linux/block/bfq-iosched.h

942 lines
31 KiB
C
Raw Normal View History

/*
* Header file for the BFQ I/O scheduler: data structures and
* prototypes of interface functions among BFQ components.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation; either version 2 of the
* License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#ifndef _BFQ_H
#define _BFQ_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_weight_counter - counter of the number of all active entities
* with a given weight.
*/
struct bfq_weight_counter {
unsigned int weight; /* weight of the entities this counter refers to */
unsigned int num_active; /* nr of active entities with this weight */
/*
* Weights tree member (see bfq_data's @queue_weights_tree and
* @group_weights_tree)
*/
struct rb_node weights_node;
};
/**
* 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;
/* pointer to the weight counter associated with this entity */
struct bfq_weight_counter *weight_counter;
/*
* 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;
/* node for the device's burst list */
struct hlist_node burst_list_node;
/* 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;
/*
* Same purpose as the previous fields for the value of the
* field keeping the queue's belonging to a large burst
*/
bool saved_in_large_burst;
/*
* True if the queue belonged to a burst list before its merge
* with another cooperating queue.
*/
bool was_in_burst_list;
/*
* 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;
/*
* rbtree of weight counters of @bfq_queues, sorted by
* weight. Used to keep track of whether all @bfq_queues have
* the same weight. The tree contains one counter for each
* distinct weight associated to some active and not
* weight-raised @bfq_queue (see the comments to the functions
* bfq_weights_tree_[add|remove] for further details).
*/
struct rb_root queue_weights_tree;
/*
* rbtree of non-queue @bfq_entity weight counters, sorted by
* weight. Used to keep track of whether all @bfq_groups have
* the same weight. The tree contains one counter for each
* distinct weight associated to some active @bfq_group (see
* the comments to the functions bfq_weights_tree_[add|remove]
* for further details).
*/
struct rb_root group_weights_tree;
/*
* 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;
/* 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;
/*
* Last time at which a queue entered the current burst of
* queues being activated shortly after each other; for more
* details about this and the following parameters related to
* a burst of activations, see the comments on the function
* bfq_handle_burst.
*/
unsigned long last_ins_in_burst;
/*
* Reference time interval used to decide whether a queue has
* been activated shortly after @last_ins_in_burst.
*/
unsigned long bfq_burst_interval;
/* number of queues in the current burst of queue activations */
int burst_size;
/* common parent entity for the queues in the burst */
struct bfq_entity *burst_parent_entity;
/* Maximum burst size above which the current queue-activation
* burst is deemed as 'large'.
*/
unsigned long bfq_large_burst_thresh;
/* true if a large queue-activation burst is in progress */
bool large_burst;
/*
* Head of the burst list (as for the above fields, more
* details in the comments on the function bfq_handle_burst).
*/
struct hlist_head burst_list;
/* 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;
};
enum bfqq_state_flags {
BFQQF_just_created = 0, /* queue just allocated */
BFQQF_busy, /* 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_in_large_burst, /*
* bfqq activated in a large burst,
* see comments to bfq_handle_burst.
*/
BFQQF_softrt_update, /*
* may need softrt-next-start
* update
*/
BFQQF_coop, /* bfqq is shared */
BFQQF_split_coop /* shared bfqq will be split */
};
#define BFQ_BFQQ_FNS(name) \
void bfq_mark_bfqq_##name(struct bfq_queue *bfqq); \
void bfq_clear_bfqq_##name(struct bfq_queue *bfqq); \
int bfq_bfqq_##name(const struct bfq_queue *bfqq);
BFQ_BFQQ_FNS(just_created);
BFQ_BFQQ_FNS(busy);
BFQ_BFQQ_FNS(wait_request);
BFQ_BFQQ_FNS(non_blocking_wait_rq);
BFQ_BFQQ_FNS(fifo_expire);
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
/* 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.
* @active_entities: number of active entities belonging to the group;
* unused for the root group. Used to know whether there
* are groups with more than one active @bfq_entity
* (see the comments to the function
* bfq_bfqq_may_idle()).
