bio.c

/*
 * Copyright (C) 2001 Jens Axboe <axboe@kernel.dk>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public Licens
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
 *
 */
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/bio.h>
#include <linux/blkdev.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 <scsi/sg.h>		/* for struct sg_iovec */

#include <trace/events/block.h>

/*
 * Test patch to inline a certain number of bi_io_vec's inside the bio
 * itself, to shrink a bio data allocation from two mempool calls to one
 */
#define BIO_INLINE_VECS		4

static mempool_t *bio_split_pool __read_mostly;

/*
 * if you change this list, also change bvec_alloc or things will
 * break badly! cannot be bigger than what you can fit into an
 * unsigned short
 */
#define BV(x) { .nr_vecs = x, .name = "biovec-"__stringify(x) }
static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = {
	BV(1), BV(4), BV(16), BV(64), BV(128), BV(BIO_MAX_PAGES),
};
#undef BV

/*
 * 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 struct bio_slab *bio_slabs;
static unsigned int bio_slab_nr, bio_slab_max;

static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size)
{
	unsigned int sz = sizeof(struct bio) + extra_size;
	struct kmem_cache *slab = NULL;
	struct bio_slab *bslab, *new_bio_slabs;
	unsigned int new_bio_slab_max;
	unsigned int i, entry = -1;

	mutex_lock(&bio_slab_lock);

	i = 0;
	while (i < bio_slab_nr) {
		bslab = &bio_slabs[i];

		if (!bslab->slab && entry == -1)
			entry = i;
		else if (bslab->slab_size == sz) {
			slab = bslab->slab;
			bslab->slab_ref++;
			break;
		}
		i++;
	}

	if (slab)
		goto out_unlock;

	if (bio_slab_nr == bio_slab_max && entry == -1) {
		new_bio_slab_max = bio_slab_max << 1;
		new_bio_slabs = krealloc(bio_slabs,
					 new_bio_slab_max * sizeof(struct bio_slab),
					 GFP_KERNEL);
		if (!new_bio_slabs)
			goto out_unlock;
		bio_slab_max = new_bio_slab_max;
		bio_slabs = new_bio_slabs;
	}
	if (entry == -1)
		entry = bio_slab_nr++;

	bslab = &bio_slabs[entry];

	snprintf(bslab->name, sizeof(bslab->name), "bio-%d", entry);
	slab = kmem_cache_create(bslab->name, sz, 0, SLAB_HWCACHE_ALIGN, NULL);
	if (!slab)
		goto out_unlock;

	printk(KERN_INFO "bio: create slab <%s> at %d\n", bslab->name, entry);
	bslab->slab = slab;
	bslab->slab_ref = 1;
	bslab->slab_size = sz;
out_unlock:
	mutex_unlock(&bio_slab_lock);
	return slab;
}

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

	mutex_lock(&bio_slab_lock);

	for (i = 0; i < bio_slab_nr; i++) {
		if (bs->bio_slab == bio_slabs[i].slab) {
			bslab = &bio_slabs[i];
			break;
		}
	}

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

	WARN_ON(!bslab->slab_ref);

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

	kmem_cache_destroy(bslab->slab);
	bslab->slab = NULL;

out:
	mutex_unlock(&bio_slab_lock);
}

unsigned int bvec_nr_vecs(unsigned short idx)
{
	return bvec_slabs[idx].nr_vecs;
}

void bvec_free_bs(struct bio_set *bs, struct bio_vec *bv, unsigned int idx)
{
	BIO_BUG_ON(idx >= BIOVEC_NR_POOLS);

	if (idx == BIOVEC_MAX_IDX)
		mempool_free(bv, bs->bvec_pool);
	else {
		struct biovec_slab *bvs = bvec_slabs + idx;

		kmem_cache_free(bvs->slab, bv);
	}
}

struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx,
			      struct bio_set *bs)
{
	struct bio_vec *bvl;

	/*
	 * see comment near bvec_array define!
	 */
	switch (nr) {
	case 1:
		*idx = 0;
		break;
	case 2 ... 4:
		*idx = 1;
		break;
	case 5 ... 16:
		*idx = 2;
		break;
	case 17 ... 64:
		*idx = 3;
		break;
	case 65 ... 128:
		*idx = 4;
		break;
	case 129 ... BIO_MAX_PAGES:
		*idx = 5;
		break;
	default:
		return NULL;
	}

	/*
	 * idx now points to the pool we want to allocate from. only the
	 * 1-vec entry pool is mempool backed.
	 */
	if (*idx == BIOVEC_MAX_IDX) {
fallback:
		bvl = mempool_alloc(bs->bvec_pool, gfp_mask);
	} else {
		struct biovec_slab *bvs = bvec_slabs + *idx;
		gfp_t __gfp_mask = gfp_mask & ~(__GFP_WAIT | __GFP_IO);

