bdev_get_queue(bdev);

	if (q)
		ret = &q->backing_dev_info;
	return ret;
}
EXPORT_SYMBOL(blk_get_backing_dev_info);

void blk_rq_init(struct request_queue *q, struct request *rq)
{
	memset(rq, 0, sizeof(*rq));

	INIT_LIST_HEAD(&rq->queuelist);
	INIT_LIST_HEAD(&rq->timeout_list);
	rq->cpu = -1;
	rq->q = q;
	rq->__sector = (sector_t) -1;
	INIT_HLIST_NODE(&rq->hash);
	RB_CLEAR_NODE(&rq->rb_node);
	rq->cmd = rq->__cmd;
	rq->cmd_len = BLK_MAX_CDB;
	rq->tag = -1;
	rq->ref_count = 1;
	rq->start_time = jiffies;
	set_start_time_ns(rq);
	rq->part = NULL;
}
EXPORT_SYMBOL(blk_rq_init);

static void req_bio_endio(struct request *rq, struct bio *bio,
			  unsigned int nbytes, int error)
{
	if (error)
		clear_bit(BIO_UPTODATE, &bio->bi_flags);
	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
		error = -EIO;

	if (unlikely(nbytes > bio->bi_size)) {
		printk(KERN_ERR "%s: want %u bytes done, %u left\n",
		       __func__, nbytes, bio->bi_size);
		nbytes = bio->bi_size;
	}

	if (unlikely(rq->cmd_flags & REQ_QUIET))
		set_bit(BIO_QUIET, &bio->bi_flags);

	bio->bi_size -= nbytes;
	bio->bi_sector += (nbytes >> 9);

	if (bio_integrity(bio))
		bio_integrity_advance(bio, nbytes);

	/* don't actually finish bio if it's part of flush sequence */
	if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
		bio_endio(bio, error);
}

void blk_dump_rq_flags(struct request *rq, char *msg)
{
	int bit;

	printk(KERN_INFO "%s: dev %s: type=%x, flags=%x\n", msg,
		rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
		rq->cmd_flags);

	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u\n",
	       (unsigned long long)blk_rq_pos(rq),
	       blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
	printk(KERN_INFO "  bio %p, biotail %p, buffer %p, len %u\n",
	       rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq));

	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
		printk(KERN_INFO "  cdb: ");
		for (bit = 0; bit < BLK_MAX_CDB; bit++)
			printk("%02x ", rq->cmd[bit]);
		printk("\n");
	}
}
EXPORT_SYMBOL(blk_dump_rq_flags);

static void blk_delay_work(struct work_struct *work)
{
	struct request_queue *q;

	q = container_of(work, struct request_queue, delay_work.work);
	spin_lock_irq(q->queue_lock);
	__blk_run_queue(q);
	spin_unlock_irq(q->queue_lock);
}

/**
 * blk_delay_queue - restart queueing after defined interval
 * @q:		The &struct request_queue in question
 * @msecs:	Delay in msecs
 *
 * Description:
 *   Sometimes queueing needs to be postponed for a little while, to allow
 *   resources to come back. This function will make sure that queueing is
 *   restarted around the specified time.
 */
void blk_delay_queue(struct request_queue *q, unsigned long msecs)
{
	queue_delayed_work(kblockd_workqueue, &q->delay_work,
				msecs_to_jiffies(msecs));
}
EXPORT_SYMBOL(blk_delay_queue);

/**
 * blk_start_queue - restart a previously stopped queue
 * @q:    The &struct request_queue in question
 *
 * Description:
 *   blk_start_queue() will clear the stop flag on the queue, and call
 *   the request_fn for the queue if it was in a stopped state when
 *   entered. Also see blk_stop_queue(). Queue lock must be held.
 **/
void blk_start_queue(struct request_queue *q)
{
	WARN_ON(!irqs_disabled());

	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
	__blk_run_queue(q);
}
EXPORT_SYMBOL(blk_start_queue);

/**
 * blk_stop_queue - stop a queue
 * @q:    The &struct request_queue in question
 *
 * Description:
 *   The Linux block layer assumes that a block driver will consume all
 *   entries on the request queue when the request_fn strategy is called.
 *   Often this will not happen, because of hardware limitations (queue
 *   depth settings). If a device driver gets a 'queue full' response,
 *   or if it simply chooses not to queue more I/O at one point, it can
 *   call this function to prevent the request_fn from being called until
 *   the driver has signalled it's ready to go again. This happens by calling
 *   blk_start_queue() to restart queue operations. Queue lock must be held.
 **/
void blk_stop_queue(struct request_queue *q)
{
	__cancel_delayed_work(&q->delay_work);
	queue_flag_set(QUEUE_FLAG_STOPPED, q);
}
EXPORT_SYMBOL(blk_stop_queue);

/**
 * blk_sync_queue - cancel any pending callbacks on a queue
 * @q: the queue
 *
 * Description:
 *     The block layer may perform asynchronous callback activity
 *     on a queue, such as calling the unplug function after a timeout.
 *     A block device may call blk_sync_queue to ensure that any
 *     such activity is cancelled, thus allowing it to release resources
 *     that the callbacks might use. The caller must already have made sure
 *     that its ->make_request_fn will not re-add plugging prior to calling
 *     this function.
 *
 *     This function does not cancel any asynchronous activity arising
 *     out of elevator or throttling code. That would require elevaotor_exit()
 *     and blkcg_exit_queue() to be called with queue lock initialized.
 *
 */
void blk_sync_queue(struct request_queue *q)
{
	del_timer_sync(&q->timeout);
	cancel_delayed_work_sync(&q->delay_work);
}
EXPORT_SYMBOL(blk_sync_queue);

/**
 * __blk_run_queue - run a single device queue
 * @q:	The queue to run
 *
 * Description:
 *    See @blk_run_queue. This variant must be called with the queue lock
 *    held and interrupts disabled.
 */
void __blk_run_queue(struct request_queue *q)
{
	if (unlikely(blk_queue_stopped(q)))
		return;

	q->request_fn(q);
}
EXPORT_SYMBOL(__blk_run_queue);

/**
 * blk_run_queue_async - run a single device queue in workqueue context
 * @q:	The queue to run
 *
 * Description:
 *    Tells kblockd to perform the equivalent of @blk_run_queue on behalf
 *    of us.
 */
void blk_run_queue_async(struct request_queue *q)
{
	if (likely(!blk_queue_stopped(q))) {
		__cancel_delayed_work(&q->delay_work);
		queue_delayed_work(kblockd_workqueue, &q->delay_work, 0);
	}
}
EXPORT_SYMBOL(blk_run_queue_async);

/**
 * blk_run_queue - run a single device queue
 * @q: The queue to run
 *
 * Description:
 *    Invoke request handling on this queue, if it has pending work to do.
 *    May be used to restart queueing when a request has completed.
 */
void blk_run_queue(struct request_queue *q)
{
	unsigned long flags;

	spin_lock_irqsave(q->queue_lock, flags);
	__blk_run_queue(q);
	spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(blk_run_queue);

void blk_put_queue(struct request_queue *q)
{
	kobject_put(&q->kobj);
}
EXPORT_SYMBOL(blk_put_queue);

/**
 * blk_drain_queue - drain requests from request_queue
 * @q: queue to drain
 * @drain_all: whether to drain all requests or only the ones w/ ELVPRIV
 *
 * Drain requests from @q.  If @drain_all is set, all requests are drained.
 * If not, only ELVPRIV requests are drained.  The caller is responsible
 * for ensuring that no new requests which need to be drained are queued.
 */
void blk_drain_queue(struct request_queue *q, bool drain_all)
{
	int i;

	while (true) {
		bool drain = false;

		spin_lock_irq(q->queue_lock);

		/*
		 * The caller might be trying to drain @q before its
		 * elevator is initialized.
		 */
		if (q->elevator)
			elv_drain_elevator(q);

		blkcg_drain_queue(q);

		/*
		 * This function might be called on a queue which failed
		 * driver init after queue creation or is not yet fully
		 * active yet.  Some drivers (e.g. fd and loop) get unhappy
		 * in such cases.  Kick queue iff dispatch queue has
		 * something on it and @q has request_fn set.
		 */
		if (!list_empty(&q->queue_head) && q->request_fn)
			__blk_run_queue(q);

		drain |= q->nr_rqs_elvpriv;

		/*
		 * Unfortunately, requests are queued at and tracked from
		 * multiple places and there's no single counter which can
		 * be drained.  Check all the queues and counters.
		 */
		if (drain_all) {
			drain |= !list_empty(&q->queue_head);
			for (i = 0; i < 2; i++) {
				drain |= q->nr_rqs[i];
				drain |= q->in_flight[i];
				drain |= !list_empty(&q->flush_queue[i]);
			}
		}

		spin_unlock_irq(q->queue_lock);

		if (!drain)
			break;
		msleep(10);
	}

	/*
	 * With queue marked dead, any woken up waiter will fail the
	 * allocation path, so the wakeup chaining is lost and we're
	 * left with hung waiters. We need to wake up those waiters.
	 */
	if (q->request_fn) {
		struct request_list *rl;

		spin_lock_irq(q->queue_lock);

		blk_queue_for_each_rl(rl, q)
			for (i = 0; i < ARRAY_SIZE(rl->wait); i++)
				wake_up_all(&rl->wait[i]);

		spin_unlock_irq(q->queue_lock);
	}
}

/**
 * blk_queue_bypass_start - enter queue bypass mode
 * @q: queue of interest
 *
 * In bypass mode, only the dispatch FIFO queue of @q is used.  This
 * function makes @q enter bypass mode and drains all requests which were
 * throttled or issued before.  On return, it's guaranteed that no request
 * is being throttled or has ELVPRIV set and blk_queue_bypass() %true
 * inside queue or RCU read lock.
 */
void blk_queue_bypass_start(struct request_queue *q)
{
	bool drain;

	spin_lock_irq(q->queue_lock);
	drain = !q->bypass_depth++;
	queue_flag_set(QUEUE_FLAG_BYPASS, q);
	spin_unlock_irq(q->queue_lock);

	if (drain) {
		blk_drain_queue(q, false);
		/* ensure blk_queue_bypass() is %true inside RCU read lock */
		synchronize_rcu();
	}
}
EXPORT_SYMBOL_GPL(blk_queue_bypass_start);

/**
 * blk_queue_bypass_end - leave queue bypass mode
 * @q: queue of interest
 *
 * Leave bypass mode and restore the normal queueing behavior.
 */
void blk_queue_bypass_end(struct request_queue *q)
{
	spin_lock_irq(q->queue_lock);
	if (!--q->bypass_depth)
		queue_flag_clear(QUEUE_FLAG_BYPASS, q);
	WARN_ON_ONCE(q->bypass_depth < 0);
	spin_unlock_irq(q->queue_lock);
}
EXPORT_SYMBOL_GPL(blk_queue_bypass_end);

