blkdev.h 27.1 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3
#ifndef _LINUX_BLKDEV_H
#define _LINUX_BLKDEV_H

J
Jens Axboe 已提交
4 5
#ifdef CONFIG_BLOCK

6
#include <linux/sched.h>
L
Linus Torvalds 已提交
7 8 9 10 11 12 13 14 15 16 17 18
#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>
19
#include <linux/bsg.h>
L
Linus Torvalds 已提交
20 21 22

#include <asm/scatterlist.h>

23 24
struct scsi_ioctl_command;

L
Linus Torvalds 已提交
25
struct request_queue;
26
typedef struct request_queue request_queue_t __deprecated;
L
Linus Torvalds 已提交
27 28 29
struct elevator_queue;
typedef struct elevator_queue elevator_t;
struct request_pm_state;
30
struct blk_trace;
31 32
struct request;
struct sg_io_hdr;
L
Linus Torvalds 已提交
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

#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 {
65
	struct rb_node rb_node;
66 67
	void *key;

68 69
	struct cfq_queue *cfqq[2];

70 71 72
	struct io_context *ioc;

	unsigned long last_end_request;
73 74
	sector_t last_request_pos;

75 76 77 78
	unsigned long ttime_total;
	unsigned long ttime_samples;
	unsigned long ttime_mean;

79 80 81 82
	unsigned int seek_samples;
	u64 seek_total;
	sector_t seek_mean;

83 84
	struct list_head queue_list;

85 86
	void (*dtor)(struct io_context *); /* destructor */
	void (*exit)(struct io_context *); /* called on task exit */
L
Linus Torvalds 已提交
87 88 89 90 91 92 93 94 95
};

/*
 * 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;
96 97
	struct task_struct *task;

98
	unsigned int ioprio_changed;
L
Linus Torvalds 已提交
99 100 101 102 103 104 105 106

	/*
	 * 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;
107
	struct rb_root cic_root;
108
	void *ioc_data;
L
Linus Torvalds 已提交
109 110 111 112
};

void put_io_context(struct io_context *ioc);
void exit_io_context(void);
113
struct io_context *get_io_context(gfp_t gfp_flags, int node);
L
Linus Torvalds 已提交
114 115 116 117
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;
118
typedef void (rq_end_io_fn)(struct request *, int);
L
Linus Torvalds 已提交
119 120 121 122

struct request_list {
	int count[2];
	int starved[2];
T
Tejun Heo 已提交
123
	int elvpriv;
L
Linus Torvalds 已提交
124 125 126 127
	mempool_t *rq_pool;
	wait_queue_head_t wait[2];
};

128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146
/*
 * request command types
 */
enum rq_cmd_type_bits {
	REQ_TYPE_FS		= 1,	/* fs request */
	REQ_TYPE_BLOCK_PC,		/* scsi command */
	REQ_TYPE_SENSE,			/* sense request */
	REQ_TYPE_PM_SUSPEND,		/* suspend request */
	REQ_TYPE_PM_RESUME,		/* resume request */
	REQ_TYPE_PM_SHUTDOWN,		/* shutdown request */
	REQ_TYPE_FLUSH,			/* flush request */
	REQ_TYPE_SPECIAL,		/* driver defined type */
	REQ_TYPE_LINUX_BLOCK,		/* generic block layer message */
	/*
	 * for ATA/ATAPI devices. this really doesn't belong here, ide should
	 * use REQ_TYPE_SPECIAL and use rq->cmd[0] with the range of driver
	 * private REQ_LB opcodes to differentiate what type of request this is
	 */
	REQ_TYPE_ATA_TASKFILE,
147
	REQ_TYPE_ATA_PC,
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
};

/*
 * For request of type REQ_TYPE_LINUX_BLOCK, rq->cmd[0] is the opcode being
 * sent down (similar to how REQ_TYPE_BLOCK_PC means that ->cmd[] holds a
 * SCSI cdb.
 *
 * 0x00 -> 0x3f are driver private, to be used for whatever purpose they need,
 * typically to differentiate REQ_TYPE_SPECIAL requests.
 *
 */
enum {
	/*
	 * just examples for now
	 */
	REQ_LB_OP_EJECT	= 0x40,		/* eject request */
	REQ_LB_OP_FLUSH = 0x41,		/* flush device */
};

