123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548/*
 * Common Block IO controller cgroup interface
 *
 * Based on ideas and code from CFQ, CFS and BFQ:
 * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
 *
 * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
 *		      Paolo Valente <paolo.valente@unimore.it>
 *
 * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
 * 	              Nauman Rafique <nauman@google.com>
 *
 * For policy-specific per-blkcg data:
 * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it>
 *                    Arianna Avanzini <avanzini.arianna@gmail.com>
 */
#include <linux/ioprio.h>
#include <linux/kdev_t.h>
#include <linux/module.h>
#include <linux/sched/signal.h>
#include <linux/err.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/slab.h>
#include <linux/genhd.h>
#include <linux/delay.h>
#include <linux/atomic.h>
#include <linux/ctype.h>
#include <linux/blk-cgroup.h>
#include "blk.h"

#define MAX_KEY_LEN 100

/*
 * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation.
 * blkcg_pol_register_mutex nests outside of it and synchronizes entire
 * policy [un]register operations including cgroup file additions /
 * removals.  Putting cgroup file registration outside blkcg_pol_mutex
 * allows grabbing it from cgroup callbacks.
 */
static DEFINE_MUTEX(blkcg_pol_register_mutex);
static DEFINE_MUTEX(blkcg_pol_mutex);

struct blkcg blkcg_root;
EXPORT_SYMBOL_GPL(blkcg_root);

struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css;

static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];

static LIST_HEAD(all_blkcgs);		/* protected by blkcg_pol_mutex */

static bool blkcg_policy_enabled(struct request_queue *q,
				 const struct blkcg_policy *pol)
{
	return pol && test_bit(pol->plid, q->blkcg_pols);
}

/**
 * blkg_free - free a blkg
 * @blkg: blkg to free
 *
 * Free @blkg which may be partially allocated.
 */
static void blkg_free(struct blkcg_gq *blkg)
{
	int i;

	if (!blkg)
		return;

	for (i = 0; i < BLKCG_MAX_POLS; i++)
		if (blkg->pd[i])
			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);

	if (blkg->blkcg != &blkcg_root)
		blk_exit_rl(blkg->q, &blkg->rl);

	blkg_rwstat_exit(&blkg->stat_ios);
	blkg_rwstat_exit(&blkg->stat_bytes);
	kfree(blkg);
}

/**
 * blkg_alloc - allocate a blkg
 * @blkcg: block cgroup the new blkg is associated with
 * @q: request_queue the new blkg is associated with
 * @gfp_mask: allocation mask to use
 *
 * Allocate a new blkg assocating @blkcg and @q.
 */
static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
				   gfp_t gfp_mask)
{
	struct blkcg_gq *blkg;
	int i;

	/* alloc and init base part */
	blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node);
	if (!blkg)
		return NULL;

	if (blkg_rwstat_init(&blkg->stat_bytes, gfp_mask) ||
	    blkg_rwstat_init(&blkg->stat_ios, gfp_mask))
		goto err_free;

	blkg->q = q;
	INIT_LIST_HEAD(&blkg->q_node);
	blkg->blkcg = blkcg;
	atomic_set(&blkg->refcnt, 1);

	/* root blkg uses @q->root_rl, init rl only for !root blkgs */
	if (blkcg != &blkcg_root) {
		if (blk_init_rl(&blkg->rl, q, gfp_mask))
			goto err_free;
		blkg->rl.blkg = blkg;
	}

	for (i = 0; i < BLKCG_MAX_POLS; i++) {
		struct blkcg_policy *pol = blkcg_policy[i];
		struct blkg_policy_data *pd;

		if (!blkcg_policy_enabled(q, pol))
			continue;

		/* alloc per-policy data and attach it to blkg */
		pd = pol->pd_alloc_fn(gfp_mask, q->node);
		if (!pd)
			goto err_free;

		blkg->pd[i] = pd;
		pd->blkg = blkg;
		pd->plid = i;
	}

	return blkg;

err_free:
	blkg_free(blkg);
	return NULL;
}

struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
				      struct request_queue *q, bool update_hint)
{
	struct blkcg_gq *blkg;

	/*
	 * Hint didn't match.  Look up from the radix tree.  Note that the
	 * hint can only be updated under queue_lock as otherwise @blkg
	 * could have already been removed from blkg_tree.  The caller is
	 * responsible for grabbing queue_lock if @update_hint.
	 */
	blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id);
	if (blkg && blkg->q == q) {
		if (update_hint) {
			lockdep_assert_held(q->queue_lock);
			rcu_assign_pointer(blkcg->blkg_hint, blkg);
		}
		return blkg;
	}

	return NULL;
}
EXPORT_SYMBOL_GPL(blkg_lookup_slowpath);

/*
 * If @new_blkg is %NULL, this function tries to allocate a new one as
 * necessary using %GFP_NOWAIT.  @new_blkg is always consumed on return.
 */
static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
				    struct request_queue *q,
				    struct blkcg_gq *new_blkg)
{
	struct blkcg_gq *blkg;
	struct bdi_writeback_congested *wb_congested;
	int i, ret;

	WARN_ON_ONCE(!rcu_read_lock_held());
	lockdep_assert_held(q->queue_lock);

	/* blkg holds a reference to blkcg */
	if (!css_tryget_online(&blkcg->css)) {
		ret = -ENODEV;
		goto err_free_blkg;
	}

	wb_congested = wb_congested_get_create(q->backing_dev_info,
					       blkcg->css.id,
					       GFP_NOWAIT | __GFP_NOWARN);
	if (!wb_congested) {
		ret = -ENOMEM;
		goto err_put_css;
	}

	/* allocate */
	if (!new_blkg) {
		new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT | __GFP_NOWARN);
		if (unlikely(!new_blkg)) {
			ret = -ENOMEM;
			goto err_put_congested;
		}
	}
	blkg = new_blkg;
	blkg->wb_congested = wb_congested;

