summaryrefslogtreecommitdiff
path: root/include/linux/blkdev.h
blob: 860e7a485a5f08d2aaa10129d65c6339c128a008 (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
#ifndef _LINUX_BLKDEV_H
#define _LINUX_BLKDEV_H

#include <linux/config.h>
#include <linux/major.h>
#include <linux/genhd.h>
#include <linux/list.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/pagemap.h>
#include <linux/backing-dev.h>
#include <linux/wait.h>
#include <linux/mempool.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/stringify.h>

#include <asm/scatterlist.h>

struct request_queue;
typedef struct request_queue request_queue_t;
struct elevator_queue;
typedef struct elevator_queue elevator_t;
struct request_pm_state;

#define BLKDEV_MIN_RQ	4
#define BLKDEV_MAX_RQ	128	/* Default maximum */

/*
 * This is the per-process anticipatory I/O scheduler state.
 */
struct as_io_context {
	spinlock_t lock;

	void (*dtor)(struct as_io_context *aic); /* destructor */
	void (*exit)(struct as_io_context *aic); /* called on task exit */

	unsigned long state;
	atomic_t nr_queued; /* queued reads & sync writes */
	atomic_t nr_dispatched; /* number of requests gone to the drivers */

	/* IO History tracking */
	/* Thinktime */
	unsigned long last_end_request;
	unsigned long ttime_total;
	unsigned long ttime_samples;
	unsigned long ttime_mean;
	/* Layout pattern */
	unsigned int seek_samples;
	sector_t last_request_pos;
	u64 seek_total;
	sector_t seek_mean;
};

struct cfq_queue;
struct cfq_io_context {
	/*
	 * circular list of cfq_io_contexts belonging to a process io context
	 */
	struct list_head list;
	struct cfq_queue *cfqq;
	void *key;

	struct io_context *ioc;

	unsigned long last_end_request;
	unsigned long last_queue;
	unsigned long ttime_total;
	unsigned long ttime_samples;
	unsigned long ttime_mean;

	void (*dtor)(struct cfq_io_context *);
	void (*exit)(struct cfq_io_context *);
};

/*
 * This is the per-process I/O subsystem state.  It is refcounted and
 * kmalloc'ed. Currently all fields are modified in process io context
 * (apart from the atomic refcount), so require no locking.
 */
struct io_context {
	atomic_t refcount;
	struct task_struct *task;

	int (*set_ioprio)(struct io_context *, unsigned int);

	/*
	 * For request batching
	 */
	unsigned long last_waited; /* Time last woken after wait for request */
	int nr_batch_requests;     /* Number of requests left in the batch */

	struct as_io_context *aic;
	struct cfq_io_context *cic;
};

void put_io_context(struct io_context *ioc);
void exit_io_context(void);
struct io_context *current_io_context(gfp_t gfp_flags);
struct io_context *get_io_context(gfp_t gfp_flags);
void copy_io_context(struct io_context **pdst, struct io_context **psrc);
void swap_io_context(struct io_context **ioc1, struct io_context **ioc2);

struct request;
typedef void (rq_end_io_fn)(struct request *, int);

struct request_list {
	int count[2];
	int starved[2];
	int elvpriv;
	mempool_t *rq_pool;
	wait_queue_head_t wait[2];
};

#define BLK_MAX_CDB	16

/*
 * try to put the fields that are referenced together in the same cacheline
 */
struct request {
	struct list_head queuelist;
	struct list_head donelist;

	unsigned long flags;		/* see REQ_ bits below */

	/* Maintain bio traversal state for part by part I/O submission.
	 * hard_* are block layer internals, no driver should touch them!
	 */

	sector_t sector;		/* next sector to submit */
	unsigned long nr_sectors;	/* no. of sectors left to submit */
	/* no. of sectors left to submit in the current segment */
	unsigned int current_nr_sectors;

	sector_t hard_sector;		/* next sector to complete */
	unsigned long hard_nr_sectors;	/* no. of sectors left to complete */
	/* no. of sectors left to complete in the current segment */
	unsigned int hard_cur_sectors;

	struct bio *bio;
	struct bio *biotail;

	void *elevator_private;
	void *completion_data;

	unsigned short ioprio;

	int rq_status;	/* should split this into a few status bits */
	struct gendisk *rq_disk;
	int errors;
	unsigned long start_time;

	/* Number of scatter-gather DMA addr+len pairs after
	 * physical address coalescing is performed.
	 */
	unsigned short nr_phys_segments;

