/* SPDX-License-Identifier: GPL-2.0 */#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/percpu.h>#include <linux/percpu_counter.h>#include <linux/u64_stats_sync.h>#include <linux/seq_file.h>#include <linux/radix-tree.h>#include <linux/blkdev.h>#include <linux/atomic.h>#include <linux/kthread.h>#include <linux/fs.h> /* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */#define BLKG_STAT_CPU_BATCH (INT_MAX / 2) /* Max limits for throttle policy */#define THROTL_IOPS_MAX UINT_MAX #ifdef CONFIG_BLK_CGROUP enum blkg_iostat_type { BLKG_IOSTAT_READ, BLKG_IOSTAT_WRITE, BLKG_IOSTAT_DISCARD, BLKG_IOSTAT_NR,}; struct blkcg_gq; struct blkcg { struct cgroup_subsys_state css; spinlock_t lock; refcount_t online_pin; struct radix_tree_root blkg_tree; struct blkcg_gq __rcu *blkg_hint; struct hlist_head blkg_list; struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; struct list_head all_blkcgs_node;#ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list;#endif}; struct blkg_iostat { u64 bytes[BLKG_IOSTAT_NR]; u64 ios[BLKG_IOSTAT_NR];}; struct blkg_iostat_set { struct u64_stats_sync sync; struct blkg_iostat cur; struct blkg_iostat last;}; /* * 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 blkg:policy pair is * represented by a blkg_policy_data which is allocated and freed by each * policy's pd_alloc/free_fn() methods. A policy can allocate private data * area by allocating larger data structure which embeds blkg_policy_data * at the beginning. */struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid;}; /* * Policies that need to keep per-blkcg data which is independent from any * request_queue associated to it should implement cpd_alloc/free_fn() * methods. A policy can allocate private data area by allocating larger * data structure which embeds blkcg_policy_data at the beginning. * cpd_init() is invoked to let each policy handle per-blkcg data. */struct blkcg_policy_data { /* the blkcg and policy id this per-policy data belongs to */ struct blkcg *blkcg; int plid;}; /* 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; /* * Each blkg gets congested separately and the congestion state is * propagated to the matching bdi_writeback_congested. */ struct bdi_writeback_congested *wb_congested; /* all non-root blkcg_gq's are guaranteed to have access to parent */ struct blkcg_gq *parent; /* reference count */ struct percpu_ref refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; struct blkg_iostat_set __percpu *iostat_cpu; struct blkg_iostat_set iostat; struct blkg_policy_data *pd[BLKCG_MAX_POLS]; spinlock_t async_bio_lock; struct bio_list async_bios; struct work_struct async_bio_work; atomic_t use_delay; atomic64_t delay_nsec; atomic64_t delay_start; u64 last_delay; int last_use; struct rcu_head rcu_head;}; typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp);typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd);typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd);typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd);typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, struct request_queue *q, struct blkcg *blkcg);typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd);typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd);typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd);typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd);typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd);typedef size_t (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, char *buf, size_t size); struct blkcg_policy { int plid; /* cgroup files for the policy */ struct cftype *dfl_cftypes; struct cftype *legacy_cftypes; /* operations */ blkcg_pol_alloc_cpd_fn *cpd_alloc_fn; blkcg_pol_init_cpd_fn *cpd_init_fn; blkcg_pol_free_cpd_fn *cpd_free_fn; blkcg_pol_bind_cpd_fn *cpd_bind_fn; blkcg_pol_alloc_pd_fn *pd_alloc_fn; blkcg_pol_init_pd_fn *pd_init_fn; blkcg_pol_online_pd_fn *pd_online_fn; blkcg_pol_offline_pd_fn *pd_offline_fn; blkcg_pol_free_pd_fn *pd_free_fn; blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn; blkcg_pol_stat_pd_fn *pd_stat_fn;}; extern struct blkcg blkcg_root;extern struct cgroup_subsys_state * const blkcg_root_css;extern bool blkcg_debug_stats; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint);struct blkcg_gq *__blkg_lookup_create(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_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); const char *blkg_dev_name(struct blkcg_gq *blkg);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); struct blkg_conf_ctx { struct gendisk *disk; struct blkcg_gq *blkg; char *body;}; struct