diff options
Diffstat (limited to 'block/cfq-iosched.c')
| -rw-r--r-- | block/cfq-iosched.c | 4020 |
1 files changed, 3141 insertions, 879 deletions
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 1e2aff812ee..cadc3784174 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -7,17 +7,21 @@ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> */ #include <linux/module.h> +#include <linux/slab.h> #include <linux/blkdev.h> #include <linux/elevator.h> +#include <linux/jiffies.h> #include <linux/rbtree.h> #include <linux/ioprio.h> #include <linux/blktrace_api.h> +#include "blk.h" +#include "blk-cgroup.h" /* * tunables */ /* max queue in one round of service */ -static const int cfq_quantum = 4; +static const int cfq_quantum = 8; static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 }; /* maximum backwards seek, in KiB */ static const int cfq_back_max = 16 * 1024; @@ -27,6 +31,9 @@ static const int cfq_slice_sync = HZ / 10; static int cfq_slice_async = HZ / 25; static const int cfq_slice_async_rq = 2; static int cfq_slice_idle = HZ / 125; +static int cfq_group_idle = HZ / 125; +static const int cfq_target_latency = HZ * 3/10; /* 300 ms */ +static const int cfq_hist_divisor = 4; /* * offset from end of service tree @@ -39,26 +46,34 @@ static int cfq_slice_idle = HZ / 125; #define CFQ_MIN_TT (2) #define CFQ_SLICE_SCALE (5) +#define CFQ_HW_QUEUE_MIN (5) +#define CFQ_SERVICE_SHIFT 12 -#define RQ_CIC(rq) \ - ((struct cfq_io_context *) (rq)->elevator_private) -#define RQ_CFQQ(rq) (struct cfq_queue *) ((rq)->elevator_private2) +#define CFQQ_SEEK_THR (sector_t)(8 * 100) +#define CFQQ_CLOSE_THR (sector_t)(8 * 1024) +#define CFQQ_SECT_THR_NONROT (sector_t)(2 * 32) +#define CFQQ_SEEKY(cfqq) (hweight32(cfqq->seek_history) > 32/8) -static struct kmem_cache *cfq_pool; -static struct kmem_cache *cfq_ioc_pool; +#define RQ_CIC(rq) icq_to_cic((rq)->elv.icq) +#define RQ_CFQQ(rq) (struct cfq_queue *) ((rq)->elv.priv[0]) +#define RQ_CFQG(rq) (struct cfq_group *) ((rq)->elv.priv[1]) -static DEFINE_PER_CPU(unsigned long, ioc_count); -static struct completion *ioc_gone; -static DEFINE_SPINLOCK(ioc_gone_lock); +static struct kmem_cache *cfq_pool; #define CFQ_PRIO_LISTS IOPRIO_BE_NR #define cfq_class_idle(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE) #define cfq_class_rt(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_RT) -#define ASYNC (0) -#define SYNC (1) - #define sample_valid(samples) ((samples) > 80) +#define rb_entry_cfqg(node) rb_entry((node), struct cfq_group, rb_node) + +struct cfq_ttime { + unsigned long last_end_request; + + unsigned long ttime_total; + unsigned long ttime_samples; + unsigned long ttime_mean; +}; /* * Most of our rbtree usage is for sorting with min extraction, so @@ -69,24 +84,268 @@ static DEFINE_SPINLOCK(ioc_gone_lock); struct cfq_rb_root { struct rb_root rb; struct rb_node *left; + unsigned count; + u64 min_vdisktime; + struct cfq_ttime ttime; +}; +#define CFQ_RB_ROOT (struct cfq_rb_root) { .rb = RB_ROOT, \ + .ttime = {.last_end_request = jiffies,},} + +/* + * Per process-grouping structure + */ +struct cfq_queue { + /* reference count */ + int ref; + /* various state flags, see below */ + unsigned int flags; + /* parent cfq_data */ + struct cfq_data *cfqd; + /* service_tree member */ + struct rb_node rb_node; + /* service_tree key */ + unsigned long rb_key; + /* prio tree member */ + struct rb_node p_node; + /* prio tree root we belong to, if any */ + struct rb_root *p_root; + /* sorted list of pending requests */ + struct rb_root sort_list; + /* if fifo isn't expired, next request to serve */ + struct request *next_rq; + /* requests queued in sort_list */ + int queued[2]; + /* currently allocated requests */ + int allocated[2]; + /* fifo list of requests in sort_list */ + struct list_head fifo; + + /* time when queue got scheduled in to dispatch first request. */ + unsigned long dispatch_start; + unsigned int allocated_slice; + unsigned int slice_dispatch; + /* time when first request from queue completed and slice started. */ + unsigned long slice_start; + unsigned long slice_end; + long slice_resid; + + /* pending priority requests */ + int prio_pending; + /* number of requests that are on the dispatch list or inside driver */ + int dispatched; + + /* io prio of this group */ + unsigned short ioprio, org_ioprio; + unsigned short ioprio_class; + + pid_t pid; + + u32 seek_history; + sector_t last_request_pos; + + struct cfq_rb_root *service_tree; + struct cfq_queue *new_cfqq; + struct cfq_group *cfqg; + /* Number of sectors dispatched from queue in single dispatch round */ + unsigned long nr_sectors; +}; + +/* + * First index in the service_trees. + * IDLE is handled separately, so it has negative index + */ +enum wl_class_t { + BE_WORKLOAD = 0, + RT_WORKLOAD = 1, + IDLE_WORKLOAD = 2, + CFQ_PRIO_NR, +}; + +/* + * Second index in the service_trees. + */ +enum wl_type_t { + ASYNC_WORKLOAD = 0, + SYNC_NOIDLE_WORKLOAD = 1, + 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; + 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; + + /* + * Per group busy queues average. Useful for workload slice calc. We + * create the array for each prio class but at run time it is used + * only for RT and BE class and slot for IDLE class remains unused. + * This is primarily done to avoid confusion and a gcc warning. + */ + unsigned int busy_queues_avg[CFQ_PRIO_NR]; + /* + * rr lists of queues with requests. We maintain service trees for + * RT and BE classes. These trees are subdivided in subclasses + * of SYNC, SYNC_NOIDLE and ASYNC based on workload type. For IDLE + * class there is no subclassification and all the cfq queues go on + * a single tree service_tree_idle. + * Counts are embedded in the cfq_rb_root + */ + struct cfq_rb_root service_trees[2][3]; + struct cfq_rb_root service_tree_idle; + + 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 }; -#define CFQ_RB_ROOT (struct cfq_rb_root) { RB_ROOT, NULL, } /* * Per block device queue structure */ 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; + + /* + * The priority currently being served + */ + enum wl_class_t serving_wl_class; + enum wl_type_t serving_wl_type; + unsigned long workload_expires; + struct cfq_group *serving_group; /* - * rr list of queues with requests and the count of them + * Each priority tree is sorted by next_request position. These + * trees are used when determining if two or more queues are + * interleaving requests (see cfq_close_cooperator). */ - struct cfq_rb_root service_tree; + struct rb_root prio_trees[CFQ_PRIO_LISTS]; + unsigned int busy_queues; + unsigned int busy_sync_queues; int rq_in_driver; - int sync_flight; + int rq_in_flight[2]; + + /* + * queue-depth detection + */ + int rq_queued; int hw_tag; + /* + * hw_tag can be + * -1 => indeterminate, (cfq will behave as if NCQ is present, to allow better detection) + * 1 => NCQ is present (hw_tag_est_depth is the estimated max depth) + * 0 => no NCQ + */ + int hw_tag_est_depth; + unsigned int hw_tag_samples; /* * idle window management @@ -95,7 +354,7 @@ struct cfq_data { struct work_struct unplug_work; struct cfq_queue *active_queue; - struct cfq_io_context *active_cic; + struct cfq_io_cq *active_cic; /* * async queue for each priority case @@ -104,7 +363,6 @@ struct cfq_data { struct cfq_queue *async_idle_cfqq; sector_t last_position; - unsigned long last_end_request; /* * tunables, see top of file @@ -116,62 +374,47 @@ struct cfq_data { unsigned int cfq_slice[2]; unsigned int cfq_slice_async_rq; unsigned int cfq_slice_idle; + unsigned int cfq_group_idle; + unsigned int cfq_latency; + unsigned int cfq_target_latency; - struct list_head cic_list; -}; + /* + * Fallback dummy cfqq for extreme OOM conditions + */ + struct cfq_queue oom_cfqq; -/* - * Per process-grouping structure - */ -struct cfq_queue { - /* reference count */ - atomic_t ref; - /* various state flags, see below */ - unsigned int flags; - /* parent cfq_data */ - struct cfq_data *cfqd; - /* service_tree member */ - struct rb_node rb_node; - /* service_tree key */ - unsigned long rb_key; - /* sorted list of pending requests */ - struct rb_root sort_list; - /* if fifo isn't expired, next request to serve */ - struct request *next_rq; - /* requests queued in sort_list */ - int queued[2]; - /* currently allocated requests */ - int allocated[2]; - /* fifo list of requests in sort_list */ - struct list_head fifo; + unsigned long last_delayed_sync; +}; - unsigned long slice_end; - long slice_resid; +static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd); - /* pending metadata requests */ - int meta_pending; - /* number of requests that are on the dispatch list or inside driver */ - int dispatched; +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; - /* io prio of this group */ - unsigned short ioprio, org_ioprio; - unsigned short ioprio_class, org_ioprio_class; + if (class == IDLE_WORKLOAD) + return &cfqg->service_tree_idle; - pid_t pid; -}; + return &cfqg->service_trees[class][type]; +} enum cfqq_state_flags { CFQ_CFQQ_FLAG_on_rr = 0, /* on round-robin busy list */ CFQ_CFQQ_FLAG_wait_request, /* waiting for a request */ - CFQ_CFQQ_FLAG_must_alloc, /* must be allowed rq alloc */ + CFQ_CFQQ_FLAG_must_dispatch, /* must be allowed a dispatch */ CFQ_CFQQ_FLAG_must_alloc_slice, /* per-slice must_alloc flag */ - CFQ_CFQQ_FLAG_must_dispatch, /* must dispatch, even if expired */ CFQ_CFQQ_FLAG_fifo_expire, /* FIFO checked in this slice */ CFQ_CFQQ_FLAG_idle_window, /* slice idling enabled */ CFQ_CFQQ_FLAG_prio_changed, /* task priority has changed */ - CFQ_CFQQ_FLAG_queue_new, /* queue never been serviced */ CFQ_CFQQ_FLAG_slice_new, /* no requests dispatched in slice */ CFQ_CFQQ_FLAG_sync, /* synchronous queue */ + CFQ_CFQQ_FLAG_coop, /* cfqq is shared */ + CFQ_CFQQ_FLAG_split_coop, /* shared cfqq will be splitted */ + CFQ_CFQQ_FLAG_deep, /* sync cfqq experienced large depth */ + CFQ_CFQQ_FLAG_wait_busy, /* Waiting for next request */ }; #define CFQ_CFQQ_FNS(name) \ @@ -190,50 +433,471 @@ static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq) \ CFQ_CFQQ_FNS(on_rr); CFQ_CFQQ_FNS(wait_request); -CFQ_CFQQ_FNS(must_alloc); -CFQ_CFQQ_FNS(must_alloc_slice); CFQ_CFQQ_FNS(must_dispatch); +CFQ_CFQQ_FNS(must_alloc_slice); CFQ_CFQQ_FNS(fifo_expire); CFQ_CFQQ_FNS(idle_window); CFQ_CFQQ_FNS(prio_changed); -CFQ_CFQQ_FNS(queue_new); CFQ_CFQQ_FNS(slice_new); CFQ_CFQQ_FNS(sync); +CFQ_CFQQ_FNS(coop); +CFQ_CFQQ_FNS(split_coop); +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 + +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) { } + #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) + +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) +/* Traverses through cfq group service trees */ +#define for_each_cfqg_st(cfqg, i, j, st) \ + for (i = 0; i <= IDLE_WORKLOAD; i++) \ + for (j = 0, st = i < IDLE_WORKLOAD ? &cfqg->service_trees[i][j]\ + : &cfqg->service_tree_idle; \ + (i < IDLE_WORKLOAD && j <= SYNC_WORKLOAD) || \ + (i == IDLE_WORKLOAD && j == 0); \ + j++, st = i < IDLE_WORKLOAD ? \ + &cfqg->service_trees[i][j]: NULL) \ + +static inline bool cfq_io_thinktime_big(struct cfq_data *cfqd, + struct cfq_ttime *ttime, bool group_idle) +{ + unsigned long slice; + if (!sample_valid(ttime->ttime_samples)) + return false; + if (group_idle) + slice = cfqd->cfq_group_idle; + else + slice = cfqd->cfq_slice_idle; + return ttime->ttime_mean > slice; +} + +static inline bool iops_mode(struct cfq_data *cfqd) +{ + /* + * If we are not idling on queues and it is a NCQ drive, parallel + * execution of requests is on and measuring time is not possible + * in most of the cases until and unless we drive shallower queue + * depths and that becomes a performance bottleneck. In such cases + * switch to start providing fairness in terms of number of IOs. + */ + if (!cfqd->cfq_slice_idle && cfqd->hw_tag) + return true; + else + return false; +} + +static inline enum wl_class_t cfqq_class(struct cfq_queue *cfqq) +{ + if (cfq_class_idle(cfqq)) + return IDLE_WORKLOAD; + if (cfq_class_rt(cfqq)) + return RT_WORKLOAD; + return BE_WORKLOAD; +} + + +static enum wl_type_t cfqq_type(struct cfq_queue *cfqq) +{ + if (!cfq_cfqq_sync(cfqq)) + return ASYNC_WORKLOAD; + if (!cfq_cfqq_idle_window(cfqq)) + return SYNC_NOIDLE_WORKLOAD; + return SYNC_WORKLOAD; +} + +static inline int cfq_group_busy_queues_wl(enum wl_class_t wl_class, + struct cfq_data *cfqd, + struct cfq_group *cfqg) +{ + if (wl_class == IDLE_WORKLOAD) + return cfqg->service_tree_idle.