diff options
Diffstat (limited to 'block/cfq-iosched.c')
| -rw-r--r-- | block/cfq-iosched.c | 1696 |
1 files changed, 1207 insertions, 489 deletions
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index d0ba5053366..cadc3784174 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -15,7 +15,7 @@ #include <linux/ioprio.h> #include <linux/blktrace_api.h> #include "blk.h" -#include "cfq.h" +#include "blk-cgroup.h" /* * tunables @@ -85,7 +85,6 @@ struct cfq_rb_root { struct rb_root rb; struct rb_node *left; unsigned count; - unsigned total_weight; u64 min_vdisktime; struct cfq_ttime ttime; }; @@ -155,7 +154,7 @@ struct cfq_queue { * First index in the service_trees. * IDLE is handled separately, so it has negative index */ -enum wl_prio_t { +enum wl_class_t { BE_WORKLOAD = 0, RT_WORKLOAD = 1, IDLE_WORKLOAD = 2, @@ -171,16 +170,96 @@ enum wl_type_t { SYNC_WORKLOAD = 2 }; +struct cfqg_stats { +#ifdef CONFIG_CFQ_GROUP_IOSCHED + /* total bytes transferred */ + struct blkg_rwstat service_bytes; + /* total IOs serviced, post merge */ + struct blkg_rwstat serviced; + /* number of ios merged */ + struct blkg_rwstat merged; + /* total time spent on device in ns, may not be accurate w/ queueing */ + struct blkg_rwstat service_time; + /* total time spent waiting in scheduler queue in ns */ + struct blkg_rwstat wait_time; + /* number of IOs queued up */ + struct blkg_rwstat queued; + /* total sectors transferred */ + struct blkg_stat sectors; + /* total disk time and nr sectors dispatched by this group */ + struct blkg_stat time; +#ifdef CONFIG_DEBUG_BLK_CGROUP + /* time not charged to this cgroup */ + struct blkg_stat unaccounted_time; + /* sum of number of ios queued across all samples */ + struct blkg_stat avg_queue_size_sum; + /* count of samples taken for average */ + struct blkg_stat avg_queue_size_samples; + /* how many times this group has been removed from service tree */ + struct blkg_stat dequeue; + /* total time spent waiting for it to be assigned a timeslice. */ + struct blkg_stat group_wait_time; + /* time spent idling for this blkcg_gq */ + struct blkg_stat idle_time; + /* total time with empty current active q with other requests queued */ + struct blkg_stat empty_time; + /* fields after this shouldn't be cleared on stat reset */ + uint64_t start_group_wait_time; + uint64_t start_idle_time; + uint64_t start_empty_time; + uint16_t flags; +#endif /* CONFIG_DEBUG_BLK_CGROUP */ +#endif /* CONFIG_CFQ_GROUP_IOSCHED */ +}; + /* This is per cgroup per device grouping structure */ struct cfq_group { + /* must be the first member */ + struct blkg_policy_data pd; + /* group service_tree member */ struct rb_node rb_node; /* group service_tree key */ u64 vdisktime; + + /* + * The number of active cfqgs and sum of their weights under this + * cfqg. This covers this cfqg's leaf_weight and all children's + * weights, but does not cover weights of further descendants. + * + * If a cfqg is on the service tree, it's active. An active cfqg + * also activates its parent and contributes to the children_weight + * of the parent. + */ + int nr_active; + unsigned int children_weight; + + /* + * vfraction is the fraction of vdisktime that the tasks in this + * cfqg are entitled to. This is determined by compounding the + * ratios walking up from this cfqg to the root. + * + * It is in fixed point w/ CFQ_SERVICE_SHIFT and the sum of all + * vfractions on a service tree is approximately 1. The sum may + * deviate a bit due to rounding errors and fluctuations caused by + * cfqgs entering and leaving the service tree. + */ + unsigned int vfraction; + + /* + * There are two weights - (internal) weight is the weight of this + * cfqg against the sibling cfqgs. leaf_weight is the wight of + * this cfqg against the child cfqgs. For the root cfqg, both + * weights are kept in sync for backward compatibility. + */ unsigned int weight; unsigned int new_weight; - bool needs_update; + unsigned int dev_weight; + + unsigned int leaf_weight; + unsigned int new_leaf_weight; + unsigned int dev_leaf_weight; /* number of cfqq currently on this group */ int nr_cfqq; @@ -203,23 +282,25 @@ struct cfq_group { struct cfq_rb_root service_trees[2][3]; struct cfq_rb_root service_tree_idle; - unsigned long saved_workload_slice; - enum wl_type_t saved_workload; - enum wl_prio_t saved_serving_prio; - struct blkio_group blkg; -#ifdef CONFIG_CFQ_GROUP_IOSCHED - struct hlist_node cfqd_node; - int ref; -#endif + unsigned long saved_wl_slice; + enum wl_type_t saved_wl_type; + enum wl_class_t saved_wl_class; + /* number of requests that are on the dispatch list or inside driver */ int dispatched; struct cfq_ttime ttime; + struct cfqg_stats stats; /* stats for this cfqg */ + struct cfqg_stats dead_stats; /* stats pushed from dead children */ }; struct cfq_io_cq { struct io_cq icq; /* must be the first member */ struct cfq_queue *cfqq[2]; struct cfq_ttime ttime; + int ioprio; /* the current ioprio */ +#ifdef CONFIG_CFQ_GROUP_IOSCHED + uint64_t blkcg_id; /* the current blkcg ID */ +#endif }; /* @@ -229,13 +310,13 @@ struct cfq_data { struct request_queue *queue; /* Root service tree for cfq_groups */ struct cfq_rb_root grp_service_tree; - struct cfq_group root_group; + struct cfq_group *root_group; /* * The priority currently being served */ - enum wl_prio_t serving_prio; - enum wl_type_t serving_type; + enum wl_class_t serving_wl_class; + enum wl_type_t serving_wl_type; unsigned long workload_expires; struct cfq_group *serving_group; @@ -295,6 +376,7 @@ struct cfq_data { unsigned int cfq_slice_idle; unsigned int cfq_group_idle; unsigned int cfq_latency; + unsigned int cfq_target_latency; /* * Fallback dummy cfqq for extreme OOM conditions @@ -302,27 +384,21 @@ struct cfq_data { struct cfq_queue oom_cfqq; unsigned long last_delayed_sync; - - /* List of cfq groups being managed on this device*/ - struct hlist_head cfqg_list; - - /* Number of groups which are on blkcg->blkg_list */ - unsigned int nr_blkcg_linked_grps; }; static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd); -static struct cfq_rb_root *service_tree_for(struct cfq_group *cfqg, - enum wl_prio_t prio, +static struct cfq_rb_root *st_for(struct cfq_group *cfqg, + enum wl_class_t class, enum wl_type_t type) { if (!cfqg) return NULL; - if (prio == IDLE_WORKLOAD) + if (class == IDLE_WORKLOAD) return &cfqg->service_tree_idle; - return &cfqg->service_trees[prio][type]; + return &cfqg->service_trees[class][type]; } enum cfqq_state_flags { @@ -370,21 +446,337 @@ CFQ_CFQQ_FNS(deep); CFQ_CFQQ_FNS(wait_busy); #undef CFQ_CFQQ_FNS +static inline struct cfq_group *pd_to_cfqg(struct blkg_policy_data *pd) +{ + return pd ? container_of(pd, struct cfq_group, pd) : NULL; +} + +static inline struct blkcg_gq *cfqg_to_blkg(struct cfq_group *cfqg) +{ + return pd_to_blkg(&cfqg->pd); +} + +#if defined(CONFIG_CFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP) + +/* cfqg stats flags */ +enum cfqg_stats_flags { + CFQG_stats_waiting = 0, + CFQG_stats_idling, + CFQG_stats_empty, +}; + +#define CFQG_FLAG_FNS(name) \ +static inline void cfqg_stats_mark_##name(struct cfqg_stats *stats) \ +{ \ + stats->flags |= (1 << CFQG_stats_##name); \ +} \ +static inline void cfqg_stats_clear_##name(struct cfqg_stats *stats) \ +{ \ + stats->flags &= ~(1 << CFQG_stats_##name); \ +} \ +static inline int cfqg_stats_##name(struct cfqg_stats *stats) \ +{ \ + return (stats->flags & (1 << CFQG_stats_##name)) != 0; \ +} \ + +CFQG_FLAG_FNS(waiting) +CFQG_FLAG_FNS(idling) +CFQG_FLAG_FNS(empty) +#undef CFQG_FLAG_FNS + +/* This should be called with the queue_lock held. */ +static void cfqg_stats_update_group_wait_time(struct cfqg_stats *stats) +{ + unsigned long long now; + + if (!cfqg_stats_waiting(stats)) + return; + + now = sched_clock(); + if (time_after64(now, stats->start_group_wait_time)) + blkg_stat_add(&stats->group_wait_time, + now - stats->start_group_wait_time); + cfqg_stats_clear_waiting(stats); +} + +/* This should be called with the queue_lock held. */ +static void cfqg_stats_set_start_group_wait_time(struct cfq_group *cfqg, + struct cfq_group *curr_cfqg) +{ + struct cfqg_stats *stats = &cfqg->stats; + + if (cfqg_stats_waiting(stats)) + return; + if (cfqg == curr_cfqg) + return; + stats->start_group_wait_time = sched_clock(); + cfqg_stats_mark_waiting(stats); +} + +/* This should be called with the queue_lock held. */ +static void cfqg_stats_end_empty_time(struct cfqg_stats *stats) +{ + unsigned long long now; + + if (!cfqg_stats_empty(stats)) + return; + + now = sched_clock(); + if (time_after64(now, stats->start_empty_time)) + blkg_stat_add(&stats->empty_time, + now - stats->start_empty_time); + cfqg_stats_clear_empty(stats); +} + +static void cfqg_stats_update_dequeue(struct cfq_group *cfqg) +{ + blkg_stat_add(&cfqg->stats.dequeue, 1); +} + +static void cfqg_stats_set_start_empty_time(struct cfq_group *cfqg) +{ + struct cfqg_stats *stats = &cfqg->stats; + + if (blkg_rwstat_total(&stats->queued)) + return; + + /* + * group is already marked empty. This can happen if cfqq got new + * request in parent group and moved to this group while being added + * to service tree. Just ignore the event and move on. + */ + if (cfqg_stats_empty(stats)) + return; + + stats->start_empty_time = sched_clock(); + cfqg_stats_mark_empty(stats); +} + +static void cfqg_stats_update_idle_time(struct cfq_group *cfqg) +{ + struct cfqg_stats *stats = &cfqg->stats; + + if (cfqg_stats_idling(stats)) { + unsigned long long now = sched_clock(); + + if (time_after64(now, stats->start_idle_time)) + blkg_stat_add(&stats->idle_time, + now - stats->start_idle_time); + cfqg_stats_clear_idling(stats); + } +} + +static void cfqg_stats_set_start_idle_time(struct cfq_group *cfqg) +{ + struct cfqg_stats *stats = &cfqg->stats; + + BUG_ON(cfqg_stats_idling(stats)); + + stats->start_idle_time = sched_clock(); + cfqg_stats_mark_idling(stats); +} + +static void cfqg_stats_update_avg_queue_size(struct cfq_group *cfqg) +{ + struct cfqg_stats *stats = &cfqg->stats; + + blkg_stat_add(&stats->avg_queue_size_sum, + blkg_rwstat_total(&stats->queued)); + blkg_stat_add(&stats->avg_queue_size_samples, 1); + cfqg_stats_update_group_wait_time(stats); +} + +#else /* CONFIG_CFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */ + +static inline void cfqg_stats_set_start_group_wait_time(struct cfq_group *cfqg, struct cfq_group *curr_cfqg) { } +static inline void cfqg_stats_end_empty_time(struct cfqg_stats *stats) { } +static inline void cfqg_stats_update_dequeue(struct cfq_group *cfqg) { } +static inline void cfqg_stats_set_start_empty_time(struct cfq_group *cfqg) { } +static inline void cfqg_stats_update_idle_time(struct cfq_group *cfqg) { } +static inline void cfqg_stats_set_start_idle_time(struct cfq_group *cfqg) { } +static inline void cfqg_stats_update_avg_queue_size(struct cfq_group *cfqg) { } + +#endif /* CONFIG_CFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */ + #ifdef CONFIG_CFQ_GROUP_IOSCHED -#define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \ - blk_add_trace_msg((cfqd)->queue, "cfq%d%c %s " fmt, (cfqq)->pid, \ - cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \ - blkg_path(&(cfqq)->cfqg->blkg), ##args) -#define cfq_log_cfqg(cfqd, cfqg, fmt, args...) \ - blk_add_trace_msg((cfqd)->queue, "%s " fmt, \ - blkg_path(&(cfqg)->blkg), ##args) \ +static struct blkcg_policy blkcg_policy_cfq; + +static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg) +{ + return pd_to_cfqg(blkg_to_pd(blkg, &blkcg_policy_cfq)); +} + +static inline struct cfq_group *cfqg_parent(struct cfq_group *cfqg) +{ + struct blkcg_gq *pblkg = cfqg_to_blkg(cfqg)->parent; + + return pblkg ? blkg_to_cfqg(pblkg) : NULL; +} + +static inline void cfqg_get(struct cfq_group *cfqg) +{ + return blkg_get(cfqg_to_blkg(cfqg)); +} + +static inline void cfqg_put(struct cfq_group *cfqg) +{ + return blkg_put(cfqg_to_blkg(cfqg)); +} + +#define cfq_log_cfqq(cfqd, cfqq, fmt, args...) do { \ + char __pbuf[128]; \ + \ + blkg_path(cfqg_to_blkg((cfqq)->cfqg), __pbuf, sizeof(__pbuf)); \ + blk_add_trace_msg((cfqd)->queue, "cfq%d%c%c %s " fmt, (cfqq)->pid, \ + cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \ + cfqq_type((cfqq)) == SYNC_NOIDLE_WORKLOAD ? 'N' : ' ',\ + __pbuf, ##args); \ +} while (0) + +#define cfq_log_cfqg(cfqd, cfqg, fmt, args...) do { \ + char __pbuf[128]; \ + \ + blkg_path(cfqg_to_blkg(cfqg), __pbuf, sizeof(__pbuf)); \ + blk_add_trace_msg((cfqd)->queue, "%s " fmt, __pbuf, ##args); \ +} while (0) + +static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg, + struct cfq_group *curr_cfqg, int rw) +{ + blkg_rwstat_add(&cfqg->stats.queued, rw, 1); + cfqg_stats_end_empty_time(&cfqg->stats); + cfqg_stats_set_start_group_wait_time(cfqg, curr_cfqg); +} + +static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg, + unsigned long time, unsigned long unaccounted_time) +{ + blkg_stat_add(&cfqg->stats.time, time); +#ifdef CONFIG_DEBUG_BLK_CGROUP + blkg_stat_add(&cfqg->stats.unaccounted_time, unaccounted_time); +#endif +} + +static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int rw) +{ + blkg_rwstat_add(&cfqg->stats.queued, rw, -1); +} + +static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int rw) +{ + blkg_rwstat_add(&cfqg->stats.merged, rw, 1); +} + +static inline void cfqg_stats_update_dispatch(struct cfq_group *cfqg, + uint64_t bytes, int rw) +{ + blkg_stat_add(&cfqg->stats.sectors, bytes >> 9); + blkg_rwstat_add(&cfqg->stats.serviced, rw, 1); + blkg_rwstat_add(&cfqg->stats.service_bytes, rw, bytes); +} + +static inline void cfqg_stats_update_completion(struct cfq_group *cfqg, + uint64_t start_time, uint64_t io_start_time, int rw) +{ + struct cfqg_stats *stats = &cfqg->stats; + unsigned long long now = sched_clock(); + + if (time_after64(now, io_start_time)) + blkg_rwstat_add(&stats->service_time, rw, now - io_start_time); + if (time_after64(io_start_time, start_time)) + blkg_rwstat_add(&stats->wait_time, rw, + io_start_time - start_time); +} + +/* @stats = 0 */ +static void cfqg_stats_reset(struct cfqg_stats *stats) +{ + /* queued stats shouldn't be cleared */ + blkg_rwstat_reset(&stats->service_bytes); + blkg_rwstat_reset(&stats->serviced); + blkg_rwstat_reset(&stats->merged); + blkg_rwstat_reset(&stats->service_time); + blkg_rwstat_reset(&stats->wait_time); + blkg_stat_reset(&stats->time); +#ifdef CONFIG_DEBUG_BLK_CGROUP + blkg_stat_reset(&stats->unaccounted_time); + blkg_stat_reset(&stats->avg_queue_size_sum); + blkg_stat_reset(&stats->avg_queue_size_samples); + blkg_stat_reset(&stats->dequeue); + blkg_stat_reset(&stats->group_wait_time); + blkg_stat_reset(&stats->idle_time); + blkg_stat_reset(&stats->empty_time); +#endif +} + +/* @to += @from */ +static void cfqg_stats_merge(struct cfqg_stats *to, struct cfqg_stats *from) +{ + /* queued stats shouldn't be cleared */ + blkg_rwstat_merge(&to->service_bytes, &from->service_bytes); + blkg_rwstat_merge(&to->serviced, &from->serviced); + blkg_rwstat_merge(&to->merged, &from->merged); + blkg_rwstat_merge(&to->service_time, &from->service_time); + blkg_rwstat_merge(&to->wait_time, &from->wait_time); + blkg_stat_merge(&from->time, &from->time); +#ifdef CONFIG_DEBUG_BLK_CGROUP + blkg_stat_merge(&to->unaccounted_time, &from->unaccounted_time); + blkg_stat_merge(&to->avg_queue_size_sum, &from->avg_queue_size_sum); + blkg_stat_merge(&to->avg_queue_size_samples, &from->avg_queue_size_samples); + blkg_stat_merge(&to->dequeue, &from->dequeue); + blkg_stat_merge(&to->group_wait_time, &from->group_wait_time); + blkg_stat_merge(&to->idle_time, &from->idle_time); + blkg_stat_merge(&to->empty_time, &from->empty_time); +#endif +} + +/* + * Transfer @cfqg's stats to its parent's dead_stats so that the ancestors' + * recursive stats can still account for the amount used by this cfqg after + * it's gone. + */ +static void cfqg_stats_xfer_dead(struct cfq_group *cfqg) +{ + struct cfq_group *parent = cfqg_parent(cfqg); + + lockdep_assert_held(cfqg_to_blkg(cfqg)->q->queue_lock); + + if (unlikely(!parent)) + return; + + cfqg_stats_merge(&parent->dead_stats, &cfqg->stats); + cfqg_stats_merge(&parent->dead_stats, &cfqg->dead_stats); + cfqg_stats_reset(&cfqg->stats); + cfqg_stats_reset(&cfqg->dead_stats); +} + +#else /* CONFIG_CFQ_GROUP_IOSCHED */ + +static inline struct cfq_group *cfqg_parent(struct cfq_group *cfqg) { return NULL; } +static inline void cfqg_get(struct cfq_group *cfqg) { } +static inline void cfqg_put(struct cfq_group *cfqg) { } -#else #define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \ - blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args) + blk_add_trace_msg((cfqd)->queue, "cfq%d%c%c " fmt, (cfqq)->pid, \ + cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \ + cfqq_type((cfqq)) == SYNC_NOIDLE_WORKLOAD ? 'N' : ' ',\ + ##args) #define cfq_log_cfqg(cfqd, cfqg, fmt, args...) do {} while (0) -#endif + +static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg, + struct cfq_group *curr_cfqg, int rw) { } +static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg, + unsigned long time, unsigned long unaccounted_time) { } +static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int rw) { } +static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int rw) { } +static inline void cfqg_stats_update_dispatch(struct cfq_group *cfqg, + uint64_t bytes, int rw) { } +static inline void cfqg_stats_update_completion(struct cfq_group *cfqg, + uint64_t start_time, uint64_t io_start_time, int rw) { } + +#endif /* CONFIG_CFQ_GROUP_IOSCHED */ + #define cfq_log(cfqd, fmt, args...) \ blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args) @@ -426,7 +818,7 @@ static inline bool iops_mode(struct cfq_data *cfqd) return false; } -static inline enum wl_prio_t cfqq_prio(struct cfq_queue *cfqq) +static inline enum wl_class_t cfqq_class(struct cfq_queue *cfqq) { if (cfq_class_idle(cfqq)) return IDLE_WORKLOAD; @@ -445,28 +837,29 @@ static enum wl_type_t cfqq_type(struct cfq_queue *cfqq) return SYNC_WORKLOAD; } -static inline int cfq_group_busy_queues_wl(enum wl_prio_t wl, +static inline int cfq_group_busy_queues_wl(enum wl_class_t wl_class, struct cfq_data *cfqd, struct cfq_group *cfqg) { - if (wl == IDLE_WORKLOAD) + if (wl_class == IDLE_WORKLOAD) return cfqg->service_tree_idle.count; - return cfqg->service_trees[wl][ASYNC_WORKLOAD].count - + cfqg->service_trees[wl][SYNC_NOIDLE_WORKLOAD].count - + cfqg->service_trees[wl][SYNC_WORKLOAD].count; + return cfqg->service_trees[wl_class][ASYNC_WORKLOAD].count + + cfqg->service_trees[wl_class][SYNC_NOIDLE_WORKLOAD].count + + cfqg->service_trees[wl_class][SYNC_WORKLOAD].count; } static inline int cfqg_busy_async_queues(struct cfq_data *cfqd, struct cfq_group *cfqg) { - return cfqg->service_trees[RT_WORKLOAD][ASYNC_WORKLOAD].count - + cfqg->service_trees[BE_WORKLOAD][ASYNC_WORKLOAD].count; + return cfqg->service_trees[RT_WORKLOAD][ASYNC_WORKLOAD].count + + cfqg->service_trees[BE_WORKLOAD][ASYNC_WORKLOAD].count; } static void cfq_dispatch_insert(struct request_queue *, struct request *); -static struct cfq_queue *cfq_get_queue(struct cfq_data *, bool, - struct io_context *, gfp_t); +static struct cfq_queue *cfq_get_queue(struct cfq_data *cfqd, bool is_sync, + struct cfq_io_cq *cic, struct bio *bio, + gfp_t gfp_mask); static inline struct cfq_io_cq *icq_to_cic(struct io_cq *icq) { @@ -515,7 +908,7 @@ static inline void cfq_schedule_dispatch(struct cfq_data *cfqd) { if (cfqd->busy_queues) { cfq_log(cfqd, "schedule