summaryrefslogtreecommitdiff
path: root/block/bsg.c
blob: a333c9337093f8c580105c45e89ab49690f7d242 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
/*
 * bsg.c - block layer implementation of the sg v3 interface
 *
 * Copyright (C) 2004 Jens Axboe <axboe@suse.de> SUSE Labs
 * Copyright (C) 2004 Peter M. Jones <pjones@redhat.com>
 *
 *  This file is subject to the terms and conditions of the GNU General Public
 *  License version 2.  See the file "COPYING" in the main directory of this
 *  archive for more details.
 *
 */
/*
 * TODO
 *	- Should this get merged, block/scsi_ioctl.c will be migrated into
 *	  this file. To keep maintenance down, it's easier to have them
 *	  seperated right now.
 *
 */
#include <linux/module.h>
#include <linux/init.h>
#include <linux/file.h>
#include <linux/blkdev.h>
#include <linux/poll.h>
#include <linux/cdev.h>
#include <linux/percpu.h>
#include <linux/uio.h>
#include <linux/bsg.h>

#include <scsi/scsi.h>
#include <scsi/scsi_ioctl.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_driver.h>
#include <scsi/sg.h>

static char bsg_version[] = "block layer sg (bsg) 0.4";

struct bsg_device {
	request_queue_t *queue;
	spinlock_t lock;
	struct list_head busy_list;
	struct list_head done_list;
	struct hlist_node dev_list;
	atomic_t ref_count;
	int minor;
	int queued_cmds;
	int done_cmds;
	wait_queue_head_t wq_done;
	wait_queue_head_t wq_free;
	char name[BUS_ID_SIZE];
	int max_queue;
	unsigned long flags;
};

enum {
	BSG_F_BLOCK		= 1,
	BSG_F_WRITE_PERM	= 2,
};

#define BSG_DEFAULT_CMDS	64
#define BSG_MAX_DEVS		32768

#undef BSG_DEBUG

#ifdef BSG_DEBUG
#define dprintk(fmt, args...) printk(KERN_ERR "%s: " fmt, __FUNCTION__, ##args)
#else
#define dprintk(fmt, args...)
#endif

#define list_entry_bc(entry)	list_entry((entry), struct bsg_command, list)

/*
 * just for testing
 */
#define BSG_MAJOR	(240)

static DEFINE_MUTEX(bsg_mutex);
static int bsg_device_nr, bsg_minor_idx;

#define BSG_LIST_SIZE	(8)
#define bsg_list_idx(minor)	((minor) & (BSG_LIST_SIZE - 1))
static struct hlist_head bsg_device_list[BSG_LIST_SIZE];

static struct class *bsg_class;
static LIST_HEAD(bsg_class_list);

static struct kmem_cache *bsg_cmd_cachep;

/*
 * our internal command type
 */
struct bsg_command {
	struct bsg_device *bd;
	struct list_head list;
	struct request *rq;
	struct bio *bio;
	int err;
	struct sg_io_v4 hdr;
	struct sg_io_v4 __user *uhdr;
	char sense[SCSI_SENSE_BUFFERSIZE];
};

static void bsg_free_command(struct bsg_command *bc)
{
	struct bsg_device *bd = bc->bd;
	unsigned long flags;

	kmem_cache_free(bsg_cmd_cachep, bc);

	spin_lock_irqsave(&bd->lock, flags);
	bd->queued_cmds--;
	spin_unlock_irqrestore(&bd->lock, flags);

	wake_up(&bd->wq_free);
}

static struct bsg_command *__bsg_alloc_command(struct bsg_device *bd)
{
	struct bsg_command *bc = NULL;

	spin_lock_irq(&bd->lock);

	if (bd->queued_cmds >= bd->max_queue)
		goto out;

	bd->queued_cmds++;
	spin_unlock_irq(&bd->lock);

	bc = kmem_cache_alloc(bsg_cmd_cachep, GFP_USER);
	if (unlikely(!bc)) {
		spin_lock_irq(&bd->lock);
		bd->queued_cmds--;
		goto out;
	}

