#include "blk-mq.h"
#include "blk-mq-tag.h"
#include "blk-mq-sched.h"
-#include <linux/blktrace_api.h>
-#include <linux/hrtimer.h>
-#include <linux/blk-cgroup.h>
-
-#define BFQ_IOPRIO_CLASSES 3
-#define BFQ_CL_IDLE_TIMEOUT (HZ/5)
-
-#define BFQ_MIN_WEIGHT 1
-#define BFQ_MAX_WEIGHT 1000
-#define BFQ_WEIGHT_CONVERSION_COEFF 10
-
-#define BFQ_DEFAULT_QUEUE_IOPRIO 4
-
-#define BFQ_WEIGHT_LEGACY_DFL 100
-#define BFQ_DEFAULT_GRP_IOPRIO 0
-#define BFQ_DEFAULT_GRP_CLASS IOPRIO_CLASS_BE
-
-/*
- * Soft real-time applications are extremely more latency sensitive
- * than interactive ones. Over-raise the weight of the former to
- * privilege them against the latter.
- */
-#define BFQ_SOFTRT_WEIGHT_FACTOR 100
-
-struct bfq_entity;
-
-/**
- * struct bfq_service_tree - per ioprio_class service tree.
- *
- * Each service tree represents a B-WF2Q+ scheduler on its own. Each
- * ioprio_class has its own independent scheduler, and so its own
- * bfq_service_tree. All the fields are protected by the queue lock
- * of the containing bfqd.
- */
-struct bfq_service_tree {
- /* tree for active entities (i.e., those backlogged) */
- struct rb_root active;
- /* tree for idle entities (i.e., not backlogged, with V <= F_i)*/
- struct rb_root idle;
-
- /* idle entity with minimum F_i */
- struct bfq_entity *first_idle;
- /* idle entity with maximum F_i */
- struct bfq_entity *last_idle;
-
- /* scheduler virtual time */
- u64 vtime;
- /* scheduler weight sum; active and idle entities contribute to it */
- unsigned long wsum;
-};
-
-/**
- * struct bfq_sched_data - multi-class scheduler.
- *
- * bfq_sched_data is the basic scheduler queue. It supports three
- * ioprio_classes, and can be used either as a toplevel queue or as an
- * intermediate queue on a hierarchical setup. @next_in_service
- * points to the active entity of the sched_data service trees that
- * will be scheduled next. It is used to reduce the number of steps
- * needed for each hierarchical-schedule update.
- *
- * The supported ioprio_classes are the same as in CFQ, in descending
- * priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE.
- * Requests from higher priority queues are served before all the
- * requests from lower priority queues; among requests of the same
- * queue requests are served according to B-WF2Q+.
- * All the fields are protected by the queue lock of the containing bfqd.
- */
-struct bfq_sched_data {
- /* entity in service */
- struct bfq_entity *in_service_entity;
- /* head-of-line entity (see comments above) */
- struct bfq_entity *next_in_service;
- /* array of service trees, one per ioprio_class */
- struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES];
- /* last time CLASS_IDLE was served */
- unsigned long bfq_class_idle_last_service;
-
-};
-
-/**
- * struct bfq_entity - schedulable entity.
- *
- * A bfq_entity is used to represent either a bfq_queue (leaf node in the
- * cgroup hierarchy) or a bfq_group into the upper level scheduler. Each
- * entity belongs to the sched_data of the parent group in the cgroup
- * hierarchy. Non-leaf entities have also their own sched_data, stored
- * in @my_sched_data.
- *
- * Each entity stores independently its priority values; this would
- * allow different weights on different devices, but this
- * functionality is not exported to userspace by now. Priorities and
- * weights are updated lazily, first storing the new values into the
- * new_* fields, then setting the @prio_changed flag. As soon as
- * there is a transition in the entity state that allows the priority
- * update to take place the effective and the requested priority
- * values are synchronized.
- *
- * Unless cgroups are used, the weight value is calculated from the
- * ioprio to export the same interface as CFQ. When dealing with
- * ``well-behaved'' queues (i.e., queues that do not spend too much
- * time to consume their budget and have true sequential behavior, and
- * when there are no external factors breaking anticipation) the
- * relative weights at each level of the cgroups hierarchy should be
- * guaranteed. All the fields are protected by the queue lock of the
- * containing bfqd.
- */
-struct bfq_entity {
- /* service_tree member */
- struct rb_node rb_node;
-
- /*
- * Flag, true if the entity is on a tree (either the active or
- * the idle one of its service_tree) or is in service.
- */
- bool on_st;
-
- /* B-WF2Q+ start and finish timestamps [sectors/weight] */
- u64 start, finish;
-
- /* tree the entity is enqueued into; %NULL if not on a tree */
- struct rb_root *tree;
-
- /*
- * minimum start time of the (active) subtree rooted at this
- * entity; used for O(log N) lookups into active trees
- */
- u64 min_start;
-
- /* amount of service received during the last service slot */
- int service;
-
- /* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
- int budget;
-
- /* weight of the queue */
- int weight;
- /* next weight if a change is in progress */
- int new_weight;
-
- /* original weight, used to implement weight boosting */
- int orig_weight;
-
- /* parent entity, for hierarchical scheduling */
- struct bfq_entity *parent;
-
- /*
- * For non-leaf nodes in the hierarchy, the associated
- * scheduler queue, %NULL on leaf nodes.
- */
- struct bfq_sched_data *my_sched_data;
- /* the scheduler queue this entity belongs to */
- struct bfq_sched_data *sched_data;
-
- /* flag, set to request a weight, ioprio or ioprio_class change */
- int prio_changed;
-};
-
-struct bfq_group;
-
-/**
- * struct bfq_ttime - per process thinktime stats.
- */
-struct bfq_ttime {
- /* completion time of the last request */
- u64 last_end_request;
-
- /* total process thinktime */
- u64 ttime_total;
- /* number of thinktime samples */
- unsigned long ttime_samples;
- /* average process thinktime */
- u64 ttime_mean;
-};
-
-/**
- * struct bfq_queue - leaf schedulable entity.
- *
- * A bfq_queue is a leaf request queue; it can be associated with an
- * io_context or more, if it is async or shared between cooperating
- * processes. @cgroup holds a reference to the cgroup, to be sure that it
- * does not disappear while a bfqq still references it (mostly to avoid
- * races between request issuing and task migration followed by cgroup
- * destruction).
- * All the fields are protected by the queue lock of the containing bfqd.
- */
-struct bfq_queue {
- /* reference counter */
- int ref;
- /* parent bfq_data */
- struct bfq_data *bfqd;
-
- /* current ioprio and ioprio class */
- unsigned short ioprio, ioprio_class;
- /* next ioprio and ioprio class if a change is in progress */
- unsigned short new_ioprio, new_ioprio_class;
-
- /*
- * Shared bfq_queue if queue is cooperating with one or more
- * other queues.
- */
- struct bfq_queue *new_bfqq;
- /* request-position tree member (see bfq_group's @rq_pos_tree) */
- struct rb_node pos_node;
- /* request-position tree root (see bfq_group's @rq_pos_tree) */
- struct rb_root *pos_root;
-
- /* sorted list of pending requests */
- struct rb_root sort_list;
- /* if fifo isn't expired, next request to serve */
- struct request *next_rq;
- /* number of sync and async requests queued */
- int queued[2];
- /* number of requests currently allocated */
- int allocated;
- /* number of pending metadata requests */
- int meta_pending;
- /* fifo list of requests in sort_list */
- struct list_head fifo;
-
- /* entity representing this queue in the scheduler */
- struct bfq_entity entity;
-
- /* maximum budget allowed from the feedback mechanism */
- int max_budget;
- /* budget expiration (in jiffies) */
- unsigned long budget_timeout;
-
- /* number of requests on the dispatch list or inside driver */
- int dispatched;
-
- /* status flags */
- unsigned long flags;
-
- /* node for active/idle bfqq list inside parent bfqd */
- struct list_head bfqq_list;
-
- /* associated @bfq_ttime struct */
- struct bfq_ttime ttime;
-
- /* bit vector: a 1 for each seeky requests in history */
- u32 seek_history;
- /* position of the last request enqueued */
- sector_t last_request_pos;
-
- /* Number of consecutive pairs of request completion and
- * arrival, such that the queue becomes idle after the
- * completion, but the next request arrives within an idle
- * time slice; used only if the queue's IO_bound flag has been
- * cleared.
- */
- unsigned int requests_within_timer;
-
- /* pid of the process owning the queue, used for logging purposes */
- pid_t pid;
-
- /*
- * Pointer to the bfq_io_cq owning the bfq_queue, set to %NULL
- * if the queue is shared.
- */
- struct bfq_io_cq *bic;
-
- /* current maximum weight-raising time for this queue */
- unsigned long wr_cur_max_time;
- /*
- * Minimum time instant such that, only if a new request is
- * enqueued after this time instant in an idle @bfq_queue with
- * no outstanding requests, then the task associated with the
- * queue it is deemed as soft real-time (see the comments on
- * the function bfq_bfqq_softrt_next_start())
- */
- unsigned long soft_rt_next_start;
- /*
- * Start time of the current weight-raising period if
- * the @bfq-queue is being weight-raised, otherwise
- * finish time of the last weight-raising period.
- */
- unsigned long last_wr_start_finish;
- /* factor by which the weight of this queue is multiplied */
- unsigned int wr_coeff;
- /*
- * Time of the last transition of the @bfq_queue from idle to
- * backlogged.
- */
- unsigned long last_idle_bklogged;
- /*
- * Cumulative service received from the @bfq_queue since the
- * last transition from idle to backlogged.
- */
- unsigned long service_from_backlogged;
-
- /*
- * Value of wr start time when switching to soft rt
- */
- unsigned long wr_start_at_switch_to_srt;
-
- unsigned long split_time; /* time of last split */
-};
-
-/**
- * struct bfq_io_cq - per (request_queue, io_context) structure.
- */
-struct bfq_io_cq {
- /* associated io_cq structure */
- struct io_cq icq; /* must be the first member */
- /* array of two process queues, the sync and the async */
- struct bfq_queue *bfqq[2];
- /* per (request_queue, blkcg) ioprio */
- int ioprio;
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
- uint64_t blkcg_serial_nr; /* the current blkcg serial */
-#endif
- /*
- * Snapshot of the idle window before merging; taken to
- * remember this value while the queue is merged, so as to be
- * able to restore it in case of split.
- */
- bool saved_idle_window;
- /*
- * Same purpose as the previous two fields for the I/O bound
- * classification of a queue.
- */
- bool saved_IO_bound;
-
- /*
- * Similar to previous fields: save wr information.
- */
- unsigned long saved_wr_coeff;
- unsigned long saved_last_wr_start_finish;
- unsigned long saved_wr_start_at_switch_to_srt;
- unsigned int saved_wr_cur_max_time;
- struct bfq_ttime saved_ttime;
-};
-
-enum bfq_device_speed {
- BFQ_BFQD_FAST,
- BFQ_BFQD_SLOW,
-};
-
-/**
- * struct bfq_data - per-device data structure.
- *
- * All the fields are protected by @lock.
- */
-struct bfq_data {
- /* device request queue */
- struct request_queue *queue;
- /* dispatch queue */
- struct list_head dispatch;
-
- /* root bfq_group for the device */
- struct bfq_group *root_group;
-
- /*
- * Number of bfq_queues containing requests (including the
- * queue in service, even if it is idling).
- */
- int busy_queues;
- /* number of weight-raised busy @bfq_queues */
- int wr_busy_queues;
- /* number of queued requests */
- int queued;
- /* number of requests dispatched and waiting for completion */
- int rq_in_driver;
-
- /*
- * Maximum number of requests in driver in the last
- * @hw_tag_samples completed requests.
- */
- int max_rq_in_driver;
- /* number of samples used to calculate hw_tag */
- int hw_tag_samples;
- /* flag set to one if the driver is showing a queueing behavior */
- int hw_tag;
-
- /* number of budgets assigned */
- int budgets_assigned;
-
- /*
- * Timer set when idling (waiting) for the next request from
- * the queue in service.
- */
- struct hrtimer idle_slice_timer;
-
- /* bfq_queue in service */
- struct bfq_queue *in_service_queue;
- /* bfq_io_cq (bic) associated with the @in_service_queue */
- struct bfq_io_cq *in_service_bic;
-
- /* on-disk position of the last served request */
- sector_t last_position;
-
- /* time of last request completion (ns) */
- u64 last_completion;
-
- /* time of first rq dispatch in current observation interval (ns) */
- u64 first_dispatch;
- /* time of last rq dispatch in current observation interval (ns) */
- u64 last_dispatch;
-
- /* beginning of the last budget */
- ktime_t last_budget_start;
- /* beginning of the last idle slice */
- ktime_t last_idling_start;
-
- /* number of samples in current observation interval */
- int peak_rate_samples;
- /* num of samples of seq dispatches in current observation interval */
- u32 sequential_samples;
- /* total num of sectors transferred in current observation interval */
- u64 tot_sectors_dispatched;
- /* max rq size seen during current observation interval (sectors) */
- u32 last_rq_max_size;
- /* time elapsed from first dispatch in current observ. interval (us) */
- u64 delta_from_first;
- /*
- * Current estimate of the device peak rate, measured in
- * [BFQ_RATE_SHIFT * sectors/usec]. The left-shift by
- * BFQ_RATE_SHIFT is performed to increase precision in
- * fixed-point calculations.
- */
- u32 peak_rate;
-
- /* maximum budget allotted to a bfq_queue before rescheduling */
- int bfq_max_budget;
-
- /* list of all the bfq_queues active on the device */
- struct list_head active_list;
- /* list of all the bfq_queues idle on the device */
- struct list_head idle_list;
-
- /*
- * Timeout for async/sync requests; when it fires, requests
- * are served in fifo order.
- */
- u64 bfq_fifo_expire[2];
- /* weight of backward seeks wrt forward ones */
- unsigned int bfq_back_penalty;
- /* maximum allowed backward seek */
- unsigned int bfq_back_max;
- /* maximum idling time */
- u32 bfq_slice_idle;
-
- /* user-configured max budget value (0 for auto-tuning) */
- int bfq_user_max_budget;
- /*
- * Timeout for bfq_queues to consume their budget; used to
- * prevent seeky queues from imposing long latencies to
- * sequential or quasi-sequential ones (this also implies that
- * seeky queues cannot receive guarantees in the service
- * domain; after a timeout they are charged for the time they
- * have been in service, to preserve fairness among them, but
- * without service-domain guarantees).
- */
- unsigned int bfq_timeout;
-
- /*
- * Number of consecutive requests that must be issued within
- * the idle time slice to set again idling to a queue which
- * was marked as non-I/O-bound (see the definition of the
- * IO_bound flag for further details).
- */
- unsigned int bfq_requests_within_timer;
-
- /*
- * Force device idling whenever needed to provide accurate
- * service guarantees, without caring about throughput
- * issues. CAVEAT: this may even increase latencies, in case
- * of useless idling for processes that did stop doing I/O.
- */
- bool strict_guarantees;
-
- /* if set to true, low-latency heuristics are enabled */
- bool low_latency;
- /*
- * Maximum factor by which the weight of a weight-raised queue
- * is multiplied.
- */
- unsigned int bfq_wr_coeff;
- /* maximum duration of a weight-raising period (jiffies) */
- unsigned int bfq_wr_max_time;
-
- /* Maximum weight-raising duration for soft real-time processes */
- unsigned int bfq_wr_rt_max_time;
- /*
- * Minimum idle period after which weight-raising may be
- * reactivated for a queue (in jiffies).
- */
- unsigned int bfq_wr_min_idle_time;
- /*
- * Minimum period between request arrivals after which
- * weight-raising may be reactivated for an already busy async
- * queue (in jiffies).
- */
- unsigned long bfq_wr_min_inter_arr_async;
-
- /* Max service-rate for a soft real-time queue, in sectors/sec */
- unsigned int bfq_wr_max_softrt_rate;
- /*
- * Cached value of the product R*T, used for computing the
- * maximum duration of weight raising automatically.
- */
- u64 RT_prod;
- /* device-speed class for the low-latency heuristic */
- enum bfq_device_speed device_speed;
-
- /* fallback dummy bfqq for extreme OOM conditions */
- struct bfq_queue oom_bfqq;
-
- spinlock_t lock;
-
- /*
- * bic associated with the task issuing current bio for
- * merging. This and the next field are used as a support to
- * be able to perform the bic lookup, needed by bio-merge
- * functions, before the scheduler lock is taken, and thus
- * avoid taking the request-queue lock while the scheduler
- * lock is being held.
- */
- struct bfq_io_cq *bio_bic;
- /* bfqq associated with the task issuing current bio for merging */
- struct bfq_queue *bio_bfqq;
-
- /*
- * io context to put right after bfqd->lock is released. This
- * filed is used to perform put_io_context, when needed, to
- * after the scheduler lock has been released, and thus
- * prevent an ioc->lock from being possibly taken while the
- * scheduler lock is being held.
- */
- struct io_context *ioc_to_put;
-};
-
-enum bfqq_state_flags {
- BFQQF_busy = 0, /* has requests or is in service */
- BFQQF_wait_request, /* waiting for a request */
- BFQQF_non_blocking_wait_rq, /*
- * waiting for a request
- * without idling the device
- */
- BFQQF_fifo_expire, /* FIFO checked in this slice */
- BFQQF_idle_window, /* slice idling enabled */
- BFQQF_sync, /* synchronous queue */
- BFQQF_IO_bound, /*
- * bfqq has timed-out at least once
- * having consumed at most 2/10 of
- * its budget
- */
- BFQQF_softrt_update, /*
- * may need softrt-next-start
- * update
- */
- BFQQF_coop, /* bfqq is shared */
- BFQQF_split_coop /* shared bfqq will be split */
-};
+#include "bfq-iosched.h"
#define BFQ_BFQQ_FNS(name) \
-static void bfq_mark_bfqq_##name(struct bfq_queue *bfqq) \
+void bfq_mark_bfqq_##name(struct bfq_queue *bfqq) \
{ \
__set_bit(BFQQF_##name, &(bfqq)->flags); \
} \
-static void bfq_clear_bfqq_##name(struct bfq_queue *bfqq) \
+void bfq_clear_bfqq_##name(struct bfq_queue *bfqq) \
{ \
__clear_bit(BFQQF_##name, &(bfqq)->flags); \
} \
-static int bfq_bfqq_##name(const struct bfq_queue *bfqq) \
+int bfq_bfqq_##name(const struct bfq_queue *bfqq) \
{ \
return test_bit(BFQQF_##name, &(bfqq)->flags); \
}
+BFQ_BFQQ_FNS(just_created);
BFQ_BFQQ_FNS(busy);
BFQ_BFQQ_FNS(wait_request);
BFQ_BFQQ_FNS(non_blocking_wait_rq);
BFQ_BFQQ_FNS(idle_window);
BFQ_BFQQ_FNS(sync);
BFQ_BFQQ_FNS(IO_bound);
+BFQ_BFQQ_FNS(in_large_burst);
BFQ_BFQQ_FNS(coop);
BFQ_BFQQ_FNS(split_coop);
BFQ_BFQQ_FNS(softrt_update);
-#undef BFQ_BFQQ_FNS
-
-/* Logging facilities. */
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-static struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
-static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
-
-#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \
- char __pbuf[128]; \
- \
- blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
- blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid, \
- bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \
- __pbuf, ##args); \
-} while (0)
-
-#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do { \
- char __pbuf[128]; \
- \
- blkg_path(bfqg_to_blkg(bfqg), __pbuf, sizeof(__pbuf)); \
- blk_add_trace_msg((bfqd)->queue, "%s " fmt, __pbuf, ##args); \
-} while (0)
-
-#else /* CONFIG_BFQ_GROUP_IOSCHED */
-
-#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \
- blk_add_trace_msg((bfqd)->queue, "bfq%d%c " fmt, (bfqq)->pid, \
- bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \
- ##args)
-#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do {} while (0)
-
-#endif /* CONFIG_BFQ_GROUP_IOSCHED */
-
-#define bfq_log(bfqd, fmt, args...) \
- blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)
-
-/* Expiration reasons. */
-enum bfqq_expiration {
- BFQQE_TOO_IDLE = 0, /*
- * queue has been idling for
- * too long
- */
- BFQQE_BUDGET_TIMEOUT, /* budget took too long to be used */
- BFQQE_BUDGET_EXHAUSTED, /* budget consumed */
- BFQQE_NO_MORE_REQUESTS, /* the queue has no more requests */
- BFQQE_PREEMPTED /* preemption in progress */
-};
-
-struct bfqg_stats {
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
- /* 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 disk time and nr sectors dispatched by this group */
- struct blkg_stat 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_BFQ_GROUP_IOSCHED */
-};
-
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-
-/*
- * struct bfq_group_data - per-blkcg storage for the blkio subsystem.