		/*
		 * Make this allocation restricted and don't dump info on
		 * allocation failures, since we'll fallback to the mempool
		 * in case of failure.
		 */
		__gfp_mask |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;

		/*
		 * Try a slab allocation. If this fails and __GFP_WAIT
		 * is set, retry with the 1-entry mempool
		 */
		bvl = kmem_cache_alloc(bvs->slab, __gfp_mask);
		if (unlikely(!bvl && (gfp_mask & __GFP_WAIT))) {
			*idx = BIOVEC_MAX_IDX;
			goto fallback;
		}
	}

	return bvl;
}

static void __bio_free(struct bio *bio)
{
	bio_disassociate_task(bio);

	if (bio_integrity(bio))
		bio_integrity_free(bio);
}

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

	__bio_free(bio);

	if (bs) {
		if (bio_has_allocated_vec(bio))
			bvec_free_bs(bs, bio->bi_io_vec, BIO_POOL_IDX(bio));

		/*
		 * 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);
	}
}

void bio_init(struct bio *bio)
{
	memset(bio, 0, sizeof(*bio));
	bio->bi_flags = 1 << BIO_UPTODATE;
	atomic_set(&bio->bi_cnt, 1);
}
EXPORT_SYMBOL(bio_init);

/**
 * bio_reset - reinitialize a bio
 * @bio:	bio to reset
 *
 * 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)
{
	unsigned long flags = bio->bi_flags & (~0UL << BIO_RESET_BITS);

	__bio_free(bio);

	memset(bio, 0, BIO_RESET_BYTES);
	bio->bi_flags = flags|(1 << BIO_UPTODATE);
}
EXPORT_SYMBOL(bio_reset);

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;

		generic_make_request(bio);
	}
}

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

	/*
	 * 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)))
		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);

	*current->bio_list = 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
 * @gfp_mask:   the GFP_ mask given to the slab allocator
 * @nr_iovecs:	number of iovecs to pre-allocate
 * @bs:		the bio_set to allocate from.
 *
 * Description:
 *   If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is
 *   backed by the @bs's mempool.
 *
 *   When @bs is not NULL, if %__GFP_WAIT 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 this 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 generic_make_request() (i.e. any block
 *   driver), bios are not submitted until after you return - see the code in
 *   generic_make_request() that converts recursion into iteration, to prevent
 *   stack overflows.
 *
 *   This would normally mean allocating multiple bios under
 *   generic_make_request() 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
 *   generic_make_request() 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(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
{
	gfp_t saved_gfp = gfp_mask;
	unsigned front_pad;
	unsigned inline_vecs;
	unsigned long idx = BIO_POOL_NONE;
	struct bio_vec *bvl = NULL;
	struct bio *bio;
	void *p;

	if (!bs) {
		if (nr_iovecs > UIO_MAXIOV)
			return NULL;

		p = kmalloc(sizeof(struct bio) +
			    nr_iovecs * sizeof(struct bio_vec),
			    gfp_mask);
		front_pad = 0;
		inline_vecs = nr_iovecs;
	} else {
		/*
		 * generic_make_request() 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 generic_make_request(). 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_WAIT; 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))
			gfp_mask &= ~__GFP_WAIT;

		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);
		}

		front_pad = bs->front_pad;
		inline_vecs = BIO_INLINE_VECS;
	}

	if (unlikely(!p))
		return NULL;

	bio = p + front_pad;
	bio_init(bio);

	if (nr_iovecs > inline_vecs) {
		bvl = bvec_alloc_bs(gfp_mask, nr_iovecs, &idx, bs);
		if (!bvl && gfp_mask != saved_gfp) {
			punt_bios_to_rescuer(bs);
			gfp_mask = saved_gfp;
			bvl = bvec_alloc_bs(gfp_mask, nr_iovecs, &idx, bs);
		}

		if (unlikely(!bvl))
			goto err_free;
	} else if (nr_iovecs) {
		bvl = bio->bi_inline_vecs;
	}

	bio->bi_pool = bs;
	bio->bi_flags |= idx << BIO_POOL_OFFSET;
	bio->bi_max_vecs = nr_iovecs;
	bio->bi_io_vec = bvl;
	return bio;

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

void zero_fill_bio(struct bio *bio)
{
	unsigned long flags;
	struct bio_vec *bv;
	int i;

	bio_for_each_segment(bv, bio, i) {
		char *data = bvec_kmap_irq(bv, &flags);
		memset(data, 0, bv->bv_len);
		flush_dcache_page(bv->bv_page);
		bvec_kunmap_irq(data, &flags);
	}
}
EXPORT_SYMBOL(zero_fill_bio);

