blkdev.h 31.0 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>
20
#include <linux/smp.h>
L
Linus Torvalds 已提交
21 22 23

#include <asm/scatterlist.h>

24 25
struct scsi_ioctl_command;

L
Linus Torvalds 已提交
26 27 28 29
struct request_queue;
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

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

struct request;
38
typedef void (rq_end_io_fn)(struct request *, int);
L
Linus Torvalds 已提交
39 40 41 42

struct request_list {
	int count[2];
	int starved[2];
T
Tejun Heo 已提交
43
	int elvpriv;
L
Linus Torvalds 已提交
44 45 46 47
	mempool_t *rq_pool;
	wait_queue_head_t wait[2];
};

48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65
/*
 * 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_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,
66
	REQ_TYPE_ATA_PC,
67 68 69 70 71 72 73 74 75 76 77 78 79
};

/*
 * 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 {
	REQ_LB_OP_EJECT	= 0x40,		/* eject request */
D
David Woodhouse 已提交
80
	REQ_LB_OP_FLUSH = 0x41,		/* flush request */
81
	REQ_LB_OP_DISCARD = 0x42,	/* discard sectors */
82 83 84
};

/*
85
 * request type modified bits. first two bits match BIO_RW* bits, important
86 87 88 89
 */
enum rq_flag_bits {
	__REQ_RW,		/* not set, read. set, write */
	__REQ_FAILFAST,		/* no low level driver retries */
D
David Woodhouse 已提交
90
	__REQ_DISCARD,		/* request to discard sectors */
91 92 93 94 95 96 97 98 99 100 101 102 103 104
	__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) */
105
	__REQ_ALLOCED,		/* request came from our alloc pool */
106
	__REQ_RW_META,		/* metadata io request */
107
	__REQ_COPY_USER,	/* contains copies of user pages */
108
	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
109 110 111 112
	__REQ_NR_BITS,		/* stops here */
};

#define REQ_RW		(1 << __REQ_RW)
D
David Woodhouse 已提交
113
#define REQ_DISCARD	(1 << __REQ_DISCARD)
114 115 116 117 118 119 120 121 122 123 124 125 126 127 128
#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)
129
#define REQ_ALLOCED	(1 << __REQ_ALLOCED)
130
#define REQ_RW_META	(1 << __REQ_RW_META)
131
#define REQ_COPY_USER	(1 << __REQ_COPY_USER)
132
#define REQ_INTEGRITY	(1 << __REQ_INTEGRITY)
133

L
Linus Torvalds 已提交
134 135 136
#define BLK_MAX_CDB	16

/*
J
Jens Axboe 已提交
137 138 139
 * try to put the fields that are referenced together in the same cacheline.
 * if you modify this structure, be sure to check block/blk-core.c:rq_init()
 * as well!
L
Linus Torvalds 已提交
140 141
 */
struct request {
142
	struct list_head queuelist;
143 144
	struct call_single_data csd;
	int cpu;
145

146
	struct request_queue *q;
147

148 149
	unsigned int cmd_flags;
	enum rq_cmd_type_bits cmd_type;
L
Linus Torvalds 已提交
150 151 152 153 154 155

	/* 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 */
156
	sector_t hard_sector;		/* next sector to complete */
L
Linus Torvalds 已提交
157
	unsigned long nr_sectors;	/* no. of sectors left to submit */
158
	unsigned long hard_nr_sectors;	/* no. of sectors left to complete */
L
Linus Torvalds 已提交
159 160 161 162 163 164 165 166 167
	/* 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;

168
	struct hlist_node hash;	/* merge hash */
169 170 171 172 173 174 175 176 177
	/*
	 * 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;
	};
178

179 180 181 182
	/*
	 * two pointers are available for the IO schedulers, if they need
	 * more they have to dynamically allocate it.
	 */
L
Linus Torvalds 已提交
183
	void *elevator_private;
184 185
	void *elevator_private2;