	memset(bc, 0, sizeof(*bc));
	bc->bd = bd;
	INIT_LIST_HEAD(&bc->list);
	dprintk("%s: returning free cmd %p\n", bd->name, bc);
	return bc;
out:
	spin_unlock_irq(&bd->lock);
	return bc;
}

static inline void
bsg_del_done_cmd(struct bsg_device *bd, struct bsg_command *bc)
{
	bd->done_cmds--;
	list_del(&bc->list);
}

static inline void
bsg_add_done_cmd(struct bsg_device *bd, struct bsg_command *bc)
{
	bd->done_cmds++;
	list_add_tail(&bc->list, &bd->done_list);
	wake_up(&bd->wq_done);
}

static inline int bsg_io_schedule(struct bsg_device *bd, int state)
{
	DEFINE_WAIT(wait);
	int ret = 0;

	spin_lock_irq(&bd->lock);

	BUG_ON(bd->done_cmds > bd->queued_cmds);

	/*
	 * -ENOSPC or -ENODATA?  I'm going for -ENODATA, meaning "I have no
	 * work to do", even though we return -ENOSPC after this same test
	 * during bsg_write() -- there, it means our buffer can't have more
	 * bsg_commands added to it, thus has no space left.
	 */
	if (bd->done_cmds == bd->queued_cmds) {
		ret = -ENODATA;
		goto unlock;
	}

	if (!test_bit(BSG_F_BLOCK, &bd->flags)) {
		ret = -EAGAIN;
		goto unlock;
	}

	prepare_to_wait(&bd->wq_done, &wait, state);
	spin_unlock_irq(&bd->lock);
	io_schedule();
	finish_wait(&bd->wq_done, &wait);

	if ((state == TASK_INTERRUPTIBLE) && signal_pending(current))
		ret = -ERESTARTSYS;

	return ret;
unlock:
	spin_unlock_irq(&bd->lock);
	return ret;
}

/*
 * get a new free command, blocking if needed and specified
 */
static struct bsg_command *bsg_get_command(struct bsg_device *bd)
{
	struct bsg_command *bc;
	int ret;

	do {
		bc = __bsg_alloc_command(bd);
		if (bc)
			break;

		ret = bsg_io_schedule(bd, TASK_INTERRUPTIBLE);
		if (ret) {
			bc = ERR_PTR(ret);
			break;
		}

	} while (1);

	return bc;
}

static int blk_fill_sgv4_hdr_rq(request_queue_t *q, struct request *rq,
				struct sg_io_v4 *hdr, int has_write_perm)
{
	memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */

	if (copy_from_user(rq->cmd, (void *)(unsigned long)hdr->request,
			   hdr->request_len))
		return -EFAULT;
	if (blk_verify_command(rq->cmd, has_write_perm))
		return -EPERM;

	/*
	 * fill in request structure
	 */
	rq->cmd_len = hdr->request_len;
	rq->cmd_type = REQ_TYPE_BLOCK_PC;

	rq->timeout = (hdr->timeout * HZ) / 1000;
	if (!rq->timeout)
		rq->timeout = q->sg_timeout;
	if (!rq->timeout)
		rq->timeout = BLK_DEFAULT_SG_TIMEOUT;

	return 0;
}

/*
 * Check if sg_io_v4 from user is allowed and valid
 */
static int
bsg_validate_sgv4_hdr(request_queue_t *q, struct sg_io_v4 *hdr, int *rw)
{
	if (hdr->guard != 'Q')
		return -EINVAL;
	if (hdr->request_len > BLK_MAX_CDB)
		return -EINVAL;
	if (hdr->dout_xfer_len > (q->max_sectors << 9) ||
	    hdr->din_xfer_len > (q->max_sectors << 9))
		return -EIO;

	/* not supported currently */
	if (hdr->protocol || hdr->subprotocol)
		return -EINVAL;

	/*
	 * looks sane, if no data then it should be fine from our POV
	 */
	if (!hdr->dout_xfer_len && !hdr->din_xfer_len)
		return 0;

	/* not supported currently */
	if (hdr->dout_xfer_len && hdr->din_xfer_len)
		return -EINVAL;