- *
- * @ps: @blkcg_policy_storage that this structure inherits
- * @weight: weight of the bfq_group
- */
-struct bfq_group_data {
- /* must be the first member */
- struct blkcg_policy_data pd;
-
- unsigned int weight;
-};
-
-/**
- * struct bfq_group - per (device, cgroup) data structure.
- * @entity: schedulable entity to insert into the parent group sched_data.
- * @sched_data: own sched_data, to contain child entities (they may be
- * both bfq_queues and bfq_groups).
- * @bfqd: the bfq_data for the device this group acts upon.
- * @async_bfqq: array of async queues for all the tasks belonging to
- * the group, one queue per ioprio value per ioprio_class,
- * except for the idle class that has only one queue.
- * @async_idle_bfqq: async queue for the idle class (ioprio is ignored).
- * @my_entity: pointer to @entity, %NULL for the toplevel group; used
- * to avoid too many special cases during group creation/
- * migration.
- * @stats: stats for this bfqg.
- * @rq_pos_tree: rbtree sorted by next_request position, used when
- * determining if two or more queues have interleaving
- * requests (see bfq_find_close_cooperator()).
- *
- * Each (device, cgroup) pair has its own bfq_group, i.e., for each cgroup
- * there is a set of bfq_groups, each one collecting the lower-level
- * entities belonging to the group that are acting on the same device.
- *
- * Locking works as follows:
- * o @bfqd is protected by the queue lock, RCU is used to access it
- * from the readers.
- * o All the other fields are protected by the @bfqd queue lock.
- */
-struct bfq_group {
- /* must be the first member */
- struct blkg_policy_data pd;
-
- struct bfq_entity entity;
- struct bfq_sched_data sched_data;
-
- void *bfqd;
-
- struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
- struct bfq_queue *async_idle_bfqq;
-
- struct bfq_entity *my_entity;
-
- struct rb_root rq_pos_tree;
-
- struct bfqg_stats stats;
-};
-
-#else
-struct bfq_group {
- struct bfq_sched_data sched_data;
-
- struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
- struct bfq_queue *async_idle_bfqq;
-
- struct rb_root rq_pos_tree;
-};
-#endif
-
-static struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
-
-static unsigned int bfq_class_idx(struct bfq_entity *entity)
-{
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-
- return bfqq ? bfqq->ioprio_class - 1 :
- BFQ_DEFAULT_GRP_CLASS - 1;
-}
-
-static struct bfq_service_tree *
-bfq_entity_service_tree(struct bfq_entity *entity)
-{
- struct bfq_sched_data *sched_data = entity->sched_data;
- unsigned int idx = bfq_class_idx(entity);
-
- return sched_data->service_tree + idx;
-}
-
-static struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync)
-{
- return bic->bfqq[is_sync];
-}
-
-static void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq,
- bool is_sync)
-{
- bic->bfqq[is_sync] = bfqq;
-}
-
-static struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
-{
- return bic->icq.q->elevator->elevator_data;
-}
-
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-
-static struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
-{
- struct bfq_entity *group_entity = bfqq->entity.parent;
-
- if (!group_entity)
- group_entity = &bfqq->bfqd->root_group->entity;
-
- return container_of(group_entity, struct bfq_group, entity);
-}
-
-#else
-
-static struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
-{
- return bfqq->bfqd->root_group;
-}
-
-#endif
-
-static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio);
-static void bfq_put_queue(struct bfq_queue *bfqq);
-static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
- struct bio *bio, bool is_sync,
- struct bfq_io_cq *bic);
-static void bfq_end_wr_async_queues(struct bfq_data *bfqd,
- struct bfq_group *bfqg);
-static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
-static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+#undef BFQ_BFQQ_FNS \
/* Expiration time of sync (0) and async (1) requests, in ns. */
static const u64 bfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 8 };
static const int bfq_async_charge_factor = 10;
/* Default timeout values, in jiffies, approximating CFQ defaults. */
-static const int bfq_timeout = HZ / 8;
+const int bfq_timeout = HZ / 8;
static struct kmem_cache *bfq_pool;
static int T_fast[2];
static int device_speed_thresh[2];
-#define BFQ_SERVICE_TREE_INIT ((struct bfq_service_tree) \
- { RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 })
-
#define RQ_BIC(rq) ((struct bfq_io_cq *) (rq)->elv.priv[0])
#define RQ_BFQQ(rq) ((rq)->elv.priv[1])
-/**
- * icq_to_bic - convert iocontext queue structure to bfq_io_cq.
- * @icq: the iocontext queue.
- */
-static struct bfq_io_cq *icq_to_bic(struct io_cq *icq)
-{
- /* bic->icq is the first member, %NULL will convert to %NULL */
- return container_of(icq, struct bfq_io_cq, icq);
-}
-
-/**
- * bfq_bic_lookup - search into @ioc a bic associated to @bfqd.
- * @bfqd: the lookup key.
- * @ioc: the io_context of the process doing I/O.
- * @q: the request queue.
- */
-static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
- struct io_context *ioc,
- struct request_queue *q)
-{
- if (ioc) {
- unsigned long flags;
- struct bfq_io_cq *icq;
-
- spin_lock_irqsave(q->queue_lock, flags);
- icq = icq_to_bic(ioc_lookup_icq(ioc, q));
- spin_unlock_irqrestore(q->queue_lock, flags);
-
- return icq;
- }
-
- return NULL;
-}
-
-/*
- * Scheduler run of queue, if there are requests pending and no one in the
- * driver that will restart queueing.
- */
-static void bfq_schedule_dispatch(struct bfq_data *bfqd)
-{
- if (bfqd->queued != 0) {
- bfq_log(bfqd, "schedule dispatch");
- blk_mq_run_hw_queues(bfqd->queue, true);
- }
-}
-
-/*
- * Next two functions release bfqd->lock and put the io context
- * pointed by bfqd->ioc_to_put. This delayed put is used to not risk
- * to take an ioc->lock while the scheduler lock is being held.
- */
-static void bfq_unlock_put_ioc(struct bfq_data *bfqd)
-{
- struct io_context *ioc_to_put = bfqd->ioc_to_put;
-
- bfqd->ioc_to_put = NULL;
- spin_unlock_irq(&bfqd->lock);
-
- if (ioc_to_put)
- put_io_context(ioc_to_put);
-}
-
-static void bfq_unlock_put_ioc_restore(struct bfq_data *bfqd,
- unsigned long flags)
-{
- struct io_context *ioc_to_put = bfqd->ioc_to_put;
-
- bfqd->ioc_to_put = NULL;
- spin_unlock_irqrestore(&bfqd->lock, flags);
-
- if (ioc_to_put)
- put_io_context(ioc_to_put);
-}
-
-/**
- * bfq_gt - compare two timestamps.
- * @a: first ts.
- * @b: second ts.
- *
- * Return @a > @b, dealing with wrapping correctly.
- */
-static int bfq_gt(u64 a, u64 b)
-{
- return (s64)(a - b) > 0;
-}
-
-static struct bfq_entity *bfq_root_active_entity(struct rb_root *tree)
-{
- struct rb_node *node = tree->rb_node;
-
- return rb_entry(node, struct bfq_entity, rb_node);
-}
-
-static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd);
-
-static bool bfq_update_parent_budget(struct bfq_entity *next_in_service);
-
-/**
- * bfq_update_next_in_service - update sd->next_in_service
- * @sd: sched_data for which to perform the update.
- * @new_entity: if not NULL, pointer to the entity whose activation,
- * requeueing or repositionig triggered the invocation of
- * this function.
- *
- * This function is called to update sd->next_in_service, which, in
- * its turn, may change as a consequence of the insertion or
- * extraction of an entity into/from one of the active trees of
- * sd. These insertions/extractions occur as a consequence of
- * activations/deactivations of entities, with some activations being
- * 'true' activations, and other activations being requeueings (i.e.,
- * implementing the second, requeueing phase of the mechanism used to
- * reposition an entity in its active tree; see comments on
- * __bfq_activate_entity and __bfq_requeue_entity for details). In
- * both the last two activation sub-cases, new_entity points to the
- * just activated or requeued entity.
- *
- * Returns true if sd->next_in_service changes in such a way that
- * entity->parent may become the next_in_service for its parent
- * entity.
- */
-static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
- struct bfq_entity *new_entity)
-{
- struct bfq_entity *next_in_service = sd->next_in_service;
- bool parent_sched_may_change = false;
-
- /*
- * If this update is triggered by the activation, requeueing
- * or repositiong of an entity that does not coincide with
- * sd->next_in_service, then a full lookup in the active tree
- * can be avoided. In fact, it is enough to check whether the
- * just-modified entity has a higher priority than
- * sd->next_in_service, or, even if it has the same priority
- * as sd->next_in_service, is eligible and has a lower virtual
- * finish time than sd->next_in_service. If this compound
- * condition holds, then the new entity becomes the new
- * next_in_service. Otherwise no change is needed.
- */
- if (new_entity && new_entity != sd->next_in_service) {
- /*
- * Flag used to decide whether to replace
- * sd->next_in_service with new_entity. Tentatively
- * set to true, and left as true if
- * sd->next_in_service is NULL.
- */
- bool replace_next = true;
-
- /*
- * If there is already a next_in_service candidate
- * entity, then compare class priorities or timestamps
- * to decide whether to replace sd->service_tree with
- * new_entity.
- */
- if (next_in_service) {
- unsigned int new_entity_class_idx =
- bfq_class_idx(new_entity);
- struct bfq_service_tree *st =
- sd->service_tree + new_entity_class_idx;
-
- /*
- * For efficiency, evaluate the most likely
- * sub-condition first.
- */
- replace_next =
- (new_entity_class_idx ==
- bfq_class_idx(next_in_service)
- &&
- !bfq_gt(new_entity->start, st->vtime)
- &&
- bfq_gt(next_in_service->finish,
- new_entity->finish))
- ||
- new_entity_class_idx <
- bfq_class_idx(next_in_service);
- }
-
- if (replace_next)
- next_in_service = new_entity;
- } else /* invoked because of a deactivation: lookup needed */
- next_in_service = bfq_lookup_next_entity(sd);
-
- if (next_in_service) {
- parent_sched_may_change = !sd->next_in_service ||
- bfq_update_parent_budget(next_in_service);
- }
-
- sd->next_in_service = next_in_service;
-
- if (!next_in_service)
- return parent_sched_may_change;
-
- return parent_sched_may_change;
-}
-
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-/* both next loops stop at one of the child entities of the root group */
-#define for_each_entity(entity) \
- for (; entity ; entity = entity->parent)
-
-/*
- * For each iteration, compute parent in advance, so as to be safe if
- * entity is deallocated during the iteration. Such a deallocation may
- * happen as a consequence of a bfq_put_queue that frees the bfq_queue
- * containing entity.
- */
-#define for_each_entity_safe(entity, parent) \
- for (; entity && ({ parent = entity->parent; 1; }); entity = parent)
-
-/*
- * Returns true if this budget changes may let next_in_service->parent
- * become the next_in_service entity for its parent entity.
- */
-static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
-{
- struct bfq_entity *bfqg_entity;
- struct bfq_group *bfqg;
- struct bfq_sched_data *group_sd;
- bool ret = false;
-
- group_sd = next_in_service->sched_data;
-
- bfqg = container_of(group_sd, struct bfq_group, sched_data);
- /*
- * bfq_group's my_entity field is not NULL only if the group
- * is not the root group. We must not touch the root entity
- * as it must never become an in-service entity.
- */
- bfqg_entity = bfqg->my_entity;
- if (bfqg_entity) {
- if (bfqg_entity->budget > next_in_service->budget)
- ret = true;
- bfqg_entity->budget = next_in_service->budget;
- }
-
- return ret;
-}
-
-/*
- * This function tells whether entity stops being a candidate for next
- * service, according to the following logic.
- *
- * This function is invoked for an entity that is about to be set in
- * service. If such an entity is a queue, then the entity is no longer
- * a candidate for next service (i.e, a candidate entity to serve
- * after the in-service entity is expired). The function then returns
- * true.
- */
-static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
-{
- if (bfq_entity_to_bfqq(entity))
- return true;
-
- return false;
-}
-
-#else /* CONFIG_BFQ_GROUP_IOSCHED */
-/*
- * Next two macros are fake loops when cgroups support is not
- * enabled. I fact, in such a case, there is only one level to go up
- * (to reach the root group).
- */
-#define for_each_entity(entity) \
- for (; entity ; entity = NULL)
-
-#define for_each_entity_safe(entity, parent) \
- for (parent = NULL; entity ; entity = parent)
-
-static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
-{
- return false;
-}
-
-static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
-{
- return true;
-}
-
-#endif /* CONFIG_BFQ_GROUP_IOSCHED */
-
-/*
- * Shift for timestamp calculations. This actually limits the maximum
- * service allowed in one timestamp delta (small shift values increase it),
- * the maximum total weight that can be used for the queues in the system
- * (big shift values increase it), and the period of virtual time
- * wraparounds.
- */
-#define WFQ_SERVICE_SHIFT 22
-
-static struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity)
-{
- struct bfq_queue *bfqq = NULL;
-
- if (!entity->my_sched_data)
- bfqq = container_of(entity, struct bfq_queue, entity);
-
- return bfqq;
-}
-
-
-/**
- * bfq_delta - map service into the virtual time domain.
- * @service: amount of service.
- * @weight: scale factor (weight of an entity or weight sum).
- */
-static u64 bfq_delta(unsigned long service, unsigned long weight)
-{
- u64 d = (u64)service << WFQ_SERVICE_SHIFT;
-
- do_div(d, weight);
- return d;
-}
-
-/**
- * bfq_calc_finish - assign the finish time to an entity.
- * @entity: the entity to act upon.
- * @service: the service to be charged to the entity.
- */
-static void bfq_calc_finish(struct bfq_entity *entity, unsigned long service)
-{
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-
- entity->finish = entity->start +
- bfq_delta(service, entity->weight);
-
- if (bfqq) {
- bfq_log_bfqq(bfqq->bfqd, bfqq,
- "calc_finish: serv %lu, w %d",
- service, entity->weight);
- bfq_log_bfqq(bfqq->bfqd, bfqq,
- "calc_finish: start %llu, finish %llu, delta %llu",
- entity->start, entity->finish,
- bfq_delta(service, entity->weight));
- }
-}
-
-/**
- * bfq_entity_of - get an entity from a node.
- * @node: the node field of the entity.
- *
- * Convert a node pointer to the relative entity. This is used only
- * to simplify the logic of some functions and not as the generic
- * conversion mechanism because, e.g., in the tree walking functions,
- * the check for a %NULL value would be redundant.
- */
-static struct bfq_entity *bfq_entity_of(struct rb_node *node)
-{
- struct bfq_entity *entity = NULL;
-
- if (node)
- entity = rb_entry(node, struct bfq_entity, rb_node);
-
- return entity;
-}
-
-/**
- * bfq_extract - remove an entity from a tree.
- * @root: the tree root.
- * @entity: the entity to remove.
- */
-static void bfq_extract(struct rb_root *root, struct bfq_entity *entity)
-{
- entity->tree = NULL;
- rb_erase(&entity->rb_node, root);
-}
-
-/**
- * bfq_idle_extract - extract an entity from the idle tree.
- * @st: the service tree of the owning @entity.
- * @entity: the entity being removed.
- */
-static void bfq_idle_extract(struct bfq_service_tree *st,
- struct bfq_entity *entity)
-{
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
- struct rb_node *next;
-
- if (entity == st->first_idle) {
- next = rb_next(&entity->rb_node);
- st->first_idle = bfq_entity_of(next);
- }
-
- if (entity == st->last_idle) {
- next = rb_prev(&entity->rb_node);
- st->last_idle = bfq_entity_of(next);
- }
-
- bfq_extract(&st->idle, entity);
-
- if (bfqq)
- list_del(&bfqq->bfqq_list);
-}
-
-/**
- * bfq_insert - generic tree insertion.
- * @root: tree root.
- * @entity: entity to insert.
- *
- * This is used for the idle and the active tree, since they are both
- * ordered by finish time.
- */
-static void bfq_insert(struct rb_root *root, struct bfq_entity *entity)
-{
- struct bfq_entity *entry;
- struct rb_node **node = &root->rb_node;
- struct rb_node *parent = NULL;
-
- while (*node) {
- parent = *node;
- entry = rb_entry(parent, struct bfq_entity, rb_node);
-
- if (bfq_gt(entry->finish, entity->finish))
- node = &parent->rb_left;
- else
- node = &parent->rb_right;
- }
-
- rb_link_node(&entity->rb_node, parent, node);
- rb_insert_color(&entity->rb_node, root);
-
- entity->tree = root;
-}
-
-/**
- * bfq_update_min - update the min_start field of a entity.
- * @entity: the entity to update.
- * @node: one of its children.
- *
- * This function is called when @entity may store an invalid value for
- * min_start due to updates to the active tree. The function assumes
- * that the subtree rooted at @node (which may be its left or its right
- * child) has a valid min_start value.
