bio.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2001 Jens Axboe <axboe@kernel.dk>
 */
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/uio.h>
#include <linux/iocontext.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/mempool.h>
#include <linux/workqueue.h>
#include <linux/cgroup.h>
#include <linux/highmem.h>
#include <linux/sched/sysctl.h>
#include <linux/blk-crypto.h>
#include <linux/xarray.h>

#include <trace/events/block.h>
#include "blk.h"
#include "blk-rq-qos.h"
#include "blk-cgroup.h"

struct bio_alloc_cache {
	struct bio		*free_list;
	unsigned int		nr;
};

static struct biovec_slab {
	int nr_vecs;
	char *name;
	struct kmem_cache *slab;
} bvec_slabs[] __read_mostly = {
	{ .nr_vecs = 16, .name = "biovec-16" },
	{ .nr_vecs = 64, .name = "biovec-64" },
	{ .nr_vecs = 128, .name = "biovec-128" },
	{ .nr_vecs = BIO_MAX_VECS, .name = "biovec-max" },
};

static struct biovec_slab *biovec_slab(unsigned short nr_vecs)
{
	switch (nr_vecs) {
	/* smaller bios use inline vecs */
	case 5 ... 16:
		return &bvec_slabs[0];
	case 17 ... 64:
		return &bvec_slabs[1];
	case 65 ... 128:
		return &bvec_slabs[2];
	case 129 ... BIO_MAX_VECS:
		return &bvec_slabs[3];
	default:
		BUG();
		return NULL;
	}
}

/*
 * fs_bio_set is the bio_set containing bio and iovec memory pools used by
 * IO code that does not need private memory pools.
 */
struct bio_set fs_bio_set;
EXPORT_SYMBOL(fs_bio_set);

/*
 * Our slab pool management
 */
struct bio_slab {
	struct kmem_cache *slab;
	unsigned int slab_ref;
	unsigned int slab_size;
	char name[8];
};
static DEFINE_MUTEX(bio_slab_lock);
static DEFINE_XARRAY(bio_slabs);

static struct bio_slab *create_bio_slab(unsigned int size)
{
	struct bio_slab *bslab = kzalloc(sizeof(*bslab), GFP_KERNEL);

	if (!bslab)
		return NULL;

	snprintf(bslab->name, sizeof(bslab->name), "bio-%d", size);
	bslab->slab = kmem_cache_create(bslab->name, size,
			ARCH_KMALLOC_MINALIGN,
			SLAB_HWCACHE_ALIGN | SLAB_TYPESAFE_BY_RCU, NULL);
	if (!bslab->slab)
		goto fail_alloc_slab;

	bslab->slab_ref = 1;
	bslab->slab_size = size;

	if (!xa_err(xa_store(&bio_slabs, size, bslab, GFP_KERNEL)))
		return bslab;

	kmem_cache_destroy(bslab->slab);

fail_alloc_slab:
	kfree(bslab);
	return NULL;
}

static inline unsigned int bs_bio_slab_size(struct bio_set *bs)
{
	return bs->front_pad + sizeof(struct bio) + bs->back_pad;
}

static struct kmem_cache *bio_find_or_create_slab(struct bio_set *bs)
{
	unsigned int size = bs_bio_slab_size(bs);
	struct bio_slab *bslab;

	mutex_lock(&bio_slab_lock);
	bslab = xa_load(&bio_slabs, size);
	if (bslab)
		bslab->slab_ref++;
	else
		bslab = create_bio_slab(size);
	mutex_unlock(&bio_slab_lock);

	if (bslab)
		return bslab->slab;
	return NULL;
}

static void bio_put_slab(struct bio_set *bs)
{
	struct bio_slab *bslab = NULL;
	unsigned int slab_size = bs_bio_slab_size(bs);

	mutex_lock(&bio_slab_lock);

	bslab = xa_load(&bio_slabs, slab_size);
	if (WARN(!bslab, KERN_ERR "bio: unable to find slab!\n"))
		goto out;