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; +} + static void cfq_dispatch_insert(struct request_queue *, struct request *); -static struct cfq_queue *cfq_get_queue(struct cfq_data *, int, - struct io_context *, gfp_t); -static struct cfq_io_context *cfq_cic_lookup(struct cfq_data *, - struct io_context *); +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_queue *cic_to_cfqq(struct cfq_io_context *cic, - int is_sync) +static inline struct cfq_io_cq *icq_to_cic(struct io_cq *icq) { - return cic->cfqq[!!is_sync]; + /* cic->icq is the first member, %NULL will convert to %NULL */ + return container_of(icq, struct cfq_io_cq, icq); } -static inline void cic_set_cfqq(struct cfq_io_context *cic, - struct cfq_queue *cfqq, int is_sync) +static inline struct cfq_io_cq *cfq_cic_lookup(struct cfq_data *cfqd, + struct io_context *ioc) { - cic->cfqq[!!is_sync] = cfqq; + if (ioc) + return icq_to_cic(ioc_lookup_icq(ioc, cfqd->queue)); + return NULL; +} + +static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_cq *cic, bool is_sync) +{ + return cic->cfqq[is_sync]; +} + +static inline void cic_set_cfqq(struct cfq_io_cq *cic, struct cfq_queue *cfqq, + bool is_sync) +{ + cic->cfqq[is_sync] = cfqq; +} + +static inline struct cfq_data *cic_to_cfqd(struct cfq_io_cq *cic) +{ + return cic->icq.q->elevator->elevator_data; } /* * We regard a request as SYNC, if it's either a read or has the SYNC bit * set (in which case it could also be direct WRITE). */ -static inline int cfq_bio_sync(struct bio *bio) +static inline bool cfq_bio_sync(struct bio *bio) { - if (bio_data_dir(bio) == READ || bio_sync(bio)) - return 1; - - return 0; + return bio_data_dir(bio) == READ || (bio->bi_rw & REQ_SYNC); } /* @@ -248,19 +912,12 @@ static inline void cfq_schedule_dispatch(struct cfq_data *cfqd) } } -static int cfq_queue_empty(struct request_queue *q) -{ - struct cfq_data *cfqd = q->elevator->elevator_data; - - return !cfqd->busy_queues; -} - /* * Scale schedule slice based on io priority. Use the sync time slice only * if a queue is marked sync and has sync io queued. A sync queue with async * io only, should not get full sync slice length. */ -static inline int cfq_prio_slice(struct cfq_data *cfqd, int sync, +static inline int cfq_prio_slice(struct cfq_data *cfqd, bool sync, unsigned short prio) { const int base_slice = cfqd->cfq_slice[sync]; @@ -276,10 +933,123 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq) return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio); } +/** + * 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 c = charge << CFQ_SERVICE_SHIFT; /* make it fixed point */ + + /* charge / vfraction */ + c <<= CFQ_SERVICE_SHIFT; + do_div(c, vfraction); + return c; +} + +static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime) +{ + s64 delta = (s64)(vdisktime - min_vdisktime); + if (delta > 0) + min_vdisktime = vdisktime; + + return min_vdisktime; +} + +static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime) +{ + s64 delta = (s64)(vdisktime - min_vdisktime); + if (delta < 0) + min_vdisktime = vdisktime; + + return min_vdisktime; +} + +static void update_min_vdisktime(struct cfq_rb_root *st) +{ + struct cfq_group *cfqg; + + if (st->left) { + cfqg = rb_entry_cfqg(st->left); + st->min_vdisktime = max_vdisktime(st->min_vdisktime, + cfqg->vdisktime); + } +} + +/* + * get averaged number of queues of RT/BE priority. + * average is updated, with a formula that gives more weight to higher numbers, + * to quickly follows sudden increases and decrease slowly + */ + +static inline unsigned cfq_group_get_avg_queues(struct cfq_data *cfqd, + struct cfq_group *cfqg, bool rt) +{ + unsigned min_q, max_q; + unsigned mult = cfq_hist_divisor - 1; + unsigned round = cfq_hist_divisor / 2; + unsigned busy = cfq_group_busy_queues_wl(rt, cfqd, cfqg); + + min_q = min(cfqg->busy_queues_avg[rt], busy); + max_q = max(cfqg->busy_queues_avg[rt], busy); + cfqg->busy_queues_avg[rt] = (mult * max_q + min_q + round) / + cfq_hist_divisor; + return cfqg->busy_queues_avg[rt]; +} + +static inline unsigned +cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg) +{ + return cfqd->cfq_target_latency * cfqg->vfraction >> CFQ_SERVICE_SHIFT; +} + +static inline unsigned +cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + unsigned slice = cfq_prio_to_slice(cfqd, cfqq); + if (cfqd->cfq_latency) { + /* + * interested queues (we consider only the ones with the same + * priority class in the cfq group) + */ + unsigned iq = cfq_group_get_avg_queues(cfqd, cfqq->cfqg, + cfq_class_rt(cfqq)); + unsigned sync_slice = cfqd->cfq_slice[1]; + unsigned expect_latency = sync_slice * iq; + unsigned group_slice = cfq_group_slice(cfqd, cfqq->cfqg); + + if (expect_latency > group_slice) { + unsigned base_low_slice = 2 * cfqd->cfq_slice_idle; + /* scale low_slice according to IO priority + * and sync vs async */ + unsigned low_slice = + min(slice, base_low_slice * slice / sync_slice); + /* the adapted slice value is scaled to fit all iqs + * into the target latency */ + slice = max(slice * group_slice / expect_latency, + low_slice); + } + } + return slice; +} + static inline void cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq) { - cfqq->slice_end = cfq_prio_to_slice(cfqd, cfqq) + jiffies; + unsigned slice = cfq_scaled_cfqq_slice(cfqd, cfqq); + + cfqq->slice_start = jiffies; + cfqq->slice_end = jiffies + slice; + cfqq->allocated_slice = slice; cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies); } @@ -288,14 +1058,14 @@ cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq) * isn't valid until the first request from the dispatch is activated * and the slice time set. */ -static inline int cfq_slice_used(struct cfq_queue *cfqq) +static inline bool cfq_slice_used(struct cfq_queue *cfqq) { if (cfq_cfqq_slice_new(cfqq)) - return 0; + return false; if (time_before(jiffies, cfqq->slice_end)) - return 0; + return false; - return 1; + return true; } /* @@ -304,9 +1074,9 @@ static inline int cfq_slice_used(struct cfq_queue *cfqq) * behind the head is penalized and only allowed to a certain extent. */ static struct request * -cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2) +cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2, sector_t last) { - sector_t last, s1, s2, d1 = 0, d2 = 0; + sector_t s1, s2, d1 = 0, d2 = 0; unsigned long back_max; #define CFQ_RQ1_WRAP 0x01 /* request 1 wraps */ #define CFQ_RQ2_WRAP 0x02 /* request 2 wraps */ @@ -317,19 +1087,14 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2) if (rq2 == NULL) return rq1; - if (rq_is_sync(rq1) && !rq_is_sync(rq2)) - return rq1; - else if (rq_is_sync(rq2) && !rq_is_sync(rq1)) - return rq2; - if (rq_is_meta(rq1) && !rq_is_meta(rq2)) - return rq1; - else if (rq_is_meta(rq2) && !rq_is_meta(rq1)) - return rq2; + if (rq_is_sync(rq1) != rq_is_sync(rq2)) + return rq_is_sync(rq1) ? rq1 : rq2; - s1 = rq1->sector; - s2 = rq2->sector; + if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_PRIO) + return rq1->cmd_flags & REQ_PRIO ? rq1 : rq2; - last = cfqd->last_position; + s1 = blk_rq_pos(rq1); + s2 = blk_rq_pos(rq2); /* * by definition, 1KiB is 2 sectors @@ -398,6 +1163,10 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2) */ static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root) { + /* Service tree is empty */ + if (!root->count) + return NULL; + if (!root->left) root->left = rb_first(&root->rb); @@ -407,13 +1176,29 @@ static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root) return NULL; } +static struct cfq_group *cfq_rb_first_group(struct cfq_rb_root *root) +{ + if (!root->left) + root->left = rb_first(&root->rb); + + if (root->left) + return rb_entry_cfqg(root->left); + + return NULL; +} + +static void rb_erase_init(struct rb_node *n, struct rb_root *root) +{ + rb_erase(n, root); + RB_CLEAR_NODE(n); +} + static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root) { if (root->left == n) root->left = NULL; - - rb_erase(n, &root->rb); - RB_CLEAR_NODE(n); + rb_erase_init(n, &root->rb); + --root->count; } /* @@ -440,7 +1225,7 @@ cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq, next = rb_entry_rq(rbnext); } - return cfq_choose_req(cfqd, next, prev); + return cfq_choose_req(cfqd, next, prev, blk_rq_pos(last)); } static unsigned long cfq_slice_offset(struct cfq_data *cfqd, @@ -449,87 +1234,915 @@ static unsigned long cfq_slice_offset(struct cfq_data *cfqd, /* * just an approximation, should be ok. */ - return (cfqd->busy_queues - 1) * (cfq_prio_slice(cfqd, 1, 0) - + return (cfqq->cfqg->nr_cfqq - 1) * (cfq_prio_slice(cfqd, 1, 0) - cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio)); } +static inline s64 +cfqg_key(struct cfq_rb_root *st, struct cfq_group *cfqg) +{ + return cfqg->vdisktime - st->min_vdisktime; +} + +static void +__cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg) +{ + struct rb_node **node = &st->rb.rb_node; + struct rb_node *parent = NULL; + struct cfq_group *__cfqg; + s64 key = cfqg_key(st, cfqg); + int left = 1; + + while (*node != NULL) { + parent = *node; + __cfqg = rb_entry_cfqg(parent); + + if (key < cfqg_key(st, __cfqg)) + node = &parent->rb_left; + else { + node = &parent->rb_right; + left = 0; + } + } + + if (left) + st->left = &cfqg->rb_node; + + rb_link_node(&cfqg->rb_node, parent, node); + rb_insert_color(&cfqg->rb_node, &st->rb); +} + +static void +cfq_update_group_weight(struct cfq_group *cfqg) +{ + BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node)); + + if (cfqg->new_weight) { + cfqg->weight = cfqg->new_weight; + 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); + + /* + * 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 +cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg) +{ + struct cfq_rb_root *st = &cfqd->grp_service_tree; + struct cfq_group *__cfqg; + struct rb_node *n; + + cfqg->nr_cfqq++; + if (!RB_EMPTY_NODE(&cfqg->rb_node)) + return; + + /* + * Currently put the group at the end. Later implement something + * so that groups get lesser vtime based on their weights, so that + * if group does not loose all if it was not continuously backlogged. + */ + n = rb_last(&st->rb); + if (n) { + __cfqg = rb_entry_cfqg(n); + cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY; + } else + cfqg->vdisktime = st->min_vdisktime; + cfq_group_service_tree_add(st, cfqg); +} + +static void +cfq_group_service_tree_del(struct cfq_rb_root *st, struct cfq_group *cfqg) +{ + 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); +} + +static void +cfq_group_notify_queue_del(struct cfq_data *cfqd, struct cfq_group *cfqg) +{ + struct cfq_rb_root *st = &cfqd->grp_service_tree; + + BUG_ON(cfqg->nr_cfqq < 1); + cfqg->nr_cfqq--; + + /* If there are other cfq queues under this group, don't delete it */ + if (cfqg->nr_cfqq) + return; + + cfq_log_cfqg(cfqd, cfqg, "del_from_rr group"); + cfq_group_service_tree_del(st, cfqg); + cfqg->saved_wl_slice = 0; + cfqg_stats_update_dequeue(cfqg); +} + +static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq, + unsigned int *unaccounted_time) +{ + unsigned int slice_used; + + /* + * Queue got expired before even a single request completed or + * got expired immediately after first request completion. + */ + if (!cfqq->slice_start || cfqq->slice_start == jiffies) { + /* + * Also charge the seek time incurred to the group, otherwise + * if there are mutiple queues in the group, each can dispatch + * a single request on seeky media and cause lots of seek time + * and group will never know it. + */ + slice_used = max_t(unsigned, (jiffies - cfqq->dispatch_start), + 1); + } else { + slice_used = jiffies - cfqq->slice_start; + if (slice_used > cfqq->allocated_slice) { + *unaccounted_time = slice_used - cfqq->allocated_slice; + slice_used = cfqq->allocated_slice; + } + if (time_after(cfqq->slice_start, cfqq->dispatch_start)) + *unaccounted_time += cfqq->slice_start - + cfqq->dispatch_start; + } + + return slice_used; +} + +static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg, + struct cfq_queue *cfqq) +{ + struct cfq_rb_root *st = &cfqd->grp_service_tree; + 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); + + if (iops_mode(cfqd)) + charge = cfqq->slice_dispatch; + else if (!cfq_cfqq_sync(cfqq) && !nr_sync) + charge = cfqq->allocated_slice; + + /* + * 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 += 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_wl_slice = cfqd->workload_expires + - jiffies; + cfqg->saved_wl_type = cfqd->serving_wl_type; + cfqg->saved_wl_class = cfqd->serving_wl_class; + } else + cfqg->saved_wl_slice = 0; + + cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime, + st->min_vdisktime); + cfq_log_cfqq(cfqq->cfqd, cfqq, + "sl_used=%u disp=%u charge=%u iops=%u sect=%lu", + used_sl, cfqq->slice_dispatch, charge, + iops_mode(cfqd), cfqq->nr_sectors); + cfqg_stats_update_timeslice_used(cfqg, used_sl, unaccounted_sl); + cfqg_stats_set_start_empty_time(cfqg); +} + +/** + * 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) +{ + 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; +} + +#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_pd_init(struct blkcg_gq *blkg) +{ + 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) +{ + /* + * @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... + */ + cfqg_stats_xfer_dead(blkg_to_cfqg(blkg)); +} + +/* 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); + +/* 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; +} + +/* 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 blkg_rwstat a, b; + + 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; +} + +static void cfq_pd_reset_stats(struct blkcg_gq *blkg) +{ + struct cfq_group *cfqg = blkg_to_cfqg(blkg); + + cfqg_stats_reset(&cfqg->stats); + cfqg_stats_reset(&cfqg->dead_stats); +} + /* - * The cfqd->service_tree holds all pending cfq_queue's that have + * 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; + + /* 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 void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) +{ + /* Currently, all async queues are mapped to root group */ + if (!cfq_cfqq_sync(cfqq)) + cfqg = cfqq->cfqd->root_group; + + cfqq->cfqg = cfqg; + /* cfqq reference on cfqg */ + cfqg_get(cfqg); +} + +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); + + if (!cfqg->dev_weight) + return 0; + return __blkg_prfill_u64(sf, pd, cfqg->dev_weight); +} + +static int cfqg_print_weight_device(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + cfqg_prfill_weight_device, &blkcg_policy_cfq, + 