REQ_TYPE_ATA_PC,
};
-enum {
- BLK_RW_ASYNC = 0,
- BLK_RW_SYNC = 1,
-};
-
/*
* 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
enum {
REQ_LB_OP_EJECT = 0x40, /* eject request */
REQ_LB_OP_FLUSH = 0x41, /* flush request */
- REQ_LB_OP_DISCARD = 0x42, /* discard sectors */
};
/*
- * request type modified bits. first two bits match BIO_RW* bits, important
+ * request type modified bits. first four bits match BIO_RW* bits, important
*/
enum rq_flag_bits {
__REQ_RW, /* not set, read. set, write */
__REQ_FAILFAST_DEV, /* no driver retries of device errors */
__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
__REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */
+ /* above flags must match BIO_RW_* */
__REQ_DISCARD, /* request to discard sectors */
__REQ_SORTED, /* elevator knows about this request */
__REQ_SOFTBARRIER, /* may not be passed by ioscheduler */
__REQ_INTEGRITY, /* integrity metadata has been remapped */
__REQ_NOIDLE, /* Don't anticipate more IO after this one */
__REQ_IO_STAT, /* account I/O stat */
+ __REQ_MIXED_MERGE, /* merge of different types, fail separately */
__REQ_NR_BITS, /* stops here */
};
#define REQ_INTEGRITY (1 << __REQ_INTEGRITY)
#define REQ_NOIDLE (1 << __REQ_NOIDLE)
#define REQ_IO_STAT (1 << __REQ_IO_STAT)
+#define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE)
+
+#define REQ_FAILFAST_MASK (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | \
+ REQ_FAILFAST_DRIVER)
#define BLK_MAX_CDB 16
struct request {
struct list_head queuelist;
struct call_single_data csd;
- int cpu;
struct request_queue *q;
enum rq_cmd_type_bits cmd_type;
unsigned long atomic_flags;
+ int cpu;
+
/* the following two fields are internal, NEVER access directly */
- sector_t __sector; /* sector cursor */
unsigned int __data_len; /* total data len */
+ sector_t __sector; /* sector cursor */
struct bio *bio;
struct bio *biotail;
};
/*
- * two pointers are available for the IO schedulers, if they need
+ * Three pointers are available for the IO schedulers, if they need
* more they have to dynamically allocate it.
*/
void *elevator_private;
void *elevator_private2;
+ void *elevator_private3;
struct gendisk *rq_disk;
unsigned long start_time;
-
+#ifdef CONFIG_BLK_CGROUP
+ unsigned long long start_time_ns;
+ unsigned long long io_start_time_ns; /* when passed to hardware */
+#endif
/* Number of scatter-gather DMA addr+len pairs after
* physical address coalescing is performed.
*/
unsigned short ioprio;
+ int ref_count;
+
void *special; /* opaque pointer available for LLD use */
char *buffer; /* kaddr of the current segment if available */
int tag;
int errors;
- int ref_count;
-
/*
* when request is used as a packet command carrier
*/
- unsigned short cmd_len;
unsigned char __cmd[BLK_MAX_CDB];
unsigned char *cmd;
+ unsigned short cmd_len;
unsigned int extra_len; /* length of alignment and padding */
unsigned int sense_len;
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 *);
-typedef int (prepare_discard_fn) (struct request_queue *, struct request *);
struct bio_vec;
struct bvec_merge_data {
unsigned int alignment_offset;
unsigned int io_min;
unsigned int io_opt;
+ unsigned int max_discard_sectors;
+ unsigned int discard_granularity;
+ unsigned int discard_alignment;
unsigned short logical_block_size;
- unsigned short max_hw_segments;
- unsigned short max_phys_segments;
+ unsigned short max_segments;
unsigned char misaligned;
+ unsigned char discard_misaligned;
unsigned char no_cluster;
+ signed char discard_zeroes_data;
};
struct request_queue
make_request_fn *make_request_fn;
prep_rq_fn *prep_rq_fn;
unplug_fn *unplug_fn;
- prepare_discard_fn *prepare_discard_fn;
merge_bvec_fn *merge_bvec_fn;
prepare_flush_fn *prepare_flush_fn;
softirq_done_fn *softirq_done_fn;
#define QUEUE_FLAG_NONROT 14 /* non-rotational device (SSD) */
#define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */
#define QUEUE_FLAG_IO_STAT 15 /* do IO stats */
+#define QUEUE_FLAG_DISCARD 16 /* supports DISCARD */
+#define QUEUE_FLAG_NOXMERGES 17 /* No extended merges */
#define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \
(1 << QUEUE_FLAG_CLUSTER) | \
- (1 << QUEUE_FLAG_STACKABLE))
+ (1 << QUEUE_FLAG_STACKABLE) | \
+ (1 << QUEUE_FLAG_SAME_COMP))
static inline int queue_is_locked(struct request_queue *q)
{
#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_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
+#define blk_queue_noxmerges(q) \
+ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
#define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
#define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