	/* link parent */
	if (blkcg_parent(blkcg)) {
		blkg->parent = __blkg_lookup(blkcg_parent(blkcg), q, false);
		if (WARN_ON_ONCE(!blkg->parent)) {
			ret = -ENODEV;
			goto err_put_congested;
		}
		blkg_get(blkg->parent);
	}

	/* invoke per-policy init */
	for (i = 0; i < BLKCG_MAX_POLS; i++) {
		struct blkcg_policy *pol = blkcg_policy[i];

		if (blkg->pd[i] && pol->pd_init_fn)
			pol->pd_init_fn(blkg->pd[i]);
	}

	/* insert */
	spin_lock(&blkcg->lock);
	ret = radix_tree_insert(&blkcg->blkg_tree, q->id, blkg);
	if (likely(!ret)) {
		hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
		list_add(&blkg->q_node, &q->blkg_list);

		for (i = 0; i < BLKCG_MAX_POLS; i++) {
			struct blkcg_policy *pol = blkcg_policy[i];

			if (blkg->pd[i] && pol->pd_online_fn)
				pol->pd_online_fn(blkg->pd[i]);
		}
	}
	blkg->online = true;
	spin_unlock(&blkcg->lock);

	if (!ret)
		return blkg;

	/* @blkg failed fully initialized, use the usual release path */
	blkg_put(blkg);
	return ERR_PTR(ret);

err_put_congested:
	wb_congested_put(wb_congested);
err_put_css:
	css_put(&blkcg->css);
err_free_blkg:
	blkg_free(new_blkg);
	return ERR_PTR(ret);
}

/**
 * blkg_lookup_create - lookup blkg, try to create one if not there
 * @blkcg: blkcg of interest
 * @q: request_queue of interest
 *
 * Lookup blkg for the @blkcg - @q pair.  If it doesn't exist, try to
 * create one.  blkg creation is performed recursively from blkcg_root such
 * that all non-root blkg's have access to the parent blkg.  This function
 * should be called under RCU read lock and @q->queue_lock.
 *
 * Returns pointer to the looked up or created blkg on success, ERR_PTR()
 * value on error.  If @q is dead, returns ERR_PTR(-EINVAL).  If @q is not
 * dead and bypassing, returns ERR_PTR(-EBUSY).
 */
struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
				    struct request_queue *q)
{
	struct blkcg_gq *blkg;

	WARN_ON_ONCE(!rcu_read_lock_held());
	lockdep_assert_held(q->queue_lock);

	/*
	 * This could be the first entry point of blkcg implementation and
	 * we shouldn't allow anything to go through for a bypassing queue.
	 */
	if (unlikely(blk_queue_bypass(q)))
		return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY);

	blkg = __blkg_lookup(blkcg, q, true);
	if (blkg)
		return blkg;

	/*
	 * Create blkgs walking down from blkcg_root to @blkcg, so that all
	 * non-root blkgs have access to their parents.
	 */
	while (true) {
		struct blkcg *pos = blkcg;
		struct blkcg *parent = blkcg_parent(blkcg);

		while (parent && !__blkg_lookup(parent, q, false)) {
			pos = parent;
			parent = blkcg_parent(parent);
		}

		blkg = blkg_create(pos, q, NULL);
		if (pos == blkcg || IS_ERR(blkg))
			return blkg;
	}
}

static void blkg_pd_offline(struct blkcg_gq *blkg)
{
	int i;

	lockdep_assert_held(blkg->q->queue_lock);
	lockdep_assert_held(&blkg->blkcg->lock);

	for (i = 0; i < BLKCG_MAX_POLS; i++) {
		struct blkcg_policy *pol = blkcg_policy[i];

		if (blkg->pd[i] && !blkg->pd[i]->offline &&
		    pol->pd_offline_fn) {
			pol->pd_offline_fn(blkg->pd[i]);
			blkg->pd[i]->offline = true;
		}
	}
}

static void blkg_destroy(struct blkcg_gq *blkg)
{
	struct blkcg *blkcg = blkg->blkcg;
	struct blkcg_gq *parent = blkg->parent;

	lockdep_assert_held(blkg->q->queue_lock);
	lockdep_assert_held(&blkcg->lock);

	/* Something wrong if we are trying to remove same group twice */
	WARN_ON_ONCE(list_empty(&blkg->q_node));
	WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node));

	if (parent) {
		blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes);
		blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios);
	}

	blkg->online = false;

	radix_tree_delete(&blkcg->blkg_tree, blkg->q->id);
	list_del_init(&blkg->q_node);
	hlist_del_init_rcu(&blkg->blkcg_node);

	/*
	 * Both setting lookup hint to and clearing it from @blkg are done
	 * under queue_lock.  If it's not pointing to @blkg now, it never
	 * will.  Hint assignment itself can race safely.
	 */
	if (rcu_access_pointer(blkcg->blkg_hint) == blkg)
		rcu_assign_pointer(blkcg->blkg_hint, NULL);

	/*
	 * Put the reference taken at the time of creation so that when all
	 * queues are gone, group can be destroyed.
	 */
	blkg_put(blkg);
}

/**
 * blkg_destroy_all - destroy all blkgs associated with a request_queue
 * @q: request_queue of interest
 *
 * Destroy all blkgs associated with @q.
 */
static void blkg_destroy_all(struct request_queue *q)
{
	struct blkcg_gq *blkg, *n;

	lockdep_assert_held(q->queue_lock);

	list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) {
		struct blkcg *blkcg = blkg->blkcg;

		spin_lock(&blkcg->lock);
		blkg_pd_offline(blkg);
		blkg_destroy(blkg);
		spin_unlock(&blkcg->lock);
	}

	q->root_blkg = NULL;
	q->root_rl.blkg = NULL;
}

/*
 * A group is RCU protected, but having an rcu lock does not mean that one
 * can access all the fields of blkg and assume these are valid.  For
 * example, don't try to follow throtl_data and request queue links.
 *
 * Having a reference to blkg under an rcu allows accesses to only values
 * local to groups like group stats and group rate limits.
 */
void __blkg_release_rcu(struct rcu_head *rcu_head)
{
	struct blkcg_gq *blkg = container_of(rcu_head, struct blkcg_gq, rcu_head);