/**
 * 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)
{
	BIO_BUG_ON(!atomic_read(&bio->bi_cnt));

	/*
	 * last put frees it
	 */
	if (atomic_dec_and_test(&bio->bi_cnt))
		bio_free(bio);
}
EXPORT_SYMBOL(bio_put);

inline int bio_phys_segments(struct request_queue *q, struct bio *bio)
{
	if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
		blk_recount_segments(q, bio);

	return bio->bi_phys_segments;
}
EXPORT_SYMBOL(bio_phys_segments);

/**
 * 	__bio_clone	-	clone a bio
 * 	@bio: destination bio
 * 	@bio_src: bio to clone
 *
 *	Clone a &bio. Caller will own the returned bio, but not
 *	the actual data it points to. Reference count of returned
 * 	bio will be one.
 */
void __bio_clone(struct bio *bio, struct bio *bio_src)
{
	memcpy(bio->bi_io_vec, bio_src->bi_io_vec,
		bio_src->bi_max_vecs * sizeof(struct bio_vec));

	/*
	 * most users will be overriding ->bi_bdev with a new target,
	 * so we don't set nor calculate new physical/hw segment counts here
	 */
	bio->bi_sector = bio_src->bi_sector;
	bio->bi_bdev = bio_src->bi_bdev;
	bio->bi_flags |= 1 << BIO_CLONED;
	bio->bi_rw = bio_src->bi_rw;
	bio->bi_vcnt = bio_src->bi_vcnt;
	bio->bi_size = bio_src->bi_size;
	bio->bi_idx = bio_src->bi_idx;
}
EXPORT_SYMBOL(__bio_clone);

/**
 *	bio_clone_bioset -	clone a bio
 *	@bio: bio to clone
 *	@gfp_mask: allocation priority
 *	@bs: bio_set to allocate from
 *
 * 	Like __bio_clone, only also allocates the returned bio
 */
struct bio *bio_clone_bioset(struct bio *bio, gfp_t gfp_mask,
			     struct bio_set *bs)
{
	struct bio *b;

	b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, bs);
	if (!b)
		return NULL;

	__bio_clone(b, bio);

	if (bio_integrity(bio)) {
		int ret;

		ret = bio_integrity_clone(b, bio, gfp_mask);

		if (ret < 0) {
			bio_put(b);
			return NULL;
		}
	}

	return b;
}
EXPORT_SYMBOL(bio_clone_bioset);

/**
 *	bio_get_nr_vecs		- return approx number of vecs
 *	@bdev:  I/O target
 *
 *	Return the approximate number of pages we can send to this target.
 *	There's no guarantee that you will be able to fit this number of pages
 *	into a bio, it does not account for dynamic restrictions that vary
 *	on offset.
 */
int bio_get_nr_vecs(struct block_device *bdev)
{
	struct request_queue *q = bdev_get_queue(bdev);
	int nr_pages;

	nr_pages = min_t(unsigned,
		     queue_max_segments(q),
		     queue_max_sectors(q) / (PAGE_SIZE >> 9) + 1);

	return min_t(unsigned, nr_pages, BIO_MAX_PAGES);

}
EXPORT_SYMBOL(bio_get_nr_vecs);

static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
			  *page, unsigned int len, unsigned int offset,
			  unsigned short max_sectors)
{
	int retried_segments = 0;
	struct bio_vec *bvec;

	/*
	 * cloned bio must not modify vec list
	 */
	if (unlikely(bio_flagged(bio, BIO_CLONED)))
		return 0;

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

	/*
	 * For filesystems with a blocksize smaller than the pagesize
	 * we will often be called with the same page as last time and
	 * a consecutive offset.  Optimize this special case.
	 */
	if (bio->bi_vcnt > 0) {
		struct bio_vec *prev = &bio->bi_io_vec[bio->bi_vcnt - 1];

		if (page == prev->bv_page &&
		    offset == prev->bv_offset + prev->bv_len) {
			unsigned int prev_bv_len = prev->bv_len;
			prev->bv_len += len;

			if (q->merge_bvec_fn) {
				struct bvec_merge_data bvm = {
					/* prev_bvec is already charged in
					   bi_size, discharge it in order to
					   simulate merging updated prev_bvec
					   as new bvec. */
					.bi_bdev = bio->bi_bdev,
					.bi_sector = bio->bi_sector,
					.bi_size = bio->bi_size - prev_bv_len,
					.bi_rw = bio->bi_rw,
				};

				if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len) {
					prev->bv_len -= len;
					return 0;
				}
			}

			goto done;
		}
	}

	if (bio->bi_vcnt >= bio->bi_max_vecs)
		return 0;