	*rw = hdr->dout_xfer_len ? WRITE : READ;

	return 0;
}

/*
 * map sg_io_v4 to a request.
 */
static struct request *
bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr)
{
	request_queue_t *q = bd->queue;
	struct request *rq;
	int ret, rw = 0; /* shut up gcc */
	unsigned int dxfer_len;
	void *dxferp = NULL;

	dprintk("map hdr %llx/%u %llx/%u\n", (unsigned long long) hdr->dout_xferp,
		hdr->dout_xfer_len, (unsigned long long) hdr->din_xferp,
		hdr->din_xfer_len);

	ret = bsg_validate_sgv4_hdr(q, hdr, &rw);
	if (ret)
		return ERR_PTR(ret);

	/*
	 * map scatter-gather elements seperately and string them to request
	 */
	rq = blk_get_request(q, rw, GFP_KERNEL);
	ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, test_bit(BSG_F_WRITE_PERM,
						       &bd->flags));
	if (ret) {
		blk_put_request(rq);
		return ERR_PTR(ret);
	}

	if (hdr->dout_xfer_len) {
		dxfer_len = hdr->dout_xfer_len;
		dxferp = (void*)(unsigned long)hdr->dout_xferp;
	} else if (hdr->din_xfer_len) {
		dxfer_len = hdr->din_xfer_len;
		dxferp = (void*)(unsigned long)hdr->din_xferp;
	} else
		dxfer_len = 0;

	if (dxfer_len) {
		ret = blk_rq_map_user(q, rq, dxferp, dxfer_len);
		if (ret) {
			dprintk("failed map at %d\n", ret);
			blk_put_request(rq);
			rq = ERR_PTR(ret);
		}
	}

	return rq;
}

/*
 * async completion call-back from the block layer, when scsi/ide/whatever
 * calls end_that_request_last() on a request
 */
static void bsg_rq_end_io(struct request *rq, int uptodate)
{
	struct bsg_command *bc = rq->end_io_data;
	struct bsg_device *bd = bc->bd;
	unsigned long flags;

	dprintk("%s: finished rq %p bc %p, bio %p stat %d\n",
		bd->name, rq, bc, bc->bio, uptodate);

	bc->hdr.duration = jiffies_to_msecs(jiffies - bc->hdr.duration);

	spin_lock_irqsave(&bd->lock, flags);
	list_del(&bc->list);
	bsg_add_done_cmd(bd, bc);
	spin_unlock_irqrestore(&bd->lock, flags);
}

/*
 * do final setup of a 'bc' and submit the matching 'rq' to the block
 * layer for io
 */
static void bsg_add_command(struct bsg_device *bd, request_queue_t *q,
			    struct bsg_command *bc, struct request *rq)
{
	rq->sense = bc->sense;
	rq->sense_len = 0;

	/*
	 * add bc command to busy queue and submit rq for io
	 */
	bc->rq = rq;
	bc->bio = rq->bio;
	bc->hdr.duration = jiffies;
	spin_lock_irq(&bd->lock);
	list_add_tail(&bc->list, &bd->busy_list);
	spin_unlock_irq(&bd->lock);

	dprintk("%s: queueing rq %p, bc %p\n", bd->name, rq, bc);

	rq->end_io_data = bc;
	blk_execute_rq_nowait(q, NULL, rq, 1, bsg_rq_end_io);
}

static inline struct bsg_command *bsg_next_done_cmd(struct bsg_device *bd)
{
	struct bsg_command *bc = NULL;

	spin_lock_irq(&bd->lock);
	if (bd->done_cmds) {
		bc = list_entry_bc(bd->done_list.next);
		bsg_del_done_cmd(bd, bc);
	}
	spin_unlock_irq(&bd->lock);

	return bc;
}

/*
 * Get a finished command from the done list
 */
static struct bsg_command *__bsg_get_done_cmd(struct bsg_device *bd, int state)
{
	struct bsg_command *bc;
	int ret;

	do {
		bc = bsg_next_done_cmd(bd);
		if (bc)
			break;

		ret = bsg_io_schedule(bd, state);
		if (ret) {
			bc = ERR_PTR(ret);
			break;
		}
	} while (1);