/**
 * blk_cleanup_queue - shutdown a request queue
 * @q: request queue to shutdown
 *
 * Mark @q DEAD, drain all pending requests, destroy and put it.  All
 * future requests will be failed immediately with -ENODEV.
 */
void blk_cleanup_queue(struct request_queue *q)
{
	spinlock_t *lock = q->queue_lock;

	/* mark @q DEAD, no new request or merges will be allowed afterwards */
	mutex_lock(&q->sysfs_lock);
	queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
	spin_lock_irq(lock);

	/*
	 * Dead queue is permanently in bypass mode till released.  Note
	 * that, unlike blk_queue_bypass_start(), we aren't performing
	 * synchronize_rcu() after entering bypass mode to avoid the delay
	 * as some drivers create and destroy a lot of queues while
	 * probing.  This is still safe because blk_release_queue() will be
	 * called only after the queue refcnt drops to zero and nothing,
	 * RCU or not, would be traversing the queue by then.
	 */
	q->bypass_depth++;
	queue_flag_set(QUEUE_FLAG_BYPASS, q);

	queue_flag_set(QUEUE_FLAG_NOMERGES, q);
	queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
	queue_flag_set(QUEUE_FLAG_DEAD, q);
	spin_unlock_irq(lock);
	mutex_unlock(&q->sysfs_lock);

	/* drain all requests queued before DEAD marking */
	blk_drain_queue(q, true);

	/* @q won't process any more request, flush async actions */
	del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
	blk_sync_queue(q);

	spin_lock_irq(lock);
	if (q->queue_lock != &q->__queue_lock)
		q->queue_lock = &q->__queue_lock;
	spin_unlock_irq(lock);

	/* @q is and will stay empty, shutdown and put */
	blk_put_queue(q);
}
EXPORT_SYMBOL(blk_cleanup_queue);

int blk_init_rl(struct request_list *rl, struct request_queue *q,
		gfp_t gfp_mask)
{
	if (unlikely(rl->rq_pool))
		return 0;

	rl->q = q;
	rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0;
	rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0;
	init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
	init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);

	rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
					  mempool_free_slab, request_cachep,
					  gfp_mask, q->node);
	if (!rl->rq_pool)
		return -ENOMEM;

	return 0;
}

void blk_exit_rl(struct request_list *rl)
{
	if (rl->rq_pool)
		mempool_destroy(rl->rq_pool);
}

struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
{
	return blk_alloc_queue_node(gfp_mask, -1);
}
EXPORT_SYMBOL(blk_alloc_queue);

struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
{
	struct request_queue *q;
	int err;

	q = kmem_cache_alloc_node(blk_requestq_cachep,
				gfp_mask | __GFP_ZERO, node_id);
	if (!q)
		return NULL;

	q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);
	if (q->id < 0)
		goto fail_q;

	q->backing_dev_info.ra_pages =
			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
	q->backing_dev_info.state = 0;
	q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
	q->backing_dev_info.name = "block";
	q->node = node_id;

	err = bdi_init(&q->backing_dev_info);
	if (err)
		goto fail_id;

	setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
		    laptop_mode_timer_fn, (unsigned long) q);
	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
	INIT_LIST_HEAD(&q->queue_head);
	INIT_LIST_HEAD(&q->timeout_list);
	INIT_LIST_HEAD(&q->icq_list);
#ifdef CONFIG_BLK_CGROUP
	INIT_LIST_HEAD(&q->blkg_list);
#endif
	INIT_LIST_HEAD(&q->flush_queue[0]);
	INIT_LIST_HEAD(&q->flush_queue[1]);
	INIT_LIST_HEAD(&q->flush_data_in_flight);
	INIT_DELAYED_WORK(&q->delay_work, blk_delay_work);

	kobject_init(&q->kobj, &blk_queue_ktype);

	mutex_init(&q->sysfs_lock);
	spin_lock_init(&q->__queue_lock);

	/*
	 * By default initialize queue_lock to internal lock and driver can
	 * override it later if need be.
	 */
	q->queue_lock = &q->__queue_lock;

	/*
	 * A queue starts its life with bypass turned on to avoid
	 * unnecessary bypass on/off overhead and nasty surprises during
	 * init.  The initial bypass will be finished at the end of
	 * blk_init_allocated_queue().
	 */
	q->bypass_depth = 1;
	__set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);

	if (blkcg_init_queue(q))
		goto fail_id;

	return q;

fail_id:
	ida_simple_remove(&blk_queue_ida, q->id);
fail_q:
	kmem_cache_free(blk_requestq_cachep, q);
	return NULL;
}
EXPORT_SYMBOL(blk_alloc_queue_node);

/**
 * blk_init_queue  - prepare a request queue for use with a block device
 * @rfn:  The function to be called to process requests that have been
 *        placed on the queue.
 * @lock: Request queue spin lock
 *
 * Description:
 *    If a block device wishes to use the standard request handling procedures,
 *    which sorts requests and coalesces adjacent requests, then it must
 *    call blk_init_queue().  The function @rfn will be called when there
 *    are requests on the queue that need to be processed.  If the device
 *    supports plugging, then @rfn may not be called immediately when requests
 *    are available on the queue, but may be called at some time later instead.
 *    Plugged queues are generally unplugged when a buffer belonging to one
 *    of the requests on the queue is needed, or due to memory pressure.
 *
 *    @rfn is not required, or even expected, to remove all requests off the
 *    queue, but only as many as it can handle at a time.  If it does leave
 *    requests on the queue, it is responsible for arranging that the requests
 *    get dealt with eventually.
 *
 *    The queue spin lock must be held while manipulating the requests on the
 *    request queue; this lock will be taken also from interrupt context, so irq
 *    disabling is needed for it.
 *
 *    Function returns a pointer to the initialized request queue, or %NULL if
 *    it didn't succeed.
 *
 * Note:
 *    blk_init_queue() must be paired with a blk_cleanup_queue() call
 *    when the block device is deactivated (such as at module unload).
 **/

struct request_queue *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock)
{
	return blk_init_queue_node(rfn, lock, -1);
}
EXPORT_SYMBOL(blk_init_queue);

struct request_queue *
blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
{
	struct request_queue *uninit_q, *q;

	uninit_q = blk_alloc_queue_node(GFP_KERNEL, node_id);
	if (!uninit_q)
		return NULL;

	q = blk_init_allocated_queue(uninit_q, rfn, lock);
	if (!q)
		blk_cleanup_queue(uninit_q);

	return q;
}
EXPORT_SYMBOL(blk_init_queue_node);

struct request_queue *
blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
			 spinlock_t *lock)
{
	if (!q)
		return NULL;

	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
		return NULL;

	q->request_fn		= rfn;
	q->prep_rq_fn		= NULL;
	q->unprep_rq_fn		= NULL;
	q->queue_flags		= QUEUE_FLAG_DEFAULT;

	/* Override internal queue lock with supplied lock pointer */
	if (lock)
		q->queue_lock		= lock;

	/*
	 * This also sets hw/phys segments, boundary and size
	 */
	blk_queue_make_request(q, blk_queue_bio);

	q->sg_reserved_size = INT_MAX;

	/* init elevator */
	if (elevator_init(q, NULL))
		return NULL;

	blk_queue_congestion_threshold(q);

	/* all done, end the initial bypass */
	blk_queue_bypass_end(q);
	return q;
}
EXPORT_SYMBOL(blk_init_allocated_queue);

bool blk_get_queue(struct request_queue *q)
{
	if (likely(!blk_queue_dead(q))) {
		__blk_get_queue(q);
		return true;
	}

	return false;
}
EXPORT_SYMBOL(blk_get_queue);

static inline void blk_free_request(struct request_list *rl, struct request *rq)
{
	if (rq->cmd_flags & REQ_ELVPRIV) {
		elv_put_request(rl->q, rq);
		if (rq->elv.icq)
			put_io_context(rq->elv.icq->ioc);
	}

	mempool_free(rq, rl->rq_pool);
}

/*
 * ioc_batching returns true if the ioc is a valid batching request and
 * should be given priority access to a request.
 */
static inline int ioc_batching(struct request_queue *q, struct io_context *ioc)
{
	if (!ioc)
		return 0;

	/*
	 * Make sure the process is able to allocate at least 1 request
	 * even if the batch times out, otherwise we could theoretically
	 * lose wakeups.
	 */
	return ioc->nr_batch_requests == q->nr_batching ||
		(ioc->nr_batch_requests > 0
		&& time_before(jiffies, ioc->last_waited + BLK_BATCH_TIME));
}

/*
 * ioc_set_batching sets ioc to be a new "batcher" if it is not one. This
 * will cause the process to be a "batcher" on all queues in the system. This
 * is the behaviour we want though - once it gets a wakeup it should be given
 * a nice run.
 */
static void ioc_set_batching(struct request_queue *q, struct io_context *ioc)
{
	if (!ioc || ioc_batching(q, ioc))
		return;

	ioc->nr_batch_requests = q->nr_batching;
	ioc->last_waited = jiffies;
}

static void __freed_request(struct request_list *rl, int sync)
{
	struct request_queue *q = rl->q;

	/*
	 * bdi isn't aware of blkcg yet.  As all async IOs end up root
	 * blkcg anyway, just use root blkcg state.
	 */
	if (rl == &q->root_rl &&
	    rl->count[sync] < queue_congestion_off_threshold(q))
		blk_clear_queue_congested(q, sync);

	if (rl->count[sync] + 1 <= q->nr_requests) {
		if (waitqueue_active(&rl->wait[sync]))
			wake_up(&rl->wait[sync]);

		blk_clear_rl_full(rl, sync);
	}
}

/*
 * A request has just been released.  Account for it, update the full and
 * congestion status, wake up any waiters.   Called under q->queue_lock.
 */
static void freed_request(struct request_list *rl, unsigned int flags)
{
	struct request_queue *q = rl->q;
	int sync = rw_is_sync(flags);

	q->nr_rqs[sync]--;
	rl->count[sync]--;
	if (flags & REQ_ELVPRIV)
		q->nr_rqs_elvpriv--;

	__freed_request(rl, sync);

	if (unlikely(rl->starved[sync ^ 1]))
		__freed_request(rl, sync ^ 1);
}

/*
 * Determine if elevator data should be initialized when allocating the
 * request associated with @bio.
 */
static bool blk_rq_should_init_elevator(struct bio *bio)
{
	if (!bio)
		return true;

	/*
	 * Flush requests do not use the elevator so skip initialization.
	 * This allows a request to share the flush and elevator data.
	 */
	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA))
		return false;

	return true;
}

/**
 * rq_ioc - determine io_context for request allocation
 * @bio: request being allocated is for this bio (can be %NULL)
 *
 * Determine io_context to use for request allocation for @bio.  May return
 * %NULL if %current->io_context doesn't exist.
 */
static struct io_context *rq_ioc(struct bio *bio)
{
#ifdef CONFIG_BLK_CGROUP
	if (bio && bio->bi_ioc)
		return bio->bi_ioc;
#endif
	return current->io_context;
}