	/* release the blkcg and parent blkg refs this blkg has been holding */
	css_put(&blkg->blkcg->css);
	if (blkg->parent)
		blkg_put(blkg->parent);

	wb_congested_put(blkg->wb_congested);

	blkg_free(blkg);
}
EXPORT_SYMBOL_GPL(__blkg_release_rcu);

/*
 * The next function used by blk_queue_for_each_rl().  It's a bit tricky
 * because the root blkg uses @q->root_rl instead of its own rl.
 */
struct request_list *__blk_queue_next_rl(struct request_list *rl,
					 struct request_queue *q)
{
	struct list_head *ent;
	struct blkcg_gq *blkg;

	/*
	 * Determine the current blkg list_head.  The first entry is
	 * root_rl which is off @q->blkg_list and mapped to the head.
	 */
	if (rl == &q->root_rl) {
		ent = &q->blkg_list;
		/* There are no more block groups, hence no request lists */
		if (list_empty(ent))
			return NULL;
	} else {
		blkg = container_of(rl, struct blkcg_gq, rl);
		ent = &blkg->q_node;
	}

	/* walk to the next list_head, skip root blkcg */
	ent = ent->next;
	if (ent == &q->root_blkg->q_node)
		ent = ent->next;
	if (ent == &q->blkg_list)
		return NULL;

	blkg = container_of(ent, struct blkcg_gq, q_node);
	return &blkg->rl;
}

static int blkcg_reset_stats(struct cgroup_subsys_state *css,
			     struct cftype *cftype, u64 val)
{
	struct blkcg *blkcg = css_to_blkcg(css);
	struct blkcg_gq *blkg;
	int i;

	mutex_lock(&blkcg_pol_mutex);
	spin_lock_irq(&blkcg->lock);

	/*
	 * Note that stat reset is racy - it doesn't synchronize against
	 * stat updates.  This is a debug feature which shouldn't exist
	 * anyway.  If you get hit by a race, retry.
	 */
	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
		blkg_rwstat_reset(&blkg->stat_bytes);
		blkg_rwstat_reset(&blkg->stat_ios);

		for (i = 0; i < BLKCG_MAX_POLS; i++) {
			struct blkcg_policy *pol = blkcg_policy[i];

			if (blkg->pd[i] && pol->pd_reset_stats_fn)
				pol->pd_reset_stats_fn(blkg->pd[i]);
		}
	}

	spin_unlock_irq(&blkcg->lock);
	mutex_unlock(&blkcg_pol_mutex);
	return 0;
}

const char *blkg_dev_name(struct blkcg_gq *blkg)
{
	/* some drivers (floppy) instantiate a queue w/o disk registered */
	if (blkg->q->backing_dev_info->dev)
		return dev_name(blkg->q->backing_dev_info->dev);
	return NULL;
}
EXPORT_SYMBOL_GPL(blkg_dev_name);

/**
 * blkcg_print_blkgs - helper for printing per-blkg data
 * @sf: seq_file to print to
 * @blkcg: blkcg of interest
 * @prfill: fill function to print out a blkg
 * @pol: policy in question
 * @data: data to be passed to @prfill
 * @show_total: to print out sum of prfill return values or not
 *
 * This function invokes @prfill on each blkg of @blkcg if pd for the
 * policy specified by @pol exists.  @prfill is invoked with @sf, the
 * policy data and @data and the matching queue lock held.  If @show_total
 * is %true, the sum of the return values from @prfill is printed with
 * "Total" label at the end.
 *
 * This is to be used to construct print functions for
 * cftype->read_seq_string method.
 */
void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
		       u64 (*prfill)(struct seq_file *,
				     struct blkg_policy_data *, int),
		       const struct blkcg_policy *pol, int data,
		       bool show_total)
{
	struct blkcg_gq *blkg;
	u64 total = 0;

	rcu_read_lock();
	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
		spin_lock_irq(blkg->q->queue_lock);
		if (blkcg_policy_enabled(blkg->q, pol))
			total += prfill(sf, blkg->pd[pol->plid], data);
		spin_unlock_irq(blkg->q->queue_lock);
	}
	rcu_read_unlock();

	if (show_total)
		seq_printf(sf, "Total %llu\n", (unsigned long long)total);
}
EXPORT_SYMBOL_GPL(blkcg_print_blkgs);

/**
 * __blkg_prfill_u64 - prfill helper for a single u64 value
 * @sf: seq_file to print to
 * @pd: policy private data of interest
 * @v: value to print
 *
 * Print @v to @sf for the device assocaited with @pd.
 */
u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v)
{
	const char *dname = blkg_dev_name(pd->blkg);

	if (!dname)
		return 0;

	seq_printf(sf, "%s %llu\n", dname, (unsigned long long)v);
	return v;
}
EXPORT_SYMBOL_GPL(__blkg_prfill_u64);

/**
 * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat
 * @sf: seq_file to print to
 * @pd: policy private data of interest
 * @rwstat: rwstat to print
 *
 * Print @rwstat to @sf for the device assocaited with @pd.
 */
u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
			 const struct blkg_rwstat *rwstat)
{
	static const char *rwstr[] = {
		[BLKG_RWSTAT_READ]	= "Read",
		[BLKG_RWSTAT_WRITE]	= "Write",
		[BLKG_RWSTAT_SYNC]	= "Sync",
		[BLKG_RWSTAT_ASYNC]	= "Async",
	};
	const char *dname = blkg_dev_name(pd->blkg);
	u64 v;
	int i;

	if (!dname)
		return 0;

	for (i = 0; i < BLKG_RWSTAT_NR; i++)
		seq_printf(sf, "%s %s %llu\n", dname, rwstr[i],
			   (unsigned long long)atomic64_read(&rwstat->aux_cnt[i]));

	v = atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_READ]) +
		atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_WRITE]);
	seq_printf(sf, "%s Total %llu\n", dname, (unsigned long long)v);
	return v;
}
EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat);

/**
 * blkg_prfill_stat - prfill callback for blkg_stat
 * @sf: seq_file to print to
 * @pd: policy private data of interest
 * @off: offset to the blkg_stat in @pd
 *
 * prfill callback for printing a blkg_stat.
 */
u64 blkg_prfill_stat(struct seq_file *sf, struct blkg_policy_data *pd, int off)
{
	return __blkg_prfill_u64(sf, pd, blkg_stat_read((void *)pd + off));
}
EXPORT_SYMBOL_GPL(blkg_prfill_stat);

/**
 * blkg_prfill_rwstat - prfill callback for blkg_rwstat
 * @sf: seq_file to print to
 * @pd: policy private data of interest
 * @off: offset to the blkg_rwstat in @pd
 *
 * prfill callback for printing a blkg_rwstat.
 */
u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
		       int off)
{
	struct blkg_rwstat rwstat = blkg_rwstat_read((void *)pd + off);

	return __blkg_prfill_rwstat(sf, pd, &rwstat);
}
EXPORT_SYMBOL_GPL(blkg_prfill_rwstat);

static u64 blkg_prfill_rwstat_field(struct seq_file *sf,
				    struct blkg_policy_data *pd, int off)
{
	struct blkg_rwstat rwstat = blkg_rwstat_read((void *)pd->blkg + off);

	return __blkg_prfill_rwstat(sf, pd, &rwstat);
}

/**
 * blkg_print_stat_bytes - seq_show callback for blkg->stat_bytes
 * @sf: seq_file to print to
 * @v: unused
 *
 * To be used as cftype->seq_show to print blkg->stat_bytes.
 * cftype->private must be set to the blkcg_policy.
 */
int blkg_print_stat_bytes(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private,
			  offsetof(struct blkcg_gq, stat_bytes), true);
	return 0;
}
EXPORT_SYMBOL_GPL(blkg_print_stat_bytes);

/**
 * blkg_print_stat_bytes - seq_show callback for blkg->stat_ios
 * @sf: seq_file to print to
 * @v: unused
 *
 * To be used as cftype->seq_show to print blkg->stat_ios.  cftype->private
 * must be set to the blkcg_policy.
 */
int blkg_print_stat_ios(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private,
			  offsetof(struct blkcg_gq, stat_ios), true);
	return 0;
}
EXPORT_SYMBOL_GPL(blkg_print_stat_ios);

static u64 blkg_prfill_rwstat_field_recursive(struct seq_file *sf,
					      struct blkg_policy_data *pd,
					      int off)
{
	struct blkg_rwstat rwstat = blkg_rwstat_recursive_sum(pd->blkg,
							      NULL, off);
	return __blkg_prfill_rwstat(sf, pd, &rwstat);
}

/**
 * blkg_print_stat_bytes_recursive - recursive version of blkg_print_stat_bytes
 * @sf: seq_file to print to
 * @v: unused
 */
int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  blkg_prfill_rwstat_field_recursive,
			  (void *)seq_cft(sf)->private,
			  offsetof(struct blkcg_gq, stat_bytes), true);
	return 0;
}
EXPORT_SYMBOL_GPL(blkg_print_stat_bytes_recursive);

/**
 * blkg_print_stat_ios_recursive - recursive version of blkg_print_stat_ios
 * @sf: seq_file to print to
 * @v: unused
 */
int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  blkg_prfill_rwstat_field_recursive,
			  (void *)seq_cft(sf)->private,
			  offsetof(struct blkcg_gq, stat_ios), true);
	return 0;
}
EXPORT_SYMBOL_GPL(blkg_print_stat_ios_recursive);

/**
 * blkg_stat_recursive_sum - collect hierarchical blkg_stat
 * @blkg: blkg of interest
 * @pol: blkcg_policy which contains the blkg_stat
 * @off: offset to the blkg_stat in blkg_policy_data or @blkg
 *
 * Collect the blkg_stat specified by @blkg, @pol and @off and all its
 * online descendants and their aux counts.  The caller must be holding the
 * queue lock for online tests.
 *
 * If @pol is NULL, blkg_stat is at @off bytes into @blkg; otherwise, it is
 * at @off bytes into @blkg's blkg_policy_data of the policy.
 */
u64 blkg_stat_recursive_sum(struct blkcg_gq *blkg,
			    struct blkcg_policy *pol, int off)
{
	struct blkcg_gq *pos_blkg;
	struct cgroup_subsys_state *pos_css;
	u64 sum = 0;

	lockdep_assert_held(blkg->q->queue_lock);

	rcu_read_lock();
	blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
		struct blkg_stat *stat;

		if (!pos_blkg->online)
			continue;

		if (pol)
			stat = (void *)blkg_to_pd(pos_blkg, pol) + off;
		else
			stat = (void *)blkg + off;

		sum += blkg_stat_read(stat) + atomic64_read(&stat->aux_cnt);
	}
	rcu_read_unlock();

	return sum;
}
EXPORT_SYMBOL_GPL(blkg_stat_recursive_sum);

/**
 * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat
 * @blkg: blkg of interest
 * @pol: blkcg_policy which contains the blkg_rwstat
 * @off: offset to the blkg_rwstat in blkg_policy_data or @blkg
 *
 * Collect the blkg_rwstat specified by @blkg, @pol and @off and all its
 * online descendants and their aux counts.  The caller must be holding the
 * queue lock for online tests.
 *
 * If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it
 * is at @off bytes into @blkg's blkg_policy_data of the policy.
 */
struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkcg_gq *blkg,
					     struct blkcg_policy *pol, int off)
{
	struct blkcg_gq *pos_blkg;
	struct cgroup_subsys_state *pos_css;
	struct blkg_rwstat sum = { };
	int i;

	lockdep_assert_held(blkg->q->queue_lock);

	rcu_read_lock();
	blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
		struct blkg_rwstat *rwstat;

		if (!pos_blkg->online)
			continue;

		if (pol)
			rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off;
		else
			rwstat = (void *)pos_blkg + off;

		for (i = 0; i < BLKG_RWSTAT_NR; i++)
			atomic64_add(atomic64_read(&rwstat->aux_cnt[i]) +
				percpu_counter_sum_positive(&rwstat->cpu_cnt[i]),
				&sum.aux_cnt[i]);
	}
	rcu_read_unlock();

	return sum;
}
EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum);

/* Performs queue bypass and policy enabled checks then looks up blkg. */
static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg,
					  const struct blkcg_policy *pol,
					  struct request_queue *q)
{
	WARN_ON_ONCE(!rcu_read_lock_held());
	lockdep_assert_held(q->queue_lock);

	if (!blkcg_policy_enabled(q, pol))
		return ERR_PTR(-EOPNOTSUPP);

	/*
	 * This could be the first entry point of blkcg implementation and
	 * we shouldn't allow anything to go through for a bypassing queue.
	 */
	if (unlikely(blk_queue_bypass(q)))
		return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY);

	return __blkg_lookup(blkcg, q, true /* update_hint */);
}

/**
 * blkg_conf_prep - parse and prepare for per-blkg config update
 * @blkcg: target block cgroup
 * @pol: target policy
 * @input: input string
 * @ctx: blkg_conf_ctx to be filled
 *
 * Parse per-blkg config update from @input and initialize @ctx with the
 * result.  @ctx->blkg points to the blkg to be updated and @ctx->body the
 * part of @input following MAJ:MIN.  This function returns with RCU read
 * lock and queue lock held and must be paired with blkg_conf_finish().
 */
int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
		   char *input, struct blkg_conf_ctx *ctx)
	__acquires(rcu) __acquires(disk->queue->queue_lock)
{
	struct gendisk *disk;
	struct request_queue *q;
	struct blkcg_gq *blkg;
	unsigned int major, minor;
	int key_len, part, ret;
	char *body;

	if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2)
		return -EINVAL;

	body = input + key_len;
	if (!isspace(*body))
		return -EINVAL;
	body = skip_spaces(body);

	disk = get_gendisk(MKDEV(major, minor), &part);
	if (!disk)
		return -ENODEV;
	if (part) {
		ret = -ENODEV;
		goto fail;
	}

	q = disk->queue;

	rcu_read_lock();
	spin_lock_irq(q->queue_lock);

	blkg = blkg_lookup_check(blkcg, pol, q);
	if (IS_ERR(blkg)) {
		ret = PTR_ERR(blkg);
		goto fail_unlock;
	}

	if (blkg)
		goto success;

	/*
	 * Create blkgs walking down from blkcg_root to @blkcg, so that all
	 * non-root blkgs have access to their parents.
	 */
	while (true) {
		struct blkcg *pos = blkcg;
		struct blkcg *parent;
		struct blkcg_gq *new_blkg;

		parent = blkcg_parent(blkcg);
		while (parent && !__blkg_lookup(parent, q, false)) {
			pos = parent;
			parent = blkcg_parent(parent);
		}

		/* Drop locks to do new blkg allocation with GFP_KERNEL. */
		spin_unlock_irq(q->queue_lock);
		rcu_read_unlock();

		new_blkg = blkg_alloc(pos, q, GFP_KERNEL);
		if (unlikely(!new_blkg)) {
			ret = -ENOMEM;
			goto fail;
		}

		rcu_read_lock();
		spin_lock_irq(q->queue_lock);

		blkg = blkg_lookup_check(pos, pol, q);
		if (IS_ERR(blkg)) {
			ret = PTR_ERR(blkg);
			goto fail_unlock;
		}

		if (blkg) {
			blkg_free(new_blkg);
		} else {
			blkg = blkg_create(pos, q, new_blkg);
			if (unlikely(IS_ERR(blkg))) {
				ret = PTR_ERR(blkg);
				goto fail_unlock;
			}
		}

		if (pos == blkcg)
			goto success;
	}
success:
	ctx->disk = disk;
	ctx->blkg = blkg;
	ctx->body = body;
	return 0;

fail_unlock:
	spin_unlock_irq(q->queue_lock);
	rcu_read_unlock();
fail:
	put_disk_and_module(disk);
	/*
	 * If queue was bypassing, we should retry.  Do so after a
	 * short msleep().  It isn't strictly necessary but queue
	 * can be bypassing for some time and it's always nice to
	 * avoid busy looping.
	 */
	if (ret == -EBUSY) {
		msleep(10);
		ret = restart_syscall();
	}
	return ret;
}
EXPORT_SYMBOL_GPL(blkg_conf_prep);

/**
 * blkg_conf_finish - finish up per-blkg config update
 * @ctx: blkg_conf_ctx intiailized by blkg_conf_prep()
 *
 * Finish up after per-blkg config update.  This function must be paired
 * with blkg_conf_prep().
 */
void blkg_conf_finish(struct blkg_conf_ctx *ctx)
	__releases(ctx->disk->queue->queue_lock) __releases(rcu)
{
	spin_unlock_irq(ctx->disk->queue->queue_lock);
	rcu_read_unlock();
	put_disk_and_module(ctx->disk);
}
EXPORT_SYMBOL_GPL(blkg_conf_finish);

static int blkcg_print_stat(struct seq_file *sf, void *v)
{
	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
	struct blkcg_gq *blkg;

	rcu_read_lock();

	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
		const char *dname;
		struct blkg_rwstat rwstat;
		u64 rbytes, wbytes, rios, wios;

		dname = blkg_dev_name(blkg);
		if (!dname)
			continue;

		spin_lock_irq(blkg->q->queue_lock);

		rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
					offsetof(struct blkcg_gq, stat_bytes));
		rbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]);
		wbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]);

		rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
					offsetof(struct blkcg_gq, stat_ios));
		rios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]);
		wios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]);

		spin_unlock_irq(blkg->q->queue_lock);

		if (rbytes || wbytes || rios || wios)
			seq_printf(sf, "%s rbytes=%llu wbytes=%llu rios=%llu wios=%llu\n",
				   dname, rbytes, wbytes, rios, wios);
	}

	rcu_read_unlock();
	return 0;
}

static struct cftype blkcg_files[] = {
	{
		.name = "stat",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = blkcg_print_stat,
	},
	{ }	/* terminate */
};

static struct cftype blkcg_legacy_files[] = {
	{
		.name = "reset_stats",
		.write_u64 = blkcg_reset_stats,
	},
	{ }	/* terminate */
};

/**
 * blkcg_css_offline - cgroup css_offline callback
 * @css: css of interest
 *
 * This function is called when @css is about to go away and responsible
 * for offlining all blkgs pd and killing all wbs associated with @css.
 * blkgs pd offline should be done while holding both q and blkcg locks.
 * As blkcg lock is nested inside q lock, this function performs reverse
 * double lock dancing.
 *
 * This is the blkcg counterpart of ioc_release_fn().
 */
static void blkcg_css_offline(struct cgroup_subsys_state *css)
{
	struct blkcg *blkcg = css_to_blkcg(css);
	struct blkcg_gq *blkg;

	spin_lock_irq(&blkcg->lock);

	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
		struct request_queue *q = blkg->q;

		if (spin_trylock(q->queue_lock)) {
			blkg_pd_offline(blkg);
			spin_unlock(q->queue_lock);
		} else {
			spin_unlock_irq(&blkcg->lock);
			cpu_relax();
			spin_lock_irq(&blkcg->lock);
		}
	}

	spin_unlock_irq(&blkcg->lock);

	wb_blkcg_offline(blkcg);
}

/**
 * blkcg_destroy_all_blkgs - destroy all blkgs associated with a blkcg
 * @blkcg: blkcg of interest
 *
 * This function is called when blkcg css is about to free and responsible for
 * destroying all blkgs associated with @blkcg.
 * blkgs should be removed while holding both q and blkcg locks. As blkcg lock
 * is nested inside q lock, this function performs reverse double lock dancing.
 */
static void blkcg_destroy_all_blkgs(struct blkcg *blkcg)
{
	spin_lock_irq(&blkcg->lock);
	while (!hlist_empty(&blkcg->blkg_list)) {
		struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first,
						    struct blkcg_gq,
						    blkcg_node);
		struct request_queue *q = blkg->q;

		if (spin_trylock(q->queue_lock)) {
			blkg_destroy(blkg);
			spin_unlock(q->queue_lock);
		} else {
			spin_unlock_irq(&blkcg->lock);
			cpu_relax();
			spin_lock_irq(&blkcg->lock);
		}
	}
	spin_unlock_irq(&blkcg->lock);
}

static void blkcg_css_free(struct cgroup_subsys_state *css)
{
	struct blkcg *blkcg = css_to_blkcg(css);
	int i;

	blkcg_destroy_all_blkgs(blkcg);

	mutex_lock(&blkcg_pol_mutex);

	list_del(&blkcg->all_blkcgs_node);

	for (i = 0; i < BLKCG_MAX_POLS; i++)
		if (blkcg->cpd[i])
			blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]);

	mutex_unlock(&blkcg_pol_mutex);

	kfree(blkcg);
}

static struct cgroup_subsys_state *
blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
{
	struct blkcg *blkcg;
	struct cgroup_subsys_state *ret;
	int i;

	mutex_lock(&blkcg_pol_mutex);

	if (!parent_css) {
		blkcg = &blkcg_root;
	} else {
		blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
		if (!blkcg) {
			ret = ERR_PTR(-ENOMEM);
			goto unlock;
		}
	}

	for (i = 0; i < BLKCG_MAX_POLS ; i++) {
		struct blkcg_policy *pol = blkcg_policy[i];
		struct blkcg_policy_data *cpd;

		/*
		 * If the policy hasn't been attached yet, wait for it
		 * to be attached before doing anything else. Otherwise,
		 * check if the policy requires any specific per-cgroup
		 * data: if it does, allocate and initialize it.
		 */
		if (!pol || !pol->cpd_alloc_fn)
			continue;

		cpd = pol->cpd_alloc_fn(GFP_KERNEL);
		if (!cpd) {
			ret = ERR_PTR(-ENOMEM);
			goto free_pd_blkcg;
		}
		blkcg->cpd[i] = cpd;
		cpd->blkcg = blkcg;
		cpd->plid = i;
		if (pol->cpd_init_fn)
			pol->cpd_init_fn(cpd);
	}

	spin_lock_init(&blkcg->lock);
	INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT | __GFP_NOWARN);
	INIT_HLIST_HEAD(&blkcg->blkg_list);
#ifdef CONFIG_CGROUP_WRITEBACK
	INIT_LIST_HEAD(&blkcg->cgwb_list);
#endif
	list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs);

	mutex_unlock(&blkcg_pol_mutex);
	return &blkcg->css;

free_pd_blkcg:
	for (i--; i >= 0; i--)
		if (blkcg->cpd[i])
			blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]);

	if (blkcg != &blkcg_root)
		kfree(blkcg);
unlock:
	mutex_unlock(&blkcg_pol_mutex);
	return ret;
}

/**
 * blkcg_init_queue - initialize blkcg part of request queue
 * @q: request_queue to initialize
 *
 * Called from blk_alloc_queue_node(). Responsible for initializing blkcg
 * part of new request_queue @q.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int blkcg_init_queue(struct request_queue *q)
{
	struct blkcg_gq *new_blkg, *blkg;
	bool preloaded;
	int ret;

	new_blkg = blkg_alloc(&blkcg_root, q, GFP_KERNEL);
	if (!new_blkg)
		return -ENOMEM;

	preloaded = !radix_tree_preload(GFP_KERNEL);

	/* Make sure the root blkg exists. */
	rcu_read_lock();
	spin_lock_irq(q->queue_lock);
	blkg = blkg_create(&blkcg_root, q, new_blkg);
	if (IS_ERR(blkg))
		goto err_unlock;
	q->root_blkg = blkg;
	q->root_rl.blkg = blkg;
	spin_unlock_irq(q->queue_lock);
	rcu_read_unlock();

	if (preloaded)
		radix_tree_preload_end();

	ret = blk_throtl_init(q);
	if (ret) {
		spin_lock_irq(q->queue_lock);
		blkg_destroy_all(q);
		spin_unlock_irq(q->queue_lock);
	}
	return ret;

err_unlock:
	spin_unlock_irq(q->queue_lock);
	rcu_read_unlock();
	if (preloaded)
		radix_tree_preload_end();
	return PTR_ERR(blkg);
}

/**
 * blkcg_drain_queue - drain blkcg part of request_queue
 * @q: request_queue to drain
 *
 * Called from blk_drain_queue().  Responsible for draining blkcg part.
 */
void blkcg_drain_queue(struct request_queue *q)
{
	lockdep_assert_held(q->queue_lock);

	/*
	 * @q could be exiting and already have destroyed all blkgs as
	 * indicated by NULL root_blkg.  If so, don't confuse policies.
	 */
	if (!q->root_blkg)
		return;

	blk_throtl_drain(q);
}

/**
 * blkcg_exit_queue - exit and release blkcg part of request_queue
 * @q: request_queue being released
 *
 * Called from blk_release_queue().  Responsible for exiting blkcg part.
 */
void blkcg_exit_queue(struct request_queue *q)
{
	spin_lock_irq(q->queue_lock);
	blkg_destroy_all(q);
	spin_unlock_irq(q->queue_lock);

	blk_throtl_exit(q);
}

/*
 * We cannot support shared io contexts, as we have no mean to support
 * two tasks with the same ioc in two different groups without major rework
 * of the main cic data structures.  For now we allow a task to change
 * its cgroup only if it's the only owner of its ioc.
 */
static int blkcg_can_attach(struct cgroup_taskset *tset)
{
	struct task_struct *task;
	struct cgroup_subsys_state *dst_css;
	struct io_context *ioc;
	int ret = 0;

	/* task_lock() is needed to avoid races with exit_io_context() */
	cgroup_taskset_for_each(task, dst_css, tset) {
		task_lock(task);
		ioc = task->io_context;
		if (ioc && atomic_read(&ioc->nr_tasks) > 1)
			ret = -EINVAL;
		task_unlock(task);
		if (ret)
			break;
	}
	return ret;
}

static void blkcg_bind(struct cgroup_subsys_state *root_css)
{
	int i;

	mutex_lock(&blkcg_pol_mutex);

	for (i = 0; i < BLKCG_MAX_POLS; i++) {
		struct blkcg_policy *pol = blkcg_policy[i];
		struct blkcg *blkcg;

		if (!pol || !pol->cpd_bind_fn)
			continue;

		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node)
			if (blkcg->cpd[pol->plid])
				pol->cpd_bind_fn(blkcg->cpd[pol->plid]);
	}
	mutex_unlock(&blkcg_pol_mutex);
}

struct cgroup_subsys io_cgrp_subsys = {
	.css_alloc = blkcg_css_alloc,
	.css_offline = blkcg_css_offline,
	.css_free = blkcg_css_free,
	.can_attach = blkcg_can_attach,
	.bind = blkcg_bind,
	.dfl_cftypes = blkcg_files,
	.legacy_cftypes = blkcg_legacy_files,
	.legacy_name = "blkio",
#ifdef CONFIG_MEMCG
	/*
	 * This ensures that, if available, memcg is automatically enabled
	 * together on the default hierarchy so that the owner cgroup can
	 * be retrieved from writeback pages.
	 */
	.depends_on = 1 << memory_cgrp_id,
#endif
};
EXPORT_SYMBOL_GPL(io_cgrp_subsys);

/**
 * blkcg_activate_policy - activate a blkcg policy on a request_queue
 * @q: request_queue of interest
 * @pol: blkcg policy to activate
 *
 * Activate @pol on @q.  Requires %GFP_KERNEL context.  @q goes through
 * bypass mode to populate its blkgs with policy_data for @pol.
 *
 * Activation happens with @q bypassed, so nobody would be accessing blkgs
 * from IO path.  Update of each blkg is protected by both queue and blkcg
 * locks so that holding either lock and testing blkcg_policy_enabled() is
 * always enough for dereferencing policy data.
 *
 * The caller is responsible for synchronizing [de]activations and policy
 * [un]registerations.  Returns 0 on success, -errno on failure.
 */
int blkcg_activate_policy(struct request_queue *q,
			  const struct blkcg_policy *pol)
{
	struct blkg_policy_data *pd_prealloc = NULL;
	struct blkcg_gq *blkg;
	int ret;

	if (blkcg_policy_enabled(q, pol))
		return 0;

	if (q->mq_ops)
		blk_mq_freeze_queue(q);
	else
		blk_queue_bypass_start(q);
pd_prealloc:
	if (!pd_prealloc) {
		pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q->node);
		if (!pd_prealloc) {
			ret = -ENOMEM;
			goto out_bypass_end;
		}
	}

	spin_lock_irq(q->queue_lock);

	list_for_each_entry(blkg, &q->blkg_list, q_node) {
		struct blkg_policy_data *pd;

		if (blkg->pd[pol->plid])
			continue;

		pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q->node);
		if (!pd)
			swap(pd, pd_prealloc);
		if (!pd) {
			spin_unlock_irq(q->queue_lock);
			goto pd_prealloc;
		}

		blkg->pd[pol->plid] = pd;
		pd->blkg = blkg;
		pd->plid = pol->plid;
		if (pol->pd_init_fn)
			pol->pd_init_fn(pd);
	}