186
	struct gendisk *rq_disk;
L
Linus Torvalds 已提交
187 188 189 190 191 192 193
	unsigned long start_time;

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

194 195
	unsigned short ioprio;

L
Linus Torvalds 已提交
196
	void *special;
197
	char *buffer;
L
Linus Torvalds 已提交
198

199 200 201 202 203
	int tag;
	int errors;

	int ref_count;

L
Linus Torvalds 已提交
204 205 206
	/*
	 * when request is used as a packet command carrier
	 */
207 208 209
	unsigned short cmd_len;
	unsigned char __cmd[BLK_MAX_CDB];
	unsigned char *cmd;
L
Linus Torvalds 已提交
210 211

	unsigned int data_len;
212
	unsigned int extra_len;	/* length of alignment and padding */
L
Linus Torvalds 已提交
213
	unsigned int sense_len;
214
	void *data;
L
Linus Torvalds 已提交
215 216 217
	void *sense;

	unsigned int timeout;
218
	int retries;
L
Linus Torvalds 已提交
219 220

	/*
221
	 * completion callback.
L
Linus Torvalds 已提交
222 223 224
	 */
	rq_end_io_fn *end_io;
	void *end_io_data;
225 226 227

	/* for bidi */
	struct request *next_rq;
L
Linus Torvalds 已提交
228 229
};

230 231 232 233 234
static inline unsigned short req_get_ioprio(struct request *req)
{
	return req->ioprio;
}

L
Linus Torvalds 已提交
235
/*
236
 * State information carried for REQ_TYPE_PM_SUSPEND and REQ_TYPE_PM_RESUME
L
Linus Torvalds 已提交
237 238 239 240 241 242 243 244 245 246 247 248 249
 * 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>

250 251 252 253
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 *);
D
David Woodhouse 已提交
254
typedef int (prepare_discard_fn) (struct request_queue *, struct request *);
L
Linus Torvalds 已提交
255 256

struct bio_vec;
257 258 259 260 261 262 263 264
struct bvec_merge_data {
	struct block_device *bi_bdev;
	sector_t bi_sector;
	unsigned bi_size;
	unsigned long bi_rw;
};
typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *,
			     struct bio_vec *);
265
typedef void (prepare_flush_fn) (struct request_queue *, struct request *);
266
typedef void (softirq_done_fn)(struct request *);
267
typedef int (dma_drain_needed_fn)(struct request *);
L
Linus Torvalds 已提交
268 269 270 271 272 273 274 275 276 277 278

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 */
279
	int real_max_depth;		/* what the array can hold */
L
Linus Torvalds 已提交
280 281 282
	atomic_t refcnt;		/* map can be shared */
};

283 284 285
#define BLK_SCSI_MAX_CMDS	(256)
#define BLK_SCSI_CMD_PER_LONG	(BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))

286
struct blk_cmd_filter {
287 288 289 290 291
	unsigned long read_ok[BLK_SCSI_CMD_PER_LONG];
	unsigned long write_ok[BLK_SCSI_CMD_PER_LONG];
	struct kobject kobj;
};

L
Linus Torvalds 已提交
292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309
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;
D
David Woodhouse 已提交
310
	prepare_discard_fn	*prepare_discard_fn;
L
Linus Torvalds 已提交
311 312
	merge_bvec_fn		*merge_bvec_fn;
	prepare_flush_fn	*prepare_flush_fn;
313
	softirq_done_fn		*softirq_done_fn;
314
	dma_drain_needed_fn	*dma_drain_needed;
L
Linus Torvalds 已提交
315

316 317 318
	/*
	 * Dispatch queue sorting
	 */
J
Jens Axboe 已提交
319
	sector_t		end_sector;
320 321
	struct request		*boundary_rq;

L
Linus Torvalds 已提交
322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341
	/*
	 * 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
342
	gfp_t			bounce_gfp;
L
Linus Torvalds 已提交
343 344 345 346 347 348 349