	/* Number of scatter-gather addr+len pairs after
	 * physical and DMA remapping hardware coalescing is performed.
	 * This is the number of scatter-gather entries the driver
	 * will actually have to deal with after DMA mapping is done.
	 */
	unsigned short nr_hw_segments;

	int tag;
	char *buffer;

	int ref_count;
	request_queue_t *q;
	struct request_list *rl;

	struct completion *waiting;
	void *special;

	/*
	 * when request is used as a packet command carrier
	 */
	unsigned int cmd_len;
	unsigned char cmd[BLK_MAX_CDB];

	unsigned int data_len;
	void *data;

	unsigned int sense_len;
	void *sense;

	unsigned int timeout;
	int retries;

	/*
	 * For Power Management requests
	 */
	struct request_pm_state *pm;

	/*
	 * completion callback. end_io_data should be folded in with waiting
	 */
	rq_end_io_fn *end_io;
	void *end_io_data;
};

/*
 * first three bits match BIO_RW* bits, important
 */
enum rq_flag_bits {
	__REQ_RW,		/* not set, read. set, write */
	__REQ_FAILFAST,		/* no low level driver retries */
	__REQ_SORTED,		/* elevator knows about this request */
	__REQ_SOFTBARRIER,	/* may not be passed by ioscheduler */
	__REQ_HARDBARRIER,	/* may not be passed by drive either */
	__REQ_FUA,		/* forced unit access */
	__REQ_CMD,		/* is a regular fs rw request */
	__REQ_NOMERGE,		/* don't touch this for merging */
	__REQ_STARTED,		/* drive already may have started this one */
	__REQ_DONTPREP,		/* don't call prep for this one */
	__REQ_QUEUED,		/* uses queueing */
	__REQ_ELVPRIV,		/* elevator private data attached */
	/*
	 * for ATA/ATAPI devices
	 */
	__REQ_PC,		/* packet command (special) */
	__REQ_BLOCK_PC,		/* queued down pc from block layer */
	__REQ_SENSE,		/* sense retrival */

	__REQ_FAILED,		/* set if the request failed */
	__REQ_QUIET,		/* don't worry about errors */
	__REQ_SPECIAL,		/* driver suplied command */
	__REQ_DRIVE_CMD,
	__REQ_DRIVE_TASK,
	__REQ_DRIVE_TASKFILE,
	__REQ_PREEMPT,		/* set for "ide_preempt" requests */
	__REQ_PM_SUSPEND,	/* suspend request */
	__REQ_PM_RESUME,	/* resume request */
	__REQ_PM_SHUTDOWN,	/* shutdown request */
	__REQ_ORDERED_COLOR,	/* is before or after barrier */
	__REQ_NR_BITS,		/* stops here */
};

#define REQ_RW		(1 << __REQ_RW)
#define REQ_FAILFAST	(1 << __REQ_FAILFAST)
#define REQ_SORTED	(1 << __REQ_SORTED)
#define REQ_SOFTBARRIER	(1 << __REQ_SOFTBARRIER)
#define REQ_HARDBARRIER	(1 << __REQ_HARDBARRIER)
#define REQ_FUA		(1 << __REQ_FUA)
#define REQ_CMD		(1 << __REQ_CMD)
#define REQ_NOMERGE	(1 << __REQ_NOMERGE)
#define REQ_STARTED	(1 << __REQ_STARTED)
#define REQ_DONTPREP	(1 << __REQ_DONTPREP)
#define REQ_QUEUED	(1 << __REQ_QUEUED)
#define REQ_ELVPRIV	(1 << __REQ_ELVPRIV)
#define REQ_PC		(1 << __REQ_PC)
#define REQ_BLOCK_PC	(1 << __REQ_BLOCK_PC)
#define REQ_SENSE	(1 << __REQ_SENSE)
#define REQ_FAILED	(1 << __REQ_FAILED)
#define REQ_QUIET	(1 << __REQ_QUIET)
#define REQ_SPECIAL	(1 << __REQ_SPECIAL)
#define REQ_DRIVE_CMD	(1 << __REQ_DRIVE_CMD)
#define REQ_DRIVE_TASK	(1 << __REQ_DRIVE_TASK)
#define REQ_DRIVE_TASKFILE	(1 << __REQ_DRIVE_TASKFILE)
#define REQ_PREEMPT	(1 << __REQ_PREEMPT)
#define REQ_PM_SUSPEND	(1 << __REQ_PM_SUSPEND)
#define REQ_PM_RESUME	(1 << __REQ_PM_RESUME)
#define REQ_PM_SHUTDOWN	(1 << __REQ_PM_SHUTDOWN)
#define REQ_ORDERED_COLOR	(1 << __REQ_ORDERED_COLOR)

