aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux/usb.h
blob: d3d0c1374334d58c684e5f1b4d13422aa8f57ae8 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
#ifndef __LINUX_USB_H
#define __LINUX_USB_H

#include <linux/mod_devicetable.h>
#include <linux/usb/ch9.h>

#define USB_MAJOR			180
#define USB_DEVICE_MAJOR		189


#ifdef __KERNEL__

#include <linux/errno.h>        /* for -ENODEV */
#include <linux/delay.h>	/* for mdelay() */
#include <linux/interrupt.h>	/* for in_interrupt() */
#include <linux/list.h>		/* for struct list_head */
#include <linux/kref.h>		/* for struct kref */
#include <linux/device.h>	/* for struct device */
#include <linux/fs.h>		/* for struct file_operations */
#include <linux/completion.h>	/* for struct completion */
#include <linux/sched.h>	/* for current && schedule_timeout */
#include <linux/mutex.h>	/* for struct mutex */
#include <linux/pm_runtime.h>	/* for runtime PM */

struct usb_device;
struct usb_driver;
struct wusb_dev;

/*-------------------------------------------------------------------------*/

/*
 * Host-side wrappers for standard USB descriptors ... these are parsed
 * from the data provided by devices.  Parsing turns them from a flat
 * sequence of descriptors into a hierarchy:
 *
 *  - devices have one (usually) or more configs;
 *  - configs have one (often) or more interfaces;
 *  - interfaces have one (usually) or more settings;
 *  - each interface setting has zero or (usually) more endpoints.
 *  - a SuperSpeed endpoint has a companion descriptor
 *
 * And there might be other descriptors mixed in with those.
 *
 * Devices may also have class-specific or vendor-specific descriptors.
 */

struct ep_device;

/**
 * struct usb_host_endpoint - host-side endpoint descriptor and queue
 * @desc: descriptor for this endpoint, wMaxPacketSize in native byteorder
 * @ss_ep_comp: SuperSpeed companion descriptor for this endpoint
 * @urb_list: urbs queued to this endpoint; maintained by usbcore
 * @hcpriv: for use by HCD; typically holds hardware dma queue head (QH)
 *	with one or more transfer descriptors (TDs) per urb
 * @ep_dev: ep_device for sysfs info
 * @extra: descriptors following this endpoint in the configuration
 * @extralen: how many bytes of "extra" are valid
 * @enabled: URBs may be submitted to this endpoint
 *
 * USB requests are always queued to a given endpoint, identified by a
 * descriptor within an active interface in a given USB configuration.
 */
struct usb_host_endpoint {
	struct usb_endpoint_descriptor		desc;
	struct usb_ss_ep_comp_descriptor	ss_ep_comp;
	struct list_head		urb_list;
	void				*hcpriv;
	struct ep_device		*ep_dev;	/* For sysfs info */

	unsigned char *extra;   /* Extra descriptors */
	int extralen;
	int enabled;
};

/* host-side wrapper for one interface setting's parsed descriptors */
struct usb_host_interface {
	struct usb_interface_descriptor	desc;

	/* array of desc.bNumEndpoint endpoints associated with this
	 * interface setting.  these will be in no particular order.
	 */
	struct usb_host_endpoint *endpoint;

	char *string;		/* iInterface string, if present */
	unsigned char *extra;   /* Extra descriptors */
	int extralen;
};

enum usb_interface_condition {
	USB_INTERFACE_UNBOUND = 0,
	USB_INTERFACE_BINDING,
	USB_INTERFACE_BOUND,
	USB_INTERFACE_UNBINDING,
};

/**
 * struct usb_interface - what usb device drivers talk to
 * @altsetting: array of interface structures, one for each alternate
 *	setting that may be selected.  Each one includes a set of
 *	endpoint configurations.  They will be in no particular order.
 * @cur_altsetting: the current altsetting.
 * @num_altsetting: number of altsettings defined.
 * @intf_assoc: interface association descriptor
 * @minor: the minor number assigned to this interface, if this
 *	interface is bound to a driver that uses the USB major number.
 *	If this interface does not use the USB major, this field should
 *	be unused.  The driver should set this value in the probe()
 *	function of the driver, after it has been assigned a minor
 *	number from the USB core by calling usb_register_dev().
 * @condition: binding state of the interface: not bound, binding
 *	(in probe()), bound to a driver, or unbinding (in disconnect())
 * @sysfs_files_created: sysfs attributes exist
 * @ep_devs_created: endpoint child pseudo-devices exist
 * @unregistering: flag set when the interface is being unregistered
 * @needs_remote_wakeup: flag set when the driver requires remote-wakeup
 *	capability during autosuspend.
 * @needs_altsetting0: flag set when a set-interface request for altsetting 0
 *	has been deferred.
 * @needs_binding: flag set when the driver should be re-probed or unbound
 *	following a reset or suspend operation it doesn't support.
 * @dev: driver model's view of this device
 * @usb_dev: if an interface is bound to the USB major, this will point
 *	to the sysfs representation for that device.
 * @pm_usage_cnt: PM usage counter for this interface
 * @reset_ws: Used for scheduling resets from atomic context.
 * @reset_running: set to 1 if the interface is currently running a
 *      queued reset so that usb_cancel_queued_reset() doesn't try to
 *      remove from the workqueue when running inside the worker
 *      thread. See __usb_queue_reset_device().
 * @resetting_device: USB core reset the device, so use alt setting 0 as
 *	current; needs bandwidth alloc after reset.
 *
 * USB device drivers attach to interfaces on a physical device.  Each
 * interface encapsulates a single high level function, such as feeding
 * an audio stream to a speaker or reporting a change in a volume control.
 * Many USB devices only have one interface.  The protocol used to talk to
 * an interface's endpoints can be defined in a usb "class" specification,
 * or by a product's vendor.  The (default) control endpoint is part of
 * every interface, but is never listed among the interface's descriptors.
 *
 * The driver that is bound to the interface can use standard driver model
 * calls such as dev_get_drvdata() on the dev member of this structure.
 *
 * Each interface may have alternate settings.  The initial configuration
 * of a device sets altsetting 0, but the device driver can change
 * that setting using usb_set_interface().  Alternate settings are often
 * used to control the use of periodic endpoints, such as by having
 * different endpoints use different amounts of reserved USB bandwidth.
 * All standards-conformant USB devices that use isochronous endpoints
 * will use them in non-default settings.
 *
 * The USB specification says that alternate setting numbers must run from
 * 0 to one less than the total number of alternate settings.  But some
 * devices manage to mess this up, and the structures aren't necessarily
 * stored in numerical order anyhow.  Use usb_altnum_to_altsetting() to
 * look up an alternate setting in the altsetting array based on its number.
 */
struct usb_interface {
	/* array of alternate settings for this interface,
	 * stored in no particular order */
	struct usb_host_interface *altsetting;

	struct usb_host_interface *cur_altsetting;	/* the currently
					 * active alternate setting */
	unsigned num_altsetting;	/* number of alternate settings */

	/* If there is an interface association descriptor then it will list
	 * the associated interfaces */
	struct usb_interface_assoc_descriptor *intf_assoc;

	int minor;			/* minor number this interface is
					 * bound to */
	enum usb_interface_condition condition;		/* state of binding */
	unsigned sysfs_files_created:1;	/* the sysfs attributes exist */
	unsigned ep_devs_created:1;	/* endpoint "devices" exist */
	unsigned unregistering:1;	/* unregistration is in progress */
	unsigned needs_remote_wakeup:1;	/* driver requires remote wakeup */
	unsigned needs_altsetting0:1;	/* switch to altsetting 0 is pending */
	unsigned needs_binding:1;	/* needs delayed unbind/rebind */
	unsigned reset_running:1;
	unsigned resetting_device:1;	/* true: bandwidth alloc after reset */

	struct device dev;		/* interface specific device info */
	struct device *usb_dev;
	atomic_t pm_usage_cnt;		/* usage counter for autosuspend */
	struct work_struct reset_ws;	/* for resets in atomic context */
};
#define	to_usb_interface(d) container_of(d, struct usb_interface, dev)

static inline void *usb_get_intfdata(struct usb_interface *intf)
{
	return dev_get_drvdata(&intf->dev);
}

static inline void usb_set_intfdata(struct usb_interface *intf, void *data)
{
	dev_set_drvdata(&intf->dev, data);
}

struct usb_interface *usb_get_intf(struct usb_interface *intf);
void usb_put_intf(struct usb_interface *intf);

/* this maximum is arbitrary */
#define USB_MAXINTERFACES	32
#define USB_MAXIADS		(USB_MAXINTERFACES/2)

/**
 * struct usb_interface_cache - long-term representation of a device interface
 * @num_altsetting: number of altsettings defined.
 * @ref: reference counter.
 * @altsetting: variable-length array of interface structures, one for
 *	each alternate setting that may be selected.  Each one includes a
 *	set of endpoint configurations.  They will be in no particular order.
 *
 * These structures persist for the lifetime of a usb_device, unlike
 * struct usb_interface (which persists only as long as its configuration
 * is installed).  The altsetting arrays can be accessed through these
 * structures at any time, permitting comparison of configurations and
 * providing support for the /proc/bus/usb/devices pseudo-file.
 */
struct usb_interface_cache {
	unsigned num_altsetting;	/* number of alternate settings */
	struct kref ref;		/* reference counter */

	/* variable-length array of alternate settings for this interface,
	 * stored in no particular order */
	struct usb_host_interface altsetting[0];
};
#define	ref_to_usb_interface_cache(r) \
		container_of(r, struct usb_interface_cache, ref)
#define	altsetting_to_usb_interface_cache(a) \
		container_of(a, struct usb_interface_cache, altsetting[0])

/**
 * struct usb_host_config - representation of a device's configuration
 * @desc: the device's configuration descriptor.
 * @string: pointer to the cached version of the iConfiguration string, if
 *	present for this configuration.
 * @intf_assoc: list of any interface association descriptors in this config
 * @interface: array of pointers to usb_interface structures, one for each
 *	interface in the configuration.  The number of interfaces is stored
 *	in desc.bNumInterfaces.  These pointers are valid only while the
 *	the configuration is active.
 * @intf_cache: array of pointers to usb_interface_cache structures, one
 *	for each interface in the configuration.  These structures exist
 *	for the entire life of the device.
 * @extra: pointer to buffer containing all extra descriptors associated
 *	with this configuration (those preceding the first interface
 *	descriptor).
 * @extralen: length of the extra descriptors buffer.
 *
 * USB devices may have multiple configurations, but only one can be active
 * at any time.  Each encapsulates a different operational environment;
 * for example, a dual-speed device would have separate configurations for
 * full-speed and high-speed operation.  The number of configurations
 * available is stored in the device descriptor as bNumConfigurations.
 *
 * A configuration can contain multiple interfaces.  Each corresponds to
 * a different function of the USB device, and all are available whenever
 * the configuration is active.  The USB standard says that interfaces
 * are supposed to be numbered from 0 to desc.bNumInterfaces-1, but a lot
 * of devices get this wrong.  In addition, the interface array is not
 * guaranteed to be sorted in numerical order.  Use usb_ifnum_to_if() to
 * look up an interface entry based on its number.
 *
 * Device drivers should not attempt to activate configurations.  The choice
 * of which configuration to install is a policy decision based on such
 * considerations as available power, functionality provided, and the user's
 * desires (expressed through userspace tools).  However, drivers can call
 * usb_reset_configuration() to reinitialize the current configuration and
 * all its interfaces.
 */
struct usb_host_config {
	struct usb_config_descriptor	desc;

	char *string;		/* iConfiguration string, if present */

	/* List of any Interface Association Descriptors in this
	 * configuration. */
	struct usb_interface_assoc_descriptor *intf_assoc[USB_MAXIADS];

	/* the interfaces associated with this configuration,
	 * stored in no particular order */
	struct usb_interface *interface[USB_MAXINTERFACES];

	/* Interface information available even when this is not the
	 * active configuration */
	struct usb_interface_cache *intf_cache[USB_MAXINTERFACES];

	unsigned char *extra;   /* Extra descriptors */
	int extralen;
};

/* USB2.0 and USB3.0 device BOS descriptor set */
struct usb_host_bos {
	struct usb_bos_descriptor	*desc;

	/* wireless cap descriptor is handled by wusb */
	struct usb_ext_cap_descriptor	*ext_cap;
	struct usb_ss_cap_descriptor	*ss_cap;
	struct usb_ss_container_id_descriptor	*ss_id;
};

int __usb_get_extra_descriptor(char *buffer, unsigned size,
	unsigned char type, void **ptr);
#define usb_get_extra_descriptor(ifpoint, type, ptr) \
				__usb_get_extra_descriptor((ifpoint)->extra, \
				(ifpoint)->extralen, \
				type, (void **)ptr)

/* ----------------------------------------------------------------------- */

/* USB device number allocation bitmap */
struct usb_devmap {
	unsigned long devicemap[128 / (8*sizeof(unsigned long))];
};

/*
 * Allocated per bus (tree of devices) we have:
 */
struct usb_bus {
	struct device *controller;	/* host/master side hardware */
	int busnum;			/* Bus number (in order of reg) */
	const char *bus_name;		/* stable id (PCI slot_name etc) */
	u8 uses_dma;			/* Does the host controller use DMA? */
	u8 uses_pio_for_control;	/*
					 * Does the host controller use PIO
					 * for control transfers?
					 */
	u8 otg_port;			/* 0, or number of OTG/HNP port */
	unsigned is_b_host:1;		/* true during some HNP roleswitches */
	unsigned b_hnp_enable:1;	/* OTG: did A-Host enable HNP? */
	unsigned sg_tablesize;		/* 0 or largest number of sg list entries */

	int devnum_next;		/* Next open device number in
					 * round-robin allocation */

	struct usb_devmap devmap;	/* device address allocation map */
	struct usb_device *root_hub;	/* Root hub */
	struct usb_bus *hs_companion;	/* Companion EHCI bus, if any */
	struct list_head bus_list;	/* list of busses */

	int bandwidth_allocated;	/* on this bus: how much of the time
					 * reserved for periodic (intr/iso)
					 * requests is used, on average?
					 * Units: microseconds/frame.
					 * Limits: Full/low speed reserve 90%,
					 * while high speed reserves 80%.
					 */
	int bandwidth_int_reqs;		/* number of Interrupt requests */
	int bandwidth_isoc_reqs;	/* number of Isoc. requests */

#ifdef CONFIG_USB_DEVICEFS
	struct dentry *usbfs_dentry;	/* usbfs dentry entry for the bus */
#endif

#if defined(CONFIG_USB_MON) || defined(CONFIG_USB_MON_MODULE)
	struct mon_bus *mon_bus;	/* non-null when associated */
	int monitored;			/* non-zero when monitored */
#endif
};

/* ----------------------------------------------------------------------- */

/* This is arbitrary.
 * From USB 2.0 spec Table 11-13, offset 7, a hub can
 * have up to 255 ports. The most yet reported is 10.
 *
 * Current Wireless USB host hardware (Intel i1480 for example) allows
 * up to 22 devices to connect. Upcoming hardware might raise that
 * limit. Because the arrays need to add a bit for hub status data, we
 * do 31, so plus one evens out to four bytes.
 */
#define USB_MAXCHILDREN		(31)

struct usb_tt;

/**
 * struct usb_device - kernel's representation of a USB device
 * @devnum: device number; address on a USB bus
 * @devpath: device ID string for use in messages (e.g., /port/...)
 * @route: tree topology hex string for use with xHCI
 * @state: device state: configured, not attached, etc.
 * @speed: device speed: high/full/low (or error)
 * @tt: Transaction Translator info; used with low/full speed dev, highspeed hub
 * @ttport: device port on that tt hub
 * @toggle: one bit for each endpoint, with ([0] = IN, [1] = OUT) endpoints
 * @parent: our hub, unless we're the root
 * @bus: bus we're part of
 * @ep0: endpoint 0 data (default control pipe)
 * @dev: generic device interface
 * @descriptor: USB device descriptor
 * @bos: USB device BOS descriptor set
 * @config: all of the device's configs
 * @actconfig: the active configuration
 * @ep_in: array of IN endpoints
 * @ep_out: array of OUT endpoints
 * @rawdescriptors: raw descriptors for each config
 * @bus_mA: Current available from the bus
 * @portnum: parent port number (origin 1)
 * @level: number of USB hub ancestors
 * @can_submit: URBs may be submitted
 * @persist_enabled:  USB_PERSIST enabled for this device
 * @have_langid: whether string_langid is valid
 * @authorized: policy has said we can use it;
 *	(user space) policy determines if we authorize this device to be
 *	used or not. By default, wired USB devices are authorized.
 *	WUSB devices are not, until we authorize them from user space.
 *	FIXME -- complete doc
 * @authenticated: Crypto authentication passed
 * @wusb: device is Wireless USB
 * @lpm_capable: device supports LPM
 * @usb2_hw_lpm_capable: device can perform USB2 hardware LPM
 * @usb2_hw_lpm_enabled: USB2 hardware LPM enabled
 * @string_langid: language ID for strings
 * @product: iProduct string, if present (static)
 * @manufacturer: iManufacturer string, if present (static)
 * @serial: iSerialNumber string, if present (static)
 * @filelist: usbfs files that are open to this device
 * @usb_classdev: USB class device that was created for usbfs device
 *	access from userspace
 * @usbfs_dentry: usbfs dentry entry for the device
 * @maxchild: number of ports if hub
 * @children: child devices - USB devices that are attached to this hub
 * @quirks: quirks of the whole device
 * @urbnum: number of URBs submitted for the whole device
 * @active_duration: total time device is not suspended
 * @connect_time: time device was first connected
 * @do_remote_wakeup:  remote wakeup should be enabled
 * @reset_resume: needs reset instead of resume
 * @wusb_dev: if this is a Wireless USB device, link to the WUSB
 *	specific data for the device.
 * @slot_id: Slot ID assigned by xHCI
 *
 * Notes:
 * Usbcore drivers should not set usbdev->state directly.  Instead use
 * usb_set_device_state().
 */
struct usb_device {
	int		devnum;
	char		devpath[16];
	u32		route;
	enum usb_device_state	state;
	enum usb_device_speed	speed;

	struct usb_tt	*tt;
	int		ttport;

	unsigned int toggle[2];

	struct usb_device *parent;
	struct usb_bus *bus;
	struct usb_host_endpoint ep0;

	struct device dev;

	struct usb_device_descriptor descriptor;
	struct usb_host_bos *bos;
	struct usb_host_config *config;

	struct usb_host_config *actconfig;
	struct usb_host_endpoint *ep_in[16];
	struct usb_host_endpoint *ep_out[16];

	char **rawdescriptors;

	unsigned short bus_mA;
	u8 portnum;
	u8 level;

	unsigned can_submit:1;
	unsigned persist_enabled:1;
	unsigned have_langid:1;
	unsigned authorized:1;
	unsigned authenticated:1;
	unsigned wusb:1;
	unsigned lpm_capable:1;
	unsigned usb2_hw_lpm_capable:1;
	unsigned usb2_hw_lpm_enabled:1;
	int string_langid;