/*
 * request type modified bits. 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_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 */
	__REQ_FAILED,		/* set if the request failed */
	__REQ_QUIET,		/* don't worry about errors */
	__REQ_PREEMPT,		/* set for "ide_preempt" requests */
	__REQ_ORDERED_COLOR,	/* is before or after barrier */
	__REQ_RW_SYNC,		/* request is sync (O_DIRECT) */
187
	__REQ_ALLOCED,		/* request came from our alloc pool */
188
	__REQ_RW_META,		/* metadata io request */
189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207
	__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_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_FAILED	(1 << __REQ_FAILED)
#define REQ_QUIET	(1 << __REQ_QUIET)
#define REQ_PREEMPT	(1 << __REQ_PREEMPT)
#define REQ_ORDERED_COLOR	(1 << __REQ_ORDERED_COLOR)
#define REQ_RW_SYNC	(1 << __REQ_RW_SYNC)
208
#define REQ_ALLOCED	(1 << __REQ_ALLOCED)
209
#define REQ_RW_META	(1 << __REQ_RW_META)
210

L
Linus Torvalds 已提交
211 212 213 214 215 216
#define BLK_MAX_CDB	16

/*
 * try to put the fields that are referenced together in the same cacheline
 */
struct request {
217 218 219
	struct list_head queuelist;
	struct list_head donelist;

220
	struct request_queue *q;
221

222 223
	unsigned int cmd_flags;
	enum rq_cmd_type_bits cmd_type;
L
Linus Torvalds 已提交
224 225 226 227 228 229

	/* 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 */
230
	sector_t hard_sector;		/* next sector to complete */
L
Linus Torvalds 已提交
231
	unsigned long nr_sectors;	/* no. of sectors left to submit */
232
	unsigned long hard_nr_sectors;	/* no. of sectors left to complete */
L
Linus Torvalds 已提交
233 234 235 236 237 238 239 240 241
	/* no. of sectors left to submit in the current segment */
	unsigned int current_nr_sectors;

	/* no. of sectors left to complete in the current segment */
	unsigned int hard_cur_sectors;

	struct bio *bio;
	struct bio *biotail;

242
	struct hlist_node hash;	/* merge hash */
243 244 245 246 247 248 249 250 251
	/*
	 * The rb_node is only used inside the io scheduler, requests
	 * are pruned when moved to the dispatch queue. So let the
	 * completion_data share space with the rb_node.
	 */
	union {
		struct rb_node rb_node;	/* sort/lookup */
		void *completion_data;
	};
252

253 254 255 256
	/*
	 * two pointers are available for the IO schedulers, if they need
	 * more they have to dynamically allocate it.
	 */
L
Linus Torvalds 已提交
257
	void *elevator_private;
258 259
	void *elevator_private2;

260
	struct gendisk *rq_disk;
L
Linus Torvalds 已提交
261 262 263 264 265 266 267 268 269 270 271 272 273 274
	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;

275 276
	unsigned short ioprio;

L
Linus Torvalds 已提交
277
	void *special;
278
	char *buffer;
L
Linus Torvalds 已提交
279

280 281 282 283 284
	int tag;
	int errors;

	int ref_count;

L
Linus Torvalds 已提交
285 286 287 288 289 290 291 292
	/*
	 * when request is used as a packet command carrier
	 */
	unsigned int cmd_len;
	unsigned char cmd[BLK_MAX_CDB];

	unsigned int data_len;
	unsigned int sense_len;
293
	void *data;
L
Linus Torvalds 已提交
294 295 296
	void *sense;

	unsigned int timeout;
297
	int retries;
L
Linus Torvalds 已提交
298 299

	/*
300
	 * completion callback.
L
Linus Torvalds 已提交
301 302 303
	 */
	rq_end_io_fn *end_io;
	void *end_io_data;
304 305 306

	/* for bidi */
	struct request *next_rq;
L
Linus Torvalds 已提交
307 308 309
};