	WARN_ON_ONCE(bslab->slab != bs->bio_slab);

	WARN_ON(!bslab->slab_ref);

	if (--bslab->slab_ref)
		goto out;

	xa_erase(&bio_slabs, slab_size);

	kmem_cache_destroy(bslab->slab);
	kfree(bslab);

out:
	mutex_unlock(&bio_slab_lock);
}

void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs)
{
	BUG_ON(nr_vecs > BIO_MAX_VECS);

	if (nr_vecs == BIO_MAX_VECS)
		mempool_free(bv, pool);
	else if (nr_vecs > BIO_INLINE_VECS)
		kmem_cache_free(biovec_slab(nr_vecs)->slab, bv);
}

/*
 * Make the first allocation restricted and don't dump info on allocation
 * failures, since we'll fall back to the mempool in case of failure.
 */
static inline gfp_t bvec_alloc_gfp(gfp_t gfp)
{
	return (gfp & ~(__GFP_DIRECT_RECLAIM | __GFP_IO)) |
		__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
}

struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
		gfp_t gfp_mask)
{
	struct biovec_slab *bvs = biovec_slab(*nr_vecs);

	if (WARN_ON_ONCE(!bvs))
		return NULL;

	/*
	 * Upgrade the nr_vecs request to take full advantage of the allocation.
	 * We also rely on this in the bvec_free path.
	 */
	*nr_vecs = bvs->nr_vecs;

	/*
	 * Try a slab allocation first for all smaller allocations.  If that
	 * fails and __GFP_DIRECT_RECLAIM is set retry with the mempool.
	 * The mempool is sized to handle up to BIO_MAX_VECS entries.
	 */
	if (*nr_vecs < BIO_MAX_VECS) {
		struct bio_vec *bvl;

		bvl = kmem_cache_alloc(bvs->slab, bvec_alloc_gfp(gfp_mask));
		if (likely(bvl) || !(gfp_mask & __GFP_DIRECT_RECLAIM))
			return bvl;
		*nr_vecs = BIO_MAX_VECS;
	}

	return mempool_alloc(pool, gfp_mask);
}

void bio_uninit(struct bio *bio)
{
#ifdef CONFIG_BLK_CGROUP
	if (bio->bi_blkg) {
		blkg_put(bio->bi_blkg);
		bio->bi_blkg = NULL;
	}
#endif
	if (bio_integrity(bio))
		bio_integrity_free(bio);

	bio_crypt_free_ctx(bio);
}
EXPORT_SYMBOL(bio_uninit);

static void bio_free(struct bio *bio)
{
	struct bio_set *bs = bio->bi_pool;
	void *p;

	bio_uninit(bio);

	if (bs) {
		bvec_free(&bs->bvec_pool, bio->bi_io_vec, bio->bi_max_vecs);

		/*
		 * If we have front padding, adjust the bio pointer before freeing
		 */
		p = bio;
		p -= bs->front_pad;

		mempool_free(p, &bs->bio_pool);
	} else {
		/* Bio was allocated by bio_kmalloc() */
		kfree(bio);
	}
}

/*
 * Users of this function have their own bio allocation. Subsequently,
 * they must remember to pair any call to bio_init() with bio_uninit()
 * when IO has completed, or when the bio is released.
 */
void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table,
	      unsigned short max_vecs, unsigned int opf)
{
	bio->bi_next = NULL;
	bio->bi_bdev = bdev;
	bio->bi_opf = opf;
	bio->bi_flags = 0;
	bio->bi_ioprio = 0;
	bio->bi_status = 0;
	bio->bi_iter.bi_sector = 0;
	bio->bi_iter.bi_size = 0;
	bio->bi_iter.bi_idx = 0;
	bio->bi_iter.bi_bvec_done = 0;
	bio->bi_end_io = NULL;
	bio->bi_private = NULL;
#ifdef CONFIG_BLK_CGROUP
	bio->bi_blkg = NULL;
	bio->bi_issue.value = 0;
	if (bdev)
		bio_associate_blkg(bio);
#ifdef CONFIG_BLK_CGROUP_IOCOST
	bio->bi_iocost_cost = 0;
#endif
#endif
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
	bio->bi_crypt_context = NULL;
#endif
#ifdef CONFIG_BLK_DEV_INTEGRITY
	bio->bi_integrity = NULL;
#endif
	bio->bi_vcnt = 0;