	/* static strings from the device */
	char *product;
	char *manufacturer;
	char *serial;

	struct list_head filelist;
#ifdef CONFIG_USB_DEVICE_CLASS
	struct device *usb_classdev;
#endif
#ifdef CONFIG_USB_DEVICEFS
	struct dentry *usbfs_dentry;
#endif

	int maxchild;
	struct usb_device *children[USB_MAXCHILDREN];

	u32 quirks;
	atomic_t urbnum;

	unsigned long active_duration;

#ifdef CONFIG_PM
	unsigned long connect_time;

	unsigned do_remote_wakeup:1;
	unsigned reset_resume:1;
#endif
	struct wusb_dev *wusb_dev;
	int slot_id;
};
#define	to_usb_device(d) container_of(d, struct usb_device, dev)

static inline struct usb_device *interface_to_usbdev(struct usb_interface *intf)
{
	return to_usb_device(intf->dev.parent);
}

extern struct usb_device *usb_get_dev(struct usb_device *dev);
extern void usb_put_dev(struct usb_device *dev);

/* USB device locking */
#define usb_lock_device(udev)		device_lock(&(udev)->dev)
#define usb_unlock_device(udev)		device_unlock(&(udev)->dev)
#define usb_trylock_device(udev)	device_trylock(&(udev)->dev)
extern int usb_lock_device_for_reset(struct usb_device *udev,
				     const struct usb_interface *iface);

/* USB port reset for device reinitialization */
extern int usb_reset_device(struct usb_device *dev);
extern void usb_queue_reset_device(struct usb_interface *dev);


/* USB autosuspend and autoresume */
#ifdef CONFIG_USB_SUSPEND
extern void usb_enable_autosuspend(struct usb_device *udev);
extern void usb_disable_autosuspend(struct usb_device *udev);

extern int usb_autopm_get_interface(struct usb_interface *intf);
extern void usb_autopm_put_interface(struct usb_interface *intf);
extern int usb_autopm_get_interface_async(struct usb_interface *intf);
extern void usb_autopm_put_interface_async(struct usb_interface *intf);
extern void usb_autopm_get_interface_no_resume(struct usb_interface *intf);
extern void usb_autopm_put_interface_no_suspend(struct usb_interface *intf);

static inline void usb_mark_last_busy(struct usb_device *udev)
{
	pm_runtime_mark_last_busy(&udev->dev);
}

#else

static inline int usb_enable_autosuspend(struct usb_device *udev)
{ return 0; }
static inline int usb_disable_autosuspend(struct usb_device *udev)
{ return 0; }

static inline int usb_autopm_get_interface(struct usb_interface *intf)
{ return 0; }
static inline int usb_autopm_get_interface_async(struct usb_interface *intf)
{ return 0; }

static inline void usb_autopm_put_interface(struct usb_interface *intf)
{ }
static inline void usb_autopm_put_interface_async(struct usb_interface *intf)
{ }
static inline void usb_autopm_get_interface_no_resume(
		struct usb_interface *intf)
{ }
static inline void usb_autopm_put_interface_no_suspend(
		struct usb_interface *intf)
{ }
static inline void usb_mark_last_busy(struct usb_device *udev)
{ }
#endif

/*-------------------------------------------------------------------------*/

/* for drivers using iso endpoints */
extern int usb_get_current_frame_number(struct usb_device *usb_dev);

/* Sets up a group of bulk endpoints to support multiple stream IDs. */
extern int usb_alloc_streams(struct usb_interface *interface,
		struct usb_host_endpoint **eps, unsigned int num_eps,
		unsigned int num_streams, gfp_t mem_flags);

/* Reverts a group of bulk endpoints back to not using stream IDs. */
extern void usb_free_streams(struct usb_interface *interface,
		struct usb_host_endpoint **eps, unsigned int num_eps,
		gfp_t mem_flags);

/* used these for multi-interface device registration */
extern int usb_driver_claim_interface(struct usb_driver *driver,
			struct usb_interface *iface, void *priv);

/**
 * usb_interface_claimed - returns true iff an interface is claimed
 * @iface: the interface being checked
 *
 * Returns true (nonzero) iff the interface is claimed, else false (zero).
 * Callers must own the driver model's usb bus readlock.  So driver
 * probe() entries don't need extra locking, but other call contexts
 * may need to explicitly claim that lock.
 *
 */
static inline int usb_interface_claimed(struct usb_interface *iface)
{
	return (iface->dev.driver != NULL);
}

extern void usb_driver_release_interface(struct usb_driver *driver,
			struct usb_interface *iface);
const struct usb_device_id *usb_match_id(struct usb_interface *interface,
					 const struct usb_device_id *id);
extern int usb_match_one_id(struct usb_interface *interface,
			    const struct usb_device_id *id);

extern struct usb_interface *usb_find_interface(struct usb_driver *drv,
		int minor);
extern struct usb_interface *usb_ifnum_to_if(const struct usb_device *dev,
		unsigned ifnum);
extern struct usb_host_interface *usb_altnum_to_altsetting(
		const struct usb_interface *intf, unsigned int altnum);
extern struct usb_host_interface *usb_find_alt_setting(
		struct usb_host_config *config,
		unsigned int iface_num,
		unsigned int alt_num);


/**
 * usb_make_path - returns stable device path in the usb tree
 * @dev: the device whose path is being constructed
 * @buf: where to put the string
 * @size: how big is "buf"?
 *
 * Returns length of the string (> 0) or negative if size was too small.
 *
 * This identifier is intended to be "stable", reflecting physical paths in
 * hardware such as physical bus addresses for host controllers or ports on
 * USB hubs.  That makes it stay the same until systems are physically
 * reconfigured, by re-cabling a tree of USB devices or by moving USB host
 * controllers.  Adding and removing devices, including virtual root hubs
 * in host controller driver modules, does not change these path identifiers;
 * neither does rebooting or re-enumerating.  These are more useful identifiers
 * than changeable ("unstable") ones like bus numbers or device addresses.
 *
 * With a partial exception for devices connected to USB 2.0 root hubs, these
 * identifiers are also predictable.  So long as the device tree isn't changed,
 * plugging any USB device into a given hub port always gives it the same path.
 * Because of the use of "companion" controllers, devices connected to ports on
 * USB 2.0 root hubs (EHCI host controllers) will get one path ID if they are
 * high speed, and a different one if they are full or low speed.
 */
static inline int usb_make_path(struct usb_device *dev, char *buf, size_t size)
{
	int actual;
	actual = snprintf(buf, size, "usb-%s-%s", dev->bus->bus_name,
			  dev->devpath);
	return (actual >= (int)size) ? -1 : actual;
}

/*-------------------------------------------------------------------------*/

#define USB_DEVICE_ID_MATCH_DEVICE \
		(USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_PRODUCT)
#define USB_DEVICE_ID_MATCH_DEV_RANGE \
		(USB_DEVICE_ID_MATCH_DEV_LO | USB_DEVICE_ID_MATCH_DEV_HI)
#define USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION \
		(USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_DEV_RANGE)
#define USB_DEVICE_ID_MATCH_DEV_INFO \
		(USB_DEVICE_ID_MATCH_DEV_CLASS | \
		USB_DEVICE_ID_MATCH_DEV_SUBCLASS | \
		USB_DEVICE_ID_MATCH_DEV_PROTOCOL)
#define USB_DEVICE_ID_MATCH_INT_INFO \
		(USB_DEVICE_ID_MATCH_INT_CLASS | \
		USB_DEVICE_ID_MATCH_INT_SUBCLASS | \
		USB_DEVICE_ID_MATCH_INT_PROTOCOL)

/**
 * USB_DEVICE - macro used to describe a specific usb device
 * @vend: the 16 bit USB Vendor ID
 * @prod: the 16 bit USB Product ID
 *
 * This macro is used to create a struct usb_device_id that matches a
 * specific device.
 */
#define USB_DEVICE(vend, prod) \
	.match_flags = USB_DEVICE_ID_MATCH_DEVICE, \
	.idVendor = (vend), \
	.idProduct = (prod)
/**
 * USB_DEVICE_VER - describe a specific usb device with a version range
 * @vend: the 16 bit USB Vendor ID
 * @prod: the 16 bit USB Product ID
 * @lo: the bcdDevice_lo value
 * @hi: the bcdDevice_hi value
 *
 * This macro is used to create a struct usb_device_id that matches a
 * specific device, with a version range.
 */
#define USB_DEVICE_VER(vend, prod, lo, hi) \
	.match_flags = USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION, \
	.idVendor = (vend), \
	.idProduct = (prod), \
	.bcdDevice_lo = (lo), \
	.bcdDevice_hi = (hi)

/**
 * USB_DEVICE_INTERFACE_PROTOCOL - describe a usb device with a specific interface protocol
 * @vend: the 16 bit USB Vendor ID
 * @prod: the 16 bit USB Product ID
 * @pr: bInterfaceProtocol value
 *
 * This macro is used to create a struct usb_device_id that matches a
 * specific interface protocol of devices.
 */
#define USB_DEVICE_INTERFACE_PROTOCOL(vend, prod, pr) \
	.match_flags = USB_DEVICE_ID_MATCH_DEVICE | \
		       USB_DEVICE_ID_MATCH_INT_PROTOCOL, \
	.idVendor = (vend), \
	.idProduct = (prod), \
	.bInterfaceProtocol = (pr)

/**
 * USB_DEVICE_INFO - macro used to describe a class of usb devices
 * @cl: bDeviceClass value
 * @sc: bDeviceSubClass value
 * @pr: bDeviceProtocol value
 *
 * This macro is used to create a struct usb_device_id that matches a
 * specific class of devices.
 */
#define USB_DEVICE_INFO(cl, sc, pr) \
	.match_flags = USB_DEVICE_ID_MATCH_DEV_INFO, \
	.bDeviceClass = (cl), \
	.bDeviceSubClass = (sc), \
	.bDeviceProtocol = (pr)

/**
 * USB_INTERFACE_INFO - macro used to describe a class of usb interfaces
 * @cl: bInterfaceClass value
 * @sc: bInterfaceSubClass value
 * @pr: bInterfaceProtocol value
 *
 * This macro is used to create a struct usb_device_id that matches a
 * specific class of interfaces.
 */
#define USB_INTERFACE_INFO(cl, sc, pr) \
	.match_flags = USB_DEVICE_ID_MATCH_INT_INFO, \
	.bInterfaceClass = (cl), \
	.bInterfaceSubClass = (sc), \
	.bInterfaceProtocol = (pr)

/**
 * USB_DEVICE_AND_INTERFACE_INFO - describe a specific usb device with a class of usb interfaces
 * @vend: the 16 bit USB Vendor ID
 * @prod: the 16 bit USB Product ID
 * @cl: bInterfaceClass value
 * @sc: bInterfaceSubClass value
 * @pr: bInterfaceProtocol value
 *
 * This macro is used to create a struct usb_device_id that matches a
 * specific device with a specific class of interfaces.
 *
 * This is especially useful when explicitly matching devices that have
 * vendor specific bDeviceClass values, but standards-compliant interfaces.
 */
#define USB_DEVICE_AND_INTERFACE_INFO(vend, prod, cl, sc, pr) \
	.match_flags = USB_DEVICE_ID_MATCH_INT_INFO \
		| USB_DEVICE_ID_MATCH_DEVICE, \
	.idVendor = (vend), \
	.idProduct = (prod), \
	.bInterfaceClass = (cl), \
	.bInterfaceSubClass = (sc), \
	.bInterfaceProtocol = (pr)

/* ----------------------------------------------------------------------- */

/* Stuff for dynamic usb ids */
struct usb_dynids {
	spinlock_t lock;
	struct list_head list;
};

struct usb_dynid {
	struct list_head node;
	struct usb_device_id id;
};

extern ssize_t usb_store_new_id(struct usb_dynids *dynids,
				struct device_driver *driver,
				const char *buf, size_t count);

/**
 * struct usbdrv_wrap - wrapper for driver-model structure
 * @driver: The driver-model core driver structure.
 * @for_devices: Non-zero for device drivers, 0 for interface drivers.
 */
struct usbdrv_wrap {
	struct device_driver driver;
	int for_devices;
};

/**
 * struct usb_driver - identifies USB interface driver to usbcore
 * @name: The driver name should be unique among USB drivers,
 *	and should normally be the same as the module name.
 * @probe: Called to see if the driver is willing to manage a particular
 *	interface on a device.  If it is, probe returns zero and uses
 *	usb_set_intfdata() to associate driver-specific data with the
 *	interface.  It may also use usb_set_interface() to specify the
 *	appropriate altsetting.  If unwilling to manage the interface,
 *	return -ENODEV, if genuine IO errors occurred, an appropriate
 *	negative errno value.
 * @disconnect: Called when the interface is no longer accessible, usually
 *	because its device has been (or is being) disconnected or the
 *	driver module is being unloaded.
 * @unlocked_ioctl: Used for drivers that want to talk to userspace through
 *	the "usbfs" filesystem.  This lets devices provide ways to
 *	expose information to user space regardless of where they
 *	do (or don't) show up otherwise in the filesystem.
 * @suspend: Called when the device is going to be suspended by the system.
 * @resume: Called when the device is being resumed by the system.
 * @reset_resume: Called when the suspended device has been reset instead
 *	of being resumed.
 * @pre_reset: Called by usb_reset_device() when the device is about to be
 *	reset.  This routine must not return until the driver has no active
 *	URBs for the device, and no more URBs may be submitted until the
 *	post_reset method is called.
 * @post_reset: Called by usb_reset_device() after the device
 *	has been reset
 * @id_table: USB drivers use ID table to support hotplugging.
 *	Export this with MODULE_DEVICE_TABLE(usb,...).  This must be set
 *	or your driver's probe function will never get called.
 * @dynids: used internally to hold the list of dynamically added device
 *	ids for this driver.
 * @drvwrap: Driver-model core structure wrapper.
 * @no_dynamic_id: if set to 1, the USB core will not allow dynamic ids to be
 *	added to this driver by preventing the sysfs file from being created.
 * @supports_autosuspend: if set to 0, the USB core will not allow autosuspend
 *	for interfaces bound to this driver.
 * @soft_unbind: if set to 1, the USB core will not kill URBs and disable
 *	endpoints before calling the driver's disconnect method.
 *
 * USB interface drivers must provide a name, probe() and disconnect()
 * methods, and an id_table.  Other driver fields are optional.
 *
 * The id_table is used in hotplugging.  It holds a set of descriptors,
 * and specialized data may be associated with each entry.  That table
 * is used by both user and kernel mode hotplugging support.
 *
 * The probe() and disconnect() methods are called in a context where
 * they can sleep, but they should avoid abusing the privilege.  Most
 * work to connect to a device should be done when the device is opened,
 * and undone at the last close.  The disconnect code needs to address
 * concurrency issues with respect to open() and close() methods, as
 * well as forcing all pending I/O requests to complete (by unlinking
 * them as necessary, and blocking until the unlinks complete).
 */
struct usb_driver {
	const char *name;

	int (*probe) (struct usb_interface *intf,
		      const struct usb_device_id *id);

	void (*disconnect) (struct usb_interface *intf);

	int (*unlocked_ioctl) (struct usb_interface *intf, unsigned int code,
			void *buf);

	int (*suspend) (struct usb_interface *intf, pm_message_t message);
	int (*resume) (struct usb_interface *intf);
	int (*reset_resume)(struct usb_interface *intf);

	int (*pre_reset)(struct usb_interface *intf);
	int (*post_reset)(struct usb_interface *intf);

	const struct usb_device_id *id_table;

	struct usb_dynids dynids;
	struct usbdrv_wrap drvwrap;
	unsigned int no_dynamic_id:1;
	unsigned int supports_autosuspend:1;
	unsigned int soft_unbind:1;
};
#define	to_usb_driver(d) container_of(d, struct usb_driver, drvwrap.driver)

/**
 * struct usb_device_driver - identifies USB device driver to usbcore
 * @name: The driver name should be unique among USB drivers,
 *	and should normally be the same as the module name.
 * @probe: Called to see if the driver is willing to manage a particular
 *	device.  If it is, probe returns zero and uses dev_set_drvdata()
 *	to associate driver-specific data with the device.  If unwilling
 *	to manage the device, return a negative errno value.
 * @disconnect: Called when the device is no longer accessible, usually
 *	because it has been (or is being) disconnected or the driver's
 *	module is being unloaded.
 * @suspend: Called when the device is going to be suspended by the system.
 * @resume: Called when the device is being resumed by the system.
 * @drvwrap: Driver-model core structure wrapper.
 * @supports_autosuspend: if set to 0, the USB core will not allow autosuspend
 *	for devices bound to this driver.
 *
 * USB drivers must provide all the fields listed above except drvwrap.
 */
struct usb_device_driver {
	const char *name;

	int (*probe) (struct usb_device *udev);
	void (*disconnect) (struct usb_device *udev);

	int (*suspend) (struct usb_device *udev, pm_message_t message);
	int (*resume) (struct usb_device *udev, pm_message_t message);
	struct usbdrv_wrap drvwrap;
	unsigned int supports_autosuspend:1;
};
#define	to_usb_device_driver(d) container_of(d, struct usb_device_driver, \
		drvwrap.driver)

extern struct bus_type usb_bus_type;

/**
 * struct usb_class_driver - identifies a USB driver that wants to use the USB major number
 * @name: the usb class device name for this driver.  Will show up in sysfs.
 * @devnode: Callback to provide a naming hint for a possible
 *	device node to create.
 * @fops: pointer to the struct file_operations of this driver.
 * @minor_base: the start of the minor range for this driver.
 *
 * This structure is used for the usb_register_dev() and
 * usb_unregister_dev() functions, to consolidate a number of the
 * parameters used for them.
 */
struct usb_class_driver {
	char *name;
	char *(*devnode)(struct device *dev, mode_t *mode);
	const struct file_operations *fops;
	int minor_base;
};

/*
 * use these in module_init()/module_exit()
 * and don't forget MODULE_DEVICE_TABLE(usb, ...)
 */
extern int usb_register_driver(struct usb_driver *, struct module *,
			       const char *);