/*
 * State information carried for REQ_PM_SUSPEND and REQ_PM_RESUME
 * requests. Some step values could eventually be made generic.
 */
struct request_pm_state
{
	/* PM state machine step value, currently driver specific */
	int	pm_step;
	/* requested PM state value (S1, S2, S3, S4, ...) */
	u32	pm_state;
	void*	data;		/* for driver use */
};

#include <linux/elevator.h>

typedef int (merge_request_fn) (request_queue_t *, struct request *,
				struct bio *);
typedef int (merge_requests_fn) (request_queue_t *, struct request *,
				 struct request *);
typedef void (request_fn_proc) (request_queue_t *q);
typedef int (make_request_fn) (request_queue_t *q, struct bio *bio);
typedef int (prep_rq_fn) (request_queue_t *, struct request *);
typedef void (unplug_fn) (request_queue_t *);

struct bio_vec;
typedef int (merge_bvec_fn) (request_queue_t *, struct bio *, struct bio_vec *);
typedef void (activity_fn) (void *data, int rw);
typedef int (issue_flush_fn) (request_queue_t *, struct gendisk *, sector_t *);
typedef void (prepare_flush_fn) (request_queue_t *, struct request *);
typedef void (softirq_done_fn)(struct request *);

enum blk_queue_state {
	Queue_down,
	Queue_up,
};

struct blk_queue_tag {
	struct request **tag_index;	/* map of busy tags */
	unsigned long *tag_map;		/* bit map of free/busy tags */
	struct list_head busy_list;	/* fifo list of busy tags */
	int busy;			/* current depth */
	int max_depth;			/* what we will send to device */
	int real_max_depth;		/* what the array can hold */
	atomic_t refcnt;		/* map can be shared */
};

struct request_queue
{
	/*
	 * Together with queue_head for cacheline sharing
	 */
	struct list_head	queue_head;
	struct request		*last_merge;
	elevator_t		*elevator;

	/*
	 * the queue request freelist, one for reads and one for writes
	 */
	struct request_list	rq;

	request_fn_proc		*request_fn;
	merge_request_fn	*back_merge_fn;
	merge_request_fn	*front_merge_fn;
	merge_requests_fn	*merge_requests_fn;
	make_request_fn		*make_request_fn;
	prep_rq_fn		*prep_rq_fn;
	unplug_fn		*unplug_fn;
	merge_bvec_fn		*merge_bvec_fn;
	activity_fn		*activity_fn;
	issue_flush_fn		*issue_flush_fn;
	prepare_flush_fn	*prepare_flush_fn;
	softirq_done_fn		*softirq_done_fn;

	/*
	 * Dispatch queue sorting
	 */
	sector_t		end_sector;
	struct request		*boundary_rq;

	/*
	 * Auto-unplugging state
	 */
	struct timer_list	unplug_timer;
	int			unplug_thresh;	/* After this many requests */
	unsigned long		unplug_delay;	/* After this many jiffies */
	struct work_struct	unplug_work;

	struct backing_dev_info	backing_dev_info;

	/*
	 * The queue owner gets to use this for whatever they like.
	 * ll_rw_blk doesn't touch it.
	 */
	void			*queuedata;

	void			*activity_data;

	/*
	 * queue needs bounce pages for pages above this limit
	 */
	unsigned long		bounce_pfn;
	gfp_t			bounce_gfp;

	/*
	 * various queue flags, see QUEUE_* below
	 */
	unsigned long		queue_flags;

	/*
	 * protects queue structures from reentrancy. ->__queue_lock should
	 * _never_ be used directly, it is queue private. always use
	 * ->queue_lock.
	 */
	spinlock_t		__queue_lock;
	spinlock_t		*queue_lock;

	/*
	 * queue kobject
	 */
	struct kobject kobj;

