summaryrefslogtreecommitdiffstats
path: root/include/linux/blkdev.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/linux/blkdev.h')
-rw-r--r--include/linux/blkdev.h909
1 files changed, 134 insertions, 775 deletions
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 12b9dbcc980e..d2d627e2c782 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -3,8 +3,6 @@
#define _LINUX_BLKDEV_H
#include <linux/sched.h>
-#include <linux/sched/clock.h>
-#include <linux/major.h>
#include <linux/genhd.h>
#include <linux/list.h>
#include <linux/llist.h>
@@ -12,17 +10,11 @@
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/wait.h>
-#include <linux/mempool.h>
-#include <linux/pfn.h>
#include <linux/bio.h>
-#include <linux/stringify.h>
#include <linux/gfp.h>
-#include <linux/smp.h>
#include <linux/rcupdate.h>
#include <linux/percpu-refcount.h>
-#include <linux/scatterlist.h>
#include <linux/blkzoned.h>
-#include <linux/pm.h>
#include <linux/sbitmap.h>
struct module;
@@ -33,14 +25,12 @@ struct request;
struct sg_io_hdr;
struct blkcg_gq;
struct blk_flush_queue;
+struct kiocb;
struct pr_ops;
struct rq_qos;
struct blk_queue_stats;
struct blk_stat_callback;
-struct blk_keyslot_manager;
-
-#define BLKDEV_MIN_RQ 4
-#define BLKDEV_MAX_RQ 128 /* Default maximum */
+struct blk_crypto_profile;
/* Must be consistent with blk_mq_poll_stats_bkt() */
#define BLK_MQ_POLL_STATS_BKTS 16
@@ -54,186 +44,13 @@ struct blk_keyslot_manager;
*/
#define BLKCG_MAX_POLS 6
-typedef void (rq_end_io_fn)(struct request *, blk_status_t);
-
-/*
- * request flags */
-typedef __u32 __bitwise req_flags_t;
-
-/* drive already may have started this one */
-#define RQF_STARTED ((__force req_flags_t)(1 << 1))
-/* may not be passed by ioscheduler */
-#define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3))
-/* request for flush sequence */
-#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4))
-/* merge of different types, fail separately */
-#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5))
-/* track inflight for MQ */
-#define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6))
-/* don't call prep for this one */
-#define RQF_DONTPREP ((__force req_flags_t)(1 << 7))
-/* vaguely specified driver internal error. Ignored by the block layer */
-#define RQF_FAILED ((__force req_flags_t)(1 << 10))
-/* don't warn about errors */
-#define RQF_QUIET ((__force req_flags_t)(1 << 11))
-/* elevator private data attached */
-#define RQF_ELVPRIV ((__force req_flags_t)(1 << 12))
-/* account into disk and partition IO statistics */
-#define RQF_IO_STAT ((__force req_flags_t)(1 << 13))
-/* runtime pm request */
-#define RQF_PM ((__force req_flags_t)(1 << 15))
-/* on IO scheduler merge hash */
-#define RQF_HASHED ((__force req_flags_t)(1 << 16))
-/* track IO completion time */
-#define RQF_STATS ((__force req_flags_t)(1 << 17))
-/* Look at ->special_vec for the actual data payload instead of the
- bio chain. */
-#define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18))
-/* The per-zone write lock is held for this request */
-#define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19))
-/* already slept for hybrid poll */
-#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20))
-/* ->timeout has been called, don't expire again */
-#define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21))
-
-/* flags that prevent us from merging requests: */
-#define RQF_NOMERGE_FLAGS \
- (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
-
-/*
- * Request state for blk-mq.
- */
-enum mq_rq_state {
- MQ_RQ_IDLE = 0,
- MQ_RQ_IN_FLIGHT = 1,
- MQ_RQ_COMPLETE = 2,
-};
-
-/*
- * Try to put the fields that are referenced together in the same cacheline.
- *
- * If you modify this structure, make sure to update blk_rq_init() and
- * especially blk_mq_rq_ctx_init() to take care of the added fields.