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

	/*
已提交
350 351 352
	 * 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
353
	 */
已提交
354
	spinlock_t		__queue_lock;
L
Linus Torvalds 已提交
355 356 357 358 359 360 361 362 363 364 365 366 367 368 369
	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;

370 371
	unsigned int		max_sectors;
	unsigned int		max_hw_sectors;
L
Linus Torvalds 已提交
372 373 374 375 376 377
	unsigned short		max_phys_segments;
	unsigned short		max_hw_segments;
	unsigned short		hardsect_size;
	unsigned int		max_segment_size;

	unsigned long		seg_boundary_mask;
J
James Bottomley 已提交
378 379
	void			*dma_drain_buffer;
	unsigned int		dma_drain_size;
380
	unsigned int		dma_pad_mask;
L
Linus Torvalds 已提交
381 382 383
	unsigned int		dma_alignment;

	struct blk_queue_tag	*queue_tags;
384
	struct list_head	tag_busy_list;
L
Linus Torvalds 已提交
385

386
	unsigned int		nr_sorted;
L
Linus Torvalds 已提交
387 388 389 390 391 392 393
	unsigned int		in_flight;

	/*
	 * sg stuff
	 */
	unsigned int		sg_timeout;
	unsigned int		sg_reserved_size;
394
	int			node;
395
#ifdef CONFIG_BLK_DEV_IO_TRACE
396
	struct blk_trace	*blk_trace;
397
#endif
L
Linus Torvalds 已提交
398 399 400
	/*
	 * reserved for flush operations
	 */
401 402 403 404
	unsigned int		ordered, next_ordered, ordseq;
	int			orderr, ordcolor;
	struct request		pre_flush_rq, bar_rq, post_flush_rq;
	struct request		*orig_bar_rq;
405 406

	struct mutex		sysfs_lock;
407 408 409 410

#if defined(CONFIG_BLK_DEV_BSG)
	struct bsg_class_device bsg_dev;
#endif
411
	struct blk_cmd_filter cmd_filter;
L
Linus Torvalds 已提交
412 413 414 415 416
};

#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 */
417 418
#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
419 420 421
#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
422
#define QUEUE_FLAG_ELVSWITCH	8	/* don't use elevator, just do FIFO */
423
#define QUEUE_FLAG_BIDI		9	/* queue supports bidi requests */
424
#define QUEUE_FLAG_NOMERGES    10	/* disable merge attempts */
425
#define QUEUE_FLAG_SAME_COMP   11	/* force complete on same CPU */
426

427 428
static inline int queue_is_locked(struct request_queue *q)
{
J
Jens Axboe 已提交
429
#ifdef CONFIG_SMP
430 431
	spinlock_t *lock = q->queue_lock;
	return lock && spin_is_locked(lock);
J
Jens Axboe 已提交
432 433 434
#else
	return 1;
#endif
435 436
}

N
Nick Piggin 已提交
437 438 439 440 441 442
static inline void queue_flag_set_unlocked(unsigned int flag,
					   struct request_queue *q)
{
	__set_bit(flag, &q->queue_flags);
}

J
Jens Axboe 已提交
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
static inline int queue_flag_test_and_clear(unsigned int flag,
					    struct request_queue *q)
{
	WARN_ON_ONCE(!queue_is_locked(q));

	if (test_bit(flag, &q->queue_flags)) {
		__clear_bit(flag, &q->queue_flags);
		return 1;
	}

	return 0;
}

static inline int queue_flag_test_and_set(unsigned int flag,
					  struct request_queue *q)
{
	WARN_ON_ONCE(!queue_is_locked(q));

	if (!test_bit(flag, &q->queue_flags)) {
		__set_bit(flag, &q->queue_flags);
		return 0;
	}

	return 1;
}

N
Nick Piggin 已提交
469 470
static inline void queue_flag_set(unsigned int flag, struct request_queue *q)
{
471
	WARN_ON_ONCE(!queue_is_locked(q));
N
Nick Piggin 已提交
472 473 474 475 476 477 478 479 480 481 482
	__set_bit(flag, &q->queue_flags);
}

static inline void queue_flag_clear_unlocked(unsigned int flag,
					     struct request_queue *q)
{
	__clear_bit(flag, &q->queue_flags);
}

static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
{
483
	WARN_ON_ONCE(!queue_is_locked(q));
N
Nick Piggin 已提交
484 485 486
	__clear_bit(flag, &q->queue_flags);
}