dispatch"); - kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work); + kblockd_schedule_work(&cfqd->unplug_work); } } @@ -540,13 +933,27 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq) return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio); } -static inline u64 cfq_scale_slice(unsigned long delta, struct cfq_group *cfqg) +/** + * cfqg_scale_charge - scale disk time charge according to cfqg weight + * @charge: disk time being charged + * @vfraction: vfraction of the cfqg, fixed point w/ CFQ_SERVICE_SHIFT + * + * Scale @charge according to @vfraction, which is in range (0, 1]. The + * scaling is inversely proportional. + * + * scaled = charge / vfraction + * + * The result is also in fixed point w/ CFQ_SERVICE_SHIFT. + */ +static inline u64 cfqg_scale_charge(unsigned long charge, + unsigned int vfraction) { - u64 d = delta << CFQ_SERVICE_SHIFT; + u64 c = charge << CFQ_SERVICE_SHIFT; /* make it fixed point */ - d = d * BLKIO_WEIGHT_DEFAULT; - do_div(d, cfqg->weight); - return d; + /* charge / vfraction */ + c <<= CFQ_SERVICE_SHIFT; + do_div(c, vfraction); + return c; } static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime) @@ -602,9 +1009,7 @@ static inline unsigned cfq_group_get_avg_queues(struct cfq_data *cfqd, static inline unsigned cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg) { - struct cfq_rb_root *st = &cfqd->grp_service_tree; - - return cfq_target_latency * cfqg->weight / st->total_weight; + return cfqd->cfq_target_latency * cfqg->vfraction >> CFQ_SERVICE_SHIFT; } static inline unsigned @@ -871,20 +1276,61 @@ static void cfq_update_group_weight(struct cfq_group *cfqg) { BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node)); - if (cfqg->needs_update) { + + if (cfqg->new_weight) { cfqg->weight = cfqg->new_weight; - cfqg->needs_update = false; + cfqg->new_weight = 0; + } + + if (cfqg->new_leaf_weight) { + cfqg->leaf_weight = cfqg->new_leaf_weight; + cfqg->new_leaf_weight = 0; } } static void cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg) { + unsigned int vfr = 1 << CFQ_SERVICE_SHIFT; /* start with 1 */ + struct cfq_group *pos = cfqg; + struct cfq_group *parent; + bool propagate; + + /* add to the service tree */ BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node)); cfq_update_group_weight(cfqg); __cfq_group_service_tree_add(st, cfqg); - st->total_weight += cfqg->weight; + + /* + * Activate @cfqg and calculate the portion of vfraction @cfqg is + * entitled to. vfraction is calculated by walking the tree + * towards the root calculating the fraction it has at each level. + * The compounded ratio is how much vfraction @cfqg owns. + * + * Start with the proportion tasks in this cfqg has against active + * children cfqgs - its leaf_weight against children_weight. + */ + propagate = !pos->nr_active++; + pos->children_weight += pos->leaf_weight; + vfr = vfr * pos->leaf_weight / pos->children_weight; + + /* + * Compound ->weight walking up the tree. Both activation and + * vfraction calculation are done in the same loop. Propagation + * stops once an already activated node is met. vfraction + * calculation should always continue to the root. + */ + while ((parent = cfqg_parent(pos))) { + if (propagate) { + propagate = !parent->nr_active++; + parent->children_weight += pos->weight; + } + vfr = vfr * pos->weight / parent->children_weight; + pos = parent; + } + + cfqg->vfraction = max_t(unsigned, vfr, 1); } static void @@ -915,7 +1361,32 @@ cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg) static void cfq_group_service_tree_del(struct cfq_rb_root *st, struct cfq_group *cfqg) { - st->total_weight -= cfqg->weight; + struct cfq_group *pos = cfqg; + bool propagate; + + /* + * Undo activation from cfq_group_service_tree_add(). Deactivate + * @cfqg and propagate deactivation upwards. + */ + propagate = !--pos->nr_active; + pos->children_weight -= pos->leaf_weight; + + while (propagate) { + struct cfq_group *parent = cfqg_parent(pos); + + /* @pos has 0 nr_active at this point */ + WARN_ON_ONCE(pos->children_weight); + pos->vfraction = 0; + + if (!parent) + break; + + propagate = !--parent->nr_active; + parent->children_weight -= pos->weight; + pos = parent; + } + + /* remove from the service tree */ if (!RB_EMPTY_NODE(&cfqg->rb_node)) cfq_rb_erase(&cfqg->rb_node, st); } @@ -934,8 +1405,8 @@ cfq_group_notify_queue_del(struct cfq_data *cfqd, struct cfq_group *cfqg) cfq_log_cfqg(cfqd, cfqg, "del_from_rr group"); cfq_group_service_tree_del(st, cfqg); - cfqg->saved_workload_slice = 0; - cfq_blkiocg_update_dequeue_stats(&cfqg->blkg, 1); + cfqg->saved_wl_slice = 0; + cfqg_stats_update_dequeue(cfqg); } static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq, @@ -977,6 +1448,7 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg, unsigned int used_sl, charge, unaccounted_sl = 0; int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg) - cfqg->service_tree_idle.count; + unsigned int vfr; BUG_ON(nr_sync < 0); used_sl = charge = cfq_cfqq_slice_usage(cfqq, &unaccounted_sl); @@ -986,20 +1458,25 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg, else if (!cfq_cfqq_sync(cfqq) && !nr_sync) charge = cfqq->allocated_slice; - /* Can't update vdisktime while group is on service tree */ + /* + * Can't update vdisktime while on service tree and cfqg->vfraction + * is valid only while on it. Cache vfr, leave the service tree, + * update vdisktime and go back on. The re-addition to the tree + * will also update the weights as necessary. + */ + vfr = cfqg->vfraction; cfq_group_service_tree_del(st, cfqg); - cfqg->vdisktime += cfq_scale_slice(charge, cfqg); - /* If a new weight was requested, update now, off tree */ + cfqg->vdisktime += cfqg_scale_charge(charge, vfr); cfq_group_service_tree_add(st, cfqg); /* This group is being expired. Save the context */ if (time_after(cfqd->workload_expires, jiffies)) { - cfqg->saved_workload_slice = cfqd->workload_expires + cfqg->saved_wl_slice = cfqd->workload_expires - jiffies; - cfqg->saved_workload = cfqd->serving_type; - cfqg->saved_serving_prio = cfqd->serving_prio; + cfqg->saved_wl_type = cfqd->serving_wl_type; + cfqg->saved_wl_class = cfqd->serving_wl_class; } else - cfqg->saved_workload_slice = 0; + cfqg->saved_wl_slice = 0; cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime, st->min_vdisktime); @@ -1007,273 +1484,514 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg, "sl_used=%u disp=%u charge=%u iops=%u sect=%lu", used_sl, cfqq->slice_dispatch, charge, iops_mode(cfqd), cfqq->nr_sectors); - cfq_blkiocg_update_timeslice_used(&cfqg->blkg, used_sl, - unaccounted_sl); - cfq_blkiocg_set_start_empty_time(&cfqg->blkg); + cfqg_stats_update_timeslice_used(cfqg, used_sl, unaccounted_sl); + cfqg_stats_set_start_empty_time(cfqg); } -#ifdef CONFIG_CFQ_GROUP_IOSCHED -static inline struct cfq_group *cfqg_of_blkg(struct blkio_group *blkg) +/** + * cfq_init_cfqg_base - initialize base part of a cfq_group + * @cfqg: cfq_group to initialize + * + * Initialize the base part which is used whether %CONFIG_CFQ_GROUP_IOSCHED + * is enabled or not. + */ +static void cfq_init_cfqg_base(struct cfq_group *cfqg) { - if (blkg) - return container_of(blkg, struct cfq_group, blkg); - return NULL; + struct cfq_rb_root *st; + int i, j; + + for_each_cfqg_st(cfqg, i, j, st) + *st = CFQ_RB_ROOT; + RB_CLEAR_NODE(&cfqg->rb_node); + + cfqg->ttime.last_end_request = jiffies; } -static void cfq_update_blkio_group_weight(void *key, struct blkio_group *blkg, - unsigned int weight) -{ - struct cfq_group *cfqg = cfqg_of_blkg(blkg); - cfqg->new_weight = weight; - cfqg->needs_update = true; +#ifdef CONFIG_CFQ_GROUP_IOSCHED +static void cfqg_stats_init(struct cfqg_stats *stats) +{ + blkg_rwstat_init(&stats->service_bytes); + blkg_rwstat_init(&stats->serviced); + blkg_rwstat_init(&stats->merged); + blkg_rwstat_init(&stats->service_time); + blkg_rwstat_init(&stats->wait_time); + blkg_rwstat_init(&stats->queued); + + blkg_stat_init(&stats->sectors); + blkg_stat_init(&stats->time); + +#ifdef CONFIG_DEBUG_BLK_CGROUP + blkg_stat_init(&stats->unaccounted_time); + blkg_stat_init(&stats->avg_queue_size_sum); + blkg_stat_init(&stats->avg_queue_size_samples); + blkg_stat_init(&stats->dequeue); + blkg_stat_init(&stats->group_wait_time); + blkg_stat_init(&stats->idle_time); + blkg_stat_init(&stats->empty_time); +#endif } -static void cfq_init_add_cfqg_lists(struct cfq_data *cfqd, - struct cfq_group *cfqg, struct blkio_cgroup *blkcg) +static void cfq_pd_init(struct blkcg_gq *blkg) { - struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info; - unsigned int major, minor; + struct cfq_group *cfqg = blkg_to_cfqg(blkg); + + cfq_init_cfqg_base(cfqg); + cfqg->weight = blkg->blkcg->cfq_weight; + cfqg->leaf_weight = blkg->blkcg->cfq_leaf_weight; + cfqg_stats_init(&cfqg->stats); + cfqg_stats_init(&cfqg->dead_stats); +} +static void cfq_pd_offline(struct blkcg_gq *blkg) +{ /* - * Add group onto cgroup list. It might happen that bdi->dev is - * not initialized yet. Initialize this new group without major - * and minor info and this info will be filled in once a new thread - * comes for IO. + * @blkg is going offline and will be ignored by + * blkg_[rw]stat_recursive_sum(). Transfer stats to the parent so + * that they don't get lost. If IOs complete after this point, the + * stats for them will be lost. Oh well... */ - if (bdi->dev) { - sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor); - cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, - (void *)cfqd, MKDEV(major, minor)); - } else - cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, - (void *)cfqd, 0); + cfqg_stats_xfer_dead(blkg_to_cfqg(blkg)); +} - cfqd->nr_blkcg_linked_grps++; - cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev); +/* offset