* @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;
block, bfq: access and cache blkg data only when safe In blk-cgroup, operations on blkg objects are protected with the request_queue lock. This is no more the lock that protects I/O-scheduler operations in blk-mq. In fact, the latter are now protected with a finer-grained per-scheduler-instance lock. As a consequence, although blkg lookups are also rcu-protected, blk-mq I/O schedulers may see inconsistent data when they access blkg and blkg-related objects. BFQ does access these objects, and does incur this problem, in the following case. The blkg_lookup performed in bfq_get_queue, being protected (only) through rcu, may happen to return the address of a copy of the original blkg. If this is the case, then the blkg_get performed in bfq_get_queue, to pin down the blkg, is useless: it does not prevent blk-cgroup code from destroying both the original blkg and all objects directly or indirectly referred by the copy of the blkg. BFQ accesses these objects, which typically causes a crash for NULL-pointer dereference of memory-protection violation. Some additional protection mechanism should be added to blk-cgroup to address this issue. In the meantime, this commit provides a quick temporary fix for BFQ: cache (when safe) blkg data that might disappear right after a blkg_lookup. In particular, this commit exploits the following facts to achieve its goal without introducing further locks. Destroy operations on a blkg invoke, as a first step, hooks of the scheduler associated with the blkg. And these hooks are executed with bfqd->lock held for BFQ. As a consequence, for any blkg associated with the request queue an instance of BFQ is attached to, we are guaranteed that such a blkg is not destroyed, and that all the pointers it contains are consistent, while that instance is holding its bfqd->lock. A blkg_lookup performed with bfqd->lock held then returns a fully consistent blkg, which remains consistent until this lock is held. In more detail, this holds even if the returned blkg is a copy of the original one. Finally, also the object describing a group inside BFQ needs to be protected from destruction on the blkg_free of the original blkg (which invokes bfq_pd_free). This commit adds private refcounting for this object, to let it disappear only after no bfq_queue refers to it any longer. This commit also removes or updates some stale comments on locking issues related to blk-cgroup operations. Reported-by: Tomas Konir <tomas.konir@gmail.com> Reported-by: Lee Tibbert <lee.tibbert@gmail.com> Reported-by: Marco Piazza <mpiazza@gmail.com> Signed-off-by: Paolo Valente <paolo.valente@linaro.org> Tested-by: Tomas Konir <tomas.konir@gmail.com> Tested-by: Lee Tibbert <lee.tibbert@gmail.com> Tested-by: Marco Piazza <mpiazza@gmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-06-05 08:11:15 +00:00
/* cached path for this blkg (see comments in bfq_bic_update_cgroup) */
char blkg_path[128];
/* reference counter (see comments in bfq_bic_update_cgroup) */
int ref;
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;
int active_entities;
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
struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
/* --------------- main algorithm interface ----------------- */
#define BFQ_SERVICE_TREE_INIT ((struct bfq_service_tree) \
{ RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 })
extern const int bfq_timeout;
struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync);
void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync);
struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic);
void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq);
void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
struct rb_root *root);
void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
struct rb_root *root);
void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bool compensate, enum bfqq_expiration reason);
void bfq_put_queue(struct bfq_queue *bfqq);
void bfq_end_wr_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
void bfq_schedule_dispatch(struct bfq_data *bfqd);
void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
/* ------------ end of main algorithm interface -------------- */
/* ---------------- cgroups-support interface ---------------- */
void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
unsigned int op);
void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op);
void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op);
void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
uint64_t io_start_time, unsigned int op);
void bfqg_stats_update_dequeue(struct bfq_group *bfqg);
void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
void bfqg_stats_update_idle_time(struct bfq_group *bfqg);
void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg);
void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg);
void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
struct bfq_group *bfqg);
void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg);
void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio);
void bfq_end_wr_async(struct bfq_data *bfqd);
struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
struct blkcg *blkcg);
struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