/* use a define to avoid include chaining to get THIS_MODULE & friends */
#define usb_register(driver) \
	usb_register_driver(driver, THIS_MODULE, KBUILD_MODNAME)

extern void usb_deregister(struct usb_driver *);

extern int usb_register_device_driver(struct usb_device_driver *,
			struct module *);
extern void usb_deregister_device_driver(struct usb_device_driver *);

extern int usb_register_dev(struct usb_interface *intf,
			    struct usb_class_driver *class_driver);
extern void usb_deregister_dev(struct usb_interface *intf,
			       struct usb_class_driver *class_driver);

extern int usb_disabled(void);

/* ----------------------------------------------------------------------- */

/*
 * URB support, for asynchronous request completions
 */

/*
 * urb->transfer_flags:
 *
 * Note: URB_DIR_IN/OUT is automatically set in usb_submit_urb().
 */
#define URB_SHORT_NOT_OK	0x0001	/* report short reads as errors */
#define URB_ISO_ASAP		0x0002	/* iso-only, urb->start_frame
					 * ignored */
#define URB_NO_TRANSFER_DMA_MAP	0x0004	/* urb->transfer_dma valid on submit */
#define URB_NO_FSBR		0x0020	/* UHCI-specific */
#define URB_ZERO_PACKET		0x0040	/* Finish bulk OUT with short packet */
#define URB_NO_INTERRUPT	0x0080	/* HINT: no non-error interrupt
					 * needed */
#define URB_FREE_BUFFER		0x0100	/* Free transfer buffer with the URB */

/* The following flags are used internally by usbcore and HCDs */
#define URB_DIR_IN		0x0200	/* Transfer from device to host */
#define URB_DIR_OUT		0
#define URB_DIR_MASK		URB_DIR_IN

#define URB_DMA_MAP_SINGLE	0x00010000	/* Non-scatter-gather mapping */
#define URB_DMA_MAP_PAGE	0x00020000	/* HCD-unsupported S-G */
#define URB_DMA_MAP_SG		0x00040000	/* HCD-supported S-G */
#define URB_MAP_LOCAL		0x00080000	/* HCD-local-memory mapping */
#define URB_SETUP_MAP_SINGLE	0x00100000	/* Setup packet DMA mapped */
#define URB_SETUP_MAP_LOCAL	0x00200000	/* HCD-local setup packet */
#define URB_DMA_SG_COMBINED	0x00400000	/* S-G entries were combined */
#define URB_ALIGNED_TEMP_BUFFER	0x00800000	/* Temp buffer was alloc'd */

struct usb_iso_packet_descriptor {
	unsigned int offset;
	unsigned int length;		/* expected length */
	unsigned int actual_length;
	int status;
};

struct urb;

struct usb_anchor {
	struct list_head urb_list;
	wait_queue_head_t wait;
	spinlock_t lock;
	unsigned int poisoned:1;
};

static inline void init_usb_anchor(struct usb_anchor *anchor)
{
	INIT_LIST_HEAD(&anchor->urb_list);
	init_waitqueue_head(&anchor->wait);
	spin_lock_init(&anchor->lock);
}

typedef void (*usb_complete_t)(struct urb *);

/**
 * struct urb - USB Request Block
 * @urb_list: For use by current owner of the URB.
 * @anchor_list: membership in the list of an anchor
 * @anchor: to anchor URBs to a common mooring
 * @ep: Points to the endpoint's data structure.  Will eventually
 *	replace @pipe.
 * @pipe: Holds endpoint number, direction, type, and more.
 *	Create these values with the eight macros available;
 *	usb_{snd,rcv}TYPEpipe(dev,endpoint), where the TYPE is "ctrl"
 *	(control), "bulk", "int" (interrupt), or "iso" (isochronous).
 *	For example usb_sndbulkpipe() or usb_rcvintpipe().  Endpoint
 *	numbers range from zero to fifteen.  Note that "in" endpoint two
 *	is a different endpoint (and pipe) from "out" endpoint two.
 *	The current configuration controls the existence, type, and
 *	maximum packet size of any given endpoint.
 * @stream_id: the endpoint's stream ID for bulk streams
 * @dev: Identifies the USB device to perform the request.
 * @status: This is read in non-iso completion functions to get the
 *	status of the particular request.  ISO requests only use it
 *	to tell whether the URB was unlinked; detailed status for
 *	each frame is in the fields of the iso_frame-desc.
 * @transfer_flags: A variety of flags may be used to affect how URB
 *	submission, unlinking, or operation are handled.  Different
 *	kinds of URB can use different flags.
 * @transfer_buffer:  This identifies the buffer to (or from) which the I/O
 *	request will be performed unless URB_NO_TRANSFER_DMA_MAP is set
 *	(however, do not leave garbage in transfer_buffer even then).
 *	This buffer must be suitable for DMA; allocate it with
 *	kmalloc() or equivalent.  For transfers to "in" endpoints, contents
 *	of this buffer will be modified.  This buffer is used for the data
 *	stage of control transfers.
 * @transfer_dma: When transfer_flags includes URB_NO_TRANSFER_DMA_MAP,
 *	the device driver is saying that it provided this DMA address,
 *	which the host controller driver should use in preference to the
 *	transfer_buffer.
 * @sg: scatter gather buffer list
 * @num_sgs: number of entries in the sg list
 * @transfer_buffer_length: How big is transfer_buffer.  The transfer may
 *	be broken up into chunks according to the current maximum packet
 *	size for the endpoint, which is a function of the configuration
 *	and is encoded in the pipe.  When the length is zero, neither
 *	transfer_buffer nor transfer_dma is used.
 * @actual_length: This is read in non-iso completion functions, and
 *	it tells how many bytes (out of transfer_buffer_length) were
 *	transferred.  It will normally be the same as requested, unless
 *	either an error was reported or a short read was performed.
 *	The URB_SHORT_NOT_OK transfer flag may be used to make such
 *	short reads be reported as errors.
 * @setup_packet: Only used for control transfers, this points to eight bytes
 *	of setup data.  Control transfers always start by sending this data
 *	to the device.  Then transfer_buffer is read or written, if needed.
 * @setup_dma: DMA pointer for the setup packet.  The caller must not use
 *	this field; setup_packet must point to a valid buffer.
 * @start_frame: Returns the initial frame for isochronous transfers.
 * @number_of_packets: Lists the number of ISO transfer buffers.
 * @interval: Specifies the polling interval for interrupt or isochronous
 *	transfers.  The units are frames (milliseconds) for full and low
 *	speed devices, and microframes (1/8 millisecond) for highspeed
 *	and SuperSpeed devices.
 * @error_count: Returns the number of ISO transfers that reported errors.
 * @context: For use in completion functions.  This normally points to
 *	request-specific driver context.
 * @complete: Completion handler. This URB is passed as the parameter to the
 *	completion function.  The completion function may then do what
 *	it likes with the URB, including resubmitting or freeing it.
 * @iso_frame_desc: Used to provide arrays of ISO transfer buffers and to
 *	collect the transfer status for each buffer.
 *
 * This structure identifies USB transfer requests.  URBs must be allocated by
 * calling usb_alloc_urb() and freed with a call to usb_free_urb().
 * Initialization may be done using various usb_fill_*_urb() functions.  URBs
 * are submitted using usb_submit_urb(), and pending requests may be canceled
 * using usb_unlink_urb() or usb_kill_urb().
 *
 * Data Transfer Buffers:
 *
 * Normally drivers provide I/O buffers allocated with kmalloc() or otherwise
 * taken from the general page pool.  That is provided by transfer_buffer
 * (control requests also use setup_packet), and host controller drivers
 * perform a dma mapping (and unmapping) for each buffer transferred.  Those
 * mapping operations can be expensive on some platforms (perhaps using a dma
 * bounce buffer or talking to an IOMMU),
 * although they're cheap on commodity x86 and ppc hardware.
 *
 * Alternatively, drivers may pass the URB_NO_TRANSFER_DMA_MAP transfer flag,
 * which tells the host controller driver that no such mapping is needed for
 * the transfer_buffer since
 * the device driver is DMA-aware.  For example, a device driver might
 * allocate a DMA buffer with usb_alloc_coherent() or call usb_buffer_map().
 * When this transfer flag is provided, host controller drivers will
 * attempt to use the dma address found in the transfer_dma
 * field rather than determining a dma address themselves.
 *
 * Note that transfer_buffer must still be set if the controller
 * does not support DMA (as indicated by bus.uses_dma) and when talking
 * to root hub. If you have to trasfer between highmem zone and the device
 * on such controller, create a bounce buffer or bail out with an error.
 * If transfer_buffer cannot be set (is in highmem) and the controller is DMA
 * capable, assign NULL to it, so that usbmon knows not to use the value.
 * The setup_packet must always be set, so it cannot be located in highmem.
 *
 * Initialization:
 *
 * All URBs submitted must initialize the dev, pipe, transfer_flags (may be
 * zero), and complete fields.  All URBs must also initialize
 * transfer_buffer and transfer_buffer_length.  They may provide the
 * URB_SHORT_NOT_OK transfer flag, indicating that short reads are
 * to be treated as errors; that flag is invalid for write requests.
 *
 * Bulk URBs may
 * use the URB_ZERO_PACKET transfer flag, indicating that bulk OUT transfers
 * should always terminate with a short packet, even if it means adding an
 * extra zero length packet.
 *
 * Control URBs must provide a valid pointer in the setup_packet field.
 * Unlike the transfer_buffer, the setup_packet may not be mapped for DMA
 * beforehand.
 *
 * Interrupt URBs must provide an interval, saying how often (in milliseconds
 * or, for highspeed devices, 125 microsecond units)
 * to poll for transfers.  After the URB has been submitted, the interval
 * field reflects how the transfer was actually scheduled.
 * The polling interval may be more frequent than requested.
 * For example, some controllers have a maximum interval of 32 milliseconds,
 * while others support intervals of up to 1024 milliseconds.
 * Isochronous URBs also have transfer intervals.  (Note that for isochronous
 * endpoints, as well as high speed interrupt endpoints, the encoding of
 * the transfer interval in the endpoint descriptor is logarithmic.
 * Device drivers must convert that value to linear units themselves.)
 *
 * Isochronous URBs normally use the URB_ISO_ASAP transfer flag, telling
 * the host controller to schedule the transfer as soon as bandwidth
 * utilization allows, and then set start_frame to reflect the actual frame
 * selected during submission.  Otherwise drivers must specify the start_frame
 * and handle the case where the transfer can't begin then.  However, drivers
 * won't know how bandwidth is currently allocated, and while they can
 * find the current frame using usb_get_current_frame_number () they can't
 * know the range for that frame number.  (Ranges for frame counter values
 * are HC-specific, and can go from 256 to 65536 frames from "now".)
 *
 * Isochronous URBs have a different data transfer model, in part because
 * the quality of service is only "best effort".  Callers provide specially
 * allocated URBs, with number_of_packets worth of iso_frame_desc structures
 * at the end.  Each such packet is an individual ISO transfer.  Isochronous
 * URBs are normally queued, submitted by drivers to arrange that
 * transfers are at least double buffered, and then explicitly resubmitted
 * in completion handlers, so
 * that data (such as audio or video) streams at as constant a rate as the
 * host controller scheduler can support.
 *
 * Completion Callbacks:
 *
 * The completion callback is made in_interrupt(), and one of the first
 * things that a completion handler should do is check the status field.
 * The status field is provided for all URBs.  It is used to report
 * unlinked URBs, and status for all non-ISO transfers.  It should not
 * be examined before the URB is returned to the completion handler.
 *
 * The context field is normally used to link URBs back to the relevant
 * driver or request state.
 *
 * When the completion callback is invoked for non-isochronous URBs, the
 * actual_length field tells how many bytes were transferred.  This field
 * is updated even when the URB terminated with an error or was unlinked.
 *
 * ISO transfer status is reported in the status and actual_length fields
 * of the iso_frame_desc array, and the number of errors is reported in
 * error_count.  Completion callbacks for ISO transfers will normally
 * (re)submit URBs to ensure a constant transfer rate.
 *
 * Note that even fields marked "public" should not be touched by the driver
 * when the urb is owned by the hcd, that is, since the call to
 * usb_submit_urb() till the entry into the completion routine.
 */
struct urb {
	/* private: usb core and host controller only fields in the urb */
	struct kref kref;		/* reference count of the URB */
	void *hcpriv;			/* private data for host controller */
	atomic_t use_count;		/* concurrent submissions counter */
	atomic_t reject;		/* submissions will fail */
	int unlinked;			/* unlink error code */

	/* public: documented fields in the urb that can be used by drivers */
	struct list_head urb_list;	/* list head for use by the urb's
					 * current owner */
	struct list_head anchor_list;	/* the URB may be anchored */
	struct usb_anchor *anchor;
	struct usb_device *dev;		/* (in) pointer to associated device */
	struct usb_host_endpoint *ep;	/* (internal) pointer to endpoint */
	unsigned int pipe;		/* (in) pipe information */
	unsigned int stream_id;		/* (in) stream ID */
	int status;			/* (return) non-ISO status */
	unsigned int transfer_flags;	/* (in) URB_SHORT_NOT_OK | ...*/
	void *transfer_buffer;		/* (in) associated data buffer */
	dma_addr_t transfer_dma;	/* (in) dma addr for transfer_buffer */
	struct scatterlist *sg;		/* (in) scatter gather buffer list */
	int num_sgs;			/* (in) number of entries in the sg list */
	u32 transfer_buffer_length;	/* (in) data buffer length */
	u32 actual_length;		/* (return) actual transfer length */
	unsigned char *setup_packet;	/* (in) setup packet (control only) */
	dma_addr_t setup_dma;		/* (in) dma addr for setup_packet */
	int start_frame;		/* (modify) start frame (ISO) */
	int number_of_packets;		/* (in) number of ISO packets */
	int interval;			/* (modify) transfer interval
					 * (INT/ISO) */
	int error_count;		/* (return) number of ISO errors */
	void *context;			/* (in) context for completion */
	usb_complete_t complete;	/* (in) completion routine */
	struct usb_iso_packet_descriptor iso_frame_desc[0];
					/* (in) ISO ONLY */
};

/* ----------------------------------------------------------------------- */

/**
 * usb_fill_control_urb - initializes a control urb
 * @urb: pointer to the urb to initialize.
 * @dev: pointer to the struct usb_device for this urb.
 * @pipe: the endpoint pipe
 * @setup_packet: pointer to the setup_packet buffer
 * @transfer_buffer: pointer to the transfer buffer
 * @buffer_length: length of the transfer buffer
 * @complete_fn: pointer to the usb_complete_t function
 * @context: what to set the urb context to.
 *
 * Initializes a control urb with the proper information needed to submit
 * it to a device.
 */
static inline void usb_fill_control_urb(struct urb *urb,
					struct usb_device *dev,
					unsigned int pipe,
					unsigned char *setup_packet,
					void *transfer_buffer,
					int buffer_length,
					usb_complete_t complete_fn,
					void *context)
{
	urb->dev = dev;
	urb->pipe = pipe;
	urb->setup_packet = setup_packet;
	urb->transfer_buffer = transfer_buffer;
	urb->transfer_buffer_length = buffer_length;
	urb->complete = complete_fn;
	urb->context = context;
}

/**
 * usb_fill_bulk_urb - macro to help initialize a bulk urb
 * @urb: pointer to the urb to initialize.
 * @dev: pointer to the struct usb_device for this urb.
 * @pipe: the endpoint pipe
 * @transfer_buffer: pointer to the transfer buffer
 * @buffer_length: length of the transfer buffer
 * @complete_fn: pointer to the usb_complete_t function
 * @context: what to set the urb context to.
 *
 * Initializes a bulk urb with the proper information needed to submit it
 * to a device.
 */
static inline void usb_fill_bulk_urb(struct urb *urb,
				     struct usb_device *dev,
				     unsigned int pipe,
				     void *transfer_buffer,
				     int buffer_length,
				     usb_complete_t complete_fn,
				     void *context)
{
	urb->dev = dev;
	urb->pipe = pipe;
	urb->transfer_buffer = transfer_buffer;
	urb->transfer_buffer_length = buffer_length;
	urb->complete = complete_fn;
	urb->context = context;
}

/**
 * usb_fill_int_urb - macro to help initialize a interrupt urb
 * @urb: pointer to the urb to initialize.
 * @dev: pointer to the struct usb_device for this urb.
 * @pipe: the endpoint pipe
 * @transfer_buffer: pointer to the transfer buffer
 * @buffer_length: length of the transfer buffer
 * @complete_fn: pointer to the usb_complete_t function
 * @context: what to set the urb context to.
 * @interval: what to set the urb interval to, encoded like
 *	the endpoint descriptor's bInterval value.
 *
 * Initializes a interrupt urb with the proper information needed to submit
 * it to a device.
 *
 * Note that High Speed and SuperSpeed interrupt endpoints use a logarithmic
 * encoding of the endpoint interval, and express polling intervals in
 * microframes (eight per millisecond) rather than in frames (one per
 * millisecond).
 *
 * Wireless USB also uses the logarithmic encoding, but specifies it in units of
 * 128us instead of 125us.  For Wireless USB devices, the interval is passed
 * through to the host controller, rather than being translated into microframe
 * units.
 */
static inline void usb_fill_int_urb(struct urb *urb,
				    struct usb_device *dev,
				    unsigned int pipe,
				    void *transfer_buffer,
				    int buffer_length,
				    usb_complete_t complete_fn,
				    void *context,
				    int interval)
{
	urb->dev = dev;
	urb->pipe = pipe;
	urb->transfer_buffer = transfer_buffer;
	urb->transfer_buffer_length = buffer_length;
	urb->complete = complete_fn;
	urb->context = context;
	if (dev->speed == USB_SPEED_HIGH || dev->speed == USB_SPEED_SUPER)
		urb->interval = 1 << (interval - 1);
	else
		urb->interval = interval;
	urb->start_frame = -1;
}

extern void usb_init_urb(struct urb *urb);
extern struct urb *usb_alloc_urb(int iso_packets, gfp_t mem_flags);
extern void usb_free_urb(struct urb *urb);
#define usb_put_urb usb_free_urb
extern struct urb *usb_get_urb(struct urb *urb);
extern int usb_submit_urb(struct urb *urb, gfp_t mem_flags);
extern int usb_unlink_urb(struct urb *urb);
extern void usb_kill_urb(struct urb *urb);
extern void usb_poison_urb(struct urb *urb);
extern void usb_unpoison_urb(struct urb *urb);
extern void usb_kill_anchored_urbs(struct usb_anchor *anchor);
extern void usb_poison_anchored_urbs(struct usb_anchor *anchor);
extern void usb_unpoison_anchored_urbs(struct usb_anchor *anchor);
extern void usb_unlink_anchored_urbs(struct usb_anchor *anchor);
extern void usb_anchor_urb(struct urb *urb, struct usb_anchor *anchor);
extern void usb_unanchor_urb(struct urb *urb);
extern int usb_wait_anchor_empty_timeout(struct usb_anchor *anchor,
					 unsigned int timeout);
extern struct urb *usb_get_from_anchor(struct usb_anchor *anchor);
extern void usb_scuttle_anchored_urbs(struct usb_anchor *anchor);
extern int usb_anchor_empty(struct usb_anchor *anchor);

