// SPDX-License-Identifier: GPL-2.0/* * Interface for controlling IO bandwidth on a request queue * * Copyright (C) 2010 Vivek Goyal <vgoyal@redhat.com> */ #include <linux/module.h>#include <linux/slab.h>#include <linux/blkdev.h>#include <linux/bio.h>#include <linux/blktrace_api.h>#include "blk.h"#include "blk-cgroup-rwstat.h"#include "blk-throttle.h" /* Max dispatch from a group in 1 round */#define THROTL_GRP_QUANTUM 8 /* Total max dispatch from all groups in one round */#define THROTL_QUANTUM 32 /* Throttling is performed over a slice and after that slice is renewed */#define DFL_THROTL_SLICE (HZ / 10) /* A workqueue to queue throttle related work */static struct workqueue_struct *kthrotld_workqueue; #define rb_entry_tg(node) rb_entry((node), struct throtl_grp, rb_node) struct throtl_data{ /* service tree for active throtl groups */ struct throtl_service_queue service_queue; struct request_queue *queue; /* Total Number of queued bios on READ and WRITE lists */ unsigned int nr_queued[2]; /* Work for dispatching throttled bios */ struct work_struct dispatch_work;}; static void throtl_pending_timer_fn(struct timer_list *t); static inline struct blkcg_gq *tg_to_blkg(struct throtl_grp *tg){ return pd_to_blkg(&tg->pd);} /** * sq_to_tg - return the throl_grp the specified service queue belongs to * @sq: the throtl_service_queue of interest * * Return the throtl_grp @sq belongs to. If @sq is the top-level one * embedded in throtl_data, %NULL is returned. */static struct throtl_grp *sq_to_tg(struct throtl_service_queue *sq){ if (sq && sq->parent_sq) return container_of(sq, struct throtl_grp, service_queue); else return NULL;} /** * sq_to_td - return throtl_data the specified service queue belongs to * @sq: the throtl_service_queue of interest * * A service_queue can be embedded in either a throtl_grp or throtl_data. * Determine the associated throtl_data accordingly and return it. */static struct throtl_data *sq_to_td(struct throtl_service_queue *sq){ struct throtl_grp *tg = sq_to_tg(sq); if (tg) return tg->td; else return container_of(sq, struct throtl_data, service_queue);} static uint64_t tg_bps_limit(struct throtl_grp *tg, int rw){ struct blkcg_gq *blkg = tg_to_blkg(tg); if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent) return U64_MAX; return tg->bps[rw];} static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw){ struct blkcg_gq *blkg = tg_to_blkg(tg); if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent) return UINT_MAX; return tg->iops[rw];} /** * throtl_log - log debug message via blktrace * @sq: the service_queue being reported * @fmt: printf format string * @args: printf args * * The messages are prefixed with "throtl BLKG_NAME" if @sq belongs to a * throtl_grp; otherwise, just "throtl". */#define throtl_log(sq, fmt, args...) do { \ struct throtl_grp *__tg = sq_to_tg((sq)); \ struct throtl_data *__td = sq_to_td((sq)); \ \ (void)__td; \ if (likely(!blk_trace_note_message_enabled(__td->queue))) \ break; \ if ((__tg)) { \ blk_add_cgroup_trace_msg(__td->queue, \ &tg_to_blkg(__tg)->blkcg->css, "throtl " fmt, ##args);\ } else { \ blk_add_trace_msg(__td->queue, "throtl " fmt, ##args); \ } \} while (0) static inline unsigned int throtl_bio_data_size(struct bio *bio){ /* assume it's one sector */ if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) return 512; return bio->bi_iter.bi_size;} static void throtl_qnode_init(struct throtl_qnode *qn, struct throtl_grp *tg){ INIT_LIST_HEAD(&qn->node); bio_list_init(&qn->bios_bps); bio_list_init(&qn->bios_iops); qn->tg = tg;} /** * throtl_qnode_add_bio - add a bio to a throtl_qnode and activate it * @bio: bio being added * @qn: qnode to add bio to * @sq: the service_queue @qn belongs to * * Add @bio to @qn and put @qn on @sq->queued if it's not already on. * @qn->tg's reference count is bumped