/*
310
 * State information carried for REQ_TYPE_PM_SUSPEND and REQ_TYPE_PM_RESUME
L
Linus Torvalds 已提交
311 312 313 314 315 316 317 318 319 320 321 322 323
 * 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>

324 325 326 327
typedef void (request_fn_proc) (struct request_queue *q);
typedef int (make_request_fn) (struct request_queue *q, struct bio *bio);
typedef int (prep_rq_fn) (struct request_queue *, struct request *);
typedef void (unplug_fn) (struct request_queue *);
L
Linus Torvalds 已提交
328 329

struct bio_vec;
330 331
typedef int (merge_bvec_fn) (struct request_queue *, struct bio *, struct bio_vec *);
typedef void (prepare_flush_fn) (struct request_queue *, struct request *);
332
typedef void (softirq_done_fn)(struct request *);
L
Linus Torvalds 已提交
333 334 335 336 337 338 339 340 341 342 343

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 */
	int busy;			/* current depth */
	int max_depth;			/* what we will send to device */
344
	int real_max_depth;		/* what the array can hold */
L
Linus Torvalds 已提交
345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367
	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;
	make_request_fn		*make_request_fn;
	prep_rq_fn		*prep_rq_fn;
	unplug_fn		*unplug_fn;
	merge_bvec_fn		*merge_bvec_fn;
	prepare_flush_fn	*prepare_flush_fn;
368
	softirq_done_fn		*softirq_done_fn;
L
Linus Torvalds 已提交
369

370 371 372
	/*
	 * Dispatch queue sorting
	 */
J
Jens Axboe 已提交
373
	sector_t		end_sector;
374 375
	struct request		*boundary_rq;

L
Linus Torvalds 已提交
376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395
	/*
	 * 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;

	/*
	 * queue needs bounce pages for pages above this limit
	 */
	unsigned long		bounce_pfn;
A
Al Viro 已提交
396
	gfp_t			bounce_gfp;
L
Linus Torvalds 已提交
397 398 399 400 401 402 403

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

	/*
已提交
404 405 406
	 * protects queue structures from reentrancy. ->__queue_lock should
	 * _never_ be used directly, it is queue private. always use
	 * ->queue_lock.
L
Linus Torvalds 已提交
407
	 */
已提交
408
	spinlock_t		__queue_lock;
L
Linus Torvalds 已提交
409 410 411 412 413 414 415 416 417 418 419 420 421 422 423
	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;

424 425
	unsigned int		max_sectors;
	unsigned int		max_hw_sectors;
L
Linus Torvalds 已提交
426 427 428 429 430 431 432 433 434
	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;
435
	struct list_head	tag_busy_list;
L
Linus Torvalds 已提交
436

437
	unsigned int		nr_sorted;
L
Linus Torvalds 已提交
438 439 440 441 442 443 444
	unsigned int		in_flight;

	/*
	 * sg stuff
	 */
	unsigned int		sg_timeout;
	unsigned int		sg_reserved_size;
445
	int			node;
446
#ifdef CONFIG_BLK_DEV_IO_TRACE
447
	struct blk_trace	*blk_trace;
448
#endif
L
Linus Torvalds 已提交
449 450 451
	/*
	 * reserved for flush operations
	 */
452 453 454 455
	unsigned int		ordered, next_ordered, ordseq;
	int			orderr, ordcolor;
	struct request		pre_flush_rq, bar_rq, post_flush_rq;
	struct request		*orig_bar_rq;
456 457

	struct mutex		sysfs_lock;
458 459 460 461

#if defined(CONFIG_BLK_DEV_BSG)
	struct bsg_class_device bsg_dev;
#endif
L
Linus Torvalds 已提交
462 463 464 465 466
};

#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 */
467 468
#define	QUEUE_FLAG_READFULL	3	/* read queue has been filled */
#define QUEUE_FLAG_WRITEFULL	4	/* write queue has been filled */
L
Linus Torvalds 已提交
469 470 471
#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 */
J
Jens Axboe 已提交
472
#define QUEUE_FLAG_ELVSWITCH	8	/* don't use elevator, just do FIFO */
473
#define QUEUE_FLAG_BIDI		9	/* queue supports bidi requests */
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