block, bfq: access and cache blkg data only when safe In blk-cgroup, operations on blkg objects are protected with the request_queue lock. This is no more the lock that protects I/O-scheduler operations in blk-mq. In fact, the latter are now protected with a finer-grained per-scheduler-instance lock. As a consequence, although blkg lookups are also rcu-protected, blk-mq I/O schedulers may see inconsistent data when they access blkg and blkg-related objects. BFQ does access these objects, and does incur this problem, in the following case. The blkg_lookup performed in bfq_get_queue, being protected (only) through rcu, may happen to return the address of a copy of the original blkg. If this is the case, then the blkg_get performed in bfq_get_queue, to pin down the blkg, is useless: it does not prevent blk-cgroup code from destroying both the original blkg and all objects directly or indirectly referred by the copy of the blkg. BFQ accesses these objects, which typically causes a crash for NULL-pointer dereference of memory-protection violation. Some additional protection mechanism should be added to blk-cgroup to address this issue. In the meantime, this commit provides a quick temporary fix for BFQ: cache (when safe) blkg data that might disappear right after a blkg_lookup. In particular, this commit exploits the following facts to achieve its goal without introducing further locks. Destroy operations on a blkg invoke, as a first step, hooks of the scheduler associated with the blkg. And these hooks are executed with bfqd->lock held for BFQ. As a consequence, for any blkg associated with the request queue an instance of BFQ is attached to, we are guaranteed that such a blkg is not destroyed, and that all the pointers it contains are consistent, while that instance is holding its bfqd->lock. A blkg_lookup performed with bfqd->lock held then returns a fully consistent blkg, which remains consistent until this lock is held. In more detail, this holds even if the returned blkg is a copy of the original one. Finally, also the object describing a group inside BFQ needs to be protected from destruction on the blkg_free of the original blkg (which invokes bfq_pd_free). This commit adds private refcounting for this object, to let it disappear only after no bfq_queue refers to it any longer. This commit also removes or updates some stale comments on locking issues related to blk-cgroup operations. Reported-by: Tomas Konir <tomas.konir@gmail.com> Reported-by: Lee Tibbert <lee.tibbert@gmail.com> Reported-by: Marco Piazza <mpiazza@gmail.com> Signed-off-by: Paolo Valente <paolo.valente@linaro.org> Tested-by: Tomas Konir <tomas.konir@gmail.com> Tested-by: Lee Tibbert <lee.tibbert@gmail.com> Tested-by: Marco Piazza <mpiazza@gmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-06-05 08:11:15 +00:00
void bfqg_and_blkg_put(struct bfq_group *bfqg);
#ifdef CONFIG_BFQ_GROUP_IOSCHED
extern struct cftype bfq_blkcg_legacy_files[];
extern struct cftype bfq_blkg_files[];
extern struct blkcg_policy blkcg_policy_bfq;
#endif
/* ------------- end of cgroups-support interface ------------- */
/* - interface of the internal hierarchical B-WF2Q+ scheduler - */
#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)
#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)
#endif /* CONFIG_BFQ_GROUP_IOSCHED */
struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq);
struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
struct bfq_service_tree *bfq_entity_service_tree(struct bfq_entity *entity);
struct bfq_entity *bfq_entity_of(struct rb_node *node);
unsigned short bfq_ioprio_to_weight(int ioprio);
void bfq_put_idle_entity(struct bfq_service_tree *st,
struct bfq_entity *entity);
struct bfq_service_tree *
__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
block, bfq: don't change ioprio class for a bfq_queue on a service tree On each deactivation or re-scheduling (after being served) of a bfq_queue, BFQ invokes the function __bfq_entity_update_weight_prio(), to perform pending updates of ioprio, weight and ioprio class for the bfq_queue. BFQ also invokes this function on I/O-request dispatches, to raise or lower weights more quickly when needed, thereby improving latency. However, the entity representing the bfq_queue may be on the active (sub)tree of a service tree when this happens, and, although with a very low probability, the bfq_queue may happen to also have a pending change of its ioprio class. If both conditions hold when __bfq_entity_update_weight_prio() is invoked, then the entity moves to a sort of hybrid state: the new service tree for the entity, as returned by bfq_entity_service_tree(), differs from service tree on which the entity still is. The functions that handle activations and deactivations of entities do not cope with such a hybrid state (and would need to become more complex to cope). This commit addresses this issue by just making __bfq_entity_update_weight_prio() not perform also a possible pending change of ioprio class, when invoked on an I/O-request dispatch for a bfq_queue. Such a change is thus postponed to when __bfq_entity_update_weight_prio() is invoked on deactivation or re-scheduling of the bfq_queue. Reported-by: Marco Piazza <mpiazza@gmail.com> Reported-by: Laurentiu Nicola <lnicola@dend.ro> Signed-off-by: Paolo Valente <paolo.valente@linaro.org> Tested-by: Marco Piazza <mpiazza@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-07-03 08:00:10 +00:00
struct bfq_entity *entity,
bool update_class_too);
void bfq_bfqq_served(struct bfq_queue *bfqq, int served);
void bfq_bfqq_charge_time(struct bfq_data *bfqd, struct bfq_queue *bfqq,
unsigned long time_ms);
bool __bfq_deactivate_entity(struct bfq_entity *entity,
bool ins_into_idle_tree);
bool next_queue_may_preempt(struct bfq_data *bfqd);
struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd);
void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bool ins_into_idle_tree, bool expiration);
void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bool expiration);
void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq);