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
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
526 527 528 529

#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)
530
#define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
531
#define blk_queue_flushing(q)	((q)->ordseq)
L
Linus Torvalds 已提交
532

533 534 535 536 537 538 539
#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
540

541
#define blk_account_rq(rq)	(blk_rq_started(rq) && (blk_fs_request(rq) || blk_discard_rq(rq))) 
L
Linus Torvalds 已提交
542

543 544
#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
545
#define blk_pm_request(rq)	\
546
	(blk_pm_suspend_request(rq) || blk_pm_resume_request(rq))
L
Linus Torvalds 已提交
547

548 549 550
#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)
D
David Woodhouse 已提交
551
#define blk_discard_rq(rq)	((rq)->cmd_flags & REQ_DISCARD)
552
#define blk_bidi_rq(rq)		((rq)->next_rq != NULL)
553
#define blk_empty_barrier(rq)	(blk_barrier_rq(rq) && blk_fs_request(rq) && !(rq)->hard_nr_sectors)
554 555
/* rq->queuelist of dequeued request must be list_empty() */
#define blk_queued_rq(rq)	(!list_empty(&(rq)->queuelist))
L
Linus Torvalds 已提交
556 557 558

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

559
#define rq_data_dir(rq)		((rq)->cmd_flags & 1)
L
Linus Torvalds 已提交
560

561 562 563 564
/*
 * 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)
565
#define rq_is_meta(rq)		((rq)->cmd_flags & REQ_RW_META)
566

L
Linus Torvalds 已提交
567 568 569 570 571 572 573 574 575 576
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)
N
Nick Piggin 已提交
577
		queue_flag_set(QUEUE_FLAG_READFULL, q);
L
Linus Torvalds 已提交
578
	else
N
Nick Piggin 已提交
579
		queue_flag_set(QUEUE_FLAG_WRITEFULL, q);
L
Linus Torvalds 已提交
580 581 582 583 584
}

static inline void blk_clear_queue_full(struct request_queue *q, int rw)
{
	if (rw == READ)
N
Nick Piggin 已提交
585
		queue_flag_clear(QUEUE_FLAG_READFULL, q);
L
Linus Torvalds 已提交
586
	else
N
Nick Piggin 已提交
587
		queue_flag_clear(QUEUE_FLAG_WRITEFULL, q);
L
Linus Torvalds 已提交
588 589 590 591 592 593 594 595 596 597
}


/*
 * 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)	\
598 599
	(!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \
	 (blk_discard_rq(rq) || blk_fs_request((rq))))
L
Linus Torvalds 已提交
600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616

/*
 * 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
 */
617 618

#if BITS_PER_LONG == 32
L
Linus Torvalds 已提交
619
#define BLK_BOUNCE_HIGH		((u64)blk_max_low_pfn << PAGE_SHIFT)
620 621 622 623
#else
#define BLK_BOUNCE_HIGH		-1ULL
#endif
#define BLK_BOUNCE_ANY		(-1ULL)
L
Linus Torvalds 已提交
624 625
#define BLK_BOUNCE_ISA		(ISA_DMA_THRESHOLD)

626 627 628 629 630
/*
 * default timeout for SG_IO if none specified
 */
#define BLK_DEFAULT_SG_TIMEOUT	(60 * HZ)

631
#ifdef CONFIG_BOUNCE
L
Linus Torvalds 已提交
632
extern int init_emergency_isa_pool(void);
633
extern void blk_queue_bounce(struct request_queue *q, struct bio **bio);
L
Linus Torvalds 已提交
634 635 636 637 638
#else
static inline int init_emergency_isa_pool(void)
{
	return 0;
}
639
static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
L
Linus Torvalds 已提交
640 641 642 643
{
}
#endif /* CONFIG_MMU */