gendisk *blkcg_conf_get_disk(char **inputp);int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx);void blkg_conf_finish(struct blkg_conf_ctx *ctx); /** * blkcg_css - find the current css * * Find the css associated with either the kthread or the current task. * This may return a dying css, so it is up to the caller to use tryget logic * to confirm it is alive and well. */static inline struct cgroup_subsys_state *blkcg_css(void){ struct cgroup_subsys_state *css; css = kthread_blkcg(); if (css) return css; return task_css(current, io_cgrp_id);} static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css){ return css ? container_of(css, struct blkcg, css) : NULL;} /** * __bio_blkcg - internal, inconsistent version to get blkcg * * DO NOT USE. * This function is inconsistent and consequently is dangerous to use. The * first part of the function returns a blkcg where a reference is owned by the * bio. This means it does not need to be rcu protected as it cannot go away * with the bio owning a reference to it. However, the latter potentially gets * it from task_css(). This can race against task migration and the cgroup * dying. It is also semantically different as it must be called rcu protected * and is susceptible to failure when trying to get a reference to it. * Therefore, it is not ok to assume that *_get() will always succeed on the * blkcg returned here. */static inline struct blkcg *__bio_blkcg(struct bio *bio){ if (bio && bio->bi_blkg) return bio->bi_blkg->blkcg; return css_to_blkcg(blkcg_css());} /** * bio_blkcg - grab the blkcg associated with a bio * @bio: target bio * * This returns the blkcg associated with a bio, %NULL if not associated. * Callers are expected to either handle %NULL or know association has been * done prior to calling this. */static inline struct blkcg *bio_blkcg(struct bio *bio){ if (bio && bio->bi_blkg) return bio->bi_blkg->blkcg; return NULL;} static inline bool blk_cgroup_congested(void){ struct cgroup_subsys_state *css; bool ret = false; rcu_read_lock(); css = kthread_blkcg(); if (!css) css = task_css(current, io_cgrp_id); while (css) { if (atomic_read(&css->cgroup->congestion_count)) { ret = true; break; } css = css->parent; } rcu_read_unlock(); return ret;} /** * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg * @return: true if this bio needs to be submitted with the root blkg context. * * In order to avoid priority inversions we sometimes need to issue a bio as if * it were attached to the root blkg, and then backcharge to the actual owning * blkg. The idea is we do bio_blkcg() to look up the actual context for the * bio and attach the appropriate blkg to the bio. Then we call this helper and * if it is true run with the root blkg for that queue and then do any * backcharging to the originating cgroup once the io is complete. */static inline bool bio_issue_as_root_blkg(struct bio *bio){ return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0;} /** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest * * Return the parent blkcg of @blkcg. Can be called anytime. */static inline struct blkcg *blkcg_parent(struct blkcg *blkcg){ return css_to_blkcg(blkcg->css.parent);} /** * __blkg_lookup - internal version of blkg_lookup() * @blkcg: blkcg of interest * @q: request_queue of interest * @update_hint: whether to update lookup hint with the result or not * * This is internal version and shouldn't be used by policy * implementations. Looks up blkgs for the @blkcg - @q pair regardless of * @q's bypass state. If @update_hint is %true, the caller should be * holding @q->queue_lock and lookup hint is updated on success. */static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q, bool update_hint){ struct blkcg_gq *blkg; if (blkcg == &blkcg_root) return q->root_blkg; blkg = rcu_dereference(blkcg->blkg_hint); if (blkg && blkg->q == q) return blkg; return blkg_lookup_slowpath(blkcg, q, update_hint);} /** * blkg_lookup - lookup blkg for the specified blkcg - q pair * @blkcg: blkcg of interest * @q: request_queue of interest * * Lookup blkg for the @blkcg - @q pair. This function should be called * under RCU read lock. */static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q){ WARN_ON_ONCE(!rcu_read_lock_held()); return __blkg_lookup(blkcg, q, false);} /** * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair * @q: request_queue of interest * * Lookup blkg for @q at the root level. See also blkg_lookup(). */static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q){ return q->root_blkg;} /** * 