when @qn is activated. See the * comment on top of throtl_qnode definition for details. */static void throtl_qnode_add_bio(struct bio *bio, struct throtl_qnode *qn, struct throtl_service_queue *sq){ bool rw = bio_data_dir(bio); /* * Split bios have already been throttled by bps, so they are * directly queued into the iops path. */ if (bio_flagged(bio, BIO_TG_BPS_THROTTLED) || bio_flagged(bio, BIO_BPS_THROTTLED)) { bio_list_add(&qn->bios_iops, bio); sq->nr_queued_iops[rw]++; } else { bio_list_add(&qn->bios_bps, bio); sq->nr_queued_bps[rw]++; } if (list_empty(&qn->node)) { list_add_tail(&qn->node, &sq->queued[rw]); blkg_get(tg_to_blkg(qn->tg)); }} /** * throtl_peek_queued - peek the first bio on a qnode list * @queued: the qnode list to peek * * Always take a bio from the head of the iops queue first. If the queue is * empty, we then take it from the bps queue to maintain the overall idea of * fetching bios from the head. */static struct bio *throtl_peek_queued(struct list_head *queued){ struct throtl_qnode *qn; struct bio *bio; if (list_empty(queued)) return NULL; qn = list_first_entry(queued, struct throtl_qnode, node); bio = bio_list_peek(&qn->bios_iops); if (!bio) bio = bio_list_peek(&qn->bios_bps); WARN_ON_ONCE(!bio); return bio;} /** * throtl_pop_queued - pop the first bio form a qnode list * @sq: the service_queue to pop a bio from * @tg_to_put: optional out argument for throtl_grp to put * @rw: read/write * * Pop the first bio from the qnode list @sq->queued. Note that we firstly * focus on the iops list because bios are ultimately dispatched from it. * After popping, the first qnode is removed from @sq->queued if empty or moved * to the end of @sq->queued so that the popping order is round-robin. * * When the first qnode is removed, its associated throtl_grp should be put * too. If @tg_to_put is NULL, this function automatically puts it; * otherwise, *@tg_to_put is set to the throtl_grp to put and the caller is * responsible for putting it. */static struct bio *throtl_pop_queued(struct throtl_service_queue *sq, struct throtl_grp **tg_to_put, bool rw){ struct list_head *queued = &sq->queued[rw]; struct throtl_qnode *qn; struct bio *bio; if (list_empty(queued)) return NULL; qn = list_first_entry(queued, struct throtl_qnode, node); bio = bio_list_pop(&qn->bios_iops); if (bio) { sq->nr_queued_iops[rw]--; } else { bio = bio_list_pop(&qn->bios_bps); if (bio) sq->nr_queued_bps[rw]--; } WARN_ON_ONCE(!bio); if (bio_list_empty(&qn->bios_bps) && bio_list_empty(&qn->bios_iops)) { list_del_init(&qn->node); if (tg_to_put) *tg_to_put = qn->tg; else blkg_put(tg_to_blkg(qn->tg)); } else { list_move_tail(&qn->node, queued); } return bio;} /* init a service_queue, assumes the caller zeroed it */static void throtl_service_queue_init(struct throtl_service_queue *sq){ INIT_LIST_HEAD(&sq->queued[READ]); INIT_LIST_HEAD(&sq->queued[WRITE]); sq->pending_tree = RB_ROOT_CACHED; timer_setup(&sq->pending_timer, throtl_pending_timer_fn, 0);} static struct blkg_policy_data *throtl_pd_alloc(struct gendisk *disk, struct blkcg *blkcg, gfp_t gfp){ struct throtl_grp *tg; int rw; tg = kzalloc_node(sizeof(*tg), gfp, disk->node_id); if (!tg) return NULL; if (blkg_rwstat_init(&tg->stat_bytes, gfp)) goto err_free_tg; if (blkg_rwstat_init(&tg->stat_ios, gfp)) goto err_exit_stat_bytes; throtl_service_queue_init(&tg->service_queue); for (rw = READ; rw <= WRITE; rw++) { throtl_qnode_init(&tg->qnode_on_self[rw], tg); throtl_qnode_init(&tg->qnode_on_parent[rw], tg); } RB_CLEAR_NODE(&tg->rb_node); tg->bps[READ] = U64_MAX; tg->bps[WRITE] = U64_MAX; tg->iops[READ] = UINT_MAX; tg->iops[WRITE] = UINT_MAX; return &tg->pd; err_exit_stat_bytes: blkg_rwstat_exit(&tg->stat_bytes);err_free_tg: kfree(tg); return NULL;} static void throtl_pd_init(struct blkg_policy_data *pd){ struct throtl_grp *tg = pd_to_tg(pd); struct blkcg_gq *blkg = tg_to_blkg(tg); struct throtl_data *td = blkg->q->td; struct throtl_service_queue *sq = &tg->service_queue; /* * If on the default hierarchy, we switch to properly hierarchical * behavior where limits on a given throtl_grp are applied to the * whole subtree rather than just the group itself. e.g. If 16M * read_bps limit is set on a parent group, summary bps of * parent group and its subtree groups can't exceed 16M for the * device. * * If not on the default hierarchy, the broken flat hierarchy * behavior is retained where all throtl_grps are treated as if * they're all separate root groups right below throtl_data. * Limits of a group don't interact with limits of other groups * regardless of the position of the group in the hierarchy. */ sq->parent_sq = &td->service_queue; if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent) sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue; tg->td = td;} /* * Set has_rules[] if @tg or any of its parents have limits configured. * This doesn't require walking up to the top of the hierarchy as the * parent's has_rules[] is guaranteed to be correct. */static void tg_update_has_rules(struct throtl_grp *tg){ struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq); int rw; for (rw = READ; rw <= WRITE; rw++) { tg->has_rules_iops[rw] = (parent_tg && parent_tg->has_rules_iops[rw]) || tg_iops_limit(tg, rw) != UINT_MAX; tg->has_rules_bps[rw] = (parent_tg && parent_tg->has_rules_bps[rw]) || tg_bps_limit(tg, rw) != U64_MAX; }} static void throtl_pd_online(struct blkg_policy_data *pd){ struct throtl_grp *tg = pd_to_tg(pd); /* * We don't want new groups to escape the limits of its ancestors. * Update has_rules[] after a new group is brought online. */ tg_update_has_rules(tg);} static void tg_release(struct rcu_head *rcu){ struct blkg_policy_data *pd = container_of(rcu, struct blkg_policy_data, rcu_head); struct throtl_grp *tg = pd_to_tg(pd); blkg_rwstat_exit(&tg->stat_bytes); blkg_rwstat_exit(&tg->stat_ios); kfree(tg);} static void throtl_pd_free(struct blkg_policy_data *pd){ struct throtl_grp *tg = pd_to_tg(pd); timer_delete_sync(&tg->service_queue.pending_timer); call_rcu(&pd->rcu_head, tg_release);} static struct throtl_grp *throtl_rb_first(struct throtl_service_queue *parent_sq){ struct rb_node *n; n = rb_first_cached(&parent_sq->pending_tree); WARN_ON_ONCE(!n); if (!n) return NULL; return rb_entry_tg(n);} static void throtl_rb_erase(struct rb_node *n, struct throtl_service_queue *parent_sq){ rb_erase_cached(n, &parent_sq->pending_tree); RB_CLEAR_NODE(n);} static void update_min_dispatch_time(struct throtl_service_queue *parent_sq){ struct throtl_grp *tg; tg = throtl_rb_first(parent_sq); if (!tg) return; parent_sq->first_pending_disptime = tg->disptime;} static void tg_service_queue_add(struct throtl_grp *tg){ struct throtl_service_queue *parent_sq = tg->service_queue.parent_sq; struct rb_node **node = &parent_sq->pending_tree.rb_root.rb_node; struct rb_node *parent = NULL; struct throtl_grp *__tg; unsigned long key = tg->disptime; bool leftmost = true; while (*node != NULL) { parent = *node; __tg = rb_entry_tg(parent); if (time_before(key, __tg->disptime)) node = &parent->rb_left; else { node = &parent->rb_right; leftmost = false; } } rb_link_node(&tg->rb_node, parent, node); rb_insert_color_cached(&tg->rb_node, &parent_sq->pending_tree, leftmost);} static void throtl_enqueue_tg(struct throtl_grp *tg){ if (!