- */
-static void bfq_update_min(struct bfq_entity *entity, struct rb_node *node)
-{
- struct bfq_entity *child;
-
- if (node) {
- child = rb_entry(node, struct bfq_entity, rb_node);
- if (bfq_gt(entity->min_start, child->min_start))
- entity->min_start = child->min_start;
- }
-}
-
-/**
- * bfq_update_active_node - recalculate min_start.
- * @node: the node to update.
- *
- * @node may have changed position or one of its children may have moved,
- * this function updates its min_start value. The left and right subtrees
- * are assumed to hold a correct min_start value.
- */
-static void bfq_update_active_node(struct rb_node *node)
-{
- struct bfq_entity *entity = rb_entry(node, struct bfq_entity, rb_node);
-
- entity->min_start = entity->start;
- bfq_update_min(entity, node->rb_right);
- bfq_update_min(entity, node->rb_left);
-}
-
-/**
- * bfq_update_active_tree - update min_start for the whole active tree.
- * @node: the starting node.
- *
- * @node must be the deepest modified node after an update. This function
- * updates its min_start using the values held by its children, assuming
- * that they did not change, and then updates all the nodes that may have
- * changed in the path to the root. The only nodes that may have changed
- * are the ones in the path or their siblings.
- */
-static void bfq_update_active_tree(struct rb_node *node)
-{
- struct rb_node *parent;
-
-up:
- bfq_update_active_node(node);
-
- parent = rb_parent(node);
- if (!parent)
- return;
-
- if (node == parent->rb_left && parent->rb_right)
- bfq_update_active_node(parent->rb_right);
- else if (parent->rb_left)
- bfq_update_active_node(parent->rb_left);
-
- node = parent;
- goto up;
-}
-
-/**
- * bfq_active_insert - insert an entity in the active tree of its
- * group/device.
- * @st: the service tree of the entity.
- * @entity: the entity being inserted.
- *
- * The active tree is ordered by finish time, but an extra key is kept
- * per each node, containing the minimum value for the start times of
- * its children (and the node itself), so it's possible to search for
- * the eligible node with the lowest finish time in logarithmic time.
- */
-static void bfq_active_insert(struct bfq_service_tree *st,
- struct bfq_entity *entity)
-{
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
- struct rb_node *node = &entity->rb_node;
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
- struct bfq_sched_data *sd = NULL;
- struct bfq_group *bfqg = NULL;
- struct bfq_data *bfqd = NULL;
-#endif
-
- bfq_insert(&st->active, entity);
-
- if (node->rb_left)
- node = node->rb_left;
- else if (node->rb_right)
- node = node->rb_right;
-
- bfq_update_active_tree(node);
-
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
- sd = entity->sched_data;
- bfqg = container_of(sd, struct bfq_group, sched_data);
- bfqd = (struct bfq_data *)bfqg->bfqd;
-#endif
- if (bfqq)
- list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
-}
-
-/**
- * bfq_ioprio_to_weight - calc a weight from an ioprio.
- * @ioprio: the ioprio value to convert.
- */
-static unsigned short bfq_ioprio_to_weight(int ioprio)
-{
- return (IOPRIO_BE_NR - ioprio) * BFQ_WEIGHT_CONVERSION_COEFF;
-}
-
-/**
- * bfq_weight_to_ioprio - calc an ioprio from a weight.
- * @weight: the weight value to convert.
- *
- * To preserve as much as possible the old only-ioprio user interface,
- * 0 is used as an escape ioprio value for weights (numerically) equal or
- * larger than IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF.
- */
-static unsigned short bfq_weight_to_ioprio(int weight)
-{
- return max_t(int, 0,
- IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - weight);
-}
-
-static void bfq_get_entity(struct bfq_entity *entity)
-{
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-
- if (bfqq) {
- bfqq->ref++;
- bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d",
- bfqq, bfqq->ref);
- }
-}
-
-/**
- * bfq_find_deepest - find the deepest node that an extraction can modify.
- * @node: the node being removed.
- *
- * Do the first step of an extraction in an rb tree, looking for the
- * node that will replace @node, and returning the deepest node that
- * the following modifications to the tree can touch. If @node is the
- * last node in the tree return %NULL.
- */
-static struct rb_node *bfq_find_deepest(struct rb_node *node)
-{
- struct rb_node *deepest;
-
- if (!node->rb_right && !node->rb_left)
- deepest = rb_parent(node);
- else if (!node->rb_right)
- deepest = node->rb_left;
- else if (!node->rb_left)
- deepest = node->rb_right;
- else {
- deepest = rb_next(node);
- if (deepest->rb_right)
- deepest = deepest->rb_right;
- else if (rb_parent(deepest) != node)
- deepest = rb_parent(deepest);
- }
-
- return deepest;
-}
-
-/**
- * bfq_active_extract - remove an entity from the active tree.
- * @st: the service_tree containing the tree.
- * @entity: the entity being removed.
- */
-static void bfq_active_extract(struct bfq_service_tree *st,
- struct bfq_entity *entity)
-{
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
- struct rb_node *node;
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
- struct bfq_sched_data *sd = NULL;
- struct bfq_group *bfqg = NULL;
- struct bfq_data *bfqd = NULL;
-#endif
-
- node = bfq_find_deepest(&entity->rb_node);
- bfq_extract(&st->active, entity);
-
- if (node)
- bfq_update_active_tree(node);
-
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
- sd = entity->sched_data;
- bfqg = container_of(sd, struct bfq_group, sched_data);
- bfqd = (struct bfq_data *)bfqg->bfqd;
-#endif
- if (bfqq)
- list_del(&bfqq->bfqq_list);
-}
-
-/**
- * bfq_idle_insert - insert an entity into the idle tree.
- * @st: the service tree containing the tree.
- * @entity: the entity to insert.
- */
-static void bfq_idle_insert(struct bfq_service_tree *st,
- struct bfq_entity *entity)
-{
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
- struct bfq_entity *first_idle = st->first_idle;
- struct bfq_entity *last_idle = st->last_idle;
-
- if (!first_idle || bfq_gt(first_idle->finish, entity->finish))
- st->first_idle = entity;
- if (!last_idle || bfq_gt(entity->finish, last_idle->finish))
- st->last_idle = entity;
-
- bfq_insert(&st->idle, entity);
-
- if (bfqq)
- list_add(&bfqq->bfqq_list, &bfqq->bfqd->idle_list);
-}
-
-/**
- * bfq_forget_entity - do not consider entity any longer for scheduling
- * @st: the service tree.
- * @entity: the entity being removed.
- * @is_in_service: true if entity is currently the in-service entity.
- *
- * Forget everything about @entity. In addition, if entity represents
- * a queue, and the latter is not in service, then release the service
- * reference to the queue (the one taken through bfq_get_entity). In
- * fact, in this case, there is really no more service reference to
- * the queue, as the latter is also outside any service tree. If,
- * instead, the queue is in service, then __bfq_bfqd_reset_in_service
- * will take care of putting the reference when the queue finally
- * stops being served.
- */
-static void bfq_forget_entity(struct bfq_service_tree *st,
- struct bfq_entity *entity,
- bool is_in_service)
-{
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-
- entity->on_st = false;
- st->wsum -= entity->weight;
- if (bfqq && !is_in_service)
- bfq_put_queue(bfqq);
-}
-
-/**
- * bfq_put_idle_entity - release the idle tree ref of an entity.
- * @st: service tree for the entity.
- * @entity: the entity being released.
- */
-static void bfq_put_idle_entity(struct bfq_service_tree *st,
- struct bfq_entity *entity)
-{
- bfq_idle_extract(st, entity);
- bfq_forget_entity(st, entity,
- entity == entity->sched_data->in_service_entity);
-}
-
-/**
- * bfq_forget_idle - update the idle tree if necessary.
- * @st: the service tree to act upon.
- *
- * To preserve the global O(log N) complexity we only remove one entry here;
- * as the idle tree will not grow indefinitely this can be done safely.
- */
-static void bfq_forget_idle(struct bfq_service_tree *st)
-{
- struct bfq_entity *first_idle = st->first_idle;
- struct bfq_entity *last_idle = st->last_idle;
-
- if (RB_EMPTY_ROOT(&st->active) && last_idle &&
- !bfq_gt(last_idle->finish, st->vtime)) {
- /*
- * Forget the whole idle tree, increasing the vtime past
- * the last finish time of idle entities.
- */
- st->vtime = last_idle->finish;
- }
-
- if (first_idle && !bfq_gt(first_idle->finish, st->vtime))
- bfq_put_idle_entity(st, first_idle);
-}
-
-static struct bfq_service_tree *
-__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
- struct bfq_entity *entity)
-{
- struct bfq_service_tree *new_st = old_st;
-
- if (entity->prio_changed) {
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
- unsigned int prev_weight, new_weight;
- struct bfq_data *bfqd = NULL;
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
- struct bfq_sched_data *sd;
- struct bfq_group *bfqg;
-#endif
-
- if (bfqq)
- bfqd = bfqq->bfqd;
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
- else {
- sd = entity->my_sched_data;
- bfqg = container_of(sd, struct bfq_group, sched_data);
- bfqd = (struct bfq_data *)bfqg->bfqd;
- }
-#endif
-
- old_st->wsum -= entity->weight;
-
- if (entity->new_weight != entity->orig_weight) {
- if (entity->new_weight < BFQ_MIN_WEIGHT ||
- entity->new_weight > BFQ_MAX_WEIGHT) {
- pr_crit("update_weight_prio: new_weight %d\n",
- entity->new_weight);
- if (entity->new_weight < BFQ_MIN_WEIGHT)
- entity->new_weight = BFQ_MIN_WEIGHT;
- else
- entity->new_weight = BFQ_MAX_WEIGHT;
- }
- entity->orig_weight = entity->new_weight;
- if (bfqq)
- bfqq->ioprio =
- bfq_weight_to_ioprio(entity->orig_weight);
- }
-
- if (bfqq)
- bfqq->ioprio_class = bfqq->new_ioprio_class;
- entity->prio_changed = 0;
-
- /*
- * NOTE: here we may be changing the weight too early,
- * this will cause unfairness. The correct approach
- * would have required additional complexity to defer
- * weight changes to the proper time instants (i.e.,
- * when entity->finish <= old_st->vtime).
- */
- new_st = bfq_entity_service_tree(entity);
-
- prev_weight = entity->weight;
- new_weight = entity->orig_weight *
- (bfqq ? bfqq->wr_coeff : 1);
- entity->weight = new_weight;
-
- new_st->wsum += entity->weight;
-
- if (new_st != old_st)
- entity->start = new_st->vtime;
- }
-
- return new_st;
-}
-
-static void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
-static struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
-
-/**
- * bfq_bfqq_served - update the scheduler status after selection for
- * service.
- * @bfqq: the queue being served.
- * @served: bytes to transfer.
- *
- * NOTE: this can be optimized, as the timestamps of upper level entities
- * are synchronized every time a new bfqq is selected for service. By now,
- * we keep it to better check consistency.
- */
-static void bfq_bfqq_served(struct bfq_queue *bfqq, int served)
-{
- struct bfq_entity *entity = &bfqq->entity;
- struct bfq_service_tree *st;
-
- for_each_entity(entity) {
- st = bfq_entity_service_tree(entity);
-
- entity->service += served;
-
- st->vtime += bfq_delta(served, st->wsum);
- bfq_forget_idle(st);
- }
- bfqg_stats_set_start_empty_time(bfqq_group(bfqq));
- bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %d secs", served);
-}
-
-/**
- * bfq_bfqq_charge_time - charge an amount of service equivalent to the length
- * of the time interval during which bfqq has been in
- * service.
- * @bfqd: the device
- * @bfqq: the queue that needs a service update.
- * @time_ms: the amount of time during which the queue has received service
- *
- * If a queue does not consume its budget fast enough, then providing
- * the queue with service fairness may impair throughput, more or less
- * severely. For this reason, queues that consume their budget slowly
- * are provided with time fairness instead of service fairness. This
- * goal is achieved through the BFQ scheduling engine, even if such an
- * engine works in the service, and not in the time domain. The trick
- * is charging these queues with an inflated amount of service, equal
- * to the amount of service that they would have received during their
- * service slot if they had been fast, i.e., if their requests had
- * been dispatched at a rate equal to the estimated peak rate.
- *
- * It is worth noting that time fairness can cause important
- * distortions in terms of bandwidth distribution, on devices with
- * internal queueing. The reason is that I/O requests dispatched
- * during the service slot of a queue may be served after that service
- * slot is finished, and may have a total processing time loosely
- * correlated with the duration of the service slot. This is
- * especially true for short service slots.
- */
-static void bfq_bfqq_charge_time(struct bfq_data *bfqd, struct bfq_queue *bfqq,
- unsigned long time_ms)
-{
- struct bfq_entity *entity = &bfqq->entity;
- int tot_serv_to_charge = entity->service;
- unsigned int timeout_ms = jiffies_to_msecs(bfq_timeout);
-
- if (time_ms > 0 && time_ms < timeout_ms)
- tot_serv_to_charge =
- (bfqd->bfq_max_budget * time_ms) / timeout_ms;
-
- if (tot_serv_to_charge < entity->service)
- tot_serv_to_charge = entity->service;
-
- /* Increase budget to avoid inconsistencies */
- if (tot_serv_to_charge > entity->budget)
- entity->budget = tot_serv_to_charge;
-
- bfq_bfqq_served(bfqq,
- max_t(int, 0, tot_serv_to_charge - entity->service));
-}
-
-static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
- struct bfq_service_tree *st,
- bool backshifted)
-{
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-
- st = __bfq_entity_update_weight_prio(st, entity);
- bfq_calc_finish(entity, entity->budget);
-
- /*
- * If some queues enjoy backshifting for a while, then their
- * (virtual) finish timestamps may happen to become lower and
- * lower than the system virtual time. In particular, if
- * these queues often happen to be idle for short time
- * periods, and during such time periods other queues with
- * higher timestamps happen to be busy, then the backshifted
- * timestamps of the former queues can become much lower than
- * the system virtual time. In fact, to serve the queues with
- * higher timestamps while the ones with lower timestamps are
- * idle, the system virtual time may be pushed-up to much
- * higher values than the finish timestamps of the idle
- * queues. As a consequence, the finish timestamps of all new
- * or newly activated queues may end up being much larger than
- * those of lucky queues with backshifted timestamps. The
- * latter queues may then monopolize the device for a lot of
- * time. This would simply break service guarantees.
- *
- * To reduce this problem, push up a little bit the
- * backshifted timestamps of the queue associated with this
- * entity (only a queue can happen to have the backshifted
- * flag set): just enough to let the finish timestamp of the
- * queue be equal to the current value of the system virtual
- * time. This may introduce a little unfairness among queues
- * with backshifted timestamps, but it does not break
- * worst-case fairness guarantees.
- *
- * As a special case, if bfqq is weight-raised, push up
- * timestamps much less, to keep very low the probability that
- * this push up causes the backshifted finish timestamps of
- * weight-raised queues to become higher than the backshifted
- * finish timestamps of non weight-raised queues.
- */
- if (backshifted && bfq_gt(st->vtime, entity->finish)) {
- unsigned long delta = st->vtime - entity->finish;
-
- if (bfqq)
- delta /= bfqq->wr_coeff;
-
- entity->start += delta;
- entity->finish += delta;
- }
-
- bfq_active_insert(st, entity);
-}
-
-/**
- * __bfq_activate_entity - handle activation of entity.
- * @entity: the entity being activated.
- * @non_blocking_wait_rq: true if entity was waiting for a request
- *
- * Called for a 'true' activation, i.e., if entity is not active and
- * one of its children receives a new request.
- *
- * Basically, this function updates the timestamps of entity and
- * inserts entity into its active tree, ater possible extracting it
- * from its idle tree.
- */
-static void __bfq_activate_entity(struct bfq_entity *entity,
- bool non_blocking_wait_rq)
-{
- struct bfq_service_tree *st = bfq_entity_service_tree(entity);
- bool backshifted = false;
- unsigned long long min_vstart;
-
- /* See comments on bfq_fqq_update_budg_for_activation */
- if (non_blocking_wait_rq && bfq_gt(st->vtime, entity->finish)) {
- backshifted = true;
- min_vstart = entity->finish;
- } else
- min_vstart = st->vtime;
-
- if (entity->tree == &st->idle) {
- /*
- * Must be on the idle tree, bfq_idle_extract() will
- * check for that.
- */
- bfq_idle_extract(st, entity);
- entity->start = bfq_gt(min_vstart, entity->finish) ?
- min_vstart : entity->finish;
- } else {
- /*
- * The finish time of the entity may be invalid, and
- * it is in the past for sure, otherwise the queue
- * would have been on the idle tree.
- */
- entity->start = min_vstart;
- st->wsum += entity->weight;
- /*
- * entity is about to be inserted into a service tree,
- * and then set in service: get a reference to make
- * sure entity does not disappear until it is no
- * longer in service or scheduled for service.
- */
- bfq_get_entity(entity);
-
- entity->on_st = true;
- }
-
- bfq_update_fin_time_enqueue(entity, st, backshifted);
-}
-
-/**
- * __bfq_requeue_entity - handle requeueing or repositioning of an entity.
- * @entity: the entity being requeued or repositioned.
- *
- * Requeueing is needed if this entity stops being served, which
- * happens if a leaf descendant entity has expired. On the other hand,
- * repositioning is needed if the next_inservice_entity for the child
- * entity has changed. See the comments inside the function for
- * details.
- *
- * Basically, this function: 1) removes entity from its active tree if
- * present there, 2) updates the timestamps of entity and 3) inserts
- * entity back into its active tree (in the new, right position for
- * the new values of the timestamps).
- */
-static void __bfq_requeue_entity(struct bfq_entity *entity)
-{
- struct bfq_sched_data *sd = entity->sched_data;
- struct bfq_service_tree *st = bfq_entity_service_tree(entity);
-
- if (entity == sd->in_service_entity) {
- /*
- * We are requeueing the current in-service entity,
- * which may have to be done for one of the following
- * reasons:
- * - entity represents the in-service queue, and the
- * in-service queue is being requeued after an
- * expiration;
- * - entity represents a group, and its budget has
- * changed because one of its child entities has
- * just been either activated or requeued for some
- * reason; the timestamps of the entity need then to
- * be updated, and the entity needs to be enqueued
- * or repositioned accordingly.
- *
- * In particular, before requeueing, the start time of
- * the entity must be moved forward to account for the
- * service that the entity has received while in
- * service. This is done by the next instructions. The
- * finish time will then be updated according to this
- * new value of the start time, and to the budget of
- * the entity.
- */
- bfq_calc_finish(entity, entity->service);
- entity->start = entity->finish;
- /*
- * In addition, if the entity had more than one child
- * when set in service, then was not extracted from
- * the active tree. This implies that the position of
- * the entity in the active tree may need to be
- * changed now, because we have just updated the start
- * time of the entity, and we will update its finish
- * time in a moment (the requeueing is then, more
- * precisely, a repositioning in this case). To
- * implement this repositioning, we: 1) dequeue the
- * entity here, 2) update the finish time and
- * requeue the entity according to the new
- * timestamps below.