	atomic_set(&bio->__bi_remaining, 1);
	atomic_set(&bio->__bi_cnt, 1);
	bio->bi_cookie = BLK_QC_T_NONE;

	bio->bi_max_vecs = max_vecs;
	bio->bi_io_vec = table;
	bio->bi_pool = NULL;
}
EXPORT_SYMBOL(bio_init);

/**
 * bio_reset - reinitialize a bio
 * @bio:	bio to reset
 * @bdev:	block device to use the bio for
 * @opf:	operation and flags for bio
 *
 * Description:
 *   After calling bio_reset(), @bio will be in the same state as a freshly
 *   allocated bio returned bio bio_alloc_bioset() - the only fields that are
 *   preserved are the ones that are initialized by bio_alloc_bioset(). See
 *   comment in struct bio.
 */
void bio_reset(struct bio *bio, struct block_device *bdev, unsigned int opf)
{
	bio_uninit(bio);
	memset(bio, 0, BIO_RESET_BYTES);
	atomic_set(&bio->__bi_remaining, 1);
	bio->bi_bdev = bdev;
	if (bio->bi_bdev)
		bio_associate_blkg(bio);
	bio->bi_opf = opf;
}
EXPORT_SYMBOL(bio_reset);

static struct bio *__bio_chain_endio(struct bio *bio)
{
	struct bio *parent = bio->bi_private;

	if (bio->bi_status && !parent->bi_status)
		parent->bi_status = bio->bi_status;
	bio_put(bio);
	return parent;
}

static void bio_chain_endio(struct bio *bio)
{
	bio_endio(__bio_chain_endio(bio));
}

/**
 * bio_chain - chain bio completions
 * @bio: the target bio
 * @parent: the parent bio of @bio
 *
 * The caller won't have a bi_end_io called when @bio completes - instead,
 * @parent's bi_end_io won't be called until both @parent and @bio have
 * completed; the chained bio will also be freed when it completes.
 *
 * The caller must not set bi_private or bi_end_io in @bio.
 */
void bio_chain(struct bio *bio, struct bio *parent)
{
	BUG_ON(bio->bi_private || bio->bi_end_io);

	bio->bi_private = parent;
	bio->bi_end_io	= bio_chain_endio;
	bio_inc_remaining(parent);
}
EXPORT_SYMBOL(bio_chain);

struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
		unsigned int nr_pages, unsigned int opf, gfp_t gfp)
{
	struct bio *new = bio_alloc(bdev, nr_pages, opf, gfp);

	if (bio) {
		bio_chain(bio, new);
		submit_bio(bio);
	}

	return new;
}
EXPORT_SYMBOL_GPL(blk_next_bio);

static void bio_alloc_rescue(struct work_struct *work)
{
	struct bio_set *bs = container_of(work, struct bio_set, rescue_work);
	struct bio *bio;

	while (1) {
		spin_lock(&bs->rescue_lock);
		bio = bio_list_pop(&bs->rescue_list);
		spin_unlock(&bs->rescue_lock);

		if (!bio)
			break;

		submit_bio_noacct(bio);
	}
}

static void punt_bios_to_rescuer(struct bio_set *bs)
{
	struct bio_list punt, nopunt;
	struct bio *bio;

	if (WARN_ON_ONCE(!bs->rescue_workqueue))
		return;
	/*
	 * In order to guarantee forward progress we must punt only bios that
	 * were allocated from this bio_set; otherwise, if there was a bio on
	 * there for a stacking driver higher up in the stack, processing it
	 * could require allocating bios from this bio_set, and doing that from
	 * our own rescuer would be bad.
	 *
	 * Since bio lists are singly linked, pop them all instead of trying to
	 * remove from the middle of the list:
	 */