- */
-struct request {
- struct request_queue *q;
- struct blk_mq_ctx *mq_ctx;
- struct blk_mq_hw_ctx *mq_hctx;
-
- unsigned int cmd_flags; /* op and common flags */
- req_flags_t rq_flags;
-
- int tag;
- int internal_tag;
-
- /* the following two fields are internal, NEVER access directly */
- unsigned int __data_len; /* total data len */
- sector_t __sector; /* sector cursor */
-
- struct bio *bio;
- struct bio *biotail;
-
- struct list_head queuelist;
-
- /*
- * The hash is used inside the scheduler, and killed once the
- * request reaches the dispatch list. The ipi_list is only used
- * to queue the request for softirq completion, which is long
- * after the request has been unhashed (and even removed from
- * the dispatch list).
- */
- union {
- struct hlist_node hash; /* merge hash */
- struct llist_node ipi_list;
- };
-
- /*
- * 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 */
- struct bio_vec special_vec;
- void *completion_data;
- int error_count; /* for legacy drivers, don't use */
- };
-
- /*
- * Three pointers are available for the IO schedulers, if they need
- * more they have to dynamically allocate it. Flush requests are
- * never put on the IO scheduler. So let the flush fields share
- * space with the elevator data.
- */
- union {
- struct {
- struct io_cq *icq;
- void *priv[2];
- } elv;
-
- struct {
- unsigned int seq;
- struct list_head list;
- rq_end_io_fn *saved_end_io;
- } flush;
- };
-
- struct gendisk *rq_disk;
- struct block_device *part;
-#ifdef CONFIG_BLK_RQ_ALLOC_TIME
- /* Time that the first bio started allocating this request. */
- u64 alloc_time_ns;
-#endif
- /* Time that this request was allocated for this IO. */
- u64 start_time_ns;
- /* Time that I/O was submitted to the device. */
- u64 io_start_time_ns;
-
-#ifdef CONFIG_BLK_WBT
- unsigned short wbt_flags;
-#endif
- /*
- * rq sectors used for blk stats. It has the same value
- * with blk_rq_sectors(rq), except that it never be zeroed
- * by completion.
- */
- unsigned short stats_sectors;
-
- /*
- * Number of scatter-gather DMA addr+len pairs after
- * physical address coalescing is performed.
- */
- unsigned short nr_phys_segments;
-
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
- unsigned short nr_integrity_segments;
-#endif
-
-#ifdef CONFIG_BLK_INLINE_ENCRYPTION
- struct bio_crypt_ctx *crypt_ctx;
- struct blk_ksm_keyslot *crypt_keyslot;
-#endif
-
- unsigned short write_hint;
- unsigned short ioprio;
-
- enum mq_rq_state state;
- refcount_t ref;
-
- unsigned int timeout;
- unsigned long deadline;
-
- union {
- struct __call_single_data csd;
- u64 fifo_time;
- };
+static inline int blk_validate_block_size(unsigned int bsize)
+{
+ if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
+ return -EINVAL;
- /*
- * completion callback.
- */
- rq_end_io_fn *end_io;
- void *end_io_data;
-};
+ return 0;
+}
static inline bool blk_op_is_passthrough(unsigned int op)
{
@@ -241,35 +58,6 @@ static inline bool blk_op_is_passthrough(unsigned int op)
return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
}
-static inline bool blk_rq_is_passthrough(struct request *rq)
-{
- return blk_op_is_passthrough(req_op(rq));
-}
-
-static inline unsigned short req_get_ioprio(struct request *req)
-{
- return req->ioprio;
-}
-
-#include <linux/elevator.h>
-
-struct blk_queue_ctx;
-
-struct bio_vec;
-
-enum blk_eh_timer_return {
- BLK_EH_DONE, /* drivers has completed the command */
- BLK_EH_RESET_TIMER, /* reset timer and try again */
-};
-
-enum blk_queue_state {
- Queue_down,
- Queue_up,
-};
-
-#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */
-#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */
-
/*
* Zoned block device models (zoned limit).
*
@@ -370,6 +158,34 @@ static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev,
#endif /* CONFIG_BLK_DEV_ZONED */
+/*
+ * Independent access ranges: struct blk_independent_access_range describes
+ * a range of contiguous sectors that can be accessed using device command
+ * execution resources that are independent from the resources used for
+ * other access ranges. This is typically found with single-LUN multi-actuator
+ * HDDs where each access range is served by a different set of heads.