/**
 * __get_request - get a free request
 * @rl: request list to allocate from
 * @rw_flags: RW and SYNC flags
 * @bio: bio to allocate request for (can be %NULL)
 * @gfp_mask: allocation mask
 *
 * Get a free request from @q.  This function may fail under memory
 * pressure or if @q is dead.
 *
 * Must be callled with @q->queue_lock held and,
 * Returns %NULL on failure, with @q->queue_lock held.
 * Returns !%NULL on success, with @q->queue_lock *not held*.
 */
static struct request *__get_request(struct request_list *rl, int rw_flags,
				     struct bio *bio, gfp_t gfp_mask)
{
	struct request_queue *q = rl->q;
	struct request *rq;
	struct elevator_type *et = q->elevator->type;
	struct io_context *ioc = rq_ioc(bio);
	struct io_cq *icq = NULL;
	const bool is_sync = rw_is_sync(rw_flags) != 0;
	int may_queue;

	if (unlikely(blk_queue_dead(q)))
		return NULL;

	may_queue = elv_may_queue(q, rw_flags);
	if (may_queue == ELV_MQUEUE_NO)
		goto rq_starved;

	if (rl->count[is_sync]+1 >= queue_congestion_on_threshold(q)) {
		if (rl->count[is_sync]+1 >= q->nr_requests) {
			/*
			 * The queue will fill after this allocation, so set
			 * it as full, and mark this process as "batching".
			 * This process will be allowed to complete a batch of
			 * requests, others will be blocked.
			 */
			if (!blk_rl_full(rl, is_sync)) {
				ioc_set_batching(q, ioc);
				blk_set_rl_full(rl, is_sync);
			} else {
				if (may_queue != ELV_MQUEUE_MUST
						&& !ioc_batching(q, ioc)) {
					/*
					 * The queue is full and the allocating
					 * process is not a "batcher", and not
					 * exempted by the IO scheduler
					 */
					return NULL;
				}
			}
		}
		/*
		 * bdi isn't aware of blkcg yet.  As all async IOs end up
		 * root blkcg anyway, just use root blkcg state.
		 */
		if (rl == &q->root_rl)
			blk_set_queue_congested(q, is_sync);
	}

	/*
	 * Only allow batching queuers to allocate up to 50% over the defined
	 * limit of requests, otherwise we could have thousands of requests
	 * allocated with any setting of ->nr_requests
	 */
	if (rl->count[is_sync] >= (3 * q->nr_requests / 2))
		return NULL;

	q->nr_rqs[is_sync]++;
	rl->count[is_sync]++;
	rl->starved[is_sync] = 0;

	/*
	 * Decide whether the new request will be managed by elevator.  If
	 * so, mark @rw_flags and increment elvpriv.  Non-zero elvpriv will
	 * prevent the current elevator from being destroyed until the new
	 * request is freed.  This guarantees icq's won't be destroyed and
	 * makes creating new ones safe.
	 *
	 * Also, lookup icq while holding queue_lock.  If it doesn't exist,
	 * it will be created after releasing queue_lock.
	 */
	if (blk_rq_should_init_elevator(bio) && !blk_queue_bypass(q)) {
		rw_flags |= REQ_ELVPRIV;
		q->nr_rqs_elvpriv++;
		if (et->icq_cache && ioc)
			icq = ioc_lookup_icq(ioc, q);
	}

	if (blk_queue_io_stat(q))
		rw_flags |= REQ_IO_STAT;
	spin_unlock_irq(q->queue_lock);

	/* allocate and init request */
	rq = mempool_alloc(rl->rq_pool, gfp_mask);
	if (!rq)
		goto fail_alloc;

	blk_rq_init(q, rq);
	blk_rq_set_rl(rq, rl);
	rq->cmd_flags = rw_flags | REQ_ALLOCED;

	/* init elvpriv */
	if (rw_flags & REQ_ELVPRIV) {
		if (unlikely(et->icq_cache && !icq)) {
			if (ioc)
				icq = ioc_create_icq(ioc, q, gfp_mask);
			if (!icq)
				goto fail_elvpriv;
		}

		rq->elv.icq = icq;
		if (unlikely(elv_set_request(q, rq, bio, gfp_mask)))
			goto fail_elvpriv;

		/* @rq->elv.icq holds io_context until @rq is freed */
		if (icq)
			get_io_context(icq->ioc);
	}
out:
	/*
	 * ioc may be NULL here, and ioc_batching will be false. That's
	 * OK, if the queue is under the request limit then requests need
	 * not count toward the nr_batch_requests limit. There will always
	 * be some limit enforced by BLK_BATCH_TIME.
	 */
	if (ioc_batching(q, ioc))
		ioc->nr_batch_requests--;

	trace_block_getrq(q, bio, rw_flags & 1);
	return rq;

fail_elvpriv:
	/*
	 * elvpriv init failed.  ioc, icq and elvpriv aren't mempool backed
	 * and may fail indefinitely under memory pressure and thus
	 * shouldn't stall IO.  Treat this request as !elvpriv.  This will
	 * disturb iosched and blkcg but weird is bettern than dead.
	 */
	printk_ratelimited(KERN_WARNING "%s: request aux data allocation failed, iosched may be disturbed\n",
			   dev_name(q->backing_dev_info.dev));

	rq->cmd_flags &= ~REQ_ELVPRIV;
	rq->elv.icq = NULL;

	spin_lock_irq(q->queue_lock);
	q->nr_rqs_elvpriv--;
	spin_unlock_irq(q->queue_lock);
	goto out;

fail_alloc:
	/*
	 * Allocation failed presumably due to memory. Undo anything we
	 * might have messed up.
	 *
	 * Allocating task should really be put onto the front of the wait
	 * queue, but this is pretty rare.
	 */
	spin_lock_irq(q->queue_lock);
	freed_request(rl, rw_flags);

	/*
	 * in the very unlikely event that allocation failed and no
	 * requests for this direction was pending, mark us starved so that
	 * freeing of a request in the other direction will notice
	 * us. another possible fix would be to split the rq mempool into
	 * READ and WRITE
	 */
rq_starved:
	if (unlikely(rl->count[is_sync] == 0))
		rl->starved[is_sync] = 1;
	return NULL;
}

/**
 * get_request - get a free request
 * @q: request_queue to allocate request from
 * @rw_flags: RW and SYNC flags
 * @bio: bio to allocate request for (can be %NULL)
 * @gfp_mask: allocation mask
 *
 * Get a free request from @q.  If %__GFP_WAIT is set in @gfp_mask, this
 * function keeps retrying under memory pressure and fails iff @q is dead.
 *
 * Must be callled with @q->queue_lock held and,
 * Returns %NULL on failure, with @q->queue_lock held.
 * Returns !%NULL on success, with @q->queue_lock *not held*.
 */
static struct request *get_request(struct request_queue *q, int rw_flags,
				   struct bio *bio, gfp_t gfp_mask)
{
	const bool is_sync = rw_is_sync(rw_flags) != 0;
	DEFINE_WAIT(wait);
	struct request_list *rl;
	struct request *rq;

	rl = blk_get_rl(q, bio);	/* transferred to @rq on success */
retry:
	rq = __get_request(rl, rw_flags, bio, gfp_mask);
	if (rq)
		return rq;

	if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dead(q))) {
		blk_put_rl(rl);
		return NULL;
	}

	/* wait on @rl and retry */
	prepare_to_wait_exclusive(&rl->wait[is_sync], &wait,
				  TASK_UNINTERRUPTIBLE);

	trace_block_sleeprq(q, bio, rw_flags & 1);

	spin_unlock_irq(q->queue_lock);
	io_schedule();

	/*
	 * After sleeping, we become a "batching" process and will be able
	 * to allocate at least one request, and up to a big batch of them
	 * for a small period time.  See ioc_batching, ioc_set_batching
	 */
	ioc_set_batching(q, current->io_context);

	spin_lock_irq(q->queue_lock);
	finish_wait(&rl->wait[is_sync], &wait);

	goto retry;
}

struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
{
	struct request *rq;

	BUG_ON(rw != READ && rw != WRITE);

	/* create ioc upfront */
	create_io_context(gfp_mask, q->node);

	spin_lock_irq(q->queue_lock);
	rq = get_request(q, rw, NULL, gfp_mask);
	if (!rq)
		spin_unlock_irq(q->queue_lock);
	/* q->queue_lock is unlocked at this point */

	return rq;
}
EXPORT_SYMBOL(blk_get_request);

/**
 * blk_make_request - given a bio, allocate a corresponding struct request.
 * @q: target request queue
 * @bio:  The bio describing the memory mappings that will be submitted for IO.
 *        It may be a chained-bio properly constructed by block/bio layer.
 * @gfp_mask: gfp flags to be used for memory allocation
 *
 * blk_make_request is the parallel of generic_make_request for BLOCK_PC
 * type commands. Where the struct request needs to be farther initialized by
 * the caller. It is passed a &struct bio, which describes the memory info of
 * the I/O transfer.
 *
 * The caller of blk_make_request must make sure that bi_io_vec
 * are set to describe the memory buffers. That bio_data_dir() will return
 * the needed direction of the request. (And all bio's in the passed bio-chain
 * are properly set accordingly)
 *
 * If called under none-sleepable conditions, mapped bio buffers must not
 * need bouncing, by calling the appropriate masked or flagged allocator,
 * suitable for the target device. Otherwise the call to blk_queue_bounce will
 * BUG.
 *
 * WARNING: When allocating/cloning a bio-chain, careful consideration should be
 * given to how you allocate bios. In particular, you cannot use __GFP_WAIT for
 * anything but the first bio in the chain. Otherwise you risk waiting for IO
 * completion of a bio that hasn't been submitted yet, thus resulting in a
 * deadlock. Alternatively bios should be allocated using bio_kmalloc() instead
 * of bio_alloc(), as that avoids the mempool deadlock.
 * If possible a big IO should be split into smaller parts when allocation
 * fails. Partial allocation should not be an error, or you risk a live-lock.
 */
struct request *blk_make_request(struct request_queue *q, struct bio *bio,
				 gfp_t gfp_mask)
{
	struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask);

	if (unlikely(!rq))
		return ERR_PTR(-ENOMEM);

	for_each_bio(bio) {
		struct bio *bounce_bio = bio;
		int ret;

		blk_queue_bounce(q, &bounce_bio);
		ret = blk_rq_append_bio(q, rq, bounce_bio);
		if (unlikely(ret)) {
			blk_put_request(rq);
			return ERR_PTR(ret);
		}
	}

	return rq;
}
EXPORT_SYMBOL(blk_make_request);

