#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_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 */
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;
+ struct rb_node rb_node;
void *key;
+ struct cfq_queue *cfqq[2];
+
struct io_context *ioc;
unsigned long last_end_request;
- unsigned long last_queue;
+ sector_t last_request_pos;
+ 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 *);
+ 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 */
};
/*
int nr_batch_requests; /* Number of requests left in the batch */
struct as_io_context *aic;
- struct cfq_io_context *cic;
+ struct rb_root cic_root;
};
void put_io_context(struct io_context *ioc);
wait_queue_head_t wait[2];
};
+/*
+ * 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_CMD,
+ REQ_TYPE_ATA_TASK,
+ REQ_TYPE_ATA_TASKFILE,
+};
+
+/*
+ * 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) */
+ __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)
+
#define BLK_MAX_CDB 16
/*
* 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! */
- unsigned long flags; /* see REQ_ bits below */
+ struct list_head queuelist;
+ struct list_head donelist;
+
+ unsigned int cmd_flags;
+ enum rq_cmd_type_bits cmd_type;
/* Maintain bio traversal state for part by part I/O submission.
* hard_* are block layer internals, no driver should touch them!
struct bio *bio;
struct bio *biotail;
+ struct hlist_node hash; /* merge hash */
+ struct rb_node rb_node; /* sort/lookup */
+
+ /*
+ * two pointers are available for the IO schedulers, if they need
+ * more they have to dynamically allocate it.
+ */
void *elevator_private;
+ void *elevator_private2;
- unsigned short ioprio;
+ 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 request_list *rl;
- 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
- */
- struct request_pm_state *pm;
-
- /*
- * completion callback. end_io_data should be folded in with waiting
+ * completion callback.
*/
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
+ * State information carried for REQ_TYPE_PM_SUSPEND and REQ_TYPE_PM_RESUME
* requests. Some step values could eventually be made generic.
*/
struct request_pm_state
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,
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
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;
-
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+ struct blk_trace *blk_trace;
+#endif
/*
* reserved for flush operations
*/
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 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_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)
#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_suspend_request(rq) ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND)
+#define blk_pm_resume_request(rq) ((rq)->cmd_type == REQ_TYPE_PM_RESUME)
#define blk_pm_request(rq) \
- ((rq)->flags & (REQ_PM_SUSPEND | REQ_PM_RESUME))
+ (blk_pm_suspend_request(rq) || blk_pm_resume_request(rq))
-#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 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)
#define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist)
-#define rq_data_dir(rq) ((rq)->flags & 1)
+#define rq_data_dir(rq) ((rq)->cmd_flags & 1)
+
+/*
+ * 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)
static inline int blk_queue_full(struct request_queue *q, int rw)
{
#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)))
+ (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && blk_fs_request((rq)))
/*
* noop, requests are automagically marked as active/inactive by I/O
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 void blk_attempt_remerge(request_queue_t *, struct request *);
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 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 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 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,
- void (*done)(struct request *));
+ struct request *, int, rq_end_io_fn *);
static inline request_queue_t *bdev_get_queue(struct block_device *bdev)
{
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
}
/*
- * 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,
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 int blk_queue_ordered(request_queue_t *, unsigned, prepare_flush_fn *);
extern void blk_queue_issue_flush_fn(request_queue_t *, issue_flush_fn *);
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))
+extern void blk_put_queue(request_queue_t *);
/*
* 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)
+#define blk_rq_tagged(rq) ((rq)->cmd_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_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 struct blk_queue_tag *blk_init_tags(int);
+extern void blk_free_tags(struct blk_queue_tag *);
+extern void blk_congestion_end(int rw);
extern void blk_rq_bio_prep(request_queue_t *, struct request *, struct bio *);
extern int blkdev_issue_flush(struct block_device *, sector_t *);