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,
};
L
Linus Torvalds 已提交
514 515 516 517

#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)
518
#define blk_queue_flushing(q)	((q)->ordseq)
L
Linus Torvalds 已提交
519

520 521 522 523 524 525 526
#define blk_fs_request(rq)	((rq)->cmd_type == REQ_TYPE_FS)
#define blk_pc_request(rq)	((rq)->cmd_type == REQ_TYPE_BLOCK_PC)
#define blk_special_request(rq)	((rq)->cmd_type == REQ_TYPE_SPECIAL)
#define blk_sense_request(rq)	((rq)->cmd_type == REQ_TYPE_SENSE)

#define blk_noretry_request(rq)	((rq)->cmd_flags & REQ_FAILFAST)
#define blk_rq_started(rq)	((rq)->cmd_flags & REQ_STARTED)
L
Linus Torvalds 已提交
527 528 529

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

530 531
#define blk_pm_suspend_request(rq)	((rq)->cmd_type == REQ_TYPE_PM_SUSPEND)
#define blk_pm_resume_request(rq)	((rq)->cmd_type == REQ_TYPE_PM_RESUME)
L
Linus Torvalds 已提交
532
#define blk_pm_request(rq)	\
533
	(blk_pm_suspend_request(rq) || blk_pm_resume_request(rq))
L
Linus Torvalds 已提交
534

535 536 537
#define blk_sorted_rq(rq)	((rq)->cmd_flags & REQ_SORTED)
#define blk_barrier_rq(rq)	((rq)->cmd_flags & REQ_HARDBARRIER)
#define blk_fua_rq(rq)		((rq)->cmd_flags & REQ_FUA)
538
#define blk_bidi_rq(rq)		((rq)->next_rq != NULL)
539
#define blk_empty_barrier(rq)	(blk_barrier_rq(rq) && blk_fs_request(rq) && !(rq)->hard_nr_sectors)
540 541
/* rq->queuelist of dequeued request must be list_empty() */
#define blk_queued_rq(rq)	(!list_empty(&(rq)->queuelist))
L
Linus Torvalds 已提交
542 543 544

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

545
#define rq_data_dir(rq)		((rq)->cmd_flags & 1)
L
Linus Torvalds 已提交
546

547 548 549 550
/*
 * We regard a request as sync, if it's a READ or a SYNC write.
 */
#define rq_is_sync(rq)		(rq_data_dir((rq)) == READ || (rq)->cmd_flags & REQ_RW_SYNC)
551
#define rq_is_meta(rq)		((rq)->cmd_flags & REQ_RW_META)
552

L
Linus Torvalds 已提交
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
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)	\
584
	(!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && blk_fs_request((rq)))
L
Linus Torvalds 已提交
585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605

/*
 * 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)

606 607 608 609 610
/*
 * default timeout for SG_IO if none specified
 */
#define BLK_DEFAULT_SG_TIMEOUT	(60 * HZ)

611
#ifdef CONFIG_BOUNCE
L
Linus Torvalds 已提交
612
extern int init_emergency_isa_pool(void);
613
extern void blk_queue_bounce(struct request_queue *q, struct bio **bio);
L
Linus Torvalds 已提交
614 615 616 617 618
#else
static inline int init_emergency_isa_pool(void)
{
	return 0;
}
619
static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
L
Linus Torvalds 已提交
620 621 622 623
{
}
#endif /* CONFIG_MMU */

624 625 626 627 628 629 630
struct req_iterator {
	int i;
	struct bio *bio;
};

/* This should not be used directly - use rq_for_each_segment */
#define __rq_for_each_bio(_bio, rq)	\
L
Linus Torvalds 已提交
631 632 633
	if ((rq->bio))			\
		for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next)

634 635 636 637 638 639 640
#define rq_for_each_segment(bvl, _rq, _iter)			\
	__rq_for_each_bio(_iter.bio, _rq)			\
		bio_for_each_segment(bvl, _iter.bio, _iter.i)

#define rq_iter_last(rq, _iter)					\
		(_iter.bio->bi_next == NULL && _iter.i == _iter.bio->bi_vcnt-1)

