#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 <asm/scatterlist.h>
+struct scsi_ioctl_command;
+
struct request_queue;
typedef struct request_queue request_queue_t;
-struct elevator_s;
-typedef struct elevator_s elevator_t;
+struct elevator_queue;
+typedef struct elevator_queue elevator_t;
struct request_pm_state;
+struct blk_trace;
#define BLKDEV_MIN_RQ 4
#define BLKDEV_MAX_RQ 128 /* Default maximum */
sector_t seek_mean;
};
+struct cfq_queue;
+struct cfq_io_context {
+ struct rb_node rb_node;
+ void *key;
+
+ struct cfq_queue *cfqq[2];
+
+ struct io_context *ioc;
+
+ unsigned long last_end_request;
+ sector_t last_request_pos;
+ unsigned long last_queue;
+
+ unsigned long ttime_total;
+ unsigned long ttime_samples;
+ unsigned long ttime_mean;
+
+ unsigned int seek_samples;
+ u64 seek_total;
+ sector_t seek_mean;
+
+ struct list_head queue_list;
+
+ void (*dtor)(struct io_context *); /* destructor */
+ void (*exit)(struct io_context *); /* called on task exit */
+};
+
/*
* This is the per-process I/O subsystem state. It is refcounted and
* kmalloc'ed. Currently all fields are modified in process io context
*/
struct io_context {
atomic_t refcount;
- pid_t pid;
+ struct task_struct *task;
+
+ int (*set_ioprio)(struct io_context *, unsigned int);
/*
* For request batching
int nr_batch_requests; /* Number of requests left in the batch */
struct as_io_context *aic;
+ struct rb_root cic_root;
};
void put_io_context(struct io_context *ioc);
void exit_io_context(void);
-struct io_context *get_io_context(int gfp_flags);
+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];
};
* try to put the fields that are referenced together in the same cacheline
*/
struct request {
- struct list_head queuelist; /* looking for ->queue? you must _not_
- * access it directly, use
- * blkdev_dequeue_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.
/* no. of sectors left to complete in the current segment */
unsigned int hard_cur_sectors;
- /* no. of segments left to submit in the current bio */
- unsigned short nr_cbio_segments;
- /* no. of sectors left to submit in the current bio */
- unsigned long nr_cbio_sectors;
-
- struct bio *cbio; /* next bio to submit */
- struct bio *bio; /* next unfinished bio to complete */
+ struct bio *bio;
struct bio *biotail;
void *elevator_private;
+ void *completion_data;
int rq_status; /* should split this into a few status bits */
- struct gendisk *rq_disk;
int errors;
+ struct gendisk *rq_disk;
unsigned long start_time;
/* Number of scatter-gather DMA addr+len pairs after
*/
unsigned short nr_hw_segments;
+ unsigned short ioprio;
+
int tag;
- char *buffer;
int ref_count;
request_queue_t *q;
struct completion *waiting;
void *special;
+ char *buffer;
/*
* when request is used as a packet command carrier
unsigned char cmd[BLK_MAX_CDB];
unsigned int data_len;
- void *data;
-
unsigned int sense_len;
+ void *data;
void *sense;
unsigned int timeout;
+ int retries;
/*
- * For Power Management requests
+ * completion callback. end_io_data should be folded in with waiting
*/
- struct request_pm_state *pm;
+ rq_end_io_fn *end_io;
+ void *end_io_data;
};
/*
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_PM_SUSPEND, /* suspend request */
__REQ_PM_RESUME, /* resume request */
__REQ_PM_SHUTDOWN, /* shutdown request */
- __REQ_BAR_PREFLUSH, /* barrier pre-flush done */
- __REQ_BAR_POSTFLUSH, /* barrier post-flush */
+ __REQ_ORDERED_COLOR, /* is before or after barrier */
+ __REQ_RW_SYNC, /* request is sync (O_DIRECT) */
__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_PM_SUSPEND (1 << __REQ_PM_SUSPEND)
#define REQ_PM_RESUME (1 << __REQ_PM_RESUME)
#define REQ_PM_SHUTDOWN (1 << __REQ_PM_SHUTDOWN)
-#define REQ_BAR_PREFLUSH (1 << __REQ_BAR_PREFLUSH)
-#define REQ_BAR_POSTFLUSH (1 << __REQ_BAR_POSTFLUSH)
+#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR)
+#define REQ_RW_SYNC (1 << __REQ_RW_SYNC)
/*
* State information carried for REQ_PM_SUSPEND and REQ_PM_RESUME
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,
};
-#define BLK_TAGS_PER_LONG (sizeof(unsigned long) * 8)
-#define BLK_TAGS_MASK (BLK_TAGS_PER_LONG - 1)
-
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 queue_head;
struct request *last_merge;
- elevator_t elevator;
+ elevator_t *elevator;
/*
* the queue request freelist, one for reads and one for writes
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
* queue needs bounce pages for pages above this limit
*/
unsigned long bounce_pfn;
- int bounce_gfp;
+ gfp_t bounce_gfp;
/*
* various queue flags, see QUEUE_* below
unsigned long queue_flags;
/*
- * protects queue structures from reentrancy
+ * 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;
/*
unsigned long nr_requests; /* Max # of requests */
unsigned int nr_congestion_on;
unsigned int nr_congestion_off;
+ unsigned int nr_batching;
- unsigned short max_sectors;
- unsigned short max_hw_sectors;
+ unsigned int max_sectors;