	bio_list_init(&punt);
	bio_list_init(&nopunt);

	while ((bio = bio_list_pop(&current->bio_list[0])))
		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
	current->bio_list[0] = nopunt;

	bio_list_init(&nopunt);
	while ((bio = bio_list_pop(&current->bio_list[1])))
		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
	current->bio_list[1] = nopunt;

	spin_lock(&bs->rescue_lock);
	bio_list_merge(&bs->rescue_list, &punt);
	spin_unlock(&bs->rescue_lock);

	queue_work(bs->rescue_workqueue, &bs->rescue_work);
}

/**
 * bio_alloc_bioset - allocate a bio for I/O
 * @bdev:	block device to allocate the bio for (can be %NULL)
 * @nr_vecs:	number of bvecs to pre-allocate
 * @opf:	operation and flags for bio
 * @gfp_mask:   the GFP_* mask given to the slab allocator
 * @bs:		the bio_set to allocate from.
 *
 * Allocate a bio from the mempools in @bs.
 *
 * If %__GFP_DIRECT_RECLAIM is set then bio_alloc will always be able to
 * allocate a bio.  This is due to the mempool guarantees.  To make this work,
 * callers must never allocate more than 1 bio at a time from the general pool.
 * Callers that need to allocate more than 1 bio must always submit the
 * previously allocated bio for IO before attempting to allocate a new one.
 * Failure to do so can cause deadlocks under memory pressure.
 *
 * Note that when running under submit_bio_noacct() (i.e. any block driver),
 * bios are not submitted until after you return - see the code in
 * submit_bio_noacct() that converts recursion into iteration, to prevent
 * stack overflows.
 *
 * This would normally mean allocating multiple bios under submit_bio_noacct()
 * would be susceptible to deadlocks, but we have
 * deadlock avoidance code that resubmits any blocked bios from a rescuer
 * thread.
 *
 * However, we do not guarantee forward progress for allocations from other
 * mempools. Doing multiple allocations from the same mempool under
 * submit_bio_noacct() should be avoided - instead, use bio_set's front_pad
 * for per bio allocations.
 *
 * Returns: Pointer to new bio on success, NULL on failure.
 */
struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
			     unsigned int opf, gfp_t gfp_mask,
			     struct bio_set *bs)
{
	gfp_t saved_gfp = gfp_mask;
	struct bio *bio;
	void *p;

	/* should not use nobvec bioset for nr_vecs > 0 */
	if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_vecs > 0))
		return NULL;

	/*
	 * submit_bio_noacct() converts recursion to iteration; this means if
	 * we're running beneath it, any bios we allocate and submit will not be
	 * submitted (and thus freed) until after we return.
	 *
	 * This exposes us to a potential deadlock if we allocate multiple bios
	 * from the same bio_set() while running underneath submit_bio_noacct().
	 * If we were to allocate multiple bios (say a stacking block driver
	 * that was splitting bios), we would deadlock if we exhausted the
	 * mempool's reserve.
	 *
	 * We solve this, and guarantee forward progress, with a rescuer
	 * workqueue per bio_set. If we go to allocate and there are bios on
	 * current->bio_list, we first try the allocation without
	 * __GFP_DIRECT_RECLAIM; if that fails, we punt those bios we would be
	 * blocking to the rescuer workqueue before we retry with the original
	 * gfp_flags.
	 */
	if (current->bio_list &&
	    (!bio_list_empty(&current->bio_list[0]) ||
	     !bio_list_empty(&current->bio_list[1])) &&
	    bs->rescue_workqueue)
		gfp_mask &= ~__GFP_DIRECT_RECLAIM;

	p = mempool_alloc(&bs->bio_pool, gfp_mask);
	if (!p && gfp_mask != saved_gfp) {
		punt_bios_to_rescuer(bs);
		gfp_mask = saved_gfp;
		p = mempool_alloc(&bs->bio_pool, gfp_mask);
	}
	if (unlikely(!p))
		return NULL;