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;} static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg, struct blkcg_policy *pol){ return blkcg ? blkcg->cpd[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;} static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd){ return cpd ? cpd->blkcg : NULL;} extern void blkcg_destroy_blkgs(struct blkcg *blkcg); /** * blkcg_pin_online - pin online state * @blkcg: blkcg of interest * * While pinned, a blkcg is kept online. This is primarily used to * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline * while an associated cgwb is still active. */static inline void blkcg_pin_online(struct blkcg *blkcg){ refcount_inc(&blkcg->online_pin);} /** * blkcg_unpin_online - unpin online state * @blkcg: blkcg of interest * * This is primarily used to impedance-match blkg and cgwb lifetimes so * that blkg doesn't go offline while an associated cgwb is still active. * When this count goes to zero, all active cgwbs have finished so the * blkcg can continue destruction by calling blkcg_destroy_blkgs(). */static inline void blkcg_unpin_online(struct blkcg *blkcg){ do { if (!refcount_dec_and_test(&blkcg->online_pin)) break; blkcg_destroy_blkgs(blkcg); blkcg = blkcg_parent(blkcg); } while (blkcg);} /** * 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){ return cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);} /** * blkg_get - get a blkg reference * @blkg: blkg to get * * The caller should be holding an existing reference. */static inline void blkg_get(struct blkcg_gq *blkg){ percpu_ref_get(&blkg->refcnt);} /** * blkg_tryget - try and get a blkg reference * @blkg: blkg to get * * This is for use when doing an RCU lookup of the blkg. We may be in the midst * of freeing this blkg, so we can only use it if the refcnt is not zero. */static inline bool blkg_tryget(struct blkcg_gq *blkg){ return blkg && percpu_ref_tryget(&blkg->refcnt);} /** * blkg_tryget_closest - try and get a blkg ref on the closet blkg * @blkg: blkg to get * * This needs to be called rcu protected. As the failure mode here is to walk * up the blkg tree, this ensure that the blkg->parent pointers are always * valid. This returns the blkg that it ended up taking a reference on or %NULL * if no reference was taken. */static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg){ struct blkcg_gq *ret_blkg = NULL; WARN_ON_ONCE(!rcu_read_lock_held()); while (blkg) { if (blkg_tryget(blkg)) { ret_blkg = blkg;Lines 1–500 of 766. Load more
/* SPDX-License-Identifier: GPL-2.0 */ #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/percpu.h> #include <linux/percpu_counter.h> #include <linux/u64_stats_sync.h> #include <linux/seq_file.h> #include <linux/radix-tree.h> #include <linux/blkdev.h> #include <linux/atomic.h> #include <linux/kthread.h> #include <linux/fs.h> /* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ #define BLKG_STAT_CPU_BATCH (INT_MAX / 2) /* Max limits for throttle policy */ #define THROTL_IOPS_MAX UINT_MAX #ifdef CONFIG_BLK_CGROUP enum blkg_iostat_type { BLKG_IOSTAT_READ, BLKG_IOSTAT_WRITE, BLKG_IOSTAT_DISCARD, BLKG_IOSTAT_NR, }; struct blkcg_gq; struct blkcg { struct cgroup_subsys_state css; spinlock_t lock; refcount_t online_pin; struct radix_tree_root blkg_tree; struct blkcg_gq __rcu *blkg_hint; struct hlist_head blkg_list; struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; struct list_head all_blkcgs_node; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; #endif }; struct blkg_iostat { u64 bytes[BLKG_IOSTAT_NR]; u64 ios[BLKG_IOSTAT_NR]; }; struct blkg_iostat_set { struct u64_stats_sync sync; struct blkg_iostat cur; struct blkg_iostat last; }; /* * 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 blkg:policy pair is * represented by a blkg_policy_data which is allocated and freed by each * policy's pd_alloc/free_fn() methods. A policy can allocate private data * area by allocating larger data structure which embeds blkg_policy_data * at the beginning. */ struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid; }; /* * Policies that need to keep per-blkcg data which is independent from any * request_queue associated to it should implement cpd_alloc/free_fn() * methods. A policy can allocate private data area by allocating larger * data structure which embeds blkcg_policy_data at the beginning. * cpd_init() is invoked to let each policy handle per-blkcg data. */ struct blkcg_policy_data { /* the blkcg and policy id this per-policy data belongs to */ struct blkcg *blkcg; int plid; }; /* 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; /* * Each blkg gets congested