	/*
	 * queue settings
	 */
	unsigned long		nr_requests;	/* Max # of requests */
	unsigned int		nr_congestion_on;
	unsigned int		nr_congestion_off;
	unsigned int		nr_batching;

	unsigned int		max_sectors;
	unsigned int		max_hw_sectors;
	unsigned short		max_phys_segments;
	unsigned short		max_hw_segments;
	unsigned short		hardsect_size;
	unsigned int		max_segment_size;

	unsigned long		seg_boundary_mask;
	unsigned int		dma_alignment;

	struct blk_queue_tag	*queue_tags;

	atomic_t		refcnt;

	unsigned int		nr_sorted;
	unsigned int		in_flight;

	/*
	 * sg stuff
	 */
	unsigned int		sg_timeout;
	unsigned int		sg_reserved_size;
	int			node;

	/*
	 * reserved for flush operations
	 */
	unsigned int		ordered, next_ordered, ordseq;
	int			orderr, ordcolor;
	struct request		pre_flush_rq, bar_rq, post_flush_rq;
	struct request		*orig_bar_rq;
	unsigned int		bi_size;
};

#define RQ_INACTIVE		(-1)
#define RQ_ACTIVE		1
#define RQ_SCSI_BUSY		0xffff
#define RQ_SCSI_DONE		0xfffe
#define RQ_SCSI_DISCONNECTING	0xffe0

#define QUEUE_FLAG_CLUSTER	0	/* cluster several segments into 1 */
#define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
#define QUEUE_FLAG_STOPPED	2	/* queue is stopped */
#define	QUEUE_FLAG_READFULL	3	/* write queue has been filled */
#define QUEUE_FLAG_WRITEFULL	4	/* read queue has been filled */
#define QUEUE_FLAG_DEAD		5	/* queue being torn down */
#define QUEUE_FLAG_REENTER	6	/* Re-entrancy avoidance */
#define QUEUE_FLAG_PLUGGED	7	/* queue is plugged */
#define QUEUE_FLAG_ELVSWITCH	8	/* don't use elevator, just do FIFO */

enum {
	/*
	 * Hardbarrier is supported with one of the following methods.
	 *
	 * NONE		: hardbarrier unsupported
	 * DRAIN	: ordering by draining is enough
	 * DRAIN_FLUSH	: ordering by draining w/ pre and post flushes
	 * DRAIN_FUA	: ordering by draining w/ pre flush and FUA write
	 * TAG		: ordering by tag is enough
	 * TAG_FLUSH	: ordering by tag w/ pre and post flushes
	 * TAG_FUA	: ordering by tag w/ pre flush and FUA write
	 */
	QUEUE_ORDERED_NONE	= 0x00,
	QUEUE_ORDERED_DRAIN	= 0x01,
	QUEUE_ORDERED_TAG	= 0x02,

	QUEUE_ORDERED_PREFLUSH	= 0x10,
	QUEUE_ORDERED_POSTFLUSH	= 0x20,
	QUEUE_ORDERED_FUA	= 0x40,

	QUEUE_ORDERED_DRAIN_FLUSH = QUEUE_ORDERED_DRAIN |
			QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH,
	QUEUE_ORDERED_DRAIN_FUA	= QUEUE_ORDERED_DRAIN |
			QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_FUA,
	QUEUE_ORDERED_TAG_FLUSH	= QUEUE_ORDERED_TAG |
			QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH,
	QUEUE_ORDERED_TAG_FUA	= QUEUE_ORDERED_TAG |
			QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_FUA,

	/*
	 * Ordered operation sequence
	 */
	QUEUE_ORDSEQ_STARTED	= 0x01,	/* flushing in progress */
	QUEUE_ORDSEQ_DRAIN	= 0x02,	/* waiting for the queue to be drained */
	QUEUE_ORDSEQ_PREFLUSH	= 0x04,	/* pre-flushing in progress */
	QUEUE_ORDSEQ_BAR	= 0x08,	/* original barrier req in progress */
	QUEUE_ORDSEQ_POSTFLUSH	= 0x10,	/* post-flushing in progress */
	QUEUE_ORDSEQ_DONE	= 0x20,
};

#define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
#define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
#define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
#define blk_queue_flushing(q)	((q)->ordseq)

#define blk_fs_request(rq)	((rq)->flags & REQ_CMD)
#define blk_pc_request(rq)	((rq)->flags & REQ_BLOCK_PC)
#define blk_noretry_request(rq)	((rq)->flags & REQ_FAILFAST)
#define blk_rq_started(rq)	((rq)->flags & REQ_STARTED)