	bio = p + bs->front_pad;
	if (nr_vecs > BIO_INLINE_VECS) {
		struct bio_vec *bvl = NULL;

		bvl = bvec_alloc(&bs->bvec_pool, &nr_vecs, gfp_mask);
		if (!bvl && gfp_mask != saved_gfp) {
			punt_bios_to_rescuer(bs);
			gfp_mask = saved_gfp;
			bvl = bvec_alloc(&bs->bvec_pool, &nr_vecs, gfp_mask);
		}
		if (unlikely(!bvl))
			goto err_free;

		bio_init(bio, bdev, bvl, nr_vecs, opf);
	} else if (nr_vecs) {
		bio_init(bio, bdev, bio->bi_inline_vecs, BIO_INLINE_VECS, opf);
	} else {
		bio_init(bio, bdev, NULL, 0, opf);
	}

	bio->bi_pool = bs;
	return bio;

err_free:
	mempool_free(p, &bs->bio_pool);
	return NULL;
}
EXPORT_SYMBOL(bio_alloc_bioset);

/**
 * bio_kmalloc - kmalloc a bio for I/O
 * @gfp_mask:   the GFP_* mask given to the slab allocator
 * @nr_iovecs:	number of iovecs to pre-allocate
 *
 * Use kmalloc to allocate and initialize a bio.
 *
 * Returns: Pointer to new bio on success, NULL on failure.
 */
struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs)
{
	struct bio *bio;

	if (nr_iovecs > UIO_MAXIOV)
		return NULL;

	bio = kmalloc(struct_size(bio, bi_inline_vecs, nr_iovecs), gfp_mask);
	if (unlikely(!bio))
		return NULL;
	bio_init(bio, NULL, nr_iovecs ? bio->bi_inline_vecs : NULL, nr_iovecs,
		 0);
	bio->bi_pool = NULL;
	return bio;
}
EXPORT_SYMBOL(bio_kmalloc);

void zero_fill_bio(struct bio *bio)
{
	struct bio_vec bv;
	struct bvec_iter iter;

	bio_for_each_segment(bv, bio, iter)
		memzero_bvec(&bv);
}
EXPORT_SYMBOL(zero_fill_bio);

/**
 * bio_truncate - truncate the bio to small size of @new_size
 * @bio:	the bio to be truncated
 * @new_size:	new size for truncating the bio
 *
 * Description:
 *   Truncate the bio to new size of @new_size. If bio_op(bio) is
 *   REQ_OP_READ, zero the truncated part. This function should only
 *   be used for handling corner cases, such as bio eod.
 */
static void bio_truncate(struct bio *bio, unsigned new_size)
{
	struct bio_vec bv;
	struct bvec_iter iter;
	unsigned int done = 0;
	bool truncated = false;

	if (new_size >= bio->bi_iter.bi_size)
		return;

	if (bio_op(bio) != REQ_OP_READ)
		goto exit;

	bio_for_each_segment(bv, bio, iter) {
		if (done + bv.bv_len > new_size) {
			unsigned offset;

			if (!truncated)
				offset = new_size - done;
			else
				offset = 0;
			zero_user(bv.bv_page, bv.bv_offset + offset,
				  bv.bv_len - offset);
			truncated = true;
		}
		done += bv.bv_len;
	}

 exit:
	/*
	 * Don't touch bvec table here and make it really immutable, since
	 * fs bio user has to retrieve all pages via bio_for_each_segment_all
	 * in its .end_bio() callback.
	 *
	 * It is enough to truncate bio by updating .bi_size since we can make
	 * correct bvec with the updated .bi_size for drivers.
	 */
	bio->bi_iter.bi_size = new_size;
}

/**
 * guard_bio_eod - truncate a BIO to fit the block device
 * @bio:	bio to truncate
 *
 * This allows us to do IO even on the odd last sectors of a device, even if the
 * block size is some multiple of the physical sector size.
 *
 * We'll just truncate the bio to the size of the device, and clear the end of
 * the buffer head manually.  Truly out-of-range accesses will turn into actual
 * I/O errors, this only handles the "we need to be able to do I/O at the final
 * sector" case.
 */
void guard_bio_eod(struct bio *bio)
{
	sector_t maxsector = bdev_nr_sectors(bio->bi_bdev);

	if (!maxsector)
		return;