L
Linus Torvalds 已提交
641 642 643 644 645
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 *);
646
extern void __blk_put_request(struct request_queue *, struct request *);
647
extern void blk_end_sync_rq(struct request *rq, int error);
648 649 650 651 652 653
extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
extern void blk_insert_request(struct request_queue *, struct request *, int, void *);
extern void blk_requeue_request(struct request_queue *, struct request *);
extern void blk_plug_device(struct request_queue *);
extern int blk_remove_plug(struct request_queue *);
extern void blk_recount_segments(struct request_queue *, struct bio *);
654 655
extern int scsi_cmd_ioctl(struct file *, struct request_queue *,
			  struct gendisk *, unsigned int, void __user *);
656 657
extern int sg_scsi_ioctl(struct file *, struct request_queue *,
		struct gendisk *, struct scsi_ioctl_command __user *);
658

J
Jens Axboe 已提交
659 660 661
/*
 * Temporary export, until SCSI gets fixed up.
 */
N
NeilBrown 已提交
662 663
extern int blk_rq_append_bio(struct request_queue *q, struct request *rq,
			     struct bio *bio);
J
Jens Axboe 已提交
664

665 666 667 668 669
/*
 * A queue has just exitted congestion.  Note this in the global counter of
 * congested queues, and wake up anyone who was waiting for requests to be
 * put back.
 */
670
static inline void blk_clear_queue_congested(struct request_queue *q, int rw)
671 672 673 674 675 676 677 678
{
	clear_bdi_congested(&q->backing_dev_info, rw);
}

/*
 * A queue has just entered congestion.  Flag that in the queue's VM-visible
 * state flags and increment the global gounter of congested queues.
 */
679
static inline void blk_set_queue_congested(struct request_queue *q, int rw)
680 681 682 683
{
	set_bdi_congested(&q->backing_dev_info, rw);
}

684 685
extern void blk_start_queue(struct request_queue *q);
extern void blk_stop_queue(struct request_queue *q);
L
Linus Torvalds 已提交
686
extern void blk_sync_queue(struct request_queue *q);
687 688 689 690
extern void __blk_stop_queue(struct request_queue *q);
extern void blk_run_queue(struct request_queue *);
extern void blk_start_queueing(struct request_queue *);
extern int blk_rq_map_user(struct request_queue *, struct request *, void __user *, unsigned long);
J
Jens Axboe 已提交
691
extern int blk_rq_unmap_user(struct bio *);
692 693
extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t);
extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
694
			       struct sg_iovec *, int, unsigned int);
695
extern int blk_execute_rq(struct request_queue *, struct gendisk *,
696
			  struct request *, int);
697
extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
698
				  struct request *, int, rq_end_io_fn *);
699
extern int blk_verify_command(unsigned char *, int);
700
extern void blk_unplug(struct request_queue *q);
701

702
static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
L
Linus Torvalds 已提交
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
{
	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.
 */
729 730
extern int blk_end_request(struct request *rq, int error, int nr_bytes);
extern int __blk_end_request(struct request *rq, int error, int nr_bytes);
L
Linus Torvalds 已提交
731 732
extern int end_that_request_first(struct request *, int, int);
extern int end_that_request_chunk(struct request *, int, int);
733
extern void end_that_request_last(struct request *, int);
734 735 736
extern void end_request(struct request *, int);
extern void end_queued_request(struct request *, int);
extern void end_dequeued_request(struct request *, int);
737 738
extern void blk_complete_request(struct request *);

L
Linus Torvalds 已提交
739 740 741 742 743 744 745 746 747 748
/*
 * 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)
{
749
	elv_dequeue_request(req->q, req);
L
Linus Torvalds 已提交
750 751 752 753 754
}