- */
- if (entity->tree)
- bfq_active_extract(st, entity);
- } else { /* The entity is already active, and not in service */
- /*
- * In this case, this function gets called only if the
- * next_in_service entity below this entity has
- * changed, and this change has caused the budget of
- * this entity to change, which, finally implies that
- * the finish time of this entity must be
- * updated. Such an update may cause the scheduling,
- * i.e., the position in the active tree, of this
- * entity to change. We handle this change by: 1)
- * dequeueing the entity here, 2) updating the finish
- * time and requeueing the entity according to the new
- * timestamps below. This is the same approach as the
- * non-extracted-entity sub-case above.
- */
- bfq_active_extract(st, entity);
- }
-
- bfq_update_fin_time_enqueue(entity, st, false);
-}
-
-static void __bfq_activate_requeue_entity(struct bfq_entity *entity,
- struct bfq_sched_data *sd,
- bool non_blocking_wait_rq)
-{
- struct bfq_service_tree *st = bfq_entity_service_tree(entity);
-
- if (sd->in_service_entity == entity || entity->tree == &st->active)
- /*
- * in service or already queued on the active tree,
- * requeue or reposition
- */
- __bfq_requeue_entity(entity);
- else
- /*
- * Not in service and not queued on its active tree:
- * the activity is idle and this is a true activation.
- */
- __bfq_activate_entity(entity, non_blocking_wait_rq);
-}
-
-
-/**
- * bfq_activate_entity - activate or requeue an entity representing a bfq_queue,
- * and activate, requeue or reposition all ancestors
- * for which such an update becomes necessary.
- * @entity: the entity to activate.
- * @non_blocking_wait_rq: true if this entity was waiting for a request
- * @requeue: true if this is a requeue, which implies that bfqq is
- * being expired; thus ALL its ancestors stop being served and must
- * therefore be requeued
- */
-static void bfq_activate_requeue_entity(struct bfq_entity *entity,
- bool non_blocking_wait_rq,
- bool requeue)
-{
- struct bfq_sched_data *sd;
-
- for_each_entity(entity) {
- sd = entity->sched_data;
- __bfq_activate_requeue_entity(entity, sd, non_blocking_wait_rq);
-
- if (!bfq_update_next_in_service(sd, entity) && !requeue)
- break;
- }
-}
-
-/**
- * __bfq_deactivate_entity - deactivate an entity from its service tree.
- * @entity: the entity to deactivate.
- * @ins_into_idle_tree: if false, the entity will not be put into the
- * idle tree.
- *
- * Deactivates an entity, independently from its previous state. Must
- * be invoked only if entity is on a service tree. Extracts the entity
- * from that tree, and if necessary and allowed, puts it on the idle
- * tree.
- */
-static bool __bfq_deactivate_entity(struct bfq_entity *entity,
- bool ins_into_idle_tree)
-{
- struct bfq_sched_data *sd = entity->sched_data;
- struct bfq_service_tree *st = bfq_entity_service_tree(entity);
- int is_in_service = entity == sd->in_service_entity;
-
- if (!entity->on_st) /* entity never activated, or already inactive */
- return false;
-
- if (is_in_service)
- bfq_calc_finish(entity, entity->service);
-
- if (entity->tree == &st->active)
- bfq_active_extract(st, entity);
- else if (!is_in_service && entity->tree == &st->idle)
- bfq_idle_extract(st, entity);
-
- if (!ins_into_idle_tree || !bfq_gt(entity->finish, st->vtime))
- bfq_forget_entity(st, entity, is_in_service);
- else
- bfq_idle_insert(st, entity);
-
- return true;
-}
-
-/**
- * bfq_deactivate_entity - deactivate an entity representing a bfq_queue.
- * @entity: the entity to deactivate.
- * @ins_into_idle_tree: true if the entity can be put on the idle tree
- */
-static void bfq_deactivate_entity(struct bfq_entity *entity,
- bool ins_into_idle_tree,
- bool expiration)
-{
- struct bfq_sched_data *sd;
- struct bfq_entity *parent = NULL;
-
- for_each_entity_safe(entity, parent) {
- sd = entity->sched_data;
-
- if (!__bfq_deactivate_entity(entity, ins_into_idle_tree)) {
- /*
- * entity is not in any tree any more, so
- * this deactivation is a no-op, and there is
- * nothing to change for upper-level entities
- * (in case of expiration, this can never
- * happen).
- */
- return;
- }
-
- if (sd->next_in_service == entity)
- /*
- * entity was the next_in_service entity,
- * then, since entity has just been
- * deactivated, a new one must be found.
- */
- bfq_update_next_in_service(sd, NULL);
-
- if (sd->next_in_service)
- /*
- * The parent entity is still backlogged,
- * because next_in_service is not NULL. So, no
- * further upwards deactivation must be
- * performed. Yet, next_in_service has
- * changed. Then the schedule does need to be
- * updated upwards.
- */
- break;
-
- /*
- * If we get here, then the parent is no more
- * backlogged and we need to propagate the
- * deactivation upwards. Thus let the loop go on.
- */
-
- /*
- * Also let parent be queued into the idle tree on
- * deactivation, to preserve service guarantees, and
- * assuming that who invoked this function does not
- * need parent entities too to be removed completely.
- */
- ins_into_idle_tree = true;
- }
-
- /*
- * If the deactivation loop is fully executed, then there are
- * no more entities to touch and next loop is not executed at
- * all. Otherwise, requeue remaining entities if they are
- * about to stop receiving service, or reposition them if this
- * is not the case.
- */
- entity = parent;
- for_each_entity(entity) {
- /*
- * Invoke __bfq_requeue_entity on entity, even if
- * already active, to requeue/reposition it in the
- * active tree (because sd->next_in_service has
- * changed)
- */
- __bfq_requeue_entity(entity);
-
- sd = entity->sched_data;
- if (!bfq_update_next_in_service(sd, entity) &&
- !expiration)
- /*
- * next_in_service unchanged or not causing
- * any change in entity->parent->sd, and no
- * requeueing needed for expiration: stop
- * here.
- */
- break;
- }
-}
-
-/**
- * bfq_calc_vtime_jump - compute the value to which the vtime should jump,
- * if needed, to have at least one entity eligible.
- * @st: the service tree to act upon.
- *
- * Assumes that st is not empty.
- */
-static u64 bfq_calc_vtime_jump(struct bfq_service_tree *st)
-{
- struct bfq_entity *root_entity = bfq_root_active_entity(&st->active);
-
- if (bfq_gt(root_entity->min_start, st->vtime))
- return root_entity->min_start;
-
- return st->vtime;
-}
-
-static void bfq_update_vtime(struct bfq_service_tree *st, u64 new_value)
-{
- if (new_value > st->vtime) {
- st->vtime = new_value;
- bfq_forget_idle(st);
- }
-}
-
-/**
- * bfq_first_active_entity - find the eligible entity with
- * the smallest finish time
- * @st: the service tree to select from.
- * @vtime: the system virtual to use as a reference for eligibility
- *
- * This function searches the first schedulable entity, starting from the
- * root of the tree and going on the left every time on this side there is
- * a subtree with at least one eligible (start >= vtime) entity. The path on
- * the right is followed only if a) the left subtree contains no eligible
- * entities and b) no eligible entity has been found yet.
- */
-static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st,
- u64 vtime)
-{
- struct bfq_entity *entry, *first = NULL;
- struct rb_node *node = st->active.rb_node;
-
- while (node) {
- entry = rb_entry(node, struct bfq_entity, rb_node);
-left:
- if (!bfq_gt(entry->start, vtime))
- first = entry;
-
- if (node->rb_left) {
- entry = rb_entry(node->rb_left,
- struct bfq_entity, rb_node);
- if (!bfq_gt(entry->min_start, vtime)) {
- node = node->rb_left;
- goto left;
- }
- }
- if (first)
- break;
- node = node->rb_right;
- }
-
- return first;
-}
-
-/**
- * __bfq_lookup_next_entity - return the first eligible entity in @st.
- * @st: the service tree.
- *
- * If there is no in-service entity for the sched_data st belongs to,
- * then return the entity that will be set in service if:
- * 1) the parent entity this st belongs to is set in service;
- * 2) no entity belonging to such parent entity undergoes a state change
- * that would influence the timestamps of the entity (e.g., becomes idle,
- * becomes backlogged, changes its budget, ...).
- *
- * In this first case, update the virtual time in @st too (see the
- * comments on this update inside the function).
- *
- * In constrast, if there is an in-service entity, then return the
- * entity that would be set in service if not only the above
- * conditions, but also the next one held true: the currently
- * in-service entity, on expiration,
- * 1) gets a finish time equal to the current one, or
- * 2) is not eligible any more, or
- * 3) is idle.
- */
-static struct bfq_entity *
-__bfq_lookup_next_entity(struct bfq_service_tree *st, bool in_service)
-{
- struct bfq_entity *entity;
- u64 new_vtime;
-
- if (RB_EMPTY_ROOT(&st->active))
- return NULL;
-
- /*
- * Get the value of the system virtual time for which at
- * least one entity is eligible.
- */
- new_vtime = bfq_calc_vtime_jump(st);
-
- /*
- * If there is no in-service entity for the sched_data this
- * active tree belongs to, then push the system virtual time
- * up to the value that guarantees that at least one entity is
- * eligible. If, instead, there is an in-service entity, then
- * do not make any such update, because there is already an
- * eligible entity, namely the in-service one (even if the
- * entity is not on st, because it was extracted when set in
- * service).
- */
- if (!in_service)
- bfq_update_vtime(st, new_vtime);
-
- entity = bfq_first_active_entity(st, new_vtime);
-
- return entity;
-}
-
-/**
- * bfq_lookup_next_entity - return the first eligible entity in @sd.
- * @sd: the sched_data.
- *
- * This function is invoked when there has been a change in the trees
- * for sd, and we need know what is the new next entity after this
- * change.
- */
-static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd)
-{
- struct bfq_service_tree *st = sd->service_tree;
- struct bfq_service_tree *idle_class_st = st + (BFQ_IOPRIO_CLASSES - 1);
- struct bfq_entity *entity = NULL;
- int class_idx = 0;
-
- /*
- * Choose from idle class, if needed to guarantee a minimum
- * bandwidth to this class (and if there is some active entity
- * in idle class). This should also mitigate
- * priority-inversion problems in case a low priority task is
- * holding file system resources.
- */
- if (time_is_before_jiffies(sd->bfq_class_idle_last_service +
- BFQ_CL_IDLE_TIMEOUT)) {
- if (!RB_EMPTY_ROOT(&idle_class_st->active))
- class_idx = BFQ_IOPRIO_CLASSES - 1;
- /* About to be served if backlogged, or not yet backlogged */
- sd->bfq_class_idle_last_service = jiffies;
- }
-
- /*
- * Find the next entity to serve for the highest-priority
- * class, unless the idle class needs to be served.
- */
- for (; class_idx < BFQ_IOPRIO_CLASSES; class_idx++) {
- entity = __bfq_lookup_next_entity(st + class_idx,
- sd->in_service_entity);
-
- if (entity)
- break;
- }
-
- if (!entity)
- return NULL;
-
- return entity;
-}
-
-static bool next_queue_may_preempt(struct bfq_data *bfqd)
-{
- struct bfq_sched_data *sd = &bfqd->root_group->sched_data;
-
- return sd->next_in_service != sd->in_service_entity;
-}
-
-/*
- * Get next queue for service.
- */
-static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
-{
- struct bfq_entity *entity = NULL;
- struct bfq_sched_data *sd;
- struct bfq_queue *bfqq;
-
- if (bfqd->busy_queues == 0)
- return NULL;
-
- /*
- * Traverse the path from the root to the leaf entity to
- * serve. Set in service all the entities visited along the
- * way.
- */
- sd = &bfqd->root_group->sched_data;
- for (; sd ; sd = entity->my_sched_data) {
- /*
- * WARNING. We are about to set the in-service entity
- * to sd->next_in_service, i.e., to the (cached) value
- * returned by bfq_lookup_next_entity(sd) the last
- * time it was invoked, i.e., the last time when the
- * service order in sd changed as a consequence of the
- * activation or deactivation of an entity. In this
- * respect, if we execute bfq_lookup_next_entity(sd)
- * in this very moment, it may, although with low
- * probability, yield a different entity than that
- * pointed to by sd->next_in_service. This rare event
- * happens in case there was no CLASS_IDLE entity to
- * serve for sd when bfq_lookup_next_entity(sd) was
- * invoked for the last time, while there is now one
- * such entity.
- *
- * If the above event happens, then the scheduling of
- * such entity in CLASS_IDLE is postponed until the
- * service of the sd->next_in_service entity
- * finishes. In fact, when the latter is expired,
- * bfq_lookup_next_entity(sd) gets called again,
- * exactly to update sd->next_in_service.
- */
-
- /* Make next_in_service entity become in_service_entity */
- entity = sd->next_in_service;
- sd->in_service_entity = entity;
-
- /*
- * Reset the accumulator of the amount of service that
- * the entity is about to receive.
- */
- entity->service = 0;
-
- /*
- * If entity is no longer a candidate for next
- * service, then we extract it from its active tree,
- * for the following reason. To further boost the
- * throughput in some special case, BFQ needs to know
- * which is the next candidate entity to serve, while
- * there is already an entity in service. In this
- * respect, to make it easy to compute/update the next
- * candidate entity to serve after the current
- * candidate has been set in service, there is a case
- * where it is necessary to extract the current
- * candidate from its service tree. Such a case is
- * when the entity just set in service cannot be also
- * a candidate for next service. Details about when
- * this conditions holds are reported in the comments
- * on the function bfq_no_longer_next_in_service()
- * invoked below.
- */
- if (bfq_no_longer_next_in_service(entity))
- bfq_active_extract(bfq_entity_service_tree(entity),
- entity);
-
- /*
- * For the same reason why we may have just extracted
- * entity from its active tree, we may need to update
- * next_in_service for the sched_data of entity too,
- * regardless of whether entity has been extracted.
- * In fact, even if entity has not been extracted, a
- * descendant entity may get extracted. Such an event
- * would cause a change in next_in_service for the
- * level of the descendant entity, and thus possibly
- * back to upper levels.
- *
- * We cannot perform the resulting needed update
- * before the end of this loop, because, to know which
- * is the correct next-to-serve candidate entity for
- * each level, we need first to find the leaf entity
- * to set in service. In fact, only after we know
- * which is the next-to-serve leaf entity, we can
- * discover whether the parent entity of the leaf
- * entity becomes the next-to-serve, and so on.
- */
-
- }
-
- bfqq = bfq_entity_to_bfqq(entity);
-
- /*
- * We can finally update all next-to-serve entities along the
- * path from the leaf entity just set in service to the root.
- */
- for_each_entity(entity) {
- struct bfq_sched_data *sd = entity->sched_data;
-
- if (!bfq_update_next_in_service(sd, NULL))
- break;
- }
-
- return bfqq;
-}
-
-static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
-{
- struct bfq_queue *in_serv_bfqq = bfqd->in_service_queue;
- struct bfq_entity *in_serv_entity = &in_serv_bfqq->entity;
- struct bfq_entity *entity = in_serv_entity;
-
- if (bfqd->in_service_bic) {
- /*
- * Schedule the release of a reference to
- * bfqd->in_service_bic->icq.ioc to right after the
- * scheduler lock is released. This ioc is not
- * released immediately, to not risk to possibly take
- * an ioc->lock while holding the scheduler lock.
- */
- bfqd->ioc_to_put = bfqd->in_service_bic->icq.ioc;
- bfqd->in_service_bic = NULL;
- }
-
- bfq_clear_bfqq_wait_request(in_serv_bfqq);
- hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
- bfqd->in_service_queue = NULL;
-
- /*
- * When this function is called, all in-service entities have
- * been properly deactivated or requeued, so we can safely
- * execute the final step: reset in_service_entity along the
- * path from entity to the root.
- */
- for_each_entity(entity)
- entity->sched_data->in_service_entity = NULL;
-
- /*
- * in_serv_entity is no longer in service, so, if it is in no
- * service tree either, then release the service reference to
- * the queue it represents (taken with bfq_get_entity).
- */
- if (!in_serv_entity->on_st)
- bfq_put_queue(in_serv_bfqq);
-}
-
-static void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
- bool ins_into_idle_tree, bool expiration)
-{
- struct bfq_entity *entity = &bfqq->entity;
-
- bfq_deactivate_entity(entity, ins_into_idle_tree, expiration);
-}
-
-static void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
-{
- struct bfq_entity *entity = &bfqq->entity;
-
- bfq_activate_requeue_entity(entity, bfq_bfqq_non_blocking_wait_rq(bfqq),
- false);
- bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
-}
-
-static void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
-{
- struct bfq_entity *entity = &bfqq->entity;
-
- bfq_activate_requeue_entity(entity, false,
- bfqq == bfqd->in_service_queue);
-}
-
-static void bfqg_stats_update_dequeue(struct bfq_group *bfqg);
-
-/*
- * Called when the bfqq no longer has requests pending, remove it from
- * the service tree. As a special case, it can be invoked during an
- * expiration.
- */
-static void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
- bool expiration)
-{
- bfq_log_bfqq(bfqd, bfqq, "del from busy");
-
- bfq_clear_bfqq_busy(bfqq);
-
- bfqd->busy_queues--;
-
- if (bfqq->wr_coeff > 1)
- bfqd->wr_busy_queues--;
-
- bfqg_stats_update_dequeue(bfqq_group(bfqq));
-
- bfq_deactivate_bfqq(bfqd, bfqq, true, expiration);
-}
-
-/*
- * Called when an inactive queue receives a new request.