	/*
	 * If the *whole* IO is past the end of the device,
	 * let it through, and the IO layer will turn it into
	 * an EIO.
	 */
	if (unlikely(bio->bi_iter.bi_sector >= maxsector))
		return;

	maxsector -= bio->bi_iter.bi_sector;
	if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
		return;

	bio_truncate(bio, maxsector << 9);
}

#define ALLOC_CACHE_MAX		512
#define ALLOC_CACHE_SLACK	 64

static void bio_alloc_cache_prune(struct bio_alloc_cache *cache,
				  unsigned int nr)
{
	unsigned int i = 0;
	struct bio *bio;

	while ((bio = cache->free_list) != NULL) {
		cache->free_list = bio->bi_next;
		cache->nr--;
		bio_free(bio);
		if (++i == nr)
			break;
	}
}

static int bio_cpu_dead(unsigned int cpu, struct hlist_node *node)
{
	struct bio_set *bs;

	bs = hlist_entry_safe(node, struct bio_set, cpuhp_dead);
	if (bs->cache) {
		struct bio_alloc_cache *cache = per_cpu_ptr(bs->cache, cpu);

		bio_alloc_cache_prune(cache, -1U);
	}
	return 0;
}

static void bio_alloc_cache_destroy(struct bio_set *bs)
{
	int cpu;

	if (!bs->cache)
		return;

	cpuhp_state_remove_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead);
	for_each_possible_cpu(cpu) {
		struct bio_alloc_cache *cache;

		cache = per_cpu_ptr(bs->cache, cpu);
		bio_alloc_cache_prune(cache, -1U);
	}
	free_percpu(bs->cache);
}

/**
 * bio_put - release a reference to a bio
 * @bio:   bio to release reference to
 *
 * Description:
 *   Put a reference to a &struct bio, either one you have gotten with
 *   bio_alloc, bio_get or bio_clone_*. The last put of a bio will free it.
 **/
void bio_put(struct bio *bio)
{
	if (unlikely(bio_flagged(bio, BIO_REFFED))) {
		BUG_ON(!atomic_read(&bio->__bi_cnt));
		if (!atomic_dec_and_test(&bio->__bi_cnt))
			return;
	}

	if (bio_flagged(bio, BIO_PERCPU_CACHE)) {
		struct bio_alloc_cache *cache;

		bio_uninit(bio);
		cache = per_cpu_ptr(bio->bi_pool->cache, get_cpu());
		bio->bi_next = cache->free_list;
		cache->free_list = bio;
		if (++cache->nr > ALLOC_CACHE_MAX + ALLOC_CACHE_SLACK)
			bio_alloc_cache_prune(cache, ALLOC_CACHE_SLACK);
		put_cpu();
	} else {
		bio_free(bio);
	}
}
EXPORT_SYMBOL(bio_put);

static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp)
{
	bio_set_flag(bio, BIO_CLONED);
	if (bio_flagged(bio_src, BIO_THROTTLED))
		bio_set_flag(bio, BIO_THROTTLED);
	if (bio->bi_bdev == bio_src->bi_bdev &&
	    bio_flagged(bio_src, BIO_REMAPPED))
		bio_set_flag(bio, BIO_REMAPPED);
	bio->bi_ioprio = bio_src->bi_ioprio;
	bio->bi_iter = bio_src->bi_iter;

	bio_clone_blkg_association(bio, bio_src);
	blkcg_bio_issue_init(bio);

	if (bio_crypt_clone(bio, bio_src, gfp) < 0)
		return -ENOMEM;
	if (bio_integrity(bio_src) &&
	    bio_integrity_clone(bio, bio_src, gfp) < 0)
		return -ENOMEM;
	return 0;
}