#define blk_queue_flushing(q) ((q)->ordseq)
#define blk_queue_stackable(q) \
test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags)
+#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
#define blk_fs_request(rq) ((rq)->cmd_type == REQ_TYPE_FS)
#define blk_pc_request(rq) ((rq)->cmd_type == REQ_TYPE_BLOCK_PC)
int nr_entries;
unsigned long offset;
int null_mapped;
+ int from_user;
};
struct req_iterator {
#define rq_iter_last(rq, _iter) \
(_iter.bio->bi_next == NULL && _iter.i == _iter.bio->bi_vcnt-1)
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform"
+#endif
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+extern void rq_flush_dcache_pages(struct request *rq);
+#else
+static inline void rq_flush_dcache_pages(struct request *rq)
+{
+}
+#endif
+
extern int blk_register_queue(struct gendisk *disk);
extern void blk_unregister_queue(struct gendisk *disk);
extern void register_disk(struct gendisk *dev);
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);
-}
-
/*
- * blk_rq_pos() : the current sector
- * blk_rq_bytes() : bytes left in the entire request
- * blk_rq_cur_bytes() : bytes left in the current segment
- * blk_rq_sectors() : sectors left in the entire request
- * blk_rq_cur_sectors() : sectors left in the current segment
+ * blk_rq_pos() : the current sector
+ * blk_rq_bytes() : bytes left in the entire request
+ * blk_rq_cur_bytes() : bytes left in the current segment
+ * blk_rq_err_bytes() : bytes left till the next error boundary
+ * blk_rq_sectors() : sectors left in the entire request
+ * blk_rq_cur_sectors() : sectors left in the current segment
*/
static inline sector_t blk_rq_pos(const struct request *rq)
{
return rq->bio ? bio_cur_bytes(rq->bio) : 0;
}
+extern unsigned int blk_rq_err_bytes(const struct request *rq);
+
static inline unsigned int blk_rq_sectors(const struct request *rq)
{
return blk_rq_bytes(rq) >> 9;
unsigned int nr_bytes);
extern void blk_end_request_all(struct request *rq, int error);
extern bool blk_end_request_cur(struct request *rq, int error);
+extern bool blk_end_request_err(struct request *rq, int error);
extern bool __blk_end_request(struct request *rq, int error,
unsigned int nr_bytes);
extern void __blk_end_request_all(struct request *rq, int error);
extern bool __blk_end_request_cur(struct request *rq, int error);
+extern bool __blk_end_request_err(struct request *rq, int error);
extern void blk_complete_request(struct request *);
extern void __blk_complete_request(struct request *);
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_hw_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_segments(struct request_queue *, unsigned short);
extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
+extern void blk_queue_max_discard_sectors(struct request_queue *q,
+ unsigned int max_discard_sectors);
extern void blk_queue_logical_block_size(struct request_queue *, unsigned short);
extern void blk_queue_physical_block_size(struct request_queue *, unsigned short);
extern void blk_queue_alignment_offset(struct request_queue *q,
unsigned int alignment);
+extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
+extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
extern void blk_set_default_limits(struct queue_limits *lim);
extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
sector_t offset);
+extern int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
+ sector_t offset);
extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
sector_t offset);
extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
extern void blk_queue_dma_alignment(struct request_queue *, int);
extern void blk_queue_update_dma_alignment(struct request_queue *, int);
extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
-extern void blk_queue_set_discard(struct request_queue *, prepare_discard_fn *);
extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
return NULL;
return bqt->tag_index[tag];
}
-
-extern int blkdev_issue_flush(struct block_device *, sector_t *);
-extern int blkdev_issue_discard(struct block_device *,
- sector_t sector, sector_t nr_sects, gfp_t);
-
+enum{
+ BLKDEV_WAIT, /* wait for completion */
+ BLKDEV_BARRIER, /*issue request with barrier */
+};
+#define BLKDEV_IFL_WAIT (1 << BLKDEV_WAIT)
+#define BLKDEV_IFL_BARRIER (1 << BLKDEV_BARRIER)
+extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *,
+ unsigned long);
+extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+ sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
+extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
+ sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
static inline int sb_issue_discard(struct super_block *sb,