separately and the congestion state is * propagated to the matching bdi_writeback_congested. */ struct bdi_writeback_congested *wb_congested; /* all non-root blkcg_gq's are guaranteed to have access to parent */ struct blkcg_gq *parent; /* reference count */ struct percpu_ref refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; struct blkg_iostat_set __percpu *iostat_cpu; struct blkg_iostat_set iostat; struct blkg_policy_data *pd[BLKCG_MAX_POLS]; spinlock_t async_bio_lock; struct bio_list async_bios; struct work_struct async_bio_work; atomic_t use_delay; atomic64_t delay_nsec; atomic64_t delay_start; u64 last_delay; int last_use; struct rcu_head rcu_head; }; typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd); typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd); typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd); typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, struct request_queue *q, struct blkcg *blkcg); typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); typedef size_t (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, char *buf, size_t size); struct blkcg_policy { int plid; /* cgroup files for the policy */ struct cftype *dfl_cftypes; struct cftype *legacy_cftypes; /* operations */ blkcg_pol_alloc_cpd_fn *cpd_alloc_fn; blkcg_pol_init_cpd_fn *cpd_init_fn; blkcg_pol_free_cpd_fn *cpd_free_fn; blkcg_pol_bind_cpd_fn *cpd_bind_fn; blkcg_pol_alloc_pd_fn *pd_alloc_fn; blkcg_pol_init_pd_fn *pd_init_fn; blkcg_pol_online_pd_fn *pd_online_fn; blkcg_pol_offline_pd_fn *pd_offline_fn; blkcg_pol_free_pd_fn *pd_free_fn; blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn; blkcg_pol_stat_pd_fn *pd_stat_fn; }; extern struct blkcg blkcg_root; extern struct cgroup_subsys_state * const blkcg_root_css; extern bool blkcg_debug_stats; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); struct blkcg_gq *__blkg_lookup_create(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_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); const char *blkg_dev_name(struct blkcg_gq *blkg); 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); struct blkg_conf_ctx { struct gendisk *disk; struct blkcg_gq *blkg; char *body; }; struct gendisk *blkcg_conf_get_disk(char **inputp); int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx); void blkg_conf_finish(struct blkg_conf_ctx *ctx); /** * blkcg_css - find the current css * * Find the css associated with either the kthread or the current task. * This may return a dying css, so it is up to the caller to use tryget logic * to confirm it is alive and well. */ static inline struct cgroup_subsys_state *blkcg_css(void) { struct cgroup_subsys_state *css; css = kthread_blkcg(); if (css) return css; return task_css(current, io_cgrp_id); } static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; } /** * __bio_blkcg - internal, inconsistent version to get blkcg * * DO NOT USE. * This function is inconsistent and consequently is dangerous to use. The * first part of the function returns a blkcg where a reference is owned by the * bio. This means it does not need to be rcu protected as it cannot go away * with the bio owning a reference to it. However, the latter potentially gets * it from task_css(). This can race against task migration and the cgroup * dying. It is also semantically different as it must be called rcu protected * and is susceptible to failure when trying to get a reference to it. * Therefore, it is not ok to assume that *_get() will always succeed on the * blkcg returned here. */ static inline struct blkcg *__bio_blkcg(struct bio *bio) { if (bio && bio->bi_blkg) return bio->bi_blkg->blkcg; return css_to_blkcg(blkcg_css()); } /** * bio_blkcg - grab the blkcg associated with a bio * @bio: target bio * * This returns the blkcg associated with a bio, %NULL if not associated. * Callers are expected to either handle %NULL or know association has been * done prior to calling this. */ static inline struct blkcg *bio_blkcg(struct bio *bio) { if (bio && bio->bi_blkg) return bio->bi_blkg->blkcg; return NULL; } static inline bool blk_cgroup_congested(void) { struct cgroup_subsys_state *css; bool ret = false; rcu_read_lock(); css = kthread_blkcg(); if (!css) css = task_css(current, io_cgrp_id); while (css) { if (atomic_read(&css->cgroup->congestion_count)) { ret = true; break; } css = css->parent; } rcu_read_unlock(); return ret; } /** * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg * @return: true if this bio needs to be submitted with the root blkg context. * * In order to avoid priority inversions we sometimes need