(tg->flags & THROTL_TG_PENDING)) { tg_service_queue_add(tg); tg->flags |= THROTL_TG_PENDING; tg->service_queue.parent_sq->nr_pending++; }} static void throtl_dequeue_tg(struct throtl_grp *tg){ if (tg->flags & THROTL_TG_PENDING) { struct throtl_service_queue *parent_sq = tg->service_queue.parent_sq; throtl_rb_erase(&tg->rb_node, parent_sq); --parent_sq->nr_pending; tg->flags &= ~THROTL_TG_PENDING; }} /* Call with queue lock held */static void throtl_schedule_pending_timer(struct throtl_service_queue *sq, unsigned long expires){ unsigned long max_expire = jiffies + 8 * DFL_THROTL_SLICE; /* * Since we are adjusting the throttle limit dynamically, the sleep * time calculated according to previous limit might be invalid. It's * possible the cgroup sleep time is very long and no other cgroups * have IO running so notify the limit changes. Make sure the cgroup * doesn't sleep too long to avoid the missed notification. */ if (time_after(expires, max_expire)) expires = max_expire; mod_timer(&sq->pending_timer, expires); throtl_log(sq, "schedule timer. delay=%lu jiffies=%lu", expires - jiffies, jiffies);} /** * throtl_schedule_next_dispatch - schedule the next dispatch cycle * @sq: the service_queue to schedule dispatch for * @force: force scheduling * * Arm @sq->pending_timer so that the next dispatch cycle starts on the * dispatch time of the first pending child. Returns %true if either timer * is armed or there's no pending child left. %false if the current * dispatch window is still open and the caller should continue * dispatching. * * If @force is %true, the dispatch timer is always scheduled and this * function is guaranteed to return %true. This is to be used when the * caller can't dispatch itself and needs to invoke pending_timer * unconditionally. Note that forced scheduling is likely to induce short * delay before dispatch starts even if @sq->first_pending_disptime is not * in the future and thus shouldn't be used in hot paths. */static bool throtl_schedule_next_dispatch(struct throtl_service_queue *sq, bool force){ /* any pending children left? */ if (!sq->nr_pending) return true; update_min_dispatch_time(sq); /* is the next dispatch time in the future? */ if (force || time_after(sq->first_pending_disptime, jiffies)) {Lines 1–500 of 1911. Load more
// SPDX-License-Identifier: GPL-2.0 /* * Interface for controlling IO bandwidth on a request queue * * Copyright (C) 2010 Vivek Goyal <vgoyal@redhat.com> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/bio.h> #include <linux/blktrace_api.h> #include "blk.h" #include "blk-cgroup-rwstat.h" #include "blk-throttle.h" /* Max dispatch from a group in 1 round */ #define THROTL_GRP_QUANTUM 8 /* Total max dispatch from all groups in one round */ #define THROTL_QUANTUM 32 /* Throttling is performed over a slice and after that slice is renewed */ #define DFL_THROTL_SLICE (HZ / 10) /* A workqueue to queue throttle related work */ static struct workqueue_struct *kthrotld_workqueue; #define rb_entry_tg(node) rb_entry((node), struct throtl_grp, rb_node) struct throtl_data { /* service tree for active throtl groups */ struct throtl_service_queue service_queue; struct request_queue *queue; /* Total Number of queued bios on READ and WRITE lists */ unsigned int nr_queued[2]; /* Work for dispatching throttled bios */ struct work_struct dispatch_work; }; static void throtl_pending_timer_fn(struct timer_list *t); static inline struct blkcg_gq *tg_to_blkg(struct throtl_grp *tg) { return pd_to_blkg(&tg->pd); } /** * sq_to_tg - return the throl_grp the specified service queue belongs to * @sq: the throtl_service_queue of interest * * Return the throtl_grp @sq belongs to. If @sq is the top-level one * embedded in throtl_data, %NULL is returned. */ static struct throtl_grp *sq_to_tg(struct throtl_service_queue *sq) { if (sq && sq->parent_sq) return container_of(sq, struct throtl_grp, service_queue); else return NULL; } /** * sq_to_td - return throtl_data the specified service queue belongs to * @sq: the throtl_service_queue of interest * * A service_queue can be embedded in either a throtl_grp or throtl_data. * Determine the associated throtl_data accordingly and return it. */ static struct throtl_data *sq_to_td(struct throtl_service_queue *sq) { struct throtl_grp *tg = sq_to_tg(sq); if (tg) return tg->td; else return container_of(sq, struct throtl_data, service_queue); } static uint64_t tg_bps_limit(struct throtl_grp *tg, int rw) { struct blkcg_gq *blkg = tg_to_blkg(tg); if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent) return U64_MAX; return tg->bps[rw]; } static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw) { struct blkcg_gq *blkg = tg_to_blkg(tg); if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent) return UINT_MAX; return tg->iops[rw]; } /** * throtl_log - log debug message via blktrace * @sq: the service_queue being reported * @fmt: printf format string * @args: printf args * * The messages are prefixed with "throtl BLKG_NAME" if @sq belongs to a * throtl_grp; otherwise, just "throtl". */ #define throtl_log(sq, fmt, args...) do { \ struct throtl_grp *__tg = sq_to_tg((sq)); \ struct throtl_data *__td = sq_to_td((sq)); \ \ (void)__td; \ if (likely(!blk_trace_note_message_enabled(__td->queue))) \ break; \ if ((__tg)) { \ blk_add_cgroup_trace_msg(__td->queue, \ &tg_to_blkg(__tg)->blkcg->css, "throtl " fmt, ##args);\ } else { \ blk_add_trace_msg(__td->queue, "throtl " fmt, ##args); \ } \ } while (0) static inline unsigned int throtl_bio_data_size(struct bio *bio) { /* assume it's one sector */ if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) return 512; return bio->bi_iter.bi_size; } static void throtl_qnode_init(struct throtl_qnode *qn, struct throtl_grp *tg) { INIT_LIST_HEAD(&qn->node); bio_list_init(&qn->bios_bps); bio_list_init(&qn->bios_iops); qn->tg = tg; } /** * throtl_qnode_add_bio - add a bio to a throtl_qnode and activate it * @bio: bio being added * @qn: qnode to add bio to * @sq: the service_queue @qn belongs to * * Add @bio to @qn and put @qn on @sq->queued if it's not already on. * @qn->tg's reference count is bumped when @qn is activated. See the * comment on top of throtl_qnode definition for details. */ static void throtl_qnode_add_bio(struct bio *bio, struct throtl_qnode *qn, struct throtl_service_queue *sq) { bool rw = bio_data_dir(bio); /* * Split bios have already been throttled by bps, so they are * directly queued into the iops path. */ if (bio_flagged(bio, BIO_TG_BPS_THROTTLED) || bio_flagged(bio, BIO_BPS_THROTTLED)) { bio_list_add(&qn->bios_iops, bio); sq->nr_queued_iops[rw]++; } else { bio_list_add(&qn->bios_bps, bio); sq->nr_queued_bps[rw]++; } if (list_empty(&qn->node)) { list_add_tail(&qn->node, &sq->queued[rw]); blkg_get(tg_to_blkg(qn->tg)); } } /** * throtl_peek_queued - peek the first bio on a qnode list * @queued: the qnode list to peek * * Always take a bio from the head of the iops queue first. If the queue is * empty, we then take it from the bps queue to maintain the overall idea of * fetching bios from the head. */ static struct bio *throtl_peek_queued(struct list_head *queued) { struct throtl_qnode *qn; struct bio *bio; if (list_empty(queued)) return NULL; qn = list_first_entry(queued, struct throtl_qnode, node); bio = bio_list_peek(&qn->bios_iops); if (!bio) bio = bio_list_peek(&qn->bios_bps); WARN_ON_ONCE(!bio); return bio; } /** * throtl_pop_queued - pop the first bio form a qnode list * @sq: the service_queue to pop a bio from * @tg_to_put: optional out argument for throtl_grp to put * @rw: read/write * * Pop the first bio from the qnode list @sq->queued. Note that we firstly * focus on the iops list because bios are ultimately dispatched from it. * After popping, the first qnode is removed from @sq->queued if empty or moved * to the end of @sq->queued so that the popping order is round-robin. * * When the first qnode is removed, its associated throtl_grp should be put * too. If @tg_to_put is NULL, this function automatically puts it; * otherwise, *@tg_to_put is set to the