/**
 * blk_requeue_request - put a request back on queue
 * @q:		request queue where request should be inserted
 * @rq:		request to be inserted
 *
 * Description:
 *    Drivers often keep queueing requests until the hardware cannot accept
 *    more, when that condition happens we need to put the request back
 *    on the queue. Must be called with queue lock held.
 */
void blk_requeue_request(struct request_queue *q, struct request *rq)
{
	blk_delete_timer(rq);
	blk_clear_rq_complete(rq);
	trace_block_rq_requeue(q, rq);

	if (blk_rq_tagged(rq))
		blk_queue_end_tag(q, rq);

	BUG_ON(blk_queued_rq(rq));

	elv_requeue_request(q, rq);
}
EXPORT_SYMBOL(blk_requeue_request);

static void add_acct_request(struct request_queue *q, struct request *rq,
			     int where)
{
	drive_stat_acct(rq, 1);
	__elv_add_request(q, rq, where);
}

static void part_round_stats_single(int cpu, struct hd_struct *part,
				    unsigned long now)
{
	if (now == part->stamp)
		return;

	if (part_in_flight(part)) {
		__part_stat_add(cpu, part, time_in_queue,
				part_in_flight(part) * (now - part->stamp));
		__part_stat_add(cpu, part, io_ticks, (now - part->stamp));
	}
	part->stamp = now;
}

/**
 * part_round_stats() - Round off the performance stats on a struct disk_stats.
 * @cpu: cpu number for stats access
 * @part: target partition
 *
 * The average IO queue length and utilisation statistics are maintained
 * by observing the current state of the queue length and the amount of
 * time it has been in this state for.
 *
 * Normally, that accounting is done on IO completion, but that can result
 * in more than a second's worth of IO being accounted for within any one
 * second, leading to >100% utilisation.  To deal with that, we call this
 * function to do a round-off before returning the results when reading
 * /proc/diskstats.  This accounts immediately for all queue usage up to
 * the current jiffies and restarts the counters again.
 */
void part_round_stats(int cpu, struct hd_struct *part)
{
	unsigned long now = jiffies;

	if (part->partno)
		part_round_stats_single(cpu, &part_to_disk(part)->part0, now);
	part_round_stats_single(cpu, part, now);
}
EXPORT_SYMBOL_GPL(part_round_stats);

/*
 * queue lock must be held
 */
void __blk_put_request(struct request_queue *q, struct request *req)
{
	if (unlikely(!q))
		return;
	if (unlikely(--req->ref_count))
		return;

	elv_completed_request(q, req);

	/* this is a bio leak */
	WARN_ON(req->bio != NULL);

	/*
	 * Request may not have originated from ll_rw_blk. if not,
	 * it didn't come out of our reserved rq pools
	 */
	if (req->cmd_flags & REQ_ALLOCED) {
		unsigned int flags = req->cmd_flags;
		struct request_list *rl = blk_rq_rl(req);

		BUG_ON(!list_empty(&req->queuelist));
		BUG_ON(!hlist_unhashed(&req->hash));

		blk_free_request(rl, req);
		freed_request(rl, flags);
		blk_put_rl(rl);
	}
}
EXPORT_SYMBOL_GPL(__blk_put_request);

void blk_put_request(struct request *req)
{
	unsigned long flags;
	struct request_queue *q = req->q;

	spin_lock_irqsave(q->queue_lock, flags);
	__blk_put_request(q, req);
	spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(blk_put_request);

/**
 * blk_add_request_payload - add a payload to a request
 * @rq: request to update
 * @page: page backing the payload
 * @len: length of the payload.
 *
 * This allows to later add a payload to an already submitted request by
 * a block driver.  The driver needs to take care of freeing the payload
 * itself.
 *
 * Note that this is a quite horrible hack and nothing but handling of
 * discard requests should ever use it.
 */
void blk_add_request_payload(struct request *rq, struct page *page,
		unsigned int len)
{
	struct bio *bio = rq->bio;

	bio->bi_io_vec->bv_page = page;
	bio->bi_io_vec->bv_offset = 0;
	bio->bi_io_vec->bv_len = len;

	bio->bi_size = len;
	bio->bi_vcnt = 1;
	bio->bi_phys_segments = 1;

	rq->__data_len = rq->resid_len = len;
	rq->nr_phys_segments = 1;
	rq->buffer = bio_data(bio);
}
EXPORT_SYMBOL_GPL(blk_add_request_payload);

static bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
				   struct bio *bio)
{
	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;

	if (!ll_back_merge_fn(q, req, bio))
		return false;

	trace_block_bio_backmerge(q, bio);

	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
		blk_rq_set_mixed_merge(req);

	req->biotail->bi_next = bio;
	req->biotail = bio;
	req->__data_len += bio->bi_size;
	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));

	drive_stat_acct(req, 0);
	return true;
}

static bool bio_attempt_front_merge(struct request_queue *q,
				    struct request *req, struct bio *bio)
{
	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;

	if (!ll_front_merge_fn(q, req, bio))
		return false;

	trace_block_bio_frontmerge(q, bio);

	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
		blk_rq_set_mixed_merge(req);

	bio->bi_next = req->bio;
	req->bio = bio;

	/*
	 * may not be valid. if the low level driver said
	 * it didn't need a bounce buffer then it better
	 * not touch req->buffer either...
	 */
	req->buffer = bio_data(bio);
	req->__sector = bio->bi_sector;
	req->__data_len += bio->bi_size;
	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));

	drive_stat_acct(req, 0);
	return true;
}

/**
 * attempt_plug_merge - try to merge with %current's plugged list
 * @q: request_queue new bio is being queued at
 * @bio: new bio being queued
 * @request_count: out parameter for number of traversed plugged requests
 *
 * Determine whether @bio being queued on @q can be merged with a request
 * on %current's plugged list.  Returns %true if merge was successful,
 * otherwise %false.
 *
 * Plugging coalesces IOs from the same issuer for the same purpose without
 * going through @q->queue_lock.  As such it's more of an issuing mechanism
 * than scheduling, and the request, while may have elvpriv data, is not
 * added on the elevator at this point.  In addition, we don't have
 * reliable access to the elevator outside queue lock.  Only check basic
 * merging parameters without querying the elevator.
 */
static bool attempt_plug_merge(struct request_queue *q, struct bio *bio,
			       unsigned int *request_count)
{
	struct blk_plug *plug;
	struct request *rq;
	bool ret = false;

	plug = current->plug;
	if (!plug)
		goto out;
	*request_count = 0;

	list_for_each_entry_reverse(rq, &plug->list, queuelist) {
		int el_ret;

		if (rq->q == q)
			(*request_count)++;

		if (rq->q != q || !blk_rq_merge_ok(rq, bio))
			continue;

		el_ret = blk_try_merge(rq, bio);
		if (el_ret == ELEVATOR_BACK_MERGE) {
			ret = bio_attempt_back_merge(q, rq, bio);
			if (ret)
				break;
		} else if (el_ret == ELEVATOR_FRONT_MERGE) {
			ret = bio_attempt_front_merge(q, rq, bio);
			if (ret)
				break;
		}
	}
out:
	return ret;
}

void init_request_from_bio(struct request *req, struct bio *bio)
{
	req->cmd_type = REQ_TYPE_FS;

	req->cmd_flags |= bio->bi_rw & REQ_COMMON_MASK;
	if (bio->bi_rw & REQ_RAHEAD)
		req->cmd_flags |= REQ_FAILFAST_MASK;

	req->errors = 0;
	req->__sector = bio->bi_sector;
	req->ioprio = bio_prio(bio);
	blk_rq_bio_prep(req->q, req, bio);
}

void blk_queue_bio(struct request_queue *q, struct bio *bio)
{
	const bool sync = !!(bio->bi_rw & REQ_SYNC);
	struct blk_plug *plug;
	int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT;
	struct request *req;
	unsigned int request_count = 0;

	/*
	 * low level driver can indicate that it wants pages above a
	 * certain limit bounced to low memory (ie for highmem, or even
	 * ISA dma in theory)
	 */
	blk_queue_bounce(q, &bio);

	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
		spin_lock_irq(q->queue_lock);
		where = ELEVATOR_INSERT_FLUSH;
		goto get_rq;
	}

	/*
	 * Check if we can merge with the plugged list before grabbing
	 * any locks.
	 */
	if (attempt_plug_merge(q, bio, &request_count))
		return;

	spin_lock_irq(q->queue_lock);

	el_ret = elv_merge(q, &req, bio);
	if (el_ret == ELEVATOR_BACK_MERGE) {
		if (bio_attempt_back_merge(q, req, bio)) {
			elv_bio_merged(q, req, bio);
			if (!attempt_back_merge(q, req))
				elv_merged_request(q, req, el_ret);
			goto out_unlock;
		}
	} else if (el_ret == ELEVATOR_FRONT_MERGE) {
		if (bio_attempt_front_merge(q, req, bio)) {
			elv_bio_merged(q, req, bio);
			if (!attempt_front_merge(q, req))
				elv_merged_request(q, req, el_ret);
			goto out_unlock;
		}
	}

get_rq:
	/*
	 * This sync check and mask will be re-done in init_request_from_bio(),
	 * but we need to set it earlier to expose the sync flag to the
	 * rq allocator and io schedulers.
	 */
	rw_flags = bio_data_dir(bio);
	if (sync)
		rw_flags |= REQ_SYNC;

	/*
	 * Grab a free request. This is might sleep but can not fail.
	 * Returns with the queue unlocked.
	 */
	req = get_request(q, rw_flags, bio, GFP_NOIO);
	if (unlikely(!req)) {
		bio_endio(bio, -ENODEV);	/* @q is dead */
		goto out_unlock;
	}

	/*
	 * After dropping the lock and possibly sleeping here, our request
	 * may now be mergeable after it had proven unmergeable (above).
	 * We don't worry about that case for efficiency. It won't happen
	 * often, and the elevators are able to handle it.
	 */
	init_request_from_bio(req, bio);

	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags))
		req->cpu = raw_smp_processor_id();

	plug = current->plug;
	if (plug) {
		/*
		 * If this is the first request added after a plug, fire
		 * of a plug trace. If others have been added before, check
		 * if we have multiple devices in this plug. If so, make a
		 * note to sort the list before dispatch.
		 */
		if (list_empty(&plug->list))
			trace_block_plug(q);
		else {
			if (!plug->should_sort) {
				struct request *__rq;

				__rq = list_entry_rq(plug->list.prev);
				if (__rq->q != q)
					plug->should_sort = 1;
			}
			if (request_count >= BLK_MAX_REQUEST_COUNT) {
				blk_flush_plug_list(plug, false);
				trace_block_plug(q);
			}
		}
		list_add_tail(&req->queuelist, &plug->list);
		drive_stat_acct(req, 1);
	} else {
		spin_lock_irq(q->queue_lock);
		add_acct_request(q, req, where);
		__blk_run_queue(q);
out_unlock:
		spin_unlock_irq(q->queue_lock);
	}
}
EXPORT_SYMBOL_GPL(blk_queue_bio);	/* for device mapper only */