	/*
	 * we might lose a segment or two here, but rather that than
	 * make this too complex.
	 */

	while (bio->bi_phys_segments >= queue_max_segments(q)) {

		if (retried_segments)
			return 0;

		retried_segments = 1;
		blk_recount_segments(q, bio);
	}

	/*
	 * setup the new entry, we might clear it again later if we
	 * cannot add the page
	 */
	bvec = &bio->bi_io_vec[bio->bi_vcnt];
	bvec->bv_page = page;
	bvec->bv_len = len;
	bvec->bv_offset = offset;

	/*
	 * if queue has other restrictions (eg varying max sector size
	 * depending on offset), it can specify a merge_bvec_fn in the
	 * queue to get further control
	 */
	if (q->merge_bvec_fn) {
		struct bvec_merge_data bvm = {
			.bi_bdev = bio->bi_bdev,
			.bi_sector = bio->bi_sector,
			.bi_size = bio->bi_size,
			.bi_rw = bio->bi_rw,
		};

		/*
		 * merge_bvec_fn() returns number of bytes it can accept
		 * at this offset
		 */
		if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len) {
			bvec->bv_page = NULL;
			bvec->bv_len = 0;
			bvec->bv_offset = 0;
			return 0;
		}
	}

	/* If we may be able to merge these biovecs, force a recount */
	if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
		bio->bi_flags &= ~(1 << BIO_SEG_VALID);

	bio->bi_vcnt++;
	bio->bi_phys_segments++;
 done:
	bio->bi_size += len;
	return len;
}

/**
 *	bio_add_pc_page	-	attempt to add page to 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 REQ_PC bios.
 */
int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page,
		    unsigned int len, unsigned int offset)
{
	return __bio_add_page(q, bio, page, len, offset,
			      queue_max_hw_sectors(q));
}
EXPORT_SYMBOL(bio_add_pc_page);

/**
 *	bio_add_page	-	attempt to add page to 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. 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.
 */
int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
		 unsigned int offset)
{
	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
	return __bio_add_page(q, bio, page, len, offset, queue_max_sectors(q));
}
EXPORT_SYMBOL(bio_add_page);

struct bio_map_data {
	struct bio_vec *iovecs;
	struct sg_iovec *sgvecs;
	int nr_sgvecs;
	int is_our_pages;
};

static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
			     struct sg_iovec *iov, int iov_count,
			     int is_our_pages)
{
	memcpy(bmd->iovecs, bio->bi_io_vec, sizeof(struct bio_vec) * bio->bi_vcnt);
	memcpy(bmd->sgvecs, iov, sizeof(struct sg_iovec) * iov_count);
	bmd->nr_sgvecs = iov_count;
	bmd->is_our_pages = is_our_pages;
	bio->bi_private = bmd;
}

static void bio_free_map_data(struct bio_map_data *bmd)
{
	kfree(bmd->iovecs);
	kfree(bmd->sgvecs);
	kfree(bmd);
}

static struct bio_map_data *bio_alloc_map_data(int nr_segs,
					       unsigned int iov_count,
					       gfp_t gfp_mask)
{
	struct bio_map_data *bmd;

	if (iov_count > UIO_MAXIOV)
		return NULL;

	bmd = kmalloc(sizeof(*bmd), gfp_mask);
	if (!bmd)
		return NULL;

	bmd->iovecs = kmalloc(sizeof(struct bio_vec) * nr_segs, gfp_mask);
	if (!bmd->iovecs) {
		kfree(bmd);
		return NULL;
	}

	bmd->sgvecs = kmalloc(sizeof(struct sg_iovec) * iov_count, gfp_mask);
	if (bmd->sgvecs)
		return bmd;

	kfree(bmd->iovecs);
	kfree(bmd);
	return NULL;
}

static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
			  struct sg_iovec *iov, int iov_count,
			  int to_user, int from_user, int do_free_page)
{
	int ret = 0, i;
	struct bio_vec *bvec;
	int iov_idx = 0;
	unsigned int iov_off = 0;