644 645 646 647 648 649 650
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
651 652 653
	if ((rq->bio))			\
		for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next)

654 655 656 657 658 659 660
#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
661 662 663 664
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);
665
extern void blk_rq_init(struct request_queue *q, struct request *rq);
L
Linus Torvalds 已提交
666
extern void blk_put_request(struct request *);
667 668 669 670 671
extern void __blk_put_request(struct request_queue *, struct request *);
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 *);
672
extern void blk_plug_device_unlocked(struct request_queue *);
673 674
extern int blk_remove_plug(struct request_queue *);
extern void blk_recount_segments(struct request_queue *, struct bio *);
675 676
extern int scsi_cmd_ioctl(struct file *, struct request_queue *,
			  struct gendisk *, unsigned int, void __user *);
677 678
extern int sg_scsi_ioctl(struct file *, struct request_queue *,
		struct gendisk *, struct scsi_ioctl_command __user *);
679

J
Jens Axboe 已提交
680 681 682
/*
 * Temporary export, until SCSI gets fixed up.
 */
N
NeilBrown 已提交
683 684
extern int blk_rq_append_bio(struct request_queue *q, struct request *rq,
			     struct bio *bio);
J
Jens Axboe 已提交
685

686 687 688 689 690
/*
 * 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.
 */
691
static inline void blk_clear_queue_congested(struct request_queue *q, int rw)
692 693 694 695 696 697 698 699
{
	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.
 */
700
static inline void blk_set_queue_congested(struct request_queue *q, int rw)
701 702 703 704
{
	set_bdi_congested(&q->backing_dev_info, rw);
}

705 706
extern void blk_start_queue(struct request_queue *q);
extern void blk_stop_queue(struct request_queue *q);
L
Linus Torvalds 已提交
707
extern void blk_sync_queue(struct request_queue *q);
708
extern void __blk_stop_queue(struct request_queue *q);
N
Nick Piggin 已提交
709
extern void __blk_run_queue(struct request_queue *);
710 711 712
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
713
extern int blk_rq_unmap_user(struct bio *);
714 715
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 *,
716
			       struct sg_iovec *, int, unsigned int);
717
extern int blk_execute_rq(struct request_queue *, struct gendisk *,
718
			  struct request *, int);
719
extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
720
				  struct request *, int, rq_end_io_fn *);
721
extern void blk_unplug(struct request_queue *q);
722

723
static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
L
Linus Torvalds 已提交
724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741
{
	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);
}

/*
742 743 744
 * blk_end_request() and friends.
 * __blk_end_request() and end_request() must be called with
 * the request queue spinlock acquired.
L
Linus Torvalds 已提交
745 746
 *
 * Several drivers define their own end_request and call
747 748
 * blk_end_request() for parts of the original function.
 * This prevents code duplication in drivers.
L
Linus Torvalds 已提交
749
 */
750 751 752 753 754 755
extern int blk_end_request(struct request *rq, int error,
				unsigned int nr_bytes);
extern int __blk_end_request(struct request *rq, int error,
				unsigned int nr_bytes);
extern int blk_end_bidi_request(struct request *rq, int error,
				unsigned int nr_bytes, unsigned int bidi_bytes);
756 757 758
extern void end_request(struct request *, int);
extern void end_queued_request(struct request *, int);
extern void end_dequeued_request(struct request *, int);
759 760 761
extern int blk_end_request_callback(struct request *rq, int error,
				unsigned int nr_bytes,
				int (drv_callback)(struct request *));
762 763
extern void blk_complete_request(struct request *);