/*
 * If bio->bi_dev is a partition, remap the location
 */
static inline void blk_partition_remap(struct bio *bio)
{
	struct block_device *bdev = bio->bi_bdev;

	if (bio_sectors(bio) && bdev != bdev->bd_contains) {
		struct hd_struct *p = bdev->bd_part;

		bio->bi_sector += p->start_sect;
		bio->bi_bdev = bdev->bd_contains;

		trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), bio,
				      bdev->bd_dev,
				      bio->bi_sector - p->start_sect);
	}
}

static void handle_bad_sector(struct bio *bio)
{
	char b[BDEVNAME_SIZE];

	printk(KERN_INFO "attempt to access beyond end of device\n");
	printk(KERN_INFO "%s: rw=%ld, want=%Lu, limit=%Lu\n",
			bdevname(bio->bi_bdev, b),
			bio->bi_rw,
			(unsigned long long)bio->bi_sector + bio_sectors(bio),
			(long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));

	set_bit(BIO_EOF, &bio->bi_flags);
}

#ifdef CONFIG_FAIL_MAKE_REQUEST

static DECLARE_FAULT_ATTR(fail_make_request);

static int __init setup_fail_make_request(char *str)
{
	return setup_fault_attr(&fail_make_request, str);
}
__setup("fail_make_request=", setup_fail_make_request);

static bool should_fail_request(struct hd_struct *part, unsigned int bytes)
{
	return part->make_it_fail && should_fail(&fail_make_request, bytes);
}

static int __init fail_make_request_debugfs(void)
{
	struct dentry *dir = fault_create_debugfs_attr("fail_make_request",
						NULL, &fail_make_request);

	return IS_ERR(dir) ? PTR_ERR(dir) : 0;
}

late_initcall(fail_make_request_debugfs);

#else /* CONFIG_FAIL_MAKE_REQUEST */

static inline bool should_fail_request(struct hd_struct *part,
					unsigned int bytes)
{
	return false;
}

#endif /* CONFIG_FAIL_MAKE_REQUEST */

/*
 * Check whether this bio extends beyond the end of the device.
 */
static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors)
{
	sector_t maxsector;

	if (!nr_sectors)
		return 0;

	/* Test device or partition size, when known. */
	maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
	if (maxsector) {
		sector_t sector = bio->bi_sector;

		if (maxsector < nr_sectors || maxsector - nr_sectors < sector) {
			/*
			 * This may well happen - the kernel calls bread()
			 * without checking the size of the device, e.g., when
			 * mounting a device.
			 */
			handle_bad_sector(bio);
			return 1;
		}
	}

	return 0;
}

static noinline_for_stack bool
generic_make_request_checks(struct bio *bio)
{
	struct request_queue *q;
	int nr_sectors = bio_sectors(bio);
	int err = -EIO;
	char b[BDEVNAME_SIZE];
	struct hd_struct *part;

	might_sleep();

	if (bio_check_eod(bio, nr_sectors))
		goto end_io;

	q = bdev_get_queue(bio->bi_bdev);
	if (unlikely(!q)) {
		printk(KERN_ERR
		       "generic_make_request: Trying to access "
			"nonexistent block-device %s (%Lu)\n",
			bdevname(bio->bi_bdev, b),
			(long long) bio->bi_sector);
		goto end_io;
	}

	if (unlikely(!(bio->bi_rw & REQ_DISCARD) &&
		     nr_sectors > queue_max_hw_sectors(q))) {
		printk(KERN_ERR "bio too big device %s (%u > %u)\n",
		       bdevname(bio->bi_bdev, b),
		       bio_sectors(bio),
		       queue_max_hw_sectors(q));
		goto end_io;
	}

	part = bio->bi_bdev->bd_part;
	if (should_fail_request(part, bio->bi_size) ||
	    should_fail_request(&part_to_disk(part)->part0,
				bio->bi_size))
		goto end_io;

	/*
	 * If this device has partitions, remap block n
	 * of partition p to block n+start(p) of the disk.
	 */
	blk_partition_remap(bio);

	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio))
		goto end_io;

	if (bio_check_eod(bio, nr_sectors))
		goto end_io;

	/*
	 * Filter flush bio's early so that make_request based
	 * drivers without flush support don't have to worry
	 * about them.
	 */
	if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) && !q->flush_flags) {
		bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA);
		if (!nr_sectors) {
			err = 0;
			goto end_io;
		}
	}

	if ((bio->bi_rw & REQ_DISCARD) &&
	    (!blk_queue_discard(q) ||
	     ((bio->bi_rw & REQ_SECURE) &&
	      !blk_queue_secdiscard(q)))) {
		err = -EOPNOTSUPP;
		goto end_io;
	}

	/*
	 * Various block parts want %current->io_context and lazy ioc
	 * allocation ends up trading a lot of pain for a small amount of
	 * memory.  Just allocate it upfront.  This may fail and block
	 * layer knows how to live with it.
	 */
	create_io_context(GFP_ATOMIC, q->node);

	if (blk_throtl_bio(q, bio))
		return false;	/* throttled, will be resubmitted later */

	trace_block_bio_queue(q, bio);
	return true;

end_io:
	bio_endio(bio, err);
	return false;
}

/**
 * generic_make_request - hand a buffer to its device driver for I/O
 * @bio:  The bio describing the location in memory and on the device.
 *
 * generic_make_request() is used to make I/O requests of block
 * devices. It is passed a &struct bio, which describes the I/O that needs
 * to be done.
 *
 * generic_make_request() does not return any status.  The
 * success/failure status of the request, along with notification of
 * completion, is delivered asynchronously through the bio->bi_end_io
 * function described (one day) else where.
 *
 * The caller of generic_make_request must make sure that bi_io_vec
 * are set to describe the memory buffer, and that bi_dev and bi_sector are
 * set to describe the device address, and the
 * bi_end_io and optionally bi_private are set to describe how
 * completion notification should be signaled.
 *
 * generic_make_request and the drivers it calls may use bi_next if this
 * bio happens to be merged with someone else, and may resubmit the bio to
 * a lower device by calling into generic_make_request recursively, which
 * means the bio should NOT be touched after the call to ->make_request_fn.
 */
void generic_make_request(struct bio *bio)
{
	struct bio_list bio_list_on_stack;

	if (!generic_make_request_checks(bio))
		return;

	/*
	 * We only want one ->make_request_fn to be active at a time, else
	 * stack usage with stacked devices could be a problem.  So use
	 * current->bio_list to keep a list of requests submited by a
	 * make_request_fn function.  current->bio_list is also used as a
	 * flag to say if generic_make_request is currently active in this
	 * task or not.  If it is NULL, then no make_request is active.  If
	 * it is non-NULL, then a make_request is active, and new requests
	 * should be added at the tail
	 */
	if (current->bio_list) {
		bio_list_add(current->bio_list, bio);
		return;
	}

	/* following loop may be a bit non-obvious, and so deserves some
	 * explanation.
	 * Before entering the loop, bio->bi_next is NULL (as all callers
	 * ensure that) so we have a list with a single bio.
	 * We pretend that we have just taken it off a longer list, so
	 * we assign bio_list to a pointer to the bio_list_on_stack,
	 * thus initialising the bio_list of new bios to be
	 * added.  ->make_request() may indeed add some more bios
	 * through a recursive call to generic_make_request.  If it
	 * did, we find a non-NULL value in bio_list and re-enter the loop
	 * from the top.  In this case we really did just take the bio
	 * of the top of the list (no pretending) and so remove it from
	 * bio_list, and call into ->make_request() again.
	 */
	BUG_ON(bio->bi_next);
	bio_list_init(&bio_list_on_stack);
	current->bio_list = &bio_list_on_stack;
	do {
		struct request_queue *q = bdev_get_queue(bio->bi_bdev);

		q->make_request_fn(q, bio);

		bio = bio_list_pop(current->bio_list);
	} while (bio);
	current->bio_list = NULL; /* deactivate */
}
EXPORT_SYMBOL(generic_make_request);

/**
 * submit_bio - submit a bio to the block device layer for I/O
 * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
 * @bio: The &struct bio which describes the I/O
 *
 * submit_bio() is very similar in purpose to generic_make_request(), and
 * uses that function to do most of the work. Both are fairly rough
 * interfaces; @bio must be presetup and ready for I/O.
 *
 */
void submit_bio(int rw, struct bio *bio)
{
	int count = bio_sectors(bio);

	bio->bi_rw |= rw;

	/*
	 * If it's a regular read/write or a barrier with data attached,
	 * go through the normal accounting stuff before submission.
	 */
	if (bio_has_data(bio) && !(rw & REQ_DISCARD)) {
		if (rw & WRITE) {
			count_vm_events(PGPGOUT, count);
		} else {
			task_io_account_read(bio->bi_size);
			count_vm_events(PGPGIN, count);
		}

		if (unlikely(block_dump)) {
			char b[BDEVNAME_SIZE];
			printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n",
			current->comm, task_pid_nr(current),
				(rw & WRITE) ? "WRITE" : "READ",
				(unsigned long long)bio->bi_sector,
				bdevname(bio->bi_bdev, b),
				count);
		}
	}

	generic_make_request(bio);
}
EXPORT_SYMBOL(submit_bio);

/**
 * blk_rq_check_limits - Helper function to check a request for the queue limit
 * @q:  the queue
 * @rq: the request being checked
 *
 * Description:
 *    @rq may have been made based on weaker limitations of upper-level queues
 *    in request stacking drivers, and it may violate the limitation of @q.
 *    Since the block layer and the underlying device driver trust @rq
 *    after it is inserted to @q, it should be checked against @q before
 *    the insertion using this generic function.
 *
 *    This function should also be useful for request stacking drivers
 *    in some cases below, so export this function.
 *    Request stacking drivers like request-based dm may change the queue
 *    limits while requests are in the queue (e.g. dm's table swapping).
 *    Such request stacking drivers should check those requests agaist
 *    the new queue limits again when they dispatch those requests,
 *    although such checkings are also done against the old queue limits
 *    when submitting requests.
 */
int blk_rq_check_limits(struct request_queue *q, struct request *rq)
{
	if (rq->cmd_flags & REQ_DISCARD)
		return 0;

	if (blk_rq_sectors(rq) > queue_max_sectors(q) ||
	    blk_rq_bytes(rq) > queue_max_hw_sectors(q) << 9) {
		printk(KERN_ERR "%s: over max size limit.\n", __func__);
		return -EIO;
	}

	/*
	 * queue's settings related to segment counting like q->bounce_pfn
	 * may differ from that of other stacking queues.
	 * Recalculate it to check the request correctly on this queue's
	 * limitation.
	 */
	blk_recalc_rq_segments(rq);
	if (rq->nr_phys_segments > queue_max_segments(q)) {
		printk(KERN_ERR "%s: over max segments limit.\n", __func__);
		return -EIO;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(blk_rq_check_limits);