+ unsigned int max_hw_sectors;
unsigned short max_phys_segments;
unsigned short max_hw_segments;
unsigned short hardsect_size;
struct blk_queue_tag *queue_tags;
- atomic_t refcnt;
-
+ unsigned int nr_sorted;
unsigned int in_flight;
/*
*/
unsigned int sg_timeout;
unsigned int sg_reserved_size;
+ int node;
+
+ struct blk_trace *blk_trace;
+
+ /*
+ * 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;
+
+ struct mutex sysfs_lock;
};
#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_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_ORDERED 8 /* supports ordered writes */
+#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_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_barrier_preflush(rq) ((rq)->flags & REQ_BAR_PREFLUSH)
-#define blk_barrier_postflush(rq) ((rq)->flags & REQ_BAR_POSTFLUSH)
+#define blk_fua_rq(rq) ((rq)->flags & REQ_FUA)
#define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist)
*/
#define blk_queue_headactive(q, head_active)
-/* current index into bio being processed for submission */
-#define blk_rq_idx(rq) ((rq)->cbio->bi_vcnt - (rq)->nr_cbio_segments)
-
-/* current bio vector being processed */
-#define blk_rq_vec(rq) (bio_iovec_idx((rq)->cbio, blk_rq_idx(rq)))
-
-/* current offset with respect to start of the segment being submitted */
-#define blk_rq_offset(rq) \
- (((rq)->hard_cur_sectors - (rq)->current_nr_sectors) << 9)
-
-/*
- * temporarily mapping a (possible) highmem bio (typically for PIO transfer)
- */
-
-/* Assumes rq->cbio != NULL */
-static inline char * rq_map_buffer(struct request *rq, unsigned long *flags)
-{
- return (__bio_kmap_irq(rq->cbio, blk_rq_idx(rq), flags)
- + blk_rq_offset(rq));
-}
-
-static inline void rq_unmap_buffer(char *buffer, unsigned long *flags)
-{
- __bio_kunmap_irq(buffer, flags);
-}
-
/*
* q->prep_rq_fn return values
*/
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_attempt_remerge(request_queue_t *, struct request *);
-extern void __blk_attempt_remerge(request_queue_t *, struct request *);
-extern struct request *blk_get_request(request_queue_t *, int, int);
-extern void blk_put_request(struct request *);
-extern void blk_insert_request(request_queue_t *, struct request *, int, void *, int);
+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 blk_phys_contig_segment(request_queue_t *q, struct bio *, struct bio *);
-extern int blk_hw_contig_segment(request_queue_t *q, struct bio *, struct bio *);
extern int scsi_cmd_ioctl(struct file *, struct gendisk *, unsigned int, void __user *);
+extern int sg_scsi_ioctl(struct file *, struct request_queue *,
+ struct gendisk *, struct scsi_ioctl_command __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 struct request *blk_rq_map_user(request_queue_t *, int, void __user *, unsigned int);
-extern int blk_rq_unmap_user(struct request *, struct bio *, unsigned int);
-extern int blk_execute_rq(request_queue_t *, struct gendisk *, struct request *);
+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)
{
*/
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 *);
-extern int process_that_request_first(struct request *, unsigned 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
static inline void blkdev_dequeue_request(struct request *req)
{
- BUG_ON(list_empty(&req->queuelist));
+ elv_dequeue_request(req->q, req);
+}
- list_del_init(&req->queuelist);
+/*
+ * 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--;
- if (req->rl)
- elv_remove_request(req->q, req);
+ 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 short);
+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_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 void blk_queue_ordered(request_queue_t *, int);
+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 blkdev_scsi_issue_flush_fn(request_queue_t *, struct gendisk *, sector_t *);
+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 long nr_blockdev_pages(void);
int blk_get_queue(request_queue_t *);
-request_queue_t *blk_alloc_queue(int);
-#define blk_put_queue(q) blk_cleanup_queue((q))
+request_queue_t *blk_alloc_queue(gfp_t);
+request_queue_t *blk_alloc_queue_node(gfp_t, int);
+extern void blk_put_queue(request_queue_t *);
/*
* tag stuff
extern long blk_congestion_wait(int rw, long timeout);
extern void blk_rq_bio_prep(request_queue_t *, struct request *, struct bio *);
-extern void blk_rq_prep_restart(struct request *);
extern int blkdev_issue_flush(struct block_device *, sector_t *);
#define MAX_PHYS_SEGMENTS 128
#define MAX_HW_SEGMENTS 128
-#define MAX_SECTORS 255
+#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)
-extern void drive_stat_acct(struct request *, int, int);
-
static inline int queue_hardsect_size(request_queue_t *q)
{
int retval = 512;
return bits;
}
-extern inline unsigned int block_size(struct block_device *bdev)
+static inline unsigned int block_size(struct block_device *bdev)
{
return bdev->bd_block_size;
}
git://git.onelab.eu / linux-2.6.git / blobdiff