Pavel Begunkovblock: rename bi_bvec_doneb539aea3 months agoHistory
820 lines · 24.5 KB · C
RawDownload
/* SPDX-License-Identifier: GPL-2.0 */#ifndef BLK_INTERNAL_H#define BLK_INTERNAL_H #include <linux/bio-integrity.h>#include <linux/blk-crypto.h>#include <linux/part_stat.h>#include <linux/lockdep.h>#include <linux/memblock.h>	/* for max_pfn/max_low_pfn */#include <linux/sched/sysctl.h>#include <linux/timekeeping.h>#include <xen/xen.h>#include "blk-crypto-internal.h" struct elv_change_ctx; /* * Default upper limit for the software max_sectors limit used for regular I/Os. * This can be increased through sysfs. * * This should not be confused with the max_hw_sector limit that is entirely * controlled by the block device driver, usually based on hardware limits. */#define BLK_DEF_MAX_SECTORS_CAP	(SZ_4M >> SECTOR_SHIFT) #define	BLK_DEV_MAX_SECTORS	(LLONG_MAX >> 9)#define	BLK_MIN_SEGMENT_SIZE	4096 /* Max future timer expiry for timeouts */#define BLK_MAX_TIMEOUT		(5 * HZ) extern const struct kobj_type blk_queue_ktype;extern struct dentry *blk_debugfs_root; struct blk_flush_queue {	spinlock_t		mq_flush_lock;	unsigned int		flush_pending_idx:1;	unsigned int		flush_running_idx:1;	blk_status_t 		rq_status;	unsigned long		flush_pending_since;	struct list_head	flush_queue[2];	unsigned long		flush_data_in_flight;	struct request		*flush_rq;	struct rcu_head		rcu_head;}; bool is_flush_rq(struct request *req); struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size,					      gfp_t flags);void blk_free_flush_queue(struct blk_flush_queue *q); const char *blk_status_to_str(blk_status_t status);const char *blk_status_to_tag(blk_status_t status);blk_status_t tag_to_blk_status(const char *tag);enum req_op str_to_blk_op(const char *op); bool __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic);bool blk_queue_start_drain(struct request_queue *q);bool __blk_freeze_queue_start(struct request_queue *q,			      struct task_struct *owner);int __bio_queue_enter(struct request_queue *q, struct bio *bio);void submit_bio_noacct_nocheck(struct bio *bio, bool split);int bio_submit_or_kill(struct bio *bio, unsigned int flags); static inline bool blk_try_enter_queue(struct request_queue *q, bool pm){	rcu_read_lock();	if (!percpu_ref_tryget_live_rcu(&q->q_usage_counter))		goto fail; 	/*	 * The code that increments the pm_only counter must ensure that the	 * counter is globally visible before the queue is unfrozen.	 */	if (blk_queue_pm_only(q) &&	    (!pm || queue_rpm_status(q) == RPM_SUSPENDED))		goto fail_put; 	rcu_read_unlock();	return true; fail_put:	blk_queue_exit(q);fail:	rcu_read_unlock();	return false;} static inline int bio_queue_enter(struct bio *bio){	struct request_queue *q = bdev_get_queue(bio->bi_bdev); 	if (blk_try_enter_queue(q, false)) {		rwsem_acquire_read(&q->io_lockdep_map, 0, 0, _RET_IP_);		rwsem_release(&q->io_lockdep_map, _RET_IP_);		return 0;	}	return __bio_queue_enter(q, bio);} static inline void blk_wait_io(struct completion *done){	/* Prevent hang_check timer from firing at us during very long I/O */	unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2; 	if (timeout)		while (!wait_for_completion_io_timeout(done, timeout))			;	else		wait_for_completion_io(done);} struct block_device *blkdev_get_no_open(dev_t dev, bool autoload);void blkdev_put_no_open(struct block_device *bdev); bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv,		struct page *page, unsigned len, unsigned offset); static inline bool biovec_phys_mergeable(struct request_queue *q,		struct bio_vec *vec1, struct bio_vec *vec2){	unsigned long mask = queue_segment_boundary(q);	phys_addr_t addr1 = bvec_phys(vec1);	phys_addr_t addr2 = bvec_phys(vec2); 	/*	 * Merging adjacent physical pages may not work correctly under KMSAN	 * if their metadata pages aren't adjacent. Just disable merging.	 */	if (IS_ENABLED(CONFIG_KMSAN))		return false; 	if (addr1 + vec1->bv_len != addr2)		return false;	if (!zone_device_pages_have_same_pgmap(vec1->bv_page, vec2->bv_page))		return false;	if (xen_domain() && !xen_biovec_phys_mergeable(vec1, vec2->bv_page))		return false;	if ((addr1 | mask) != ((addr2 + vec2->bv_len - 1) | mask))		return false;	return true;} /* * Check if two pages from potentially different zone device pgmaps can * coexist as separate bvec entries in the same bio. * * The block DMA iterator (blk_dma_map_iter_start) caches the P2PDMA mapping * state from the first segment and applies it to all subsequent segments, so * P2PDMA pages from different pgmaps must not be mixed in the same bio. * * Other zone device types (FS_DAX, GENERIC) use the same dma_map_phys() path * as normal RAM.  