0, false); + return 0; +} + +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); + + if (!cfqg->dev_leaf_weight) + return 0; + return __blkg_prfill_u64(sf, pd, cfqg->dev_leaf_weight); +} + +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; +} + +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; +} + +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; +} + +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; + + ret = blkg_conf_prep(blkcg, &blkcg_policy_cfq, buf, &ctx); + if (ret) + return ret; + + 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; + } + + blkg_conf_finish(&ctx); + return ret ?: nbytes; +} + +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 ssize_t cfqg_set_leaf_weight_device(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return __cfqg_set_weight_device(of, buf, nbytes, off, true); +} + +static int __cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val, bool is_leaf_weight) +{ + struct blkcg *blkcg = css_to_blkcg(css); + struct blkcg_gq *blkg; + + 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 int cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val) +{ + return __cfq_set_weight(css, cft, val, false); +} + +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 int cfqg_print_stat(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat, + &blkcg_policy_cfq, seq_cft(sf)->private, false); + return 0; +} + +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; +} + +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); + + return __blkg_prfill_u64(sf, pd, sum); +} + +static u64 cfqg_prfill_rwstat_recursive(struct seq_file *sf, + struct blkg_policy_data *pd, int off) +{ + struct blkg_rwstat sum = cfqg_rwstat_pd_recursive_sum(pd, off); + + return __blkg_prfill_rwstat(sf, pd, &sum); +} + +static int cfqg_print_stat_recursive(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + cfqg_prfill_stat_recursive, &blkcg_policy_cfq, + seq_cft(sf)->private, false); + return 0; +} + +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; +} + +#ifdef CONFIG_DEBUG_BLK_CGROUP +static u64 cfqg_prfill_avg_queue_size(struct seq_file *sf, + struct blkg_policy_data *pd, int off) +{ + 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; +} + +/* print avg_queue_size */ +static int cfqg_print_avg_queue_size(struct seq_file *sf, void *v) +{ + 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 +cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) { + cfqq->cfqg = cfqg; +} + +#endif /* GROUP_IOSCHED */ + +/* + * The cfqd->service_trees holds all pending cfq_queue's that have * requests waiting to be processed. It is sorted in the order that * we will service the queues. */ -static void cfq_service_tree_add(struct cfq_data *cfqd, - struct cfq_queue *cfqq, int add_front) +static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, + bool add_front) { struct rb_node **p, *parent; struct cfq_queue *__cfqq; unsigned long rb_key; + struct cfq_rb_root *st; int left; + int new_cfqq = 1; + st = st_for(cfqq->cfqg, cfqq_class(cfqq), cfqq_type(cfqq)); if (cfq_class_idle(cfqq)) { rb_key = CFQ_IDLE_DELAY; - parent = rb_last(&cfqd->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; } else rb_key += jiffies; } else if (!add_front) { + /* + * Get our rb key offset. Subtract any residual slice + * value carried from last service. A negative resid + * count indicates slice overrun, and this should position + * the next service time further away in the tree. + */ rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies; - rb_key += cfqq->slice_resid; + rb_key -= cfqq->slice_resid; cfqq->slice_resid = 0; - } else - rb_key = 0; + } else { + rb_key = -HZ; + __cfqq = cfq_rb_first(st); + rb_key += __cfqq ? __cfqq->rb_key : jiffies; + } if (!RB_EMPTY_NODE(&cfqq->rb_node)) { + new_cfqq = 0; /* * same position, nothing more to do */ - if (rb_key == cfqq->rb_key) + if (rb_key == cfqq->rb_key && cfqq->service_tree == st) return; - cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree); + cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree); + cfqq->service_tree = NULL; } left = 1; parent = NULL; - p = &cfqd->service_tree.rb.rb_node; + cfqq->service_tree = st; + p = &st->rb.rb_node; + while (*p) { + parent = *p; + __cfqq = rb_entry(parent, struct cfq_queue, rb_node); + + /* + * sort by key, that represents service time. + */ + if (time_before(rb_key, __cfqq->rb_key)) + p = &parent->rb_left; + else { + p = &parent->rb_right; + left = 0; + } + } + + if (left) + st->left = &cfqq->rb_node; + + cfqq->rb_key = rb_key; + rb_link_node(&cfqq->rb_node, parent, p); + rb_insert_color(&cfqq->rb_node, &st->rb); + st->count++; + if (add_front || !new_cfqq) + return; + cfq_group_notify_queue_add(cfqd, cfqq->cfqg); +} + +static struct cfq_queue * +cfq_prio_tree_lookup(struct cfq_data *cfqd, struct rb_root *root, + sector_t sector, struct rb_node **ret_parent, + struct rb_node ***rb_link) +{ + struct rb_node **p, *parent; + struct cfq_queue *cfqq = NULL; + + parent = NULL; + p = &root->rb_node; while (*p) { struct rb_node **n; parent = *p; - __cfqq = rb_entry(parent, struct cfq_queue, rb_node); + cfqq = rb_entry(parent, struct cfq_queue, p_node); /* - * sort RT queues first, we always want to give - * preference to them. IDLE queues goes to the back. - * after that, sort on the next service time. + * Sort strictly based on sector. Smallest to the left, + * largest to the right. */ - if (cfq_class_rt(cfqq) > cfq_class_rt(__cfqq)) - n = &(*p)->rb_left; - else if (cfq_class_rt(cfqq) < cfq_class_rt(__cfqq)) + if (sector > blk_rq_pos(cfqq->next_rq)) n = &(*p)->rb_right; - else if (cfq_class_idle(cfqq) < cfq_class_idle(__cfqq)) - n = &(*p)->rb_left; - else if (cfq_class_idle(cfqq) > cfq_class_idle(__cfqq)) - n = &(*p)->rb_right; - else if (rb_key < __cfqq->rb_key) + else if (sector < blk_rq_pos(cfqq->next_rq)) n = &(*p)->rb_left; else - n = &(*p)->rb_right; + break; + p = n; + cfqq = NULL; + } - if (n == &(*p)->rb_right) - left = 0; + *ret_parent = parent; + if (rb_link) + *rb_link = p; + return cfqq; +} - p = n; +static void cfq_prio_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + struct rb_node **p, *parent; + struct cfq_queue *__cfqq; + + if (cfqq->p_root) { + rb_erase(&cfqq->p_node, cfqq->p_root); + cfqq->p_root = NULL; } - if (left) - cfqd->service_tree.left = &cfqq->rb_node; + if (cfq_class_idle(cfqq)) + return; + if (!cfqq->next_rq) + return; - cfqq->rb_key = rb_key; - rb_link_node(&cfqq->rb_node, parent, p); - rb_insert_color(&cfqq->rb_node, &cfqd->service_tree.rb); + cfqq->p_root = &cfqd->prio_trees[cfqq->org_ioprio]; + __cfqq = cfq_prio_tree_lookup(cfqd, cfqq->p_root, + blk_rq_pos(cfqq->next_rq), &parent, &p); + if (!__cfqq) { + rb_link_node(&cfqq->p_node, parent, p); + rb_insert_color(&cfqq->p_node, cfqq->p_root); + } else + cfqq->p_root = NULL; } /* @@ -540,8 +2153,10 @@ static void cfq_resort_rr_list(struct cfq_data *cfqd, struct cfq_queue *cfqq) /* * Resorting requires the cfqq to be on the RR list already. */ - if (cfq_cfqq_on_rr(cfqq)) + if (cfq_cfqq_on_rr(cfqq)) { cfq_service_tree_add(cfqd, cfqq, 0); + cfq_prio_tree_add(cfqd, cfqq); + } } /* @@ -554,6 +2169,8 @@ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq) BUG_ON(cfq_cfqq_on_rr(cfqq)); cfq_mark_cfqq_on_rr(cfqq); cfqd->busy_queues++; + if (cfq_cfqq_sync(cfqq)) + cfqd->busy_sync_queues++; cfq_resort_rr_list(cfqd, cfqq); } @@ -568,11 +2185,20 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq) BUG_ON(!cfq_cfqq_on_rr(cfqq)); cfq_clear_cfqq_on_rr(cfqq); - if (!RB_EMPTY_NODE(&cfqq->rb_node)) - cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree); + if (!RB_EMPTY_NODE(&cfqq->rb_node)) { + cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree); + cfqq->service_tree = NULL; + } + if (cfqq->p_root) { + rb_erase(&cfqq->p_node, cfqq->p_root); + cfqq->p_root = NULL; + } + cfq_group_notify_queue_del(cfqd, cfqq->cfqg); BUG_ON(!cfqd->busy_queues); cfqd->busy_queues--; + if (cfq_cfqq_sync(cfqq)) + cfqd->busy_sync_queues--; } /* @@ -581,7 +2207,6 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq) static void cfq_del_rq_rb(struct request *rq) { struct cfq_queue *cfqq = RQ_CFQQ(rq); - struct cfq_data *cfqd = cfqq->cfqd; const int sync = rq_is_sync(rq); BUG_ON(!cfqq->queued[sync]); @@ -589,24 +2214,28 @@ static void cfq_del_rq_rb(struct request *rq) elv_rb_del(&cfqq->sort_list, rq); - if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list)) - cfq_del_cfqq_rr(cfqd, cfqq); + if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list)) { + /* + * Queue will be deleted from service tree when we actually + * expire it later. Right now just remove it from prio tree + * as it is empty. + */ + if (cfqq->p_root) { + rb_erase(&cfqq->p_node, cfqq->p_root); + cfqq->p_root = NULL; + } + } } static void cfq_add_rq_rb(struct request *rq) { struct cfq_queue *cfqq = RQ_CFQQ(rq); struct cfq_data *cfqd = cfqq->cfqd; - struct request *__alias; + struct request *prev; cfqq->queued[rq_is_sync(rq)]++; - /* - * looks a little odd, but the first insert might return an alias. - * if that happens, put the alias on the dispatch list - */ - while ((__alias = elv_rb_add(&cfqq->sort_list, rq)) != NULL) - cfq_dispatch_insert(cfqd->queue, __alias); + elv_rb_add(&cfqq->sort_list, rq); if (!cfq_cfqq_on_rr(cfqq)) cfq_add_cfqq_rr(cfqd, cfqq); @@ -614,7 +2243,15 @@ static void cfq_add_rq_rb(struct request *rq) /* * check if this request is a better next-serve candidate */ - cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq); + prev = cfqq->next_rq; + cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq, cfqd->last_position); + + /* + * adjust priority tree position, if ->next_rq changes + */ + if (prev != cfqq->next_rq) + cfq_prio_tree_add(cfqd, cfqq); + BUG_ON(!cfqq->next_rq); } @@ -622,14 +2259,17 @@ 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)]--; + cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags); cfq_add_rq_rb(rq); + cfqg_stats_update_io_add(RQ_CFQG(rq), cfqq->cfqd->serving_group, + rq->cmd_flags); } static struct request * cfq_find_rq_fmerge(struct cfq_data *cfqd, struct bio *bio) { struct task_struct *tsk = current; - struct cfq_io_context *cic; + struct cfq_io_cq *cic; struct cfq_queue *cfqq; cic = cfq_cic_lookup(cfqd, tsk->io_context); @@ -637,11 +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; } @@ -654,16 +2291,7 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq) cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d", cfqd->rq_in_driver); - /* - * If the depth is larger 1, it really could be queueing. But lets - * make the mark a little higher - idling could still be good for - * low queueing, and a low queueing number could also just indicate - * a SCSI mid layer like behaviour where limit+1 is often seen. - */ - if (!cfqd->hw_tag && cfqd->rq_in_driver > 4) - cfqd->hw_tag = 1; - - cfqd->last_position = rq->hard_sector + rq->hard_nr_sectors; + cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq); } static void cfq_deactivate_request(struct request_queue *q, struct request *rq) @@ -686,9 +2314,11 @@ static void cfq_remove_request(struct request *rq) list_del_init(&rq->queuelist); cfq_del_rq_rb(rq); - if (rq_is_meta(rq)) { - WARN_ON(!cfqq->meta_pending); - cfqq->meta_pending--; + cfqq->cfqd->rq_queued--; + 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--; } } @@ -717,58 +2347,97 @@ 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) +{ + cfqg_stats_update_io_merged(RQ_CFQG(req), bio->bi_rw); +} + static void cfq_merged_requests(struct request_queue *q, struct request *rq, struct request *next) { + struct cfq_queue *cfqq = RQ_CFQQ(rq); + struct cfq_data *cfqd = q->elevator->elevator_data; + /* * reposition in fifo if next is older than rq */ if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) && - time_before(next->start_time, rq->start_time)) + time_before(next->fifo_time, rq->fifo_time) && + cfqq == RQ_CFQQ(next)) { list_move(&rq->queuelist, &next->queuelist); + rq->fifo_time = next->fifo_time; + } + if (cfqq->next_rq == next) + cfqq->next_rq = rq; cfq_remove_request(next); + cfqg_stats_update_io_merged(RQ_CFQG(rq), next->cmd_flags); + + cfqq = RQ_CFQQ(next); + /* + * all requests of this queue are merged to other queues, delete it + * from the service tree. If it's the active_queue, + * cfq_dispatch_requests() will choose to expire it or do idle + */ + if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list) && + cfqq != cfqd->active_queue) + cfq_del_cfqq_rr(cfqd, cfqq); } static int cfq_allow_merge(struct request_queue *q, struct request *rq, struct bio *bio) { struct cfq_data *cfqd = q->elevator->elevator_data; - struct cfq_io_context *cic; + struct cfq_io_cq *cic; struct cfq_queue *cfqq; /* * Disallow merge of a sync bio into an async request. */ if (cfq_bio_sync(bio) && !rq_is_sync(rq)) - return 0; + return false; /* - * Lookup the cfqq that this bio will be queued with. Allow + * Lookup the cfqq that this bio will be queued with and allow * merge only if rq is queued there. */ cic = cfq_cic_lookup(cfqd, current->io_context); if (!cic) - return 0; + return false; cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio)); - if (cfqq == RQ_CFQQ(rq)) - return 1; + return cfqq == RQ_CFQQ(rq); +} - return 0; +static inline void cfq_del_timer(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + del_timer(&cfqd->idle_slice_timer); + 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"); + 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; cfqq->slice_end = 0; + cfqq->slice_dispatch = 0; + cfqq->nr_sectors = 0; + + cfq_clear_cfqq_wait_request(cfqq); + cfq_clear_cfqq_must_dispatch(cfqq); cfq_clear_cfqq_must_alloc_slice(cfqq); cfq_clear_cfqq_fifo_expire(cfqq); cfq_mark_cfqq_slice_new(cfqq); - cfq_clear_cfqq_queue_new(cfqq); + + cfq_del_timer(cfqd, cfqq); } cfqd->active_queue = cfqq; @@ -779,36 +2448,53 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd, */ static void __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq, - int timed_out) + bool timed_out) { cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out); if (cfq_cfqq_wait_request(cfqq)) - del_timer(&cfqd->idle_slice_timer); + cfq_del_timer(cfqd, cfqq); - cfq_clear_cfqq_must_dispatch(cfqq); cfq_clear_cfqq_wait_request(cfqq); + cfq_clear_cfqq_wait_busy(cfqq); + + /* + * If this cfqq is shared between multiple processes, check to + * make sure that those processes are still issuing I/Os within + * the mean seek distance. If not, it may be time to break the + * queues apart again. + */ + if (cfq_cfqq_coop(cfqq) && CFQQ_SEEKY(cfqq)) + cfq_mark_cfqq_split_coop(cfqq); /* * store what was left of this slice, if the queue idled/timed out */ - if (timed_out && !cfq_cfqq_slice_new(cfqq)) { - cfqq->slice_resid = cfqq->slice_end - jiffies; + if (timed_out) { + if (cfq_cfqq_slice_new(cfqq)) + cfqq->slice_resid = cfq_scaled_cfqq_slice(cfqd, cfqq); + else + cfqq->slice_resid = cfqq->slice_end - jiffies; cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid); } + cfq_group_served(cfqd, cfqq->cfqg, cfqq); + + if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list)) + cfq_del_cfqq_rr(cfqd, cfqq); + cfq_resort_rr_list(cfqd, cfqq); if (cfqq == cfqd->active_queue) cfqd->active_queue = NULL; if (cfqd->active_cic) { - put_io_context(cfqd->active_cic->ioc); + put_io_context(cfqd->active_cic->icq.ioc); cfqd->active_cic = NULL; } } -static inline void cfq_slice_expired(struct cfq_data *cfqd, int timed_out) +static inline void cfq_slice_expired(struct cfq_data *cfqd, bool timed_out) { struct cfq_queue *cfqq = cfqd->active_queue; @@ -822,20 +2508,49 @@ static inline void cfq_slice_expired(struct cfq_data *cfqd, int timed_out) */ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd) { - if (RB_EMPTY_ROOT(&cfqd->service_tree.rb)) + 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 (!st) + return NULL; + if (RB_EMPTY_ROOT(&st->rb)) + return NULL; + return cfq_rb_first(st); +} + +static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd) +{ + struct cfq_group *cfqg; + struct cfq_queue *cfqq; + int i, j; + struct cfq_rb_root *st; + + if (!cfqd->rq_queued) + return NULL; + + cfqg = cfq_get_next_cfqg(cfqd); + if (!cfqg) return NULL; - return cfq_rb_first(&cfqd->service_tree); + for_each_cfqg_st(cfqg, i, j, st) + if ((cfqq = cfq_rb_first(st)) != NULL) + return cfqq; + return NULL; } /* * Get and set a new active queue for service. */ -static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd) +static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd, + struct cfq_queue *cfqq) { - struct cfq_queue *cfqq; + if (!cfqq) + cfqq = cfq_get_next_queue(cfqd); - cfqq = cfq_get_next_queue(cfqd); __cfq_set_active_queue(cfqd, cfqq); return cfqq; } @@ -843,40 +2558,165 @@ static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd) static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd, struct request *rq) { - if (rq->sector >= cfqd->last_position) - return rq->sector - cfqd->last_position; + if (blk_rq_pos(rq) >= cfqd->last_position) + return blk_rq_pos(rq) - cfqd->last_position; else - return cfqd->last_position - rq->sector; + return cfqd->last_position - blk_rq_pos(rq); } -static inline int cfq_rq_close(struct cfq_data *cfqd, struct request *rq) +static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq, + struct request *rq) { - struct cfq_io_context *cic = cfqd->active_cic; + return cfq_dist_from_last(cfqd, rq) <= CFQQ_CLOSE_THR; +} - if (!sample_valid(cic->seek_samples)) - return 0; +static struct cfq_queue *cfqq_close(struct cfq_data *cfqd, + struct cfq_queue *cur_cfqq) +{ + struct rb_root *root = &cfqd->prio_trees[cur_cfqq->org_ioprio]; + struct rb_node *parent, *node; + struct cfq_queue *__cfqq; + sector_t sector = cfqd->last_position; + + if (RB_EMPTY_ROOT(root)) + return NULL; + + /* + * First, if we find a request starting at the end of the last + * request, choose it. + */ + __cfqq = cfq_prio_tree_lookup(cfqd, root, sector, &parent, NULL); + if (__cfqq) + return __cfqq; + + /* + * If the exact sector wasn't found, the parent of the NULL leaf + * will contain the closest sector. + */ + __cfqq = rb_entry(parent, struct cfq_queue, p_node); + if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq)) + return __cfqq; + + if (blk_rq_pos(__cfqq->next_rq) < sector) + node = rb_next(&__cfqq->p_node); + else + node = rb_prev(&__cfqq->p_node); + if (!node) + return NULL; + + __cfqq = rb_entry(node, struct cfq_queue, p_node); + if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq)) + return __cfqq; - return cfq_dist_from_last(cfqd, rq) <= cic->seek_mean; + return NULL; } -static int cfq_close_cooperator(struct cfq_data *cfq_data, - struct cfq_queue *cfqq) +/* + * cfqd - obvious + * cur_cfqq - passed in so that we don't decide that the current queue is + * closely cooperating with itself. + * + * So, basically we're assuming that that cur_cfqq has dispatched at least + * one request, and that cfqd->last_position reflects a position on the disk + * associated with the I/O issued by cur_cfqq. I'm not sure this is a valid + * assumption. + */ +static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd, + struct cfq_queue *cur_cfqq) { + struct cfq_queue *cfqq; + + if (cfq_class_idle(cur_cfqq)) + return NULL; + if (!cfq_cfqq_sync(cur_cfqq)) + return NULL; + if (CFQQ_SEEKY(cur_cfqq)) + return NULL; + + /* + * Don't search priority tree if it's the only queue in the group. + */ + if (cur_cfqq->cfqg->nr_cfqq == 1) + return NULL; + /* * We should notice if some of the queues are cooperating, eg * working closely on the same area of the disk. In that case, * we can group them together and don't waste time idling. */ - return 0; + cfqq = cfqq_close(cfqd, cur_cfqq); + if (!cfqq) + return NULL; + + /* If new queue belongs to different cfq_group, don't choose it */ + if (cur_cfqq->cfqg != cfqq->cfqg) + return NULL; + + /* + * It only makes sense to merge sync queues. + */ + if (!cfq_cfqq_sync(cfqq)) + return NULL; + if (CFQQ_SEEKY(cfqq)) + return NULL; + + /* + * Do not merge queues of different priority classes + */ + if (cfq_class_rt(cfqq) != cfq_class_rt(cur_cfqq)) + return NULL; + + return cfqq; } -#define CIC_SEEKY(cic) ((cic)->seek_mean > (8 * 1024)) +/* + * Determine whether we should enforce idle window for this queue. + */ + +static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + enum wl_class_t wl_class = cfqq_class(cfqq); + struct cfq_rb_root *st = cfqq->service_tree; + + BUG_ON(!st); + BUG_ON(!st->count); + + if (!cfqd->cfq_slice_idle) + return false; + + /* We never do for idle class queues. */ + if (wl_class == IDLE_WORKLOAD) + return false; + + /* We do for queues that were marked with idle window flag. */ + if (cfq_cfqq_idle_window(cfqq) && + !(blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag)) + return true; + + /* + * Otherwise, we do only if they are the last ones + * in their service tree. + */ + 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", st->count); + return false; +} static void cfq_arm_slice_timer(struct cfq_data *cfqd) { struct cfq_queue *cfqq = cfqd->active_queue; - struct cfq_io_context *cic; - unsigned long sl; + struct cfq_io_cq *cic; + unsigned long sl, group_idle = 0; + + /* + * SSD device without seek penalty, disable idling. But only do so + * for devices that support queuing, otherwise we still have a problem + * with sync vs async workloads. + */ + if (blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag) + return; WARN_ON(!RB_EMPTY_ROOT(&cfqq->sort_list)); WARN_ON(cfq_cfqq_slice_new(cfqq)); @@ -884,43 +2724,54 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) /* * idle is disabled, either manually or by past process history */ - if (!cfqd->cfq_slice_idle || !cfq_cfqq_idle_window(cfqq)) - return; + if (!cfq_should_idle(cfqd, cfqq)) { + /* no queue idling. Check for group idling */ + if (cfqd->cfq_group_idle) + group_idle = cfqd->cfq_group_idle; + else + return; + } /* - * still requests with the driver, don't idle + * still active requests from this queue, don't idle */ - if (cfqd->rq_in_driver) + if (cfqq->dispatched) return; /* * task has exited, don't wait */ cic = cfqd->active_cic; - if (!cic || !atomic_read(&cic->ioc->nr_tasks)) + if (!cic || !atomic_read(&cic->icq.ioc->active_ref)) return; /* - * See if this prio level has a good candidate + * If our average think time is larger than the remaining time + * slice, then don't idle. This avoids overrunning the allotted + * time slice. */ - if (cfq_close_cooperator(cfqd, cfqq) && - (sample_valid(cic->ttime_samples) && cic->ttime_mean > 2)) + if (sample_valid(cic->ttime.ttime_samples) && + (cfqq->slice_end - jiffies < cic->ttime.ttime_mean)) { + cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%lu", + cic->ttime.ttime_mean); + return; + } + + /* There are other queues in the group, don't do group idle */ + if (group_idle && cfqq->cfqg->nr_cfqq > 1) return; - cfq_mark_cfqq_must_dispatch(cfqq); cfq_mark_cfqq_wait_request(cfqq); - /* - * we don't want to idle for seeks, but we do want to allow - * fair distribution of slice time for a process doing back-to-back - * seeks. so allow a little bit of time for him to submit a new rq - */ - sl = cfqd->cfq_slice_idle; - if (sample_valid(cic->seek_samples) && CIC_SEEKY(cic)) - sl = min(sl, msecs_to_jiffies(CFQ_MIN_TT)); + if (group_idle) + sl = cfqd->cfq_group_idle; + else + sl = cfqd->cfq_slice_idle; mod_timer(&cfqd->idle_slice_timer, jiffies + sl); - cfq_log(cfqd, "arm_idle: %lu", sl); + cfqg_stats_set_start_idle_time(cfqq->cfqg); + cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu group_idle: %d", sl, + group_idle ? 1 : 0); } /* @@ -933,12 +2784,15 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq) cfq_log_cfqq(cfqd, cfqq, "dispatch_insert"); + cfqq->next_rq = cfq_find_next_rq(cfqd, cfqq, rq); cfq_remove_request(rq); cfqq->dispatched++; + (RQ_CFQG(rq))->dispatched++; elv_dispatch_sort(q, rq); - if (cfq_cfqq_sync(cfqq)) - cfqd->sync_flight++; + cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++; + cfqq->nr_sectors += blk_rq_sectors(rq); + cfqg_stats_update_dispatch(cfqq->cfqg, blk_rq_bytes(rq), rq->cmd_flags); } /* @@ -946,9 +2800,7 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq) */ static struct request *cfq_check_fifo(struct cfq_queue *cfqq) { - struct cfq_data *cfqd = cfqq->cfqd; - struct request *rq; - int fifo; + struct request *rq = NULL; if (cfq_cfqq_fifo_expire(cfqq)) return NULL; @@ -958,13 +2810,11 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq) if (list_empty(&cfqq->fifo)) return NULL; - fifo = cfq_cfqq_sync(cfqq); rq = rq_entry_fifo(cfqq->fifo.next); - - if (time_before(jiffies, rq->start_time + cfqd->cfq_fifo_expire[fifo])) + if (time_before(jiffies, rq->fifo_time)) rq = NULL; - cfq_log_cfqq(cfqd, cfqq, "fifo=%p", rq); + cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq); return rq; } @@ -975,7 +2825,197 @@ cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq) WARN_ON(cfqq->ioprio >= IOPRIO_BE_NR); - return 2 * (base_rq + base_rq * (CFQ_PRIO_LISTS - 1 - cfqq->ioprio)); + return 2 * base_rq * (IOPRIO_BE_NR - cfqq->ioprio); +} + +/* + * Must be called with the queue_lock held. + */ +static int cfqq_process_refs(struct cfq_queue *cfqq) +{ + int process_refs, io_refs; + + io_refs = cfqq->allocated[READ] + cfqq->allocated[WRITE]; + process_refs = cfqq->ref - io_refs; + BUG_ON(process_refs < 0); + return process_refs; +} + +static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq) +{ + int process_refs, new_process_refs; + struct cfq_queue *__cfqq; + + /* + * If there are no process references on the new_cfqq, then it is + * unsafe to follow the ->new_cfqq chain as other cfqq's in the + * chain may have dropped their last reference (not just their + * last process reference). + */ + if (!cfqq_process_refs(new_cfqq)) + return; + + /* Avoid a circular list and skip interim queue merges */ + while ((__cfqq = new_cfqq->new_cfqq)) { + if (__cfqq == cfqq) + return; + new_cfqq = __cfqq; + } + + process_refs = cfqq_process_refs(cfqq); + new_process_refs = cfqq_process_refs(new_cfqq); + /* + * If the process for the cfqq has gone away, there is no + * sense in merging the queues. + */ + if (process_refs == 0 || new_process_refs == 0) + return; + + /* + * Merge in the direction of the lesser amount of work. + */ + if (new_process_refs >= process_refs) { + cfqq->new_cfqq = new_cfqq; + new_cfqq->ref += process_refs; + } else { + new_cfqq->new_cfqq = cfqq; + cfqq->ref += new_process_refs; + } +} + +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; + bool key_valid = false; + unsigned long lowest_key = 0; + enum wl_type_t cur_best = SYNC_NOIDLE_WORKLOAD; + + for (i = 0; i <= SYNC_WORKLOAD; ++i) { + /* select the one with lowest rb_key */ + 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; + cur_best = i; + key_valid = true; + } + } + + return cur_best; +} + +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_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_wl_class = RT_WORKLOAD; + else if (cfq_group_busy_queues_wl(BE_WORKLOAD, cfqd, cfqg)) + cfqd->serving_wl_class = BE_WORKLOAD; + else { + cfqd->serving_wl_class = IDLE_WORKLOAD; + cfqd->workload_expires = jiffies + 1; + return; + } + + if (original_class != cfqd->serving_wl_class) + goto new_workload; + + /* + * For RT and BE, we have to choose also the type + * (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload + * expiration time + */ + st = st_for(cfqg, cfqd->serving_wl_class, cfqd->serving_wl_type); + count = st->count; + + /* + * check workload expiration, and that we still have other queues ready + */ + if (count && !time_after(jiffies, cfqd->workload_expires)) + return; + +new_workload: + /* otherwise select new workload 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; + + /* + * the workload slice is computed as a fraction of target latency + * proportional to the number of queues in that workload, over + * all the queues in the same priority class + */ + group_slice = cfq_group_slice(cfqd, cfqg); + + slice = group_slice * count / + 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_wl_type == ASYNC_WORKLOAD) { + unsigned int tmp; + + /* + * Async queues are currently system wide. Just taking + * proportion of queues with-in same group will lead to higher + * async ratio system wide as generally root group is going + * to have higher weight. A more accurate thing would be to + * calculate system wide asnc/sync ratio. + */ + tmp = cfqd->cfq_target_latency * + cfqg_busy_async_queues(cfqd, cfqg); + tmp = tmp/cfqd->busy_queues; + slice = min_t(unsigned, slice, tmp); + + /* async workload slice is scaled down according to + * the sync/async slice ratio. */ + slice = slice * cfqd->cfq_slice[0] / cfqd->cfq_slice[1]; + } else + /* sync workload slice is at least 2 * cfq_slice_idle */ + slice = max(slice, 2 * cfqd->cfq_slice_idle); + + slice = max_t(unsigned, slice, CFQ_MIN_TT); + cfq_log(cfqd, "workload slice:%d", slice); + cfqd->workload_expires = jiffies + slice; +} + +static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd) +{ + struct cfq_rb_root *st = &cfqd->grp_service_tree; + struct cfq_group *cfqg; + + if (RB_EMPTY_ROOT(&st->rb)) + return NULL; + cfqg = cfq_rb_first_group(st); + update_min_vdisktime(st); + return cfqg; +} + +static void cfq_choose_cfqg(struct cfq_data *cfqd) +{ + struct cfq_group *cfqg = cfq_get_next_cfqg(cfqd); + + cfqd->serving_group = cfqg; + + /* Restore the workload type data */ + 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_wl_class_and_type(cfqd, cfqg); } /* @@ -984,19 +3024,43 @@ cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq) */ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) { - struct cfq_queue *cfqq; + struct cfq_queue *cfqq, *new_cfqq = NULL; cfqq = cfqd->active_queue; if (!cfqq) goto new_queue; + if (!cfqd->rq_queued) + return NULL; + /* - * The active queue has run out of time, expire it and select new. + * We were waiting for group to get backlogged. Expire the queue */ - if (cfq_slice_used(cfqq)) + if (cfq_cfqq_wait_busy(cfqq) && !RB_EMPTY_ROOT(&cfqq->sort_list)) goto expire; /* + * The active queue has run out of time, expire it and select new. + */ + if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq)) { + /* + * If slice had not expired at the completion of last request + * we might not have turned on wait_busy flag. Don't expire + * the queue yet. Allow the group to get backlogged. + * + * The very fact that we have used the slice, that means we + * have been idling all along on this queue and it should be + * ok to wait for this request to complete. + */ + if (cfqq->cfqg->nr_cfqq == 1 && RB_EMPTY_ROOT(&cfqq->sort_list) + && cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) { + cfqq = NULL; + goto keep_queue; + } else + goto check_group_idle; + } + + /* * The active queue has requests and isn't expired, allow it to * dispatch. */ @@ -1004,12 +3068,52 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) goto keep_queue; /* + * If another queue has a request waiting within our mean seek + * distance, let it run. The expire code will check for close + * cooperators and put the close queue at the front of the service + * tree. If possible, merge the expiring queue with the new cfqq. + */ + new_cfqq = cfq_close_cooperator(cfqd, cfqq); + if (new_cfqq) { + if (!cfqq->new_cfqq) + cfq_setup_merge(cfqq, new_cfqq); + goto expire; + } + + /* * No requests pending. If the active queue still has requests in * flight or is idling for a new request, allow either of these * conditions to happen (or time out) before selecting a new queue. */ - if (timer_pending(&cfqd->idle_slice_timer) || - (cfqq->dispatched && cfq_cfqq_idle_window(cfqq))) { + if (timer_pending(&cfqd->idle_slice_timer)) { + cfqq = NULL; + goto keep_queue; + } + + /* + * This is a deep seek queue, but the device is much faster than + * the queue can deliver, don't idle + **/ + if (CFQQ_SEEKY(cfqq) && cfq_cfqq_idle_window(cfqq) && + (cfq_cfqq_slice_new(cfqq) || + (cfqq->slice_end - jiffies > jiffies - cfqq->slice_start))) { + cfq_clear_cfqq_deep(cfqq); + cfq_clear_cfqq_idle_window(cfqq); + } + + if (cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) { + cfqq = NULL; + goto keep_queue; + } + + /* + * If group idle is enabled and there are requests dispatched from + * this group, wait for requests to complete. + */ +check_group_idle: + if (cfqd->cfq_group_idle && cfqq->cfqg->nr_cfqq == 1 && + cfqq->cfqg->dispatched && + !cfq_io_thinktime_big(cfqd, &cfqq->cfqg->ttime, true)) { cfqq = NULL; goto keep_queue; } @@ -1017,102 +3121,197 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) expire: cfq_slice_expired(cfqd, 0); new_queue: - cfqq = cfq_set_active_queue(cfqd); + /* + * Current queue expired. Check if we have to switch to a new + * service tree + */ + if (!new_cfqq) + cfq_choose_cfqg(cfqd); + + cfqq = cfq_set_active_queue(cfqd, new_cfqq); keep_queue: return cfqq; } +static int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq) +{ + int dispatched = 0; + + while (cfqq->next_rq) { + cfq_dispatch_insert(cfqq->cfqd->queue, cfqq->next_rq); + dispatched++; + } + + BUG_ON(!list_empty(&cfqq->fifo)); + + /* By default cfqq is not expired if it is empty. Do it explicitly */ + __cfq_slice_expired(cfqq->cfqd, cfqq, 0); + return dispatched; +} + /* - * Dispatch some requests from cfqq, moving them to the request queue - * dispatch list. + * Drain our current requests. Used for barriers and when switching + * io schedulers on-the-fly. */ -static int -__cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq, - int max_dispatch) +static int cfq_forced_dispatch(struct cfq_data *cfqd) { + struct cfq_queue *cfqq; int dispatched = 0; - BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list)); + /* Expire the timeslice of the current active queue first */ + cfq_slice_expired(cfqd, 0); + while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL) { + __cfq_set_active_queue(cfqd, cfqq); + dispatched += __cfq_forced_dispatch_cfqq(cfqq); + } - do { - struct request *rq; + BUG_ON(cfqd->busy_queues); - /* - * follow expired path, else get first next available - */ - rq = cfq_check_fifo(cfqq); - if (rq == NULL) - rq = cfqq->next_rq; + cfq_log(cfqd, "forced_dispatch=%d", dispatched); + return dispatched; +} - /* - * finally, insert request into driver dispatch list - */ - cfq_dispatch_insert(cfqd->queue, rq); +static inline bool cfq_slice_used_soon(struct cfq_data *cfqd, + struct cfq_queue *cfqq) +{ + /* the queue hasn't finished any request, can't estimate */ + if (cfq_cfqq_slice_new(cfqq)) + return true; + if (time_after(jiffies + cfqd->cfq_slice_idle * cfqq->dispatched, + cfqq->slice_end)) + return true; - dispatched++; + return false; +} - if (!cfqd->active_cic) { - atomic_inc(&RQ_CIC(rq)->ioc->refcount); - cfqd->active_cic = RQ_CIC(rq); - } +static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + unsigned int max_dispatch; - if (RB_EMPTY_ROOT(&cfqq->sort_list)) - break; + /* + * Drain async requests before we start sync IO + */ + if (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_flight[BLK_RW_ASYNC]) + return false; - } while (dispatched < max_dispatch); + /* + * If this is an async queue and we have sync IO in flight, let it wait + */ + if (cfqd->rq_in_flight[BLK_RW_SYNC] && !cfq_cfqq_sync(cfqq)) + return false; + + max_dispatch = max_t(unsigned int, cfqd->cfq_quantum / 2, 1); + if (cfq_class_idle(cfqq)) + max_dispatch = 1; /* - * expire an async queue immediately if it has used up its slice. idle - * queue always expire after 1 dispatch round. + * Does this cfqq already have too much IO in flight? */ - if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) && - dispatched >= cfq_prio_to_maxrq(cfqd, cfqq)) || - cfq_class_idle(cfqq))) { - cfqq->slice_end = jiffies + 1; - cfq_slice_expired(cfqd, 0); - } + if (cfqq->dispatched >= max_dispatch) { + bool promote_sync = false; + /* + * idle queue must always only have a single IO in flight + */ + if (cfq_class_idle(cfqq)) + return false; - return dispatched; -} + /* + * If there is only one sync queue + * we can ignore async queue here and give the sync + * queue no dispatch limit. The reason is a sync queue can + * preempt async queue, limiting the sync queue doesn't make + * sense. This is useful for aiostress test. + */ + if (cfq_cfqq_sync(cfqq) && cfqd->busy_sync_queues == 1) + promote_sync = true; -static int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq) -{ - int dispatched = 0; + /* + * We have other queues, don't allow more IO from this one + */ + if (cfqd->busy_queues > 1 && cfq_slice_used_soon(cfqd, cfqq) && + !promote_sync) + return false; - while (cfqq->next_rq) { - cfq_dispatch_insert(cfqq->cfqd->queue, cfqq->next_rq); - dispatched++; + /* + * Sole queue user, no limit + */ + if (cfqd->busy_queues == 1 || promote_sync) + max_dispatch = -1; + else + /* + * Normally we start throttling cfqq when cfq_quantum/2 + * requests have been dispatched. But we can drive + * deeper queue depths at the beginning of slice + * subjected to upper limit of cfq_quantum. + * */ + max_dispatch = cfqd->cfq_quantum; } - BUG_ON(!list_empty(&cfqq->fifo)); - return dispatched; + /* + * Async queues must wait a bit before being allowed dispatch. + * We also ramp up the dispatch depth gradually for async IO, + * based on the last sync IO we serviced + */ + if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_latency) { + unsigned long last_sync = jiffies - cfqd->last_delayed_sync; + unsigned int depth; + + depth = last_sync / cfqd->cfq_slice[1]; + if (!depth && !cfqq->dispatched) + depth = 1; + if (depth < max_dispatch) + max_dispatch = depth; + } + + /* + * If we're below the current max, allow a dispatch + */ + return cfqq->dispatched < max_dispatch; } /* - * Drain our current requests. Used for barriers and when switching - * io schedulers on-the-fly. + * Dispatch a request from cfqq, moving them to the request queue + * dispatch list. */ -static int cfq_forced_dispatch(struct cfq_data *cfqd) +static bool cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq) { - struct cfq_queue *cfqq; - int dispatched = 0; + struct request *rq; - while ((cfqq = cfq_rb_first(&cfqd->service_tree)) != NULL) - dispatched += __cfq_forced_dispatch_cfqq(cfqq); + BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list)); - cfq_slice_expired(cfqd, 0); + if (!cfq_may_dispatch(cfqd, cfqq)) + return false; - BUG_ON(cfqd->busy_queues); + /* + * follow expired path, else get first next available + */ + rq = cfq_check_fifo(cfqq); + if (!rq) + rq = cfqq->next_rq; - cfq_log(cfqd, "forced_dispatch=%d\n", dispatched); - return dispatched; + /* + * insert request into driver dispatch list + */ + cfq_dispatch_insert(cfqd->queue, rq); + + if (!cfqd->active_cic) { + struct cfq_io_cq *cic = RQ_CIC(rq); + + atomic_long_inc(&cic->icq.ioc->refcount); + cfqd->active_cic = cic; + } + + return true; } +/* + * Find the cfqq that we need to service and move a request from that to the + * dispatch list + */ static int cfq_dispatch_requests(struct request_queue *q, int force) { struct cfq_data *cfqd = q->elevator->elevator_data; struct cfq_queue *cfqq; - int dispatched; if (!cfqd->busy_queues) return 0; @@ -1120,146 +3319,86 @@ static int cfq_dispatch_requests(struct request_queue *q, int force) if (unlikely(force)) return cfq_forced_dispatch(cfqd); - dispatched = 0; - while ((cfqq = cfq_select_queue(cfqd)) != NULL) { - int max_dispatch; - - max_dispatch = cfqd->cfq_quantum; - if (cfq_class_idle(cfqq)) - max_dispatch = 1; - - if (cfqq->dispatched >= max_dispatch) { - if (cfqd->busy_queues > 1) - break; - if (cfqq->dispatched >= 4 * max_dispatch) - break; - } + cfqq = cfq_select_queue(cfqd); + if (!cfqq) + return 0; - if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq)) - break; + /* + * Dispatch a request from this cfqq, if it is allowed + */ + if (!cfq_dispatch_request(cfqd, cfqq)) + return 0; - cfq_clear_cfqq_must_dispatch(cfqq); - cfq_clear_cfqq_wait_request(cfqq); - del_timer(&cfqd->idle_slice_timer); + cfqq->slice_dispatch++; + cfq_clear_cfqq_must_dispatch(cfqq); - dispatched += __cfq_dispatch_requests(cfqd, cfqq, max_dispatch); + /* + * expire an async queue immediately if it has used up its slice. idle + * queue always expire after 1 dispatch round. + */ + if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) && + cfqq->slice_dispatch >= cfq_prio_to_maxrq(cfqd, cfqq)) || + cfq_class_idle(cfqq))) { + cfqq->slice_end = jiffies + 1; + cfq_slice_expired(cfqd, 0); } - cfq_log(cfqd, "dispatched=%d", dispatched); - return