| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367 | #ifndef _BLK_CGROUP_H#define _BLK_CGROUP_H/* * 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> */#include <linux/cgroup.h>#include <linux/u64_stats_sync.h>#include <linux/seq_file.h>#include <linux/radix-tree.h>#include <linux/blkdev.h>/* Max limits for throttle policy */#define THROTL_IOPS_MAX		UINT_MAX/* CFQ specific, out here for blkcg->cfq_weight */#define CFQ_WEIGHT_MIN		10#define CFQ_WEIGHT_MAX		1000#define CFQ_WEIGHT_DEFAULT	500#ifdef CONFIG_BLK_CGROUPenum blkg_rwstat_type {	BLKG_RWSTAT_READ,	BLKG_RWSTAT_WRITE,	BLKG_RWSTAT_SYNC,	BLKG_RWSTAT_ASYNC,	BLKG_RWSTAT_NR,	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,};struct blkcg_gq;struct blkcg {	struct cgroup_subsys_state	css;	spinlock_t			lock;	struct radix_tree_root		blkg_tree;	struct blkcg_gq			*blkg_hint;	struct hlist_head		blkg_list;	/* for policies to test whether associated blkcg has changed */	uint64_t			id;	/* TODO: per-policy storage in blkcg */	unsigned int			cfq_weight;	/* belongs to cfq */};struct blkg_stat {	struct u64_stats_sync		syncp;	uint64_t			cnt;};struct blkg_rwstat {	struct u64_stats_sync		syncp;	uint64_t			cnt[BLKG_RWSTAT_NR];};/* * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a * request_queue (q).  This is used by blkcg policies which need to track * information per blkcg - q pair. * * There can be multiple active blkcg policies and each has its private * data on each blkg, the size of which is determined by * blkcg_policy->pd_size.  blkcg core allocates and frees such areas * together with blkg and invokes pd_init/exit_fn() methods. * * Such private data must embed struct blkg_policy_data (pd) at the * beginning and pd_size can't be smaller than pd. */struct blkg_policy_data {	/* the blkg this per-policy data belongs to */	struct blkcg_gq			*blkg;	/* used during policy activation */	struct list_head		alloc_node;};/* association between a blk cgroup and a request queue */struct blkcg_gq {	/* Pointer to the associated request_queue */	struct request_queue		*q;	struct list_head		q_node;	struct hlist_node		blkcg_node;	struct blkcg			*blkcg;	/* request allocation list for this blkcg-q pair */	struct request_list		rl;	/* reference count */	int				refcnt;	struct blkg_policy_data		*pd[BLKCG_MAX_POLS];	struct rcu_head			rcu_head;};typedef void (blkcg_pol_init_pd_fn)(struct blkcg_gq *blkg);typedef void (blkcg_pol_exit_pd_fn)(struct blkcg_gq *blkg);typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkcg_gq *blkg);struct blkcg_policy {	int				plid;	/* policy specific private data size */	size_t				pd_size;	/* cgroup files for the policy */	struct cftype			*cftypes;	/* operations */	blkcg_pol_init_pd_fn		*pd_init_fn;	blkcg_pol_exit_pd_fn		*pd_exit_fn;	blkcg_pol_reset_pd_stats_fn	*pd_reset_stats_fn;};extern struct blkcg blkcg_root;struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q);struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,				    struct request_queue *q);int blkcg_init_queue(struct request_queue *q);void blkcg_drain_queue(struct request_queue *q);void blkcg_exit_queue(struct request_queue *q);/* Blkio controller policy registration */int blkcg_policy_register(struct blkcg_policy *pol);void blkcg_policy_unregister(struct blkcg_policy *pol);int blkcg_activate_policy(struct request_queue *q,			  const struct blkcg_policy *pol);void blkcg_deactivate_policy(struct request_queue *q,			     const struct blkcg_policy *pol);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);u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v);u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,			 const struct blkg_rwstat *rwstat);u64 blkg_prfill_stat(struct seq_file *sf, struct blkg_policy_data *pd, int off);u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,		       int off);struct blkg_conf_ctx {	struct gendisk			*disk;	struct blkcg_gq			*blkg;	u64				v;};int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,		   const char *input, struct blkg_conf_ctx *ctx);void blkg_conf_finish(struct blkg_conf_ctx *ctx);static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup){	return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),			    struct blkcg, css);}static inline struct blkcg *task_blkcg(struct task_struct *tsk){	return container_of(task_subsys_state(tsk, blkio_subsys_id),			    struct blkcg, css);}static inline struct blkcg *bio_blkcg(struct bio *bio){	if (bio && bio->bi_css)		return container_of(bio->bi_css, struct blkcg, css);	return task_blkcg(current);}/** * blkg_to_pdata - get policy private data * @blkg: blkg of interest * @pol: policy of interest * * Return pointer to private data associated with the @blkg-@pol pair. */static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,						  struct blkcg_policy *pol){	return blkg ? blkg->pd[pol->plid] : NULL;}/** * pdata_to_blkg - get blkg associated with policy private data * @pd: policy private data of interest * * @pd is policy private data.  Determine the blkg it's associated with. */static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd){	return pd ? pd->blkg : NULL;}/** * blkg_path - format cgroup path of blkg * @blkg: blkg of interest * @buf: target buffer * @buflen: target buffer length * * Format the path of the cgroup of @blkg into @buf. */static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen){	int ret;	rcu_read_lock();	ret = cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);	rcu_read_unlock();	if (ret)		strncpy(buf, "<unavailable>", buflen);	return ret;}/** * blkg_get - get a blkg reference * @blkg: blkg to get * * The caller should be holding queue_lock and an existing reference. */static inline void blkg_get(struct blkcg_gq *blkg){	lockdep_assert_held(blkg->q->queue_lock);	WARN_ON_ONCE(!blkg->refcnt);	blkg->refcnt++;}void __blkg_release(struct blkcg_gq *blkg);/** * blkg_put - put a blkg reference * @blkg: blkg to put * * The caller should be holding queue_lock. */static inline void blkg_put(struct blkcg_gq *blkg){	lockdep_assert_held(blkg->q->queue_lock);	WARN_ON_ONCE(blkg->refcnt <= 0);	if (!--blkg->refcnt)		__blkg_release(blkg);}/** * blk_get_rl - get request_list to use * @q: request_queue of interest * @bio: bio which will be attached to the allocated request (may be %NULL) * * The caller wants to allocate a request from @q to use for @bio.  Find * the request_list to use and obtain a reference on it.  Should be called * under queue_lock.  This function is guaranteed to return non-%NULL * request_list. */static inline struct request_list *blk_get_rl(struct request_queue *q,					      struct bio *bio){	struct blkcg *blkcg;	struct blkcg_gq *blkg;	rcu_read_lock();	blkcg = bio_blkcg(bio);	/* bypass blkg lookup and use @q->root_rl directly for root */	if (blkcg == &blkcg_root)		goto root_rl;	/*	 * Try to use blkg->rl.  blkg lookup may fail under memory pressure	 * or if either the blkcg or queue is going away.  Fall back to	 * root_rl in such cases.	 */	blkg = blkg_lookup_create(blkcg, q);	if (unlikely(IS_ERR(blkg)))		goto root_rl;	blkg_get(blkg);	rcu_read_unlock();	return &blkg->rl;root_rl:	rcu_read_unlock();	return &q->root_rl;}/** * blk_put_rl - put request_list * @rl: request_list to put * * Put the reference acquired by blk_get_rl().  Should be called under * queue_lock. */static inline void blk_put_rl(struct request_list *rl){	/* root_rl may not have blkg set */	if (rl->blkg && rl->blkg->blkcg != &blkcg_root)		blkg_put(rl->blkg);}/** * blk_rq_set_rl - associate a request with a request_list * @rq: request of interest * @rl: target request_list * * Associate @rq with @rl so that accounting and freeing can know the * request_list @rq came from. */static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl){	rq->rl = rl;}/** * blk_rq_rl - return the request_list a request came from * @rq: request of interest * * Return the request_list @rq is allocated from. */static inline struct request_list *blk_rq_rl(struct request *rq){	return rq->rl;}struct request_list *__blk_queue_next_rl(struct request_list *rl,					 struct request_queue *q);/** * blk_queue_for_each_rl - iterate through all request_lists of a request_queue * * Should be used under queue_lock. */#define blk_queue_for_each_rl(rl, q)	\	for ((rl) = &(q)->root_rl; (rl); (rl) = __blk_queue_next_rl((rl), (q)))/** * blkg_stat_add - add a value to a blkg_stat * @stat: target blkg_stat * @val: value to add * * Add @val to @stat.  The caller is responsible for synchronizing calls to * this function. */static inline void blkg_stat_add(struct blkg_stat *stat, uint64_t val){	u64_stats_update_begin(&stat->syncp);	stat->cnt += val;	u64_stats_update_end(&stat->syncp);}/** * blkg_stat_read - read the current value of a blkg_stat * @stat: blkg_stat to read * * Read the current value of @stat.  This function can be called without * synchroniztion and takes care of u64 atomicity. */static inline uint64_t blkg_stat_read(struct blkg_stat *stat)
 |