PRIVATE and COHERENT pages never appear in bios. */static inline bool zone_device_pages_compatible(const struct page *a,						const struct page *b){	if (is_pci_p2pdma_page(a) || is_pci_p2pdma_page(b))		return zone_device_pages_have_same_pgmap(a, b);	return true;} static inline bool __bvec_gap_to_prev(const struct queue_limits *lim,		struct bio_vec *bprv, unsigned int offset){	return (offset & lim->virt_boundary_mask) ||		((bprv->bv_offset + bprv->bv_len) & lim->virt_boundary_mask);} /* * Check if adding a bio_vec after bprv with offset would create a gap in * the SG list. Most drivers don't care about this, but some do. */static inline bool bvec_gap_to_prev(const struct queue_limits *lim,		struct bio_vec *bprv, unsigned int offset){	if (!lim->virt_boundary_mask)		return false;	return __bvec_gap_to_prev(lim, bprv, offset);} 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;} /* * There are two different ways to handle DISCARD merges: *  1) If max_discard_segments > 1, the driver treats every bio as a range and *     send the bios to controller together. The ranges don't need to be *     contiguous. *  2) Otherwise, the request will be normal read/write requests.  The ranges *     need to 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 unsigned int blk_rq_get_max_segments(struct request *rq){	if (req_op(rq) == REQ_OP_DISCARD)		return queue_max_discard_segments(rq->q);	return queue_max_segments(rq->q);} static inline unsigned int blk_queue_get_max_sectors(struct request *rq){	struct request_queue *q = rq->q;	enum req_op op = req_op(rq); 	if (unlikely(op == REQ_OP_DISCARD))		return min(q->limits.max_discard_sectors,			   UINT_MAX >> SECTOR_SHIFT); 	if (unlikely(op == REQ_OP_SECURE_ERASE))		return min(q->limits.max_secure_erase_sectors,			   UINT_MAX >> SECTOR_SHIFT); 	if (unlikely(op == REQ_OP_WRITE_ZEROES))		return q->limits.max_write_zeroes_sectors; 	if (rq->cmd_flags & REQ_ATOMIC)		return q->limits.atomic_write_max_sectors; 	return q->limits.max_sectors;} #ifdef CONFIG_BLK_DEV_INTEGRITYvoid blk_flush_integrity(void);void bio_integrity_free(struct bio *bio); /* * Integrity payloads can either be owned by the submitter, in which case * bio_uninit will free them, or owned and generated by the block layer, * in which case we'll verify them here (for reads) and free them before * the bio is handed back to the submitted. */bool __bio_integrity_endio(struct bio *bio);static inline bool bio_integrity_endio(struct bio *bio){	struct bio_integrity_payload *bip = bio_integrity(bio); 	if (bip && (bip->bip_flags & BIP_BLOCK_INTEGRITY))		return __bio_integrity_endio(bio);	return true;} bool blk_integrity_merge_rq(struct request_queue *, struct request *,		struct request *);bool blk_integrity_merge_bio(struct request_queue *, struct request *,		struct bio *); static inline bool integrity_req_gap_back_merge(struct request *req,		struct bio *next){	struct bio_integrity_payload *bip = bio_integrity(req->bio);	struct bio_integrity_payload *bip_next = bio_integrity(next); 	return bvec_gap_to_prev(&req->q->limits,				&bip->bip_vec[bip->bip_vcnt - 1],				bip_next->bip_vec[0].bv_offset);} static inline bool integrity_req_gap_front_merge(struct request *req,		struct bio *bio){	struct bio_integrity_payload *bip = bio_integrity(bio);	struct bio_integrity_payload *bip_next = bio_integrity(req->bio); 	return bvec_gap_to_prev(&req->q->limits,				&bip->bip_vec[bip->bip_vcnt - 1],				bip_next->bip_vec[0].bv_offset);} extern const struct attribute_group blk_integrity_attr_group;#else /* CONFIG_BLK_DEV_INTEGRITY */static inline bool blk_integrity_merge_rq(struct request_queue *rq,		struct request *r1, struct request *r2){	return true;}static inline bool blk_integrity_merge_bio(struct request_queue *rq,		struct request *r, struct bio *b){	return true;}static inline bool integrity_req_gap_back_merge(struct request *req,		struct bio *next){	return false;}static inline bool integrity_req_gap_front_merge(struct request *req,		struct bio *bio){	return false;} static inline void blk_flush_integrity(void){}static inline bool bio_integrity_endio(struct bio *bio){	return true;}static inline void bio_integrity_free(struct bio *bio){}#endif /* CONFIG_BLK_DEV_INTEGRITY */ unsigned long blk_rq_timeout(unsigned long timeout);void blk_add_timer(struct request *req); enum bio_merge_status {	BIO_MERGE_OK,	BIO_MERGE_NONE,	BIO_MERGE_FAILED,}; enum bio_merge_status bio_attempt_back_merge(struct request *req,		struct bio *bio, unsigned int nr_segs);bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,		unsigned int nr_segs);bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,			struct bio *bio, unsigned int nr_segs); /* * Plug flush limits */#define BLK_MAX_REQUEST_COUNT	32#define BLK_PLUG_FLUSH_SIZE	(128 * 1024) /* * Internal elevator interface */#define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED) bool