path: root/block/blk.h

/* 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/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 elevator_type;

#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 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;
};

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);

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);
void bio_await_chain(struct bio *bio);

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);

#define BIO_INLINE_VECS 4
struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
		gfp_t gfp_mask);
void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs);

bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv,
		struct page *page, unsigned len, unsigned offset,
		bool *same_page);

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 (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;
}

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 || op == REQ_OP_SECURE_ERASE))
		return min(q->limits.max_discard_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_INTEGRITY
void 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);
}