/**
 * usb_urb_dir_in - check if an URB describes an IN transfer
 * @urb: URB to be checked
 *
 * Returns 1 if @urb describes an IN transfer (device-to-host),
 * otherwise 0.
 */
static inline int usb_urb_dir_in(struct urb *urb)
{
	return (urb->transfer_flags & URB_DIR_MASK) == URB_DIR_IN;
}

/**
 * usb_urb_dir_out - check if an URB describes an OUT transfer
 * @urb: URB to be checked
 *
 * Returns 1 if @urb describes an OUT transfer (host-to-device),
 * otherwise 0.
 */
static inline int usb_urb_dir_out(struct urb *urb)
{
	return (urb->transfer_flags & URB_DIR_MASK) == URB_DIR_OUT;
}

void *usb_alloc_coherent(struct usb_device *dev, size_t size,
	gfp_t mem_flags, dma_addr_t *dma);
void usb_free_coherent(struct usb_device *dev, size_t size,
	void *addr, dma_addr_t dma);

#if 0
struct urb *usb_buffer_map(struct urb *urb);
void usb_buffer_dmasync(struct urb *urb);
void usb_buffer_unmap(struct urb *urb);
#endif

struct scatterlist;
int usb_buffer_map_sg(const struct usb_device *dev, int is_in,
		      struct scatterlist *sg, int nents);
#if 0
void usb_buffer_dmasync_sg(const struct usb_device *dev, int is_in,
			   struct scatterlist *sg, int n_hw_ents);
#endif
void usb_buffer_unmap_sg(const struct usb_device *dev, int is_in,
			 struct scatterlist *sg, int n_hw_ents);

/*-------------------------------------------------------------------*
 *                         SYNCHRONOUS CALL SUPPORT                  *
 *-------------------------------------------------------------------*/

extern int usb_control_msg(struct usb_device *dev, unsigned int pipe,
	__u8 request, __u8 requesttype, __u16 value, __u16 index,
	void *data, __u16 size, int timeout);
extern int usb_interrupt_msg(struct usb_device *usb_dev, unsigned int pipe,
	void *data, int len, int *actual_length, int timeout);
extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe,
	void *data, int len, int *actual_length,
	int timeout);

/* wrappers around usb_control_msg() for the most common standard requests */
extern int usb_get_descriptor(struct usb_device *dev, unsigned char desctype,
	unsigned char descindex, void *buf, int size);
extern int usb_get_status(struct usb_device *dev,
	int type, int target, void *data);
extern int usb_string(struct usb_device *dev, int index,
	char *buf, size_t size);

/* wrappers that also update important state inside usbcore */
extern int usb_clear_halt(struct usb_device *dev, int pipe);
extern int usb_reset_configuration(struct usb_device *dev);
extern int usb_set_interface(struct usb_device *dev, int ifnum, int alternate);
extern void usb_reset_endpoint(struct usb_device *dev, unsigned int epaddr);

/* this request isn't really synchronous, but it belongs with the others */
extern int usb_driver_set_configuration(struct usb_device *udev, int config);

/*
 * timeouts, in milliseconds, used for sending/receiving control messages
 * they typically complete within a few frames (msec) after they're issued
 * USB identifies 5 second timeouts, maybe more in a few cases, and a few
 * slow devices (like some MGE Ellipse UPSes) actually push that limit.
 */
#define USB_CTRL_GET_TIMEOUT	5000
#define USB_CTRL_SET_TIMEOUT	5000


/**
 * struct usb_sg_request - support for scatter/gather I/O
 * @status: zero indicates success, else negative errno
 * @bytes: counts bytes transferred.
 *
 * These requests are initialized using usb_sg_init(), and then are used
 * as request handles passed to usb_sg_wait() or usb_sg_cancel().  Most
 * members of the request object aren't for driver access.
 *
 * The status and bytecount values are valid only after usb_sg_wait()
 * returns.  If the status is zero, then the bytecount matches the total
 * from the request.
 *
 * After an error completion, drivers may need to clear a halt condition
 * on the endpoint.
 */
struct usb_sg_request {
	int			status;
	size_t			bytes;

	/* private:
	 * members below are private to usbcore,
	 * and are not provided for driver access!
	 */
	spinlock_t		lock;

	struct usb_device	*dev;
	int			pipe;

	int			entries;
	struct urb		**urbs;

	int			count;
	struct completion	complete;
};

int usb_sg_init(
	struct usb_sg_request	*io,
	struct usb_device	*dev,
	unsigned		pipe,
	unsigned		period,
	struct scatterlist	*sg,
	int			nents,
	size_t			length,
	gfp_t			mem_flags
);
void usb_sg_cancel(struct usb_sg_request *io);
void usb_sg_wait(struct usb_sg_request *io);


/* ----------------------------------------------------------------------- */

/*
 * For various legacy reasons, Linux has a small cookie that's paired with
 * a struct usb_device to identify an endpoint queue.  Queue characteristics
 * are defined by the endpoint's descriptor.  This cookie is called a "pipe",
 * an unsigned int encoded as:
 *
 *  - direction:	bit 7		(0 = Host-to-Device [Out],
 *					 1 = Device-to-Host [In] ...
 *					like endpoint bEndpointAddress)
 *  - device address:	bits 8-14       ... bit positions known to uhci-hcd
 *  - endpoint:		bits 15-18      ... bit positions known to uhci-hcd
 *  - pipe type:	bits 30-31	(00 = isochronous, 01 = interrupt,
 *					 10 = control, 11 = bulk)
 *
 * Given the device address and endpoint descriptor, pipes are redundant.
 */

/* NOTE:  these are not the standard USB_ENDPOINT_XFER_* values!! */
/* (yet ... they're the values used by usbfs) */
#define PIPE_ISOCHRONOUS		0
#define PIPE_INTERRUPT			1
#define PIPE_CONTROL			2
#define PIPE_BULK			3

#define usb_pipein(pipe)	((pipe) & USB_DIR_IN)
#define usb_pipeout(pipe)	(!usb_pipein(pipe))

#define usb_pipedevice(pipe)	(((pipe) >> 8) & 0x7f)
#define usb_pipeendpoint(pipe)	(((pipe) >> 15) & 0xf)

#define usb_pipetype(pipe)	(((pipe) >> 30) & 3)
#define usb_pipeisoc(pipe)	(usb_pipetype((pipe)) == PIPE_ISOCHRONOUS)
#define usb_pipeint(pipe)	(usb_pipetype((pipe)) == PIPE_INTERRUPT)
#define usb_pipecontrol(pipe)	(usb_pipetype((pipe)) == PIPE_CONTROL)
#define usb_pipebulk(pipe)	(usb_pipetype((pipe)) == PIPE_BULK)

static inline unsigned int __create_pipe(struct usb_device *dev,
		unsigned int endpoint)
{
	return (dev->devnum << 8) | (endpoint << 15);
}

/* Create various pipes... */
#define usb_sndctrlpipe(dev, endpoint)	\
	((PIPE_CONTROL << 30) | __create_pipe(dev, endpoint))
#define usb_rcvctrlpipe(dev, endpoint)	\
	((PIPE_CONTROL << 30) | __create_pipe(dev, endpoint) | USB_DIR_IN)
#define usb_sndisocpipe(dev, endpoint)	\
	((PIPE_ISOCHRONOUS << 30) | __create_pipe(dev, endpoint))
#define usb_rcvisocpipe(dev, endpoint)	\
	((PIPE_ISOCHRONOUS << 30) | __create_pipe(dev, endpoint) | USB_DIR_IN)
#define usb_sndbulkpipe(dev, endpoint)	\
	((PIPE_BULK << 30) | __create_pipe(dev, endpoint))
#define usb_rcvbulkpipe(dev, endpoint)	\
	((PIPE_BULK << 30) | __create_pipe(dev, endpoint) | USB_DIR_IN)
#define usb_sndintpipe(dev, endpoint)	\
	((PIPE_INTERRUPT << 30) | __create_pipe(dev, endpoint))
#define usb_rcvintpipe(dev, endpoint)	\
	((PIPE_INTERRUPT << 30) | __create_pipe(dev, endpoint) | USB_DIR_IN)

static inline struct usb_host_endpoint *
usb_pipe_endpoint(struct usb_device *dev, unsigned int pipe)
{
	struct usb_host_endpoint **eps;
	eps = usb_pipein(pipe) ? dev->ep_in : dev->ep_out;
	return eps[usb_pipeendpoint(pipe)];
}

/*-------------------------------------------------------------------------*/

static inline __u16
usb_maxpacket(struct usb_device *udev, int pipe, int is_out)
{
	struct usb_host_endpoint	*ep;
	unsigned			epnum = usb_pipeendpoint(pipe);

	if (is_out) {
		WARN_ON(usb_pipein(pipe));
		ep = udev->ep_out[epnum];
	} else {
		WARN_ON(usb_pipeout(pipe));
		ep = udev->ep_in[epnum];
	}
	if (!ep)
		return 0;

	/* NOTE:  only 0x07ff bits are for packet size... */
	return usb_endpoint_maxp(&ep->desc);
}

/* ----------------------------------------------------------------------- */

/* Events from the usb core */
#define USB_DEVICE_ADD		0x0001
#define USB_DEVICE_REMOVE	0x0002
#define USB_BUS_ADD		0x0003
#define USB_BUS_REMOVE		0x0004
extern void usb_register_notify(struct notifier_block *nb);
extern void usb_unregister_notify(struct notifier_block *nb);

#ifdef DEBUG
#define dbg(format, arg...)						\
	printk(KERN_DEBUG "%s: " format "\n", __FILE__, ##arg)
#else
#define dbg(format, arg...)						\
do {									\
	if (0)								\
		printk(KERN_DEBUG "%s: " format "\n", __FILE__, ##arg); \
} while (0)
#endif

#define err(format, arg...)					\
	printk(KERN_ERR KBUILD_MODNAME ": " format "\n", ##arg)

/* debugfs stuff */
extern struct dentry *usb_debug_root;

#endif  /* __KERNEL__ */

#endif
> 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756
/*
   md.c : Multiple Devices driver for Linux
	  Copyright (C) 1998, 1999, 2000 Ingo Molnar

     completely rewritten, based on the MD driver code from Marc Zyngier

   Changes:

   - RAID-1/RAID-5 extensions by Miguel de Icaza, Gadi Oxman, Ingo Molnar
   - RAID-6 extensions by H. Peter Anvin <hpa@zytor.com>
   - boot support for linear and striped mode by Harald Hoyer <HarryH@Royal.Net>
   - kerneld support by Boris Tobotras <boris@xtalk.msk.su>
   - kmod support by: Cyrus Durgin
   - RAID0 bugfixes: Mark Anthony Lisher <markal@iname.com>
   - Devfs support by Richard Gooch <rgooch@atnf.csiro.au>

   - lots of fixes and improvements to the RAID1/RAID5 and generic
     RAID code (such as request based resynchronization):

     Neil Brown <neilb@cse.unsw.edu.au>.

   - persistent bitmap code
     Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc.

   This program is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 2, or (at your option)
   any later version.

   You should have received a copy of the GNU General Public License
   (for example /usr/src/linux/COPYING); if not, write to the Free
   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/

#include <linux/kthread.h>
#include <linux/blkdev.h>
#include <linux/sysctl.h>
#include <linux/seq_file.h>
#include <linux/fs.h>
#include <linux/poll.h>
#include <linux/ctype.h>
#include <linux/string.h>
#include <linux/hdreg.h>
#include <linux/proc_fs.h>
#include <linux/random.h>
#include <linux/module.h>
#include <linux/reboot.h>
#include <linux/file.h>
#include <linux/compat.h>
#include <linux/delay.h>
#include <linux/raid/md_p.h>
#include <linux/raid/md_u.h>
#include <linux/slab.h>
#include "md.h"
#include "bitmap.h"

#ifndef MODULE
static void autostart_arrays(int part);
#endif

/* pers_list is a list of registered personalities protected
 * by pers_lock.
 * pers_lock does extra service to protect accesses to
 * mddev->thread when the mutex cannot be held.
 */
static LIST_HEAD(pers_list);
static DEFINE_SPINLOCK(pers_lock);

static void md_print_devices(void);

static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
static struct workqueue_struct *md_wq;
static struct workqueue_struct *md_misc_wq;

static int remove_and_add_spares(struct mddev *mddev,
				 struct md_rdev *this);

#define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }

/*
 * Default number of read corrections we'll attempt on an rdev
 * before ejecting it from the array. We divide the read error
 * count by 2 for every hour elapsed between read errors.
 */
#define MD_DEFAULT_MAX_CORRECTED_READ_ERRORS 20
/*
 * Current RAID-1,4,5 parallel reconstruction 'guaranteed speed limit'
 * is 1000 KB/sec, so the extra system load does not show up that much.
 * Increase it if you want to have more _guaranteed_ speed. Note that
 * the RAID driver will use the maximum available bandwidth if the IO
 * subsystem is idle. There is also an 'absolute maximum' reconstruction
 * speed limit - in case reconstruction slows down your system despite
 * idle IO detection.
 *
 * you can change it via /proc/sys/dev/raid/speed_limit_min and _max.
 * or /sys/block/mdX/md/sync_speed_{min,max}
 */

static int sysctl_speed_limit_min = 1000;
static int sysctl_speed_limit_max = 200000;
static inline int speed_min(struct mddev *mddev)
{
	return mddev->sync_speed_min ?
		mddev->sync_speed_min : sysctl_speed_limit_min;
}

static inline int speed_max(struct mddev *mddev)
{
	return mddev->sync_speed_max ?
		mddev->sync_speed_max : sysctl_speed_limit_max;
}

static struct ctl_table_header *raid_table_header;

static struct ctl_table raid_table[] = {
	{
		.procname	= "speed_limit_min",
		.data		= &sysctl_speed_limit_min,
		.maxlen		= sizeof(int),
		.mode		= S_IRUGO|S_IWUSR,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "speed_limit_max",
		.data		= &sysctl_speed_limit_max,
		.maxlen		= sizeof(int),
		.mode		= S_IRUGO|S_IWUSR,
		.proc_handler	= proc_dointvec,
	},
	{ }
};

static struct ctl_table raid_dir_table[] = {
	{
		.procname	= "raid",
		.maxlen		= 0,
		.mode		= S_IRUGO|S_IXUGO,
		.child		= raid_table,
	},
	{ }
};

static struct ctl_table raid_root_table[] = {
	{
		.procname	= "dev",
		.maxlen		= 0,
		.mode		= 0555,
		.child		= raid_dir_table,
	},
	{  }
};

static const struct block_device_operations md_fops;

static int start_readonly;

/* bio_clone_mddev
 * like bio_clone, but with a local bio set
 */

struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
			    struct mddev *mddev)
{
	struct bio *b;

	if (!mddev || !mddev->bio_set)
		return bio_alloc(gfp_mask, nr_iovecs);

	b = bio_alloc_bioset(gfp_mask, nr_iovecs, mddev->bio_set);
	if (!b)
		return NULL;
	return b;
}
EXPORT_SYMBOL_GPL(bio_alloc_mddev);

struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask,
			    struct mddev *mddev)
{
	if (!mddev || !mddev->bio_set)
		return bio_clone(bio, gfp_mask);

	return bio_clone_bioset(bio, gfp_mask, mddev->bio_set);
}
EXPORT_SYMBOL_GPL(bio_clone_mddev);

/*
 * We have a system wide 'event count' that is incremented
 * on any 'interesting' event, and readers of /proc/mdstat
 * can use 'poll' or 'select' to find out when the event
 * count increases.
 *
 * Events are:
 *  start array, stop array, error, add device, remove device,
 *  start build, activate spare
 */
static DECLARE_WAIT_QUEUE_HEAD(md_event_waiters);
static atomic_t md_event_count;
void md_new_event(struct mddev *mddev)
{
	atomic_inc(&md_event_count);
	wake_up(&md_event_waiters);
}
EXPORT_SYMBOL_GPL(md_new_event);

/* Alternate version that can be called from interrupts
 * when calling sysfs_notify isn't needed.
 */
static void md_new_event_inintr(struct mddev *mddev)
{
	atomic_inc(&md_event_count);
	wake_up(&md_event_waiters);
}

/*
 * Enables to iterate over all existing md arrays
 * all_mddevs_lock protects this list.
 */
static LIST_HEAD(all_mddevs);
static DEFINE_SPINLOCK(all_mddevs_lock);


/*
 * iterates through all used mddevs in the system.
 * We take care to grab the all_mddevs_lock whenever navigating
 * the list, and to always hold a refcount when unlocked.
 * Any code which breaks out of this loop while own
 * a reference to the current mddev and must mddev_put it.
 */
#define for_each_mddev(_mddev,_tmp)					\
									\
	for (({ spin_lock(&all_mddevs_lock); 				\
		_tmp = all_mddevs.next;					\
		_mddev = NULL;});					\
	     ({ if (_tmp != &all_mddevs)				\
			mddev_get(list_entry(_tmp, struct mddev, all_mddevs));\
		spin_unlock(&all_mddevs_lock);				\
		if (_mddev) mddev_put(_mddev);				\
		_mddev = list_entry(_tmp, struct mddev, all_mddevs);	\
		_tmp != &all_mddevs;});					\
	     ({ spin_lock(&all_mddevs_lock);				\
		_tmp = _tmp->next;})					\
		)


/* Rather than calling directly into the personality make_request function,
 * IO requests come here first so that we can check if the device is
 * being suspended pending a reconfiguration.
 * We hold a refcount over the call to ->make_request.  By the time that
 * call has finished, the bio has been linked into some internal structure
 * and so is visible to ->quiesce(), so we don't need the refcount any more.
 */
static void md_make_request(struct request_queue *q, struct bio *bio)
{
	const int rw = bio_data_dir(bio);
	struct mddev *mddev = q->queuedata;
	int cpu;
	unsigned int sectors;

	if (mddev == NULL || mddev->pers == NULL
	    || !mddev->ready) {
		bio_io_error(bio);
		return;
	}
	if (mddev->ro == 1 && unlikely(rw == WRITE)) {
		bio_endio(bio, bio_sectors(bio) == 0 ? 0 : -EROFS);
		return;
	}
	smp_rmb(); /* Ensure implications of  'active' are visible */
	rcu_read_lock();
	if (mddev->suspended) {
		DEFINE_WAIT(__wait);
		for (;;) {
			prepare_to_wait(&mddev->sb_wait, &__wait,
					TASK_UNINTERRUPTIBLE);
			if (!mddev->suspended)
				break;
			rcu_read_unlock();
			schedule();
			rcu_read_lock();
		}
		finish_wait(&mddev->sb_wait, &__wait);
	}
	atomic_inc(&mddev->active_io);
	rcu_read_unlock();