throtl_grp to put and the caller is * responsible for putting it. */ static struct bio *throtl_pop_queued(struct throtl_service_queue *sq, struct throtl_grp **tg_to_put, bool rw) { struct list_head *queued = &sq->queued[rw]; struct throtl_qnode *qn; struct bio *bio; if (list_empty(queued)) return NULL; qn = list_first_entry(queued, struct throtl_qnode, node); bio = bio_list_pop(&qn->bios_iops); if (bio) { sq->nr_queued_iops[rw]--; } else { bio = bio_list_pop(&qn->bios_bps); if (bio) sq->nr_queued_bps[rw]--; } WARN_ON_ONCE(!bio); if (bio_list_empty(&qn->bios_bps) && bio_list_empty(&qn->bios_iops)) { list_del_init(&qn->node); if (tg_to_put) *tg_to_put = qn->tg; else blkg_put(tg_to_blkg(qn->tg)); } else { list_move_tail(&qn->node, queued); } return bio; } /* init a service_queue, assumes the caller zeroed it */ static void throtl_service_queue_init(struct throtl_service_queue *sq) { INIT_LIST_HEAD(&sq->queued[READ]); INIT_LIST_HEAD(&sq->queued[WRITE]); sq->pending_tree = RB_ROOT_CACHED; timer_setup(&sq->pending_timer, throtl_pending_timer_fn, 0); } static struct blkg_policy_data *throtl_pd_alloc(struct gendisk *disk, struct blkcg *blkcg, gfp_t gfp) { struct throtl_grp *tg; int rw; tg = kzalloc_node(sizeof(*tg), gfp, disk->node_id); if (!tg) return NULL; if (blkg_rwstat_init(&tg->stat_bytes, gfp)) goto err_free_tg; if (blkg_rwstat_init(&tg->stat_ios, gfp)) goto err_exit_stat_bytes; throtl_service_queue_init(&tg->service_queue); for (rw = READ; rw <= WRITE; rw++) { throtl_qnode_init(&tg->qnode_on_self[rw], tg); throtl_qnode_init(&tg->qnode_on_parent[rw], tg); } RB_CLEAR_NODE(&tg->rb_node); tg->bps[READ] = U64_MAX; tg->bps[WRITE] = U64_MAX; tg->iops[READ] = UINT_MAX; tg->iops[WRITE] = UINT_MAX; return &tg->pd; err_exit_stat_bytes: blkg_rwstat_exit(&tg->stat_bytes); err_free_tg: kfree(tg); return NULL; } static void throtl_pd_init(struct blkg_policy_data *pd) { struct throtl_grp *tg = pd_to_tg(pd); struct blkcg_gq *blkg = tg_to_blkg(tg); struct throtl_data *td = blkg->q->td; struct throtl_service_queue *sq = &tg->service_queue; /* * If on the default hierarchy, we switch to properly hierarchical * behavior where limits on a given throtl_grp are applied to the * whole subtree rather than just the group itself. e.g. If 16M * read_bps limit is set on a parent group, summary bps of * parent group and its subtree groups can't exceed 16M for the * device. * * If not on the default hierarchy, the broken flat hierarchy * behavior is retained where all throtl_grps are treated as if * they're all separate root groups right below throtl_data. * Limits of a group don't interact with limits of other groups * regardless of the position of the group in the hierarchy. */ sq->parent_sq = &td->service_queue; if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent) sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue; tg->td = td; } /* * Set has_rules[] if @tg or any of its parents have limits configured. * This doesn't require walking up to the top of the hierarchy as the * parent's has_rules[] is guaranteed to be correct. */ static void tg_update_has_rules(struct throtl_grp *tg) { struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq); int rw; for (rw = READ; rw <= WRITE; rw++) { tg->has_rules_iops[rw] = (parent_tg && parent_tg->has_rules_iops[rw]) || tg_iops_limit(tg, rw) != UINT_MAX; tg->has_rules_bps[rw] = (parent_tg && parent_tg->has_rules_bps[rw]) || tg_bps_limit(tg, rw) != U64_MAX; } } static void throtl_pd_online(struct blkg_policy_data *pd) { struct throtl_grp *tg = pd_to_tg(pd); /* * We don't want new groups to escape the limits of its ancestors. * Update has_rules[] after a new group is brought online. */ tg_update_has_rules(tg); } static void tg_release(struct rcu_head *rcu) { struct blkg_policy_data *pd = container_of(rcu, struct blkg_policy_data, rcu_head); struct