sector_t block, sector_t 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, GFP_KERNEL);
+ return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL,
+ BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
}
extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
-#define MAX_PHYS_SEGMENTS 128
-#define MAX_HW_SEGMENTS 128
-#define SAFE_MAX_SECTORS 255
-#define BLK_DEF_MAX_SECTORS 1024
-
-#define MAX_SEGMENT_SIZE 65536
-
-#define BLK_SEG_BOUNDARY_MASK 0xFFFFFFFFUL
+enum blk_default_limits {
+ BLK_MAX_SEGMENTS = 128,
+ BLK_SAFE_MAX_SECTORS = 255,
+ BLK_DEF_MAX_SECTORS = 1024,
+ BLK_MAX_SEGMENT_SIZE = 65536,
+ BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL,
+};
#define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
return q->limits.max_hw_sectors;
}
-static inline unsigned short queue_max_hw_segments(struct request_queue *q)
-{
- return q->limits.max_hw_segments;
-}
-
-static inline unsigned short queue_max_phys_segments(struct request_queue *q)
+static inline unsigned short queue_max_segments(struct request_queue *q)
{
- return q->limits.max_phys_segments;
+ return q->limits.max_segments;
}
static inline unsigned int queue_max_segment_size(struct request_queue *q)
return q->limits.physical_block_size;
}
+static inline int bdev_physical_block_size(struct block_device *bdev)
+{
+ return queue_physical_block_size(bdev_get_queue(bdev));
+}
+
static inline unsigned int queue_io_min(struct request_queue *q)
{
return q->limits.io_min;
}
+static inline int bdev_io_min(struct block_device *bdev)
+{
+ return queue_io_min(bdev_get_queue(bdev));
+}
+
static inline unsigned int queue_io_opt(struct request_queue *q)
{
return q->limits.io_opt;
}
+static inline int bdev_io_opt(struct block_device *bdev)
+{
+ return queue_io_opt(bdev_get_queue(bdev));
+}
+
static inline int queue_alignment_offset(struct request_queue *q)
{
- if (q && q->limits.misaligned)
+ if (q->limits.misaligned)
+ return -1;
+
+ return q->limits.alignment_offset;
+}
+
+static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
+{
+ unsigned int granularity = max(lim->physical_block_size, lim->io_min);
+ unsigned int alignment = (sector << 9) & (granularity - 1);
+
+ return (granularity + lim->alignment_offset - alignment)
+ & (granularity - 1);
+}
+
+static inline int bdev_alignment_offset(struct block_device *bdev)
+{
+ struct request_queue *q = bdev_get_queue(bdev);
+
+ if (q->limits.misaligned)
return -1;
- if (q && q->limits.alignment_offset)
- return q->limits.alignment_offset;
+ if (bdev != bdev->bd_contains)
+ return bdev->bd_part->alignment_offset;
+
+ return q->limits.alignment_offset;
+}
+
+static inline int queue_discard_alignment(struct request_queue *q)
+{
+ if (q->limits.discard_misaligned)
+ return -1;
+
+ return q->limits.discard_alignment;
+}
+
+static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector)
+{
+ unsigned int alignment = (sector << 9) & (lim->discard_granularity - 1);
+
+ return (lim->discard_granularity + lim->discard_alignment - alignment)
+ & (lim->discard_granularity - 1);
+}
+
+static inline unsigned int queue_discard_zeroes_data(struct request_queue *q)
+{
+ if (q->limits.discard_zeroes_data == 1)
+ return 1;
return 0;
}
-static inline int queue_sector_alignment_offset(struct request_queue *q,
- sector_t sector)
+static inline unsigned int bdev_discard_zeroes_data(struct block_device *bdev)
{
- return ((sector << 9) - q->limits.alignment_offset)
- & (q->limits.io_min - 1);
+ return queue_discard_zeroes_data(bdev_get_queue(bdev));
}
static inline int queue_dma_alignment(struct request_queue *q)
struct work_struct;
int kblockd_schedule_work(struct request_queue *q, struct work_struct *work);
+#ifdef CONFIG_BLK_CGROUP
+static inline void set_start_time_ns(struct request *req)
+{
+ req->start_time_ns = sched_clock();
+}
+
+static inline void set_io_start_time_ns(struct request *req)
+{
+ req->io_start_time_ns = sched_clock();
+}
+
+static inline uint64_t rq_start_time_ns(struct request *req)
+{
+ return req->start_time_ns;
+}
+
+static inline uint64_t rq_io_start_time_ns(struct request *req)
+{
+ return req->io_start_time_ns;
+}
+#else
+static inline void set_start_time_ns(struct request *req) {}
+static inline void set_io_start_time_ns(struct request *req) {}
+static inline uint64_t rq_start_time_ns(struct request *req)
+{
+ return 0;
+}
+static inline uint64_t rq_io_start_time_ns(struct request *req)
+{
+ return 0;
+}
+#endif
+
#define MODULE_ALIAS_BLOCKDEV(major,minor) \
MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
#define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \