123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058/*
 * 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/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 <trace/events/block.h>
#include "blk.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

/*
 * 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[BVEC_POOL_NR] __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, ARCH_KMALLOC_MINALIGN,
				 SLAB_HWCACHE_ALIGN, NULL);
	if (!slab)
		goto out_unlock;

	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(mempool_t *pool, struct bio_vec *bv, unsigned int idx)
{
	if (!idx)
		return;
	idx--;

	BIO_BUG_ON(idx >= BVEC_POOL_NR);

	if (idx == BVEC_POOL_MAX) {
		mempool_free(bv, pool);
	} else {
		struct biovec_slab *bvs = bvec_slabs + idx;

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

struct bio_vec *bvec_alloc(gfp_t gfp_mask, int nr, unsigned long *idx,
			   mempool_t *pool)
{
	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 == BVEC_POOL_MAX) {
fallback:
		bvl = mempool_alloc(pool, gfp_mask);
	} else {
		struct biovec_slab *bvs = bvec_slabs + *idx;
		gfp_t __gfp_mask = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __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_DIRECT_RECLAIM
		 * is set, retry with the 1-entry mempool
		 */
		bvl = kmem_cache_alloc(bvs->slab, __gfp_mask);
		if (unlikely(!bvl && (gfp_mask & __GFP_DIRECT_RECLAIM))) {
			*idx = BVEC_POOL_MAX;
			goto fallback;
		}
	}

	(*idx)++;
	return bvl;
}

void bio_uninit(struct bio *bio)
{
	bio_disassociate_task(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, BVEC_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);
	}
}

/*
 * 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 bio_vec *table,
	      unsigned short max_vecs)
{
	memset(bio, 0, sizeof(*bio));
	atomic_set(&bio->__bi_remaining, 1);
	atomic_set(&bio->__bi_cnt, 1);

	bio->bi_io_vec = table;
	bio->bi_max_vecs = max_vecs;
}
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_uninit(bio);

	memset(bio, 0, BIO_RESET_BYTES);
	bio->bi_flags = flags;
	atomic_set(&bio->__bi_remaining, 1);
}
EXPORT_SYMBOL(bio_reset);

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

	if (!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 @bio's parent 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);

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;

	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
 * @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_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 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, unsigned int nr_iovecs,
			     struct bio_set *bs)
{
	gfp_t saved_gfp = gfp_mask;
	unsigned front_pad;
	unsigned inline_vecs;
	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 {
		/* should not use nobvec bioset for nr_iovecs > 0 */
		if (WARN_ON_ONCE(!bs->bvec_pool && nr_iovecs > 0))
			return NULL;
		/*
		 * 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_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);
		}

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

	if (unlikely(!p))
		return NULL;

	bio = p + front_pad;
	bio_init(bio, NULL, 0);

	if (nr_iovecs > inline_vecs) {
		unsigned long idx = 0;

		bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
		if (!bvl && gfp_mask != saved_gfp) {
			punt_bios_to_rescuer(bs);
			gfp_mask = saved_gfp;
			bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
		}

		if (unlikely(!bvl))
			goto err_free;

		bio->bi_flags |= idx << BVEC_POOL_OFFSET;
	} else if (nr_iovecs) {
		bvl = bio->bi_inline_vecs;
	}

	bio->bi_pool = bs;
	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;
	struct bvec_iter iter;

	bio_for_each_segment(bv, bio, iter) {
		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)
{
	if (!bio_flagged(bio, BIO_REFFED))
		bio_free(bio);
	else {
		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_fast - clone a bio that shares the original bio's biovec
 * 	@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.
 *
 * 	Caller must ensure that @bio_src is not freed before @bio.
 */
void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
{
	BUG_ON(bio->bi_pool && BVEC_POOL_IDX(bio));

	/*
	 * most users will be overriding ->bi_disk with a new target,
	 * so we don't set nor calculate new physical/hw segment counts here
	 */
	bio->bi_disk = bio_src->bi_disk;
	bio->bi_partno = bio_src->bi_partno;
	bio_set_flag(bio, BIO_CLONED);
	bio->bi_opf = bio_src->bi_opf;
	bio->bi_write_hint = bio_src->bi_write_hint;
	bio->bi_iter = bio_src->bi_iter;
	bio->bi_io_vec = bio_src->bi_io_vec;

	bio_clone_blkcg_association(bio, bio_src);
}
EXPORT_SYMBOL(__bio_clone_fast);

/**
 *	bio_clone_fast - clone a bio that shares the original bio's biovec
 *	@bio: bio to clone
 *	@gfp_mask: allocation priority
 *	@bs: bio_set to allocate from
 *
 * 	Like __bio_clone_fast, only also allocates the returned bio
 */
struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
{
	struct bio *b;

	b = bio_alloc_bioset(gfp_mask, 0, bs);
	if (!b)
		return NULL;

	__bio_clone_fast(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_fast);

/**
 * 	bio_clone_bioset - clone a bio
 * 	@bio_src: bio to clone
 *	@gfp_mask: allocation priority
 *	@bs: bio_set to allocate from
 *
 *	Clone bio. Caller will own the returned bio, but not the actual data it
 *	points to. Reference count of returned bio will be one.
 */
struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
			     struct bio_set *bs)
{
	struct bvec_iter iter;
	struct bio_vec bv;
	struct bio *bio;

	/*
	 * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
	 * bio_src->bi_io_vec to bio->bi_io_vec.
	 *
	 * We can't do that anymore, because:
	 *
	 *  - The point of cloning the biovec is to produce a bio with a biovec
	 *    the caller can modify: bi_idx and bi_bvec_done should be 0.
	 *
	 *  - The original bio could've had more than BIO_MAX_PAGES biovecs; if
	 *    we tried to clone the whole thing bio_alloc_bioset() would fail.
	 *    But the clone should succeed as long as the number of biovecs we
	 *    actually need to allocate is fewer than BIO_MAX_PAGES.
	 *
	 *  - Lastly, bi_vcnt should not be looked at or relied upon by code
	 *    that does not own the bio - reason being drivers don't use it for
	 *    iterating over the biovec anymore, so expecting it to be kept up
	 *    to date (i.e. for clones that share the parent biovec) is just
	 *    asking for trouble and would force extra work on
	 *    __bio_clone_fast() anyways.
	 */

	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
	if (!bio)
		return NULL;
	bio->bi_disk		= bio_src->bi_disk;
	bio->bi_opf		= bio_src->bi_opf;
	bio->bi_write_hint	= bio_src->bi_write_hint;
	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;

	switch (bio_op(bio)) {
	case REQ_OP_DISCARD:
	case REQ_OP_SECURE_ERASE:
	case REQ_OP_WRITE_ZEROES:
		break;
	case REQ_OP_WRITE_SAME:
		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
		break;
	default:
		bio_for_each_segment(bv, bio_src, iter)
			bio->bi_io_vec[bio->bi_vcnt++] = bv;
		break;
	}

	if (bio_integrity(bio_src)) {
		int ret;

		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
		if (ret < 0) {
			bio_put(bio);
			return NULL;
		}
	}

	bio_clone_blkcg_association(bio, bio_src);

	return bio;
}
EXPORT_SYMBOL(bio_clone_bioset);

/**
 *	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)
{
	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_iter.bi_size + len) >> 9) > queue_max_hw_sectors(q))
		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) {
			prev->bv_len += len;
			bio->bi_iter.bi_size += len;
			goto done;
		}

		/*
		 * If the queue doesn't support SG gaps and adding this
		 * offset would create a gap, disallow it.
		 */
		if (bvec_gap_to_prev(q, prev, offset))
			return 0;
	}

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

	/*
	 * 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;
	bio->bi_vcnt++;
	bio->bi_phys_segments++;
	bio->bi_iter.bi_size += len;

	/*
	 * Perform a recount if the number of segments is greater
	 * than queue_max_segments(q).
	 */

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

		if (retried_segments)
			goto failed;

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

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

 done:
	return len;

 failed:
	bvec->bv_page = NULL;
	bvec->bv_len = 0;
	bvec->bv_offset = 0;
	bio->bi_vcnt--;
	bio->bi_iter.bi_size -= len;
	blk_recount_segments(q, bio);
	return 0;
}
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 will only fail
 *	if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio.
 */
int bio_add_page(struct bio *bio, struct page *page,
		 unsigned int len, unsigned int offset)
{
	struct bio_vec *bv;

	/*
	 * cloned bio must not modify vec list
	 */
	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
		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) {
		bv = &bio->bi_io_vec[bio->bi_vcnt - 1];

		if (page == bv->bv_page &&
		    offset == bv->bv_offset + bv->bv_len) {
			bv->bv_len += len;
			goto done;
		}
	}

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

	bv		= &bio->bi_io_vec[bio->bi_vcnt];
	bv->bv_page	= page;
	bv->bv_len	= len;
	bv->bv_offset	= offset;

	bio->bi_vcnt++;
done:
	bio->bi_iter.bi_size += len;
	return len;
}
EXPORT_SYMBOL(bio_add_page);

/**
 * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
 * @bio: bio to add pages to
 * @iter: iov iterator describing the region to be mapped
 *
 * Pins as many pages from *iter and appends them to @bio's bvec array. The
 * pages will have to be released using put_page() when done.
 */
int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
{
	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
	struct page **pages = (struct page **)bv;
	size_t offset, diff;
	ssize_t size;

	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
	if (unlikely(size <= 0))
		return size ? size : -EFAULT;
	nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;

	/*
	 * Deep magic below:  We need to walk the pinned pages backwards
	 * because we are abusing the space allocated for the bio_vecs
	 * for the page array.  Because the bio_vecs are larger than the
	 * page pointers by definition this will always work.  But it also
	 * means we can't use bio_add_page, so any changes to it's semantics
	 * need to be reflected here as well.
	 */
	bio->bi_iter.bi_size += size;
	bio->bi_vcnt += nr_pages;

	diff = (nr_pages * PAGE_SIZE - offset) - size;
	while (nr_pages--) {
		bv[nr_pages].bv_page = pages[nr_pages];
		bv[nr_pages].bv_len = PAGE_SIZE;
		bv[nr_pages].bv_offset = 0;
	}

	bv[0].bv_offset += offset;
	bv[0].bv_len -= offset;
	if (diff)
		bv[bio->bi_vcnt - 1].bv_len -= diff;

	iov_iter_advance(iter, size);
	return 0;
}
EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);

static void submit_bio_wait_endio(struct bio *bio)
{
	complete(bio->bi_private);
}

/**
 * submit_bio_wait - submit a bio, and wait until it completes
 * @bio: The &struct bio which describes the I/O
 *
 * Simple wrapper around submit_bio(). Returns 0 on success, or the error from
 * bio_endio() on failure.
 *
 * WARNING: Unlike to how submit_bio() is usually used, this function does not
 * result in bio reference to be consumed. The caller must drop the reference
 * on his own.
 */
int submit_bio_wait(struct bio *bio)
{
	DECLARE_COMPLETION_ONSTACK_MAP(done, bio->bi_disk->lockdep_map);

	bio->bi_private = &done;
	bio->bi_end_io = submit_bio_wait_endio;
	bio->bi_opf |= REQ_SYNC;
	submit_bio(bio);
	wait_for_completion_io(&done);

	return blk_status_to_errno(bio->bi_status);
}
EXPORT_SYMBOL(submit_bio_wait);

/**
 * bio_advance - increment/complete a bio by some number of bytes
 * @bio:	bio to advance
 * @bytes:	number of bytes to complete
 *
 * This updates bi_sector, bi_size and bi_idx; if the number of bytes to
 * complete doesn't align with a bvec boundary, then bv_len and bv_offset will
 * be updated on the last bvec as well.
 *
 * @bio will then represent the remaining, uncompleted portion of the io.
 */
void bio_advance(struct bio *bio, unsigned bytes)
{
	if (bio_integrity(bio))
		bio_integrity_advance(bio, bytes);

	bio_advance_iter(bio, &bio->bi_iter, bytes);
}
EXPORT_SYMBOL(bio_advance);

/**
 * bio_alloc_pages - allocates a single page for each bvec in a bio
 * @bio: bio to allocate pages for
 * @gfp_mask: flags for allocation
 *
 * Allocates pages up to @bio->bi_vcnt.
 *
 * Returns 0 on success, -ENOMEM on failure. On failure, any allocated pages are
 * freed.
 */
int bio_alloc_pages(struct bio *bio, gfp_t gfp_mask)
{
	int i;
	struct bio_vec *bv;

	bio_for_each_segment_all(bv, bio, i) {
		bv->bv_page = alloc_page(gfp_mask);
		if (!bv->bv_page) {
			while (--bv >= bio->bi_io_vec)
				__free_page(bv->bv_page);
			return -ENOMEM;
		}
	}

	return 0;
}
EXPORT_SYMBOL(bio_alloc_pages);

/**
 * bio_copy_data - copy contents of data buffers from one chain of bios to
 * another
 * @src: source bio list
 * @dst: destination bio list
 *
 * If @src and @dst are single bios, bi_next must be NULL - otherwise, treats
 * @src and @dst as linked lists of bios.
 *
 * Stops when it reaches the end of either @src or @dst - that is, copies
 * min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of bios).
 */
void bio_copy_data(struct bio *dst, struct bio *src)
{
	struct bvec_iter src_iter, dst_iter;
	struct bio_vec src_bv, dst_bv;
	void *src_p, *dst_p;
	unsigned bytes;

	src_iter = src->bi_iter;
	dst_iter = dst->bi_iter;

	while (1) {
		if (!src_iter.bi_size) {
			src = src->bi_next;
			if (!src)
				break;

			src_iter = src->bi_iter;
		}

		if (!dst_iter.bi_size) {
			dst = dst->bi_next;
			if (!dst)
				break;

			dst_iter = dst->bi_iter;
		}

		src_bv = bio_iter_iovec(src, src_iter);
		dst_bv = bio_iter_iovec(dst, dst_iter);

		bytes = min(src_bv.bv_len, dst_bv.bv_len);

		src_p = kmap_atomic(src_bv.bv_page);
		dst_p = kmap_atomic(dst_bv.bv_page);

		memcpy(dst_p + dst_bv.bv_offset,
		       src_p + src_bv.bv_offset,
		       bytes);

		kunmap_atomic(dst_p);
		kunmap_atomic(src_p);

		bio_advance_iter(src, &src_iter, bytes);
		bio_advance_iter(dst, &dst_iter, bytes);
	}
}
EXPORT_SYMBOL(bio_copy_data);

struct bio_map_data {
	int is_our_pages;
	struct iov_iter iter;
	struct iovec iov[];
};

static struct bio_map_data *bio_alloc_map_data(struct iov_iter *data,
					       gfp_t gfp_mask)
{
	struct bio_map_data *bmd;
	if (data->nr_segs > UIO_MAXIOV)
		return NULL;

	bmd = kmalloc(sizeof(struct bio_map_data) +
		       sizeof(struct iovec) * data->nr_segs, gfp_mask);
	if (!bmd)
		return NULL;
	memcpy(bmd->iov, data->iov, sizeof(struct iovec) * data->nr_segs);
	bmd->iter = *data;
	bmd->iter.iov = bmd->iov;
	return bmd;
}

/**
 * bio_copy_from_iter - copy all pages from iov_iter to bio
 * @bio: The &struct bio which describes the I/O as destination
 * @iter: iov_iter as source
 *
 * Copy all pages from iov_iter to bio.
 * Returns 0 on success, or error on failure.
 */
static int bio_copy_from_iter(struct bio *bio, struct iov_iter *iter)
{
	int i;
	struct bio_vec *bvec;

	bio_for_each_segment_all(bvec, bio, i) {
		ssize_t ret;

		ret = copy_page_from_iter(bvec->bv_page,
					  bvec->bv_offset,
					  bvec->bv_len,
					  iter);

		if (!iov_iter_count(iter))
			break;

		if (ret < bvec->bv_len)
			return -EFAULT;
	}

	return 0;
}

/**
 * bio_copy_to_iter - copy all pages from bio to iov_iter
 * @bio: The &struct bio which describes the I/O as source
 * @iter: iov_iter as destination
 *
 * Copy all pages from bio to iov_iter.
 * Returns 0 on success, or error on failure.
 */
static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter)
{
	int i;
	struct bio_vec *bvec;

	bio_for_each_segment_all(bvec, bio, i) {
		ssize_t ret;

		ret = copy_page_to_iter(bvec->bv_page,
					bvec->bv_offset,
					bvec->bv_len,
					&iter);

		if (!iov_iter_count(&iter))
			break;

		if (ret < bvec->bv_len)
			return -EFAULT;
	}

	return 0;
}

void bio_free_pages(struct bio *bio)
{
	struct bio_vec *bvec;
	int i;

	bio_for_each_segment_all(bvec, bio, i)
		__free_page(bvec->bv_page);
}
EXPORT_SYMBOL(bio_free_pages);

/**
 *	bio_uncopy_user	-	finish previously mapped bio
 *	@bio: bio being terminated
 *
 *	Free pages allocated from bio_copy_user_iov() 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)) {
		/*
		 * if we're in a workqueue, the request is orphaned, so
		 * don't copy into a random user address space, just free
		 * and return -EINTR so user space doesn't expect any data.
		 */
		if (!current->mm)
			ret = -EINTR;
		else if (bio_data_dir(bio) == READ)
			ret = bio_copy_to_iter(bio, bmd->iter);
		if (bmd->is_our_pages)
			bio_free_pages(bio);
	}
	kfree(bmd);
	bio_put(bio);
	return ret;
}

/**
 *	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)
 *	@iter:		iovec iterator
 *	@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 iov_iter *iter,
			      gfp_t gfp_mask)
{
	struct bio_map_data *bmd;
	struct page *page;
	struct bio *bio;
	int i = 0, ret;
	int nr_pages;
	unsigned int len = iter->count;
	unsigned int offset = map_data ? offset_in_page(map_data->offset) : 0;

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

	/*
	 * We need to do a deep copy of the iov_iter including the iovecs.
	 * The caller provided iov might point to an on-stack or otherwise
	 * shortlived one.
	 */
	bmd->is_our_pages = map_data ? 0 : 1;

	nr_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE);
	if (nr_pages > BIO_MAX_PAGES)
		nr_pages = BIO_MAX_PAGES;

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

	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;

	if (map_data)
		map_data->offset += bio->bi_iter.bi_size;

	/*
	 * success
	 */
	if (((iter->type & WRITE) && (!map_data || !map_data->null_mapped)) ||
	    (map_data && map_data->from_user)) {
		ret = bio_copy_from_iter(bio, iter);
		if (ret)
			goto cleanup;
	} else {
		iov_iter_advance(iter, bio->bi_iter.bi_size);
	}

	bio->bi_private = bmd;
	if (map_data && map_data->null_mapped)
		bio_set_flag(bio, BIO_NULL_MAPPED);
	return bio;
cleanup:
	if (!map_data)
		bio_free_pages(bio);
	bio_put(bio);
out_bmd:
	kfree(bmd);
	return ERR_PTR(ret);
}

/**
 *	bio_map_user_iov - map user iovec into bio
 *	@q:		the struct request_queue for the bio
 *	@iter:		iovec iterator
 *	@gfp_mask:	memory allocation flags
 *
 *	Map the user space address into a bio suitable for io to a block
 *	device. Returns an error pointer in case of error.
 */
struct bio *bio_map_user_iov(struct request_queue *q,
			     struct iov_iter *iter,
			     gfp_t gfp_mask)
{
	int j;
	struct bio *bio;
	int ret;
	struct bio_vec *bvec;

	if (!iov_iter_count(iter))
		return ERR_PTR(-EINVAL);

	bio = bio_kmalloc(gfp_mask, iov_iter_npages(iter, BIO_MAX_PAGES));
	if (!bio)
		return ERR_PTR(-ENOMEM);

	while (iov_iter_count(iter)) {
		struct page **pages;
		ssize_t bytes;
		size_t offs, added = 0;
		int npages;

		bytes = iov_iter_get_pages_alloc(iter, &pages, LONG_MAX, &offs);
		if (unlikely(bytes <= 0)) {
			ret = bytes ? bytes : -EFAULT;
			goto out_unmap;
		}

		npages = DIV_ROUND_UP(offs + bytes, PAGE_SIZE);

		if (unlikely(offs & queue_dma_alignment(q))) {
			ret = -EINVAL;
			j = 0;
		} else {
			for (j = 0; j < npages; j++) {
				struct page *page = pages[j];
				unsigned int n = PAGE_SIZE - offs;
				unsigned short prev_bi_vcnt = bio->bi_vcnt;

				if (n > bytes)
					n = bytes;

				if (!bio_add_pc_page(q, bio, page, n, offs))
					break;

				/*
				 * check if vector was merged with previous
				 * drop page reference if needed
				 */
				if (bio->bi_vcnt == prev_bi_vcnt)
					put_page(page);

				added += n;
				bytes -= n;
				offs = 0;
			}
			iov_iter_advance(iter, added);
		}
		/*
		 * release the pages we didn't map into the bio, if any
		 */
		while (j < npages)
			put_page(pages[j++]);
		kvfree(pages);
		/* couldn't stuff something into bio? */
		if (bytes)
			break;
	}

	bio_set_flag(bio, BIO_USER_MAPPED);

	/*
	 * subtle -- if bio_map_user_iov() ended up bouncing a bio,
	 * it would normally disappear when its bi_end_io is run.
	 * however, we need it for the unmap, so grab an extra
	 * reference to it
	 */
	bio_get(bio);
	return bio;

 out_unmap:
	bio_for_each_segment_all(bvec, bio, j) {
		put_page(bvec->bv_page);
	}
	bio_put(bio);
	return ERR_PTR(ret);
}

static void __bio_unmap_user(struct bio *bio)
{
	struct bio_vec *bvec;
	int i;

	/*
	 * make sure we dirty pages we wrote to
	 */
	bio_for_each_segment_all(bvec, bio, i) {
		if (bio_data_dir(bio) == READ)
			set_page_dirty_lock(bvec->bv_page);

		put_page(bvec->bv_page);
	}

	bio_put(bio);
}

/**
 *	bio_unmap_user	-	unmap a bio
 *	@bio:		the bio being unmapped
 *
 *	Unmap a bio previously mapped by bio_map_user_iov(). Must be called from
 *	process context.
 *
 *	bio_unmap_user() may sleep.
 */
void bio_unmap_user(struct bio *bio)
{
	__bio_unmap_user(bio);
	bio_put(bio);
}

static void bio_map_kern_endio(struct bio *bio)
{
	bio_put(bio);
}

/**
 *	bio_map_kern	-	map kernel address into bio
 *	@q: the struct request_queue for the bio
 *	@data: pointer to buffer to map
 *	@len: length in bytes
 *	@gfp_mask: allocation flags for bio allocation
 *
 *	Map the kernel address into a bio suitable for io to a block
 *	device. Returns an error pointer in case of error.
 */
struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
			 gfp_t gfp_mask)
{
	unsigned long kaddr = (unsigned long)data;
	unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
	unsigned long start = kaddr >> PAGE_SHIFT;
	const int nr_pages = end - start;
	int offset, i;
	struct bio *bio;

	bio = bio_kmalloc(gfp_mask, nr_pages);
	if (!bio)
		return ERR_PTR(-ENOMEM);

	offset = offset_in_page(kaddr);
	for (i = 0; i < nr_pages; i++) {
		unsigned int bytes = PAGE_SIZE - offset;

		if (len <= 0)
			break;

		if (bytes > len)
			bytes = len;

		if (bio_add_pc_page(q, bio, virt_to_page(data), bytes,
				    offset) < bytes) {
			/* we don't support partial mappings */
			bio_put(bio);
			return ERR_PTR(-EINVAL);
		}

		data += bytes;
		len -= bytes;
		offset = 0;
	}

	bio->bi_end_io = bio_map_kern_endio;
	return bio;
}
EXPORT_SYMBOL(bio_map_kern);

static void bio_copy_kern_endio(struct bio *bio)
{
	bio_free_pages(bio);
	bio_put(bio);
}

static void bio_copy_kern_endio_read(struct bio *bio)
{
	char *p = bio->bi_private;
	struct bio_vec *bvec;
	int i;

	bio_for_each_segment_all(bvec, bio, i) {
		memcpy(p, page_address(bvec->bv_page), bvec->bv_len);
		p += bvec->bv_len;
	}

	bio_copy_kern_endio(bio);
}

/**
 *	bio_copy_kern	-	copy kernel address into bio
 *	@q: the struct request_queue for the bio
 *	@data: pointer to buffer to copy
 *	@len: length in bytes
 *	@gfp_mask: allocation flags for bio and page allocation
 *	@reading: data direction is READ
 *
 *	copy the kernel address into a bio suitable for io to a block
 *	device. Returns an error pointer in case of error.
 */
struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
			  gfp_t gfp_mask, int reading)
{
	unsigned long kaddr = (unsigned long)data;
	unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
	unsigned long start = kaddr >> PAGE_SHIFT;
	struct bio *bio;
	void *p = data;
	int nr_pages = 0;

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

	nr_pages = end - start;
	bio = bio_kmalloc(gfp_mask, nr_pages);
	if (!bio)
		return ERR_PTR(-ENOMEM);

	while (len) {
		struct page *page;
		unsigned int bytes = PAGE_SIZE;

		if (bytes > len)
			bytes = len;

		page = alloc_page(q->bounce_gfp | gfp_mask);
		if (!page)
			goto cleanup;

		if (!reading)
			memcpy(page_address(page), p, bytes);

		if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes)
			break;

		len -= bytes;
		p += bytes;
	}

	if (reading) {
		bio->bi_end_io = bio_copy_kern_endio_read;
		bio->bi_private = data;
	} else {
		bio->bi_end_io = bio_copy_kern_endio;
	}

	return bio;

cleanup:
	bio_free_pages(bio);
	bio_put(bio);
	return ERR_PTR(-ENOMEM);
}

/*
 * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions
 * for performing direct-IO in BIOs.
 *
 * The problem is that we cannot run set_page_dirty() from interrupt context
 * because the required locks are not interrupt-safe.  So what we can do is to
 * mark the pages dirty _before_ performing IO.  And in interrupt context,
 * check that the pages are still dirty.   If so, fine.  If not, redirty them
 * in process context.
 *
 * We special-case compound pages here: normally this means reads into hugetlb
 * pages.  The logic in here doesn't really work right for compound pages
 * because the VM does not uniformly chase down the head page in all cases.
 * But dirtiness of compound pages is pretty meaningless anyway: the VM doesn't
 * handle them at all.  So we skip compound pages here at an early stage.
 *
 * Note that this code is very hard to test under normal circumstances because
 * direct-io pins the pages with get_user_pages().  This makes
 * is_page_cache_freeable return false, and the VM will not clean the pages.
 * But other code (eg, flusher threads) could clean the pages if they are mapped
 * pagecache.
 *
 * Simply disabling the call to bio_set_pages_dirty() is a good way to test the
 * deferred bio dirtying paths.
 */

/*
 * bio_set_pages_dirty() will mark all the bio's pages as dirty.
 */
void bio_set_pages_dirty(struct bio *bio)
{
	struct bio_vec *bvec;
	int i;

	bio_for_each_segment_all(bvec, bio, i) {
		struct page *page = bvec->bv_page;

		if (page && !PageCompound(page))
			set_page_dirty_lock(page);
	}
}

static void bio_release_pages(struct bio *bio)
{
	struct bio_vec *bvec;
	int i;

	bio_for_each_segment_all(bvec, bio, i) {
		struct page *page = bvec->bv_page;

		if (page)
			put_page(page);
	}
}

/*
 * bio_check_pages_dirty() will check that all the BIO's pages are still dirty.
 * If they are, then fine.  If, however, some pages are clean then they must
 * have been written out during the direct-IO read.  So we take another ref on
 * the BIO and the offending pages and re-dirty the pages in process context.
 *
 * It is expected that bio_check_pages_dirty() will wholly own the BIO from
 * here on.  It will run one put_page() against each page and will run one
 * bio_put() against the BIO.
 */

static void bio_dirty_fn(struct work_struct *work);

static DECLARE_WORK(bio_dirty_work, bio_dirty_fn);
static DEFINE_SPINLOCK(bio_dirty_lock);
static struct bio *bio_dirty_list;

/*
 * This runs in process context
 */
static void bio_dirty_fn(struct work_struct *work)
{
	unsigned long flags;
	struct bio *bio;

	spin_lock_irqsave(&bio_dirty_lock, flags);
	bio = bio_dirty_list;
	bio_dirty_list = NULL;
	spin_unlock_irqrestore(&bio_dirty_lock, flags);

	while (bio) {
		struct bio *next = bio->bi_private;

		bio_set_pages_dirty(bio);
		bio_release_pages(bio);
		bio_put(bio);
		bio = next;
	}
}

void bio_check_pages_dirty(struct bio *bio)
{
	struct bio_vec *bvec;
	int nr_clean_pages = 0;
	int i;

	bio_for_each_segment_all(bvec, bio, i) {
		struct page *page = bvec->bv_page;

		if (PageDirty(page) || PageCompound(page)) {
			put_page(page);
			bvec->bv_page = NULL;
		} else {
			nr_clean_pages++;
		}
	}

	if (nr_clean_pages) {
		unsigned long flags;

		spin_lock_irqsave(&bio_dirty_lock, flags);
		bio->bi_private = bio_dirty_list;
		bio_dirty_list = bio;
		spin_unlock_irqrestore(&bio_dirty_lock, flags);
		schedule_work(&bio_dirty_work);
	} else {
		bio_put(bio);
	}
}

void generic_start_io_acct(struct request_queue *q, int rw,
			   unsigned long sectors, struct hd_struct *part)
{
	int cpu = part_stat_lock();

	part_round_stats(q, cpu, part);
	part_stat_inc(cpu, part, ios[rw]);
	part_stat_add(cpu, part, sectors[rw], sectors);
	part_inc_in_flight(q, part, rw);

	part_stat_unlock();
}
EXPORT_SYMBOL(generic_start_io_acct);

void generic_end_io_acct(struct request_queue *q, int rw,
			 struct hd_struct *part, unsigned long start_time)
{
	unsigned long duration = jiffies - start_time;
	int cpu = part_stat_lock();

	part_stat_add(cpu, part, ticks[rw], duration);
	part_round_stats(q, cpu, part);
	part_dec_in_flight(q, part, rw);

	part_stat_unlock();
}
EXPORT_SYMBOL(generic_end_io_acct);

#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
void bio_flush_dcache_pages(struct bio *bi)
{
	struct bio_vec bvec;
	struct bvec_iter iter;

	bio_for_each_segment(bvec, bi, iter)
		flush_dcache_page(bvec.bv_page);
}
EXPORT_SYMBOL(bio_flush_dcache_pages);
#endif

static inline bool bio_remaining_done(struct bio *bio)
{
	/*
	 * If we're not chaining, then ->__bi_remaining is always 1 and
	 * we always end io on the first invocation.
	 */
	if (!bio_flagged(bio, BIO_CHAIN))
		return true;

	BUG_ON(atomic_read(&bio->__bi_remaining) <= 0);

	if (atomic_dec_and_test(&bio->__bi_remaining)) {
		bio_clear_flag(bio, BIO_CHAIN);
		return true;
	}

	return false;
}

/**
 * bio_endio - end I/O on a bio
 * @bio:	bio
 *
 * Description:
 *   bio_endio() will end I/O on the whole bio. bio_endio() is the preferred
 *   way to end I/O on a bio. No one should call bi_end_io() directly on a
 *   bio unless they own it and thus know that it has an end_io function.
 *
 *   bio_endio() can be called several times on a bio that has been chained
 *   using bio_chain().  The ->bi_end_io() function will only be called the
 *   last time.  At this point the BLK_TA_COMPLETE tracing event will be
 *   generated if BIO_TRACE_COMPLETION is set.
 **/
void bio_endio(struct bio *bio)
{
again:
	if (!bio_remaining_done(bio))
		return;
	if (!bio_integrity_endio(bio))
		return;

	/*
	 * Need to have a real endio function for chained bios, otherwise
	 * various corner cases will break (like stacking block devices that
	 * save/restore bi_end_io) - however, we want to avoid unbounded
	 * recursion and blowing the stack. Tail call optimization would
	 * handle this, but compiling with frame pointers also disables
	 * gcc's sibling call optimization.
	 */
	if (bio->bi_end_io == bio_chain_endio) {
		bio = __bio_chain_endio(bio);
		goto again;
	}

	if (bio->bi_disk && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
		trace_block_bio_complete(bio->bi_disk->queue, bio,
					 blk_status_to_errno(bio->bi_status));
		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
	}

	blk_throtl_bio_endio(bio);
	/* release cgroup info */
	bio_uninit(bio);
	if (bio->bi_end_io)
		bio->bi_end_io(bio);
}
EXPORT_SYMBOL(bio_endio);

/**
 * bio_split - split a bio
 * @bio:	bio to split
 * @sectors:	number of sectors to split from the front of @bio
 * @gfp:	gfp mask
 * @bs:		bio set to allocate from
 *
 * Allocates and returns a new bio which represents @sectors from the start of
 * @bio, and updates @bio to represent the remaining sectors.
 *
 * Unless this is a discard request the newly allocated bio will point
 * to @bio's bi_io_vec; it is the caller's responsibility to ensure that
 * @bio is not freed before the split.
 */
struct bio *bio_split(struct bio *bio, int sectors,
		      gfp_t gfp, struct bio_set *bs)
{
	struct bio *split;

	BUG_ON(sectors <= 0);
	BUG_ON(sectors >= bio_sectors(bio));

	split = bio_clone_fast(bio, gfp, bs);
	if (!split)
		return NULL;

	split->bi_iter.bi_size = sectors << 9;

	if (bio_integrity(split))
		bio_integrity_trim(split);

	bio_advance(bio, split->bi_iter.bi_size);

	if (bio_flagged(bio, BIO_TRACE_COMPLETION))
		bio_set_flag(bio, BIO_TRACE_COMPLETION);

	return split;
}
EXPORT_SYMBOL(bio_split);

/**
 * bio_trim - trim a bio
 * @bio:	bio to trim
 * @offset:	number of sectors to trim from the front of @bio
 * @size:	size we want to trim @bio to, in sectors
 */
void bio_trim(struct bio *bio, int offset, int size)
{
	/* 'bio' is a cloned bio which we need to trim to match
	 * the given offset and size.
	 */

	size <<= 9;
	if (offset == 0 && size == bio->bi_iter.bi_size)
		return;

	bio_clear_flag(bio, BIO_SEG_VALID);

	bio_advance(bio, offset << 9);

	bio->bi_iter.bi_size = size;

	if (bio_integrity(bio))
		bio_integrity_trim(bio);

}
EXPORT_SYMBOL_GPL(bio_trim);

/*
 * create memory pools for biovec's in a bio_set.
 * use the global biovec slabs created for general use.
 */
mempool_t *biovec_create_pool(int pool_entries)
{
	struct biovec_slab *bp = bvec_slabs + BVEC_POOL_MAX;

	return mempool_create_slab_pool(pool_entries, bp->slab);
}

void bioset_free(struct bio_set *bs)
{
	if (bs->rescue_workqueue)
		destroy_workqueue(bs->rescue_workqueue);

	mempool_destroy(bs->bio_pool);
	mempool_destroy(bs->bvec_pool);

	bioset_integrity_free(bs);
	bio_put_slab(bs);

	kfree(bs);
}
EXPORT_SYMBOL(bioset_free);