	/*
	 * save the sectors now since our bio can
	 * go away inside make_request
	 */
	sectors = bio_sectors(bio);
	mddev->pers->make_request(mddev, bio);

	cpu = part_stat_lock();
	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
	part_stat_unlock();

	if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
		wake_up(&mddev->sb_wait);
}

/* mddev_suspend makes sure no new requests are submitted
 * to the device, and that any requests that have been submitted
 * are completely handled.
 * Once ->stop is called and completes, the module will be completely
 * unused.
 */
void mddev_suspend(struct mddev *mddev)
{
	BUG_ON(mddev->suspended);
	mddev->suspended = 1;
	synchronize_rcu();
	wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0);
	mddev->pers->quiesce(mddev, 1);

	del_timer_sync(&mddev->safemode_timer);
}
EXPORT_SYMBOL_GPL(mddev_suspend);

void mddev_resume(struct mddev *mddev)
{
	mddev->suspended = 0;
	wake_up(&mddev->sb_wait);
	mddev->pers->quiesce(mddev, 0);

	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
	md_wakeup_thread(mddev->thread);
	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
}
EXPORT_SYMBOL_GPL(mddev_resume);

int mddev_congested(struct mddev *mddev, int bits)
{
	return mddev->suspended;
}
EXPORT_SYMBOL(mddev_congested);

/*
 * Generic flush handling for md
 */

static void md_end_flush(struct bio *bio, int err)
{
	struct md_rdev *rdev = bio->bi_private;
	struct mddev *mddev = rdev->mddev;

	rdev_dec_pending(rdev, mddev);

	if (atomic_dec_and_test(&mddev->flush_pending)) {
		/* The pre-request flush has finished */
		queue_work(md_wq, &mddev->flush_work);
	}
	bio_put(bio);
}

static void md_submit_flush_data(struct work_struct *ws);

static void submit_flushes(struct work_struct *ws)
{
	struct mddev *mddev = container_of(ws, struct mddev, flush_work);
	struct md_rdev *rdev;

	INIT_WORK(&mddev->flush_work, md_submit_flush_data);
	atomic_set(&mddev->flush_pending, 1);
	rcu_read_lock();
	rdev_for_each_rcu(rdev, mddev)
		if (rdev->raid_disk >= 0 &&
		    !test_bit(Faulty, &rdev->flags)) {
			/* Take two references, one is dropped
			 * when request finishes, one after
			 * we reclaim rcu_read_lock
			 */
			struct bio *bi;
			atomic_inc(&rdev->nr_pending);
			atomic_inc(&rdev->nr_pending);
			rcu_read_unlock();
			bi = bio_alloc_mddev(GFP_NOIO, 0, mddev);
			bi->bi_end_io = md_end_flush;
			bi->bi_private = rdev;
			bi->bi_bdev = rdev->bdev;
			atomic_inc(&mddev->flush_pending);
			submit_bio(WRITE_FLUSH, bi);
			rcu_read_lock();
			rdev_dec_pending(rdev, mddev);
		}
	rcu_read_unlock();
	if (atomic_dec_and_test(&mddev->flush_pending))
		queue_work(md_wq, &mddev->flush_work);
}

static void md_submit_flush_data(struct work_struct *ws)
{
	struct mddev *mddev = container_of(ws, struct mddev, flush_work);
	struct bio *bio = mddev->flush_bio;

	if (bio->bi_iter.bi_size == 0)
		/* an empty barrier - all done */
		bio_endio(bio, 0);
	else {
		bio->bi_rw &= ~REQ_FLUSH;
		mddev->pers->make_request(mddev, bio);
	}

	mddev->flush_bio = NULL;
	wake_up(&mddev->sb_wait);
}

void md_flush_request(struct mddev *mddev, struct bio *bio)
{
	spin_lock_irq(&mddev->write_lock);
	wait_event_lock_irq(mddev->sb_wait,
			    !mddev->flush_bio,
			    mddev->write_lock);
	mddev->flush_bio = bio;
	spin_unlock_irq(&mddev->write_lock);

	INIT_WORK(&mddev->flush_work, submit_flushes);
	queue_work(md_wq, &mddev->flush_work);
}
EXPORT_SYMBOL(md_flush_request);

void md_unplug(struct blk_plug_cb *cb, bool from_schedule)
{
	struct mddev *mddev = cb->data;
	md_wakeup_thread(mddev->thread);
	kfree(cb);
}
EXPORT_SYMBOL(md_unplug);

static inline struct mddev *mddev_get(struct mddev *mddev)
{
	atomic_inc(&mddev->active);
	return mddev;
}

static void mddev_delayed_delete(struct work_struct *ws);

static void mddev_put(struct mddev *mddev)
{
	struct bio_set *bs = NULL;

	if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
		return;
	if (!mddev->raid_disks && list_empty(&mddev->disks) &&
	    mddev->ctime == 0 && !mddev->hold_active) {
		/* Array is not configured at all, and not held active,
		 * so destroy it */
		list_del_init(&mddev->all_mddevs);
		bs = mddev->bio_set;
		mddev->bio_set = NULL;
		if (mddev->gendisk) {
			/* We did a probe so need to clean up.  Call
			 * queue_work inside the spinlock so that
			 * flush_workqueue() after mddev_find will
			 * succeed in waiting for the work to be done.
			 */
			INIT_WORK(&mddev->del_work, mddev_delayed_delete);
			queue_work(md_misc_wq, &mddev->del_work);
		} else
			kfree(mddev);
	}
	spin_unlock(&all_mddevs_lock);
	if (bs)
		bioset_free(bs);
}

void mddev_init(struct mddev *mddev)
{
	mutex_init(&mddev->open_mutex);
	mutex_init(&mddev->reconfig_mutex);
	mutex_init(&mddev->bitmap_info.mutex);
	INIT_LIST_HEAD(&mddev->disks);
	INIT_LIST_HEAD(&mddev->all_mddevs);
	init_timer(&mddev->safemode_timer);
	atomic_set(&mddev->active, 1);
	atomic_set(&mddev->openers, 0);
	atomic_set(&mddev->active_io, 0);
	spin_lock_init(&mddev->write_lock);
	atomic_set(&mddev->flush_pending, 0);
	init_waitqueue_head(&mddev->sb_wait);
	init_waitqueue_head(&mddev->recovery_wait);
	mddev->reshape_position = MaxSector;
	mddev->reshape_backwards = 0;
	mddev->last_sync_action = "none";
	mddev->resync_min = 0;
	mddev->resync_max = MaxSector;
	mddev->level = LEVEL_NONE;
}
EXPORT_SYMBOL_GPL(mddev_init);

static struct mddev * mddev_find(dev_t unit)
{
	struct mddev *mddev, *new = NULL;

	if (unit && MAJOR(unit) != MD_MAJOR)
		unit &= ~((1<<MdpMinorShift)-1);

 retry:
	spin_lock(&all_mddevs_lock);

	if (unit) {
		list_for_each_entry(mddev, &all_mddevs, all_mddevs)
			if (mddev->unit == unit) {
				mddev_get(mddev);
				spin_unlock(&all_mddevs_lock);
				kfree(new);
				return mddev;
			}

		if (new) {
			list_add(&new->all_mddevs, &all_mddevs);
			spin_unlock(&all_mddevs_lock);
			new->hold_active = UNTIL_IOCTL;
			return new;
		}
	} else if (new) {
		/* find an unused unit number */
		static int next_minor = 512;
		int start = next_minor;
		int is_free = 0;
		int dev = 0;
		while (!is_free) {
			dev = MKDEV(MD_MAJOR, next_minor);
			next_minor++;
			if (next_minor > MINORMASK)
				next_minor = 0;
			if (next_minor == start) {
				/* Oh dear, all in use. */
				spin_unlock(&all_mddevs_lock);
				kfree(new);
				return NULL;
			}
				
			is_free = 1;
			list_for_each_entry(mddev, &all_mddevs, all_mddevs)
				if (mddev->unit == dev) {
					is_free = 0;
					break;
				}
		}
		new->unit = dev;
		new->md_minor = MINOR(dev);
		new->hold_active = UNTIL_STOP;
		list_add(&new->all_mddevs, &all_mddevs);
		spin_unlock(&all_mddevs_lock);
		return new;
	}
	spin_unlock(&all_mddevs_lock);

	new = kzalloc(sizeof(*new), GFP_KERNEL);
	if (!new)
		return NULL;

	new->unit = unit;
	if (MAJOR(unit) == MD_MAJOR)
		new->md_minor = MINOR(unit);
	else
		new->md_minor = MINOR(unit) >> MdpMinorShift;

	mddev_init(new);

	goto retry;
}

static inline int __must_check mddev_lock(struct mddev * mddev)
{
	return mutex_lock_interruptible(&mddev->reconfig_mutex);
}

/* Sometimes we need to take the lock in a situation where
 * failure due to interrupts is not acceptable.
 */
static inline void mddev_lock_nointr(struct mddev * mddev)
{
	mutex_lock(&mddev->reconfig_mutex);
}

static inline int mddev_is_locked(struct mddev *mddev)
{
	return mutex_is_locked(&mddev->reconfig_mutex);
}

static inline int mddev_trylock(struct mddev * mddev)
{
	return mutex_trylock(&mddev->reconfig_mutex);
}

static struct attribute_group md_redundancy_group;

static void mddev_unlock(struct mddev * mddev)
{
	if (mddev->to_remove) {
		/* These cannot be removed under reconfig_mutex as
		 * an access to the files will try to take reconfig_mutex
		 * while holding the file unremovable, which leads to
		 * a deadlock.
		 * So hold set sysfs_active while the remove in happeing,
		 * and anything else which might set ->to_remove or my
		 * otherwise change the sysfs namespace will fail with
		 * -EBUSY if sysfs_active is still set.
		 * We set sysfs_active under reconfig_mutex and elsewhere
		 * test it under the same mutex to ensure its correct value
		 * is seen.
		 */
		struct attribute_group *to_remove = mddev->to_remove;
		mddev->to_remove = NULL;
		mddev->sysfs_active = 1;
		mutex_unlock(&mddev->reconfig_mutex);

		if (mddev->kobj.sd) {
			if (to_remove != &md_redundancy_group)
				sysfs_remove_group(&mddev->kobj, to_remove);
			if (mddev->pers == NULL ||
			    mddev->pers->sync_request == NULL) {
				sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
				if (mddev->sysfs_action)
					sysfs_put(mddev->sysfs_action);
				mddev->sysfs_action = NULL;
			}
		}
		mddev->sysfs_active = 0;
	} else
		mutex_unlock(&mddev->reconfig_mutex);

	/* As we've dropped the mutex we need a spinlock to
	 * make sure the thread doesn't disappear
	 */
	spin_lock(&pers_lock);
	md_wakeup_thread(mddev->thread);
	spin_unlock(&pers_lock);
}

static struct md_rdev * find_rdev_nr(struct mddev *mddev, int nr)
{
	struct md_rdev *rdev;

	rdev_for_each(rdev, mddev)
		if (rdev->desc_nr == nr)
			return rdev;

	return NULL;
}

static struct md_rdev *find_rdev_nr_rcu(struct mddev *mddev, int nr)
{
	struct md_rdev *rdev;

	rdev_for_each_rcu(rdev, mddev)
		if (rdev->desc_nr == nr)
			return rdev;

	return NULL;
}

static struct md_rdev *find_rdev(struct mddev *mddev, dev_t dev)
{
	struct md_rdev *rdev;

	rdev_for_each(rdev, mddev)
		if (rdev->bdev->bd_dev == dev)
			return rdev;

	return NULL;
}

static struct md_rdev *find_rdev_rcu(struct mddev *mddev, dev_t dev)
{
	struct md_rdev *rdev;

	rdev_for_each_rcu(rdev, mddev)
		if (rdev->bdev->bd_dev == dev)
			return rdev;

	return NULL;
}

static struct md_personality *find_pers(int level, char *clevel)
{
	struct md_personality *pers;
	list_for_each_entry(pers, &pers_list, list) {
		if (level != LEVEL_NONE && pers->level == level)
			return pers;
		if (strcmp(pers->name, clevel)==0)
			return pers;
	}
	return NULL;
}

/* return the offset of the super block in 512byte sectors */
static inline sector_t calc_dev_sboffset(struct md_rdev *rdev)
{
	sector_t num_sectors = i_size_read(rdev->bdev->bd_inode) / 512;
	return MD_NEW_SIZE_SECTORS(num_sectors);
}

static int alloc_disk_sb(struct md_rdev * rdev)
{
	if (rdev->sb_page)
		MD_BUG();

	rdev->sb_page = alloc_page(GFP_KERNEL);
	if (!rdev->sb_page) {
		printk(KERN_ALERT "md: out of memory.\n");
		return -ENOMEM;
	}

	return 0;
}

void md_rdev_clear(struct md_rdev *rdev)
{
	if (rdev->sb_page) {
		put_page(rdev->sb_page);
		rdev->sb_loaded = 0;
		rdev->sb_page = NULL;
		rdev->sb_start = 0;
		rdev->sectors = 0;
	}
	if (rdev->bb_page) {
		put_page(rdev->bb_page);
		rdev->bb_page = NULL;
	}
	kfree(rdev->badblocks.page);
	rdev->badblocks.page = NULL;
}
EXPORT_SYMBOL_GPL(md_rdev_clear);

static void super_written(struct bio *bio, int error)
{
	struct md_rdev *rdev = bio->bi_private;
	struct mddev *mddev = rdev->mddev;

	if (error || !test_bit(BIO_UPTODATE, &bio->bi_flags)) {
		printk("md: super_written gets error=%d, uptodate=%d\n",
		       error, test_bit(BIO_UPTODATE, &bio->bi_flags));
		WARN_ON(test_bit(BIO_UPTODATE, &bio->bi_flags));
		md_error(mddev, rdev);
	}

	if (atomic_dec_and_test(&mddev->pending_writes))
		wake_up(&mddev->sb_wait);
	bio_put(bio);
}

void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
		   sector_t sector, int size, struct page *page)
{
	/* write first size bytes of page to sector of rdev
	 * Increment mddev->pending_writes before returning
	 * and decrement it on completion, waking up sb_wait
	 * if zero is reached.
	 * If an error occurred, call md_error
	 */
	struct bio *bio = bio_alloc_mddev(GFP_NOIO, 1, mddev);

	bio->bi_bdev = rdev->meta_bdev ? rdev->meta_bdev : rdev->bdev;
	bio->bi_iter.bi_sector = sector;
	bio_add_page(bio, page, size, 0);
	bio->bi_private = rdev;
	bio->bi_end_io = super_written;

	atomic_inc(&mddev->pending_writes);
	submit_bio(WRITE_FLUSH_FUA, bio);
}

void md_super_wait(struct mddev *mddev)
{
	/* wait for all superblock writes that were scheduled to complete */
	DEFINE_WAIT(wq);
	for(;;) {
		prepare_to_wait(&mddev->sb_wait, &wq, TASK_UNINTERRUPTIBLE);
		if (atomic_read(&mddev->pending_writes)==0)
			break;
		schedule();
	}
	finish_wait(&mddev->sb_wait, &wq);
}

int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
		 struct page *page, int rw, bool metadata_op)
{
	struct bio *bio = bio_alloc_mddev(GFP_NOIO, 1, rdev->mddev);
	int ret;

	bio->bi_bdev = (metadata_op && rdev->meta_bdev) ?
		rdev->meta_bdev : rdev->bdev;
	if (metadata_op)
		bio->bi_iter.bi_sector = sector + rdev->sb_start;
	else if (rdev->mddev->reshape_position != MaxSector &&
		 (rdev->mddev->reshape_backwards ==
		  (sector >= rdev->mddev->reshape_position)))
		bio->bi_iter.bi_sector = sector + rdev->new_data_offset;
	else
		bio->bi_iter.bi_sector = sector + rdev->data_offset;
	bio_add_page(bio, page, size, 0);
	submit_bio_wait(rw, bio);

	ret = test_bit(BIO_UPTODATE, &bio->bi_flags);
	bio_put(bio);
	return ret;
}
EXPORT_SYMBOL_GPL(sync_page_io);

static int read_disk_sb(struct md_rdev * rdev, int size)
{
	char b[BDEVNAME_SIZE];
	if (!rdev->sb_page) {
		MD_BUG();
		return -EINVAL;
	}
	if (rdev->sb_loaded)
		return 0;


	if (!sync_page_io(rdev, 0, size, rdev->sb_page, READ, true))
		goto fail;
	rdev->sb_loaded = 1;
	return 0;

fail:
	printk(KERN_WARNING "md: disabled device %s, could not read superblock.\n",
		bdevname(rdev->bdev,b));
	return -EINVAL;
}

static int uuid_equal(mdp_super_t *sb1, mdp_super_t *sb2)
{
	return 	sb1->set_uuid0 == sb2->set_uuid0 &&
		sb1->set_uuid1 == sb2->set_uuid1 &&
		sb1->set_uuid2 == sb2->set_uuid2 &&
		sb1->set_uuid3 == sb2->set_uuid3;
}

static int sb_equal(mdp_super_t *sb1, mdp_super_t *sb2)
{
	int ret;
	mdp_super_t *tmp1, *tmp2;

	tmp1 = kmalloc(sizeof(*tmp1),GFP_KERNEL);
	tmp2 = kmalloc(sizeof(*tmp2),GFP_KERNEL);

	if (!tmp1 || !tmp2) {
		ret = 0;
		printk(KERN_INFO "md.c sb_equal(): failed to allocate memory!\n");
		goto abort;
	}

	*tmp1 = *sb1;
	*tmp2 = *sb2;

	/*
	 * nr_disks is not constant
	 */
	tmp1->nr_disks = 0;
	tmp2->nr_disks = 0;

	ret = (memcmp(tmp1, tmp2, MD_SB_GENERIC_CONSTANT_WORDS * 4) == 0);
abort:
	kfree(tmp1);
	kfree(tmp2);
	return ret;
}


static u32 md_csum_fold(u32 csum)
{
	csum = (csum & 0xffff) + (csum >> 16);
	return (csum & 0xffff) + (csum >> 16);
}

static unsigned int calc_sb_csum(mdp_super_t * sb)
{
	u64 newcsum = 0;
	u32 *sb32 = (u32*)sb;
	int i;
	unsigned int disk_csum, csum;

	disk_csum = sb->sb_csum;
	sb->sb_csum = 0;

	for (i = 0; i < MD_SB_BYTES/4 ; i++)
		newcsum += sb32[i];
	csum = (newcsum & 0xffffffff) + (newcsum>>32);