+ * The set of independent ranges supported by the device is defined using
+ * struct blk_independent_access_ranges. The independent ranges must not overlap
+ * and must include all sectors within the disk capacity (no sector holes
+ * allowed).
+ * For a device with multiple ranges, requests targeting sectors in different
+ * ranges can be executed in parallel. A request can straddle an access range
+ * boundary.
+ */
+struct blk_independent_access_range {
+ struct kobject kobj;
+ struct request_queue *queue;
+ sector_t sector;
+ sector_t nr_sectors;
+};
+
+struct blk_independent_access_ranges {
+ struct kobject kobj;
+ bool sysfs_registered;
+ unsigned int nr_ia_ranges;
+ struct blk_independent_access_range ia_range[];
+};
+
struct request_queue {
struct request *last_merge;
struct elevator_queue *elevator;
@@ -444,8 +260,7 @@ struct request_queue {
unsigned int dma_alignment;
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
- /* Inline crypto capabilities */
- struct blk_keyslot_manager *ksm;
+ struct blk_crypto_profile *crypto_profile;
#endif
unsigned int rq_timeout;
@@ -457,10 +272,9 @@ struct request_queue {
struct timer_list timeout;
struct work_struct timeout_work;
- atomic_t nr_active_requests_shared_sbitmap;
+ atomic_t nr_active_requests_shared_tags;
- struct sbitmap_queue sched_bitmap_tags;
- struct sbitmap_queue sched_breserved_tags;
+ struct blk_mq_tags *sched_shared_tags;
struct list_head icq_list;
#ifdef CONFIG_BLK_CGROUP
@@ -536,6 +350,8 @@ struct request_queue {
*/
struct mutex mq_freeze_lock;
+ int quiesce_depth;
+
struct blk_mq_tag_set *tag_set;
struct list_head tag_set_list;
struct bio_set bio_split;
@@ -549,10 +365,14 @@ struct request_queue {
bool mq_sysfs_init_done;
- size_t cmd_size;
-
#define BLK_MAX_WRITE_HINTS 5
u64 write_hints[BLK_MAX_WRITE_HINTS];
+
+ /*
+ * Independent sector access ranges. This is always NULL for
+ * devices that do not have multiple independent access ranges.
+ */
+ struct blk_independent_access_ranges *ia_ranges;
};
/* Keep blk_queue_flag_name[] in sync with the definitions below */
@@ -638,11 +458,6 @@ extern void blk_clear_pm_only(struct request_queue *q);
#define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist)
-#define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ)
-
-#define rq_dma_dir(rq) \
- (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE)
-
#define dma_map_bvec(dev, bv, dir, attrs) \
dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \
(dir), (attrs))
@@ -758,42 +573,6 @@ static inline unsigned int queue_max_active_zones(const struct request_queue *q)
}
#endif /* CONFIG_BLK_DEV_ZONED */
-static inline bool rq_is_sync(struct request *rq)
-{
- return op_is_sync(rq->cmd_flags);
-}
-
-static inline bool rq_mergeable(struct request *rq)
-{
- if (blk_rq_is_passthrough(rq))
- return false;
-
- if (req_op(rq) == REQ_OP_FLUSH)
- return false;
-
- if (req_op(rq) == REQ_OP_WRITE_ZEROES)
- return false;
-
- if (req_op(rq) == REQ_OP_ZONE_APPEND)
- return false;
-
- if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
- return false;
- if (rq->rq_flags & RQF_NOMERGE_FLAGS)
- return false;
-
- return true;
-}
-
-static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b)
-{
- if (bio_page(a) == bio_page(b) &&
- bio_offset(a) == bio_offset(b))
- return true;
-
- return false;
-}
-
static inline unsigned int blk_queue_depth(struct request_queue *q)
{
if (q->queue_depth)
@@ -808,83 +587,20 @@ static inline unsigned int blk_queue_depth(struct request_queue *q)
#define BLK_DEFAULT_SG_TIMEOUT (60 * HZ)
#define BLK_MIN_SG_TIMEOUT (7 * HZ)
-struct rq_map_data {
- struct page **pages;
- int page_order;
- int nr_entries;
- unsigned long offset;
- int null_mapped;
- int from_user;
-};
-
-struct req_iterator {
- struct bvec_iter iter;
- struct bio *bio;
-};
-
/* This should not be used directly - use rq_for_each_segment */
#define for_each_bio(_bio) \
for (; _bio; _bio = _bio->bi_next)
-#define __rq_for_each_bio(_bio, rq) \
- if ((rq->bio)) \
- for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next)
-
-#define rq_for_each_segment(bvl, _rq, _iter) \
- __rq_for_each_bio(_iter.bio, _rq) \
- bio_for_each_segment(bvl, _iter.bio, _iter.iter)