	dprintk("%s: returning done %p\n", bd->name, bc);

	return bc;
}

static struct bsg_command *
bsg_get_done_cmd(struct bsg_device *bd, const struct iovec *iov)
{
	return __bsg_get_done_cmd(bd, TASK_INTERRUPTIBLE);
}

static struct bsg_command *
bsg_get_done_cmd_nosignals(struct bsg_device *bd)
{
	return __bsg_get_done_cmd(bd, TASK_UNINTERRUPTIBLE);
}

static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
				    struct bio *bio)
{
	int ret = 0;

	dprintk("rq %p bio %p %u\n", rq, bio, rq->errors);
	/*
	 * fill in all the output members
	 */
	hdr->device_status = status_byte(rq->errors);
	hdr->transport_status = host_byte(rq->errors);
	hdr->driver_status = driver_byte(rq->errors);
	hdr->info = 0;
	if (hdr->device_status || hdr->transport_status || hdr->driver_status)
		hdr->info |= SG_INFO_CHECK;
	hdr->din_resid = rq->data_len;
	hdr->response_len = 0;

	if (rq->sense_len && hdr->response) {
		int len = min((unsigned int) hdr->max_response_len,
			      rq->sense_len);

		ret = copy_to_user((void*)(unsigned long)hdr->response,
				   rq->sense, len);
		if (!ret)
			hdr->response_len = len;
		else
			ret = -EFAULT;
	}

	blk_rq_unmap_user(bio);
	blk_put_request(rq);

	return ret;
}

static int bsg_complete_all_commands(struct bsg_device *bd)
{
	struct bsg_command *bc;
	int ret, tret;

	dprintk("%s: entered\n", bd->name);

	set_bit(BSG_F_BLOCK, &bd->flags);

	/*
	 * wait for all commands to complete
	 */
	ret = 0;
	do {
		ret = bsg_io_schedule(bd, TASK_UNINTERRUPTIBLE);
		/*
		 * look for -ENODATA specifically -- we'll sometimes get
		 * -ERESTARTSYS when we've taken a signal, but we can't
		 * return until we're done freeing the queue, so ignore
		 * it.  The signal will get handled when we're done freeing
		 * the bsg_device.
		 */
	} while (ret != -ENODATA);

	/*
	 * discard done commands
	 */
	ret = 0;
	do {
		bc = bsg_get_done_cmd_nosignals(bd);

		/*
		 * we _must_ complete before restarting, because
		 * bsg_release can't handle this failing.
		 */
		if (PTR_ERR(bc) == -ERESTARTSYS)
			continue;
		if (IS_ERR(bc)) {
			ret = PTR_ERR(bc);
			break;
		}

		tret = blk_complete_sgv4_hdr_rq(bc->rq, &bc->hdr, bc->bio);
		if (!ret)
			ret = tret;

		bsg_free_command(bc);
	} while (1);

	return ret;
}

typedef struct bsg_command *(*bsg_command_callback)(struct bsg_device *bd, const struct iovec *iov);

static ssize_t
__bsg_read(char __user *buf, size_t count, bsg_command_callback get_bc,
	   struct bsg_device *bd, const struct iovec *iov, ssize_t *bytes_read)
{
	struct bsg_command *bc;
	int nr_commands, ret;

	if (count % sizeof(struct sg_io_v4))
		return -EINVAL;

	ret = 0;
	nr_commands = count / sizeof(struct sg_io_v4);
	while (nr_commands) {
		bc = get_bc(bd, iov);
		if (IS_ERR(bc)) {
			ret = PTR_ERR(bc);
			break;
		}