	__set_bit(pol->plid, q->blkcg_pols);
	ret = 0;

	spin_unlock_irq(q->queue_lock);
out_bypass_end:
	if (q->mq_ops)
		blk_mq_unfreeze_queue(q);
	else
		blk_queue_bypass_end(q);
	if (pd_prealloc)
		pol->pd_free_fn(pd_prealloc);
	return ret;
}
EXPORT_SYMBOL_GPL(blkcg_activate_policy);

/**
 * blkcg_deactivate_policy - deactivate a blkcg policy on a request_queue
 * @q: request_queue of interest
 * @pol: blkcg policy to deactivate
 *
 * Deactivate @pol on @q.  Follows the same synchronization rules as
 * blkcg_activate_policy().
 */
void blkcg_deactivate_policy(struct request_queue *q,
			     const struct blkcg_policy *pol)
{
	struct blkcg_gq *blkg;

	if (!blkcg_policy_enabled(q, pol))
		return;

	if (q->mq_ops)
		blk_mq_freeze_queue(q);
	else
		blk_queue_bypass_start(q);

	spin_lock_irq(q->queue_lock);

	__clear_bit(pol->plid, q->blkcg_pols);

	list_for_each_entry(blkg, &q->blkg_list, q_node) {
		if (blkg->pd[pol->plid]) {
			if (!blkg->pd[pol->plid]->offline &&
			    pol->pd_offline_fn) {
				pol->pd_offline_fn(blkg->pd[pol->plid]);
				blkg->pd[pol->plid]->offline = true;
			}
			pol->pd_free_fn(blkg->pd[pol->plid]);
			blkg->pd[pol->plid] = NULL;
		}
	}

	spin_unlock_irq(q->queue_lock);

	if (q->mq_ops)
		blk_mq_unfreeze_queue(q);
	else
		blk_queue_bypass_end(q);
}
EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);

/**
 * blkcg_policy_register - register a blkcg policy
 * @pol: blkcg policy to register
 *
 * Register @pol with blkcg core.  Might sleep and @pol may be modified on
 * successful registration.  Returns 0 on success and -errno on failure.
 */
int blkcg_policy_register(struct blkcg_policy *pol)
{
	struct blkcg *blkcg;
	int i, ret;

	mutex_lock(&blkcg_pol_register_mutex);
	mutex_lock(&blkcg_pol_mutex);

	/* find an empty slot */
	ret = -ENOSPC;
	for (i = 0; i < BLKCG_MAX_POLS; i++)
		if (!blkcg_policy[i])
			break;
	if (i >= BLKCG_MAX_POLS)
		goto err_unlock;

	/* Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs */
	if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) ||
		(!pol->pd_alloc_fn ^ !pol->pd_free_fn))
		goto err_unlock;

	/* register @pol */
	pol->plid = i;
	blkcg_policy[pol->plid] = pol;

	/* allocate and install cpd's */
	if (pol->cpd_alloc_fn) {
		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
			struct blkcg_policy_data *cpd;

			cpd = pol->cpd_alloc_fn(GFP_KERNEL);
			if (!cpd)
				goto err_free_cpds;

			blkcg->cpd[pol->plid] = cpd;
			cpd->blkcg = blkcg;
			cpd->plid = pol->plid;
			pol->cpd_init_fn(cpd);
		}
	}

	mutex_unlock(&blkcg_pol_mutex);

	/* everything is in place, add intf files for the new policy */
	if (pol->dfl_cftypes)
		WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys,
					       pol->dfl_cftypes));
	if (pol->legacy_cftypes)
		WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys,
						  pol->legacy_cftypes));
	mutex_unlock(&blkcg_pol_register_mutex);
	return 0;

err_free_cpds:
	if (pol->cpd_free_fn) {
		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
			if (blkcg->cpd[pol->plid]) {
				pol->cpd_free_fn(blkcg->cpd[pol->plid]);
				blkcg->cpd[pol->plid] = NULL;
			}
		}
	}
	blkcg_policy[pol->plid] = NULL;
err_unlock:
	mutex_unlock(&blkcg_pol_mutex);
	mutex_unlock(&blkcg_pol_register_mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(blkcg_policy_register);

/**
 * blkcg_policy_unregister - unregister a blkcg policy
 * @pol: blkcg policy to unregister
 *
 * Undo blkcg_policy_register(@pol).  Might sleep.
 */
void blkcg_policy_unregister(struct blkcg_policy *pol)
{
	struct blkcg *blkcg;

	mutex_lock(&blkcg_pol_register_mutex);

	if (WARN_ON(blkcg_policy[pol->plid] != pol))
		goto out_unlock;

	/* kill the intf files first */
	if (pol->dfl_cftypes)
		cgroup_rm_cftypes(pol->dfl_cftypes);
	if (pol->legacy_cftypes)
		cgroup_rm_cftypes(pol->legacy_cftypes);

	/* remove cpds and unregister */
	mutex_lock(&blkcg_pol_mutex);

	if (pol->cpd_free_fn) {
		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
			if (blkcg->cpd[pol->plid]) {
				pol->cpd_free_fn(blkcg->cpd[pol->plid]);
				blkcg->cpd[pol->plid] = NULL;
			}
		}
	}
	blkcg_policy[pol->plid] = NULL;

	mutex_unlock(&blkcg_pol_mutex);
out_unlock:
	mutex_unlock(&blkcg_pol_register_mutex);
}