-#define rq_for_each_bvec(bvl, _rq, _iter) \
- __rq_for_each_bio(_iter.bio, _rq) \
- bio_for_each_bvec(bvl, _iter.bio, _iter.iter)
-
-#define rq_iter_last(bvec, _iter) \
- (_iter.bio->bi_next == NULL && \
- bio_iter_last(bvec, _iter.iter))
-
-#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);
-blk_qc_t submit_bio_noacct(struct bio *bio);
-extern void blk_rq_init(struct request_queue *q, struct request *rq);
-extern void blk_put_request(struct request *);
-extern struct request *blk_get_request(struct request_queue *, unsigned int op,
- blk_mq_req_flags_t flags);
+void submit_bio_noacct(struct bio *bio);
+
extern int blk_lld_busy(struct request_queue *q);
-extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
- struct bio_set *bs, gfp_t gfp_mask,
- int (*bio_ctr)(struct bio *, struct bio *, void *),
- void *data);
-extern void blk_rq_unprep_clone(struct request *rq);
-extern blk_status_t blk_insert_cloned_request(struct request_queue *q,
- struct request *rq);
-int blk_rq_append_bio(struct request *rq, struct bio *bio);
extern void blk_queue_split(struct bio **);
extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags);
extern void blk_queue_exit(struct request_queue *q);
extern void blk_sync_queue(struct request_queue *q);
-extern int blk_rq_map_user(struct request_queue *, struct request *,
- struct rq_map_data *, void __user *, unsigned long,
- gfp_t);
-extern int blk_rq_unmap_user(struct bio *);
-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 *,
- struct rq_map_data *, const struct iov_iter *,
- gfp_t);
-extern void blk_execute_rq_nowait(struct gendisk *,
- struct request *, int, rq_end_io_fn *);
-
-blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq,
- int at_head);
/* Helper to convert REQ_OP_XXX to its string format XXX */
extern const char *blk_op_str(unsigned int op);
@@ -892,11 +608,17 @@ extern const char *blk_op_str(unsigned int op);
int blk_status_to_errno(blk_status_t status);
blk_status_t errno_to_blk_status(int errno);
-int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin);
+/* only poll the hardware once, don't continue until a completion was found */
+#define BLK_POLL_ONESHOT (1 << 0)
+/* do not sleep to wait for the expected completion time */
+#define BLK_POLL_NOSLEEP (1 << 1)
+int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags);
+int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob,
+ unsigned int flags);
static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
{
- return bdev->bd_disk->queue; /* this is never NULL */
+ return bdev->bd_queue; /* this is never NULL */
}
/*
@@ -916,47 +638,6 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT)
#define SECTOR_MASK (PAGE_SECTORS - 1)
-/*
- * 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
- * blk_rq_stats_sectors() : sectors of the entire request used for stats
- */
-static inline sector_t blk_rq_pos(const struct request *rq)
-{
- return rq->__sector;
-}
-
-static inline unsigned int blk_rq_bytes(const struct request *rq)
-{
- return rq->__data_len;
-}
-
-static inline int blk_rq_cur_bytes(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) >> SECTOR_SHIFT;
-}
-
-static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
-{
- return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
-}
-
-static inline unsigned int blk_rq_stats_sectors(const struct request *rq)
-{
- return rq->stats_sectors;
-}
-
#ifdef CONFIG_BLK_DEV_ZONED
/* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */
@@ -973,42 +654,8 @@ static inline unsigned int bio_zone_is_seq(struct bio *bio)
return blk_queue_zone_is_seq(bdev_get_queue(bio->bi_bdev),
bio->bi_iter.bi_sector);
}
-
-static inline unsigned int blk_rq_zone_no(struct request *rq)
-{
- return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
-}
-
-static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
-{
- return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
-}
#endif /* CONFIG_BLK_DEV_ZONED */
-/*
- * Some commands like WRITE SAME have a payload or data transfer size which
- * is different from the size of the request. Any driver that supports such
- * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to
- * calculate the data transfer size.