/**
 * blk_insert_cloned_request - Helper for stacking drivers to submit a request
 * @q:  the queue to submit the request
 * @rq: the request being queued
 */
int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
{
	unsigned long flags;
	int where = ELEVATOR_INSERT_BACK;

	if (blk_rq_check_limits(q, rq))
		return -EIO;

	if (rq->rq_disk &&
	    should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
		return -EIO;

	spin_lock_irqsave(q->queue_lock, flags);
	if (unlikely(blk_queue_dead(q))) {
		spin_unlock_irqrestore(q->queue_lock, flags);
		return -ENODEV;
	}

	/*
	 * Submitting request must be dequeued before calling this function
	 * because it will be linked to another request_queue
	 */
	BUG_ON(blk_queued_rq(rq));

	if (rq->cmd_flags & (REQ_FLUSH|REQ_FUA))
		where = ELEVATOR_INSERT_FLUSH;

	add_acct_request(q, rq, where);
	if (where == ELEVATOR_INSERT_FLUSH)
		__blk_run_queue(q);
	spin_unlock_irqrestore(q->queue_lock, flags);

	return 0;
}
EXPORT_SYMBOL_GPL(blk_insert_cloned_request);

/**
 * blk_rq_err_bytes - determine number of bytes till the next failure boundary
 * @rq: request to examine
 *
 * Description:
 *     A request could be merge of IOs which require different failure
 *     handling.  This function determines the number of bytes which
 *     can be failed from the beginning of the request without
 *     crossing into area which need to be retried further.
 *
 * Return:
 *     The number of bytes to fail.
 *
 * Context:
 *     queue_lock must be held.
 */
unsigned int blk_rq_err_bytes(const struct request *rq)
{
	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
	unsigned int bytes = 0;
	struct bio *bio;

	if (!(rq->cmd_flags & REQ_MIXED_MERGE))
		return blk_rq_bytes(rq);

	/*
	 * Currently the only 'mixing' which can happen is between
	 * different fastfail types.  We can safely fail portions
	 * which have all the failfast bits that the first one has -
	 * the ones which are at least as eager to fail as the first
	 * one.
	 */
	for (bio = rq->bio; bio; bio = bio->bi_next) {
		if ((bio->bi_rw & ff) != ff)
			break;
		bytes += bio->bi_size;
	}

	/* this could lead to infinite loop */
	BUG_ON(blk_rq_bytes(rq) && !bytes);
	return bytes;
}
EXPORT_SYMBOL_GPL(blk_rq_err_bytes);

static void blk_account_io_completion(struct request *req, unsigned int bytes)
{
	if (blk_do_io_stat(req)) {
		const int rw = rq_data_dir(req);
		struct hd_struct *part;
		int cpu;

		cpu = part_stat_lock();
		part = req->part;
		part_stat_add(cpu, part, sectors[rw], bytes >> 9);
		part_stat_unlock();
	}
}

static void blk_account_io_done(struct request *req)
{
	/*
	 * Account IO completion.  flush_rq isn't accounted as a
	 * normal IO on queueing nor completion.  Accounting the
	 * containing request is enough.
	 */
	if (blk_do_io_stat(req) && !(req->cmd_flags & REQ_FLUSH_SEQ)) {
		unsigned long duration = jiffies - req->start_time;
		const int rw = rq_data_dir(req);
		struct hd_struct *part;
		int cpu;

		cpu = part_stat_lock();
		part = req->part;

		part_stat_inc(cpu, part, ios[rw]);
		part_stat_add(cpu, part, ticks[rw], duration);
		part_round_stats(cpu, part);
		part_dec_in_flight(part, rw);

		hd_struct_put(part);
		part_stat_unlock();
	}
}

/**
 * blk_peek_request - peek at the top of a request queue
 * @q: request queue to peek at
 *
 * Description:
 *     Return the request at the top of @q.  The returned request
 *     should be started using blk_start_request() before LLD starts
 *     processing it.
 *
 * Return:
 *     Pointer to the request at the top of @q if available.  Null
 *     otherwise.
 *
 * Context:
 *     queue_lock must be held.
 */
struct request *blk_peek_request(struct request_queue *q)
{
	struct request *rq;
	int ret;

	while ((rq = __elv_next_request(q)) != NULL) {
		if (!(rq->cmd_flags & REQ_STARTED)) {
			/*
			 * This is the first time the device driver
			 * sees this request (possibly after
			 * requeueing).  Notify IO scheduler.
			 */
			if (rq->cmd_flags & REQ_SORTED)
				elv_activate_rq(q, rq);

			/*
			 * just mark as started even if we don't start
			 * it, a request that has been delayed should
			 * not be passed by new incoming requests
			 */
			rq->cmd_flags |= REQ_STARTED;
			trace_block_rq_issue(q, rq);
		}

		if (!q->boundary_rq || q->boundary_rq == rq) {
			q->end_sector = rq_end_sector(rq);
			q->boundary_rq = NULL;
		}

		if (rq->cmd_flags & REQ_DONTPREP)
			break;

		if (q->dma_drain_size && blk_rq_bytes(rq)) {
			/*
			 * make sure space for the drain appears we
			 * know we can do this because max_hw_segments
			 * has been adjusted to be one fewer than the
			 * device can handle
			 */
			rq->nr_phys_segments++;
		}

		if (!q->prep_rq_fn)
			break;

		ret = q->prep_rq_fn(q, rq);
		if (ret == BLKPREP_OK) {
			break;
		} else if (ret == BLKPREP_DEFER) {
			/*
			 * the request may have been (partially) prepped.
			 * we need to keep this request in the front to
			 * avoid resource deadlock.  REQ_STARTED will
			 * prevent other fs requests from passing this one.
			 */
			if (q->dma_drain_size && blk_rq_bytes(rq) &&
			    !(rq->cmd_flags & REQ_DONTPREP)) {
				/*
				 * remove the space for the drain we added
				 * so that we don't add it again
				 */
				--rq->nr_phys_segments;
			}

			rq = NULL;
			break;
		} else if (ret == BLKPREP_KILL) {
			rq->cmd_flags |= REQ_QUIET;
			/*
			 * Mark this request as started so we don't trigger
			 * any debug logic in the end I/O path.
			 */
			blk_start_request(rq);
			__blk_end_request_all(rq, -EIO);
		} else {
			printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
			break;
		}
	}

	return rq;
}
EXPORT_SYMBOL(blk_peek_request);

void blk_dequeue_request(struct request *rq)
{
	struct request_queue *q = rq->q;

	BUG_ON(list_empty(&rq->queuelist));
	BUG_ON(ELV_ON_HASH(rq));

	list_del_init(&rq->queuelist);

	/*
	 * the time frame between a request being removed from the lists
	 * and to it is freed is accounted as io that is in progress at
	 * the driver side.
	 */
	if (blk_account_rq(rq)) {
		q->in_flight[rq_is_sync(rq)]++;
		set_io_start_time_ns(rq);
	}
}

/**
 * blk_start_request - start request processing on the driver
 * @req: request to dequeue
 *
 * Description:
 *     Dequeue @req and start timeout timer on it.  This hands off the
 *     request to the driver.
 *
 *     Block internal functions which don't want to start timer should
 *     call blk_dequeue_request().
 *
 * Context:
 *     queue_lock must be held.
 */
void blk_start_request(struct request *req)
{
	blk_dequeue_request(req);

	/*
	 * We are now handing the request to the hardware, initialize
	 * resid_len to full count and add the timeout handler.
	 */
	req->resid_len = blk_rq_bytes(req);
	if (unlikely(blk_bidi_rq(req)))
		req->next_rq->resid_len = blk_rq_bytes(req->next_rq);

	blk_add_timer(req);
}
EXPORT_SYMBOL(blk_start_request);

/**
 * blk_fetch_request - fetch a request from a request queue
 * @q: request queue to fetch a request from
 *
 * Description:
 *     Return the request at the top of @q.  The request is started on
 *     return and LLD can start processing it immediately.
 *
 * Return:
 *     Pointer to the request at the top of @q if available.  Null
 *     otherwise.
 *
 * Context:
 *     queue_lock must be held.
 */
struct request *blk_fetch_request(struct request_queue *q)
{
	struct request *rq;

	rq = blk_peek_request(q);
	if (rq)
		blk_start_request(rq);
	return rq;
}
EXPORT_SYMBOL(blk_fetch_request);

/**
 * blk_update_request - Special helper function for request stacking drivers
 * @req:      the request being processed
 * @error:    %0 for success, < %0 for error
 * @nr_bytes: number of bytes to complete @req
 *
 * Description:
 *     Ends I/O on a number of bytes attached to @req, but doesn't complete
 *     the request structure even if @req doesn't have leftover.
 *     If @req has leftover, sets it up for the next range of segments.
 *
 *     This special helper function is only for request stacking drivers
 *     (e.g. request-based dm) so that they can handle partial completion.
 *     Actual device drivers should use blk_end_request instead.
 *
 *     Passing the result of blk_rq_bytes() as @nr_bytes guarantees
 *     %false return from this function.
 *
 * Return:
 *     %false - this request doesn't have any more data
 *     %true  - this request has more data
 **/
bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
{
	int total_bytes, bio_nbytes, next_idx = 0;
	struct bio *bio;

	if (!req->bio)
		return false;

	trace_block_rq_complete(req->q, req);

	/*
	 * For fs requests, rq is just carrier of independent bio's
	 * and each partial completion should be handled separately.
	 * Reset per-request error on each partial completion.
	 *
	 * TODO: tj: This is too subtle.  It would be better to let
	 * low level drivers do what they see fit.
	 */
	if (req->cmd_type == REQ_TYPE_FS)
		req->errors = 0;

	if (error && req->cmd_type == REQ_TYPE_FS &&
	    !(req->cmd_flags & REQ_QUIET)) {
		char *error_type;

		switch (error) {
		case -ENOLINK:
			error_type = "recoverable transport";
			break;
		case -EREMOTEIO:
			error_type = "critical target";
			break;
		case -EBADE:
			error_type = "critical nexus";
			break;
		case -EIO:
		default:
			error_type = "I/O";
			break;
		}
		printk(KERN_ERR "end_request: %s error, dev %s, sector %llu\n",
		       error_type, req->rq_disk ? req->rq_disk->disk_name : "?",
		       (unsigned long long)blk_rq_pos(req));
	}

	blk_account_io_completion(req, nr_bytes);

	total_bytes = bio_nbytes = 0;
	while ((bio = req->bio) != NULL) {
		int nbytes;

		if (nr_bytes >= bio->bi_size) {
			req->bio = bio->bi_next;
			nbytes = bio->bi_size;
			req_bio_endio(req, bio, nbytes, error);
			next_idx = 0;
			bio_nbytes = 0;
		} else {
			int idx = bio->bi_idx + next_idx;

			if (unlikely(idx >= bio->bi_vcnt)) {
				blk_dump_rq_flags(req, "__end_that");
				printk(KERN_ERR "%s: bio idx %d >= vcnt %d\n",
				       __func__, idx, bio->bi_vcnt);
				break;
			}

			nbytes = bio_iovec_idx(bio, idx)->bv_len;
			BIO_BUG_ON(nbytes > bio->bi_size);