to issue a bio as if * it were attached to the root blkg, and then backcharge to the actual owning * blkg. The idea is we do bio_blkcg() to look up the actual context for the * bio and attach the appropriate blkg to the bio. Then we call this helper and * if it is true run with the root blkg for that queue and then do any * backcharging to the originating cgroup once the io is complete. */ static inline bool bio_issue_as_root_blkg(struct bio *bio) { return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0; } /** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest * * Return the parent blkcg of @blkcg. Can be called anytime. */ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) { return css_to_blkcg(blkcg->css.parent); } /** * __blkg_lookup - internal version of blkg_lookup() * @blkcg: blkcg of interest * @q: request_queue of interest * @update_hint: whether to update lookup hint with the result or not * * This is internal version and shouldn't be used by policy * implementations. Looks up blkgs for the @blkcg - @q pair regardless of * @q's bypass state. If @update_hint is %true, the caller should be * holding @q->queue_lock and lookup hint is updated on success. */ static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q, bool update_hint) { struct blkcg_gq *blkg; if (blkcg == &blkcg_root) return q->root_blkg; blkg = rcu_dereference(blkcg->blkg_hint); if (blkg && blkg->q == q) return blkg; return blkg_lookup_slowpath(blkcg, q, update_hint); } /** * blkg_lookup - lookup blkg for the specified blkcg - q pair * @blkcg: blkcg of interest * @q: request_queue of interest * * Lookup blkg for the @blkcg - @q pair. This function should be called * under RCU read lock. */ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q) { WARN_ON_ONCE(!rcu_read_lock_held()); return __blkg_lookup(blkcg, q, false); } /** * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair * @q: request_queue of interest * * Lookup blkg for @q at the root level. See also blkg_lookup(). */ static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) { return q->root_blkg; } /** * 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; } static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg, struct blkcg_policy *pol) { return blkcg ? blkcg->cpd[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; } static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) { return cpd ? cpd->blkcg : NULL; } extern void blkcg_destroy_blkgs(struct blkcg *blkcg); /** * blkcg_pin_online - pin online state * @blkcg: blkcg of interest * * While pinned, a blkcg is kept online. This is primarily used to * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline * while an associated cgwb is still active. */ static inline void blkcg_pin_online(struct blkcg *blkcg) { refcount_inc(&blkcg->online_pin); } /** * blkcg_unpin_online - unpin online state * @blkcg: blkcg of interest * * This is primarily used to impedance-match blkg and cgwb lifetimes so * that blkg doesn't go offline while an associated cgwb is still active. * When this count goes to zero, all active cgwbs have finished so the * blkcg can continue destruction by calling blkcg_destroy_blkgs(). */ static inline void blkcg_unpin_online(struct blkcg *blkcg) { do { if (!refcount_dec_and_test(&blkcg->online_pin)) break; blkcg_destroy_blkgs(blkcg); blkcg = blkcg_parent(blkcg); } while (blkcg); } /** * 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) { return cgroup_path(blkg->blkcg->css.cgroup, buf, buflen); } /** * blkg_get - get a blkg reference * @blkg: blkg to get * * The caller should be holding an existing reference. */ static inline void blkg_get(struct blkcg_gq *blkg) { percpu_ref_get(&blkg->refcnt); } /** * blkg_tryget - try and get a blkg reference * @blkg: blkg to get * * This is for use when doing an RCU lookup of the blkg. We may be in the midst * of freeing this blkg, so we can only use it if the refcnt is not zero. */ static inline bool blkg_tryget(struct blkcg_gq *blkg) { return blkg && percpu_ref_tryget(&blkg->refcnt); } /** * blkg_tryget_closest - try and get a blkg ref on the closet blkg * @blkg: blkg to get * * This needs to be called rcu protected. As the failure mode here is to walk * up the blkg tree, this ensure that the blkg->parent pointers are always * valid. This returns the blkg that it ended up taking a reference on or %NULL * if no reference was taken. */ static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) { struct blkcg_gq *ret_blkg = NULL; WARN_ON_ONCE(!rcu_read_lock_held()); while (blkg) { if (blkg_tryget(blkg)) { ret_blkg = blkg;