/**
 * bio_alloc_clone - clone a bio that shares the original bio's biovec
 * @bdev: block_device to clone onto
 * @bio_src: bio to clone from
 * @gfp: allocation priority
 * @bs: bio_set to allocate from
 *
 * Allocate a new bio that is a clone of @bio_src. The caller owns the returned
 * bio, but not the actual data it points to.
 *
 * The caller must ensure that the return bio is not freed before @bio_src.
 */
struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src,
		gfp_t gfp, struct bio_set *bs)
{
	struct bio *bio;

	bio = bio_alloc_bioset(bdev, 0, bio_src->bi_opf, gfp, bs);
	if (!bio)
		return NULL;

	if (__bio_clone(bio, bio_src, gfp) < 0) {
		bio_put(bio);
		return NULL;
	}
	bio->bi_io_vec = bio_src->bi_io_vec;

	return bio;
}
EXPORT_SYMBOL(bio_alloc_clone);

/**
 * bio_init_clone - clone a bio that shares the original bio's biovec
 * @bdev: block_device to clone onto
 * @bio: bio to clone into
 * @bio_src: bio to clone from
 * @gfp: allocation priority
 *
 * Initialize a new bio in caller provided memory that is a clone of @bio_src.
 * The caller owns the returned bio, but not the actual data it points to.
 *
 * The caller must ensure that @bio_src is not freed before @bio.
 */
int bio_init_clone(struct block_device *bdev, struct bio *bio,
		struct bio *bio_src, gfp_t gfp)
{
	int ret;

	bio_init(bio, bdev, bio_src->bi_io_vec, 0, bio_src->bi_opf);
	ret = __bio_clone(bio, bio_src, gfp);
	if (ret)
		bio_uninit(bio);
	return ret;
}
EXPORT_SYMBOL(bio_init_clone);

/**
 * bio_full - check if the bio is full
 * @bio:	bio to check
 * @len:	length of one segment to be added
 *
 * Return true if @bio is full and one segment with @len bytes can't be
 * added to the bio, otherwise return false
 */
static inline bool bio_full(struct bio *bio, unsigned len)
{
	if (bio->bi_vcnt >= bio->bi_max_vecs)
		return true;
	if (bio->bi_iter.bi_size > UINT_MAX - len)
		return true;
	return false;
}

static inline bool page_is_mergeable(const struct bio_vec *bv,
		struct page *page, unsigned int len, unsigned int off,
		bool *same_page)
{
	size_t bv_end = bv->bv_offset + bv->bv_len;
	phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1;
	phys_addr_t page_addr = page_to_phys(page);

	if (vec_end_addr + 1 != page_addr + off)
		return false;
	if (xen_domain() && !xen_biovec_phys_mergeable(bv, page))
		return false;

	*same_page = ((vec_end_addr & PAGE_MASK) == page_addr);
	if (*same_page)
		return true;
	return (bv->bv_page + bv_end / PAGE_SIZE) == (page + off / PAGE_SIZE);
}

/**
 * __bio_try_merge_page - try appending data to an existing bvec.
 * @bio: destination bio
 * @page: start page to add
 * @len: length of the data to add
 * @off: offset of the data relative to @page
 * @same_page: return if the segment has been merged inside the same page
 *
 * Try to add the data at @page + @off to the last bvec of @bio.  This is a
 * useful optimisation for file systems with a block size smaller than the
 * page size.
 *
 * Warn if (@len, @off) crosses pages in case that @same_page is true.
 *
 * Return %true on success or %false on failure.
 */
static bool __bio_try_merge_page(struct bio *bio, struct page *page,
		unsigned int len, unsigned int off, bool *same_page)
{
	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
		return false;

	if (bio->bi_vcnt > 0) {
		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];

		if (page_is_mergeable(bv, page, len, off, same_page)) {
			if (bio->bi_iter.bi_size > UINT_MAX - len) {
				*same_page = false;
				return false;
			}
			bv->bv_len += len;
			bio->bi_iter.bi_size += len;
			return true;
		}
	}
	return false;
}