#ifdef CONFIG_ALPHA
	/* This used to use csum_partial, which was wrong for several
	 * reasons including that different results are returned on
	 * different architectures.  It isn't critical that we get exactly
	 * the same return value as before (we always csum_fold before
	 * testing, and that removes any differences).  However as we
	 * know that csum_partial always returned a 16bit value on
	 * alphas, do a fold to maximise conformity to previous behaviour.
	 */
	sb->sb_csum = md_csum_fold(disk_csum);
#else
	sb->sb_csum = disk_csum;
#endif
	return csum;
}


/*
 * Handle superblock details.
 * We want to be able to handle multiple superblock formats
 * so we have a common interface to them all, and an array of
 * different handlers.
 * We rely on user-space to write the initial superblock, and support
 * reading and updating of superblocks.
 * Interface methods are:
 *   int load_super(struct md_rdev *dev, struct md_rdev *refdev, int minor_version)
 *      loads and validates a superblock on dev.
 *      if refdev != NULL, compare superblocks on both devices
 *    Return:
 *      0 - dev has a superblock that is compatible with refdev
 *      1 - dev has a superblock that is compatible and newer than refdev
 *          so dev should be used as the refdev in future
 *     -EINVAL superblock incompatible or invalid
 *     -othererror e.g. -EIO
 *
 *   int validate_super(struct mddev *mddev, struct md_rdev *dev)
 *      Verify that dev is acceptable into mddev.
 *       The first time, mddev->raid_disks will be 0, and data from
 *       dev should be merged in.  Subsequent calls check that dev
 *       is new enough.  Return 0 or -EINVAL
 *
 *   void sync_super(struct mddev *mddev, struct md_rdev *dev)
 *     Update the superblock for rdev with data in mddev
 *     This does not write to disc.
 *
 */

struct super_type  {
	char		    *name;
	struct module	    *owner;
	int		    (*load_super)(struct md_rdev *rdev,
					  struct md_rdev *refdev,
					  int minor_version);
	int		    (*validate_super)(struct mddev *mddev,
					      struct md_rdev *rdev);
	void		    (*sync_super)(struct mddev *mddev,
					  struct md_rdev *rdev);
	unsigned long long  (*rdev_size_change)(struct md_rdev *rdev,
						sector_t num_sectors);
	int		    (*allow_new_offset)(struct md_rdev *rdev,
						unsigned long long new_offset);
};

/*
 * Check that the given mddev has no bitmap.
 *
 * This function is called from the run method of all personalities that do not
 * support bitmaps. It prints an error message and returns non-zero if mddev
 * has a bitmap. Otherwise, it returns 0.
 *
 */
int md_check_no_bitmap(struct mddev *mddev)
{
	if (!mddev->bitmap_info.file && !mddev->bitmap_info.offset)
		return 0;
	printk(KERN_ERR "%s: bitmaps are not supported for %s\n",
		mdname(mddev), mddev->pers->name);
	return 1;
}
EXPORT_SYMBOL(md_check_no_bitmap);

/*
 * load_super for 0.90.0 
 */
static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_version)
{
	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
	mdp_super_t *sb;
	int ret;

	/*
	 * Calculate the position of the superblock (512byte sectors),
	 * it's at the end of the disk.
	 *
	 * It also happens to be a multiple of 4Kb.
	 */
	rdev->sb_start = calc_dev_sboffset(rdev);

	ret = read_disk_sb(rdev, MD_SB_BYTES);
	if (ret) return ret;

	ret = -EINVAL;

	bdevname(rdev->bdev, b);
	sb = page_address(rdev->sb_page);

	if (sb->md_magic != MD_SB_MAGIC) {
		printk(KERN_ERR "md: invalid raid superblock magic on %s\n",
		       b);
		goto abort;
	}

	if (sb->major_version != 0 ||
	    sb->minor_version < 90 ||
	    sb->minor_version > 91) {
		printk(KERN_WARNING "Bad version number %d.%d on %s\n",
			sb->major_version, sb->minor_version,
			b);
		goto abort;
	}

	if (sb->raid_disks <= 0)
		goto abort;

	if (md_csum_fold(calc_sb_csum(sb)) != md_csum_fold(sb->sb_csum)) {
		printk(KERN_WARNING "md: invalid superblock checksum on %s\n",
			b);
		goto abort;
	}

	rdev->preferred_minor = sb->md_minor;
	rdev->data_offset = 0;
	rdev->new_data_offset = 0;
	rdev->sb_size = MD_SB_BYTES;
	rdev->badblocks.shift = -1;

	if (sb->level == LEVEL_MULTIPATH)
		rdev->desc_nr = -1;
	else
		rdev->desc_nr = sb->this_disk.number;

	if (!refdev) {
		ret = 1;
	} else {
		__u64 ev1, ev2;
		mdp_super_t *refsb = page_address(refdev->sb_page);
		if (!uuid_equal(refsb, sb)) {
			printk(KERN_WARNING "md: %s has different UUID to %s\n",
				b, bdevname(refdev->bdev,b2));
			goto abort;
		}
		if (!sb_equal(refsb, sb)) {
			printk(KERN_WARNING "md: %s has same UUID"
			       " but different superblock to %s\n",
			       b, bdevname(refdev->bdev, b2));
			goto abort;
		}
		ev1 = md_event(sb);
		ev2 = md_event(refsb);
		if (ev1 > ev2)
			ret = 1;
		else 
			ret = 0;
	}
	rdev->sectors = rdev->sb_start;
	/* Limit to 4TB as metadata cannot record more than that.
	 * (not needed for Linear and RAID0 as metadata doesn't
	 * record this size)
	 */
	if (rdev->sectors >= (2ULL << 32) && sb->level >= 1)
		rdev->sectors = (2ULL << 32) - 2;

	if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1)
		/* "this cannot possibly happen" ... */
		ret = -EINVAL;

 abort:
	return ret;
}

/*
 * validate_super for 0.90.0
 */
static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
{
	mdp_disk_t *desc;
	mdp_super_t *sb = page_address(rdev->sb_page);
	__u64 ev1 = md_event(sb);

	rdev->raid_disk = -1;
	clear_bit(Faulty, &rdev->flags);
	clear_bit(In_sync, &rdev->flags);
	clear_bit(Bitmap_sync, &rdev->flags);
	clear_bit(WriteMostly, &rdev->flags);

	if (mddev->raid_disks == 0) {
		mddev->major_version = 0;
		mddev->minor_version = sb->minor_version;
		mddev->patch_version = sb->patch_version;
		mddev->external = 0;
		mddev->chunk_sectors = sb->chunk_size >> 9;
		mddev->ctime = sb->ctime;
		mddev->utime = sb->utime;
		mddev->level = sb->level;
		mddev->clevel[0] = 0;
		mddev->layout = sb->layout;
		mddev->raid_disks = sb->raid_disks;
		mddev->dev_sectors = ((sector_t)sb->size) * 2;
		mddev->events = ev1;
		mddev->bitmap_info.offset = 0;
		mddev->bitmap_info.space = 0;
		/* bitmap can use 60 K after the 4K superblocks */
		mddev->bitmap_info.default_offset = MD_SB_BYTES >> 9;
		mddev->bitmap_info.default_space = 64*2 - (MD_SB_BYTES >> 9);
		mddev->reshape_backwards = 0;

		if (mddev->minor_version >= 91) {
			mddev->reshape_position = sb->reshape_position;
			mddev->delta_disks = sb->delta_disks;
			mddev->new_level = sb->new_level;
			mddev->new_layout = sb->new_layout;
			mddev->new_chunk_sectors = sb->new_chunk >> 9;
			if (mddev->delta_disks < 0)
				mddev->reshape_backwards = 1;
		} else {
			mddev->reshape_position = MaxSector;
			mddev->delta_disks = 0;
			mddev->new_level = mddev->level;
			mddev->new_layout = mddev->layout;
			mddev->new_chunk_sectors = mddev->chunk_sectors;
		}

		if (sb->state & (1<<MD_SB_CLEAN))
			mddev->recovery_cp = MaxSector;
		else {
			if (sb->events_hi == sb->cp_events_hi && 
				sb->events_lo == sb->cp_events_lo) {
				mddev->recovery_cp = sb->recovery_cp;
			} else
				mddev->recovery_cp = 0;
		}

		memcpy(mddev->uuid+0, &sb->set_uuid0, 4);
		memcpy(mddev->uuid+4, &sb->set_uuid1, 4);
		memcpy(mddev->uuid+8, &sb->set_uuid2, 4);
		memcpy(mddev->uuid+12,&sb->set_uuid3, 4);

		mddev->max_disks = MD_SB_DISKS;

		if (sb->state & (1<<MD_SB_BITMAP_PRESENT) &&
		    mddev->bitmap_info.file == NULL) {
			mddev->bitmap_info.offset =
				mddev->bitmap_info.default_offset;
			mddev->bitmap_info.space =
				mddev->bitmap_info.default_space;
		}

	} else if (mddev->pers == NULL) {
		/* Insist on good event counter while assembling, except
		 * for spares (which don't need an event count) */
		++ev1;
		if (sb->disks[rdev->desc_nr].state & (
			    (1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE)))
			if (ev1 < mddev->events) 
				return -EINVAL;
	} else if (mddev->bitmap) {
		/* if adding to array with a bitmap, then we can accept an
		 * older device ... but not too old.
		 */
		if (ev1 < mddev->bitmap->events_cleared)
			return 0;
		if (ev1 < mddev->events)
			set_bit(Bitmap_sync, &rdev->flags);
	} else {
		if (ev1 < mddev->events)
			/* just a hot-add of a new device, leave raid_disk at -1 */
			return 0;
	}

	if (mddev->level != LEVEL_MULTIPATH) {
		desc = sb->disks + rdev->desc_nr;

		if (desc->state & (1<<MD_DISK_FAULTY))
			set_bit(Faulty, &rdev->flags);
		else if (desc->state & (1<<MD_DISK_SYNC) /* &&
			    desc->raid_disk < mddev->raid_disks */) {
			set_bit(In_sync, &rdev->flags);
			rdev->raid_disk = desc->raid_disk;
			rdev->saved_raid_disk = desc->raid_disk;
		} else if (desc->state & (1<<MD_DISK_ACTIVE)) {
			/* active but not in sync implies recovery up to
			 * reshape position.  We don't know exactly where
			 * that is, so set to zero for now */
			if (mddev->minor_version >= 91) {
				rdev->recovery_offset = 0;
				rdev->raid_disk = desc->raid_disk;
			}
		}
		if (desc->state & (1<<MD_DISK_WRITEMOSTLY))
			set_bit(WriteMostly, &rdev->flags);
	} else /* MULTIPATH are always insync */
		set_bit(In_sync, &rdev->flags);
	return 0;
}

/*
 * sync_super for 0.90.0
 */
static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev)
{
	mdp_super_t *sb;
	struct md_rdev *rdev2;
	int next_spare = mddev->raid_disks;


	/* make rdev->sb match mddev data..
	 *
	 * 1/ zero out disks
	 * 2/ Add info for each disk, keeping track of highest desc_nr (next_spare);
	 * 3/ any empty disks < next_spare become removed
	 *
	 * disks[0] gets initialised to REMOVED because
	 * we cannot be sure from other fields if it has
	 * been initialised or not.
	 */
	int i;
	int active=0, working=0,failed=0,spare=0,nr_disks=0;

	rdev->sb_size = MD_SB_BYTES;

	sb = page_address(rdev->sb_page);

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

	sb->md_magic = MD_SB_MAGIC;
	sb->major_version = mddev->major_version;
	sb->patch_version = mddev->patch_version;
	sb->gvalid_words  = 0; /* ignored */
	memcpy(&sb->set_uuid0, mddev->uuid+0, 4);
	memcpy(&sb->set_uuid1, mddev->uuid+4, 4);
	memcpy(&sb->set_uuid2, mddev->uuid+8, 4);
	memcpy(&sb->set_uuid3, mddev->uuid+12,4);

	sb->ctime = mddev->ctime;
	sb->level = mddev->level;
	sb->size = mddev->dev_sectors / 2;
	sb->raid_disks = mddev->raid_disks;
	sb->md_minor = mddev->md_minor;
	sb->not_persistent = 0;
	sb->utime = mddev->utime;
	sb->state = 0;
	sb->events_hi = (mddev->events>>32);
	sb->events_lo = (u32)mddev->events;

	if (mddev->reshape_position == MaxSector)
		sb->minor_version = 90;
	else {
		sb->minor_version = 91;
		sb->reshape_position = mddev->reshape_position;
		sb->new_level = mddev->new_level;
		sb->delta_disks = mddev->delta_disks;
		sb->new_layout = mddev->new_layout;
		sb->new_chunk = mddev->new_chunk_sectors << 9;
	}
	mddev->minor_version = sb->minor_version;
	if (mddev->in_sync)
	{
		sb->recovery_cp = mddev->recovery_cp;
		sb->cp_events_hi = (mddev->events>>32);
		sb->cp_events_lo = (u32)mddev->events;
		if (mddev->recovery_cp == MaxSector)
			sb->state = (1<< MD_SB_CLEAN);
	} else
		sb->recovery_cp = 0;

	sb->layout = mddev->layout;
	sb->chunk_size = mddev->chunk_sectors << 9;

	if (mddev->bitmap && mddev->bitmap_info.file == NULL)
		sb->state |= (1<<MD_SB_BITMAP_PRESENT);

	sb->disks[0].state = (1<<MD_DISK_REMOVED);
	rdev_for_each(rdev2, mddev) {
		mdp_disk_t *d;
		int desc_nr;
		int is_active = test_bit(In_sync, &rdev2->flags);

		if (rdev2->raid_disk >= 0 &&
		    sb->minor_version >= 91)
			/* we have nowhere to store the recovery_offset,
			 * but if it is not below the reshape_position,
			 * we can piggy-back on that.
			 */
			is_active = 1;
		if (rdev2->raid_disk < 0 ||
		    test_bit(Faulty, &rdev2->flags))
			is_active = 0;
		if (is_active)
			desc_nr = rdev2->raid_disk;
		else
			desc_nr = next_spare++;
		rdev2->desc_nr = desc_nr;
		d = &sb->disks[rdev2->desc_nr];
		nr_disks++;
		d->number = rdev2->desc_nr;
		d->major = MAJOR(rdev2->bdev->bd_dev);
		d->minor = MINOR(rdev2->bdev->bd_dev);
		if (is_active)
			d->raid_disk = rdev2->raid_disk;
		else
			d->raid_disk = rdev2->desc_nr; /* compatibility */
		if (test_bit(Faulty, &rdev2->flags))
			d->state = (1<<MD_DISK_FAULTY);
		else if (is_active) {
			d->state = (1<<MD_DISK_ACTIVE);
			if (test_bit(In_sync, &rdev2->flags))
				d->state |= (1<<MD_DISK_SYNC);
			active++;
			working++;
		} else {
			d->state = 0;
			spare++;
			working++;
		}
		if (test_bit(WriteMostly, &rdev2->flags))
			d->state |= (1<<MD_DISK_WRITEMOSTLY);
	}
	/* now set the "removed" and "faulty" bits on any missing devices */
	for (i=0 ; i < mddev->raid_disks ; i++) {
		mdp_disk_t *d = &sb->disks[i];
		if (d->state == 0 && d->number == 0) {
			d->number = i;
			d->raid_disk = i;
			d->state = (1<<MD_DISK_REMOVED);
			d->state |= (1<<MD_DISK_FAULTY);
			failed++;
		}
	}
	sb->nr_disks = nr_disks;
	sb->active_disks = active;
	sb->working_disks = working;
	sb->failed_disks = failed;
	sb->spare_disks = spare;

	sb->this_disk = sb->disks[rdev->desc_nr];
	sb->sb_csum = calc_sb_csum(sb);
}

/*
 * rdev_size_change for 0.90.0
 */
static unsigned long long
super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
{
	if (num_sectors && num_sectors < rdev->mddev->dev_sectors)
		return 0; /* component must fit device */
	if (rdev->mddev->bitmap_info.offset)
		return 0; /* can't move bitmap */
	rdev->sb_start = calc_dev_sboffset(rdev);
	if (!num_sectors || num_sectors > rdev->sb_start)
		num_sectors = rdev->sb_start;
	/* Limit to 4TB as metadata cannot record more than that.
	 * 4TB == 2^32 KB, or 2*2^32 sectors.
	 */
	if (num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1)
		num_sectors = (2ULL << 32) - 2;
	md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
		       rdev->sb_page);
	md_super_wait(rdev->mddev);
	return num_sectors;
}

static int
super_90_allow_new_offset(struct md_rdev *rdev, unsigned long long new_offset)
{
	/* non-zero offset changes not possible with v0.90 */
	return new_offset == 0;
}

/*
 * version 1 superblock
 */

static __le32 calc_sb_1_csum(struct mdp_superblock_1 * sb)
{
	__le32 disk_csum;
	u32 csum;
	unsigned long long newcsum;
	int size = 256 + le32_to_cpu(sb->max_dev)*2;
	__le32 *isuper = (__le32*)sb;

	disk_csum = sb->sb_csum;
	sb->sb_csum = 0;
	newcsum = 0;
	for (; size >= 4; size -= 4)
		newcsum += le32_to_cpu(*isuper++);

	if (size == 2)
		newcsum += le16_to_cpu(*(__le16*) isuper);

	csum = (newcsum & 0xffffffff) + (newcsum >> 32);
	sb->sb_csum = disk_csum;
	return cpu_to_le32(csum);
}

static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors,
			    int acknowledged);
static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_version)
{
	struct mdp_superblock_1 *sb;
	int ret;
	sector_t sb_start;
	sector_t sectors;
	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
	int bmask;

	/*
	 * Calculate the position of the superblock in 512byte sectors.
	 * It is always aligned to a 4K boundary and
	 * depeding on minor_version, it can be:
	 * 0: At least 8K, but less than 12K, from end of device
	 * 1: At start of device
	 * 2: 4K from start of device.
	 */
	switch(minor_version) {
	case 0:
		sb_start = i_size_read(rdev->bdev->bd_inode) >> 9;
		sb_start -= 8*2;
		sb_start &= ~(sector_t)(4*2-1);
		break;
	case 1:
		sb_start = 0;
		break;
	case 2:
		sb_start = 8;
		break;
	default:
		return -EINVAL;
	}
	rdev->sb_start = sb_start;