blk_insert_flush(struct request *rq); void elv_update_nr_hw_queues(struct request_queue *q,		struct elv_change_ctx *ctx);void elevator_set_default(struct request_queue *q);void elevator_set_none(struct request_queue *q); ssize_t part_size_show(struct device *dev, struct device_attribute *attr,		char *buf);ssize_t part_stat_show(struct device *dev, struct device_attribute *attr,		char *buf);ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,		char *buf);ssize_t part_fail_show(struct device *dev, struct device_attribute *attr,		char *buf);ssize_t part_fail_store(struct device *dev, struct device_attribute *attr,		const char *buf, size_t count);ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);ssize_t part_timeout_store(struct device *, struct device_attribute *,				const char *, size_t); struct bio *bio_split_discard(struct bio *bio, const struct queue_limits *lim,		unsigned *nsegs);struct bio *bio_split_write_zeroes(struct bio *bio,		const struct queue_limits *lim, unsigned *nsegs);struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim,		unsigned *nr_segs);struct bio *bio_split_zone_append(struct bio *bio,		const struct queue_limits *lim, unsigned *nr_segs); /* * All drivers must accept single-segments bios that are smaller than PAGE_SIZE. * * This is a quick and dirty check that relies on the fact that bi_io_vec[0] is * always valid if a bio has data.  The check might lead to occasional false * positives when bios are cloned, but compared to the performance impact of * cloned bios themselves the loop below doesn't matter anyway. */static inline bool bio_may_need_split(struct bio *bio,		const struct queue_limits *lim){	const struct bio_vec *bv; 	if (lim->chunk_sectors)		return true; 	if (!bio->bi_io_vec)		return true; 	bv = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);	if (bio->bi_iter.bi_size > bv->bv_len - bio->bi_iter.bi_offset)		return true;	if ((bv->bv_offset | bv->bv_len) & lim->dma_alignment)		return true;	return bv->bv_len + bv->bv_offset > lim->max_fast_segment_size;} /** * __bio_split_to_limits - split a bio to fit the queue limits * @bio:     bio to be split * @lim:     queue limits to split based on * @nr_segs: returns the number of segments in the returned bio * * Check if @bio needs splitting based on the queue limits, and if so split off * a bio fitting the limits from the beginning of @bio and return it.  @bio is * shortened to the remainder and re-submitted. * * The split bio is allocated from @q->bio_split, which is provided by the * block layer. */static inline struct bio *__bio_split_to_limits(struct bio *bio,		const struct queue_limits *lim, unsigned int *nr_segs){	switch (bio_op(bio)) {	case REQ_OP_READ:	case REQ_OP_WRITE:		if (bio_may_need_split(bio, lim))			return bio_split_rw(bio, lim, nr_segs);		*nr_segs = 1;		return bio;	case REQ_OP_ZONE_APPEND:		return bio_split_zone_append(bio, lim, nr_segs);	case REQ_OP_DISCARD:	case REQ_OP_SECURE_ERASE:		return bio_split_discard(bio, lim, nr_segs);	case REQ_OP_WRITE_ZEROES:		return bio_split_write_zeroes(bio, lim, nr_segs);	default:		/* other operations can't be split */		*nr_segs = 0;		return bio;	}} /** * get_max_segment_size() - maximum number of bytes to add as a single segment * @lim: Request queue limits. * @paddr: address of the range to add * @len: maximum length available to add at @paddr * * Returns the maximum number of bytes of the range starting at @paddr that can * be added to a single segment. */static inline unsigned get_max_segment_size(const struct queue_limits *lim,		phys_addr_t paddr, unsigned int len){	/*	 * Prevent an overflow if mask = ULONG_MAX and offset = 0 by adding 1	 * after having calculated the minimum.	 */	return min_t(unsigned long, len,		min(lim->seg_boundary_mask - (lim->seg_boundary_mask & paddr),		    (unsigned long)lim->max_segment_size - 1) + 1);} int ll_back_merge_fn(struct request *req, struct bio *bio,		unsigned int nr_segs);bool blk_attempt_req_merge(struct request_queue *q, struct request *rq,				struct request *next);unsigned int blk_recalc_rq_segments(struct request *rq);bool blk_rq_merge_ok(struct request *rq, struct bio *bio);enum elv_merge blk_try_merge(struct request *rq, struct bio *bio); int blk_set_default_limits(struct queue_limits *lim);void blk_apply_bdi_limits(struct backing_dev_info *bdi,		struct queue_limits *lim);int blk_dev_init(void); void update_io_ticks(struct block_device *part, unsigned long now, bool end); static inline void req_set_nomerge(struct request_queue *q, struct request *req){	req->cmd_flags |= REQ_NOMERGE;	if (req == q->last_merge)		q->last_merge = NULL;} static inline void bdev_inc_in_flight(struct block_device *bdev,				      enum req_op op){	bool rw = op_is_write(op); 

Lines 1–500 of 820.