- */
-static void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
-{
- bfq_log_bfqq(bfqd, bfqq, "add to busy");
-
- bfq_activate_bfqq(bfqd, bfqq);
-
- bfq_mark_bfqq_busy(bfqq);
- bfqd->busy_queues++;
-
- if (bfqq->wr_coeff > 1)
- bfqd->wr_busy_queues++;
-}
-
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-
-/* bfqg stats flags */
-enum bfqg_stats_flags {
- BFQG_stats_waiting = 0,
- BFQG_stats_idling,
- BFQG_stats_empty,
-};
-
-#define BFQG_FLAG_FNS(name) \
-static void bfqg_stats_mark_##name(struct bfqg_stats *stats) \
-{ \
- stats->flags |= (1 << BFQG_stats_##name); \
-} \
-static void bfqg_stats_clear_##name(struct bfqg_stats *stats) \
-{ \
- stats->flags &= ~(1 << BFQG_stats_##name); \
-} \
-static int bfqg_stats_##name(struct bfqg_stats *stats) \
-{ \
- return (stats->flags & (1 << BFQG_stats_##name)) != 0; \
-} \
-
-BFQG_FLAG_FNS(waiting)
-BFQG_FLAG_FNS(idling)
-BFQG_FLAG_FNS(empty)
-#undef BFQG_FLAG_FNS
-
-/* This should be called with the queue_lock held. */
-static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
-{
- unsigned long long now;
-
- if (!bfqg_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);
- bfqg_stats_clear_waiting(stats);
-}
-
-/* This should be called with the queue_lock held. */
-static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
- struct bfq_group *curr_bfqg)
-{
- struct bfqg_stats *stats = &bfqg->stats;
-
- if (bfqg_stats_waiting(stats))
- return;
- if (bfqg == curr_bfqg)
- return;
- stats->start_group_wait_time = sched_clock();
- bfqg_stats_mark_waiting(stats);
-}
-
-/* This should be called with the queue_lock held. */
-static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
-{
- unsigned long long now;
-
- if (!bfqg_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);
- bfqg_stats_clear_empty(stats);
-}
-
-static void bfqg_stats_update_dequeue(struct bfq_group *bfqg)
-{
- blkg_stat_add(&bfqg->stats.dequeue, 1);
-}
-
-static void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg)
-{
- struct bfqg_stats *stats = &bfqg->stats;
-
- if (blkg_rwstat_total(&stats->queued))
- return;
-
- /*
- * group is already marked empty. This can happen if bfqq 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 (bfqg_stats_empty(stats))
- return;
-
- stats->start_empty_time = sched_clock();
- bfqg_stats_mark_empty(stats);
-}
-
-static void bfqg_stats_update_idle_time(struct bfq_group *bfqg)
-{
- struct bfqg_stats *stats = &bfqg->stats;
-
- if (bfqg_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);
- bfqg_stats_clear_idling(stats);
- }
-}
-
-static void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg)
-{
- struct bfqg_stats *stats = &bfqg->stats;
-
- stats->start_idle_time = sched_clock();
- bfqg_stats_mark_idling(stats);
-}
-
-static void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg)
-{
- struct bfqg_stats *stats = &bfqg->stats;
-
- blkg_stat_add(&stats->avg_queue_size_sum,
- blkg_rwstat_total(&stats->queued));
- blkg_stat_add(&stats->avg_queue_size_samples, 1);
- bfqg_stats_update_group_wait_time(stats);
-}
-
-/*
- * blk-cgroup policy-related handlers
- * The following functions help in converting between blk-cgroup
- * internal structures and BFQ-specific structures.
- */
-
-static struct bfq_group *pd_to_bfqg(struct blkg_policy_data *pd)
-{
- return pd ? container_of(pd, struct bfq_group, pd) : NULL;
-}
-
-static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg)
-{
- return pd_to_blkg(&bfqg->pd);
-}
-
-static struct blkcg_policy blkcg_policy_bfq;
-
-static struct bfq_group *blkg_to_bfqg(struct blkcg_gq *blkg)
-{
- return pd_to_bfqg(blkg_to_pd(blkg, &blkcg_policy_bfq));
-}
-
-/*
- * bfq_group handlers
- * The following functions help in navigating the bfq_group hierarchy
- * by allowing to find the parent of a bfq_group or the bfq_group
- * associated to a bfq_queue.
- */
-
-static struct bfq_group *bfqg_parent(struct bfq_group *bfqg)
-{
- struct blkcg_gq *pblkg = bfqg_to_blkg(bfqg)->parent;
-
- return pblkg ? blkg_to_bfqg(pblkg) : NULL;
-}
-
-static struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
-{
- struct bfq_entity *group_entity = bfqq->entity.parent;
-
- return group_entity ? container_of(group_entity, struct bfq_group,
- entity) :
- bfqq->bfqd->root_group;
-}
-
-/*
- * The following two functions handle get and put of a bfq_group by
- * wrapping the related blk-cgroup hooks.
- */
-
-static void bfqg_get(struct bfq_group *bfqg)
-{
- return blkg_get(bfqg_to_blkg(bfqg));
-}
-
-static void bfqg_put(struct bfq_group *bfqg)
-{
- return blkg_put(bfqg_to_blkg(bfqg));
-}
-
-static void bfqg_stats_update_io_add(struct bfq_group *bfqg,
- struct bfq_queue *bfqq,
- unsigned int op)
-{
- blkg_rwstat_add(&bfqg->stats.queued, op, 1);
- bfqg_stats_end_empty_time(&bfqg->stats);
- if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue))
- bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq));
-}
-
-static void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op)
-{
- blkg_rwstat_add(&bfqg->stats.queued, op, -1);
-}
-
-static void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op)
-{
- blkg_rwstat_add(&bfqg->stats.merged, op, 1);
-}
-
-static void bfqg_stats_update_completion(struct bfq_group *bfqg,
- uint64_t start_time, uint64_t io_start_time,
- unsigned int op)
-{
- struct bfqg_stats *stats = &bfqg->stats;
- unsigned long long now = sched_clock();
-
- if (time_after64(now, io_start_time))
- blkg_rwstat_add(&stats->service_time, op,
- now - io_start_time);
- if (time_after64(io_start_time, start_time))
- blkg_rwstat_add(&stats->wait_time, op,
- io_start_time - start_time);
-}
-
-/* @stats = 0 */
-static void bfqg_stats_reset(struct bfqg_stats *stats)
-{
- /* queued stats shouldn't be cleared */
- blkg_rwstat_reset(&stats->merged);
- blkg_rwstat_reset(&stats->service_time);
- blkg_rwstat_reset(&stats->wait_time);
- blkg_stat_reset(&stats->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);
-}
-
-/* @to += @from */
-static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from)
-{
- if (!to || !from)
- return;
-
- /* queued stats shouldn't be cleared */
- blkg_rwstat_add_aux(&to->merged, &from->merged);
- blkg_rwstat_add_aux(&to->service_time, &from->service_time);
- blkg_rwstat_add_aux(&to->wait_time, &from->wait_time);
- blkg_stat_add_aux(&from->time, &from->time);
- blkg_stat_add_aux(&to->avg_queue_size_sum, &from->avg_queue_size_sum);
- blkg_stat_add_aux(&to->avg_queue_size_samples,
- &from->avg_queue_size_samples);
- blkg_stat_add_aux(&to->dequeue, &from->dequeue);
- blkg_stat_add_aux(&to->group_wait_time, &from->group_wait_time);
- blkg_stat_add_aux(&to->idle_time, &from->idle_time);
- blkg_stat_add_aux(&to->empty_time, &from->empty_time);
-}
-
-/*
- * Transfer @bfqg's stats to its parent's aux counts so that the ancestors'
- * recursive stats can still account for the amount used by this bfqg after
- * it's gone.
- */
-static void bfqg_stats_xfer_dead(struct bfq_group *bfqg)
-{
- struct bfq_group *parent;
-
- if (!bfqg) /* root_group */
- return;
-
- parent = bfqg_parent(bfqg);
-
- lockdep_assert_held(bfqg_to_blkg(bfqg)->q->queue_lock);
-
- if (unlikely(!parent))
- return;
-
- bfqg_stats_add_aux(&parent->stats, &bfqg->stats);
- bfqg_stats_reset(&bfqg->stats);
-}
-
-static void bfq_init_entity(struct bfq_entity *entity,
- struct bfq_group *bfqg)
-{
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-
- entity->weight = entity->new_weight;
- entity->orig_weight = entity->new_weight;
- if (bfqq) {
- bfqq->ioprio = bfqq->new_ioprio;
- bfqq->ioprio_class = bfqq->new_ioprio_class;
- bfqg_get(bfqg);
- }
- entity->parent = bfqg->my_entity; /* NULL for root group */
- entity->sched_data = &bfqg->sched_data;
-}
-
-static void bfqg_stats_exit(struct bfqg_stats *stats)
-{
- blkg_rwstat_exit(&stats->merged);
- blkg_rwstat_exit(&stats->service_time);
- blkg_rwstat_exit(&stats->wait_time);
- blkg_rwstat_exit(&stats->queued);
- blkg_stat_exit(&stats->time);
- blkg_stat_exit(&stats->avg_queue_size_sum);
- blkg_stat_exit(&stats->avg_queue_size_samples);
- blkg_stat_exit(&stats->dequeue);
- blkg_stat_exit(&stats->group_wait_time);
- blkg_stat_exit(&stats->idle_time);
- blkg_stat_exit(&stats->empty_time);
-}
-
-static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
-{
- if (blkg_rwstat_init(&stats->merged, gfp) ||
- blkg_rwstat_init(&stats->service_time, gfp) ||
- blkg_rwstat_init(&stats->wait_time, gfp) ||
- blkg_rwstat_init(&stats->queued, gfp) ||
- blkg_stat_init(&stats->time, gfp) ||
- blkg_stat_init(&stats->avg_queue_size_sum, gfp) ||
- blkg_stat_init(&stats->avg_queue_size_samples, gfp) ||
- blkg_stat_init(&stats->dequeue, gfp) ||
- blkg_stat_init(&stats->group_wait_time, gfp) ||
- blkg_stat_init(&stats->idle_time, gfp) ||
- blkg_stat_init(&stats->empty_time, gfp)) {
- bfqg_stats_exit(stats);
- return -ENOMEM;
- }
-
- return 0;
-}
-
-static struct bfq_group_data *cpd_to_bfqgd(struct blkcg_policy_data *cpd)
-{
- return cpd ? container_of(cpd, struct bfq_group_data, pd) : NULL;
-}
-
-static struct bfq_group_data *blkcg_to_bfqgd(struct blkcg *blkcg)
-{
- return cpd_to_bfqgd(blkcg_to_cpd(blkcg, &blkcg_policy_bfq));
-}
-
-static struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp)
-{
- struct bfq_group_data *bgd;
-
- bgd = kzalloc(sizeof(*bgd), gfp);
- if (!bgd)
- return NULL;
- return &bgd->pd;
-}
-
-static void bfq_cpd_init(struct blkcg_policy_data *cpd)
-{
- struct bfq_group_data *d = cpd_to_bfqgd(cpd);
-
- d->weight = cgroup_subsys_on_dfl(io_cgrp_subsys) ?
- CGROUP_WEIGHT_DFL : BFQ_WEIGHT_LEGACY_DFL;
-}
-
-static void bfq_cpd_free(struct blkcg_policy_data *cpd)
-{
- kfree(cpd_to_bfqgd(cpd));
-}
-
-static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node)
-{
- struct bfq_group *bfqg;
-
- bfqg = kzalloc_node(sizeof(*bfqg), gfp, node);
- if (!bfqg)
- return NULL;
-
- if (bfqg_stats_init(&bfqg->stats, gfp)) {
- kfree(bfqg);
- return NULL;
- }
-
- return &bfqg->pd;
-}
-
-static void bfq_pd_init(struct blkg_policy_data *pd)
-{
- struct blkcg_gq *blkg = pd_to_blkg(pd);
- struct bfq_group *bfqg = blkg_to_bfqg(blkg);
- struct bfq_data *bfqd = blkg->q->elevator->elevator_data;
- struct bfq_entity *entity = &bfqg->entity;
- struct bfq_group_data *d = blkcg_to_bfqgd(blkg->blkcg);
-
- entity->orig_weight = entity->weight = entity->new_weight = d->weight;
- entity->my_sched_data = &bfqg->sched_data;
- bfqg->my_entity = entity; /*
- * the root_group's will be set to NULL
- * in bfq_init_queue()
- */
- bfqg->bfqd = bfqd;
- bfqg->rq_pos_tree = RB_ROOT;
-}
-
-static void bfq_pd_free(struct blkg_policy_data *pd)
-{
- struct bfq_group *bfqg = pd_to_bfqg(pd);
-
- bfqg_stats_exit(&bfqg->stats);
- return kfree(bfqg);
-}
-
-static void bfq_pd_reset_stats(struct blkg_policy_data *pd)
-{
- struct bfq_group *bfqg = pd_to_bfqg(pd);
-
- bfqg_stats_reset(&bfqg->stats);
-}
-
-static void bfq_group_set_parent(struct bfq_group *bfqg,
- struct bfq_group *parent)
-{
- struct bfq_entity *entity;
-
- entity = &bfqg->entity;
- entity->parent = parent->my_entity;
- entity->sched_data = &parent->sched_data;
-}
-
-static struct bfq_group *bfq_lookup_bfqg(struct bfq_data *bfqd,
- struct blkcg *blkcg)
-{
- struct blkcg_gq *blkg;
-
- blkg = blkg_lookup(blkcg, bfqd->queue);
- if (likely(blkg))
- return blkg_to_bfqg(blkg);
- return NULL;
-}
-
-static struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
- struct blkcg *blkcg)
-{
- struct bfq_group *bfqg, *parent;
- struct bfq_entity *entity;
-
- bfqg = bfq_lookup_bfqg(bfqd, blkcg);
-
- if (unlikely(!bfqg))
- return NULL;
-
- /*
- * Update chain of bfq_groups as we might be handling a leaf group
- * which, along with some of its relatives, has not been hooked yet
- * to the private hierarchy of BFQ.
- */
- entity = &bfqg->entity;
- for_each_entity(entity) {
- bfqg = container_of(entity, struct bfq_group, entity);
- if (bfqg != bfqd->root_group) {
- parent = bfqg_parent(bfqg);
- if (!parent)
- parent = bfqd->root_group;
- bfq_group_set_parent(bfqg, parent);
- }
- }
-
- return bfqg;
-}
-
-static void bfq_pos_tree_add_move(struct bfq_data *bfqd,
- struct bfq_queue *bfqq);
-static void bfq_bfqq_expire(struct bfq_data *bfqd,
- struct bfq_queue *bfqq,
- bool compensate,
- enum bfqq_expiration reason);
-
-/**
- * bfq_bfqq_move - migrate @bfqq to @bfqg.
- * @bfqd: queue descriptor.
- * @bfqq: the queue to move.
- * @bfqg: the group to move to.
- *
- * Move @bfqq to @bfqg, deactivating it from its old group and reactivating
- * it on the new one. Avoid putting the entity on the old group idle tree.
- *
- * Must be called under the queue lock; the cgroup owning @bfqg must
- * not disappear (by now this just means that we are called under
- * rcu_read_lock()).
- */
-static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
- struct bfq_group *bfqg)
-{
- struct bfq_entity *entity = &bfqq->entity;
-
- /* If bfqq is empty, then bfq_bfqq_expire also invokes
- * bfq_del_bfqq_busy, thereby removing bfqq and its entity
- * from data structures related to current group. Otherwise we
- * need to remove bfqq explicitly with bfq_deactivate_bfqq, as
- * we do below.
- */
- if (bfqq == bfqd->in_service_queue)
- bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
- false, BFQQE_PREEMPTED);
-
- if (bfq_bfqq_busy(bfqq))
- bfq_deactivate_bfqq(bfqd, bfqq, false, false);
- else if (entity->on_st)
- bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
- bfqg_put(bfqq_group(bfqq));
-
- /*
- * Here we use a reference to bfqg. We don't need a refcounter
- * as the cgroup reference will not be dropped, so that its
- * destroy() callback will not be invoked.
- */
- entity->parent = bfqg->my_entity;
- entity->sched_data = &bfqg->sched_data;
- bfqg_get(bfqg);
-
- if (bfq_bfqq_busy(bfqq)) {
- bfq_pos_tree_add_move(bfqd, bfqq);
- bfq_activate_bfqq(bfqd, bfqq);
- }
-
- if (!bfqd->in_service_queue && !bfqd->rq_in_driver)
- bfq_schedule_dispatch(bfqd);
-}
-
-/**
- * __bfq_bic_change_cgroup - move @bic to @cgroup.
- * @bfqd: the queue descriptor.
- * @bic: the bic to move.
- * @blkcg: the blk-cgroup to move to.
- *
- * Move bic to blkcg, assuming that bfqd->queue is locked; the caller
- * has to make sure that the reference to cgroup is valid across the call.
- *
- * NOTE: an alternative approach might have been to store the current
- * cgroup in bfqq and getting a reference to it, reducing the lookup
- * time here, at the price of slightly more complex code.
- */
-static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
- struct bfq_io_cq *bic,
- struct blkcg *blkcg)
-{
- struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0);
- struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1);
- struct bfq_group *bfqg;
- struct bfq_entity *entity;
-
- bfqg = bfq_find_set_group(bfqd, blkcg);
-
- if (unlikely(!bfqg))
- bfqg = bfqd->root_group;
-
- if (async_bfqq) {
- entity = &async_bfqq->entity;
-
- if (entity->sched_data != &bfqg->sched_data) {
- bic_set_bfqq(bic, NULL, 0);
- bfq_log_bfqq(bfqd, async_bfqq,
- "bic_change_group: %p %d",
- async_bfqq, async_bfqq->ref);
- bfq_put_queue(async_bfqq);
- }
- }
-
- if (sync_bfqq) {
- entity = &sync_bfqq->entity;
- if (entity->sched_data != &bfqg->sched_data)
- bfq_bfqq_move(bfqd, sync_bfqq, bfqg);
- }
-
- return bfqg;
-}
-
-static void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
-{
- struct bfq_data *bfqd = bic_to_bfqd(bic);
- struct bfq_group *bfqg = NULL;
- uint64_t serial_nr;
-
- rcu_read_lock();
- serial_nr = bio_blkcg(bio)->css.serial_nr;
-
- /*
- * Check whether blkcg has changed. The condition may trigger
- * spuriously on a newly created cic but there's no harm.
- */
- if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr))
- goto out;
-
- bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio));
- bic->blkcg_serial_nr = serial_nr;
-out:
- rcu_read_unlock();
-}
-
-/**
- * bfq_flush_idle_tree - deactivate any entity on the idle tree of @st.
- * @st: the service tree being flushed.
- */
-static void bfq_flush_idle_tree(struct bfq_service_tree *st)
-{
- struct bfq_entity *entity = st->first_idle;
-
- for (; entity ; entity = st->first_idle)
- __bfq_deactivate_entity(entity, false);
-}
-
-/**
- * bfq_reparent_leaf_entity - move leaf entity to the root_group.
- * @bfqd: the device data structure with the root group.
- * @entity: the entity to move.
- */
-static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
- struct bfq_entity *entity)
-{
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-
- bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
-}
-
-/**
- * bfq_reparent_active_entities - move to the root group all active
- * entities.
- * @bfqd: the device data structure with the root group.
- * @bfqg: the group to move from.
- * @st: the service tree with the entities.
- *
- * Needs queue_lock to be taken and reference to be valid over the call.
- */
-static void bfq_reparent_active_entities(struct bfq_data *bfqd,
- struct bfq_group *bfqg,
- struct bfq_service_tree *st)
-{
- struct rb_root *active = &st->active;
- struct bfq_entity *entity = NULL;
-
- if (!RB_EMPTY_ROOT(&st->active))
- entity = bfq_entity_of(rb_first(active));
-
- for (; entity ; entity = bfq_entity_of(rb_first(active)))
- bfq_reparent_leaf_entity(bfqd, entity);
-
- if (bfqg->sched_data.in_service_entity)
- bfq_reparent_leaf_entity(bfqd,
- bfqg->sched_data.in_service_entity);
-}
-
-/**
- * bfq_pd_offline - deactivate the entity associated with @pd,
- * and reparent its children entities.
- * @pd: descriptor of the policy going offline.