			/*
			 * not a complete bvec done
			 */
			if (unlikely(nbytes > nr_bytes)) {
				bio_nbytes += nr_bytes;
				total_bytes += nr_bytes;
				break;
			}

			/*
			 * advance to the next vector
			 */
			next_idx++;
			bio_nbytes += nbytes;
		}

		total_bytes += nbytes;
		nr_bytes -= nbytes;

		bio = req->bio;
		if (bio) {
			/*
			 * end more in this run, or just return 'not-done'
			 */
			if (unlikely(nr_bytes <= 0))
				break;
		}
	}

	/*
	 * completely done
	 */
	if (!req->bio) {
		/*
		 * Reset counters so that the request stacking driver
		 * can find how many bytes remain in the request
		 * later.
		 */
		req->__data_len = 0;
		return false;
	}

	/*
	 * if the request wasn't completed, update state
	 */
	if (bio_nbytes) {
		req_bio_endio(req, bio, bio_nbytes, error);
		bio->bi_idx += next_idx;
		bio_iovec(bio)->bv_offset += nr_bytes;
		bio_iovec(bio)->bv_len -= nr_bytes;
	}

	req->__data_len -= total_bytes;
	req->buffer = bio_data(req->bio);

	/* update sector only for requests with clear definition of sector */
	if (req->cmd_type == REQ_TYPE_FS || (req->cmd_flags & REQ_DISCARD))
		req->__sector += total_bytes >> 9;

	/* mixed attributes always follow the first bio */
	if (req->cmd_flags & REQ_MIXED_MERGE) {
		req->cmd_flags &= ~REQ_FAILFAST_MASK;
		req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK;
	}

	/*
	 * If total number of sectors is less than the first segment
	 * size, something has gone terribly wrong.
	 */
	if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
		blk_dump_rq_flags(req, "request botched");
		req->__data_len = blk_rq_cur_bytes(req);
	}

	/* recalculate the number of segments */
	blk_recalc_rq_segments(req);

	return true;
}
EXPORT_SYMBOL_GPL(blk_update_request);

static bool blk_update_bidi_request(struct request *rq, int error,
				    unsigned int nr_bytes,
				    unsigned int bidi_bytes)
{
	if (blk_update_request(rq, error, nr_bytes))
		return true;

	/* Bidi request must be completed as a whole */
	if (unlikely(blk_bidi_rq(rq)) &&
	    blk_update_request(rq->next_rq, error, bidi_bytes))
		return true;

	if (blk_queue_add_random(rq->q))
		add_disk_randomness(rq->rq_disk);

	return false;
}

/**
 * blk_unprep_request - unprepare a request
 * @req:	the request
 *
 * This function makes a request ready for complete resubmission (or
 * completion).  It happens only after all error handling is complete,
 * so represents the appropriate moment to deallocate any resources
 * that were allocated to the request in the prep_rq_fn.  The queue
 * lock is held when calling this.
 */
void blk_unprep_request(struct request *req)
{
	struct request_queue *q = req->q;

	req->cmd_flags &= ~REQ_DONTPREP;
	if (q->unprep_rq_fn)
		q->unprep_rq_fn(q, req);
}
EXPORT_SYMBOL_GPL(blk_unprep_request);

/*
 * queue lock must be held
 */
static void blk_finish_request(struct request *req, int error)
{
	if (blk_rq_tagged(req))
		blk_queue_end_tag(req->q, req);

	BUG_ON(blk_queued_rq(req));

	if (unlikely(laptop_mode) && req->cmd_type == REQ_TYPE_FS)
		laptop_io_completion(&req->q->backing_dev_info);

	blk_delete_timer(req);

	if (req->cmd_flags & REQ_DONTPREP)
		blk_unprep_request(req);


	blk_account_io_done(req);

	if (req->end_io)
		req->end_io(req, error);
	else {
		if (blk_bidi_rq(req))
			__blk_put_request(req->next_rq->q, req->next_rq);

		__blk_put_request(req->q, req);
	}
}

/**
 * blk_end_bidi_request - Complete a bidi request
 * @rq:         the request to complete
 * @error:      %0 for success, < %0 for error
 * @nr_bytes:   number of bytes to complete @rq
 * @bidi_bytes: number of bytes to complete @rq->next_rq
 *
 * Description:
 *     Ends I/O on a number of bytes attached to @rq and @rq->next_rq.
 *     Drivers that supports bidi can safely call this member for any
 *     type of request, bidi or uni.  In the later case @bidi_bytes is
 *     just ignored.
 *
 * Return:
 *     %false - we are done with this request
 *     %true  - still buffers pending for this request
 **/
static bool blk_end_bidi_request(struct request *rq, int error,
				 unsigned int nr_bytes, unsigned int bidi_bytes)
{
	struct request_queue *q = rq->q;
	unsigned long flags;

	if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
		return true;

	spin_lock_irqsave(q->queue_lock, flags);
	blk_finish_request(rq, error);
	spin_unlock_irqrestore(q->queue_lock, flags);

	return false;
}

/**
 * __blk_end_bidi_request - Complete a bidi request with queue lock held
 * @rq:         the request to complete
 * @error:      %0 for success, < %0 for error
 * @nr_bytes:   number of bytes to complete @rq
 * @bidi_bytes: number of bytes to complete @rq->next_rq
 *
 * Description:
 *     Identical to blk_end_bidi_request() except that queue lock is
 *     assumed to be locked on entry and remains so on return.
 *
 * Return:
 *     %false - we are done with this request
 *     %true  - still buffers pending for this request
 **/
bool __blk_end_bidi_request(struct request *rq, int error,
				   unsigned int nr_bytes, unsigned int bidi_bytes)
{
	if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
		return true;

	blk_finish_request(rq, error);

	return false;
}

/**
 * blk_end_request - Helper function for drivers to complete the request.
 * @rq:       the request being processed
 * @error:    %0 for success, < %0 for error
 * @nr_bytes: number of bytes to complete
 *
 * Description:
 *     Ends I/O on a number of bytes attached to @rq.
 *     If @rq has leftover, sets it up for the next range of segments.
 *
 * Return:
 *     %false - we are done with this request
 *     %true  - still buffers pending for this request
 **/
bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
{
	return blk_end_bidi_request(rq, error, nr_bytes, 0);
}
EXPORT_SYMBOL(blk_end_request);

/**
 * blk_end_request_all - Helper function for drives to finish the request.
 * @rq: the request to finish
 * @error: %0 for success, < %0 for error
 *
 * Description:
 *     Completely finish @rq.
 */
void blk_end_request_all(struct request *rq, int error)
{
	bool pending;
	unsigned int bidi_bytes = 0;

	if (unlikely(blk_bidi_rq(rq)))
		bidi_bytes = blk_rq_bytes(rq->next_rq);

	pending = blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
	BUG_ON(pending);
}
EXPORT_SYMBOL(blk_end_request_all);

/**
 * blk_end_request_cur - Helper function to finish the current request chunk.
 * @rq: the request to finish the current chunk for
 * @error: %0 for success, < %0 for error
 *
 * Description:
 *     Complete the current consecutively mapped chunk from @rq.
 *
 * Return:
 *     %false - we are done with this request
 *     %true  - still buffers pending for this request
 */
bool blk_end_request_cur(struct request *rq, int error)
{
	return blk_end_request(rq, error, blk_rq_cur_bytes(rq));
}
EXPORT_SYMBOL(blk_end_request_cur);

/**
 * blk_end_request_err - Finish a request till the next failure boundary.
 * @rq: the request to finish till the next failure boundary for
 * @error: must be negative errno
 *
 * Description:
 *     Complete @rq till the next failure boundary.
 *
 * Return:
 *     %false - we are done with this request
 *     %true  - still buffers pending for this request
 */
bool blk_end_request_err(struct request *rq, int error)
{
	WARN_ON(error >= 0);
	return blk_end_request(rq, error, blk_rq_err_bytes(rq));
}
EXPORT_SYMBOL_GPL(blk_end_request_err);

/**
 * __blk_end_request - Helper function for drivers to complete the request.
 * @rq:       the request being processed
 * @error:    %0 for success, < %0 for error
 * @nr_bytes: number of bytes to complete
 *
 * Description:
 *     Must be called with queue lock held unlike blk_end_request().
 *
 * Return:
 *     %false - we are done with this request
 *     %true  - still buffers pending for this request
 **/
bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
{
	return __blk_end_bidi_request(rq, error, nr_bytes, 0);
}
EXPORT_SYMBOL(__blk_end_request);

/**
 * __blk_end_request_all - Helper function for drives to finish the request.
 * @rq: the request to finish
 * @error: %0 for success, < %0 for error
 *
 * Description:
 *     Completely finish @rq.  Must be called with queue lock held.
 */
void __blk_end_request_all(struct request *rq, int error)
{
	bool pending;
	unsigned int bidi_bytes = 0;

	if (unlikely(blk_bidi_rq(rq)))
		bidi_bytes = blk_rq_bytes(rq->next_rq);

	pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
	BUG_ON(pending);
}
EXPORT_SYMBOL(__blk_end_request_all);

/**
 * __blk_end_request_cur - Helper function to finish the current request chunk.
 * @rq: the request to finish the current chunk for
 * @error: %0 for success, < %0 for error
 *
 * Description:
 *     Complete the current consecutively mapped chunk from @rq.  Must
 *     be called with queue lock held.
 *
 * Return:
 *     %false - we are done with this request
 *     %true  - still buffers pending for this request
 */
bool __blk_end_request_cur(struct request *rq, int error)
{
	return __blk_end_request(rq, error, blk_rq_cur_bytes(rq));
}
EXPORT_SYMBOL(__blk_end_request_cur);

/**
 * __blk_end_request_err - Finish a request till the next failure boundary.
 * @rq: the request to finish till the next failure boundary for
 * @error: must be negative errno
 *
 * Description:
 *     Complete @rq till the next failure boundary.  Must be called
 *     with queue lock held.
 *
 * Return:
 *     %false - we are done with this request
 *     %true  - still buffers pending for this request
 */
bool __blk_end_request_err(struct request *rq, int error)
{
	WARN_ON(error >= 0);
	return __blk_end_request(rq, error, blk_rq_err_bytes(rq));
}
EXPORT_SYMBOL_GPL(__blk_end_request_err);

void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
		     struct bio *bio)
{
	/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
	rq->cmd_flags |= bio->bi_rw & REQ_WRITE;

	if (bio_has_data(bio)) {
		rq->nr_phys_segments = bio_phys_segments(q, bio);
		rq->buffer = bio_data(bio);
	}
	rq->__data_len = bio->bi_size;
	rq->bio = rq->biotail = bio;

	if (bio->bi_bdev)
		rq->rq_disk = bio->bi_bdev->bd_disk;
}

#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
/**
 * rq_flush_dcache_pages - Helper function to flush all pages in a request
 * @rq: the request to be flushed
 *
 * Description:
 *     Flush all pages in @rq.
 */
void rq_flush_dcache_pages(struct request *rq)
{
	struct req_iterator iter;
	struct bio_vec *bvec;

	rq_for_each_segment(bvec, rq, iter)
		flush_dcache_page(bvec->bv_page);
}
EXPORT_SYMBOL_GPL(rq_flush_dcache_pages);
#endif