#define blk_account_rq(rq)	(blk_rq_started(rq) && blk_fs_request(rq))

#define blk_pm_suspend_request(rq)	((rq)->flags & REQ_PM_SUSPEND)
#define blk_pm_resume_request(rq)	((rq)->flags & REQ_PM_RESUME)
#define blk_pm_request(rq)	\
	((rq)->flags & (REQ_PM_SUSPEND | REQ_PM_RESUME))

#define blk_sorted_rq(rq)	((rq)->flags & REQ_SORTED)
#define blk_barrier_rq(rq)	((rq)->flags & REQ_HARDBARRIER)
#define blk_fua_rq(rq)		((rq)->flags & REQ_FUA)

#define list_entry_rq(ptr)	list_entry((ptr), struct request, queuelist)

#define rq_data_dir(rq)		((rq)->flags & 1)

static inline int blk_queue_full(struct request_queue *q, int rw)
{
	if (rw == READ)
		return test_bit(QUEUE_FLAG_READFULL, &q->queue_flags);
	return test_bit(QUEUE_FLAG_WRITEFULL, &q->queue_flags);
}

static inline void blk_set_queue_full(struct request_queue *q, int rw)
{
	if (rw == READ)
		set_bit(QUEUE_FLAG_READFULL, &q->queue_flags);
	else
		set_bit(QUEUE_FLAG_WRITEFULL, &q->queue_flags);
}

static inline void blk_clear_queue_full(struct request_queue *q, int rw)
{
	if (rw == READ)
		clear_bit(QUEUE_FLAG_READFULL, &q->queue_flags);
	else
		clear_bit(QUEUE_FLAG_WRITEFULL, &q->queue_flags);
}


/*
 * mergeable request must not have _NOMERGE or _BARRIER bit set, nor may
 * it already be started by driver.
 */
#define RQ_NOMERGE_FLAGS	\
	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER)
#define rq_mergeable(rq)	\
	(!((rq)->flags & RQ_NOMERGE_FLAGS) && blk_fs_request((rq)))

/*
 * noop, requests are automagically marked as active/inactive by I/O
 * scheduler -- see elv_next_request
 */
#define blk_queue_headactive(q, head_active)

/*
 * q->prep_rq_fn return values
 */
#define BLKPREP_OK		0	/* serve it */
#define BLKPREP_KILL		1	/* fatal error, kill */
#define BLKPREP_DEFER		2	/* leave on queue */

extern unsigned long blk_max_low_pfn, blk_max_pfn;

/*
 * standard bounce addresses:
 *
 * BLK_BOUNCE_HIGH	: bounce all highmem pages
 * BLK_BOUNCE_ANY	: don't bounce anything
 * BLK_BOUNCE_ISA	: bounce pages above ISA DMA boundary
 */
#define BLK_BOUNCE_HIGH		((u64)blk_max_low_pfn << PAGE_SHIFT)
#define BLK_BOUNCE_ANY		((u64)blk_max_pfn << PAGE_SHIFT)
#define BLK_BOUNCE_ISA		(ISA_DMA_THRESHOLD)

#ifdef CONFIG_MMU
extern int init_emergency_isa_pool(void);
extern void blk_queue_bounce(request_queue_t *q, struct bio **bio);
#else
static inline int init_emergency_isa_pool(void)
{
	return 0;
}
static inline void blk_queue_bounce(request_queue_t *q, struct bio **bio)
{
}
#endif /* CONFIG_MMU */

#define rq_for_each_bio(_bio, rq)	\
	if ((rq->bio))			\
		for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next)

struct sec_size {
	unsigned block_size;
	unsigned block_size_bits;
};