	__bio_for_each_segment(bvec, bio, i, 0) {
		char *bv_addr = page_address(bvec->bv_page);
		unsigned int bv_len = iovecs[i].bv_len;

		while (bv_len && iov_idx < iov_count) {
			unsigned int bytes;
			char __user *iov_addr;

			bytes = min_t(unsigned int,
				      iov[iov_idx].iov_len - iov_off, bv_len);
			iov_addr = iov[iov_idx].iov_base + iov_off;

			if (!ret) {
				if (to_user)
					ret = copy_to_user(iov_addr, bv_addr,
							   bytes);

				if (from_user)
					ret = copy_from_user(bv_addr, iov_addr,
							     bytes);

				if (ret)
					ret = -EFAULT;
			}

			bv_len -= bytes;
			bv_addr += bytes;
			iov_addr += bytes;
			iov_off += bytes;

			if (iov[iov_idx].iov_len == iov_off) {
				iov_idx++;
				iov_off = 0;
			}
		}

		if (do_free_page)
			__free_page(bvec->bv_page);
	}

	return ret;
}

/**
 *	bio_uncopy_user	-	finish previously mapped bio
 *	@bio: bio being terminated
 *
 *	Free pages allocated from bio_copy_user() and write back data
 *	to user space in case of a read.
 */
int bio_uncopy_user(struct bio *bio)
{
	struct bio_map_data *bmd = bio->bi_private;
	int ret = 0;

	if (!bio_flagged(bio, BIO_NULL_MAPPED))
		ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
				     bmd->nr_sgvecs, bio_data_dir(bio) == READ,
				     0, bmd->is_our_pages);
	bio_free_map_data(bmd);
	bio_put(bio);
	return ret;
}
EXPORT_SYMBOL(bio_uncopy_user);

/**
 *	bio_copy_user_iov	-	copy user data to bio
 *	@q: destination block queue
 *	@map_data: pointer to the rq_map_data holding pages (if necessary)
 *	@iov:	the iovec.
 *	@iov_count: number of elements in the iovec
 *	@write_to_vm: bool indicating writing to pages or not
 *	@gfp_mask: memory allocation flags
 *
 *	Prepares and returns a bio for indirect user io, bouncing data
 *	to/from kernel pages as necessary. Must be paired with
 *	call bio_uncopy_user() on io completion.
 */
struct bio *bio_copy_user_iov(struct request_queue *q,
			      struct rq_map_data *map_data,
			      struct sg_iovec *iov, int iov_count,
			      int write_to_vm, gfp_t gfp_mask)
{
	struct bio_map_data *bmd;
	struct bio_vec *bvec;
	struct page *page;
	struct bio *bio;
	int i, ret;
	int nr_pages = 0;
	unsigned int len = 0;
	unsigned int offset = map_data ? map_data->offset & ~PAGE_MASK : 0;

	for (i = 0; i < iov_count; i++) {
		unsigned long uaddr;
		unsigned long end;
		unsigned long start;

		uaddr = (unsigned long)iov[i].iov_base;
		end = (uaddr + iov[i].iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT;
		start = uaddr >> PAGE_SHIFT;

		/*
		 * Overflow, abort
		 */
		if (end < start)
			return ERR_PTR(-EINVAL);

		nr_pages += end - start;
		len += iov[i].iov_len;
	}

	if (offset)
		nr_pages++;

	bmd = bio_alloc_map_data(nr_pages, iov_count, gfp_mask);
	if (!bmd)
		return ERR_PTR(-ENOMEM);

	ret = -ENOMEM;
	bio = bio_kmalloc(gfp_mask, nr_pages);
	if (!bio)
		goto out_bmd;

	if (!write_to_vm)
		bio->bi_rw |= REQ_WRITE;

	ret = 0;

	if (map_data) {
		nr_pages = 1 << map_data->page_order;
		i = map_data->offset / PAGE_SIZE;
	}
	while (len) {
		unsigned int bytes = PAGE_SIZE;

		bytes -= offset;

		if (bytes > len)
			bytes = len;

		if (map_data) {
			if (i == map_data->nr_entries * nr_pages) {
				ret = -ENOMEM;
				break;
			}

			page = map_data->pages[i / nr_pages];
			page += (i % nr_pages);

			i++;
		} else {
			page = alloc_page(q->bounce_gfp | gfp_mask);
			if (!page) {
				ret = -ENOMEM;
				break;
			}
		}

		if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes)
			break;

		len -= bytes;
		offset = 0;
	}

	if (ret)
		goto cleanup;

	/*
	 * success
	 */
	if ((!write_to_vm && (!map_data || !map_data->null_mapped)) ||
	    (map_data && map_data->from_user)) {
		ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0, 1, 0);
		if (ret)
			goto cleanup;
	}

	bio_set_map_data(bmd, bio, iov, iov_count, map_data ? 0 : 1);
	return bio;
cleanup:
	if (!map_data)
		bio_for_each_segment(bvec, bio, i)
			__free_page(bvec->bv_page);