/*
 * Try to merge a page into a segment, while obeying the hardware segment
 * size limit.  This is not for normal read/write bios, but for passthrough
 * or Zone Append operations that we can't split.
 */
static bool bio_try_merge_hw_seg(struct request_queue *q, struct bio *bio,
				 struct page *page, unsigned len,
				 unsigned offset, bool *same_page)
{
	struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
	unsigned long mask = queue_segment_boundary(q);
	phys_addr_t addr1 = page_to_phys(bv->bv_page) + bv->bv_offset;
	phys_addr_t addr2 = page_to_phys(page) + offset + len - 1;

	if ((addr1 | mask) != (addr2 | mask))
		return false;
	if (bv->bv_len + len > queue_max_segment_size(q))
		return false;
	return __bio_try_merge_page(bio, page, len, offset, same_page);
}

/**
 * bio_add_hw_page - attempt to add a page to a bio with hw constraints
 * @q: the target queue
 * @bio: destination bio
 * @page: page to add
 * @len: vec entry length
 * @offset: vec entry offset
 * @max_sectors: maximum number of sectors that can be added
 * @same_page: return if the segment has been merged inside the same page
 *
 * Add a page to a bio while respecting the hardware max_sectors, max_segment
 * and gap limitations.
 */
int bio_add_hw_page(struct request_queue *q, struct bio *bio,
		struct page *page, unsigned int len, unsigned int offset,
		unsigned int max_sectors, bool *same_page)
{
	struct bio_vec *bvec;

	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
		return 0;

	if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors)
		return 0;

	if (bio->bi_vcnt > 0) {
		if (bio_try_merge_hw_seg(q, bio, page, len, offset, same_page))
			return len;

		/*
		 * If the queue doesn't support SG gaps and adding this segment
		 * would create a gap, disallow it.
		 */
		bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
		if (bvec_gap_to_prev(q, bvec, offset))
			return 0;
	}

	if (bio_full(bio, len))
		return 0;

	if (bio->bi_vcnt >= queue_max_segments(q))
		return 0;

	bvec = &bio->bi_io_vec[bio->bi_vcnt];
	bvec->bv_page = page;
	bvec->bv_len = len;
	bvec->bv_offset = offset;
	bio->bi_vcnt++;
	bio->bi_iter.bi_size += len;
	return len;
}

/**
 * bio_add_pc_page	- attempt to add page to passthrough bio
 * @q: the target queue
 * @bio: destination bio
 * @page: page to add
 * @len: vec entry length
 * @offset: vec entry offset
 *
 * Attempt to add a page to the bio_vec maplist. This can fail for a
 * number of reasons, such as the bio being full or target block device
 * limitations. The target block device must allow bio's up to PAGE_SIZE,
 * so it is always possible to add a single page to an empty bio.
 *
 * This should only be used by passthrough bios.
 */
int bio_add_pc_page(struct request_queue *q, struct bio *bio,
		struct page *page, unsigned int len, unsigned int offset)
{
	bool same_page = false;
	return bio_add_hw_page(q, bio, page, len, offset,
			queue_max_hw_sectors(q), &same_page);
}
EXPORT_SYMBOL(bio_add_pc_page);

/**
 * bio_add_zone_append_page - attempt to add page to zone-append bio
 * @bio: destination bio
 * @page: page to add
 * @len: vec entry length
 * @offset: vec entry offset
 *
 * Attempt to add a page to the bio_vec maplist of a bio that will be submitted
 * for a zone-append request. This can fail for a number of reasons, such as the
 * bio being full or the target block device is not a zoned block device or
 * other limitations of the target block device. The target block device must
 * allow bio's up to PAGE_SIZE, so it is always possible to add a single page
 * to an empty bio.
 *
 * Returns: number of bytes added to the bio, or 0 in case of a failure.
 */
int bio_add_zone_append_page(struct bio *bio, struct page *page,
			     unsigned int len, unsigned int offset)
{
	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
	bool same_page = false;