extern int blk_register_queue(struct gendisk *disk);
extern void blk_unregister_queue(struct gendisk *disk);
extern void register_disk(struct gendisk *dev);
extern void generic_make_request(struct bio *bio);
extern void blk_put_request(struct request *);
extern void __blk_put_request(request_queue_t *, struct request *);
extern void blk_end_sync_rq(struct request *rq, int error);
extern struct request *blk_get_request(request_queue_t *, int, gfp_t);
extern void blk_insert_request(request_queue_t *, struct request *, int, void *);
extern void blk_requeue_request(request_queue_t *, struct request *);
extern void blk_plug_device(request_queue_t *);
extern int blk_remove_plug(request_queue_t *);
extern void blk_recount_segments(request_queue_t *, struct bio *);
extern int scsi_cmd_ioctl(struct file *, struct gendisk *, unsigned int, void __user *);
extern void blk_start_queue(request_queue_t *q);
extern void blk_stop_queue(request_queue_t *q);
extern void blk_sync_queue(struct request_queue *q);
extern void __blk_stop_queue(request_queue_t *q);
extern void blk_run_queue(request_queue_t *);
extern void blk_queue_activity_fn(request_queue_t *, activity_fn *, void *);
extern int blk_rq_map_user(request_queue_t *, struct request *, void __user *, unsigned int);
extern int blk_rq_unmap_user(struct bio *, unsigned int);
extern int blk_rq_map_kern(request_queue_t *, struct request *, void *, unsigned int, gfp_t);
extern int blk_rq_map_user_iov(request_queue_t *, struct request *, struct sg_iovec *, int);
extern int blk_execute_rq(request_queue_t *, struct gendisk *,
			  struct request *, int);
extern void blk_execute_rq_nowait(request_queue_t *, struct gendisk *,
				  struct request *, int, rq_end_io_fn *);

static inline request_queue_t *bdev_get_queue(struct block_device *bdev)
{
	return bdev->bd_disk->queue;
}

static inline void blk_run_backing_dev(struct backing_dev_info *bdi,
				       struct page *page)
{
	if (bdi && bdi->unplug_io_fn)
		bdi->unplug_io_fn(bdi, page);
}

static inline void blk_run_address_space(struct address_space *mapping)
{
	if (mapping)
		blk_run_backing_dev(mapping->backing_dev_info, NULL);
}

/*
 * end_request() and friends. Must be called with the request queue spinlock
 * acquired. All functions called within end_request() _must_be_ atomic.
 *
 * Several drivers define their own end_request and call
 * end_that_request_first() and end_that_request_last()
 * for parts of the original function. This prevents
 * code duplication in drivers.
 */
extern int end_that_request_first(struct request *, int, int);
extern int end_that_request_chunk(struct request *, int, int);
extern void end_that_request_last(struct request *, int);
extern void end_request(struct request *req, int uptodate);
extern void blk_complete_request(struct request *);

static inline int rq_all_done(struct request *rq, unsigned int nr_bytes)
{
	if (blk_fs_request(rq))
		return (nr_bytes >= (rq->hard_nr_sectors << 9));
	else if (blk_pc_request(rq))
		return nr_bytes >= rq->data_len;

	return 0;
}

/*
 * end_that_request_first/chunk() takes an uptodate argument. we account
 * any value <= as an io error. 0 means -EIO for compatability reasons,
 * any other < 0 value is the direct error type. An uptodate value of
 * 1 indicates successful io completion
 */
#define end_io_error(uptodate)	(unlikely((uptodate) <= 0))

static inline void blkdev_dequeue_request(struct request *req)
{
	elv_dequeue_request(req->q, req);
}

/*
 * This should be in elevator.h, but that requires pulling in rq and q
 */
static inline void elv_dispatch_add_tail(struct request_queue *q,
					 struct request *rq)
{
	if (q->last_merge == rq)
		q->last_merge = NULL;
	q->nr_sorted--;

	q->end_sector = rq_end_sector(rq);
	q->boundary_rq = rq;
	list_add_tail(&rq->queuelist, &q->queue_head);
}

/*
 * Access functions for manipulating queue properties
 */
extern request_queue_t *blk_init_queue_node(request_fn_proc *rfn,
					spinlock_t *lock, int node_id);
extern request_queue_t *blk_init_queue(request_fn_proc *, spinlock_t *);
extern void blk_cleanup_queue(request_queue_t *);
extern void blk_queue_make_request(request_queue_t *, make_request_fn *);
extern void blk_queue_bounce_limit(request_queue_t *, u64);
extern void blk_queue_max_sectors(request_queue_t *, unsigned int);
extern void blk_queue_max_phys_segments(request_queue_t *, unsigned short);
extern void blk_queue_max_hw_segments(request_queue_t *, unsigned short);
extern void blk_queue_max_segment_size(request_queue_t *, unsigned int);
extern void blk_queue_hardsect_size(request_queue_t *, unsigned short);
extern void blk_queue_stack_limits(request_queue_t *t, request_queue_t *b);
extern void blk_queue_segment_boundary(request_queue_t *, unsigned long);
extern void blk_queue_prep_rq(request_queue_t *, prep_rq_fn *pfn);
extern void blk_queue_merge_bvec(request_queue_t *, merge_bvec_fn *);
extern void blk_queue_dma_alignment(request_queue_t *, int);
extern void blk_queue_softirq_done(request_queue_t *, softirq_done_fn *);
extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
extern int blk_queue_ordered(request_queue_t *, unsigned, prepare_flush_fn *);
extern void blk_queue_issue_flush_fn(request_queue_t *, issue_flush_fn *);
extern int blk_do_ordered(request_queue_t *, struct request **);
extern unsigned blk_ordered_cur_seq(request_queue_t *);
extern unsigned blk_ordered_req_seq(struct request *);
extern void blk_ordered_complete_seq(request_queue_t *, unsigned, int);