- */
-static inline unsigned int blk_rq_payload_bytes(struct request *rq)
-{
- if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
- return rq->special_vec.bv_len;
- return blk_rq_bytes(rq);
-}
-
-/*
- * Return the first full biovec in the request. The caller needs to check that
- * there are any bvecs before calling this helper.
- */
-static inline struct bio_vec req_bvec(struct request *rq)
-{
- if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
- return rq->special_vec;
- return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter);
-}
-
static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
int op)
{
@@ -1048,47 +695,6 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q,
return min(q->limits.max_sectors, chunk_sectors);
}
-static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
- sector_t offset)
-{
- struct request_queue *q = rq->q;
-
- if (blk_rq_is_passthrough(rq))
- return q->limits.max_hw_sectors;
-
- if (!q->limits.chunk_sectors ||
- req_op(rq) == REQ_OP_DISCARD ||
- req_op(rq) == REQ_OP_SECURE_ERASE)
- return blk_queue_get_max_sectors(q, req_op(rq));
-
- return min(blk_max_size_offset(q, offset, 0),
- blk_queue_get_max_sectors(q, req_op(rq)));
-}
-
-static inline unsigned int blk_rq_count_bios(struct request *rq)
-{
- unsigned int nr_bios = 0;
- struct bio *bio;
-
- __rq_for_each_bio(bio, rq)
- nr_bios++;
-
- return nr_bios;
-}
-
-void blk_steal_bios(struct bio_list *list, struct request *rq);
-
-/*
- * Request completion related functions.
- *
- * blk_update_request() completes given number of bytes and updates
- * the request without completing it.
- */
-extern bool blk_update_request(struct request *rq, blk_status_t error,
- unsigned int nr_bytes);
-
-extern void blk_abort_request(struct request *);
-
/*
* Access functions for manipulating queue properties
*/
@@ -1133,46 +739,24 @@ 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_rq_timeout(struct request_queue *, unsigned int);
extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
-extern void blk_queue_required_elevator_features(struct request_queue *q,
- unsigned int features);
-extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
- struct device *dev);
-/*
- * Number of physical segments as sent to the device.
- *
- * Normally this is the number of discontiguous data segments sent by the
- * submitter. But for data-less command like discard we might have no
- * actual data segments submitted, but the driver might have to add it's
- * own special payload. In that case we still return 1 here so that this
- * special payload will be mapped.
- */
-static inline unsigned short blk_rq_nr_phys_segments(struct request *rq)
-{
- if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
- return 1;
- return rq->nr_phys_segments;
-}
+struct blk_independent_access_ranges *
+disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges);
+void disk_set_independent_access_ranges(struct gendisk *disk,
+ struct blk_independent_access_ranges *iars);
/*
- * Number of discard segments (or ranges) the driver needs to fill in.
- * Each discard bio merged into a request is counted as one segment.
+ * Elevator features for blk_queue_required_elevator_features:
*/
-static inline unsigned short blk_rq_nr_discard_segments(struct request *rq)
-{
- return max_t(unsigned short, rq->nr_phys_segments, 1);
-}
+/* Supports zoned block devices sequential write constraint */
+#define ELEVATOR_F_ZBD_SEQ_WRITE (1U << 0)
+/* Supports scheduling on multiple hardware queues */
+#define ELEVATOR_F_MQ_AWARE (1U << 1)
-int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
- struct scatterlist *sglist, struct scatterlist **last_sg);
-static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq,
- struct scatterlist *sglist)
-{
- struct scatterlist *last_sg = NULL;
-
- return __blk_rq_map_sg(q, rq, sglist, &last_sg);
-}
-extern void blk_dump_rq_flags(struct request *, char *);
+extern void blk_queue_required_elevator_features(struct request_queue *q,
+ unsigned int features);
+extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
+ struct device *dev);
bool __must_check blk_get_queue(struct request_queue *);
extern void blk_put_queue(struct request_queue *);
@@ -1187,19 +771,24 @@ extern void blk_set_queue_dying(struct request_queue *);
* as the lock contention for request_queue lock is reduced.