dispatched; + cfq_log_cfqq(cfqd, cfqq, "dispatched a request"); + return 1; } /* * task holds one reference to the queue, dropped when task exits. each rq * in-flight on this queue also holds a reference, dropped when rq is freed. * + * Each cfq queue took a reference on the parent group. Drop it now. * queue lock must be held here. */ static void cfq_put_queue(struct cfq_queue *cfqq) { struct cfq_data *cfqd = cfqq->cfqd; + struct cfq_group *cfqg; - BUG_ON(atomic_read(&cfqq->ref) <= 0); + BUG_ON(cfqq->ref <= 0); - if (!atomic_dec_and_test(&cfqq->ref)) + cfqq->ref--; + if (cfqq->ref) return; cfq_log_cfqq(cfqd, cfqq, "put_queue"); BUG_ON(rb_first(&cfqq->sort_list)); BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]); - BUG_ON(cfq_cfqq_on_rr(cfqq)); + cfqg = cfqq->cfqg; if (unlikely(cfqd->active_queue == cfqq)) { __cfq_slice_expired(cfqd, cfqq, 0); cfq_schedule_dispatch(cfqd); } + BUG_ON(cfq_cfqq_on_rr(cfqq)); kmem_cache_free(cfq_pool, cfqq); + cfqg_put(cfqg); } -/* - * Must always be called with the rcu_read_lock() held - */ -static void -__call_for_each_cic(struct io_context *ioc, - void (*func)(struct io_context *, struct cfq_io_context *)) +static void cfq_put_cooperator(struct cfq_queue *cfqq) { - struct cfq_io_context *cic; - struct hlist_node *n; + struct cfq_queue *__cfqq, *next; - hlist_for_each_entry_rcu(cic, n, &ioc->cic_list, cic_list) - func(ioc, cic); -} - -/* - * Call func for each cic attached to this ioc. - */ -static void -call_for_each_cic(struct io_context *ioc, - void (*func)(struct io_context *, struct cfq_io_context *)) -{ - rcu_read_lock(); - __call_for_each_cic(ioc, func); - rcu_read_unlock(); -} - -static void cfq_cic_free_rcu(struct rcu_head *head) -{ - struct cfq_io_context *cic; - - cic = container_of(head, struct cfq_io_context, rcu_head); - - kmem_cache_free(cfq_ioc_pool, cic); - elv_ioc_count_dec(ioc_count); - - if (ioc_gone) { - /* - * CFQ scheduler is exiting, grab exit lock and check - * the pending io context count. If it hits zero, - * complete ioc_gone and set it back to NULL - */ - spin_lock(&ioc_gone_lock); - if (ioc_gone && !elv_ioc_count_read(ioc_count)) { - complete(ioc_gone); - ioc_gone = NULL; - } - spin_unlock(&ioc_gone_lock); - } -} - -static void cfq_cic_free(struct cfq_io_context *cic) -{ - call_rcu(&cic->rcu_head, cfq_cic_free_rcu); -} - -static void cic_free_func(struct io_context *ioc, struct cfq_io_context *cic) -{ - unsigned long flags; - - BUG_ON(!cic->dead_key); - - spin_lock_irqsave(&ioc->lock, flags); - radix_tree_delete(&ioc->radix_root, cic->dead_key); - hlist_del_rcu(&cic->cic_list); - spin_unlock_irqrestore(&ioc->lock, flags); - - cfq_cic_free(cic); -} - -/* - * Must be called with rcu_read_lock() held or preemption otherwise disabled. - * Only two callers of this - ->dtor() which is called with the rcu_read_lock(), - * and ->trim() which is called with the task lock held - */ -static void cfq_free_io_context(struct io_context *ioc) -{ /* - * ioc->refcount is zero here, or we are called from elv_unregister(), - * so no more cic's are allowed to be linked into this ioc. So it - * should be ok to iterate over the known list, we will see all cic's - * since no new ones are added. + * If this queue was scheduled to merge with another queue, be + * sure to drop the reference taken on that queue (and others in + * the merge chain). See cfq_setup_merge and cfq_merge_cfqqs. */ - __call_for_each_cic(ioc, cic_free_func); + __cfqq = cfqq->new_cfqq; + while (__cfqq) { + if (__cfqq == cfqq) { + WARN(1, "cfqq->new_cfqq loop detected\n"); + break; + } + next = __cfqq->new_cfqq; + cfq_put_queue(__cfqq); + __cfqq = next; + } } static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) @@ -1269,81 +3408,35 @@ static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) cfq_schedule_dispatch(cfqd); } + cfq_put_cooperator(cfqq); + cfq_put_queue(cfqq); } -static void __cfq_exit_single_io_context(struct cfq_data *cfqd, - struct cfq_io_context *cic) +static void cfq_init_icq(struct io_cq *icq) { - struct io_context *ioc = cic->ioc; - - list_del_init(&cic->queue_list); - - /* - * Make sure key == NULL is seen for dead queues - */ - smp_wmb(); - cic->dead_key = (unsigned long) cic->key; - cic->key = NULL; - - if (ioc->ioc_data == cic) - rcu_assign_pointer(ioc->ioc_data, NULL); - - if (cic->cfqq[ASYNC]) { - cfq_exit_cfqq(cfqd, cic->cfqq[ASYNC]); - cic->cfqq[ASYNC] = NULL; - } + struct cfq_io_cq *cic = icq_to_cic(icq); - if (cic->cfqq[SYNC]) { - cfq_exit_cfqq(cfqd, cic->cfqq[SYNC]); - cic->cfqq[SYNC] = NULL; - } + cic->ttime.last_end_request = jiffies; } -static void cfq_exit_single_io_context(struct io_context *ioc, - struct cfq_io_context *cic) +static void cfq_exit_icq(struct io_cq *icq) { - struct cfq_data *cfqd = cic->key; - - if (cfqd) { - struct request_queue *q = cfqd->queue; - unsigned long flags; + struct cfq_io_cq *cic = icq_to_cic(icq); + struct cfq_data *cfqd = cic_to_cfqd(cic); - spin_lock_irqsave(q->queue_lock, flags); - __cfq_exit_single_io_context(cfqd, cic); - spin_unlock_irqrestore(q->queue_lock, flags); + if (cic->cfqq[BLK_RW_ASYNC]) { + cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_ASYNC]); + cic->cfqq[BLK_RW_ASYNC] = NULL; } -} -/* - * The process that ioc belongs to has exited, we need to clean up - * and put the internal structures we have that belongs to that process. - */ -static void cfq_exit_io_context(struct io_context *ioc) -{ - call_for_each_cic(ioc, cfq_exit_single_io_context); -} - -static struct cfq_io_context * -cfq_alloc_io_context(struct cfq_data *cfqd, gfp_t gfp_mask) -{ - struct cfq_io_context *cic; - - cic = kmem_cache_alloc_node(cfq_ioc_pool, gfp_mask | __GFP_ZERO, - cfqd->queue->node); - if (cic) { - cic->last_end_request = jiffies; - INIT_LIST_HEAD(&cic->queue_list); - INIT_HLIST_NODE(&cic->cic_list); - cic->dtor = cfq_free_io_context; - cic->exit = cfq_exit_io_context; - elv_ioc_count_inc(ioc_count); + if (cic->cfqq[BLK_RW_SYNC]) { + cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_SYNC]); + cic->cfqq[BLK_RW_SYNC] = NULL; } - - return cic; } -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; @@ -1351,7 +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); @@ -1363,11 +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: @@ -1382,106 +3475,149 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc) * elevate the priority of this queue */ cfqq->org_ioprio = cfqq->ioprio; - cfqq->org_ioprio_class = cfqq->ioprio_class; cfq_clear_cfqq_prio_changed(cfqq); } -static void changed_ioprio(struct io_context *ioc, struct cfq_io_context *cic) +static void check_ioprio_changed(struct cfq_io_cq *cic, struct bio *bio) { - struct cfq_data *cfqd = cic->key; + int ioprio = cic->icq.ioc->ioprio; + struct cfq_data *cfqd = cic_to_cfqd(cic); struct cfq_queue *cfqq; - unsigned long flags; - 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; - spin_lock_irqsave(cfqd->queue->queue_lock, flags); - - cfqq = cic->cfqq[ASYNC]; + cfqq = cic->cfqq[BLK_RW_ASYNC]; if (cfqq) { struct cfq_queue *new_cfqq; - new_cfqq = cfq_get_queue(cfqd, ASYNC, cic->ioc, GFP_ATOMIC); + new_cfqq = cfq_get_queue(cfqd, BLK_RW_ASYNC, cic, bio, + GFP_ATOMIC); if (new_cfqq) { - cic->cfqq[ASYNC] = new_cfqq; + cic->cfqq[BLK_RW_ASYNC] = new_cfqq; cfq_put_queue(cfqq); } } - cfqq = cic->cfqq[SYNC]; + cfqq = cic->cfqq[BLK_RW_SYNC]; if (cfqq) cfq_mark_cfqq_prio_changed(cfqq); - spin_unlock_irqrestore(cfqd->queue->queue_lock, flags); + cic->ioprio = ioprio; +} + +static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq, + pid_t pid, bool is_sync) +{ + RB_CLEAR_NODE(&cfqq->rb_node); + RB_CLEAR_NODE(&cfqq->p_node); + INIT_LIST_HEAD(&cfqq->fifo); + + cfqq->ref = 0; + cfqq->cfqd = cfqd; + + cfq_mark_cfqq_prio_changed(cfqq); + + if (is_sync) { + if (!cfq_class_idle(cfqq)) + cfq_mark_cfqq_idle_window(cfqq); + cfq_mark_cfqq_sync(cfqq); + } + cfqq->pid = pid; } -static void cfq_ioc_set_ioprio(struct io_context *ioc) +#ifdef CONFIG_CFQ_GROUP_IOSCHED +static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) { - call_for_each_cic(ioc, changed_ioprio); - ioc->ioprio_changed = 0; + struct cfq_data *cfqd = cic_to_cfqd(cic); + struct cfq_queue *sync_cfqq; + uint64_t id; + + rcu_read_lock(); + id = bio_blkcg(bio)->id; + rcu_read_unlock(); + + /* + * 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 + * assigned in new group upon arrival of a fresh request. + */ + cfq_log_cfqq(cfqd, sync_cfqq, "changed cgroup"); + 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, int 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_context *cic; + struct cfq_group *cfqg; retry: - 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); - if (!cfqq) { + /* + * Always try a new alloc if we fell back to the OOM cfqq + * originally, since it should just be a temporary situation. + */ + if (!cfqq || cfqq == &cfqd->oom_cfqq) { + cfqq = NULL; if (new_cfqq) { cfqq = new_cfqq; new_cfqq = NULL; } else if (gfp_mask & __GFP_WAIT) { - /* - * Inform the allocator of the fact that we will - * just repeat this allocation if it fails, to allow - * the allocator to do whatever it needs to attempt to - * free memory. - */ + rcu_read_unlock(); spin_unlock_irq(cfqd->queue->queue_lock); new_cfqq = kmem_cache_alloc_node(cfq_pool, - gfp_mask | __GFP_NOFAIL | __GFP_ZERO, + gfp_mask | __GFP_ZERO, cfqd->queue->node); spin_lock_irq(cfqd->queue->queue_lock); - goto retry; + if (new_cfqq) + goto retry; + else + return &cfqd->oom_cfqq; } else { cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask | __GFP_ZERO, cfqd->queue->node); - if (!cfqq) - goto out; } - RB_CLEAR_NODE(&cfqq->rb_node); - INIT_LIST_HEAD(&cfqq->fifo); - - atomic_set(&cfqq->ref, 0); - cfqq->cfqd = cfqd; - - cfq_mark_cfqq_prio_changed(cfqq); - cfq_mark_cfqq_queue_new(cfqq); - - cfq_init_prio_data(cfqq, ioc); - - if (is_sync) { - if (!cfq_class_idle(cfqq)) - cfq_mark_cfqq_idle_window(cfqq); - cfq_mark_cfqq_sync(cfqq); - } - cfqq->pid = current->pid; - cfq_log_cfqq(cfqd, cfqq, "alloced"); + if (cfqq) { + cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync); + cfq_init_prio_data(cfqq, cic); + cfq_link_cfqq_cfqg(cfqq, cfqg); + cfq_log_cfqq(cfqd, cfqq, "alloced"); + } else + cfqq = &cfqd->oom_cfqq; } if (new_cfqq) kmem_cache_free(cfq_pool, new_cfqq); -out: - WARN_ON((gfp_mask & __GFP_WAIT) && !cfqq); + rcu_read_unlock(); return cfqq; } @@ -1491,6 +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: @@ -1501,11 +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, int 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; @@ -1514,205 +3653,64 @@ cfq_get_queue(struct cfq_data *cfqd, int is_sync, struct io_context *ioc, cfqq = *async_cfqq; } - if (!cfqq) { - cfqq = cfq_find_alloc_queue(cfqd, is_sync, ioc, gfp_mask); - if (!cfqq) - return NULL; - } + if (!cfqq) + 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 */ if (!is_sync && !(*async_cfqq)) { - atomic_inc(&cfqq->ref); + cfqq->ref++; *async_cfqq = cfqq; } - atomic_inc(&cfqq->ref); + cfqq->ref++; return cfqq; } -/* - * We drop cfq io contexts lazily, so we may find a dead one. - */ static void -cfq_drop_dead_cic(struct cfq_data *cfqd, struct io_context *ioc, - struct cfq_io_context *cic) +__cfq_update_io_thinktime(struct cfq_ttime *ttime, unsigned long slice_idle) { - unsigned long flags; - - WARN_ON(!list_empty(&cic->queue_list)); - - spin_lock_irqsave(&ioc->lock, flags); + unsigned long elapsed = jiffies - ttime->last_end_request; + elapsed = min(elapsed, 2UL * slice_idle); - BUG_ON(ioc->ioc_data == cic); - - radix_tree_delete(&ioc->radix_root, (unsigned long) cfqd); - hlist_del_rcu(&cic->cic_list); - spin_unlock_irqrestore(&ioc->lock, flags); - - cfq_cic_free(cic); -} - -static struct cfq_io_context * -cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc) -{ - struct cfq_io_context *cic; - unsigned long flags; - void *k; - - if (unlikely(!ioc)) - return NULL; - - rcu_read_lock(); - - /* - * we maintain a last-hit cache, to avoid browsing over the tree - */ - cic = rcu_dereference(ioc->ioc_data); - if (cic && cic->key == cfqd) { - rcu_read_unlock(); - return cic; - } - - do { - cic = radix_tree_lookup(&ioc->radix_root, (unsigned long) cfqd); - rcu_read_unlock(); - if (!cic) - break; - /* ->key must be copied to avoid race with cfq_exit_queue() */ - k = cic->key; - if (unlikely(!k)) { - cfq_drop_dead_cic(cfqd, ioc, cic); - rcu_read_lock(); - continue; - } - - spin_lock_irqsave(&ioc->lock, flags); - rcu_assign_pointer(ioc->ioc_data, cic); - spin_unlock_irqrestore(&ioc->lock, flags); - break; - } while (1); - - return cic; -} - -/* - * Add cic into ioc, using cfqd as the search key. This enables us to lookup - * the process specific cfq io context when entered from the block layer. - * Also adds the cic to a per-cfqd list, used when this queue is removed. - */ -static int cfq_cic_link(struct cfq_data *cfqd, struct io_context *ioc, - struct cfq_io_context *cic, gfp_t gfp_mask) -{ - unsigned long flags; - int ret; - - ret = radix_tree_preload(gfp_mask); - if (!ret) { - cic->ioc = ioc; - cic->key = cfqd; - - spin_lock_irqsave(&ioc->lock, flags); - ret = radix_tree_insert(&ioc->radix_root, - (unsigned long) cfqd, cic); - if (!ret) - hlist_add_head_rcu(&cic->cic_list, &ioc->cic_list); - spin_unlock_irqrestore(&ioc->lock, flags); - - radix_tree_preload_end(); - - if (!ret) { - spin_lock_irqsave(cfqd->queue->queue_lock, flags); - list_add(&cic->queue_list, &cfqd->cic_list); - spin_unlock_irqrestore(cfqd->queue->queue_lock, flags); - } - } - - if (ret) - printk(KERN_ERR "cfq: cic link failed!