extern int blk_rq_map_sg(request_queue_t *, struct request *, struct scatterlist *);
extern void blk_dump_rq_flags(struct request *, char *);
extern void generic_unplug_device(request_queue_t *);
extern void __generic_unplug_device(request_queue_t *);
extern long nr_blockdev_pages(void);

int blk_get_queue(request_queue_t *);
request_queue_t *blk_alloc_queue(gfp_t);
request_queue_t *blk_alloc_queue_node(gfp_t, int);
#define blk_put_queue(q) blk_cleanup_queue((q))

/*
 * tag stuff
 */
#define blk_queue_tag_depth(q)		((q)->queue_tags->busy)
#define blk_queue_tag_queue(q)		((q)->queue_tags->busy < (q)->queue_tags->max_depth)
#define blk_rq_tagged(rq)		((rq)->flags & REQ_QUEUED)
extern int blk_queue_start_tag(request_queue_t *, struct request *);
extern struct request *blk_queue_find_tag(request_queue_t *, int);
extern void blk_queue_end_tag(request_queue_t *, struct request *);
extern int blk_queue_init_tags(request_queue_t *, int, struct blk_queue_tag *);
extern void blk_queue_free_tags(request_queue_t *);
extern int blk_queue_resize_tags(request_queue_t *, int);
extern void blk_queue_invalidate_tags(request_queue_t *);
extern long blk_congestion_wait(int rw, long timeout);

extern void blk_rq_bio_prep(request_queue_t *, struct request *, struct bio *);
extern int blkdev_issue_flush(struct block_device *, sector_t *);

#define MAX_PHYS_SEGMENTS 128
#define MAX_HW_SEGMENTS 128
#define SAFE_MAX_SECTORS 255
#define BLK_DEF_MAX_SECTORS 1024

#define MAX_SEGMENT_SIZE	65536

#define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)

static inline int queue_hardsect_size(request_queue_t *q)
{
	int retval = 512;

	if (q && q->hardsect_size)
		retval = q->hardsect_size;

	return retval;
}

static inline int bdev_hardsect_size(struct block_device *bdev)
{
	return queue_hardsect_size(bdev_get_queue(bdev));
}

static inline int queue_dma_alignment(request_queue_t *q)
{
	int retval = 511;

	if (q && q->dma_alignment)
		retval = q->dma_alignment;

	return retval;
}

static inline int bdev_dma_aligment(struct block_device *bdev)
{
	return queue_dma_alignment(bdev_get_queue(bdev));
}

#define blk_finished_io(nsects)	do { } while (0)
#define blk_started_io(nsects)	do { } while (0)

/* assumes size > 256 */
static inline unsigned int blksize_bits(unsigned int size)
{
	unsigned int bits = 8;
	do {
		bits++;
		size >>= 1;
	} while (size > 256);
	return bits;
}

static inline unsigned int block_size(struct block_device *bdev)
{
	return bdev->bd_block_size;
}

typedef struct {struct page *v;} Sector;

unsigned char *read_dev_sector(struct block_device *, sector_t, Sector *);

static inline void put_dev_sector(Sector p)
{
	page_cache_release(p.v);
}

struct work_struct;
int kblockd_schedule_work(struct work_struct *work);
void kblockd_flush(void);

#ifdef CONFIG_LBD
# include <asm/div64.h>
# define sector_div(a, b) do_div(a, b)
#else
# define sector_div(n, b)( \
{ \
	int _res; \
	_res = (n) % (b); \
	(n) /= (b); \
	_res; \
} \
)
#endif 

#define MODULE_ALIAS_BLOCKDEV(major,minor) \
	MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
#define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
	MODULE_ALIAS("block-major-" __stringify(major) "-*")


#endif