/*
 * Access functions for manipulating queue properties
 */
755
extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn,
756
					spinlock_t *lock, int node_id);
757 758 759 760 761 762 763 764 765 766 767 768 769 770
extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *);
extern void blk_cleanup_queue(struct request_queue *);
extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
extern void blk_queue_bounce_limit(struct request_queue *, u64);
extern void blk_queue_max_sectors(struct request_queue *, unsigned int);
extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short);
extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short);
extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
extern void blk_queue_hardsect_size(struct request_queue *, unsigned short);
extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn);
extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *);
extern void blk_queue_dma_alignment(struct request_queue *, int);
771
extern void blk_queue_update_dma_alignment(struct request_queue *, int);
772
extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
L
Linus Torvalds 已提交
773
extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
774 775 776
extern int blk_queue_ordered(struct request_queue *, unsigned, prepare_flush_fn *);
extern int blk_do_ordered(struct request_queue *, struct request **);
extern unsigned blk_ordered_cur_seq(struct request_queue *);
777
extern unsigned blk_ordered_req_seq(struct request *);
778
extern void blk_ordered_complete_seq(struct request_queue *, unsigned, int);
L
Linus Torvalds 已提交
779

780
extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
L
Linus Torvalds 已提交
781
extern void blk_dump_rq_flags(struct request *, char *);
782 783
extern void generic_unplug_device(struct request_queue *);
extern void __generic_unplug_device(struct request_queue *);
L
Linus Torvalds 已提交
784 785
extern long nr_blockdev_pages(void);

786 787 788 789
int blk_get_queue(struct request_queue *);
struct request_queue *blk_alloc_queue(gfp_t);
struct request_queue *blk_alloc_queue_node(gfp_t, int);
extern void blk_put_queue(struct request_queue *);
L
Linus Torvalds 已提交
790 791 792 793 794 795

/*
 * 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)
796
#define blk_rq_tagged(rq)		((rq)->cmd_flags & REQ_QUEUED)
797 798 799 800 801 802 803
extern int blk_queue_start_tag(struct request_queue *, struct request *);
extern struct request *blk_queue_find_tag(struct request_queue *, int);
extern void blk_queue_end_tag(struct request_queue *, struct request *);
extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *);
extern void blk_queue_free_tags(struct request_queue *);
extern int blk_queue_resize_tags(struct request_queue *, int);
extern void blk_queue_invalidate_tags(struct request_queue *);
804 805
extern struct blk_queue_tag *blk_init_tags(int);
extern void blk_free_tags(struct blk_queue_tag *);
L
Linus Torvalds 已提交
806

807 808 809 810 811 812 813 814
static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
						int tag)
{
	if (unlikely(bqt == NULL || tag >= bqt->real_max_depth))
		return NULL;
	return bqt->tag_index[tag];
}

L
Linus Torvalds 已提交
815 816 817 818
extern int blkdev_issue_flush(struct block_device *, sector_t *);

#define MAX_PHYS_SEGMENTS 128
#define MAX_HW_SEGMENTS 128
819 820
#define SAFE_MAX_SECTORS 255
#define BLK_DEF_MAX_SECTORS 1024
L
Linus Torvalds 已提交
821 822 823 824 825

#define MAX_SEGMENT_SIZE	65536

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

826
static inline int queue_hardsect_size(struct request_queue *q)
L
Linus Torvalds 已提交
827 828 829 830 831 832 833 834 835 836 837 838 839 840
{
	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));
}

841
static inline int queue_dma_alignment(struct request_queue *q)
L
Linus Torvalds 已提交
842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861
{
	int retval = 511;

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

	return retval;
}

/* 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;
}

862
static inline unsigned int block_size(struct block_device *bdev)
L
Linus Torvalds 已提交
863 864 865 866 867 868 869 870 871 872 873 874 875 876 877
{
	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);
A
Andrew Morton 已提交
878
void kblockd_flush_work(struct work_struct *work);
L
Linus Torvalds 已提交
879 880 881 882 883 884 885

#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) "-*")


886 887 888 889 890 891 892 893 894 895 896
#else /* CONFIG_BLOCK */
/*
 * stubs for when the block layer is configured out
 */
#define buffer_heads_over_limit 0

static inline long nr_blockdev_pages(void)
{
	return 0;
}

897 898 899
static inline void exit_io_context(void)
{
}
900 901 902

#endif /* CONFIG_BLOCK */

L
Linus Torvalds 已提交
903
#endif