\n"); - - return ret; -} - -/* - * Setup general io context and cfq io context. There can be several cfq - * io contexts per general io context, if this process is doing io to more - * than one device managed by cfq. - */ -static struct cfq_io_context * -cfq_get_io_context(struct cfq_data *cfqd, gfp_t gfp_mask) -{ - struct io_context *ioc = NULL; - struct cfq_io_context *cic; - - might_sleep_if(gfp_mask & __GFP_WAIT); - - ioc = get_io_context(gfp_mask, cfqd->queue->node); - if (!ioc) - return NULL; - - cic = cfq_cic_lookup(cfqd, ioc); - if (cic) - goto out; - - cic = cfq_alloc_io_context(cfqd, gfp_mask); - if (cic == NULL) - goto err; - - if (cfq_cic_link(cfqd, ioc, cic, gfp_mask)) - goto err_free; - -out: - smp_read_barrier_depends(); - if (unlikely(ioc->ioprio_changed)) - cfq_ioc_set_ioprio(ioc); - - return cic; -err_free: - cfq_cic_free(cic); -err: - put_io_context(ioc); - return NULL; + ttime->ttime_samples = (7*ttime->ttime_samples + 256) / 8; + ttime->ttime_total = (7*ttime->ttime_total + 256*elapsed) / 8; + ttime->ttime_mean = (ttime->ttime_total + 128) / ttime->ttime_samples; } static void -cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_io_context *cic) +cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_queue *cfqq, + struct cfq_io_cq *cic) { - unsigned long elapsed = jiffies - cic->last_end_request; - unsigned long ttime = min(elapsed, 2UL * cfqd->cfq_slice_idle); - - cic->ttime_samples = (7*cic->ttime_samples + 256) / 8; - cic->ttime_total = (7*cic->ttime_total + 256*ttime) / 8; - cic->ttime_mean = (cic->ttime_total + 128) / cic->ttime_samples; + if (cfq_cfqq_sync(cfqq)) { + __cfq_update_io_thinktime(&cic->ttime, cfqd->cfq_slice_idle); + __cfq_update_io_thinktime(&cfqq->service_tree->ttime, + cfqd->cfq_slice_idle); + } +#ifdef CONFIG_CFQ_GROUP_IOSCHED + __cfq_update_io_thinktime(&cfqq->cfqg->ttime, cfqd->cfq_group_idle); +#endif } static void -cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic, +cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq, struct request *rq) { - sector_t sdist; - u64 total; - - if (cic->last_request_pos < rq->sector) - sdist = rq->sector - cic->last_request_pos; - else - sdist = cic->last_request_pos - rq->sector; + sector_t sdist = 0; + sector_t n_sec = blk_rq_sectors(rq); + if (cfqq->last_request_pos) { + if (cfqq->last_request_pos < blk_rq_pos(rq)) + sdist = blk_rq_pos(rq) - cfqq->last_request_pos; + else + sdist = cfqq->last_request_pos - blk_rq_pos(rq); + } - /* - * Don't allow the seek distance to get too large from the - * odd fragment, pagein, etc - */ - if (cic->seek_samples <= 60) /* second&third seek */ - sdist = min(sdist, (cic->seek_mean * 4) + 2*1024*1024); + cfqq->seek_history <<= 1; + if (blk_queue_nonrot(cfqd->queue)) + cfqq->seek_history |= (n_sec < CFQQ_SECT_THR_NONROT); else - sdist = min(sdist, (cic->seek_mean * 4) + 2*1024*64); - - cic->seek_samples = (7*cic->seek_samples + 256) / 8; - cic->seek_total = (7*cic->seek_total + (u64)256*sdist) / 8; - total = cic->seek_total + (cic->seek_samples/2); - do_div(total, cic->seek_samples); - cic->seek_mean = (sector_t)total; + cfqq->seek_history |= (sdist > CFQQ_SEEK_THR); } /* @@ -1721,7 +3719,7 @@ cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic, */ static void cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq, - struct cfq_io_context *cic) + struct cfq_io_cq *cic) { int old_idle, enable_idle; @@ -1733,11 +3731,17 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq, enable_idle = old_idle = cfq_cfqq_idle_window(cfqq); - if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle || - (cfqd->hw_tag && CIC_SEEKY(cic))) + if (cfqq->queued[0] + cfqq->queued[1] >= 4) + cfq_mark_cfqq_deep(cfqq); + + if (cfqq->next_rq && (cfqq->next_rq->cmd_flags & REQ_NOIDLE)) + enable_idle = 0; + else if (!atomic_read(&cic->icq.ioc->active_ref) || + !cfqd->cfq_slice_idle || + (!cfq_cfqq_deep(cfqq) && CFQQ_SEEKY(cfqq))) enable_idle = 0; - else if (sample_valid(cic->ttime_samples)) { - if (cic->ttime_mean > cfqd->cfq_slice_idle) + else if (sample_valid(cic->ttime.ttime_samples)) { + if (cic->ttime.ttime_mean > cfqd->cfq_slice_idle) enable_idle = 0; else enable_idle = 1; @@ -1756,7 +3760,7 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq, * Check if new_cfqq should preempt the currently active queue. Return 0 for * no or if we aren't sure, a 1 will cause a preempt. */ -static int +static bool cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, struct request *rq) { @@ -1764,42 +3768,68 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, cfqq = cfqd->active_queue; if (!cfqq) - return 0; - - if (cfq_slice_used(cfqq)) - return 1; + return false; if (cfq_class_idle(new_cfqq)) - return 0; + return false; if (cfq_class_idle(cfqq)) - return 1; + return true; + + /* + * Don't allow a non-RT request to preempt an ongoing RT cfqq timeslice. + */ + if (cfq_class_rt(cfqq) && !cfq_class_rt(new_cfqq)) + return false; /* * if the new request is sync, but the currently running queue is * not, let the sync request have priority. */ if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq)) - return 1; + return true; + + if (new_cfqq->cfqg != cfqq->cfqg) + return false; + + if (cfq_slice_used(cfqq)) + return true; + + /* Allow preemption only if we are idling on sync-noidle tree */ + 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)) + return true; /* * So both queues are sync. Let the new request get disk time if * it's a metadata request and the current queue is doing regular IO. */ - if (rq_is_meta(rq) && !cfqq->meta_pending) - return 1; + if ((rq->cmd_flags & REQ_PRIO) && !cfqq->prio_pending) + return true; + + /* + * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice. + */ + if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq)) + return true; + + /* An idle queue should not be idle now for some reason */ + if (RB_EMPTY_ROOT(&cfqq->sort_list) && !cfq_should_idle(cfqd, cfqq)) + return true; if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq)) - return 0; + return false; /* * if this request is as-good as one we would expect from the * current cfqq, let it preempt */ - if (cfq_rq_close(cfqd, rq)) - return 1; + if (cfq_rq_close(cfqd, cfqq, rq)) + return true; - return 0; + return false; } /* @@ -1808,10 +3838,19 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, */ static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq) { + enum wl_type_t old_type = cfqq_type(cfqd->active_queue); + cfq_log_cfqq(cfqd, cfqq, "preempt"); cfq_slice_expired(cfqd, 1); /* + * workload type is changed, don't save slice, otherwise preempt + * doesn't happen + */ + if (old_type != cfqq_type(cfqq)) + cfqq->cfqg->saved_wl_slice = 0; + + /* * Put the new queue at the front of the of the current list, * so we know that it will be selected next. */ @@ -1831,37 +3870,49 @@ static void cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, struct request *rq) { - struct cfq_io_context *cic = RQ_CIC(rq); + struct cfq_io_cq *cic = RQ_CIC(rq); - if (rq_is_meta(rq)) - cfqq->meta_pending++; + cfqd->rq_queued++; + if (rq->cmd_flags & REQ_PRIO) + cfqq->prio_pending++; - cfq_update_io_thinktime(cfqd, cic); - cfq_update_io_seektime(cfqd, cic, rq); + cfq_update_io_thinktime(cfqd, cfqq, cic); + cfq_update_io_seektime(cfqd, cfqq, rq); cfq_update_idle_window(cfqd, cfqq, cic); - cic->last_request_pos = rq->sector + rq->nr_sectors; + cfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq); if (cfqq == cfqd->active_queue) { /* - * if we are waiting for a request for this queue, let it rip - * immediately and flag that we must not expire this queue - * just now + * Remember that we saw a request from this process, but + * don't start queuing just yet. Otherwise we risk seeing lots + * of tiny requests, because we disrupt the normal plugging + * and merging. If the request is already larger than a single + * page, let it rip immediately. For that case we assume that + * merging is already done. Ditto for a busy system that + * has other work pending, don't risk delaying until the + * idle timer unplug to continue working. */ if (cfq_cfqq_wait_request(cfqq)) { - cfq_mark_cfqq_must_dispatch(cfqq); - del_timer(&cfqd->idle_slice_timer); - blk_start_queueing(cfqd->queue); + if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE || + cfqd->busy_queues > 1) { + cfq_del_timer(cfqd, cfqq); + cfq_clear_cfqq_wait_request(cfqq); + __blk_run_queue(cfqd->queue); + } else { + cfqg_stats_update_idle_time(cfqq->cfqg); + cfq_mark_cfqq_must_dispatch(cfqq); + } } } else if (cfq_should_preempt(cfqd, cfqq, rq)) { /* * not the active queue - expire current slice if it is * idle and has expired it's mean thinktime or this new queue - * has some old slice time left and is of higher priority + * has some old slice time left and is of higher priority or + * this new queue is RT and the current one is BE */ cfq_preempt_queue(cfqd, cfqq); - cfq_mark_cfqq_must_dispatch(cfqq); - blk_start_queueing(cfqd->queue); + __blk_run_queue(cfqd->queue); } } @@ -1871,13 +3922,88 @@ 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)->ioc); + cfq_init_prio_data(cfqq, RQ_CIC(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); + cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group, + rq->cmd_flags); + cfq_rq_enqueued(cfqd, cfqq, rq); +} - list_add_tail(&rq->queuelist, &cfqq->fifo); +/* + * Update hw_tag based on peak queue depth over 50 samples under + * sufficient load. + */ +static void cfq_update_hw_tag(struct cfq_data *cfqd) +{ + struct cfq_queue *cfqq = cfqd->active_queue; - cfq_rq_enqueued(cfqd, cfqq, rq); + if (cfqd->rq_in_driver > cfqd->hw_tag_est_depth) + cfqd->hw_tag_est_depth = cfqd->rq_in_driver; + + if (cfqd->hw_tag == 1) + return; + + if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN && + cfqd->rq_in_driver <= CFQ_HW_QUEUE_MIN) + return; + + /* + * If active queue hasn't enough requests and can idle, cfq might not + * dispatch sufficient requests to hardware. Don't zero hw_tag in this + * case + */ + if (cfqq && cfq_cfqq_idle_window(cfqq) && + cfqq->dispatched + cfqq->queued[0] + cfqq->queued[1] < + CFQ_HW_QUEUE_MIN && cfqd->rq_in_driver < CFQ_HW_QUEUE_MIN) + return; + + if (cfqd->hw_tag_samples++ < 50) + return; + + if (cfqd->hw_tag_est_depth >= CFQ_HW_QUEUE_MIN) + cfqd->hw_tag = 1; + else + cfqd->hw_tag = 0; +} + +static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + struct cfq_io_cq *cic = cfqd->active_cic; + + /* If the queue already has requests, don't wait */ + if (!RB_EMPTY_ROOT(&cfqq->sort_list)) + return false; + + /* If there are other queues in the group, don't wait */ + if (cfqq->cfqg->nr_cfqq > 1) + return false; + + /* the only queue in the group, but think time is big */ + if (cfq_io_thinktime_big(cfqd, &cfqq->cfqg->ttime, true)) + return false; + + if (cfq_slice_used(cfqq)) + return true; + + /* if slice left is less than think time, wait busy */ + if (cic && sample_valid(cic->ttime.ttime_samples) + && (cfqq->slice_end - jiffies < cic->ttime.ttime_mean)) + return true; + + /* + * If think times is less than a jiffy than ttime_mean=0 and above + * will not be true. It might happen that slice has not expired yet + * but will expire soon (4-5 ns) during select_queue(). To cover the + * case where think time is less than a jiffy, mark the queue wait + * busy if only 1 jiffy is left in the slice. + */ + if (cfqq->slice_end - jiffies == 1) + return true; + + return false; } static void cfq_completed_request(struct request_queue *q, struct request *rq) @@ -1888,71 +4014,89 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) unsigned long now; now = jiffies; - cfq_log_cfqq(cfqd, cfqq, "complete"); + cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", + !!