		/*
		 * this is the only case where we need to copy data back
		 * after completing the request. so do that here,
		 * bsg_complete_work() cannot do that for us
		 */
		ret = blk_complete_sgv4_hdr_rq(bc->rq, &bc->hdr, bc->bio);

		if (copy_to_user(buf, (char *) &bc->hdr, sizeof(bc->hdr)))
			ret = -EFAULT;

		bsg_free_command(bc);

		if (ret)
			break;

		buf += sizeof(struct sg_io_v4);
		*bytes_read += sizeof(struct sg_io_v4);
		nr_commands--;
	}

	return ret;
}

static inline void bsg_set_block(struct bsg_device *bd, struct file *file)
{
	if (file->f_flags & O_NONBLOCK)
		clear_bit(BSG_F_BLOCK, &bd->flags);
	else
		set_bit(BSG_F_BLOCK, &bd->flags);
}

static inline void bsg_set_write_perm(struct bsg_device *bd, struct file *file)
{
	if (file->f_mode & FMODE_WRITE)
		set_bit(BSG_F_WRITE_PERM, &bd->flags);
	else
		clear_bit(BSG_F_WRITE_PERM, &bd->flags);
}

static inline int err_block_err(int ret)
{
	if (ret && ret != -ENOSPC && ret != -ENODATA && ret != -EAGAIN)
		return 1;

	return 0;
}

static ssize_t
bsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
	struct bsg_device *bd = file->private_data;
	int ret;
	ssize_t bytes_read;

	dprintk("%s: read %Zd bytes\n", bd->name, count);

	bsg_set_block(bd, file);
	bytes_read = 0;
	ret = __bsg_read(buf, count, bsg_get_done_cmd,
			bd, NULL, &bytes_read);
	*ppos = bytes_read;

	if (!bytes_read || (bytes_read && err_block_err(ret)))
		bytes_read = ret;

	return bytes_read;
}

static ssize_t __bsg_write(struct bsg_device *bd, const char __user *buf,
			   size_t count, ssize_t *bytes_read)
{
	struct bsg_command *bc;
	struct request *rq;
	int ret, nr_commands;

	if (count % sizeof(struct sg_io_v4))
		return -EINVAL;

	nr_commands = count / sizeof(struct sg_io_v4);
	rq = NULL;
	bc = NULL;
	ret = 0;
	while (nr_commands) {
		request_queue_t *q = bd->queue;

		bc = bsg_get_command(bd);
		if (!bc)
			break;
		if (IS_ERR(bc)) {
			ret = PTR_ERR(bc);
			bc = NULL;
			break;
		}

		bc->uhdr = (struct sg_io_v4 __user *) buf;
		if (copy_from_user(&bc->hdr, buf, sizeof(bc->hdr))) {
			ret = -EFAULT;
			break;
		}

		/*
		 * get a request, fill in the blanks, and add to request queue
		 */
		rq = bsg_map_hdr(bd, &bc->hdr);
		if (IS_ERR(rq)) {
			ret = PTR_ERR(rq);
			rq = NULL;
			break;
		}

		bsg_add_command(bd, q, bc, rq);
		bc = NULL;
		rq = NULL;
		nr_commands--;
		buf += sizeof(struct sg_io_v4);
		*bytes_read += sizeof(struct sg_io_v4);
	}

	if (bc)
		bsg_free_command(bc);

	return ret;
}

static ssize_t
bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
{
	struct bsg_device *bd = file->private_data;
	ssize_t bytes_read;
	int ret;

	dprintk("%s: write %Zd bytes\n", bd->name, count);

	bsg_set_block(bd, file);
	bsg_set_write_perm(bd, file);

	bytes_read = 0;
	ret = __bsg_write(bd, buf, count, &bytes_read);
	*ppos = bytes_read;

	/*
	 * return bytes written on non-fatal errors
	 */
	if (!bytes_read || (bytes_read && err_block_err(ret)))
		bytes_read = ret;

	dprintk("%s: returning %Zd\n", bd->name, bytes_read);
	return bytes_read;
}

static struct bsg_device *bsg_alloc_device(void)
{
	struct bsg_device *bd;

	bd = kzalloc(sizeof(struct bsg_device), GFP_KERNEL);
	if (unlikely(!bd))
		return NULL;

	spin_lock_init(&bd->lock);

	bd->max_queue = BSG_DEFAULT_CMDS;