delta from cfqg->stats to cfqg->dead_stats */ +static const int dead_stats_off_delta = offsetof(struct cfq_group, dead_stats) - + offsetof(struct cfq_group, stats); - /* Add group on cfqd list */ - hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list); +/* to be used by recursive prfill, sums live and dead stats recursively */ +static u64 cfqg_stat_pd_recursive_sum(struct blkg_policy_data *pd, int off) +{ + u64 sum = 0; + + sum += blkg_stat_recursive_sum(pd, off); + sum += blkg_stat_recursive_sum(pd, off + dead_stats_off_delta); + return sum; } -/* - * Should be called from sleepable context. No request queue lock as per - * cpu stats are allocated dynamically and alloc_percpu needs to be called - * from sleepable context. - */ -static struct cfq_group * cfq_alloc_cfqg(struct cfq_data *cfqd) +/* to be used by recursive prfill, sums live and dead rwstats recursively */ +static struct blkg_rwstat cfqg_rwstat_pd_recursive_sum(struct blkg_policy_data *pd, + int off) { - struct cfq_group *cfqg = NULL; - int i, j, ret; - struct cfq_rb_root *st; + struct blkg_rwstat a, b; - cfqg = kzalloc_node(sizeof(*cfqg), GFP_ATOMIC, cfqd->queue->node); - if (!cfqg) - return NULL; + a = blkg_rwstat_recursive_sum(pd, off); + b = blkg_rwstat_recursive_sum(pd, off + dead_stats_off_delta); + blkg_rwstat_merge(&a, &b); + return a; +} - for_each_cfqg_st(cfqg, i, j, st) - *st = CFQ_RB_ROOT; - RB_CLEAR_NODE(&cfqg->rb_node); +static void cfq_pd_reset_stats(struct blkcg_gq *blkg) +{ + struct cfq_group *cfqg = blkg_to_cfqg(blkg); - cfqg->ttime.last_end_request = jiffies; + cfqg_stats_reset(&cfqg->stats); + cfqg_stats_reset(&cfqg->dead_stats); +} - /* - * Take the initial reference that will be released on destroy - * This can be thought of a joint reference by cgroup and - * elevator which will be dropped by either elevator exit - * or cgroup deletion path depending on who is exiting first. - */ - cfqg->ref = 1; +/* + * Search for the cfq group current task belongs to. request_queue lock must + * be held. + */ +static struct cfq_group *cfq_lookup_create_cfqg(struct cfq_data *cfqd, + struct blkcg *blkcg) +{ + struct request_queue *q = cfqd->queue; + struct cfq_group *cfqg = NULL; - ret = blkio_alloc_blkg_stats(&cfqg->blkg); - if (ret) { - kfree(cfqg); - return NULL; + /* avoid lookup for the common case where there's no blkcg */ + if (blkcg == &blkcg_root) { + cfqg = cfqd->root_group; + } else { + struct blkcg_gq *blkg; + + blkg = blkg_lookup_create(blkcg, q); + if (!IS_ERR(blkg)) + cfqg = blkg_to_cfqg(blkg); } return cfqg; } -static struct cfq_group * -cfq_find_cfqg(struct cfq_data *cfqd, struct blkio_cgroup *blkcg) +static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) { - struct cfq_group *cfqg = NULL; - void *key = cfqd; - struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info; - unsigned int major, minor; + /* Currently, all async queues are mapped to root group */ + if (!cfq_cfqq_sync(cfqq)) + cfqg = cfqq->cfqd->root_group; - /* - * This is the common case when there are no blkio cgroups. - * Avoid lookup in this case - */ - if (blkcg == &blkio_root_cgroup) - cfqg = &cfqd->root_group; - else - cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key)); + cfqq->cfqg = cfqg; + /* cfqq reference on cfqg */ + cfqg_get(cfqg); +} - if (cfqg && !cfqg->blkg.dev && bdi->dev && dev_name(bdi->dev)) { - sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor); - cfqg->blkg.dev = MKDEV(major, minor); - } +static u64 cfqg_prfill_weight_device(struct seq_file *sf, + struct blkg_policy_data *pd, int off) +{ + struct cfq_group *cfqg = pd_to_cfqg(pd); - return cfqg; + if (!cfqg->dev_weight) + return 0; + return __blkg_prfill_u64(sf, pd, cfqg->dev_weight); } -/* - * Search for the cfq group current task belongs to. request_queue lock must - * be held. - */ -static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd) +static int cfqg_print_weight_device(struct seq_file *sf, void *v) { - struct blkio_cgroup *blkcg; - struct cfq_group *cfqg = NULL, *__cfqg = NULL; - struct request_queue *q = cfqd->queue; + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + cfqg_prfill_weight_device, &blkcg_policy_cfq, + 0, false); + return 0; +} - rcu_read_lock(); - blkcg = task_blkio_cgroup(current); - cfqg = cfq_find_cfqg(cfqd, blkcg); - if (cfqg) { - rcu_read_unlock(); - return cfqg; - } +static u64 cfqg_prfill_leaf_weight_device(struct seq_file *sf, + struct blkg_policy_data *pd, int off) +{ + struct cfq_group *cfqg = pd_to_cfqg(pd); - /* - * Need to allocate a group. Allocation of group also needs allocation - * of per cpu stats which in-turn takes a mutex() and can block. Hence - * we need to drop rcu lock and queue_lock before we call alloc. - * - * Not taking any queue reference here and assuming that queue is - * around by the time we return. CFQ queue allocation code does - * the same. It might be racy though. - */ + if (!cfqg->dev_leaf_weight) + return 0; + return __blkg_prfill_u64(sf, pd, cfqg->dev_leaf_weight); +} - rcu_read_unlock(); - spin_unlock_irq(q->queue_lock); +static int cfqg_print_leaf_weight_device(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + cfqg_prfill_leaf_weight_device, &blkcg_policy_cfq, + 0, false); + return 0; +} - cfqg = cfq_alloc_cfqg(cfqd); +static int cfq_print_weight(struct seq_file *sf, void *v) +{ + seq_printf(sf, "%u\n", css_to_blkcg(seq_css(sf))->cfq_weight); + return 0; +} - spin_lock_irq(q->queue_lock); +static int cfq_print_leaf_weight(struct seq_file *sf, void *v) +{ + seq_printf(sf, "%u\n", css_to_blkcg(seq_css(sf))->cfq_leaf_weight); + return 0; +} - rcu_read_lock(); - blkcg = task_blkio_cgroup(current); +static ssize_t __cfqg_set_weight_device(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off, + bool is_leaf_weight) +{ + struct blkcg *blkcg = css_to_blkcg(of_css(of)); + struct blkg_conf_ctx ctx; + struct cfq_group *cfqg; + int ret; - /* - * If some other thread already allocated the group while we were - * not holding queue lock, free up the group - */ - __cfqg = cfq_find_cfqg(cfqd, blkcg); + ret = blkg_conf_prep(blkcg, &blkcg_policy_cfq, buf, &ctx); + if (ret) + return ret; - if (__cfqg) { - kfree(cfqg); - rcu_read_unlock(); - return __cfqg; + ret = -EINVAL; + cfqg = blkg_to_cfqg(ctx.blkg); + if (!ctx.v || (ctx.v >= CFQ_WEIGHT_MIN && ctx.v <= CFQ_WEIGHT_MAX)) { + if (!is_leaf_weight) { + cfqg->dev_weight = ctx.v; + cfqg->new_weight = ctx.v ?: blkcg->cfq_weight; + } else { + cfqg->dev_leaf_weight = ctx.v; + cfqg->new_leaf_weight = ctx.v ?: blkcg->cfq_leaf_weight; + } + ret = 0; } - if (!cfqg) - cfqg = &cfqd->root_group; + blkg_conf_finish(&ctx); + return ret ?: nbytes; +} - cfq_init_add_cfqg_lists(cfqd, cfqg, blkcg); - rcu_read_unlock(); - return cfqg; +static ssize_t cfqg_set_weight_device(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return __cfqg_set_weight_device(of, buf, nbytes, off, false); } -static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg) +static ssize_t cfqg_set_leaf_weight_device(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { - cfqg->ref++; - return cfqg; + return __cfqg_set_weight_device(of, buf, nbytes, off, true); } -static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) +static int __cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val, bool is_leaf_weight) { - /* Currently, all async queues are mapped to root group */ - if (!cfq_cfqq_sync(cfqq)) - cfqg = &cfqq->cfqd->root_group; + struct blkcg *blkcg = css_to_blkcg(css); + struct blkcg_gq *blkg; - cfqq->cfqg = cfqg; - /* cfqq reference on cfqg */ - cfqq->cfqg->ref++; + if (val < CFQ_WEIGHT_MIN || val > CFQ_WEIGHT_MAX) + return -EINVAL; + + spin_lock_irq(&blkcg->lock); + + if (!is_leaf_weight) + blkcg->cfq_weight = val; + else + blkcg->cfq_leaf_weight = val; + + hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { + struct cfq_group *cfqg = blkg_to_cfqg(blkg); + + if (!cfqg) + continue; + + if (!is_leaf_weight) { + if (!cfqg->dev_weight) + cfqg->new_weight = blkcg->cfq_weight; + } else { + if (!cfqg->dev_leaf_weight) + cfqg->new_leaf_weight = blkcg->cfq_leaf_weight; + } + } + + spin_unlock_irq(&blkcg->lock); + return 0; } -static void cfq_put_cfqg(struct cfq_group *cfqg) +static int cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val) { - struct cfq_rb_root *st; - int i, j; + return __cfq_set_weight(css, cft, val, false); +} - BUG_ON(cfqg->ref <= 0); - cfqg->ref--; - if (cfqg->ref) - return; - for_each_cfqg_st(cfqg, i, j, st) - BUG_ON(!RB_EMPTY_ROOT(&st->rb)); - free_percpu(cfqg->blkg.stats_cpu); - kfree(cfqg); +static int cfq_set_leaf_weight(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) +{ + return __cfq_set_weight(css, cft, val, true); } -static void cfq_destroy_cfqg(struct cfq_data *cfqd, struct cfq_group *cfqg) +static int cfqg_print_stat(struct seq_file *sf, void *v) { - /* Something wrong if we are trying to remove same group twice */ - BUG_ON(hlist_unhashed(&cfqg->cfqd_node)); + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat, + &blkcg_policy_cfq, seq_cft(sf)->private, false); + return 0; +} - hlist_del_init(&cfqg->cfqd_node); +static int cfqg_print_rwstat(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat, + &blkcg_policy_cfq, seq_cft(sf)->private, true); + return 0; +} - BUG_ON(cfqd->nr_blkcg_linked_grps <= 0); - cfqd->nr_blkcg_linked_grps--; +static u64 cfqg_prfill_stat_recursive(struct seq_file *sf, + struct blkg_policy_data *pd, int off) +{ + u64 sum = cfqg_stat_pd_recursive_sum(pd, off); - /* - * Put the reference taken at the time of creation so that when all - * queues are gone, group can be destroyed. - */ - cfq_put_cfqg(cfqg); + return __blkg_prfill_u64(sf, pd, sum); } -static