	/* superblock is rarely larger than 1K, but it can be larger,
	 * and it is safe to read 4k, so we do that
	 */
	ret = read_disk_sb(rdev, 4096);
	if (ret) return ret;


	sb = page_address(rdev->sb_page);

	if (sb->magic != cpu_to_le32(MD_SB_MAGIC) ||
	    sb->major_version != cpu_to_le32(1) ||
	    le32_to_cpu(sb->max_dev) > (4096-256)/2 ||
	    le64_to_cpu(sb->super_offset) != rdev->sb_start ||
	    (le32_to_cpu(sb->feature_map) & ~MD_FEATURE_ALL) != 0)
		return -EINVAL;

	if (calc_sb_1_csum(sb) != sb->sb_csum) {
		printk("md: invalid superblock checksum on %s\n",
			bdevname(rdev->bdev,b));
		return -EINVAL;
	}
	if (le64_to_cpu(sb->data_size) < 10) {
		printk("md: data_size too small on %s\n",
		       bdevname(rdev->bdev,b));
		return -EINVAL;
	}
	if (sb->pad0 ||
	    sb->pad3[0] ||
	    memcmp(sb->pad3, sb->pad3+1, sizeof(sb->pad3) - sizeof(sb->pad3[1])))
		/* Some padding is non-zero, might be a new feature */
		return -EINVAL;

	rdev->preferred_minor = 0xffff;
	rdev->data_offset = le64_to_cpu(sb->data_offset);
	rdev->new_data_offset = rdev->data_offset;
	if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE) &&
	    (le32_to_cpu(sb->feature_map) & MD_FEATURE_NEW_OFFSET))
		rdev->new_data_offset += (s32)le32_to_cpu(sb->new_offset);
	atomic_set(&rdev->corrected_errors, le32_to_cpu(sb->cnt_corrected_read));

	rdev->sb_size = le32_to_cpu(sb->max_dev) * 2 + 256;
	bmask = queue_logical_block_size(rdev->bdev->bd_disk->queue)-1;
	if (rdev->sb_size & bmask)
		rdev->sb_size = (rdev->sb_size | bmask) + 1;

	if (minor_version
	    && rdev->data_offset < sb_start + (rdev->sb_size/512))
		return -EINVAL;
	if (minor_version
	    && rdev->new_data_offset < sb_start + (rdev->sb_size/512))
		return -EINVAL;

	if (sb->level == cpu_to_le32(LEVEL_MULTIPATH))
		rdev->desc_nr = -1;
	else
		rdev->desc_nr = le32_to_cpu(sb->dev_number);

	if (!rdev->bb_page) {
		rdev->bb_page = alloc_page(GFP_KERNEL);
		if (!rdev->bb_page)
			return -ENOMEM;
	}
	if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BAD_BLOCKS) &&
	    rdev->badblocks.count == 0) {
		/* need to load the bad block list.
		 * Currently we limit it to one page.
		 */
		s32 offset;
		sector_t bb_sector;
		u64 *bbp;
		int i;
		int sectors = le16_to_cpu(sb->bblog_size);
		if (sectors > (PAGE_SIZE / 512))
			return -EINVAL;
		offset = le32_to_cpu(sb->bblog_offset);
		if (offset == 0)
			return -EINVAL;
		bb_sector = (long long)offset;
		if (!sync_page_io(rdev, bb_sector, sectors << 9,
				  rdev->bb_page, READ, true))
			return -EIO;
		bbp = (u64 *)page_address(rdev->bb_page);
		rdev->badblocks.shift = sb->bblog_shift;
		for (i = 0 ; i < (sectors << (9-3)) ; i++, bbp++) {
			u64 bb = le64_to_cpu(*bbp);
			int count = bb & (0x3ff);
			u64 sector = bb >> 10;
			sector <<= sb->bblog_shift;
			count <<= sb->bblog_shift;
			if (bb + 1 == 0)
				break;
			if (md_set_badblocks(&rdev->badblocks,
					     sector, count, 1) == 0)
				return -EINVAL;
		}
	} else if (sb->bblog_offset != 0)
		rdev->badblocks.shift = 0;

	if (!refdev) {
		ret = 1;
	} else {
		__u64 ev1, ev2;
		struct mdp_superblock_1 *refsb = page_address(refdev->sb_page);

		if (memcmp(sb->set_uuid, refsb->set_uuid, 16) != 0 ||
		    sb->level != refsb->level ||
		    sb->layout != refsb->layout ||
		    sb->chunksize != refsb->chunksize) {
			printk(KERN_WARNING "md: %s has strangely different"
				" superblock to %s\n",
				bdevname(rdev->bdev,b),
				bdevname(refdev->bdev,b2));
			return -EINVAL;
		}
		ev1 = le64_to_cpu(sb->events);
		ev2 = le64_to_cpu(refsb->events);

		if (ev1 > ev2)
			ret = 1;
		else
			ret = 0;
	}
	if (minor_version) {
		sectors = (i_size_read(rdev->bdev->bd_inode) >> 9);
		sectors -= rdev->data_offset;
	} else
		sectors = rdev->sb_start;
	if (sectors < le64_to_cpu(sb->data_size))
		return -EINVAL;
	rdev->sectors = le64_to_cpu(sb->data_size);
	return ret;
}

static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
{
	struct mdp_superblock_1 *sb = page_address(rdev->sb_page);
	__u64 ev1 = le64_to_cpu(sb->events);

	rdev->raid_disk = -1;
	clear_bit(Faulty, &rdev->flags);
	clear_bit(In_sync, &rdev->flags);
	clear_bit(Bitmap_sync, &rdev->flags);
	clear_bit(WriteMostly, &rdev->flags);

	if (mddev->raid_disks == 0) {
		mddev->major_version = 1;
		mddev->patch_version = 0;
		mddev->external = 0;
		mddev->chunk_sectors = le32_to_cpu(sb->chunksize);
		mddev->ctime = le64_to_cpu(sb->ctime) & ((1ULL << 32)-1);
		mddev->utime = le64_to_cpu(sb->utime) & ((1ULL << 32)-1);
		mddev->level = le32_to_cpu(sb->level);
		mddev->clevel[0] = 0;
		mddev->layout = le32_to_cpu(sb->layout);
		mddev->raid_disks = le32_to_cpu(sb->raid_disks);
		mddev->dev_sectors = le64_to_cpu(sb->size);
		mddev->events = ev1;
		mddev->bitmap_info.offset = 0;
		mddev->bitmap_info.space = 0;
		/* Default location for bitmap is 1K after superblock
		 * using 3K - total of 4K
		 */
		mddev->bitmap_info.default_offset = 1024 >> 9;
		mddev->bitmap_info.default_space = (4096-1024) >> 9;
		mddev->reshape_backwards = 0;

		mddev->recovery_cp = le64_to_cpu(sb->resync_offset);
		memcpy(mddev->uuid, sb->set_uuid, 16);

		mddev->max_disks =  (4096-256)/2;

		if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET) &&
		    mddev->bitmap_info.file == NULL) {
			mddev->bitmap_info.offset =
				(__s32)le32_to_cpu(sb->bitmap_offset);
			/* Metadata doesn't record how much space is available.
			 * For 1.0, we assume we can use up to the superblock
			 * if before, else to 4K beyond superblock.
			 * For others, assume no change is possible.
			 */
			if (mddev->minor_version > 0)
				mddev->bitmap_info.space = 0;
			else if (mddev->bitmap_info.offset > 0)
				mddev->bitmap_info.space =
					8 - mddev->bitmap_info.offset;
			else
				mddev->bitmap_info.space =
					-mddev->bitmap_info.offset;
		}

		if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) {
			mddev->reshape_position = le64_to_cpu(sb->reshape_position);
			mddev->delta_disks = le32_to_cpu(sb->delta_disks);
			mddev->new_level = le32_to_cpu(sb->new_level);
			mddev->new_layout = le32_to_cpu(sb->new_layout);
			mddev->new_chunk_sectors = le32_to_cpu(sb->new_chunk);
			if (mddev->delta_disks < 0 ||
			    (mddev->delta_disks == 0 &&
			     (le32_to_cpu(sb->feature_map)
			      & MD_FEATURE_RESHAPE_BACKWARDS)))
				mddev->reshape_backwards = 1;
		} else {
			mddev->reshape_position = MaxSector;
			mddev->delta_disks = 0;
			mddev->new_level = mddev->level;
			mddev->new_layout = mddev->layout;
			mddev->new_chunk_sectors = mddev->chunk_sectors;
		}

	} else if (mddev->pers == NULL) {
		/* Insist of good event counter while assembling, except for
		 * spares (which don't need an event count) */
		++ev1;
		if (rdev->desc_nr >= 0 &&
		    rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
		    le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < 0xfffe)
			if (ev1 < mddev->events)
				return -EINVAL;
	} else if (mddev->bitmap) {
		/* If adding to array with a bitmap, then we can accept an
		 * older device, but not too old.
		 */
		if (ev1 < mddev->bitmap->events_cleared)
			return 0;
		if (ev1 < mddev->events)
			set_bit(Bitmap_sync, &rdev->flags);
	} else {
		if (ev1 < mddev->events)
			/* just a hot-add of a new device, leave raid_disk at -1 */
			return 0;
	}
	if (mddev->level != LEVEL_MULTIPATH) {
		int role;
		if (rdev->desc_nr < 0 ||
		    rdev->desc_nr >= le32_to_cpu(sb->max_dev)) {
			role = 0xffff;
			rdev->desc_nr = -1;
		} else
			role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
		switch(role) {
		case 0xffff: /* spare */
			break;
		case 0xfffe: /* faulty */
			set_bit(Faulty, &rdev->flags);
			break;
		default:
			rdev->saved_raid_disk = role;
			if ((le32_to_cpu(sb->feature_map) &
			     MD_FEATURE_RECOVERY_OFFSET)) {
				rdev->recovery_offset = le64_to_cpu(sb->recovery_offset);
				if (!(le32_to_cpu(sb->feature_map) &
				      MD_FEATURE_RECOVERY_BITMAP))
					rdev->saved_raid_disk = -1;
			} else
				set_bit(In_sync, &rdev->flags);
			rdev->raid_disk = role;
			break;
		}
		if (sb->devflags & WriteMostly1)
			set_bit(WriteMostly, &rdev->flags);
		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT)
			set_bit(Replacement, &rdev->flags);
	} else /* MULTIPATH are always insync */
		set_bit(In_sync, &rdev->flags);

	return 0;
}

static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev)
{
	struct mdp_superblock_1 *sb;
	struct md_rdev *rdev2;
	int max_dev, i;
	/* make rdev->sb match mddev and rdev data. */

	sb = page_address(rdev->sb_page);

	sb->feature_map = 0;
	sb->pad0 = 0;
	sb->recovery_offset = cpu_to_le64(0);
	memset(sb->pad3, 0, sizeof(sb->pad3));

	sb->utime = cpu_to_le64((__u64)mddev->utime);
	sb->events = cpu_to_le64(mddev->events);
	if (mddev->in_sync)
		sb->resync_offset = cpu_to_le64(mddev->recovery_cp);
	else
		sb->resync_offset = cpu_to_le64(0);

	sb->cnt_corrected_read = cpu_to_le32(atomic_read(&rdev->corrected_errors));

	sb->raid_disks = cpu_to_le32(mddev->raid_disks);
	sb->size = cpu_to_le64(mddev->dev_sectors);
	sb->chunksize = cpu_to_le32(mddev->chunk_sectors);
	sb->level = cpu_to_le32(mddev->level);
	sb->layout = cpu_to_le32(mddev->layout);

	if (test_bit(WriteMostly, &rdev->flags))
		sb->devflags |= WriteMostly1;
	else
		sb->devflags &= ~WriteMostly1;
	sb->data_offset = cpu_to_le64(rdev->data_offset);
	sb->data_size = cpu_to_le64(rdev->sectors);

	if (mddev->bitmap && mddev->bitmap_info.file == NULL) {
		sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_info.offset);
		sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
	}

	if (rdev->raid_disk >= 0 &&
	    !test_bit(In_sync, &rdev->flags)) {
		sb->feature_map |=
			cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET);
		sb->recovery_offset =
			cpu_to_le64(rdev->recovery_offset);
		if (rdev->saved_raid_disk >= 0 && mddev->bitmap)
			sb->feature_map |=
				cpu_to_le32(MD_FEATURE_RECOVERY_BITMAP);
	}
	if (test_bit(Replacement, &rdev->flags))
		sb->feature_map |=
			cpu_to_le32(MD_FEATURE_REPLACEMENT);

	if (mddev->reshape_position != MaxSector) {
		sb->feature_map |= cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE);
		sb->reshape_position = cpu_to_le64(mddev->reshape_position);
		sb->new_layout = cpu_to_le32(mddev->new_layout);
		sb->delta_disks = cpu_to_le32(mddev->delta_disks);
		sb->new_level = cpu_to_le32(mddev->new_level);
		sb->new_chunk = cpu_to_le32(mddev->new_chunk_sectors);
		if (mddev->delta_disks == 0 &&
		    mddev->reshape_backwards)
			sb->feature_map
				|= cpu_to_le32(MD_FEATURE_RESHAPE_BACKWARDS);
		if (rdev->new_data_offset != rdev->data_offset) {
			sb->feature_map
				|= cpu_to_le32(MD_FEATURE_NEW_OFFSET);
			sb->new_offset = cpu_to_le32((__u32)(rdev->new_data_offset
							     - rdev->data_offset));
		}
	}

	if (rdev->badblocks.count == 0)
		/* Nothing to do for bad blocks*/ ;
	else if (sb->bblog_offset == 0)
		/* Cannot record bad blocks on this device */
		md_error(mddev, rdev);
	else {
		struct badblocks *bb = &rdev->badblocks;
		u64 *bbp = (u64 *)page_address(rdev->bb_page);
		u64 *p = bb->page;
		sb->feature_map |= cpu_to_le32(MD_FEATURE_BAD_BLOCKS);
		if (bb->changed) {
			unsigned seq;

retry:
			seq = read_seqbegin(&bb->lock);

			memset(bbp, 0xff, PAGE_SIZE);

			for (i = 0 ; i < bb->count ; i++) {
				u64 internal_bb = p[i];
				u64 store_bb = ((BB_OFFSET(internal_bb) << 10)
						| BB_LEN(internal_bb));
				bbp[i] = cpu_to_le64(store_bb);
			}
			bb->changed = 0;
			if (read_seqretry(&bb->lock, seq))
				goto retry;

			bb->sector = (rdev->sb_start +
				      (int)le32_to_cpu(sb->bblog_offset));
			bb->size = le16_to_cpu(sb->bblog_size);
		}
	}

	max_dev = 0;
	rdev_for_each(rdev2, mddev)
		if (rdev2->desc_nr+1 > max_dev)
			max_dev = rdev2->desc_nr+1;

	if (max_dev > le32_to_cpu(sb->max_dev)) {
		int bmask;
		sb->max_dev = cpu_to_le32(max_dev);
		rdev->sb_size = max_dev * 2 + 256;
		bmask = queue_logical_block_size(rdev->bdev->bd_disk->queue)-1;
		if (rdev->sb_size & bmask)
			rdev->sb_size = (rdev->sb_size | bmask) + 1;
	} else
		max_dev = le32_to_cpu(sb->max_dev);

	for (i=0; i<max_dev;i++)
		sb->dev_roles[i] = cpu_to_le16(0xfffe);
	
	rdev_for_each(rdev2, mddev) {
		i = rdev2->desc_nr;
		if (test_bit(Faulty, &rdev2->flags))
			sb->dev_roles[i] = cpu_to_le16(0xfffe);
		else if (test_bit(In_sync, &rdev2->flags))
			sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
		else if (rdev2->raid_disk >= 0)
			sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
		else
			sb->dev_roles[i] = cpu_to_le16(0xffff);
	}

	sb->sb_csum = calc_sb_1_csum(sb);
}

static unsigned long long
super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
{
	struct mdp_superblock_1 *sb;
	sector_t max_sectors;
	if (num_sectors && num_sectors < rdev->mddev->dev_sectors)
		return 0; /* component must fit device */
	if (rdev->data_offset != rdev->new_data_offset)
		return 0; /* too confusing */
	if (rdev->sb_start < rdev->data_offset) {
		/* minor versions 1 and 2; superblock before data */
		max_sectors = i_size_read(rdev->bdev->bd_inode) >> 9;
		max_sectors -= rdev->data_offset;
		if (!num_sectors || num_sectors > max_sectors)
			num_sectors = max_sectors;
	} else if (rdev->mddev->bitmap_info.offset) {
		/* minor version 0 with bitmap we can't move */
		return 0;
	} else {
		/* minor version 0; superblock after data */
		sector_t sb_start;
		sb_start = (i_size_read(rdev->bdev->bd_inode) >> 9) - 8*2;
		sb_start &= ~(sector_t)(4*2 - 1);
		max_sectors = rdev->sectors + sb_start - rdev->sb_start;
		if (!num_sectors || num_sectors > max_sectors)
			num_sectors = max_sectors;
		rdev->sb_start = sb_start;
	}
	sb = page_address(rdev->sb_page);
	sb->data_size = cpu_to_le64(num_sectors);
	sb->super_offset = rdev->sb_start;
	sb->sb_csum = calc_sb_1_csum(sb);
	md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
		       rdev->sb_page);
	md_super_wait(rdev->mddev);
	return num_sectors;

}

static int
super_1_allow_new_offset(struct md_rdev *rdev,
			 unsigned long long new_offset)
{
	/* All necessary checks on new >= old have been done */
	struct bitmap *bitmap;
	if (new_offset >= rdev->data_offset)
		return 1;

	/* with 1.0 metadata, there is no metadata to tread on
	 * so we can always move back */
	if (rdev->mddev->minor_version == 0)
		return 1;

	/* otherwise we must be sure not to step on
	 * any metadata, so stay:
	 * 36K beyond start of superblock
	 * beyond end of badblocks
	 * beyond write-intent bitmap
	 */
	if (rdev->sb_start + (32+4)*2 > new_offset)
		return 0;
	bitmap = rdev->mddev->bitmap;
	if (bitmap && !rdev->mddev->bitmap_info.file &&
	    rdev->sb_start + rdev->mddev->bitmap_info.offset +
	    bitmap->storage.file_pages * (PAGE_SIZE>>9) > new_offset)
		return 0;
	if (rdev->badblocks.sector + rdev->badblocks.size > new_offset)
		return 0;

	return 1;
}

static struct super_type super_types[] = {
	[0] = {
		.name	= "0.90.0",
		.owner	= THIS_MODULE,
		.load_super	    = super_90_load,
		.validate_super	    = super_90_validate,
		.sync_super	    = super_90_sync,
		.rdev_size_change   = super_90_rdev_size_change,
		.allow_new_offset   = super_90_allow_new_offset,
	},
	[1] = {
		.name	= "md-1",
		.owner	= THIS_MODULE,
		.load_super	    = super_1_load,
		.validate_super	    = super_1_validate,
		.sync_super	    = super_1_sync,
		.rdev_size_change   = super_1_rdev_size_change,
		.allow_new_offset   = super_1_allow_new_offset,
	},
};

static void sync_super(struct mddev *mddev, struct md_rdev *rdev)
{
	if (mddev->sync_super) {
		mddev->sync_super(mddev, rdev);
		return;
	}