L
Linus Torvalds 已提交
764
/*
765 766 767
 * blk_end_request() takes bytes instead of sectors as a complete size.
 * blk_rq_bytes() returns bytes left to complete in the entire request.
 * blk_rq_cur_bytes() returns bytes left to complete in the current segment.
L
Linus Torvalds 已提交
768
 */
769 770
extern unsigned int blk_rq_bytes(struct request *rq);
extern unsigned int blk_rq_cur_bytes(struct request *rq);
L
Linus Torvalds 已提交
771 772 773

static inline void blkdev_dequeue_request(struct request *req)
{
774
	elv_dequeue_request(req->q, req);
L
Linus Torvalds 已提交
775 776 777 778 779
}

/*
 * Access functions for manipulating queue properties
 */
780
extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn,
781
					spinlock_t *lock, int node_id);
782 783 784 785 786 787 788 789 790 791
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);
792
extern void blk_queue_dma_pad(struct request_queue *, unsigned int);
793
extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
794 795 796
extern int blk_queue_dma_drain(struct request_queue *q,
			       dma_drain_needed_fn *dma_drain_needed,
			       void *buf, unsigned int size);
797 798 799 800
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);
801
extern void blk_queue_update_dma_alignment(struct request_queue *, int);
802
extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
D
David Woodhouse 已提交
803
extern void blk_queue_set_discard(struct request_queue *, prepare_discard_fn *);
L
Linus Torvalds 已提交
804
extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
805 806 807
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 *);
808
extern unsigned blk_ordered_req_seq(struct request *);
809
extern void blk_ordered_complete_seq(struct request_queue *, unsigned, int);
L
Linus Torvalds 已提交
810

811
extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
L
Linus Torvalds 已提交
812
extern void blk_dump_rq_flags(struct request *, char *);
813 814
extern void generic_unplug_device(struct request_queue *);
extern void __generic_unplug_device(struct request_queue *);
L
Linus Torvalds 已提交
815 816
extern long nr_blockdev_pages(void);

817 818 819 820
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
821 822 823 824

/*
 * tag stuff
 */
825
#define blk_rq_tagged(rq)		((rq)->cmd_flags & REQ_QUEUED)
826 827 828 829 830 831 832
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 *);
833 834
extern struct blk_queue_tag *blk_init_tags(int);
extern void blk_free_tags(struct blk_queue_tag *);
L
Linus Torvalds 已提交
835

836 837 838 839 840 841 842 843
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
844
extern int blkdev_issue_flush(struct block_device *, sector_t *);
D
David Woodhouse 已提交
845 846 847 848 849 850 851 852 853 854
extern int blkdev_issue_discard(struct block_device *, sector_t sector,
				unsigned nr_sects);

static inline int sb_issue_discard(struct super_block *sb,
				   sector_t block, unsigned nr_blocks)
{
	block <<= (sb->s_blocksize_bits - 9);
	nr_blocks <<= (sb->s_blocksize_bits - 9);
	return blkdev_issue_discard(sb->s_bdev, block, nr_blocks);
}
L
Linus Torvalds 已提交
855

856 857 858
/*
* command filter functions
*/
859
extern int blk_verify_command(struct blk_cmd_filter *filter,
860
			      unsigned char *cmd, int has_write_perm);
861
extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter);
862

L
Linus Torvalds 已提交
863 864
#define MAX_PHYS_SEGMENTS 128
#define MAX_HW_SEGMENTS 128
865 866
#define SAFE_MAX_SECTORS 255
#define BLK_DEF_MAX_SECTORS 1024
L
Linus Torvalds 已提交
867 868 869 870 871

#define MAX_SEGMENT_SIZE	65536

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

872
static inline int queue_hardsect_size(struct request_queue *q)
L
Linus Torvalds 已提交
873 874 875 876 877 878 879 880 881 882 883 884 885 886
{
	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));
}

887
static inline int queue_dma_alignment(struct request_queue *q)
L
Linus Torvalds 已提交
888
{
889
	return q ? q->dma_alignment : 511;
L
Linus Torvalds 已提交
890 891 892 893 894 895 896 897 898 899 900 901 902
}