void cfq_release_cfq_groups(struct cfq_data *cfqd) +static u64 cfqg_prfill_rwstat_recursive(struct seq_file *sf, + struct blkg_policy_data *pd, int off) { - struct hlist_node *pos, *n; - struct cfq_group *cfqg; + struct blkg_rwstat sum = cfqg_rwstat_pd_recursive_sum(pd, off); - hlist_for_each_entry_safe(cfqg, pos, n, &cfqd->cfqg_list, cfqd_node) { - /* - * If cgroup removal path got to blk_group first and removed - * it from cgroup list, then it will take care of destroying - * cfqg also. - */ - if (!cfq_blkiocg_del_blkio_group(&cfqg->blkg)) - cfq_destroy_cfqg(cfqd, cfqg); - } + return __blkg_prfill_rwstat(sf, pd, &sum); } -/* - * Blk cgroup controller notification saying that blkio_group object is being - * delinked as associated cgroup object is going away. That also means that - * no new IO will come in this group. So get rid of this group as soon as - * any pending IO in the group is finished. - * - * This function is called under rcu_read_lock(). key is the rcu protected - * pointer. That means "key" is a valid cfq_data pointer as long as we are rcu - * read lock. - * - * "key" was fetched from blkio_group under blkio_cgroup->lock. That means - * it should not be NULL as even if elevator was exiting, cgroup deltion - * path got to it first. - */ -static void cfq_unlink_blkio_group(void *key, struct blkio_group *blkg) +static int cfqg_print_stat_recursive(struct seq_file *sf, void *v) { - unsigned long flags; - struct cfq_data *cfqd = key; + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + cfqg_prfill_stat_recursive, &blkcg_policy_cfq, + seq_cft(sf)->private, false); + return 0; +} - spin_lock_irqsave(cfqd->queue->queue_lock, flags); - cfq_destroy_cfqg(cfqd, cfqg_of_blkg(blkg)); - spin_unlock_irqrestore(cfqd->queue->queue_lock, flags); +static int cfqg_print_rwstat_recursive(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + cfqg_prfill_rwstat_recursive, &blkcg_policy_cfq, + seq_cft(sf)->private, true); + return 0; } -#else /* GROUP_IOSCHED */ -static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd) +#ifdef CONFIG_DEBUG_BLK_CGROUP +static u64 cfqg_prfill_avg_queue_size(struct seq_file *sf, + struct blkg_policy_data *pd, int off) { - return &cfqd->root_group; + struct cfq_group *cfqg = pd_to_cfqg(pd); + u64 samples = blkg_stat_read(&cfqg->stats.avg_queue_size_samples); + u64 v = 0; + + if (samples) { + v = blkg_stat_read(&cfqg->stats.avg_queue_size_sum); + v = div64_u64(v, samples); + } + __blkg_prfill_u64(sf, pd, v); + return 0; } -static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg) +/* print avg_queue_size */ +static int cfqg_print_avg_queue_size(struct seq_file *sf, void *v) { - return cfqg; + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + cfqg_prfill_avg_queue_size, &blkcg_policy_cfq, + 0, false); + return 0; +} +#endif /* CONFIG_DEBUG_BLK_CGROUP */ + +static struct cftype cfq_blkcg_files[] = { + /* on root, weight is mapped to leaf_weight */ + { + .name = "weight_device", + .flags = CFTYPE_ONLY_ON_ROOT, + .seq_show = cfqg_print_leaf_weight_device, + .write = cfqg_set_leaf_weight_device, + }, + { + .name = "weight", + .flags = CFTYPE_ONLY_ON_ROOT, + .seq_show = cfq_print_leaf_weight, + .write_u64 = cfq_set_leaf_weight, + }, + + /* no such mapping necessary for !roots */ + { + .name = "weight_device", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cfqg_print_weight_device, + .write = cfqg_set_weight_device, + }, + { + .name = "weight", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cfq_print_weight, + .write_u64 = cfq_set_weight, + }, + + { + .name = "leaf_weight_device", + .seq_show = cfqg_print_leaf_weight_device, + .write = cfqg_set_leaf_weight_device, + }, + { + .name = "leaf_weight", + .seq_show = cfq_print_leaf_weight, + .write_u64 = cfq_set_leaf_weight, + }, + + /* statistics, covers only the tasks in the cfqg */ + { + .name = "time", + .private = offsetof(struct cfq_group, stats.time), + .seq_show = cfqg_print_stat, + }, + { + .name = "sectors", + .private = offsetof(struct cfq_group, stats.sectors), + .seq_show = cfqg_print_stat, + }, + { + .name = "io_service_bytes", + .private = offsetof(struct cfq_group, stats.service_bytes), + .seq_show = cfqg_print_rwstat, + }, + { + .name = "io_serviced", + .private = offsetof(struct cfq_group, stats.serviced), + .seq_show = cfqg_print_rwstat, + }, + { + .name = "io_service_time", + .private = offsetof(struct cfq_group, stats.service_time), + .seq_show = cfqg_print_rwstat, + }, + { + .name = "io_wait_time", + .private = offsetof(struct cfq_group, stats.wait_time), + .seq_show = cfqg_print_rwstat, + }, + { + .name = "io_merged", + .private = offsetof(struct cfq_group, stats.merged), + .seq_show = cfqg_print_rwstat, + }, + { + .name = "io_queued", + .private = offsetof(struct cfq_group, stats.queued), + .seq_show = cfqg_print_rwstat, + }, + + /* the same statictics which cover the cfqg and its descendants */ + { + .name = "time_recursive", + .private = offsetof(struct cfq_group, stats.time), + .seq_show = cfqg_print_stat_recursive, + }, + { + .name = "sectors_recursive", + .private = offsetof(struct cfq_group, stats.sectors), + .seq_show = cfqg_print_stat_recursive, + }, + { + .name = "io_service_bytes_recursive", + .private = offsetof(struct cfq_group, stats.service_bytes), + .seq_show = cfqg_print_rwstat_recursive, + }, + { + .name = "io_serviced_recursive", + .private = offsetof(struct cfq_group, stats.serviced), + .seq_show = cfqg_print_rwstat_recursive, + }, + { + .name = "io_service_time_recursive", + .private = offsetof(struct cfq_group, stats.service_time), + .seq_show = cfqg_print_rwstat_recursive, + }, + { + .name = "io_wait_time_recursive", + .private = offsetof(struct cfq_group, stats.wait_time), + .seq_show = cfqg_print_rwstat_recursive, + }, + { + .name = "io_merged_recursive", + .private = offsetof(struct cfq_group, stats.merged), + .seq_show = cfqg_print_rwstat_recursive, + }, + { + .name = "io_queued_recursive", + .private = offsetof(struct cfq_group, stats.queued), + .seq_show = cfqg_print_rwstat_recursive, + }, +#ifdef CONFIG_DEBUG_BLK_CGROUP + { + .name = "avg_queue_size", + .seq_show = cfqg_print_avg_queue_size, + }, + { + .name = "group_wait_time", + .private = offsetof(struct cfq_group, stats.group_wait_time), + .seq_show = cfqg_print_stat, + }, + { + .name = "idle_time", + .private = offsetof(struct cfq_group, stats.idle_time), + .seq_show = cfqg_print_stat, + }, + { + .name = "empty_time", + .private = offsetof(struct cfq_group, stats.empty_time), + .seq_show = cfqg_print_stat, + }, + { + .name = "dequeue", + .private = offsetof(struct cfq_group, stats.dequeue), + .seq_show = cfqg_print_stat, + }, + { + .name = "unaccounted_time", + .private = offsetof(struct cfq_group, stats.unaccounted_time), + .seq_show = cfqg_print_stat, + }, +#endif /* CONFIG_DEBUG_BLK_CGROUP */ + { } /* terminate */ +}; +#else /* GROUP_IOSCHED */ +static struct cfq_group *cfq_lookup_create_cfqg(struct cfq_data *cfqd, + struct blkcg *blkcg) +{ + return cfqd->root_group; } static inline void @@ -1281,9 +1999,6 @@ cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) { cfqq->cfqg = cfqg; } -static void cfq_release_cfq_groups(struct cfq_data *cfqd) {} -static inline void cfq_put_cfqg(struct cfq_group *cfqg) {} - #endif /* GROUP_IOSCHED */ /* @@ -1297,15 +2012,14 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, struct rb_node **p, *parent; struct cfq_queue *__cfqq; unsigned long rb_key; - struct cfq_rb_root *service_tree; + struct cfq_rb_root *st; int left; int new_cfqq = 1; - service_tree = service_tree_for(cfqq->cfqg, cfqq_prio(cfqq), - cfqq_type(cfqq)); + st = st_for(cfqq->cfqg, cfqq_class(cfqq), cfqq_type(cfqq)); if (cfq_class_idle(cfqq)) { rb_key = CFQ_IDLE_DELAY; - parent = rb_last(&service_tree->rb); + parent = rb_last(&st->rb); if (parent && parent != &cfqq->rb_node) { __cfqq = rb_entry(parent, struct cfq_queue, rb_node); rb_key += __cfqq->rb_key; @@ -1323,7 +2037,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfqq->slice_resid = 0; } else { rb_key = -HZ; - __cfqq = cfq_rb_first(service_tree); + __cfqq = cfq_rb_first(st); rb_key += __cfqq ? __cfqq->rb_key : jiffies; } @@ -1332,8 +2046,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, /* * same position, nothing more to do */ - if (rb_key == cfqq->rb_key && - cfqq->service_tree == service_tree) + if (rb_key == cfqq->rb_key && cfqq->service_tree == st) return; cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree); @@ -1342,11 +2055,9 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, left = 1; parent = NULL; - cfqq->service_tree = service_tree; - p = &service_tree->rb.rb_node; + cfqq->service_tree = st; + p = &st->rb.rb_node; while (*p) { - struct rb_node **n; - parent = *p; __cfqq = rb_entry(parent, struct cfq_queue, rb_node); @@ -1354,22 +2065,20 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, * sort by key, that represents service time. */ if (time_before(rb_key, __cfqq->rb_key)) - n = &(*p)->rb_left; + p = &parent->rb_left; else { - n = &(*p)->rb_right; + p = &parent->rb_right; left = 0; } - - p = n; } if (left) - service_tree->left = &cfqq->rb_node; + st->left = &cfqq->rb_node; cfqq->rb_key = rb_key; rb_link_node(&cfqq->rb_node, parent, p); - rb_insert_color(&cfqq->rb_node, &service_tree->rb); - service_tree->count++; + rb_insert_color(&cfqq->rb_node, &st->rb); + st->count++; if (add_front || !new_cfqq) return; cfq_group_notify_queue_add(cfqd, cfqq->cfqg); @@ -1550,12 +2259,10 @@ static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq) { elv_rb_del(&cfqq->sort_list, rq); cfqq->queued[rq_is_sync(rq)]--; - cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg, - rq_data_dir(rq), rq_is_sync(rq)); + cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags); cfq_add_rq_rb(rq); - cfq_blkiocg_update_io_add_stats(&(RQ_CFQG(rq))->blkg, - &cfqq->cfqd->serving_group->blkg, rq_data_dir(rq), - rq_is_sync(rq)); + cfqg_stats_update_io_add(RQ_CFQG(rq), cfqq->cfqd->serving_group, + rq->cmd_flags); } static struct request * @@ -1570,11 +2277,8 @@ cfq_find_rq_fmerge(struct cfq_data *cfqd, struct bio *bio) return NULL; cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio)); - if (cfqq) { - sector_t sector = bio->bi_sector + bio_sectors(bio); - - return elv_rb_find(&cfqq->sort_list, sector); - } + if (cfqq) + return elv_rb_find(&cfqq->sort_list, bio_end_sector(bio)); return NULL; } @@ -1611,8 +2315,7 @@ static void cfq_remove_request(struct request *rq) cfq_del_rq_rb(rq); cfqq->cfqd->rq_queued--; - cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg, - rq_data_dir(rq), rq_is_sync(rq)); + cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags); if (rq->cmd_flags & REQ_PRIO) { WARN_ON(!cfqq->prio_pending); cfqq->prio_pending--; @@ -1647,8 +2350,7 @@ static void cfq_merged_request(struct request_queue *q, struct request *req, static void cfq_bio_merged(struct request_queue *q, struct request *req, struct bio *bio) { - cfq_blkiocg_update_io_merged_stats(&(RQ_CFQG(req))->blkg, - bio_data_dir(bio), cfq_bio_sync(bio)); + cfqg_stats_update_io_merged(RQ_CFQG(req), bio->bi_rw); } static void @@ -1662,16 +2364,16 @@ cfq_merged_requests(struct request_queue *q, struct request *rq, * reposition in fifo if next is older than rq */ if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) && - time_before(rq_fifo_time(next), rq_fifo_time(rq))) { + time_before(next->fifo_time, rq->fifo_time) && + cfqq == RQ_CFQQ(next)) { list_move(&rq->queuelist, &next->queuelist); - rq_set_fifo_time(rq, rq_fifo_time(next)); + rq->fifo_time = next->fifo_time; } if (cfqq->next_rq == next) cfqq->next_rq = rq; cfq_remove_request(next); - cfq_blkiocg_update_io_merged_stats(&(RQ_CFQG(rq))->blkg, - rq_data_dir(next), rq_is_sync(next)); + cfqg_stats_update_io_merged(RQ_CFQG(rq), next->cmd_flags); cfqq = RQ_CFQQ(next); /* @@ -1712,16 +2414,16 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq, static inline void cfq_del_timer(struct cfq_data *cfqd, struct cfq_queue *cfqq) { del_timer(&cfqd->idle_slice_timer); - cfq_blkiocg_update_idle_time_stats(&cfqq->cfqg->blkg); + cfqg_stats_update_idle_time(cfqq->cfqg); } static void __cfq_set_active_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq) { if (cfqq) { - cfq_log_cfqq(cfqd, cfqq, "set_active wl_prio:%d wl_type:%d", - cfqd->serving_prio, cfqd->serving_type); - cfq_blkiocg_update_avg_queue_size_stats(&cfqq->cfqg->blkg); + cfq_log_cfqq(cfqd, cfqq, "set_active wl_class:%d wl_type:%d", + cfqd->serving_wl_class, cfqd->serving_wl_type); + cfqg_stats_update_avg_queue_size(cfqq->cfqg); cfqq->slice_start = 0; cfqq->dispatch_start = jiffies; cfqq->allocated_slice = 0; @@ -1806,19 +2508,18 @@ static inline void cfq_slice_expired(struct cfq_data *cfqd, bool timed_out) */ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd) { - struct cfq_rb_root *service_tree = - service_tree_for(cfqd->serving_group, cfqd->serving_prio, - cfqd->serving_type); + struct cfq_rb_root *st = st_for(cfqd->serving_group, + cfqd->serving_wl_class, cfqd->serving_wl_type); if (!cfqd->rq_queued) return NULL; /* There is nothing to dispatch */ - if (!service_tree) + if (!st) return NULL; - if (RB_EMPTY_ROOT(&service_tree->rb)) + if (RB_EMPTY_ROOT(&st->rb)) return NULL; - return cfq_rb_first(service_tree); + return cfq_rb_first(st); } static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd) @@ -1974,17 +2675,17 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd, static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq) { - enum wl_prio_t prio = cfqq_prio(cfqq); - struct cfq_rb_root *service_tree = cfqq->service_tree; + enum wl_class_t wl_class = cfqq_class(cfqq); + struct cfq_rb_root *st = cfqq->service_tree; - BUG_ON(!service_tree); - BUG_ON(!service_tree->count); + BUG_ON(!st); + BUG_ON(!st->count); if (!cfqd->cfq_slice_idle) return false; /* We never do for idle class queues. */ - if (prio == IDLE_WORKLOAD) + if (wl_class == IDLE_WORKLOAD) return false; /* We do for queues that were marked with idle window flag. */ @@ -1996,11 +2697,10 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq) * Otherwise, we do only if they are the last ones * in their service tree. */ - if (service_tree->count == 1 && cfq_cfqq_sync(cfqq) && - !cfq_io_thinktime_big(cfqd, &service_tree->ttime, false)) + if (st->count == 1 && cfq_cfqq_sync(cfqq) && + !cfq_io_thinktime_big(cfqd, &st->ttime, false)) return true; - cfq_log_cfqq(cfqd, cfqq, "Not idling. st->count:%d", - service_tree->count); + cfq_log_cfqq(cfqd, cfqq, "Not idling. st->count:%d", st->count); return false; } @@ -2042,7 +2742,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) * task has exited, don't wait */ cic = cfqd->active_cic; - if (!cic || !atomic_read(&cic->icq.ioc->nr_tasks)) + if (!cic || !atomic_read(&cic->icq.ioc->active_ref)) return; /* @@ -2069,7 +2769,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) sl = cfqd->cfq_slice_idle; mod_timer(&cfqd->idle_slice_timer, jiffies + sl); - cfq_blkiocg_update_set_idle_time_stats(&cfqq->cfqg->blkg); + cfqg_stats_set_start_idle_time(cfqq->cfqg); cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu group_idle: %d", sl, group_idle ? 1 : 0); } @@ -2092,8 +2792,7 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq) cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++; cfqq->nr_sectors += blk_rq_sectors(rq); - cfq_blkiocg_update_dispatch_stats(&cfqq->cfqg->blkg, blk_rq_bytes(rq), - rq_data_dir(rq), rq_is_sync(rq)); + cfqg_stats_update_dispatch(cfqq->cfqg, blk_rq_bytes(rq), rq->cmd_flags); } /* @@ -2112,7 +2811,7 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq) return NULL; rq = rq_entry_fifo(cfqq->fifo.next); - if (time_before(jiffies, rq_fifo_time(rq))) + if (time_before(jiffies, rq->fifo_time)) rq = NULL; cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq); @@ -2184,8 +2883,8 @@ static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq) } } -static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd, - struct cfq_group *cfqg, enum wl_prio_t prio) +static enum wl_type_t cfq_choose_wl_type(struct cfq_data *cfqd, + struct cfq_group *cfqg, enum wl_class_t wl_class) { struct cfq_queue *queue; int i; @@ -2195,7 +2894,7 @@ static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd, for (i = 0; i <= SYNC_WORKLOAD; ++i) { /* select the one with lowest rb_key */ - queue = cfq_rb_first(service_tree_for(cfqg, prio, i)); + queue = cfq_rb_first(st_for(cfqg, wl_class, i)); if (queue && (!key_valid || time_before(queue->rb_key, lowest_key))) { lowest_key = queue->rb_key; @@ -2207,26 +2906,27 @@ static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd, return cur_best; } -static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg) +static void +choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg) { unsigned slice; unsigned count; struct cfq_rb_root *st; unsigned group_slice; - enum wl_prio_t original_prio = cfqd->serving_prio; + enum wl_class_t original_class = cfqd->serving_wl_class; /* Choose next priority. RT > BE > IDLE */ if (cfq_group_busy_queues_wl(RT_WORKLOAD, cfqd, cfqg)) - cfqd->serving_prio = RT_WORKLOAD; + cfqd->serving_wl_class = RT_WORKLOAD; else if (cfq_group_busy_queues_wl(BE_WORKLOAD, cfqd, cfqg)) - cfqd->serving_prio = BE_WORKLOAD; + cfqd->serving_wl_class = BE_WORKLOAD; else { - cfqd->serving_prio = IDLE_WORKLOAD; + cfqd->serving_wl_class = IDLE_WORKLOAD; cfqd->workload_expires = jiffies + 1; return; } - if (original_prio != cfqd->serving_prio) + if (original_class != cfqd->serving_wl_class) goto new_workload; /* @@ -2234,7 +2934,7 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg) * (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload * expiration time */ - st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type); + st = st_for(cfqg, cfqd->serving_wl_class, cfqd->serving_wl_type); count = st->count; /* @@ -2245,9 +2945,9 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg) new_workload: /* otherwise select new workload type */ - cfqd->serving_type = - cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio); - st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type); + cfqd->serving_wl_type = cfq_choose_wl_type(cfqd, cfqg, + cfqd->serving_wl_class); + st = st_for(cfqg, cfqd->serving_wl_class, cfqd->serving_wl_type); count = st->count; /* @@ -2258,10 +2958,11 @@ new_workload: group_slice = cfq_group_slice(cfqd, cfqg); slice = group_slice * count / - max_t(unsigned, cfqg->busy_queues_avg[cfqd->serving_prio], - cfq_group_busy_queues_wl(cfqd->serving_prio, cfqd, cfqg)); + max_t(unsigned, cfqg->busy_queues_avg[cfqd->serving_wl_class], + cfq_group_busy_queues_wl(cfqd->serving_wl_class, cfqd, + cfqg)); - if (cfqd->serving_type == ASYNC_WORKLOAD) { + if (cfqd->serving_wl_type == ASYNC_WORKLOAD) { unsigned int tmp; /* @@ -2271,7 +2972,8 @@ new_workload: * to have higher weight. A more accurate thing would be to * calculate system wide asnc/sync ratio. */ - tmp = cfq_target_latency * cfqg_busy_async_queues(cfqd, cfqg); + tmp = cfqd->cfq_target_latency * + cfqg_busy_async_queues(cfqd, cfqg); tmp = tmp/cfqd->busy_queues; slice = min_t(unsigned, slice, tmp); @@ -2306,14 +3008,14 @@ static void cfq_choose_cfqg(struct cfq_data *cfqd) cfqd->serving_group = cfqg; /* Restore the workload type data */ - if (cfqg->saved_workload_slice) { - cfqd->workload_expires = jiffies + cfqg->saved_workload_slice; - cfqd->serving_type = cfqg->saved_workload; - cfqd->serving_prio = cfqg->saved_serving_prio; + if (cfqg->saved_wl_slice) { + cfqd->workload_expires = jiffies + cfqg->saved_wl_slice; + cfqd->serving_wl_type = cfqg->saved_wl_type; + cfqd->serving_wl_class = cfqg->saved_wl_class; } else cfqd->workload_expires = jiffies - 1; - choose_service_tree(cfqd, cfqg); + choose_wl_class_and_type(cfqd, cfqg); } /* @@ -2675,7 +3377,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq) BUG_ON(cfq_cfqq_on_rr(cfqq)); kmem_cache_free(cfq_pool, cfqq); - cfq_put_cfqg(cfqg); + cfqg_put(cfqg); } static void cfq_put_cooperator(struct cfq_queue *cfqq) @@ -2734,7 +3436,7 @@ static void cfq_exit_icq(struct io_cq *icq) } } -static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc) +static void cfq_init_prio_data(struct cfq_queue *cfqq, struct cfq_io_cq *cic) { struct task_struct *tsk = current; int ioprio_class; @@ -2742,7 +3444,7 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc) if (!cfq_cfqq_prio_changed(cfqq)) return; - ioprio_class = IOPRIO_PRIO_CLASS(ioc->ioprio); + ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio); switch (ioprio_class) { default: printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class); @@ -2754,11 +3456,11 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc) cfqq->ioprio_class = task_nice_ioclass(tsk); break; case IOPRIO_CLASS_RT: - cfqq->ioprio = task_ioprio(ioc); + cfqq->ioprio = IOPRIO_PRIO_DATA(cic->ioprio); cfqq->ioprio_class = IOPRIO_CLASS_RT; break; case IOPRIO_CLASS_BE: - cfqq->ioprio = task_ioprio(ioc); + cfqq->ioprio = IOPRIO_PRIO_DATA(cic->ioprio); cfqq->ioprio_class = IOPRIO_CLASS_BE; break; case IOPRIO_CLASS_IDLE: @@ -2776,19 +3478,24 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc) cfq_clear_cfqq_prio_changed(cfqq); } -static void changed_ioprio(struct cfq_io_cq *cic) +static void check_ioprio_changed(struct cfq_io_cq *cic, struct bio *bio) { + int ioprio = cic->icq.ioc->ioprio; struct cfq_data *cfqd = cic_to_cfqd(cic); struct cfq_queue *cfqq; - if (unlikely(!cfqd)) + /* + * Check whether ioprio has changed. The condition may trigger + * spuriously on a newly created cic but there's no harm. + */ + if (unlikely(!cfqd) || likely(cic->ioprio == ioprio)) return; cfqq = cic->cfqq[BLK_RW_ASYNC]; if (cfqq) { struct cfq_queue *new_cfqq; - new_cfqq = cfq_get_queue(cfqd, BLK_RW_ASYNC, cic->icq.ioc, - GFP_ATOMIC); + new_cfqq = cfq_get_queue(cfqd, BLK_RW_ASYNC, cic, bio, + GFP_ATOMIC); if (new_cfqq) { cic->cfqq[BLK_RW_ASYNC] = new_cfqq; cfq_put_queue(cfqq); @@ -2798,6 +3505,8 @@ static void changed_ioprio(struct cfq_io_cq *cic) cfqq = cic->cfqq[BLK_RW_SYNC]; if (cfqq) cfq_mark_cfqq_prio_changed(cfqq); + + cic->ioprio = ioprio; } static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq, @@ -2821,17 +3530,24 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq, } #ifdef CONFIG_CFQ_GROUP_IOSCHED -static void changed_cgroup(struct cfq_io_cq *cic) +static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) { - struct cfq_queue *sync_cfqq = cic_to_cfqq(cic, 1); struct cfq_data *cfqd = cic_to_cfqd(cic); - struct request_queue *q; + struct cfq_queue *sync_cfqq; + uint64_t id; - if (unlikely(!cfqd)) - return; + rcu_read_lock(); + id = bio_blkcg(bio)->id; + rcu_read_unlock(); - q = cfqd->queue; + /* + * Check whether blkcg has changed. The condition may trigger + * spuriously on a newly created cic but there's no harm. + */ + if (unlikely(!cfqd) || likely(cic->blkcg_id == id)) + return; + sync_cfqq = cic_to_cfqq(cic, 1); if (sync_cfqq) { /* * Drop reference to sync queue. A new sync queue will be @@ -2841,21 +3557,26 @@ static void changed_cgroup(struct cfq_io_cq *cic) cic_set_cfqq(cic, NULL, 1); cfq_put_queue(sync_cfqq); } + + cic->blkcg_id = id; } +#else +static inline void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) { } #endif /* CONFIG_CFQ_GROUP_IOSCHED */ static struct cfq_queue * -cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync, - struct io_context *ioc, gfp_t gfp_mask) +cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic, + struct bio *bio, gfp_t gfp_mask) { + struct blkcg *blkcg; struct cfq_queue *cfqq, *new_cfqq = NULL; - struct cfq_io_cq *cic; struct cfq_group *cfqg; retry: - cfqg = cfq_get_cfqg(cfqd); - cic = cfq_cic_lookup(cfqd, ioc); - /* cic always exists here */ + rcu_read_lock(); + + blkcg = bio_blkcg(bio); + cfqg = cfq_lookup_create_cfqg(cfqd, blkcg); cfqq = cic_to_cfqq(cic, is_sync); /* @@ -2868,6 +3589,7 @@ retry: cfqq = new_cfqq; new_cfqq = NULL; } else if (gfp_mask & __GFP_WAIT) { + rcu_read_unlock(); spin_unlock_irq(cfqd->queue->queue_lock); new_cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask | __GFP_ZERO, @@ -2875,6 +3597,8 @@ retry: spin_lock_irq(cfqd->queue->queue_lock); if (new_cfqq) goto retry; + else + return &cfqd->oom_cfqq; } else { cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask | __GFP_ZERO, @@ -2883,7 +3607,7 @@ retry: if (cfqq) { cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync); - cfq_init_prio_data(cfqq, ioc); + cfq_init_prio_data(cfqq, cic); cfq_link_cfqq_cfqg(cfqq, cfqg); cfq_log_cfqq(cfqd, cfqq, "alloced"); } else @@ -2893,6 +3617,7 @@ retry: if (new_cfqq) kmem_cache_free(cfq_pool, new_cfqq); + rcu_read_unlock(); return cfqq; } @@ -2902,6 +3627,9 @@ cfq_async_queue_prio(struct cfq_data *cfqd, int ioprio_class, int ioprio) switch (ioprio_class) { case IOPRIO_CLASS_RT: return &cfqd->async_cfqq[0][ioprio]; + case IOPRIO_CLASS_NONE: + ioprio = IOPRIO_NORM; + /* fall through */ case IOPRIO_CLASS_BE: return &cfqd->async_cfqq[1][ioprio]; case IOPRIO_CLASS_IDLE: @@ -2912,11 +3640,11 @@ cfq_async_queue_prio(struct cfq_data *cfqd, int ioprio_class, int ioprio) } static struct cfq_queue * -cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct io_context *ioc, - gfp_t gfp_mask) +cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic, + struct bio *bio, gfp_t gfp_mask) { - const int ioprio = task_ioprio(ioc); - const int ioprio_class = task_ioprio_class(ioc); + const int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio); + const int ioprio = IOPRIO_PRIO_DATA(cic->ioprio); struct cfq_queue **async_cfqq = NULL; struct cfq_queue *cfqq = NULL; @@ -2926,7 +3654,7 @@ cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct io_context *ioc, } if (!cfqq) - cfqq = cfq_find_alloc_queue(cfqd, is_sync, ioc, gfp_mask); + cfqq = cfq_find_alloc_queue(cfqd, is_sync, cic, bio, gfp_mask); /* * pin the queue now that it's allocated, scheduler exit will prune it @@ -3008,7 +3736,7 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq, if (cfqq->next_rq && (cfqq->next_rq->cmd_flags & REQ_NOIDLE)) enable_idle = 0; - else if (!atomic_read(&cic->icq.ioc->nr_tasks) || + else if (!atomic_read(&cic->icq.ioc->active_ref) || !cfqd->cfq_slice_idle || (!cfq_cfqq_deep(cfqq) && CFQQ_SEEKY(cfqq))) enable_idle = 0; @@ -3068,7 +3796,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, return true; /* Allow preemption only if we are idling on sync-noidle tree */ - if (cfqd->serving_type == SYNC_NOIDLE_WORKLOAD && + if (cfqd->serving_wl_type == SYNC_NOIDLE_WORKLOAD && cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD && new_cfqq->service_tree->count == 2 && RB_EMPTY_ROOT(&cfqq->sort_list)) @@ -3120,7 +3848,7 @@ static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq) * doesn't happen */ if (old_type != cfqq_type(cfqq)) - cfqq->cfqg->saved_workload_slice = 0; + cfqq->cfqg->saved_wl_slice = 0; /* * Put the new queue at the front of the of the current list, @@ -3172,8 +3900,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfq_clear_cfqq_wait_request(cfqq); __blk_run_queue(cfqd->queue); } else { - cfq_blkiocg_update_idle_time_stats( - &cfqq->cfqg->blkg); + cfqg_stats_update_idle_time(cfqq->cfqg); cfq_mark_cfqq_must_dispatch(cfqq); } } @@ -3195,14 +3922,13 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq) struct cfq_queue *cfqq = RQ_CFQQ(rq); cfq_log_cfqq(cfqd, cfqq, "insert_request"); - cfq_init_prio_data(cfqq, RQ_CIC(rq)->icq.ioc); + cfq_init_prio_data(cfqq, RQ_CIC(rq)); - rq_set_fifo_time(rq, jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)]); + rq->fifo_time = jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)]; list_add_tail(&rq->queuelist, &cfqq->fifo); cfq_add_rq_rb(rq); - cfq_blkiocg_update_io_add_stats(&(RQ_CFQG(rq))->blkg, - &cfqd->serving_group->blkg, rq_data_dir(rq), - rq_is_sync(rq)); + cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group, + rq->cmd_flags); cfq_rq_enqueued(cfqd, cfqq, rq); } @@ -3298,23 +4024,23 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) cfqd->rq_in_driver--; cfqq->dispatched--; (RQ_CFQG(rq))->dispatched--; - cfq_blkiocg_update_completion_stats(&cfqq->cfqg->blkg, - rq_start_time_ns(rq), rq_io_start_time_ns(rq), - rq_data_dir(rq), rq_is_sync(rq)); + cfqg_stats_update_completion(cfqq->cfqg, rq_start_time_ns(rq), + rq_io_start_time_ns(rq), rq->cmd_flags); cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--; if (sync) { - struct cfq_rb_root *service_tree; + struct cfq_rb_root *st; RQ_CIC(rq)->ttime.last_end_request = now; if (cfq_cfqq_on_rr(cfqq)) - service_tree = cfqq->service_tree; + st = cfqq->service_tree; else - service_tree = service_tree_for(cfqq->cfqg, - cfqq_prio(cfqq), cfqq_type(cfqq)); - service_tree->ttime.last_end_request = now; + st = st_for(cfqq->cfqg, cfqq_class(cfqq), + cfqq_type(cfqq)); + + st->ttime.last_end_request = now; if (!time_after(rq->start_time + cfqd->cfq_fifo_expire[1], now)) cfqd->last_delayed_sync = now; } @@ -3397,7 +4123,7 @@ static int cfq_may_queue(struct request_queue *q, int rw) cfqq = cic_to_cfqq(cic, rw_is_sync(rw)); if (cfqq) { - cfq_init_prio_data(cfqq, cic->icq.ioc); + cfq_init_prio_data(cfqq, cic); return __cfq_may_queue(cfqq); } @@ -3419,7 +4145,7 @@ static void