throtl_grp *tg = pd_to_tg(pd); blkg_rwstat_exit(&tg->stat_bytes); blkg_rwstat_exit(&tg->stat_ios); kfree(tg); } static void throtl_pd_free(struct blkg_policy_data *pd) { struct throtl_grp *tg = pd_to_tg(pd); timer_delete_sync(&tg->service_queue.pending_timer); call_rcu(&pd->rcu_head, tg_release); } static struct throtl_grp * throtl_rb_first(struct throtl_service_queue *parent_sq) { struct rb_node *n; n = rb_first_cached(&parent_sq->pending_tree); WARN_ON_ONCE(!n); if (!n) return NULL; return rb_entry_tg(n); } static void throtl_rb_erase(struct rb_node *n, struct throtl_service_queue *parent_sq) { rb_erase_cached(n, &parent_sq->pending_tree); RB_CLEAR_NODE(n); } static void update_min_dispatch_time(struct throtl_service_queue *parent_sq) { struct throtl_grp *tg; tg = throtl_rb_first(parent_sq); if (!tg) return; parent_sq->first_pending_disptime = tg->disptime; } static void tg_service_queue_add(struct throtl_grp *tg) { struct throtl_service_queue *parent_sq = tg->service_queue.parent_sq; struct rb_node **node = &parent_sq->pending_tree.rb_root.rb_node; struct rb_node *parent = NULL; struct throtl_grp *__tg; unsigned long key = tg->disptime; bool leftmost = true; while (*node != NULL) { parent = *node; __tg = rb_entry_tg(parent); if (time_before(key, __tg->disptime)) node = &parent->rb_left; else { node = &parent->rb_right; leftmost = false; } } rb_link_node(&tg->rb_node, parent, node); rb_insert_color_cached(&tg->rb_node, &parent_sq->pending_tree, leftmost); } static void throtl_enqueue_tg(struct throtl_grp *tg) { if (!(tg->flags & THROTL_TG_PENDING)) { tg_service_queue_add(tg); tg->flags |= THROTL_TG_PENDING; tg->service_queue.parent_sq->nr_pending++; } } static void throtl_dequeue_tg(struct throtl_grp *tg) { if (tg->flags & THROTL_TG_PENDING) { struct throtl_service_queue *parent_sq = tg->service_queue.parent_sq; throtl_rb_erase(&tg->rb_node, parent_sq); --parent_sq->nr_pending; tg->flags &= ~THROTL_TG_PENDING; } } /* Call with queue lock held */ static void throtl_schedule_pending_timer(struct throtl_service_queue *sq, unsigned long expires) { unsigned long max_expire = jiffies + 8 * DFL_THROTL_SLICE; /* * Since we are adjusting the throttle limit dynamically, the sleep * time calculated according to previous limit might be invalid. It's * possible the cgroup sleep time is very long and no other cgroups * have IO running so notify the limit changes. Make sure the cgroup * doesn't sleep too long to avoid the missed notification. */ if (time_after(expires, max_expire)) expires = max_expire; mod_timer(&sq->pending_timer, expires); throtl_log(sq, "schedule timer. delay=%lu jiffies=%lu", expires - jiffies, jiffies); } /** * throtl_schedule_next_dispatch - schedule the next dispatch cycle * @sq: the service_queue to schedule dispatch for * @force: force scheduling * * Arm @sq->pending_timer so that the next dispatch cycle starts on the * dispatch time of the first pending child. Returns %true if either timer * is armed or there's no pending child left. %false if the current * dispatch window is still open and the caller should continue * dispatching. * * If @force is %true, the dispatch timer is always scheduled and this * function is guaranteed to return %true. This is to be used when the * caller can't dispatch itself and needs to invoke pending_timer * unconditionally. Note that forced scheduling is likely to induce short * delay before dispatch starts even if @sq->first_pending_disptime is not * in the future and thus shouldn't be used in hot paths. */ static bool throtl_schedule_next_dispatch(struct throtl_service_queue *sq, bool force) { /* any pending children left? */ if (!sq->nr_pending) return true; update_min_dispatch_time(sq); /* is the next dispatch time in the future? */ if (force || time_after(sq->first_pending_disptime, jiffies)) {