/* 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;
}

903
static inline unsigned int block_size(struct block_device *bdev)
L
Linus Torvalds 已提交
904 905 906 907 908 909 910 911 912 913 914 915 916 917
{
	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;
918
int kblockd_schedule_work(struct request_queue *q, struct work_struct *work);
A
Andrew Morton 已提交
919
void kblockd_flush_work(struct work_struct *work);
L
Linus Torvalds 已提交
920 921 922 923 924 925

#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) "-*")

926 927
#if defined(CONFIG_BLK_DEV_INTEGRITY)

928 929
#define INTEGRITY_FLAG_READ	2	/* verify data integrity on read */
#define INTEGRITY_FLAG_WRITE	4	/* generate data integrity on write */
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

struct blk_integrity_exchg {
	void			*prot_buf;
	void			*data_buf;
	sector_t		sector;
	unsigned int		data_size;
	unsigned short		sector_size;
	const char		*disk_name;
};

typedef void (integrity_gen_fn) (struct blk_integrity_exchg *);
typedef int (integrity_vrfy_fn) (struct blk_integrity_exchg *);
typedef void (integrity_set_tag_fn) (void *, void *, unsigned int);
typedef void (integrity_get_tag_fn) (void *, void *, unsigned int);

struct blk_integrity {
	integrity_gen_fn	*generate_fn;
	integrity_vrfy_fn	*verify_fn;
	integrity_set_tag_fn	*set_tag_fn;
	integrity_get_tag_fn	*get_tag_fn;

	unsigned short		flags;
	unsigned short		tuple_size;
	unsigned short		sector_size;
	unsigned short		tag_size;

	const char		*name;

	struct kobject		kobj;
};

extern int blk_integrity_register(struct gendisk *, struct blk_integrity *);
extern void blk_integrity_unregister(struct gendisk *);
extern int blk_integrity_compare(struct block_device *, struct block_device *);
extern int blk_rq_map_integrity_sg(struct request *, struct scatterlist *);
extern int blk_rq_count_integrity_sg(struct request *);

static inline unsigned short blk_integrity_tuple_size(struct blk_integrity *bi)
{
	if (bi)
		return bi->tuple_size;

	return 0;
}

static inline struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
{
	return bdev->bd_disk->integrity;
}

static inline unsigned int bdev_get_tag_size(struct block_device *bdev)
{
	struct blk_integrity *bi = bdev_get_integrity(bdev);

	if (bi)
		return bi->tag_size;

	return 0;
}

static inline int bdev_integrity_enabled(struct block_device *bdev, int rw)
{
	struct blk_integrity *bi = bdev_get_integrity(bdev);

	if (bi == NULL)
		return 0;

	if (rw == READ && bi->verify_fn != NULL &&
998
	    (bi->flags & INTEGRITY_FLAG_READ))
999 1000 1001
		return 1;

	if (rw == WRITE && bi->generate_fn != NULL &&
1002
	    (bi->flags & INTEGRITY_FLAG_WRITE))
1003 1004 1005 1006 1007 1008 1009
		return 1;

	return 0;
}

static inline int blk_integrity_rq(struct request *rq)
{
1010 1011 1012
	if (rq->bio == NULL)
		return 0;

1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028
	return bio_integrity(rq->bio);
}

#else /* CONFIG_BLK_DEV_INTEGRITY */

#define blk_integrity_rq(rq)			(0)
#define blk_rq_count_integrity_sg(a)		(0)
#define blk_rq_map_integrity_sg(a, b)		(0)
#define bdev_get_integrity(a)			(0)
#define bdev_get_tag_size(a)			(0)
#define blk_integrity_compare(a, b)		(0)
#define blk_integrity_register(a, b)		(0)
#define blk_integrity_unregister(a)		do { } while (0);

#endif /* CONFIG_BLK_DEV_INTEGRITY */

1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041
#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;
}

#endif /* CONFIG_BLOCK */

L
Linus Torvalds 已提交
1042
#endif