/**
 * blk_lld_busy - Check if underlying low-level drivers of a device are busy
 * @q : the queue of the device being checked
 *
 * Description:
 *    Check if underlying low-level drivers of a device are busy.
 *    If the drivers want to export their busy state, they must set own
 *    exporting function using blk_queue_lld_busy() first.
 *
 *    Basically, this function is used only by request stacking drivers
 *    to stop dispatching requests to underlying devices when underlying
 *    devices are busy.  This behavior helps more I/O merging on the queue
 *    of the request stacking driver and prevents I/O throughput regression
 *    on burst I/O load.
 *
 * Return:
 *    0 - Not busy (The request stacking driver should dispatch request)
 *    1 - Busy (The request stacking driver should stop dispatching request)
 */
int blk_lld_busy(struct request_queue *q)
{
	if (q->lld_busy_fn)
		return q->lld_busy_fn(q);

	return 0;
}
EXPORT_SYMBOL_GPL(blk_lld_busy);

/**
 * blk_rq_unprep_clone - Helper function to free all bios in a cloned request
 * @rq: the clone request to be cleaned up
 *
 * Description:
 *     Free all bios in @rq for a cloned request.
 */
void blk_rq_unprep_clone(struct request *rq)
{
	struct bio *bio;

	while ((bio = rq->bio) != NULL) {
		rq->bio = bio->bi_next;

		bio_put(bio);
	}
}
EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);

/*
 * Copy attributes of the original request to the clone request.
 * The actual data parts (e.g. ->cmd, ->buffer, ->sense) are not copied.
 */
static void __blk_rq_prep_clone(struct request *dst, struct request *src)
{
	dst->cpu = src->cpu;
	dst->cmd_flags = (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
	dst->cmd_type = src->cmd_type;
	dst->__sector = blk_rq_pos(src);
	dst->__data_len = blk_rq_bytes(src);
	dst->nr_phys_segments = src->nr_phys_segments;
	dst->ioprio = src->ioprio;
	dst->extra_len = src->extra_len;
}

/**
 * blk_rq_prep_clone - Helper function to setup clone request
 * @rq: the request to be setup
 * @rq_src: original request to be cloned
 * @bs: bio_set that bios for clone are allocated from
 * @gfp_mask: memory allocation mask for bio
 * @bio_ctr: setup function to be called for each clone bio.
 *           Returns %0 for success, non %0 for failure.
 * @data: private data to be passed to @bio_ctr
 *
 * Description:
 *     Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
 *     The actual data parts of @rq_src (e.g. ->cmd, ->buffer, ->sense)
 *     are not copied, and copying such parts is the caller's responsibility.
 *     Also, pages which the original bios are pointing to are not copied
 *     and the cloned bios just point same pages.
 *     So cloned bios must be completed before original bios, which means
 *     the caller must complete @rq before @rq_src.
 */
int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
		      struct bio_set *bs, gfp_t gfp_mask,
		      int (*bio_ctr)(struct bio *, struct bio *, void *),
		      void *data)
{
	struct bio *bio, *bio_src;

	if (!bs)
		bs = fs_bio_set;

	blk_rq_init(NULL, rq);

	__rq_for_each_bio(bio_src, rq_src) {
		bio = bio_alloc_bioset(gfp_mask, bio_src->bi_max_vecs, bs);
		if (!bio)
			goto free_and_out;

		__bio_clone(bio, bio_src);

		if (bio_integrity(bio_src) &&
		    bio_integrity_clone(bio, bio_src, gfp_mask, bs))
			goto free_and_out;

		if (bio_ctr && bio_ctr(bio, bio_src, data))
			goto free_and_out;

		if (rq->bio) {
			rq->biotail->bi_next = bio;
			rq->biotail = bio;
		} else
			rq->bio = rq->biotail = bio;
	}

	__blk_rq_prep_clone(rq, rq_src);

	return 0;

free_and_out:
	if (bio)
		bio_free(bio, bs);
	blk_rq_unprep_clone(rq);

	return -ENOMEM;
}
EXPORT_SYMBOL_GPL(blk_rq_prep_clone);

int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
{
	return queue_work(kblockd_workqueue, work);
}
EXPORT_SYMBOL(kblockd_schedule_work);

int kblockd_schedule_delayed_work(struct request_queue *q,
			struct delayed_work *dwork, unsigned long delay)
{
	return queue_delayed_work(kblockd_workqueue, dwork, delay);
}
EXPORT_SYMBOL(kblockd_schedule_delayed_work);

#define PLUG_MAGIC	0x91827364

/**
 * blk_start_plug - initialize blk_plug and track it inside the task_struct
 * @plug:	The &struct blk_plug that needs to be initialized
 *
 * Description:
 *   Tracking blk_plug inside the task_struct will help with auto-flushing the
 *   pending I/O should the task end up blocking between blk_start_plug() and
 *   blk_finish_plug(). This is important from a performance perspective, but
 *   also ensures that we don't deadlock. For instance, if the task is blocking
 *   for a memory allocation, memory reclaim could end up wanting to free a
 *   page belonging to that request that is currently residing in our private
 *   plug. By flushing the pending I/O when the process goes to sleep, we avoid
 *   this kind of deadlock.
 */
void blk_start_plug(struct blk_plug *plug)
{
	struct task_struct *tsk = current;

	plug->magic = PLUG_MAGIC;
	INIT_LIST_HEAD(&plug->list);
	INIT_LIST_HEAD(&plug->cb_list);
	plug->should_sort = 0;

	/*
	 * If this is a nested plug, don't actually assign it. It will be
	 * flushed on its own.
	 */
	if (!tsk->plug) {
		/*
		 * Store ordering should not be needed here, since a potential
		 * preempt will imply a full memory barrier
		 */
		tsk->plug = plug;
	}
}
EXPORT_SYMBOL(blk_start_plug);

static int plug_rq_cmp(void *priv, struct list_head *a, struct list_head *b)
{
	struct request *rqa = container_of(a, struct request, queuelist);
	struct request *rqb = container_of(b, struct request, queuelist);

	return !(rqa->q <= rqb->q);
}

/*
 * If 'from_schedule' is true, then postpone the dispatch of requests
 * until a safe kblockd context. We due this to avoid accidental big
 * additional stack usage in driver dispatch, in places where the originally
 * plugger did not intend it.
 */
static void queue_unplugged(struct request_queue *q, unsigned int depth,
			    bool from_schedule)
	__releases(q->queue_lock)
{
	trace_block_unplug(q, depth, !from_schedule);

	/*
	 * Don't mess with dead queue.
	 */
	if (unlikely(blk_queue_dead(q))) {
		spin_unlock(q->queue_lock);
		return;
	}

	/*
	 * If we are punting this to kblockd, then we can safely drop
	 * the queue_lock before waking kblockd (which needs to take
	 * this lock).
	 */
	if (from_schedule) {
		spin_unlock(q->queue_lock);
		blk_run_queue_async(q);
	} else {
		__blk_run_queue(q);
		spin_unlock(q->queue_lock);
	}

}

static void flush_plug_callbacks(struct blk_plug *plug)
{
	LIST_HEAD(callbacks);

	if (list_empty(&plug->cb_list))
		return;

	list_splice_init(&plug->cb_list, &callbacks);

	while (!list_empty(&callbacks)) {
		struct blk_plug_cb *cb = list_first_entry(&callbacks,
							  struct blk_plug_cb,
							  list);
		list_del(&cb->list);
		cb->callback(cb);
	}
}

struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data,
				      int size)
{
	struct blk_plug *plug = current->plug;
	struct blk_plug_cb *cb;

	if (!plug)
		return NULL;

	list_for_each_entry(cb, &plug->cb_list, list)
		if (cb->callback == unplug && cb->data == data)
			return cb;

	/* Not currently on the callback list */
	BUG_ON(size < sizeof(*cb));
	cb = kzalloc(size, GFP_ATOMIC);
	if (cb) {
		cb->data = data;
		cb->callback = unplug;
		list_add(&cb->list, &plug->cb_list);
	}
	return cb;
}
EXPORT_SYMBOL(blk_check_plugged);

void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
	struct request_queue *q;
	unsigned long flags;
	struct request *rq;
	LIST_HEAD(list);
	unsigned int depth;

	BUG_ON(plug->magic != PLUG_MAGIC);

	flush_plug_callbacks(plug);
	if (list_empty(&plug->list))
		return;

	list_splice_init(&plug->list, &list);

	if (plug->should_sort) {
		list_sort(NULL, &list, plug_rq_cmp);
		plug->should_sort = 0;
	}

	q = NULL;
	depth = 0;

	/*
	 * Save and disable interrupts here, to avoid doing it for every
	 * queue lock we have to take.
	 */
	local_irq_save(flags);
	while (!list_empty(&list)) {
		rq = list_entry_rq(list.next);
		list_del_init(&rq->queuelist);
		BUG_ON(!rq->q);
		if (rq->q != q) {
			/*
			 * This drops the queue lock
			 */
			if (q)
				queue_unplugged(q, depth, from_schedule);
			q = rq->q;
			depth = 0;
			spin_lock(q->queue_lock);
		}

		/*
		 * Short-circuit if @q is dead
		 */
		if (unlikely(blk_queue_dead(q))) {
			__blk_end_request_all(rq, -ENODEV);
			continue;
		}

		/*
		 * rq is already accounted, so use raw insert
		 */
		if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA))
			__elv_add_request(q, rq, ELEVATOR_INSERT_FLUSH);
		else
			__elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE);

		depth++;
	}

	/*
	 * This drops the queue lock
	 */
	if (q)
		queue_unplugged(q, depth, from_schedule);

	local_irq_restore(flags);
}

void blk_finish_plug(struct blk_plug *plug)
{
	blk_flush_plug_list(plug, false);

	if (plug == current->plug)
		current->plug = NULL;
}
EXPORT_SYMBOL(blk_finish_plug);

int __init blk_dev_init(void)
{
	BUILD_BUG_ON(__REQ_NR_BITS > 8 *
			sizeof(((struct request *)0)->cmd_flags));

	/* used for unplugging and affects IO latency/throughput - HIGHPRI */
	kblockd_workqueue = alloc_workqueue("kblockd",
					    WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
	if (!kblockd_workqueue)
		panic("Failed to create kblockd\n");

	request_cachep = kmem_cache_create("blkdev_requests",
			sizeof(struct request), 0, SLAB_PANIC, NULL);

	blk_requestq_cachep = kmem_cache_create("blkdev_queue",
			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);

	return 0;
}
OpenPOWER on IntegriCloud