*
* It is ok not to disable preemption when adding the request to the plug list
- * or when attempting a merge, because blk_schedule_flush_list() will only flush
- * the plug list when the task sleeps by itself. For details, please see
- * schedule() where blk_schedule_flush_plug() is called.
+ * or when attempting a merge. For details, please see schedule() where
+ * blk_flush_plug() is called.
*/
struct blk_plug {
- struct list_head mq_list; /* blk-mq requests */
- struct list_head cb_list; /* md requires an unplug callback */
+ struct request *mq_list; /* blk-mq requests */
+
+ /* if ios_left is > 1, we can batch tag/rq allocations */
+ struct request *cached_rq;
+ unsigned short nr_ios;
+
unsigned short rq_count;
+
bool multiple_queues;
+ bool has_elevator;
bool nowait;
+
+ struct list_head cb_list; /* md requires an unplug callback */
};
-#define BLK_MAX_REQUEST_COUNT 16
-#define BLK_PLUG_FLUSH_SIZE (128 * 1024)
struct blk_plug_cb;
typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool);
@@ -1211,32 +800,17 @@ struct blk_plug_cb {
extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug,
void *data, int size);
extern void blk_start_plug(struct blk_plug *);
+extern void blk_start_plug_nr_ios(struct blk_plug *, unsigned short);
extern void blk_finish_plug(struct blk_plug *);
-extern void blk_flush_plug_list(struct blk_plug *, bool);
-static inline void blk_flush_plug(struct task_struct *tsk)
-{
- struct blk_plug *plug = tsk->plug;
-
- if (plug)
- blk_flush_plug_list(plug, false);
-}
-
-static inline void blk_schedule_flush_plug(struct task_struct *tsk)
-{
- struct blk_plug *plug = tsk->plug;
-
- if (plug)
- blk_flush_plug_list(plug, true);
-}
+void blk_flush_plug(struct blk_plug *plug, bool from_schedule);
static inline bool blk_needs_flush_plug(struct task_struct *tsk)
{
struct blk_plug *plug = tsk->plug;
return plug &&
- (!list_empty(&plug->mq_list) ||
- !list_empty(&plug->cb_list));
+ (plug->mq_list || !list_empty(&plug->cb_list));
}
int blkdev_issue_flush(struct block_device *bdev);
@@ -1245,23 +819,23 @@ long nr_blockdev_pages(void);
struct blk_plug {
};
-static inline void blk_start_plug(struct blk_plug *plug)
+static inline void blk_start_plug_nr_ios(struct blk_plug *plug,
+ unsigned short nr_ios)
{
}
-static inline void blk_finish_plug(struct blk_plug *plug)
+static inline void blk_start_plug(struct blk_plug *plug)
{
}
-static inline void blk_flush_plug(struct task_struct *task)
+static inline void blk_finish_plug(struct blk_plug *plug)
{
}
-static inline void blk_schedule_flush_plug(struct task_struct *task)
+static inline void blk_flush_plug(struct blk_plug *plug, bool async)
{
}
-
static inline bool blk_needs_flush_plug(struct task_struct *tsk)
{
return false;
@@ -1499,22 +1073,6 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector
return offset << SECTOR_SHIFT;
}
-/*
- * Two cases of handling DISCARD merge:
- * If max_discard_segments > 1, the driver takes every bio
- * as a range and send them to controller together. The ranges
- * needn't to be contiguous.
- * Otherwise, the bios/requests will be handled as same as
- * others which should be contiguous.