- *
- * blkio already grabs the queue_lock for us, so no need to use
- * RCU-based magic
- */
-static void bfq_pd_offline(struct blkg_policy_data *pd)
-{
- struct bfq_service_tree *st;
- struct bfq_group *bfqg = pd_to_bfqg(pd);
- struct bfq_data *bfqd = bfqg->bfqd;
- struct bfq_entity *entity = bfqg->my_entity;
- unsigned long flags;
- int i;
-
- if (!entity) /* root group */
- return;
-
- spin_lock_irqsave(&bfqd->lock, flags);
- /*
- * Empty all service_trees belonging to this group before
- * deactivating the group itself.
- */
- for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) {
- st = bfqg->sched_data.service_tree + i;
-
- /*
- * The idle tree may still contain bfq_queues belonging
- * to exited task because they never migrated to a different
- * cgroup from the one being destroyed now. No one else
- * can access them so it's safe to act without any lock.
- */
- bfq_flush_idle_tree(st);
-
- /*
- * It may happen that some queues are still active
- * (busy) upon group destruction (if the corresponding
- * processes have been forced to terminate). We move
- * all the leaf entities corresponding to these queues
- * to the root_group.
- * Also, it may happen that the group has an entity
- * in service, which is disconnected from the active
- * tree: it must be moved, too.
- * There is no need to put the sync queues, as the
- * scheduler has taken no reference.
- */
- bfq_reparent_active_entities(bfqd, bfqg, st);
- }
-
- __bfq_deactivate_entity(entity, false);
- bfq_put_async_queues(bfqd, bfqg);
-
- bfq_unlock_put_ioc_restore(bfqd, flags);
- /*
- * @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...
- */
- bfqg_stats_xfer_dead(bfqg);
-}
-
-static void bfq_end_wr_async(struct bfq_data *bfqd)
-{
- struct blkcg_gq *blkg;
-
- list_for_each_entry(blkg, &bfqd->queue->blkg_list, q_node) {
- struct bfq_group *bfqg = blkg_to_bfqg(blkg);
-
- bfq_end_wr_async_queues(bfqd, bfqg);
- }
- bfq_end_wr_async_queues(bfqd, bfqd->root_group);
-}
-
-static int bfq_io_show_weight(struct seq_file *sf, void *v)
-{
- struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
- struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
- unsigned int val = 0;
-
- if (bfqgd)
- val = bfqgd->weight;
-
- seq_printf(sf, "%u\n", val);
-
- return 0;
-}
-
-static int bfq_io_set_weight_legacy(struct cgroup_subsys_state *css,
- struct cftype *cftype,
- u64 val)
-{
- struct blkcg *blkcg = css_to_blkcg(css);
- struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
- struct blkcg_gq *blkg;
- int ret = -ERANGE;
-
- if (val < BFQ_MIN_WEIGHT || val > BFQ_MAX_WEIGHT)
- return ret;
-
- ret = 0;
- spin_lock_irq(&blkcg->lock);
- bfqgd->weight = (unsigned short)val;
- hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
- struct bfq_group *bfqg = blkg_to_bfqg(blkg);
-
- if (!bfqg)
- continue;
- /*
- * Setting the prio_changed flag of the entity
- * to 1 with new_weight == weight would re-set
- * the value of the weight to its ioprio mapping.
- * Set the flag only if necessary.
- */
- if ((unsigned short)val != bfqg->entity.new_weight) {
- bfqg->entity.new_weight = (unsigned short)val;
- /*
- * Make sure that the above new value has been
- * stored in bfqg->entity.new_weight before
- * setting the prio_changed flag. In fact,
- * this flag may be read asynchronously (in
- * critical sections protected by a different
- * lock than that held here), and finding this
- * flag set may cause the execution of the code
- * for updating parameters whose value may
- * depend also on bfqg->entity.new_weight (in
- * __bfq_entity_update_weight_prio).
- * This barrier makes sure that the new value
- * of bfqg->entity.new_weight is correctly
- * seen in that code.
- */
- smp_wmb();
- bfqg->entity.prio_changed = 1;
- }
- }
- spin_unlock_irq(&blkcg->lock);
-
- return ret;
-}
-
-static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
- char *buf, size_t nbytes,
- loff_t off)
-{
- u64 weight;
- /* First unsigned long found in the file is used */
- int ret = kstrtoull(strim(buf), 0, &weight);
-
- if (ret)
- return ret;
-
- return bfq_io_set_weight_legacy(of_css(of), NULL, weight);
-}
-
-static int bfqg_print_stat(struct seq_file *sf, void *v)
-{
- blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
- &blkcg_policy_bfq, seq_cft(sf)->private, false);
- return 0;
-}
-
-static int bfqg_print_rwstat(struct seq_file *sf, void *v)
-{
- blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
- &blkcg_policy_bfq, seq_cft(sf)->private, true);
- return 0;
-}
-
-static u64 bfqg_prfill_stat_recursive(struct seq_file *sf,
- struct blkg_policy_data *pd, int off)
-{
- u64 sum = blkg_stat_recursive_sum(pd_to_blkg(pd),
- &blkcg_policy_bfq, off);
- return __blkg_prfill_u64(sf, pd, sum);
-}
-
-static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf,
- struct blkg_policy_data *pd, int off)
-{
- struct blkg_rwstat sum = blkg_rwstat_recursive_sum(pd_to_blkg(pd),
- &blkcg_policy_bfq,
- off);
- return __blkg_prfill_rwstat(sf, pd, &sum);
-}
-
-static int bfqg_print_stat_recursive(struct seq_file *sf, void *v)
-{
- blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
- bfqg_prfill_stat_recursive, &blkcg_policy_bfq,
- seq_cft(sf)->private, false);
- return 0;
-}
-
-static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
-{
- blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
- bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq,
- seq_cft(sf)->private, true);
- return 0;
-}
-
-static u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd,
- int off)
-{
- u64 sum = blkg_rwstat_total(&pd->blkg->stat_bytes);
-
- return __blkg_prfill_u64(sf, pd, sum >> 9);
-}
-
-static int bfqg_print_stat_sectors(struct seq_file *sf, void *v)
-{
- blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
- bfqg_prfill_sectors, &blkcg_policy_bfq, 0, false);
- return 0;
-}
-
-static u64 bfqg_prfill_sectors_recursive(struct seq_file *sf,
- struct blkg_policy_data *pd, int off)
+struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync)
{
- struct blkg_rwstat tmp = blkg_rwstat_recursive_sum(pd->blkg, NULL,
- offsetof(struct blkcg_gq, stat_bytes));
- u64 sum = atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_READ]) +
- atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_WRITE]);
-
- return __blkg_prfill_u64(sf, pd, sum >> 9);
+ return bic->bfqq[is_sync];
}
-static int bfqg_print_stat_sectors_recursive(struct seq_file *sf, void *v)
+void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync)
{
- blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
- bfqg_prfill_sectors_recursive, &blkcg_policy_bfq, 0,
- false);
- return 0;
+ bic->bfqq[is_sync] = bfqq;
}
-static u64 bfqg_prfill_avg_queue_size(struct seq_file *sf,
- struct blkg_policy_data *pd, int off)
+struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
{
- struct bfq_group *bfqg = pd_to_bfqg(pd);
- u64 samples = blkg_stat_read(&bfqg->stats.avg_queue_size_samples);
- u64 v = 0;
-
- if (samples) {
- v = blkg_stat_read(&bfqg->stats.avg_queue_size_sum);
- v = div64_u64(v, samples);
- }
- __blkg_prfill_u64(sf, pd, v);
- return 0;
+ return bic->icq.q->elevator->elevator_data;
}
-/* print avg_queue_size */
-static int bfqg_print_avg_queue_size(struct seq_file *sf, void *v)
+/**
+ * icq_to_bic - convert iocontext queue structure to bfq_io_cq.
+ * @icq: the iocontext queue.
+ */
+static struct bfq_io_cq *icq_to_bic(struct io_cq *icq)
{
- blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
- bfqg_prfill_avg_queue_size, &blkcg_policy_bfq,
- 0, false);
- return 0;
+ /* bic->icq is the first member, %NULL will convert to %NULL */
+ return container_of(icq, struct bfq_io_cq, icq);
}
-static struct bfq_group *
-bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
+/**
+ * bfq_bic_lookup - search into @ioc a bic associated to @bfqd.
+ * @bfqd: the lookup key.
+ * @ioc: the io_context of the process doing I/O.
+ * @q: the request queue.
+ */
+static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
+ struct io_context *ioc,
+ struct request_queue *q)
{
- int ret;
-
- ret = blkcg_activate_policy(bfqd->queue, &blkcg_policy_bfq);
- if (ret)
- return NULL;
-
- return blkg_to_bfqg(bfqd->queue->root_blkg);
-}
-
-static struct cftype bfq_blkcg_legacy_files[] = {
- {
- .name = "bfq.weight",
- .flags = CFTYPE_NOT_ON_ROOT,
- .seq_show = bfq_io_show_weight,
- .write_u64 = bfq_io_set_weight_legacy,
- },
-
- /* statistics, covers only the tasks in the bfqg */
- {
- .name = "bfq.time",
- .private = offsetof(struct bfq_group, stats.time),
- .seq_show = bfqg_print_stat,
- },
- {
- .name = "bfq.sectors",
- .seq_show = bfqg_print_stat_sectors,
- },
- {
- .name = "bfq.io_service_bytes",
- .private = (unsigned long)&blkcg_policy_bfq,
- .seq_show = blkg_print_stat_bytes,
- },
- {
- .name = "bfq.io_serviced",
- .private = (unsigned long)&blkcg_policy_bfq,
- .seq_show = blkg_print_stat_ios,
- },
- {
- .name = "bfq.io_service_time",
- .private = offsetof(struct bfq_group, stats.service_time),
- .seq_show = bfqg_print_rwstat,
- },
- {
- .name = "bfq.io_wait_time",
- .private = offsetof(struct bfq_group, stats.wait_time),
- .seq_show = bfqg_print_rwstat,
- },
- {
- .name = "bfq.io_merged",
- .private = offsetof(struct bfq_group, stats.merged),
- .seq_show = bfqg_print_rwstat,
- },
- {
- .name = "bfq.io_queued",
- .private = offsetof(struct bfq_group, stats.queued),
- .seq_show = bfqg_print_rwstat,
- },
-
- /* the same statictics which cover the bfqg and its descendants */
- {
- .name = "bfq.time_recursive",
- .private = offsetof(struct bfq_group, stats.time),
- .seq_show = bfqg_print_stat_recursive,
- },
- {
- .name = "bfq.sectors_recursive",
- .seq_show = bfqg_print_stat_sectors_recursive,
- },
- {
- .name = "bfq.io_service_bytes_recursive",
- .private = (unsigned long)&blkcg_policy_bfq,
- .seq_show = blkg_print_stat_bytes_recursive,
- },
- {
- .name = "bfq.io_serviced_recursive",
- .private = (unsigned long)&blkcg_policy_bfq,
- .seq_show = blkg_print_stat_ios_recursive,
- },
- {
- .name = "bfq.io_service_time_recursive",
- .private = offsetof(struct bfq_group, stats.service_time),
- .seq_show = bfqg_print_rwstat_recursive,
- },
- {
- .name = "bfq.io_wait_time_recursive",
- .private = offsetof(struct bfq_group, stats.wait_time),
- .seq_show = bfqg_print_rwstat_recursive,
- },
- {
- .name = "bfq.io_merged_recursive",
- .private = offsetof(struct bfq_group, stats.merged),
- .seq_show = bfqg_print_rwstat_recursive,
- },
- {
- .name = "bfq.io_queued_recursive",
- .private = offsetof(struct bfq_group, stats.queued),
- .seq_show = bfqg_print_rwstat_recursive,
- },
- {
- .name = "bfq.avg_queue_size",
- .seq_show = bfqg_print_avg_queue_size,
- },
- {
- .name = "bfq.group_wait_time",
- .private = offsetof(struct bfq_group, stats.group_wait_time),
- .seq_show = bfqg_print_stat,
- },
- {
- .name = "bfq.idle_time",
- .private = offsetof(struct bfq_group, stats.idle_time),
- .seq_show = bfqg_print_stat,
- },
- {
- .name = "bfq.empty_time",
- .private = offsetof(struct bfq_group, stats.empty_time),
- .seq_show = bfqg_print_stat,
- },
- {
- .name = "bfq.dequeue",
- .private = offsetof(struct bfq_group, stats.dequeue),
- .seq_show = bfqg_print_stat,
- },
- { } /* terminate */
-};
-
-static struct cftype bfq_blkg_files[] = {
- {
- .name = "bfq.weight",
- .flags = CFTYPE_NOT_ON_ROOT,
- .seq_show = bfq_io_show_weight,
- .write = bfq_io_set_weight,
- },
- {} /* terminate */
-};
+ if (ioc) {
+ unsigned long flags;
+ struct bfq_io_cq *icq;
-#else /* CONFIG_BFQ_GROUP_IOSCHED */
-
-static inline void bfqg_stats_update_io_add(struct bfq_group *bfqg,
- struct bfq_queue *bfqq, unsigned int op) { }
-static inline void
-bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { }
-static inline void
-bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { }
-static inline void bfqg_stats_update_completion(struct bfq_group *bfqg,
- uint64_t start_time, uint64_t io_start_time,
- unsigned int op) { }
-static inline void
-bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
- struct bfq_group *curr_bfqg) { }
-static inline void bfqg_stats_end_empty_time(struct bfqg_stats *stats) { }
-static inline void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
-static inline void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
-static inline void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
-static inline void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { }
-static inline void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { }
-
-static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
- struct bfq_group *bfqg) {}
-
-static void bfq_init_entity(struct bfq_entity *entity,
- struct bfq_group *bfqg)
-{
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+ spin_lock_irqsave(q->queue_lock, flags);
+ icq = icq_to_bic(ioc_lookup_icq(ioc, q));
+ spin_unlock_irqrestore(q->queue_lock, flags);
- entity->weight = entity->new_weight;
- entity->orig_weight = entity->new_weight;
- if (bfqq) {
- bfqq->ioprio = bfqq->new_ioprio;
- bfqq->ioprio_class = bfqq->new_ioprio_class;
+ return icq;
}
- entity->sched_data = &bfqg->sched_data;
-}
-
-static void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) {}
-
-static void bfq_end_wr_async(struct bfq_data *bfqd)
-{
- bfq_end_wr_async_queues(bfqd, bfqd->root_group);
-}
-
-static struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
- struct blkcg *blkcg)
-{
- return bfqd->root_group;
-}
-static struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
-{
- return bfqq->bfqd->root_group;
+ return NULL;
}
-static struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd,
- int node)
+/*
+ * Scheduler run of queue, if there are requests pending and no one in the
+ * driver that will restart queueing.
+ */
+void bfq_schedule_dispatch(struct bfq_data *bfqd)
{
- struct bfq_group *bfqg;
- int i;
-
- bfqg = kmalloc_node(sizeof(*bfqg), GFP_KERNEL | __GFP_ZERO, node);
- if (!bfqg)
- return NULL;
-
- for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
- bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
-
- return bfqg;
+ if (bfqd->queued != 0) {
+ bfq_log(bfqd, "schedule dispatch");
+ blk_mq_run_hw_queues(bfqd->queue, true);
+ }
}
-#endif /* CONFIG_BFQ_GROUP_IOSCHED */
#define bfq_class_idle(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
#define bfq_class_rt(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_RT)
return bfqq;
}
-static void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
struct rb_node **p, *parent;
struct bfq_queue *__bfqq;
bfqq->pos_root = NULL;
}
+/*
+ * Tell whether there are active queues or groups with differentiated weights.
+ */
+static bool bfq_differentiated_weights(struct bfq_data *bfqd)
+{
+ /*
+ * For weights to differ, at least one of the trees must contain
+ * at least two nodes.
+ */
+ return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
+ (bfqd->queue_weights_tree.rb_node->rb_left ||
+ bfqd->queue_weights_tree.rb_node->rb_right)
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ ) ||
+ (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) &&
+ (bfqd->group_weights_tree.rb_node->rb_left ||
+ bfqd->group_weights_tree.rb_node->rb_right)
+#endif
+ );
+}
+
+/*
+ * The following function returns true if every queue must receive the
+ * same share of the throughput (this condition is used when deciding
+ * whether idling may be disabled, see the comments in the function
+ * bfq_bfqq_may_idle()).
+ *
+ * Such a scenario occurs when:
+ * 1) all active queues have the same weight,
+ * 2) all active groups at the same level in the groups tree have the same
+ * weight,
+ * 3) all active groups at the same level in the groups tree have the same
+ * number of children.
+ *
+ * Unfortunately, keeping the necessary state for evaluating exactly the
+ * above symmetry conditions would be quite complex and time-consuming.
+ * Therefore this function evaluates, instead, the following stronger
+ * sub-conditions, for which it is much easier to maintain the needed
+ * state:
+ * 1) all active queues have the same weight,
+ * 2) all active groups have the same weight,
+ * 3) all active groups have at most one active child each.
+ * In particular, the last two conditions are always true if hierarchical
+ * support and the cgroups interface are not enabled, thus no state needs
+ * to be maintained in this case.
+ */
+static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
+{
+ return !bfq_differentiated_weights(bfqd);
+}
+
+/*
+ * If the weight-counter tree passed as input contains no counter for
+ * the weight of the input entity, then add that counter; otherwise just
+ * increment the existing counter.
+ *
+ * Note that weight-counter trees contain few nodes in mostly symmetric
+ * scenarios. For example, if all queues have the same weight, then the
+ * weight-counter tree for the queues may contain at most one node.
+ * This holds even if low_latency is on, because weight-raised queues
+ * are not inserted in the tree.
+ * In most scenarios, the rate at which nodes are created/destroyed
+ * should be low too.
+ */
+void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
+ struct rb_root *root)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+ /*
+ * Do not insert if the entity is already associated with a
+ * counter, which happens if:
+ * 1) the entity is associated with a queue,
+ * 2) a request arrival has caused the queue to become both
+ * non-weight-raised, and hence change its weight, and
+ * backlogged; in this respect, each of the two events
+ * causes an invocation of this function,
+ * 3) this is the invocation of this function caused by the
+ * second event. This second invocation is actually useless,
+ * and we handle this fact by exiting immediately. More
+ * efficient or clearer solutions might possibly be adopted.
+ */
+ if (entity->weight_counter)
+ return;
+
+ while (*new) {
+ struct bfq_weight_counter *__counter = container_of(*new,
+ struct bfq_weight_counter,
+ weights_node);
+ parent = *new;
+
+ if (entity->weight == __counter->weight) {
+ entity->weight_counter = __counter;
+ goto inc_counter;
+ }
+ if (entity->weight < __counter->weight)
+ new = &((*new)->rb_left);
+ else
+ new = &((*new)->rb_right);
+ }
+
+ entity->weight_counter = kzalloc(sizeof(struct bfq_weight_counter),
+ GFP_ATOMIC);
+
+ /*
+ * In the unlucky event of an allocation failure, we just
+ * exit. This will cause the weight of entity to not be
+ * considered in bfq_differentiated_weights, which, in its
+ * turn, causes the scenario to be deemed wrongly symmetric in
+ * case entity's weight would have been the only weight making
+ * the scenario asymmetric. On the bright side, no unbalance
+ * will however occur when entity becomes inactive again (the
+ * invocation of this function is triggered by an activation
+ * of entity). In fact, bfq_weights_tree_remove does nothing
+ * if !entity->weight_counter.