	INIT_LIST_HEAD(&bd->busy_list);
	INIT_LIST_HEAD(&bd->done_list);
	INIT_HLIST_NODE(&bd->dev_list);

	init_waitqueue_head(&bd->wq_free);
	init_waitqueue_head(&bd->wq_done);
	return bd;
}

static int bsg_put_device(struct bsg_device *bd)
{
	int ret = 0;

	mutex_lock(&bsg_mutex);

	if (!atomic_dec_and_test(&bd->ref_count))
		goto out;

	dprintk("%s: tearing down\n", bd->name);

	/*
	 * close can always block
	 */
	set_bit(BSG_F_BLOCK, &bd->flags);

	/*
	 * correct error detection baddies here again. it's the responsibility
	 * of the app to properly reap commands before close() if it wants
	 * fool-proof error detection
	 */
	ret = bsg_complete_all_commands(bd);

	blk_put_queue(bd->queue);
	hlist_del(&bd->dev_list);
	kfree(bd);
out:
	mutex_unlock(&bsg_mutex);
	return ret;
}

static struct bsg_device *bsg_add_device(struct inode *inode,
					 struct request_queue *rq,
					 struct file *file)
{
	struct bsg_device *bd = NULL;
#ifdef BSG_DEBUG
	unsigned char buf[32];
#endif

	bd = bsg_alloc_device();
	if (!bd)
		return ERR_PTR(-ENOMEM);

	bd->queue = rq;
	kobject_get(&rq->kobj);
	bsg_set_block(bd, file);

	atomic_set(&bd->ref_count, 1);
	bd->minor = iminor(inode);
	mutex_lock(&bsg_mutex);
	hlist_add_head(&bd->dev_list, &bsg_device_list[bsg_list_idx(bd->minor)]);

	strncpy(bd->name, rq->bsg_dev.class_dev->class_id, sizeof(bd->name) - 1);
	dprintk("bound to <%s>, max queue %d\n",
		format_dev_t(buf, inode->i_rdev), bd->max_queue);

	mutex_unlock(&bsg_mutex);
	return bd;
}

static struct bsg_device *__bsg_get_device(int minor)
{
	struct hlist_head *list = &bsg_device_list[bsg_list_idx(minor)];
	struct bsg_device *bd = NULL;
	struct hlist_node *entry;

	mutex_lock(&bsg_mutex);

	hlist_for_each(entry, list) {
		bd = hlist_entry(entry, struct bsg_device, dev_list);
		if (bd->minor == minor) {
			atomic_inc(&bd->ref_count);
			break;
		}

		bd = NULL;
	}

	mutex_unlock(&bsg_mutex);
	return bd;
}

static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file)
{
	struct bsg_device *bd = __bsg_get_device(iminor(inode));
	struct bsg_class_device *bcd, *__bcd;

	if (bd)
		return bd;

	/*
	 * find the class device
	 */
	bcd = NULL;
	mutex_lock(&bsg_mutex);
	list_for_each_entry(__bcd, &bsg_class_list, list) {
		if (__bcd->minor == iminor(inode)) {
			bcd = __bcd;
			break;
		}
	}
	mutex_unlock(&bsg_mutex);

	if (!bcd)
		return ERR_PTR(-ENODEV);

	return bsg_add_device(inode, bcd->queue, file);
}

static int bsg_open(struct inode *inode, struct file *file)
{
	struct bsg_device *bd = bsg_get_device(inode, file);

	if (IS_ERR(bd))
		return PTR_ERR(bd);

	file->private_data = bd;
	return 0;
}

static int bsg_release(struct inode *inode, struct file *file)
{
	struct bsg_device *bd = file->private_data;

	file->private_data = NULL;
	return bsg_put_device(bd);
}

static unsigned int bsg_poll(struct file *file, poll_table *wait)
{
	struct bsg_device *bd = file->private_data;
	unsigned int mask = 0;

	poll_wait(file, &bd->wq_done, wait);
	poll_wait(file, &bd->wq_free, wait);

	spin_lock_irq(&bd->lock);
	if (!list_empty(&bd->done_list))
		mask |= POLLIN | POLLRDNORM;
	if (bd->queued_cmds >= bd->max_queue)
		mask |= POLLOUT;
	spin_unlock_irq(&bd->lock);