- */
-static inline bool blk_discard_mergable(struct request *req)
-{
- if (req_op(req) == REQ_OP_DISCARD &&
- queue_max_discard_segments(req->q) > 1)
- return true;
- return false;
-}
-
static inline int bdev_discard_alignment(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
@@ -1628,210 +1186,28 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned lo
#define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
MODULE_ALIAS("block-major-" __stringify(major) "-*")
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-
-enum blk_integrity_flags {
- BLK_INTEGRITY_VERIFY = 1 << 0,
- BLK_INTEGRITY_GENERATE = 1 << 1,
- BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2,
- BLK_INTEGRITY_IP_CHECKSUM = 1 << 3,
-};
-
-struct blk_integrity_iter {
- void *prot_buf;
- void *data_buf;
- sector_t seed;
- unsigned int data_size;
- unsigned short interval;
- const char *disk_name;
-};
-
-typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *);
-typedef void (integrity_prepare_fn) (struct request *);
-typedef void (integrity_complete_fn) (struct request *, unsigned int);
-
-struct blk_integrity_profile {
- integrity_processing_fn *generate_fn;
- integrity_processing_fn *verify_fn;
- integrity_prepare_fn *prepare_fn;
- integrity_complete_fn *complete_fn;
- const char *name;
-};
-
-extern void blk_integrity_register(struct gendisk *, struct blk_integrity *);
-extern void blk_integrity_unregister(struct gendisk *);
-extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
-extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
- struct scatterlist *);
-extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
-
-static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
-{
- struct blk_integrity *bi = &disk->queue->integrity;
-
- if (!bi->profile)
- return NULL;
-
- return bi;
-}
-
-static inline
-struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
-{
- return blk_get_integrity(bdev->bd_disk);
-}
-
-static inline bool
-blk_integrity_queue_supports_integrity(struct request_queue *q)
-{
- return q->integrity.profile;
-}
-
-static inline bool blk_integrity_rq(struct request *rq)
-{
- return rq->cmd_flags & REQ_INTEGRITY;
-}
-
-static inline void blk_queue_max_integrity_segments(struct request_queue *q,
- unsigned int segs)
-{
- q->limits.max_integrity_segments = segs;
-}
-
-static inline unsigned short
-queue_max_integrity_segments(const struct request_queue *q)
-{
- return q->limits.max_integrity_segments;
-}
-
-/**
- * bio_integrity_intervals - Return number of integrity intervals for a bio
- * @bi: blk_integrity profile for device
- * @sectors: Size of the bio in 512-byte sectors
- *
- * Description: The block layer calculates everything in 512 byte
- * sectors but integrity metadata is done in terms of the data integrity
- * interval size of the storage device. Convert the block layer sectors
- * to the appropriate number of integrity intervals.
- */
-static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
- unsigned int sectors)
-{
- return sectors >> (bi->interval_exp - 9);
-}
-
-static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
- unsigned int sectors)
-{
- return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
-}
-
-/*
- * Return the first bvec that contains integrity data. Only drivers that are
- * limited to a single integrity segment should use this helper.
- */
-static inline struct bio_vec *rq_integrity_vec(struct request *rq)
-{
- if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1))
- return NULL;
- return rq->bio->bi_integrity->bip_vec;
-}
-
-#else /* CONFIG_BLK_DEV_INTEGRITY */
-
-struct bio;
-struct block_device;
-struct gendisk;
-struct blk_integrity;
-
-static inline int blk_integrity_rq(struct request *rq)
-{
- return 0;
-}
-static inline int blk_rq_count_integrity_sg(struct request_queue *q,
- struct bio *b)
-{
- return 0;
-}
-static inline int blk_rq_map_integrity_sg(struct request_queue *q,
- struct bio *b,
- struct scatterlist *s)
-{
- return 0;
-}
-static inline struct blk_integrity *bdev_get_integrity(struct block_device *b)
-{
- return NULL;
-}
-static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
-{
- return NULL;
-}
-static inline bool
-blk_integrity_queue_supports_integrity(struct request_queue *q)
-{
- return false;
-}
-static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b)
-{
- return 0;
-}