+ */
+ if (unlikely(!entity->weight_counter))
+ return;
+
+ entity->weight_counter->weight = entity->weight;
+ rb_link_node(&entity->weight_counter->weights_node, parent, new);
+ rb_insert_color(&entity->weight_counter->weights_node, root);
+
+inc_counter:
+ entity->weight_counter->num_active++;
+}
+
+/*
+ * Decrement the weight counter associated with the entity, and, if the
+ * counter reaches 0, remove the counter from the tree.
+ * See the comments to the function bfq_weights_tree_add() for considerations
+ * about overhead.
+ */
+void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
+ struct rb_root *root)
+{
+ if (!entity->weight_counter)
+ return;
+
+ entity->weight_counter->num_active--;
+ if (entity->weight_counter->num_active > 0)
+ goto reset_entity_pointer;
+
+ rb_erase(&entity->weight_counter->weights_node, root);
+ kfree(entity->weight_counter);
+
+reset_entity_pointer:
+ entity->weight_counter = NULL;
+}
+
/*
* Return expired entry, or NULL to just start from scratch in rbtree.
*/
bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish;
bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time;
- if (bfqq->wr_coeff > 1 &&
+ if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
time_is_before_jiffies(bfqq->last_wr_start_finish +
- bfqq->wr_cur_max_time)) {
+ bfqq->wr_cur_max_time))) {
bfq_log_bfqq(bfqq->bfqd, bfqq,
"resume state: switching off wr");
return bfqq->ref - bfqq->allocated - bfqq->entity.on_st;
}
+/* Empty burst list and add just bfqq (see comments on bfq_handle_burst) */
+static void bfq_reset_burst_list(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ struct bfq_queue *item;
+ struct hlist_node *n;
+
+ hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node)
+ hlist_del_init(&item->burst_list_node);
+ hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+ bfqd->burst_size = 1;
+ bfqd->burst_parent_entity = bfqq->entity.parent;
+}
+
+/* Add bfqq to the list of queues in current burst (see bfq_handle_burst) */
+static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ /* Increment burst size to take into account also bfqq */
+ bfqd->burst_size++;
+
+ if (bfqd->burst_size == bfqd->bfq_large_burst_thresh) {
+ struct bfq_queue *pos, *bfqq_item;
+ struct hlist_node *n;
+
+ /*
+ * Enough queues have been activated shortly after each
+ * other to consider this burst as large.
+ */
+ bfqd->large_burst = true;
+
+ /*
+ * We can now mark all queues in the burst list as
+ * belonging to a large burst.
+ */
+ hlist_for_each_entry(bfqq_item, &bfqd->burst_list,
+ burst_list_node)
+ bfq_mark_bfqq_in_large_burst(bfqq_item);
+ bfq_mark_bfqq_in_large_burst(bfqq);
+
+ /*
+ * From now on, and until the current burst finishes, any
+ * new queue being activated shortly after the last queue
+ * was inserted in the burst can be immediately marked as
+ * belonging to a large burst. So the burst list is not
+ * needed any more. Remove it.
+ */
+ hlist_for_each_entry_safe(pos, n, &bfqd->burst_list,
+ burst_list_node)
+ hlist_del_init(&pos->burst_list_node);
+ } else /*
+ * Burst not yet large: add bfqq to the burst list. Do
+ * not increment the ref counter for bfqq, because bfqq
+ * is removed from the burst list before freeing bfqq
+ * in put_queue.
+ */
+ hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+}
+
+/*
+ * If many queues belonging to the same group happen to be created
+ * shortly after each other, then the processes associated with these
+ * queues have typically a common goal. In particular, bursts of queue
+ * creations are usually caused by services or applications that spawn
+ * many parallel threads/processes. Examples are systemd during boot,
+ * or git grep. To help these processes get their job done as soon as
+ * possible, it is usually better to not grant either weight-raising
+ * or device idling to their queues.
+ *
+ * In this comment we describe, firstly, the reasons why this fact
+ * holds, and, secondly, the next function, which implements the main
+ * steps needed to properly mark these queues so that they can then be
+ * treated in a different way.
+ *
+ * The above services or applications benefit mostly from a high
+ * throughput: the quicker the requests of the activated queues are
+ * cumulatively served, the sooner the target job of these queues gets
+ * completed. As a consequence, weight-raising any of these queues,
+ * which also implies idling the device for it, is almost always
+ * counterproductive. In most cases it just lowers throughput.
+ *
+ * On the other hand, a burst of queue creations may be caused also by
+ * the start of an application that does not consist of a lot of
+ * parallel I/O-bound threads. In fact, with a complex application,
+ * several short processes may need to be executed to start-up the
+ * application. In this respect, to start an application as quickly as
+ * possible, the best thing to do is in any case to privilege the I/O
+ * related to the application with respect to all other
+ * I/O. Therefore, the best strategy to start as quickly as possible
+ * an application that causes a burst of queue creations is to
+ * weight-raise all the queues created during the burst. This is the
+ * exact opposite of the best strategy for the other type of bursts.
+ *
+ * In the end, to take the best action for each of the two cases, the
+ * two types of bursts need to be distinguished. Fortunately, this
+ * seems relatively easy, by looking at the sizes of the bursts. In
+ * particular, we found a threshold such that only bursts with a
+ * larger size than that threshold are apparently caused by
+ * services or commands such as systemd or git grep. For brevity,
+ * hereafter we call just 'large' these bursts. BFQ *does not*
+ * weight-raise queues whose creation occurs in a large burst. In
+ * addition, for each of these queues BFQ performs or does not perform
+ * idling depending on which choice boosts the throughput more. The
+ * exact choice depends on the device and request pattern at
+ * hand.
+ *
+ * Unfortunately, false positives may occur while an interactive task
+ * is starting (e.g., an application is being started). The
+ * consequence is that the queues associated with the task do not
+ * enjoy weight raising as expected. Fortunately these false positives
+ * are very rare. They typically occur if some service happens to
+ * start doing I/O exactly when the interactive task starts.
+ *
+ * Turning back to the next function, it implements all the steps
+ * needed to detect the occurrence of a large burst and to properly
+ * mark all the queues belonging to it (so that they can then be
+ * treated in a different way). This goal is achieved by maintaining a
+ * "burst list" that holds, temporarily, the queues that belong to the
+ * burst in progress. The list is then used to mark these queues as
+ * belonging to a large burst if the burst does become large. The main
+ * steps are the following.
+ *
+ * . when the very first queue is created, the queue is inserted into the
+ * list (as it could be the first queue in a possible burst)
+ *
+ * . if the current burst has not yet become large, and a queue Q that does
+ * not yet belong to the burst is activated shortly after the last time
+ * at which a new queue entered the burst list, then the function appends
+ * Q to the burst list
+ *
+ * . if, as a consequence of the previous step, the burst size reaches
+ * the large-burst threshold, then
+ *
+ * . all the queues in the burst list are marked as belonging to a
+ * large burst
+ *
+ * . the burst list is deleted; in fact, the burst list already served
+ * its purpose (keeping temporarily track of the queues in a burst,
+ * so as to be able to mark them as belonging to a large burst in the
+ * previous sub-step), and now is not needed any more
+ *
+ * . the device enters a large-burst mode
+ *
+ * . if a queue Q that does not belong to the burst is created while
+ * the device is in large-burst mode and shortly after the last time
+ * at which a queue either entered the burst list or was marked as
+ * belonging to the current large burst, then Q is immediately marked
+ * as belonging to a large burst.
+ *
+ * . if a queue Q that does not belong to the burst is created a while
+ * later, i.e., not shortly after, than the last time at which a queue
+ * either entered the burst list or was marked as belonging to the
+ * current large burst, then the current burst is deemed as finished and:
+ *
+ * . the large-burst mode is reset if set
+ *
+ * . the burst list is emptied
+ *
+ * . Q is inserted in the burst list, as Q may be the first queue
+ * in a possible new burst (then the burst list contains just Q
+ * after this step).
+ */
+static void bfq_handle_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ /*
+ * If bfqq is already in the burst list or is part of a large
+ * burst, or finally has just been split, then there is
+ * nothing else to do.
+ */
+ if (!hlist_unhashed(&bfqq->burst_list_node) ||
+ bfq_bfqq_in_large_burst(bfqq) ||
+ time_is_after_eq_jiffies(bfqq->split_time +
+ msecs_to_jiffies(10)))
+ return;
+
+ /*
+ * If bfqq's creation happens late enough, or bfqq belongs to
+ * a different group than the burst group, then the current
+ * burst is finished, and related data structures must be
+ * reset.
+ *
+ * In this respect, consider the special case where bfqq is
+ * the very first queue created after BFQ is selected for this
+ * device. In this case, last_ins_in_burst and
+ * burst_parent_entity are not yet significant when we get
+ * here. But it is easy to verify that, whether or not the
+ * following condition is true, bfqq will end up being
+ * inserted into the burst list. In particular the list will
+ * happen to contain only bfqq. And this is exactly what has
+ * to happen, as bfqq may be the first queue of the first
+ * burst.
+ */
+ if (time_is_before_jiffies(bfqd->last_ins_in_burst +
+ bfqd->bfq_burst_interval) ||
+ bfqq->entity.parent != bfqd->burst_parent_entity) {
+ bfqd->large_burst = false;
+ bfq_reset_burst_list(bfqd, bfqq);
+ goto end;
+ }
+
+ /*
+ * If we get here, then bfqq is being activated shortly after the
+ * last queue. So, if the current burst is also large, we can mark
+ * bfqq as belonging to this large burst immediately.
+ */
+ if (bfqd->large_burst) {
+ bfq_mark_bfqq_in_large_burst(bfqq);
+ goto end;
+ }
+
+ /*
+ * If we get here, then a large-burst state has not yet been
+ * reached, but bfqq is being activated shortly after the last
+ * queue. Then we add bfqq to the burst.
+ */
+ bfq_add_to_burst(bfqd, bfqq);
+end:
+ /*
+ * At this point, bfqq either has been added to the current
+ * burst or has caused the current burst to terminate and a
+ * possible new burst to start. In particular, in the second
+ * case, bfqq has become the first queue in the possible new
+ * burst. In both cases last_ins_in_burst needs to be moved
+ * forward.
+ */
+ bfqd->last_ins_in_burst = jiffies;
+}
+
static int bfq_bfqq_budget_left(struct bfq_queue *bfqq)
{
struct bfq_entity *entity = &bfqq->entity;
return bfqd->bfq_max_budget / 32;
}
-static void bfq_bfqq_expire(struct bfq_data *bfqd,
- struct bfq_queue *bfqq,
- bool compensate,
- enum bfqq_expiration reason);
-
/*
* The next function, invoked after the input queue bfqq switches from
* idle to busy, updates the budget of bfqq. The function also tells
unsigned int old_wr_coeff,
bool wr_or_deserves_wr,
bool interactive,
+ bool in_burst,
bool soft_rt)
{
if (old_wr_coeff == 1 && wr_or_deserves_wr) {
if (interactive) { /* update wr coeff and duration */
bfqq->wr_coeff = bfqd->bfq_wr_coeff;
bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
- } else if (soft_rt) {
+ } else if (in_burst)
+ bfqq->wr_coeff = 1;
+ else if (soft_rt) {
/*
* The application is now or still meeting the
* requirements for being deemed soft rt. We
struct request *rq,
bool *interactive)
{
- bool soft_rt, wr_or_deserves_wr, bfqq_wants_to_preempt,
+ bool soft_rt, in_burst, wr_or_deserves_wr,
+ bfqq_wants_to_preempt,
idle_for_long_time = bfq_bfqq_idle_for_long_time(bfqd, bfqq),
/*
* See the comments on
/*
* bfqq deserves to be weight-raised if:
* - it is sync,
+ * - it does not belong to a large burst,
* - it has been idle for enough time or is soft real-time,
* - is linked to a bfq_io_cq (it is not shared in any sense).
*/
+ in_burst = bfq_bfqq_in_large_burst(bfqq);
soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
+ !in_burst &&
time_is_before_jiffies(bfqq->soft_rt_next_start);
- *interactive = idle_for_long_time;
+ *interactive = !in_burst && idle_for_long_time;
wr_or_deserves_wr = bfqd->low_latency &&
(bfqq->wr_coeff > 1 ||
(bfq_bfqq_sync(bfqq) &&
arrived_in_time,
wr_or_deserves_wr);
+ /*
+ * If bfqq happened to be activated in a burst, but has been
+ * idle for much more than an interactive queue, then we
+ * assume that, in the overall I/O initiated in the burst, the
+ * I/O associated with bfqq is finished. So bfqq does not need
+ * to be treated as a queue belonging to a burst
+ * anymore. Accordingly, we reset bfqq's in_large_burst flag
+ * if set, and remove bfqq from the burst list if it's
+ * there. We do not decrement burst_size, because the fact
+ * that bfqq does not need to belong to the burst list any
+ * more does not invalidate the fact that bfqq was created in
+ * a burst.
+ */
+ if (likely(!bfq_bfqq_just_created(bfqq)) &&
+ idle_for_long_time &&
+ time_is_before_jiffies(
+ bfqq->budget_timeout +
+ msecs_to_jiffies(10000))) {
+ hlist_del_init(&bfqq->burst_list_node);
+ bfq_clear_bfqq_in_large_burst(bfqq);
+ }
+
+ bfq_clear_bfqq_just_created(bfqq);
+
+
if (!bfq_bfqq_IO_bound(bfqq)) {
if (arrived_in_time) {
bfqq->requests_within_timer++;
old_wr_coeff,
wr_or_deserves_wr,
*interactive,
+ in_burst,
soft_rt);
if (old_wr_coeff != bfqq->wr_coeff)
bfqq->entity.prio_changed = 1;
}
-static void bfq_end_wr_async_queues(struct bfq_data *bfqd,
- struct bfq_group *bfqg)
+void bfq_end_wr_async_queues(struct bfq_data *bfqd,
+ struct bfq_group *bfqg)
{
int i, j;
* first time that the requests of some process are redirected to
* it.
*
- * We redirect bfqq to new_bfqq and not the opposite, because we
- * are in the context of the process owning bfqq, hence we have
- * the io_cq of this process. So we can immediately configure this
- * io_cq to redirect the requests of the process to new_bfqq.
+ * We redirect bfqq to new_bfqq and not the opposite, because
+ * we are in the context of the process owning bfqq, thus we
+ * have the io_cq of this process. So we can immediately
+ * configure this io_cq to redirect the requests of the
+ * process to new_bfqq. In contrast, the io_cq of new_bfqq is
+ * not available any more (new_bfqq->bic == NULL).
*
- * NOTE, even if new_bfqq coincides with the in-service queue, the
- * io_cq of new_bfqq is not available, because, if the in-service
- * queue is shared, bfqd->in_service_bic may not point to the
- * io_cq of the in-service queue.
- * Redirecting the requests of the process owning bfqq to the
- * currently in-service queue is in any case the best option, as
- * we feed the in-service queue with new requests close to the
- * last request served and, by doing so, hopefully increase the
- * throughput.
+ * Anyway, even in case new_bfqq coincides with the in-service
+ * queue, redirecting requests the in-service queue is the
+ * best option, as we feed the in-service queue with new
+ * requests close to the last request served and, by doing so,
+ * are likely to increase the throughput.
*/
bfqq->new_bfqq = new_bfqq;
new_bfqq->ref += process_refs;
in_service_bfqq = bfqd->in_service_queue;
- if (!in_service_bfqq || in_service_bfqq == bfqq ||
- !bfqd->in_service_bic || wr_from_too_long(in_service_bfqq) ||
+ if (!in_service_bfqq || in_service_bfqq == bfqq
+ || wr_from_too_long(in_service_bfqq) ||
unlikely(in_service_bfqq == &bfqd->oom_bfqq))
goto check_scheduled;
bic->saved_ttime = bfqq->ttime;
bic->saved_idle_window = bfq_bfqq_idle_window(bfqq);
bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
+ bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
+ bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
bic->saved_wr_coeff = bfqq->wr_coeff;
bic->saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt;
bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
}
-static void bfq_get_bic_reference(struct bfq_queue *bfqq)
-{
- /*
- * If bfqq->bic has a non-NULL value, the bic to which it belongs
- * is about to begin using a shared bfq_queue.
- */
- if (bfqq->bic)
- atomic_long_inc(&bfqq->bic->icq.ioc->refcount);
-}
-
static void
bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
* where bfqq has just been created, but has not yet made it
* to be weight-raised (which may happen because EQM may merge
* bfqq even before bfq_add_request is executed for the first
- * time for bfqq).
+ * time for bfqq). Handling this case would however be very
+ * easy, thanks to the flag just_created.
*/
if (new_bfqq->wr_coeff == 1 && bfqq->wr_coeff > 1) {
new_bfqq->wr_coeff = bfqq->wr_coeff;
bfq_log_bfqq(bfqd, new_bfqq, "merge_bfqqs: wr_busy %d",
bfqd->wr_busy_queues);
- /*
- * Grab a reference to the bic, to prevent it from being destroyed
- * before being possibly touched by a bfq_split_bfqq().
- */
- bfq_get_bic_reference(bfqq);
- bfq_get_bic_reference(new_bfqq);
/*
* Merge queues (that is, let bic redirect its requests to new_bfqq)
*/
static void bfq_arm_slice_timer(struct bfq_data *bfqd)
{
struct bfq_queue *bfqq = bfqd->in_service_queue;
- struct bfq_io_cq *bic;
u32 sl;
- /* Processes have exited, don't wait. */
- bic = bfqd->in_service_bic;
- if (!bic || atomic_read(&bic->icq.ioc->active_ref) == 0)
- return;
-
bfq_mark_bfqq_wait_request(bfqq);
/*
*/
sl = bfqd->bfq_slice_idle;
/*
- * Unless the queue is being weight-raised, grant only minimum
- * idle time if the queue is seeky. A long idling is preserved
- * for a weight-raised queue, because it is needed for
- * guaranteeing to the queue its reserved share of the
- * throughput.
- */
- if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1)
+ * Unless the queue is being weight-raised or the scenario is
+ * asymmetric, grant only minimum idle time if the queue
+ * is seeky. A long idling is preserved for a weight-raised
+ * queue, or, more in general, in an asymmetric scenario,
+ * because a long idling is needed for guaranteeing to a queue
+ * its reserved share of the throughput (in particular, it is
+ * needed if the queue has a higher weight than some other
+ * queue).
+ */
+ if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
+ bfq_symmetric_scenario(bfqd))
sl = min_t(u64, sl, BFQ_MIN_TT);
bfqd->last_idling_start = ktime_get();
* former on a timeslice basis, without violating service domain
* guarantees among the latter.