	BUG_ON(mddev->major_version >= ARRAY_SIZE(super_types));

	super_types[mddev->major_version].sync_super(mddev, rdev);
}

static int match_mddev_units(struct mddev *mddev1, struct mddev *mddev2)
{
	struct md_rdev *rdev, *rdev2;

	rcu_read_lock();
	rdev_for_each_rcu(rdev, mddev1)
		rdev_for_each_rcu(rdev2, mddev2)
			if (rdev->bdev->bd_contains ==
			    rdev2->bdev->bd_contains) {
				rcu_read_unlock();
				return 1;
			}
	rcu_read_unlock();
	return 0;
}

static LIST_HEAD(pending_raid_disks);

/*
 * Try to register data integrity profile for an mddev
 *
 * This is called when an array is started and after a disk has been kicked
 * from the array. It only succeeds if all working and active component devices
 * are integrity capable with matching profiles.
 */
int md_integrity_register(struct mddev *mddev)
{
	struct md_rdev *rdev, *reference = NULL;

	if (list_empty(&mddev->disks))
		return 0; /* nothing to do */
	if (!mddev->gendisk || blk_get_integrity(mddev->gendisk))
		return 0; /* shouldn't register, or already is */
	rdev_for_each(rdev, mddev) {
		/* skip spares and non-functional disks */
		if (test_bit(Faulty, &rdev->flags))
			continue;
		if (rdev->raid_disk < 0)
			continue;
		if (!reference) {
			/* Use the first rdev as the reference */
			reference = rdev;
			continue;
		}
		/* does this rdev's profile match the reference profile? */
		if (blk_integrity_compare(reference->bdev->bd_disk,
				rdev->bdev->bd_disk) < 0)
			return -EINVAL;
	}
	if (!reference || !bdev_get_integrity(reference->bdev))
		return 0;
	/*
	 * All component devices are integrity capable and have matching
	 * profiles, register the common profile for the md device.
	 */
	if (blk_integrity_register(mddev->gendisk,
			bdev_get_integrity(reference->bdev)) != 0) {
		printk(KERN_ERR "md: failed to register integrity for %s\n",
			mdname(mddev));
		return -EINVAL;
	}
	printk(KERN_NOTICE "md: data integrity enabled on %s\n", mdname(mddev));
	if (bioset_integrity_create(mddev->bio_set, BIO_POOL_SIZE)) {
		printk(KERN_ERR "md: failed to create integrity pool for %s\n",
		       mdname(mddev));
		return -EINVAL;
	}
	return 0;
}
EXPORT_SYMBOL(md_integrity_register);

/* Disable data integrity if non-capable/non-matching disk is being added */
void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
{
	struct blk_integrity *bi_rdev;
	struct blk_integrity *bi_mddev;

	if (!mddev->gendisk)
		return;

	bi_rdev = bdev_get_integrity(rdev->bdev);
	bi_mddev = blk_get_integrity(mddev->gendisk);

	if (!bi_mddev) /* nothing to do */
		return;
	if (rdev->raid_disk < 0) /* skip spares */
		return;
	if (bi_rdev && blk_integrity_compare(mddev->gendisk,
					     rdev->bdev->bd_disk) >= 0)
		return;
	printk(KERN_NOTICE "disabling data integrity on %s\n", mdname(mddev));
	blk_integrity_unregister(mddev->gendisk);
}
EXPORT_SYMBOL(md_integrity_add_rdev);

static int bind_rdev_to_array(struct md_rdev * rdev, struct mddev * mddev)
{
	char b[BDEVNAME_SIZE];
	struct kobject *ko;
	char *s;
	int err;

	if (rdev->mddev) {
		MD_BUG();
		return -EINVAL;
	}

	/* prevent duplicates */
	if (find_rdev(mddev, rdev->bdev->bd_dev))
		return -EEXIST;

	/* make sure rdev->sectors exceeds mddev->dev_sectors */
	if (rdev->sectors && (mddev->dev_sectors == 0 ||
			rdev->sectors < mddev->dev_sectors)) {
		if (mddev->pers) {
			/* Cannot change size, so fail
			 * If mddev->level <= 0, then we don't care
			 * about aligning sizes (e.g. linear)
			 */
			if (mddev->level > 0)
				return -ENOSPC;
		} else
			mddev->dev_sectors = rdev->sectors;
	}

	/* Verify rdev->desc_nr is unique.
	 * If it is -1, assign a free number, else
	 * check number is not in use
	 */
	if (rdev->desc_nr < 0) {
		int choice = 0;
		if (mddev->pers) choice = mddev->raid_disks;
		while (find_rdev_nr(mddev, choice))
			choice++;
		rdev->desc_nr = choice;
	} else {
		if (find_rdev_nr(mddev, rdev->desc_nr))
			return -EBUSY;
	}
	if (mddev->max_disks && rdev->desc_nr >= mddev->max_disks) {
		printk(KERN_WARNING "md: %s: array is limited to %d devices\n",
		       mdname(mddev), mddev->max_disks);
		return -EBUSY;
	}
	bdevname(rdev->bdev,b);
	while ( (s=strchr(b, '/')) != NULL)
		*s = '!';

	rdev->mddev = mddev;
	printk(KERN_INFO "md: bind<%s>\n", b);

	if ((err = kobject_add(&rdev->kobj, &mddev->kobj, "dev-%s", b)))
		goto fail;

	ko = &part_to_dev(rdev->bdev->bd_part)->kobj;
	if (sysfs_create_link(&rdev->kobj, ko, "block"))
		/* failure here is OK */;
	rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state");

	list_add_rcu(&rdev->same_set, &mddev->disks);
	bd_link_disk_holder(rdev->bdev, mddev->gendisk);

	/* May as well allow recovery to be retried once */
	mddev->recovery_disabled++;

	return 0;

 fail:
	printk(KERN_WARNING "md: failed to register dev-%s for %s\n",
	       b, mdname(mddev));
	return err;
}

static void md_delayed_delete(struct work_struct *ws)
{
	struct md_rdev *rdev = container_of(ws, struct md_rdev, del_work);
	kobject_del(&rdev->kobj);
	kobject_put(&rdev->kobj);
}

static void unbind_rdev_from_array(struct md_rdev * rdev)
{
	char b[BDEVNAME_SIZE];
	if (!rdev->mddev) {
		MD_BUG();
		return;
	}
	bd_unlink_disk_holder(rdev->bdev, rdev->mddev->gendisk);
	list_del_rcu(&rdev->same_set);
	printk(KERN_INFO "md: unbind<%s>\n", bdevname(rdev->bdev,b));
	rdev->mddev = NULL;
	sysfs_remove_link(&rdev->kobj, "block");
	sysfs_put(rdev->sysfs_state);
	rdev->sysfs_state = NULL;
	rdev->badblocks.count = 0;
	/* We need to delay this, otherwise we can deadlock when
	 * writing to 'remove' to "dev/state".  We also need
	 * to delay it due to rcu usage.
	 */
	synchronize_rcu();
	INIT_WORK(&rdev->del_work, md_delayed_delete);
	kobject_get(&rdev->kobj);
	queue_work(md_misc_wq, &rdev->del_work);
}

/*
 * prevent the device from being mounted, repartitioned or
 * otherwise reused by a RAID array (or any other kernel
 * subsystem), by bd_claiming the device.
 */
static int lock_rdev(struct md_rdev *rdev, dev_t dev, int shared)
{
	int err = 0;
	struct block_device *bdev;
	char b[BDEVNAME_SIZE];

	bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
				 shared ? (struct md_rdev *)lock_rdev : rdev);
	if (IS_ERR(bdev)) {
		printk(KERN_ERR "md: could not open %s.\n",
			__bdevname(dev, b));
		return PTR_ERR(bdev);
	}
	rdev->bdev = bdev;
	return err;
}

static void unlock_rdev(struct md_rdev *rdev)
{
	struct block_device *bdev = rdev->bdev;
	rdev->bdev = NULL;
	if (!bdev)
		MD_BUG();
	blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}

void md_autodetect_dev(dev_t dev);

static void export_rdev(struct md_rdev * rdev)
{
	char b[BDEVNAME_SIZE];
	printk(KERN_INFO "md: export_rdev(%s)\n",
		bdevname(rdev->bdev,b));
	if (rdev->mddev)
		MD_BUG();
	md_rdev_clear(rdev);
#ifndef MODULE
	if (test_bit(AutoDetected, &rdev->flags))
		md_autodetect_dev(rdev->bdev->bd_dev);
#endif
	unlock_rdev(rdev);
	kobject_put(&rdev->kobj);
}

static void kick_rdev_from_array(struct md_rdev * rdev)
{
	unbind_rdev_from_array(rdev);
	export_rdev(rdev);
}

static void export_array(struct mddev *mddev)
{
	struct md_rdev *rdev, *tmp;

	rdev_for_each_safe(rdev, tmp, mddev) {
		if (!rdev->mddev) {
			MD_BUG();
			continue;
		}
		kick_rdev_from_array(rdev);
	}
	if (!list_empty(&mddev->disks))
		MD_BUG();
	mddev->raid_disks = 0;
	mddev->major_version = 0;
}

static void print_desc(mdp_disk_t *desc)
{
	printk(" DISK<N:%d,(%d,%d),R:%d,S:%d>\n", desc->number,
		desc->major,desc->minor,desc->raid_disk,desc->state);
}

static void print_sb_90(mdp_super_t *sb)
{
	int i;

	printk(KERN_INFO 
		"md:  SB: (V:%d.%d.%d) ID:<%08x.%08x.%08x.%08x> CT:%08x\n",
		sb->major_version, sb->minor_version, sb->patch_version,
		sb->set_uuid0, sb->set_uuid1, sb->set_uuid2, sb->set_uuid3,
		sb->ctime);
	printk(KERN_INFO "md:     L%d S%08d ND:%d RD:%d md%d LO:%d CS:%d\n",
		sb->level, sb->size, sb->nr_disks, sb->raid_disks,
		sb->md_minor, sb->layout, sb->chunk_size);
	printk(KERN_INFO "md:     UT:%08x ST:%d AD:%d WD:%d"
		" FD:%d SD:%d CSUM:%08x E:%08lx\n",
		sb->utime, sb->state, sb->active_disks, sb->working_disks,
		sb->failed_disks, sb->spare_disks,
		sb->sb_csum, (unsigned long)sb->events_lo);

	printk(KERN_INFO);
	for (i = 0; i < MD_SB_DISKS; i++) {
		mdp_disk_t *desc;

		desc = sb->disks + i;
		if (desc->number || desc->major || desc->minor ||
		    desc->raid_disk || (desc->state && (desc->state != 4))) {
			printk("     D %2d: ", i);
			print_desc(desc);
		}
	}
	printk(KERN_INFO "md:     THIS: ");
	print_desc(&sb->this_disk);
}

static void print_sb_1(struct mdp_superblock_1 *sb)
{
	__u8 *uuid;

	uuid = sb->set_uuid;
	printk(KERN_INFO
	       "md:  SB: (V:%u) (F:0x%08x) Array-ID:<%pU>\n"
	       "md:    Name: \"%s\" CT:%llu\n",
		le32_to_cpu(sb->major_version),
		le32_to_cpu(sb->feature_map),
		uuid,
		sb->set_name,
		(unsigned long long)le64_to_cpu(sb->ctime)
		       & MD_SUPERBLOCK_1_TIME_SEC_MASK);

	uuid = sb->device_uuid;
	printk(KERN_INFO
	       "md:       L%u SZ%llu RD:%u LO:%u CS:%u DO:%llu DS:%llu SO:%llu"
			" RO:%llu\n"
	       "md:     Dev:%08x UUID: %pU\n"
	       "md:       (F:0x%08x) UT:%llu Events:%llu ResyncOffset:%llu CSUM:0x%08x\n"
	       "md:         (MaxDev:%u) \n",
		le32_to_cpu(sb->level),
		(unsigned long long)le64_to_cpu(sb->size),
		le32_to_cpu(sb->raid_disks),
		le32_to_cpu(sb->layout),
		le32_to_cpu(sb->chunksize),
		(unsigned long long)le64_to_cpu(sb->data_offset),
		(unsigned long long)le64_to_cpu(sb->data_size),
		(unsigned long long)le64_to_cpu(sb->super_offset),
		(unsigned long long)le64_to_cpu(sb->recovery_offset),
		le32_to_cpu(sb->dev_number),
		uuid,
		sb->devflags,
		(unsigned long long)le64_to_cpu(sb->utime) & MD_SUPERBLOCK_1_TIME_SEC_MASK,
		(unsigned long long)le64_to_cpu(sb->events),
		(unsigned long long)le64_to_cpu(sb->resync_offset),
		le32_to_cpu(sb->sb_csum),
		le32_to_cpu(sb->max_dev)
		);
}

static void print_rdev(struct md_rdev *rdev, int major_version)
{
	char b[BDEVNAME_SIZE];
	printk(KERN_INFO "md: rdev %s, Sect:%08llu F:%d S:%d DN:%u\n",
		bdevname(rdev->bdev, b), (unsigned long long)rdev->sectors,
	        test_bit(Faulty, &rdev->flags), test_bit(In_sync, &rdev->flags),
	        rdev->desc_nr);
	if (rdev->sb_loaded) {
		printk(KERN_INFO "md: rdev superblock (MJ:%d):\n", major_version);
		switch (major_version) {
		case 0:
			print_sb_90(page_address(rdev->sb_page));
			break;
		case 1:
			print_sb_1(page_address(rdev->sb_page));
			break;
		}
	} else
		printk(KERN_INFO "md: no rdev superblock!\n");
}

static void md_print_devices(void)
{
	struct list_head *tmp;
	struct md_rdev *rdev;
	struct mddev *mddev;
	char b[BDEVNAME_SIZE];

	printk("\n");
	printk("md:	**********************************\n");
	printk("md:	* <COMPLETE RAID STATE PRINTOUT> *\n");
	printk("md:	**********************************\n");
	for_each_mddev(mddev, tmp) {

		if (mddev->bitmap)
			bitmap_print_sb(mddev->bitmap);
		else
			printk("%s: ", mdname(mddev));
		rdev_for_each(rdev, mddev)
			printk("<%s>", bdevname(rdev->bdev,b));
		printk("\n");

		rdev_for_each(rdev, mddev)
			print_rdev(rdev, mddev->major_version);
	}
	printk("md:	**********************************\n");
	printk("\n");
}


static void sync_sbs(struct mddev * mddev, int nospares)
{
	/* Update each superblock (in-memory image), but
	 * if we are allowed to, skip spares which already
	 * have the right event counter, or have one earlier
	 * (which would mean they aren't being marked as dirty
	 * with the rest of the array)
	 */
	struct md_rdev *rdev;
	rdev_for_each(rdev, mddev) {
		if (rdev->sb_events == mddev->events ||
		    (nospares &&
		     rdev->raid_disk < 0 &&
		     rdev->sb_events+1 == mddev->events)) {
			/* Don't update this superblock */
			rdev->sb_loaded = 2;
		} else {
			sync_super(mddev, rdev);
			rdev->sb_loaded = 1;
		}
	}
}

static void md_update_sb(struct mddev * mddev, int force_change)
{
	struct md_rdev *rdev;
	int sync_req;
	int nospares = 0;
	int any_badblocks_changed = 0;

	if (mddev->ro) {
		if (force_change)
			set_bit(MD_CHANGE_DEVS, &mddev->flags);
		return;
	}
repeat:
	/* First make sure individual recovery_offsets are correct */
	rdev_for_each(rdev, mddev) {
		if (rdev->raid_disk >= 0 &&
		    mddev->delta_disks >= 0 &&
		    !test_bit(In_sync, &rdev->flags) &&
		    mddev->curr_resync_completed > rdev->recovery_offset)
				rdev->recovery_offset = mddev->curr_resync_completed;

	}	
	if (!mddev->persistent) {
		clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
		clear_bit(MD_CHANGE_DEVS, &mddev->flags);
		if (!mddev->external) {
			clear_bit(MD_CHANGE_PENDING, &mddev->flags);
			rdev_for_each(rdev, mddev) {
				if (rdev->badblocks.changed) {
					rdev->badblocks.changed = 0;
					md_ack_all_badblocks(&rdev->badblocks);
					md_error(mddev, rdev);
				}
				clear_bit(Blocked, &rdev->flags);
				clear_bit(BlockedBadBlocks, &rdev->flags);
				wake_up(&rdev->blocked_wait);
			}
		}
		wake_up(&mddev->sb_wait);
		return;
	}

	spin_lock_irq(&mddev->write_lock);

	mddev->utime = get_seconds();

	if (test_and_clear_bit(MD_CHANGE_DEVS, &mddev->flags))
		force_change = 1;
	if (test_and_clear_bit(MD_CHANGE_CLEAN, &mddev->flags))
		/* just a clean<-> dirty transition, possibly leave spares alone,
		 * though if events isn't the right even/odd, we will have to do
		 * spares after all
		 */
		nospares = 1;
	if (force_change)
		nospares = 0;
	if (mddev->degraded)
		/* If the array is degraded, then skipping spares is both
		 * dangerous and fairly pointless.
		 * Dangerous because a device that was removed from the array
		 * might have a event_count that still looks up-to-date,
		 * so it can be re-added without a resync.
		 * Pointless because if there are any spares to skip,
		 * then a recovery will happen and soon that array won't
		 * be degraded any more and the spare can go back to sleep then.
		 */
		nospares = 0;

	sync_req = mddev->in_sync;

	/* If this is just a dirty<->clean transition, and the array is clean
	 * and 'events' is odd, we can roll back to the previous clean state */
	if (nospares
	    && (mddev->in_sync && mddev->recovery_cp == MaxSector)
	    && mddev->can_decrease_events
	    && mddev->events != 1) {
		mddev->events--;
		mddev->can_decrease_events = 0;
	} else {
		/* otherwise we have to go forward and ... */
		mddev->events ++;
		mddev->can_decrease_events = nospares;
	}