(rq->cmd_flags & REQ_NOIDLE)); + + cfq_update_hw_tag(cfqd); WARN_ON(!cfqd->rq_in_driver); WARN_ON(!cfqq->dispatched); cfqd->rq_in_driver--; cfqq->dispatched--; + (RQ_CFQG(rq))->dispatched--; + cfqg_stats_update_completion(cfqq->cfqg, rq_start_time_ns(rq), + rq_io_start_time_ns(rq), rq->cmd_flags); - if (cfq_cfqq_sync(cfqq)) - cfqd->sync_flight--; + cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--; + + if (sync) { + struct cfq_rb_root *st; - if (!cfq_class_idle(cfqq)) - cfqd->last_end_request = now; + RQ_CIC(rq)->ttime.last_end_request = now; - if (sync) - RQ_CIC(rq)->last_end_request = now; + if (cfq_cfqq_on_rr(cfqq)) + st = cfqq->service_tree; + else + 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; + } + +#ifdef CONFIG_CFQ_GROUP_IOSCHED + cfqq->cfqg->ttime.last_end_request = now; +#endif /* * If this is the active queue, check if it needs to be expired, * or if we want to idle in case it has no pending requests. */ if (cfqd->active_queue == cfqq) { + const bool cfqq_empty = RB_EMPTY_ROOT(&cfqq->sort_list); + if (cfq_cfqq_slice_new(cfqq)) { cfq_set_prio_slice(cfqd, cfqq); cfq_clear_cfqq_slice_new(cfqq); } + + /* + * Should we wait for next request to come in before we expire + * the queue. + */ + if (cfq_should_wait_busy(cfqd, cfqq)) { + unsigned long extend_sl = cfqd->cfq_slice_idle; + if (!cfqd->cfq_slice_idle) + extend_sl = cfqd->cfq_group_idle; + cfqq->slice_end = jiffies + extend_sl; + cfq_mark_cfqq_wait_busy(cfqq); + cfq_log_cfqq(cfqd, cfqq, "will busy wait"); + } + + /* + * Idling is not enabled on: + * - expired queues + * - idle-priority queues + * - async queues + * - queues with still some requests queued + * - when there is a close cooperator + */ if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq)) cfq_slice_expired(cfqd, 1); - else if (sync && RB_EMPTY_ROOT(&cfqq->sort_list)) + else if (sync && cfqq_empty && + !cfq_close_cooperator(cfqd, cfqq)) { cfq_arm_slice_timer(cfqd); + } } if (!cfqd->rq_in_driver) cfq_schedule_dispatch(cfqd); } -/* - * we temporarily boost lower priority queues if they are holding fs exclusive - * resources. they are boosted to normal prio (CLASS_BE/4) - */ -static void cfq_prio_boost(struct cfq_queue *cfqq) -{ - if (has_fs_excl()) { - /* - * boost idle prio on transactions that would lock out other - * users of the filesystem - */ - if (cfq_class_idle(cfqq)) - cfqq->ioprio_class = IOPRIO_CLASS_BE; - if (cfqq->ioprio > IOPRIO_NORM) - cfqq->ioprio = IOPRIO_NORM; - } else { - /* - * check if we need to unboost the queue - */ - if (cfqq->ioprio_class != cfqq->org_ioprio_class) - cfqq->ioprio_class = cfqq->org_ioprio_class; - if (cfqq->ioprio != cfqq->org_ioprio) - cfqq->ioprio = cfqq->org_ioprio; - } -} - static inline int __cfq_may_queue(struct cfq_queue *cfqq) { - if ((cfq_cfqq_wait_request(cfqq) || cfq_cfqq_must_alloc(cfqq)) && - !cfq_cfqq_must_alloc_slice(cfqq)) { + if (cfq_cfqq_wait_request(cfqq) && !cfq_cfqq_must_alloc_slice(cfqq)) { cfq_mark_cfqq_must_alloc_slice(cfqq); return ELV_MQUEUE_MUST; } @@ -1964,7 +4108,7 @@ static int cfq_may_queue(struct request_queue *q, int rw) { struct cfq_data *cfqd = q->elevator->elevator_data; struct task_struct *tsk = current; - struct cfq_io_context *cic; + struct cfq_io_cq *cic; struct cfq_queue *cfqq; /* @@ -1977,10 +4121,9 @@ static int cfq_may_queue(struct request_queue *q, int rw) if (!cic) return ELV_MQUEUE_MAY; - cfqq = cic_to_cfqq(cic, rw & REQ_RW_SYNC); + cfqq = cic_to_cfqq(cic, rw_is_sync(rw)); if (cfqq) { - cfq_init_prio_data(cfqq, cic->ioc); - cfq_prio_boost(cfqq); + cfq_init_prio_data(cfqq, cic); return __cfq_may_queue(cfqq); } @@ -2001,65 +4144,100 @@ static void cfq_put_request(struct request *rq) BUG_ON(!cfqq->allocated[rw]); cfqq->allocated[rw]--; - put_io_context(RQ_CIC(rq)->ioc); - - rq->elevator_private = NULL; - rq->elevator_private2 = NULL; + /* Put down rq reference on cfqg */ + cfqg_put(RQ_CFQG(rq)); + rq->elv.priv[0] = NULL; + rq->elv.priv[1] = NULL; cfq_put_queue(cfqq); } } +static struct cfq_queue * +cfq_merge_cfqqs(struct cfq_data *cfqd, struct cfq_io_cq *cic, + struct cfq_queue *cfqq) +{ + cfq_log_cfqq(cfqd, cfqq, "merging with queue %p", cfqq->new_cfqq); + cic_set_cfqq(cic, cfqq->new_cfqq, 1); + cfq_mark_cfqq_coop(cfqq->new_cfqq); + cfq_put_queue(cfqq); + return cic_to_cfqq(cic, 1); +} + +/* + * Returns NULL if a new cfqq should be allocated, or the old cfqq if this + * was the last process referring to said cfqq. + */ +static struct cfq_queue * +split_cfqq(struct cfq_io_cq *cic, struct cfq_queue *cfqq) +{ + if (cfqq_process_refs(cfqq) == 1) { + cfqq->pid = current->pid; + cfq_clear_cfqq_coop(cfqq); + cfq_clear_cfqq_split_coop(cfqq); + return cfqq; + } + + cic_set_cfqq(cic, NULL, 1); + + cfq_put_cooperator(cfqq); + + cfq_put_queue(cfqq); + return NULL; +} /* * 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_context *cic; + struct cfq_io_cq *cic = icq_to_cic(rq->elv.icq); const int rw = rq_data_dir(rq); - const int is_sync = rq_is_sync(rq); + const bool is_sync = rq_is_sync(rq); struct cfq_queue *cfqq; - unsigned long flags; might_sleep_if(gfp_mask & __GFP_WAIT); - cic = cfq_get_io_context(cfqd, gfp_mask); - - spin_lock_irqsave(q->queue_lock, flags); - - if (!cic) - goto queue_fail; + spin_lock_irq(q->queue_lock); + check_ioprio_changed(cic, bio); + check_blkcg_changed(cic, bio); +new_queue: cfqq = cic_to_cfqq(cic, is_sync); - if (!cfqq) { - cfqq = cfq_get_queue(cfqd, is_sync, cic->ioc, gfp_mask); - - if (!cfqq) - goto queue_fail; - + if (!cfqq || cfqq == &cfqd->oom_cfqq) { + cfqq = cfq_get_queue(cfqd, is_sync, cic, bio, gfp_mask); cic_set_cfqq(cic, cfqq, is_sync); + } else { + /* + * If the queue was seeky for too long, break it apart. + */ + if (cfq_cfqq_coop(cfqq) && cfq_cfqq_split_coop(cfqq)) { + cfq_log_cfqq(cfqd, cfqq, "breaking apart cfqq"); + cfqq = split_cfqq(cic, cfqq); + if (!cfqq) + goto new_queue; + } + + /* + * Check to see if this queue is scheduled to merge with + * another, closely cooperating queue. The merging of + * queues happens here as it must be done in process context. + * The reference on new_cfqq was taken in merge_cfqqs. + */ + if (cfqq->new_cfqq) + cfqq = cfq_merge_cfqqs(cfqd, cic, cfqq); } cfqq->allocated[rw]++; - cfq_clear_cfqq_must_alloc(cfqq); - atomic_inc(&cfqq->ref); - spin_unlock_irqrestore(q->queue_lock, flags); - - rq->elevator_private = cic; - rq->elevator_private2 = cfqq; + cfqq->ref++; + cfqg_get(cfqq->cfqg); + rq->elv.priv[0] = cfqq; + rq->elv.priv[1] = cfqq->cfqg; + spin_unlock_irq(q->queue_lock); return 0; - -queue_fail: - if (cic) - put_io_context(cic->ioc); - - cfq_schedule_dispatch(cfqd); - spin_unlock_irqrestore(q->queue_lock, flags); - cfq_log(cfqd, "set_request fail"); - return 1; } static void cfq_kick_queue(struct work_struct *work) @@ -2067,11 +4245,10 @@ static void cfq_kick_queue(struct work_struct *work) struct cfq_data *cfqd = container_of(work, struct cfq_data, unplug_work); struct request_queue *q = cfqd->queue; - unsigned long flags; - spin_lock_irqsave(q->queue_lock, flags); - blk_start_queueing(q); - spin_unlock_irqrestore(q->queue_lock, flags); + spin_lock_irq(q->queue_lock); + __blk_run_queue(cfqd->queue); + spin_unlock_irq(q->queue_lock); } /* @@ -2093,6 +4270,12 @@ static void cfq_idle_slice_timer(unsigned long data) timed_out = 0; /* + * We saw a request before the queue expired, let it through + */ + if (cfq_cfqq_must_dispatch(cfqq)) + goto out_kick; + + /* * expired */ if (cfq_slice_used(cfqq)) @@ -2108,10 +4291,13 @@ static void cfq_idle_slice_timer(unsigned long data) /* * not expired and it has a request pending, let it dispatch */ - if (!RB_EMPTY_ROOT(&cfqq->sort_list)) { - cfq_mark_cfqq_must_dispatch(cfqq); + if (!RB_EMPTY_ROOT(&cfqq->sort_list)) goto out_kick; - } + + /* + * Queue depth flag is reset only when the idle didn't succeed + */ + cfq_clear_cfqq_deep(cfqq); } expire: cfq_slice_expired(cfqd, timed_out); @@ -2124,7 +4310,7 @@ out_cont: static void cfq_shutdown_timer_wq(struct cfq_data *cfqd) { del_timer_sync(&cfqd->idle_slice_timer); - kblockd_flush_work(&cfqd->unplug_work); + cancel_work_sync(&cfqd->unplug_work); } static void cfq_put_async_queues(struct cfq_data *cfqd) @@ -2142,7 +4328,7 @@ static void cfq_put_async_queues(struct cfq_data *cfqd) cfq_put_queue(cfqd->async_idle_cfqq); } -static void cfq_exit_queue(elevator_t *e) +static void cfq_exit_queue(struct elevator_queue *e) { struct cfq_data *cfqd = e->elevator_data; struct request_queue *q = cfqd->queue; @@ -2154,35 +4340,87 @@ static void cfq_exit_queue(elevator_t *e) if (cfqd->active_queue) __cfq_slice_expired(cfqd, cfqd->active_queue, 0); - while (!list_empty(&cfqd->cic_list)) { - struct cfq_io_context *cic = list_entry(cfqd->cic_list.next, - struct cfq_io_context, - queue_list); - - __cfq_exit_single_io_context(cfqd, cic); - } - cfq_put_async_queues(cfqd); spin_unlock_irq(q->queue_lock); cfq_shutdown_timer_wq(cfqd); +#ifdef CONFIG_CFQ_GROUP_IOSCHED + 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; + 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; - cfqd->service_tree = CFQ_RB_ROOT; - INIT_LIST_HEAD(&cfqd->cic_list); + cfqd = kzalloc_node(sizeof(*cfqd), GFP_KERNEL, q->node); + if (!cfqd) { + kobject_put(&eq->kobj); + return -ENOMEM; + } + eq->elevator_data = cfqd; cfqd->queue = q; + spin_lock_irq(q->queue_lock); + q->elevator = eq; + spin_unlock_irq(q->queue_lock); + + /* 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 + ret = blkcg_activate_policy(q, &blkcg_policy_cfq); + if (ret) + goto out_free; + + 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; + + 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 + * to add magic to the rb code + */ + for (i = 0; i < CFQ_PRIO_LISTS; i++) + cfqd->prio_trees[i] = RB_ROOT; + + /* + * 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. 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++; + + 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; @@ -2190,7 +4428,6 @@ static void *cfq_init_queue(struct request_queue *q) INIT_WORK(&cfqd->unplug_work, cfq_kick_queue); - cfqd->last_end_request = jiffies; cfqd->cfq_quantum = cfq_quantum; cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0]; cfqd->cfq_fifo_expire[1] = cfq_fifo_expire[1]; @@ -2198,38 +4435,23 @@ 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; - - return cfqd; -} - -static void cfq_slab_kill(void) -{ + cfqd->cfq_group_idle = cfq_group_idle; + cfqd->cfq_latency = 1; + cfqd->hw_tag = -1; /* - * Caller already ensured that pending RCU callbacks are completed, - * so we should have no busy allocations at this point. + * we optimistically start assuming sync ops weren't delayed in last + * second, in order to have larger depth for async operations. */ - if (cfq_pool) - kmem_cache_destroy(cfq_pool); - if (cfq_ioc_pool) - kmem_cache_destroy(cfq_ioc_pool); -} - -static int __init cfq_slab_setup(void) -{ - cfq_pool = KMEM_CACHE(cfq_queue, 0); - if (!cfq_pool) - goto fail; - - cfq_ioc_pool = KMEM_CACHE(cfq_io_context, 0); - if (!cfq_ioc_pool) - goto fail; - + cfqd->last_delayed_sync = jiffies - HZ; return 0; -fail: - cfq_slab_kill(); - return -ENOMEM; + +out_free: + kfree(cfqd); + kobject_put(&eq->kobj); + return ret; } /* @@ -2238,7 +4460,7 @@ fail: 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 @@ -2251,7 +4473,7 @@ cfq_var_store(unsigned int *var, const char *page, size_t count) } #define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \ -static ssize_t __FUNC(elevator_t *e, char *page) \ +static ssize_t __FUNC(struct elevator_queue *e, char *page) \ { \ struct cfq_data *cfqd = e->elevator_data; \ unsigned int __data = __VAR; \ @@ -2265,13 +4487,16 @@ SHOW_FUNCTION(cfq_fifo_expire_async_show, cfqd->cfq_fifo_expire[0], 1); SHOW_FUNCTION(cfq_back_seek_max_show, cfqd->cfq_back_max, 0); SHOW_FUNCTION(cfq_back_seek_penalty_show, cfqd->cfq_back_penalty, 0); SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_idle, 1); +SHOW_FUNCTION(cfq_group_idle_show, cfqd->cfq_group_idle, 1); 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) \ -static ssize_t __FUNC(elevator_t *e, const char *page, size_t count) \ +static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count) \ { \ struct cfq_data *cfqd = e->elevator_data; \ unsigned int __data; \ @@ -2295,10 +4520,13 @@ STORE_FUNCTION(cfq_back_seek_max_store, &cfqd->cfq_back_max, 0, UINT_MAX, 0); STORE_FUNCTION(cfq_back_seek_penalty_store, &cfqd->cfq_back_penalty, 1, UINT_MAX, 0); STORE_FUNCTION(cfq_slice_idle_store, &cfqd->cfq_slice_idle, 0, UINT_MAX, 1); +STORE_FUNCTION(cfq_group_idle_store, &cfqd->cfq_group_idle, 0, UINT_MAX, 1); STORE_FUNCTION(cfq_slice_sync_store, &cfqd->cfq_slice[1], 1, UINT_MAX, 1); 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) \ @@ -2314,6 +4542,9 @@ static struct elv_fs_entry cfq_attrs[] = { CFQ_ATTR(slice_async), CFQ_ATTR(slice_async_rq), CFQ_ATTR(slice_idle), + CFQ_ATTR(group_idle), + CFQ_ATTR(low_latency), + CFQ_ATTR(target_latency), __ATTR_NULL }; @@ -2323,28 +4554,44 @@ static struct elevator_type iosched_cfq = { .elevator_merged_fn = cfq_merged_request, .elevator_merge_req_fn = cfq_merged_requests, .elevator_allow_merge_fn = cfq_allow_merge, + .elevator_bio_merged_fn = cfq_bio_merged, .elevator_dispatch_fn = cfq_dispatch_requests, .elevator_add_req_fn = cfq_insert_request, .elevator_activate_req_fn = cfq_activate_request, .elevator_deactivate_req_fn = cfq_deactivate_request, - .elevator_queue_empty_fn = cfq_queue_empty, .elevator_completed_req_fn = cfq_completed_request, .elevator_former_req_fn = elv_rb_former_request, .elevator_latter_req_fn = elv_rb_latter_request, + .elevator_init_icq_fn = cfq_init_icq, + .elevator_exit_icq_fn = cfq_exit_icq, .elevator_set_req_fn = cfq_set_request, .elevator_put_req_fn = cfq_put_request, .elevator_may_queue_fn = cfq_may_queue, .elevator_init_fn = cfq_init_queue, .elevator_exit_fn = cfq_exit_queue, - .trim = cfq_free_io_context, }, + .icq_size = sizeof(struct cfq_io_cq), + .icq_align = __alignof__(struct cfq_io_cq), .elevator_attrs = cfq_attrs, - .elevator_name = "cfq", + .elevator_name = "cfq", .elevator_owner = THIS_MODULE, }; +#ifdef CONFIG_CFQ_GROUP_IOSCHED +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, +}; +#endif + static int __init cfq_init(void) { + int ret; + /* * could be 0 on HZ < 1000 setups */ @@ -2353,29 +4600,44 @@ static int __init cfq_init(void) if (!cfq_slice_idle) cfq_slice_idle = 1; - if (cfq_slab_setup()) - return -ENOMEM; +#ifdef CONFIG_CFQ_GROUP_IOSCHED + if (!cfq_group_idle) + cfq_group_idle = 1; - elv_register(&iosched_cfq); + ret = blkcg_policy_register(&blkcg_policy_cfq); + if (ret) + return ret; +#else + cfq_group_idle = 0; +#endif + + ret = -ENOMEM; + cfq_pool = KMEM_CACHE(cfq_queue, 0); + if (!cfq_pool) + goto err_pol_unreg; + + ret = elv_register(&iosched_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) { - DECLARE_COMPLETION_ONSTACK(all_gone); +#ifdef CONFIG_CFQ_GROUP_IOSCHED + blkcg_policy_unregister(&blkcg_policy_cfq); +#endif elv_unregister(&iosched_cfq); - ioc_gone = &all_gone; - /* ioc_gone's update must be visible before reading ioc_count */ - smp_wmb(); - - /* - * this also protects us from entering cfq_slab_kill() with - * pending RCU callbacks - */ - if (elv_ioc_count_read(ioc_count)) - wait_for_completion(&all_gone); - cfq_slab_kill(); + kmem_cache_destroy(cfq_pool); } module_init(cfq_init); |