*/
-static void bfq_bfqq_expire(struct bfq_data *bfqd,
- struct bfq_queue *bfqq,
- bool compensate,
- enum bfqq_expiration reason)
+void bfq_bfqq_expire(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ bool compensate,
+ enum bfqq_expiration reason)
{
bool slow;
unsigned long delta = 0;
{
struct bfq_data *bfqd = bfqq->bfqd;
bool idling_boosts_thr, idling_boosts_thr_without_issues,
+ idling_needed_for_service_guarantees,
asymmetric_scenario;
if (bfqd->strict_guarantees)
* The next variable takes into account the cases where idling
* boosts the throughput.
*
- * The value of the variable is computed considering that
- * idling is usually beneficial for the throughput if:
+ * The value of the variable is computed considering, first, that
+ * idling is virtually always beneficial for the throughput if:
* (a) the device is not NCQ-capable, or
- * (b) regardless of the presence of NCQ, the request pattern
- * for bfqq is I/O-bound (possible throughput losses
- * caused by granting idling to seeky queues are mitigated
- * by the fact that, in all scenarios where boosting
- * throughput is the best thing to do, i.e., in all
- * symmetric scenarios, only a minimal idle time is
- * allowed to seeky queues).
- */
- idling_boosts_thr = !bfqd->hw_tag || bfq_bfqq_IO_bound(bfqq);
+ * (b) regardless of the presence of NCQ, the device is rotational
+ * and the request pattern for bfqq is I/O-bound and sequential.
+ *
+ * Secondly, and in contrast to the above item (b), idling an
+ * NCQ-capable flash-based device would not boost the
+ * throughput even with sequential I/O; rather it would lower
+ * the throughput in proportion to how fast the device
+ * is. Accordingly, the next variable is true if any of the
+ * above conditions (a) and (b) is true, and, in particular,
+ * happens to be false if bfqd is an NCQ-capable flash-based
+ * device.
+ */
+ idling_boosts_thr = !bfqd->hw_tag ||
+ (!blk_queue_nonrot(bfqd->queue) && bfq_bfqq_IO_bound(bfqq) &&
+ bfq_bfqq_idle_window(bfqq));
/*
* The value of the next variable,
bfqd->wr_busy_queues == 0;
/*
- * There is then a case where idling must be performed not for
- * throughput concerns, but to preserve service guarantees. To
- * introduce it, we can note that allowing the drive to
- * enqueue more than one request at a time, and hence
+ * There is then a case where idling must be performed not
+ * for throughput concerns, but to preserve service
+ * guarantees.
+ *
+ * To introduce this case, we can note that allowing the drive
+ * to enqueue more than one request at a time, and hence
* delegating de facto final scheduling decisions to the
- * drive's internal scheduler, causes loss of control on the
+ * drive's internal scheduler, entails loss of control on the
* actual request service order. In particular, the critical
- * situation is when requests from different processes happens
+ * situation is when requests from different processes happen
* to be present, at the same time, in the internal queue(s)
* of the drive. In such a situation, the drive, by deciding
* the service order of the internally-queued requests, does
* the service distribution enforced by the drive's internal
* scheduler is likely to coincide with the desired
* device-throughput distribution only in a completely
- * symmetric scenario where: (i) each of these processes must
- * get the same throughput as the others; (ii) all these
- * processes have the same I/O pattern (either sequential or
- * random). In fact, in such a scenario, the drive will tend
- * to treat the requests of each of these processes in about
- * the same way as the requests of the others, and thus to
- * provide each of these processes with about the same
- * throughput (which is exactly the desired throughput
- * distribution). In contrast, in any asymmetric scenario,
- * device idling is certainly needed to guarantee that bfqq
- * receives its assigned fraction of the device throughput
- * (see [1] for details).
+ * symmetric scenario where:
+ * (i) each of these processes must get the same throughput as
+ * the others;
+ * (ii) all these processes have the same I/O pattern
+ (either sequential or random).
+ * In fact, in such a scenario, the drive will tend to treat
+ * the requests of each of these processes in about the same
+ * way as the requests of the others, and thus to provide
+ * each of these processes with about the same throughput
+ * (which is exactly the desired throughput distribution). In
+ * contrast, in any asymmetric scenario, device idling is
+ * certainly needed to guarantee that bfqq receives its
+ * assigned fraction of the device throughput (see [1] for
+ * details).
+ *
+ * We address this issue by controlling, actually, only the
+ * symmetry sub-condition (i), i.e., provided that
+ * sub-condition (i) holds, idling is not performed,
+ * regardless of whether sub-condition (ii) holds. In other
+ * words, only if sub-condition (i) holds, then idling is
+ * allowed, and the device tends to be prevented from queueing
+ * many requests, possibly of several processes. The reason
+ * for not controlling also sub-condition (ii) is that we
+ * exploit preemption to preserve guarantees in case of
+ * symmetric scenarios, even if (ii) does not hold, as
+ * explained in the next two paragraphs.
+ *
+ * Even if a queue, say Q, is expired when it remains idle, Q
+ * can still preempt the new in-service queue if the next
+ * request of Q arrives soon (see the comments on
+ * bfq_bfqq_update_budg_for_activation). If all queues and
+ * groups have the same weight, this form of preemption,
+ * combined with the hole-recovery heuristic described in the
+ * comments on function bfq_bfqq_update_budg_for_activation,
+ * are enough to preserve a correct bandwidth distribution in
+ * the mid term, even without idling. In fact, even if not
+ * idling allows the internal queues of the device to contain
+ * many requests, and thus to reorder requests, we can rather
+ * safely assume that the internal scheduler still preserves a
+ * minimum of mid-term fairness. The motivation for using
+ * preemption instead of idling is that, by not idling,
+ * service guarantees are preserved without minimally
+ * sacrificing throughput. In other words, both a high
+ * throughput and its desired distribution are obtained.
+ *
+ * More precisely, this preemption-based, idleless approach
+ * provides fairness in terms of IOPS, and not sectors per
+ * second. This can be seen with a simple example. Suppose
+ * that there are two queues with the same weight, but that
+ * the first queue receives requests of 8 sectors, while the
+ * second queue receives requests of 1024 sectors. In
+ * addition, suppose that each of the two queues contains at
+ * most one request at a time, which implies that each queue
+ * always remains idle after it is served. Finally, after
+ * remaining idle, each queue receives very quickly a new
+ * request. It follows that the two queues are served
+ * alternatively, preempting each other if needed. This
+ * implies that, although both queues have the same weight,
+ * the queue with large requests receives a service that is
+ * 1024/8 times as high as the service received by the other
+ * queue.
*
- * As for sub-condition (i), actually we check only whether
- * bfqq is being weight-raised. In fact, if bfqq is not being
- * weight-raised, we have that:
- * - if the process associated with bfqq is not I/O-bound, then
- * it is not either latency- or throughput-critical; therefore
- * idling is not needed for bfqq;
- * - if the process asociated with bfqq is I/O-bound, then
- * idling is already granted with bfqq (see the comments on
- * idling_boosts_thr).
+ * On the other hand, device idling is performed, and thus
+ * pure sector-domain guarantees are provided, for the
+ * following queues, which are likely to need stronger
+ * throughput guarantees: weight-raised queues, and queues
+ * with a higher weight than other queues. When such queues
+ * are active, sub-condition (i) is false, which triggers
+ * device idling.
*
- * We do not check sub-condition (ii) at all, i.e., the next
- * variable is true if and only if bfqq is being
- * weight-raised. We do not need to control sub-condition (ii)
- * for the following reason:
- * - if bfqq is being weight-raised, then idling is already
- * guaranteed to bfqq by sub-condition (i);
- * - if bfqq is not being weight-raised, then idling is
- * already guaranteed to bfqq (only) if it matters, i.e., if
- * bfqq is associated to a currently I/O-bound process (see
- * the above comment on sub-condition (i)).
+ * According to the above considerations, the next variable is
+ * true (only) if sub-condition (i) holds. To compute the
+ * value of this variable, we not only use the return value of
+ * the function bfq_symmetric_scenario(), but also check
+ * whether bfqq is being weight-raised, because
+ * bfq_symmetric_scenario() does not take into account also
+ * weight-raised queues (see comments on
+ * bfq_weights_tree_add()).
*
* As a side note, it is worth considering that the above
* device-idling countermeasures may however fail in the
* following unlucky scenario: if idling is (correctly)
- * disabled in a time period during which the symmetry
- * sub-condition holds, and hence the device is allowed to
+ * disabled in a time period during which all symmetry
+ * sub-conditions hold, and hence the device is allowed to
* enqueue many requests, but at some later point in time some
* sub-condition stops to hold, then it may become impossible
* to let requests be served in the desired order until all
* the requests already queued in the device have been served.
*/
- asymmetric_scenario = bfqq->wr_coeff > 1;
+ asymmetric_scenario = bfqq->wr_coeff > 1 ||
+ !bfq_symmetric_scenario(bfqd);
+
+ /*
+ * Finally, there is a case where maximizing throughput is the
+ * best choice even if it may cause unfairness toward
+ * bfqq. Such a case is when bfqq became active in a burst of
+ * queue activations. Queues that became active during a large
+ * burst benefit only from throughput, as discussed in the
+ * comments on bfq_handle_burst. Thus, if bfqq became active
+ * in a burst and not idling the device maximizes throughput,
+ * then the device must no be idled, because not idling the
+ * device provides bfqq and all other queues in the burst with
+ * maximum benefit. Combining this and the above case, we can
+ * now establish when idling is actually needed to preserve
+ * service guarantees.
+ */
+ idling_needed_for_service_guarantees =
+ asymmetric_scenario && !bfq_bfqq_in_large_burst(bfqq);
/*
* We have now all the components we need to compute the return
* is necessary to preserve service guarantees.
*/
return bfq_bfqq_sync(bfqq) &&
- (idling_boosts_thr_without_issues || asymmetric_scenario);
+ (idling_boosts_thr_without_issues ||
+ idling_needed_for_service_guarantees);
}
/*
bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change");
/*
- * If too much time has elapsed from the beginning of
- * this weight-raising period, then end weight raising.
+ * If the queue was activated in a burst, or too much
+ * time has elapsed from the beginning of this
+ * weight-raising period, then end weight raising.
*/
- if (time_is_before_jiffies(bfqq->last_wr_start_finish +
- bfqq->wr_cur_max_time)) {
+ if (bfq_bfqq_in_large_burst(bfqq))
+ bfq_bfqq_end_wr(bfqq);
+ else if (time_is_before_jiffies(bfqq->last_wr_start_finish +
+ bfqq->wr_cur_max_time)) {
if (bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time ||
time_is_before_jiffies(bfqq->wr_start_at_switch_to_srt +
- bfq_wr_duration(bfqd)))
+ bfq_wr_duration(bfqd)))
bfq_bfqq_end_wr(bfqq);
else {
/* switch back to interactive wr */
*/
bfq_update_wr_data(bfqd, bfqq);
- if (!bfqd->in_service_bic) {
- atomic_long_inc(&RQ_BIC(rq)->icq.ioc->refcount);
- bfqd->in_service_bic = RQ_BIC(rq);
- }
-
/*
* Expire bfqq, pretending that its budget expired, if bfqq
* belongs to CLASS_IDLE and other queues are waiting for
spin_lock_irq(&bfqd->lock);
rq = __bfq_dispatch_request(hctx);
- bfq_unlock_put_ioc(bfqd);
+ spin_unlock_irq(&bfqd->lock);
return rq;
}
* Scheduler lock must be held here. Recall not to use bfqq after calling
* this function on it.
*/
-static void bfq_put_queue(struct bfq_queue *bfqq)
+void bfq_put_queue(struct bfq_queue *bfqq)
{
#ifdef CONFIG_BFQ_GROUP_IOSCHED
struct bfq_group *bfqg = bfqq_group(bfqq);
if (bfqq->ref)
return;
- bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p freed", bfqq);
+ if (bfq_bfqq_sync(bfqq))
+ /*
+ * The fact that this queue is being destroyed does not
+ * invalidate the fact that this queue may have been
+ * activated during the current burst. As a consequence,
+ * although the queue does not exist anymore, and hence
+ * needs to be removed from the burst list if there,
+ * the burst size has not to be decremented.
+ */
+ hlist_del_init(&bfqq->burst_list_node);
kmem_cache_free(bfq_pool, bfqq);
#ifdef CONFIG_BFQ_GROUP_IOSCHED
unsigned long flags;
spin_lock_irqsave(&bfqd->lock, flags);
- /*
- * If the bic is using a shared queue, put the
- * reference taken on the io_context when the bic
- * started using a shared bfq_queue. This put cannot
- * make ioc->ref_count reach 0, then no ioc->lock
- * risks to be taken (leading to possible deadlock
- * scenarios).
- */
- if (is_sync && bfq_bfqq_coop(bfqq))
- put_io_context(bic->icq.ioc);
-
bfq_exit_bfqq(bfqd, bfqq);
bic_set_bfqq(bic, NULL, is_sync);
- bfq_unlock_put_ioc_restore(bfqd, flags);
+ spin_unlock_irqrestore(&bfqd->lock, flags);
}
}
bfqq->entity.prio_changed = 1;
}
+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
+ struct bio *bio, bool is_sync,
+ struct bfq_io_cq *bic);
+
static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio)
{
struct bfq_data *bfqd = bic_to_bfqd(bic);
{
RB_CLEAR_NODE(&bfqq->entity.rb_node);
INIT_LIST_HEAD(&bfqq->fifo);
+ INIT_HLIST_NODE(&bfqq->burst_list_node);
bfqq->ref = 0;
bfqq->bfqd = bfqd;
if (!bfq_class_idle(bfqq))
bfq_mark_bfqq_idle_window(bfqq);
bfq_mark_bfqq_sync(bfqq);
+ bfq_mark_bfqq_just_created(bfqq);
} else
bfq_clear_bfqq_sync(bfqq);
new_bfqq->allocated++;
bfqq->allocated--;
new_bfqq->ref++;
+ bfq_clear_bfqq_just_created(bfqq);
/*
* If the bic associated with the process
* issuing this request still points to bfqq
}
}
- bfq_unlock_put_ioc(bfqd);
+ spin_unlock_irq(&bfqd->lock);
}
static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
* mechanism).
*/
bfqq->budget_timeout = jiffies;
+
+ bfq_weights_tree_remove(bfqd, &bfqq->entity,
+ &bfqd->queue_weights_tree);
}
now_ns = ktime_get_ns();
bfq_completed_request(bfqq, bfqd);
bfq_put_rq_priv_body(bfqq);
- bfq_unlock_put_ioc_restore(bfqd, flags);
+ spin_unlock_irqrestore(&bfqd->lock, flags);
} else {
/*
* Request rq may be still/already in the scheduler,
bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);
bic_set_bfqq(bic, bfqq, is_sync);
- if (split && is_sync)
+ if (split && is_sync) {
+ if ((bic->was_in_burst_list && bfqd->large_burst) ||
+ bic->saved_in_large_burst)
+ bfq_mark_bfqq_in_large_burst(bfqq);
+ else {
+ bfq_clear_bfqq_in_large_burst(bfqq);
+ if (bic->was_in_burst_list)
+ hlist_add_head(&bfqq->burst_list_node,
+ &bfqd->burst_list);
+ }
bfqq->split_time = jiffies;
+ }
return bfqq;
}
const int is_sync = rq_is_sync(rq);
struct bfq_queue *bfqq;
bool new_queue = false;
+ bool split = false;
spin_lock_irq(&bfqd->lock);
/* If the queue was seeky for too long, break it apart. */
if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
+
+ /* Update bic before losing reference to bfqq */
+ if (bfq_bfqq_in_large_burst(bfqq))
+ bic->saved_in_large_burst = true;
+
bfqq = bfq_split_bfqq(bic, bfqq);
- /*
- * A reference to bic->icq.ioc needs to be
- * released after a queue split. Do not do it
- * immediately, to not risk to possibly take
- * an ioc->lock while holding the scheduler
- * lock.
- */
- bfqd->ioc_to_put = bic->icq.ioc;
+ split = true;
if (!bfqq)
bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,
*/
if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) {
bfqq->bic = bic;
- if (bfqd->ioc_to_put) { /* if true, there has been a split */
+ if (split) {
/*
* The queue has just been split from a shared
* queue: restore the idle window and the
}
}
- bfq_unlock_put_ioc(bfqd);
+ if (unlikely(bfq_bfqq_just_created(bfqq)))
+ bfq_handle_burst(bfqd, bfqq);
+
+ spin_unlock_irq(&bfqd->lock);
return 0;
bfq_bfqq_expire(bfqd, bfqq, true, reason);
schedule_dispatch:
- bfq_unlock_put_ioc_restore(bfqd, flags);
+ spin_unlock_irqrestore(&bfqd->lock, flags);
bfq_schedule_dispatch(bfqd);
}
* we reparent them to the root cgroup (i.e., the only one that will
* exist for sure until all the requests on a device are gone).
*/
-static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
+void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
{
int i, j;
bfqd->oom_bfqq.new_ioprio_class = IOPRIO_CLASS_BE;
bfqd->oom_bfqq.entity.new_weight =
bfq_ioprio_to_weight(bfqd->oom_bfqq.new_ioprio);
+
+ /* oom_bfqq does not participate to bursts */
+ bfq_clear_bfqq_just_created(&bfqd->oom_bfqq);
+
/*
* Trigger weight initialization, according to ioprio, at the
* oom_bfqq's first activation. The oom_bfqq's ioprio and ioprio
HRTIMER_MODE_REL);
bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
+ bfqd->queue_weights_tree = RB_ROOT;
+ bfqd->group_weights_tree = RB_ROOT;
+
INIT_LIST_HEAD(&bfqd->active_list);
INIT_LIST_HEAD(&bfqd->idle_list);
+ INIT_HLIST_HEAD(&bfqd->burst_list);
bfqd->hw_tag = -1;
bfqd->bfq_requests_within_timer = 120;
+ bfqd->bfq_large_burst_thresh = 8;
+ bfqd->bfq_burst_interval = msecs_to_jiffies(180);
+
bfqd->low_latency = true;
/*
.elevator_owner = THIS_MODULE,
};
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
-static struct blkcg_policy blkcg_policy_bfq = {
- .dfl_cftypes = bfq_blkg_files,
- .legacy_cftypes = bfq_blkcg_legacy_files,
-
- .cpd_alloc_fn = bfq_cpd_alloc,
- .cpd_init_fn = bfq_cpd_init,
- .cpd_bind_fn = bfq_cpd_init,
- .cpd_free_fn = bfq_cpd_free,
-
- .pd_alloc_fn = bfq_pd_alloc,
- .pd_init_fn = bfq_pd_init,
- .pd_offline_fn = bfq_pd_offline,
- .pd_free_fn = bfq_pd_free,
- .pd_reset_stats_fn = bfq_pd_reset_stats,
-};
-#endif
-
static int __init bfq_init(void)
{
int ret;