cfq_put_request(struct request *rq) cfqq->allocated[rw]--; /* Put down rq reference on cfqg */ - cfq_put_cfqg(RQ_CFQG(rq)); + cfqg_put(RQ_CFQG(rq)); rq->elv.priv[0] = NULL; rq->elv.priv[1] = NULL; @@ -3463,7 +4189,8 @@ split_cfqq(struct cfq_io_cq *cic, struct cfq_queue *cfqq) * Allocate cfq data structures associated with this request. */ static int -cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask) +cfq_set_request(struct request_queue *q, struct request *rq, struct bio *bio, + gfp_t gfp_mask) { struct cfq_data *cfqd = q->elevator->elevator_data; struct cfq_io_cq *cic = icq_to_cic(rq->elv.icq); @@ -3475,20 +4202,12 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask) spin_lock_irq(q->queue_lock); - /* handle changed notifications */ - if (unlikely(cic->icq.changed)) { - if (test_and_clear_bit(ICQ_IOPRIO_CHANGED, &cic->icq.changed)) - changed_ioprio(cic); -#ifdef CONFIG_CFQ_GROUP_IOSCHED - if (test_and_clear_bit(ICQ_CGROUP_CHANGED, &cic->icq.changed)) - changed_cgroup(cic); -#endif - } - + check_ioprio_changed(cic, bio); + check_blkcg_changed(cic, bio); new_queue: cfqq = cic_to_cfqq(cic, is_sync); if (!cfqq || cfqq == &cfqd->oom_cfqq) { - cfqq = cfq_get_queue(cfqd, is_sync, cic->icq.ioc, gfp_mask); + cfqq = cfq_get_queue(cfqd, is_sync, cic, bio, gfp_mask); cic_set_cfqq(cic, cfqq, is_sync); } else { /* @@ -3514,8 +4233,9 @@ new_queue: cfqq->allocated[rw]++; cfqq->ref++; + cfqg_get(cfqq->cfqg); rq->elv.priv[0] = cfqq; - rq->elv.priv[1] = cfq_ref_get_cfqg(cfqq->cfqg); + rq->elv.priv[1] = cfqq->cfqg; spin_unlock_irq(q->queue_lock); return 0; } @@ -3612,7 +4332,6 @@ static void cfq_exit_queue(struct elevator_queue *e) { struct cfq_data *cfqd = e->elevator_data; struct request_queue *q = cfqd->queue; - bool wait = false; cfq_shutdown_timer_wq(cfqd); @@ -3622,89 +4341,64 @@ static void cfq_exit_queue(struct elevator_queue *e) __cfq_slice_expired(cfqd, cfqd->active_queue, 0); cfq_put_async_queues(cfqd); - cfq_release_cfq_groups(cfqd); - - /* - * If there are groups which we could not unlink from blkcg list, - * wait for a rcu period for them to be freed. - */ - if (cfqd->nr_blkcg_linked_grps) - wait = true; spin_unlock_irq(q->queue_lock); cfq_shutdown_timer_wq(cfqd); - /* - * Wait for cfqg->blkg->key accessors to exit their grace periods. - * Do this wait only if there are other unlinked groups out - * there. This can happen if cgroup deletion path claimed the - * responsibility of cleaning up a group before queue cleanup code - * get to the group. - * - * Do not call synchronize_rcu() unconditionally as there are drivers - * which create/delete request queue hundreds of times during scan/boot - * and synchronize_rcu() can take significant time and slow down boot. - */ - if (wait) - synchronize_rcu(); - #ifdef CONFIG_CFQ_GROUP_IOSCHED - /* Free up per cpu stats for root group */ - free_percpu(cfqd->root_group.blkg.stats_cpu); + blkcg_deactivate_policy(q, &blkcg_policy_cfq); +#else + kfree(cfqd->root_group); #endif kfree(cfqd); } -static void *cfq_init_queue(struct request_queue *q) +static int cfq_init_queue(struct request_queue *q, struct elevator_type *e) { struct cfq_data *cfqd; - int i, j; - struct cfq_group *cfqg; - struct cfq_rb_root *st; + struct blkcg_gq *blkg __maybe_unused; + int i, ret; + struct elevator_queue *eq; - cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node); - if (!cfqd) - return NULL; + eq = elevator_alloc(q, e); + if (!eq) + return -ENOMEM; - /* Init root service tree */ - cfqd->grp_service_tree = CFQ_RB_ROOT; + cfqd = kzalloc_node(sizeof(*cfqd), GFP_KERNEL, q->node); + if (!cfqd) { + kobject_put(&eq->kobj); + return -ENOMEM; + } + eq->elevator_data = cfqd; - /* Init root group */ - cfqg = &cfqd->root_group; - for_each_cfqg_st(cfqg, i, j, st) - *st = CFQ_RB_ROOT; - RB_CLEAR_NODE(&cfqg->rb_node); + cfqd->queue = q; + spin_lock_irq(q->queue_lock); + q->elevator = eq; + spin_unlock_irq(q->queue_lock); - /* Give preference to root group over other groups */ - cfqg->weight = 2*BLKIO_WEIGHT_DEFAULT; + /* Init root service tree */ + cfqd->grp_service_tree = CFQ_RB_ROOT; + /* Init root group and prefer root group over other groups by default */ #ifdef CONFIG_CFQ_GROUP_IOSCHED - /* - * Set root group reference to 2. One reference will be dropped when - * all groups on cfqd->cfqg_list are being deleted during queue exit. - * Other reference will remain there as we don't want to delete this - * group as it is statically allocated and gets destroyed when - * throtl_data goes away. - */ - cfqg->ref = 2; - - if (blkio_alloc_blkg_stats(&cfqg->blkg)) { - kfree(cfqg); - kfree(cfqd); - return NULL; - } - - rcu_read_lock(); + ret = blkcg_activate_policy(q, &blkcg_policy_cfq); + if (ret) + goto out_free; - cfq_blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg, - (void *)cfqd, 0); - rcu_read_unlock(); - cfqd->nr_blkcg_linked_grps++; + cfqd->root_group = blkg_to_cfqg(q->root_blkg); +#else + ret = -ENOMEM; + cfqd->root_group = kzalloc_node(sizeof(*cfqd->root_group), + GFP_KERNEL, cfqd->queue->node); + if (!cfqd->root_group) + goto out_free; - /* Add group on cfqd->cfqg_list */ - hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list); + cfq_init_cfqg_base(cfqd->root_group); #endif + cfqd->root_group->weight = 2 * CFQ_WEIGHT_DEFAULT; + cfqd->root_group->leaf_weight = 2 * CFQ_WEIGHT_DEFAULT; + /* * Not strictly needed (since RB_ROOT just clears the node and we * zeroed cfqd on alloc), but better be safe in case someone decides @@ -3716,13 +4410,17 @@ static void *cfq_init_queue(struct request_queue *q) /* * Our fallback cfqq if cfq_find_alloc_queue() runs into OOM issues. * Grab a permanent reference to it, so that the normal code flow - * will not attempt to free it. + * will not attempt to free it. oom_cfqq is linked to root_group + * but shouldn't hold a reference as it'll never be unlinked. Lose + * the reference from linking right away. */ cfq_init_cfqq(cfqd, &cfqd->oom_cfqq, 1, 0); cfqd->oom_cfqq.ref++; - cfq_link_cfqq_cfqg(&cfqd->oom_cfqq, &cfqd->root_group); - cfqd->queue = q; + spin_lock_irq(q->queue_lock); + cfq_link_cfqq_cfqg(&cfqd->oom_cfqq, cfqd->root_group); + cfqg_put(cfqd->root_group); + spin_unlock_irq(q->queue_lock); init_timer(&cfqd->idle_slice_timer); cfqd->idle_slice_timer.function = cfq_idle_slice_timer; @@ -3737,6 +4435,7 @@ static void *cfq_init_queue(struct request_queue *q) cfqd->cfq_back_penalty = cfq_back_penalty; cfqd->cfq_slice[0] = cfq_slice_async; cfqd->cfq_slice[1] = cfq_slice_sync; + cfqd->cfq_target_latency = cfq_target_latency; cfqd->cfq_slice_async_rq = cfq_slice_async_rq; cfqd->cfq_slice_idle = cfq_slice_idle; cfqd->cfq_group_idle = cfq_group_idle; @@ -3747,7 +4446,12 @@ static void *cfq_init_queue(struct request_queue *q) * second, in order to have larger depth for async operations. */ cfqd->last_delayed_sync = jiffies - HZ; - return cfqd; + return 0; + +out_free: + kfree(cfqd); + kobject_put(&eq->kobj); + return ret; } /* @@ -3756,7 +4460,7 @@ static void *cfq_init_queue(struct request_queue *q) static ssize_t cfq_var_show(unsigned int var, char *page) { - return sprintf(page, "%d\n", var); + return sprintf(page, "%u\n", var); } static ssize_t @@ -3788,6 +4492,7 @@ SHOW_FUNCTION(cfq_slice_sync_show, cfqd->cfq_slice[1], 1); SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1); SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0); SHOW_FUNCTION(cfq_low_latency_show, cfqd->cfq_latency, 0); +SHOW_FUNCTION(cfq_target_latency_show, cfqd->cfq_target_latency, 1); #undef SHOW_FUNCTION #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ @@ -3821,6 +4526,7 @@ STORE_FUNCTION(cfq_slice_async_store, &cfqd->cfq_slice[0], 1, UINT_MAX, 1); STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1, UINT_MAX, 0); STORE_FUNCTION(cfq_low_latency_store, &cfqd->cfq_latency, 0, 1, 0); +STORE_FUNCTION(cfq_target_latency_store, &cfqd->cfq_target_latency, 1, UINT_MAX, 1); #undef STORE_FUNCTION #define CFQ_ATTR(name) \ @@ -3838,6 +4544,7 @@ static struct elv_fs_entry cfq_attrs[] = { CFQ_ATTR(slice_idle), CFQ_ATTR(group_idle), CFQ_ATTR(low_latency), + CFQ_ATTR(target_latency), __ATTR_NULL }; @@ -3871,15 +4578,14 @@ static struct elevator_type iosched_cfq = { }; #ifdef CONFIG_CFQ_GROUP_IOSCHED -static struct blkio_policy_type blkio_policy_cfq = { - .ops = { - .blkio_unlink_group_fn = cfq_unlink_blkio_group, - .blkio_update_group_weight_fn = cfq_update_blkio_group_weight, - }, - .plid = BLKIO_POLICY_PROP, +static struct blkcg_policy blkcg_policy_cfq = { + .pd_size = sizeof(struct cfq_group), + .cftypes = cfq_blkcg_files, + + .pd_init_fn = cfq_pd_init, + .pd_offline_fn = cfq_pd_offline, + .pd_reset_stats_fn = cfq_pd_reset_stats, }; -#else -static struct blkio_policy_type blkio_policy_cfq; #endif static int __init cfq_init(void) @@ -3897,27 +4603,39 @@ static int __init cfq_init(void) #ifdef CONFIG_CFQ_GROUP_IOSCHED if (!cfq_group_idle) cfq_group_idle = 1; + + ret = blkcg_policy_register(&blkcg_policy_cfq); + if (ret) + return ret; #else - cfq_group_idle = 0; + cfq_group_idle = 0; #endif + + ret = -ENOMEM; cfq_pool = KMEM_CACHE(cfq_queue, 0); if (!cfq_pool) - return -ENOMEM; + goto err_pol_unreg; ret = elv_register(&iosched_cfq); - if (ret) { - kmem_cache_destroy(cfq_pool); - return ret; - } - - blkio_policy_register(&blkio_policy_cfq); + if (ret) + goto err_free_pool; return 0; + +err_free_pool: + kmem_cache_destroy(cfq_pool); +err_pol_unreg: +#ifdef CONFIG_CFQ_GROUP_IOSCHED + blkcg_policy_unregister(&blkcg_policy_cfq); +#endif + return ret; } static void __exit cfq_exit(void) { - blkio_policy_unregister(&blkio_policy_cfq); +#ifdef CONFIG_CFQ_GROUP_IOSCHED + blkcg_policy_unregister(&blkcg_policy_cfq); +#endif elv_unregister(&iosched_cfq); kmem_cache_destroy(cfq_pool); } |