/**
 * bioset_create  - Create a bio_set
 * @pool_size:	Number of bio and bio_vecs to cache in the mempool
 * @front_pad:	Number of bytes to allocate in front of the returned bio
 * @flags:	Flags to modify behavior, currently %BIOSET_NEED_BVECS
 *              and %BIOSET_NEED_RESCUER
 *
 * Description:
 *    Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
 *    to ask for a number of bytes to be allocated in front of the bio.
 *    Front pad allocation is useful for embedding the bio inside
 *    another structure, to avoid allocating extra data to go with the bio.
 *    Note that the bio must be embedded at the END of that structure always,
 *    or things will break badly.
 *    If %BIOSET_NEED_BVECS is set in @flags, a separate pool will be allocated
 *    for allocating iovecs.  This pool is not needed e.g. for bio_clone_fast().
 *    If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used to
 *    dispatch queued requests when the mempool runs out of space.
 *
 */
struct bio_set *bioset_create(unsigned int pool_size,
			      unsigned int front_pad,
			      int flags)
{
	unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec);
	struct bio_set *bs;

	bs = kzalloc(sizeof(*bs), GFP_KERNEL);
	if (!bs)
		return NULL;

	bs->front_pad = front_pad;

	spin_lock_init(&bs->rescue_lock);
	bio_list_init(&bs->rescue_list);
	INIT_WORK(&bs->rescue_work, bio_alloc_rescue);

	bs->bio_slab = bio_find_or_create_slab(front_pad + back_pad);
	if (!bs->bio_slab) {
		kfree(bs);
		return NULL;
	}

	bs->bio_pool = mempool_create_slab_pool(pool_size, bs->bio_slab);
	if (!bs->bio_pool)
		goto bad;

	if (flags & BIOSET_NEED_BVECS) {
		bs->bvec_pool = biovec_create_pool(pool_size);
		if (!bs->bvec_pool)
			goto bad;
	}

	if (!(flags & BIOSET_NEED_RESCUER))
		return bs;

	bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0);
	if (!bs->rescue_workqueue)
		goto bad;

	return bs;
bad:
	bioset_free(bs);
	return NULL;
}
EXPORT_SYMBOL(bioset_create);

#ifdef CONFIG_BLK_CGROUP

/**
 * bio_associate_blkcg - associate a bio with the specified blkcg
 * @bio: target bio
 * @blkcg_css: css of the blkcg to associate
 *
 * Associate @bio with the blkcg specified by @blkcg_css.  Block layer will
 * treat @bio as if it were issued by a task which belongs to the blkcg.
 *
 * This function takes an extra reference of @blkcg_css which will be put
 * when @bio is released.  The caller must own @bio and is responsible for
 * synchronizing calls to this function.
 */
int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css)
{
	if (unlikely(bio->bi_css))
		return -EBUSY;
	css_get(blkcg_css);
	bio->bi_css = blkcg_css;
	return 0;
}
EXPORT_SYMBOL_GPL(bio_associate_blkcg);

/**
 * bio_disassociate_task - undo bio_associate_current()
 * @bio: target bio
 */
void bio_disassociate_task(struct bio *bio)
{
	if (bio->bi_ioc) {
		put_io_context(bio->bi_ioc);
		bio->bi_ioc = NULL;
	}
	if (bio->bi_css) {
		css_put(bio->bi_css);
		bio->bi_css = NULL;
	}
}

/**
 * bio_clone_blkcg_association - clone blkcg association from src to dst bio
 * @dst: destination bio
 * @src: source bio
 */
void bio_clone_blkcg_association(struct bio *dst, struct bio *src)
{
	if (src->bi_css)
		WARN_ON(bio_associate_blkcg(dst, src->bi_css));
}
EXPORT_SYMBOL_GPL(bio_clone_blkcg_association);
#endif /* CONFIG_BLK_CGROUP */

static void __init biovec_init_slabs(void)
{
	int i;

	for (i = 0; i < BVEC_POOL_NR; i++) {
		int size;
		struct biovec_slab *bvs = bvec_slabs + i;

		if (bvs->nr_vecs <= BIO_INLINE_VECS) {
			bvs->slab = NULL;
			continue;
		}

		size = bvs->nr_vecs * sizeof(struct bio_vec);
		bvs->slab = kmem_cache_create(bvs->name, size, 0,
                                SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
	}
}

static int __init init_bio(void)
{
	bio_slab_max = 2;
	bio_slab_nr = 0;
	bio_slabs = kzalloc(bio_slab_max * sizeof(struct bio_slab), GFP_KERNEL);
	if (!bio_slabs)
		panic("bio: can't allocate bios\n");

	bio_integrity_init();
	biovec_init_slabs();

	fs_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
	if (!fs_bio_set)
		panic("bio: can't allocate bios\n");

	if (bioset_integrity_create(fs_bio_set, BIO_POOL_SIZE))
		panic("bio: can't create integrity pool\n");

	return 0;
}
subsys_initcall