	return mask;
}

static int
bsg_ioctl(struct inode *inode, struct file *file, unsigned int cmd,
	  unsigned long arg)
{
	struct bsg_device *bd = file->private_data;
	int __user *uarg = (int __user *) arg;

	if (!bd)
		return -ENXIO;

	switch (cmd) {
		/*
		 * our own ioctls
		 */
	case SG_GET_COMMAND_Q:
		return put_user(bd->max_queue, uarg);
	case SG_SET_COMMAND_Q: {
		int queue;

		if (get_user(queue, uarg))
			return -EFAULT;
		if (queue < 1)
			return -EINVAL;

		spin_lock_irq(&bd->lock);
		bd->max_queue = queue;
		spin_unlock_irq(&bd->lock);
		return 0;
	}

	/*
	 * SCSI/sg ioctls
	 */
	case SG_GET_VERSION_NUM:
	case SCSI_IOCTL_GET_IDLUN:
	case SCSI_IOCTL_GET_BUS_NUMBER:
	case SG_SET_TIMEOUT:
	case SG_GET_TIMEOUT:
	case SG_GET_RESERVED_SIZE:
	case SG_SET_RESERVED_SIZE:
	case SG_EMULATED_HOST:
	case SCSI_IOCTL_SEND_COMMAND: {
		void __user *uarg = (void __user *) arg;
		return scsi_cmd_ioctl(file, bd->queue, NULL, cmd, uarg);
	}
	case SG_IO: {
		struct request *rq;
		struct bio *bio;
		struct sg_io_v4 hdr;

		if (copy_from_user(&hdr, uarg, sizeof(hdr)))
			return -EFAULT;

		rq = bsg_map_hdr(bd, &hdr);
		if (IS_ERR(rq))
			return PTR_ERR(rq);

		bio = rq->bio;
		blk_execute_rq(bd->queue, NULL, rq, 0);
		blk_complete_sgv4_hdr_rq(rq, &hdr, bio);

		if (copy_to_user(uarg, &hdr, sizeof(hdr)))
			return -EFAULT;

		return 0;
	}
	/*
	 * block device ioctls
	 */
	default:
#if 0
		return ioctl_by_bdev(bd->bdev, cmd, arg);
#else
		return -ENOTTY;
#endif
	}
}

static struct file_operations bsg_fops = {
	.read		=	bsg_read,
	.write		=	bsg_write,
	.poll		=	bsg_poll,
	.open		=	bsg_open,
	.release	=	bsg_release,
	.ioctl		=	bsg_ioctl,
	.owner		=	THIS_MODULE,
};

void bsg_unregister_queue(struct request_queue *q)
{
	struct bsg_class_device *bcd = &q->bsg_dev;

	if (!bcd->class_dev)
		return;

	mutex_lock(&bsg_mutex);
	sysfs_remove_link(&q->kobj, "bsg");
	class_device_destroy(bsg_class, MKDEV(BSG_MAJOR, bcd->minor));
	bcd->class_dev = NULL;
	list_del_init(&bcd->list);
	bsg_device_nr--;
	mutex_unlock(&bsg_mutex);
}
EXPORT_SYMBOL_GPL(bsg_unregister_queue);

int bsg_register_queue(struct request_queue *q, const char *name)
{
	struct bsg_class_device *bcd, *__bcd;
	dev_t dev;
	int ret = -EMFILE;
	struct class_device *class_dev = NULL;

	/*
	 * we need a proper transport to send commands, not a stacked device
	 */
	if (!q->request_fn)
		return 0;

	bcd = &q->bsg_dev;
	memset(bcd, 0, sizeof(*bcd));
	INIT_LIST_HEAD(&bcd->list);

	mutex_lock(&bsg_mutex);
	if (bsg_device_nr == BSG_MAX_DEVS) {
		printk(KERN_ERR "bsg: too many bsg devices\n");
		goto err;
	}

retry:
	list_for_each_entry(__bcd, &bsg_class_list, list) {
		if (__bcd->minor == bsg_minor_idx) {
			bsg_minor_idx++;
			if (bsg_minor_idx == BSG_MAX_DEVS)
				bsg_minor_idx = 0;
			goto retry;
		}
	}