-static inline void blk_integrity_register(struct gendisk *d,
- struct blk_integrity *b)
-{
-}
-static inline void blk_integrity_unregister(struct gendisk *d)
-{
-}
-static inline void blk_queue_max_integrity_segments(struct request_queue *q,
- unsigned int segs)
-{
-}
-static inline unsigned short queue_max_integrity_segments(const struct request_queue *q)
-{
- return 0;
-}
-
-static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
- unsigned int sectors)
-{
- return 0;
-}
-
-static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
- unsigned int sectors)
-{
- return 0;
-}
-
-static inline struct bio_vec *rq_integrity_vec(struct request *rq)
-{
- return NULL;
-}
-
-#endif /* CONFIG_BLK_DEV_INTEGRITY */
-
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
-bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q);
+bool blk_crypto_register(struct blk_crypto_profile *profile,
+ struct request_queue *q);
-void blk_ksm_unregister(struct request_queue *q);
+void blk_crypto_unregister(struct request_queue *q);
#else /* CONFIG_BLK_INLINE_ENCRYPTION */
-static inline bool blk_ksm_register(struct blk_keyslot_manager *ksm,
- struct request_queue *q)
+static inline bool blk_crypto_register(struct blk_crypto_profile *profile,
+ struct request_queue *q)
{
return true;
}
-static inline void blk_ksm_unregister(struct request_queue *q) { }
+static inline void blk_crypto_unregister(struct request_queue *q) { }
#endif /* CONFIG_BLK_INLINE_ENCRYPTION */
struct block_device_operations {
- blk_qc_t (*submit_bio) (struct bio *bio);
+ void (*submit_bio)(struct bio *bio);
int (*open) (struct block_device *, fmode_t);
void (*release) (struct gendisk *, fmode_t);
int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
@@ -1869,60 +1245,6 @@ extern int bdev_read_page(struct block_device *, sector_t, struct page *);
extern int bdev_write_page(struct block_device *, sector_t, struct page *,
struct writeback_control *);
-#ifdef CONFIG_BLK_DEV_ZONED
-bool blk_req_needs_zone_write_lock(struct request *rq);
-bool blk_req_zone_write_trylock(struct request *rq);
-void __blk_req_zone_write_lock(struct request *rq);
-void __blk_req_zone_write_unlock(struct request *rq);
-
-static inline void blk_req_zone_write_lock(struct request *rq)
-{
- if (blk_req_needs_zone_write_lock(rq))
- __blk_req_zone_write_lock(rq);
-}
-
-static inline void blk_req_zone_write_unlock(struct request *rq)
-{
- if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED)
- __blk_req_zone_write_unlock(rq);
-}
-
-static inline bool blk_req_zone_is_write_locked(struct request *rq)
-{
- return rq->q->seq_zones_wlock &&
- test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock);
-}
-
-static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
-{
- if (!blk_req_needs_zone_write_lock(rq))
- return true;
- return !blk_req_zone_is_write_locked(rq);
-}
-#else
-static inline bool blk_req_needs_zone_write_lock(struct request *rq)
-{
- return false;
-}
-
-static inline void blk_req_zone_write_lock(struct request *rq)
-{
-}
-
-static inline void blk_req_zone_write_unlock(struct request *rq)
-{
-}
-static inline bool blk_req_zone_is_write_locked(struct request *rq)
-{
- return false;
-}
-
-static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
-{
- return true;
-}
-#endif /* CONFIG_BLK_DEV_ZONED */
-
static inline void blk_wake_io_task(struct task_struct *waiter)
{
/*
@@ -2005,4 +1327,41 @@ int fsync_bdev(struct block_device *bdev);
int freeze_bdev(struct block_device *bdev);
int thaw_bdev(struct block_device *bdev);
+struct io_comp_batch {
+ struct request *req_list;
+ bool need_ts;
+ void (*complete)(struct io_comp_batch *);
+};
+
+#define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { }
+
+#define rq_list_add(listptr, rq) do { \
+ (rq)->rq_next = *(listptr); \
+ *(listptr) = rq; \
+} while (0)
+
+#define rq_list_pop(listptr) \
+({ \
+ struct request *__req = NULL; \
+ if ((listptr) && *(listptr)) { \
+ __req = *(listptr); \
+ *(listptr) = __req->rq_next; \
+ } \
+ __req; \
+})
+
+#define rq_list_peek(listptr) \
+({ \
+ struct request *__req = NULL; \
+ if ((listptr) && *(listptr)) \
+ __req = *(listptr); \
+ __req; \
+})
+
+#define rq_list_for_each(listptr, pos) \
+ for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) \
+
+#define rq_list_next(rq) (rq)->rq_next
+#define rq_list_empty(list) ((list) == (struct request *) NULL)
+
#endif /* _LINUX_BLKDEV_H */