	bcd->minor = bsg_minor_idx++;
	if (bsg_minor_idx == BSG_MAX_DEVS)
		bsg_minor_idx = 0;

	bcd->queue = q;
	dev = MKDEV(BSG_MAJOR, bcd->minor);
	class_dev = class_device_create(bsg_class, NULL, dev, bcd->dev, "%s", name);
	if (IS_ERR(class_dev)) {
		ret = PTR_ERR(class_dev);
		goto err;
	}
	bcd->class_dev = class_dev;

	if (q->kobj.dentry) {
		ret = sysfs_create_link(&q->kobj, &bcd->class_dev->kobj, "bsg");
		if (ret)
			goto err;
	}

	list_add_tail(&bcd->list, &bsg_class_list);
	bsg_device_nr++;

	mutex_unlock(&bsg_mutex);
	return 0;
err:
	if (class_dev)
		class_device_destroy(bsg_class, MKDEV(BSG_MAJOR, bcd->minor));
	mutex_unlock(&bsg_mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(bsg_register_queue);

static int bsg_add(struct class_device *cl_dev, struct class_interface *cl_intf)
{
	int ret;
	struct scsi_device *sdp = to_scsi_device(cl_dev->dev);
	struct request_queue *rq = sdp->request_queue;

	if (rq->kobj.parent)
		ret = bsg_register_queue(rq, kobject_name(rq->kobj.parent));
	else
		ret = bsg_register_queue(rq, kobject_name(&sdp->sdev_gendev.kobj));
	return ret;
}

static void bsg_remove(struct class_device *cl_dev, struct class_interface *cl_intf)
{
	bsg_unregister_queue(to_scsi_device(cl_dev->dev)->request_queue);
}

static struct class_interface bsg_intf = {
	.add	= bsg_add,
	.remove	= bsg_remove,
};

static struct cdev bsg_cdev = {
	.kobj   = {.name = "bsg", },
	.owner  = THIS_MODULE,
};

static int __init bsg_init(void)
{
	int ret, i;

	bsg_cmd_cachep = kmem_cache_create("bsg_cmd",
				sizeof(struct bsg_command), 0, 0, NULL, NULL);
	if (!bsg_cmd_cachep) {
		printk(KERN_ERR "bsg: failed creating slab cache\n");
		return -ENOMEM;
	}

	for (i = 0; i < BSG_LIST_SIZE; i++)
		INIT_HLIST_HEAD(&bsg_device_list[i]);

	bsg_class = class_create(THIS_MODULE, "bsg");
	if (IS_ERR(bsg_class)) {
		kmem_cache_destroy(bsg_cmd_cachep);
		return PTR_ERR(bsg_class);
	}

	ret = register_chrdev_region(MKDEV(BSG_MAJOR, 0), BSG_MAX_DEVS, "bsg");
	if (ret) {
		kmem_cache_destroy(bsg_cmd_cachep);
		class_destroy(bsg_class);
		return ret;
	}

	cdev_init(&bsg_cdev, &bsg_fops);
	ret = cdev_add(&bsg_cdev, MKDEV(BSG_MAJOR, 0), BSG_MAX_DEVS);
	if (ret) {
		kmem_cache_destroy(bsg_cmd_cachep);
		class_destroy(bsg_class);
		unregister_chrdev_region(MKDEV(BSG_MAJOR, 0), BSG_MAX_DEVS);
		return ret;
	}

	ret = scsi_register_interface(&bsg_intf);
	if (ret) {
		printk(KERN_ERR "bsg: failed register scsi interface %d\n", ret);
		kmem_cache_destroy(bsg_cmd_cachep);
		class_destroy(bsg_class);
		unregister_chrdev(BSG_MAJOR, "bsg");
		return ret;
	}

	printk(KERN_INFO "%s loaded\n", bsg_version);
	return 0;
}

MODULE_AUTHOR("Jens Axboe");
MODULE_DESCRIPTION("Block layer SGSI generic (sg) driver");
MODULE_LICENSE("GPL");

device_initcall(bsg_init);