/* --------------- end of interface of B-WF2Q+ ---------------- */
/* Logging facilities. */
#ifdef CONFIG_BFQ_GROUP_IOSCHED
struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \
block, bfq: access and cache blkg data only when safe In blk-cgroup, operations on blkg objects are protected with the request_queue lock. This is no more the lock that protects I/O-scheduler operations in blk-mq. In fact, the latter are now protected with a finer-grained per-scheduler-instance lock. As a consequence, although blkg lookups are also rcu-protected, blk-mq I/O schedulers may see inconsistent data when they access blkg and blkg-related objects. BFQ does access these objects, and does incur this problem, in the following case. The blkg_lookup performed in bfq_get_queue, being protected (only) through rcu, may happen to return the address of a copy of the original blkg. If this is the case, then the blkg_get performed in bfq_get_queue, to pin down the blkg, is useless: it does not prevent blk-cgroup code from destroying both the original blkg and all objects directly or indirectly referred by the copy of the blkg. BFQ accesses these objects, which typically causes a crash for NULL-pointer dereference of memory-protection violation. Some additional protection mechanism should be added to blk-cgroup to address this issue. In the meantime, this commit provides a quick temporary fix for BFQ: cache (when safe) blkg data that might disappear right after a blkg_lookup. In particular, this commit exploits the following facts to achieve its goal without introducing further locks. Destroy operations on a blkg invoke, as a first step, hooks of the scheduler associated with the blkg. And these hooks are executed with bfqd->lock held for BFQ. As a consequence, for any blkg associated with the request queue an instance of BFQ is attached to, we are guaranteed that such a blkg is not destroyed, and that all the pointers it contains are consistent, while that instance is holding its bfqd->lock. A blkg_lookup performed with bfqd->lock held then returns a fully consistent blkg, which remains consistent until this lock is held. In more detail, this holds even if the returned blkg is a copy of the original one. Finally, also the object describing a group inside BFQ needs to be protected from destruction on the blkg_free of the original blkg (which invokes bfq_pd_free). This commit adds private refcounting for this object, to let it disappear only after no bfq_queue refers to it any longer. This commit also removes or updates some stale comments on locking issues related to blk-cgroup operations. Reported-by: Tomas Konir <tomas.konir@gmail.com> Reported-by: Lee Tibbert <lee.tibbert@gmail.com> Reported-by: Marco Piazza <mpiazza@gmail.com> Signed-off-by: Paolo Valente <paolo.valente@linaro.org> Tested-by: Tomas Konir <tomas.konir@gmail.com> Tested-by: Lee Tibbert <lee.tibbert@gmail.com> Tested-by: Marco Piazza <mpiazza@gmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-06-05 08:11:15 +00:00
blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid,\
bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \
block, bfq: access and cache blkg data only when safe In blk-cgroup, operations on blkg objects are protected with the request_queue lock. This is no more the lock that protects I/O-scheduler operations in blk-mq. In fact, the latter are now protected with a finer-grained per-scheduler-instance lock. As a consequence, although blkg lookups are also rcu-protected, blk-mq I/O schedulers may see inconsistent data when they access blkg and blkg-related objects. BFQ does access these objects, and does incur this problem, in the following case. The blkg_lookup performed in bfq_get_queue, being protected (only) through rcu, may happen to return the address of a copy of the original blkg. If this is the case, then the blkg_get performed in bfq_get_queue, to pin down the blkg, is useless: it does not prevent blk-cgroup code from destroying both the original blkg and all objects directly or indirectly referred by the copy of the blkg. BFQ accesses these objects, which typically causes a crash for NULL-pointer dereference of memory-protection violation. Some additional protection mechanism should be added to blk-cgroup to address this issue. In the meantime, this commit provides a quick temporary fix for BFQ: cache (when safe) blkg data that might disappear right after a blkg_lookup. In particular, this commit exploits the following facts to achieve its goal without introducing further locks. Destroy operations on a blkg invoke, as a first step, hooks of the scheduler associated with the blkg. And these hooks are executed with bfqd->lock held for BFQ. As a consequence, for any blkg associated with the request queue an instance of BFQ is attached to, we are guaranteed that such a blkg is not destroyed, and that all the pointers it contains are consistent, while that instance is holding its bfqd->lock. A blkg_lookup performed with bfqd->lock held then returns a fully consistent blkg, which remains consistent until this lock is held. In more detail, this holds even if the returned blkg is a copy of the original one. Finally, also the object describing a group inside BFQ needs to be protected from destruction on the blkg_free of the original blkg (which invokes bfq_pd_free). This commit adds private refcounting for this object, to let it disappear only after no bfq_queue refers to it any longer. This commit also removes or updates some stale comments on locking issues related to blk-cgroup operations. Reported-by: Tomas Konir <tomas.konir@gmail.com> Reported-by: Lee Tibbert <lee.tibbert@gmail.com> Reported-by: Marco Piazza <mpiazza@gmail.com> Signed-off-by: Paolo Valente <paolo.valente@linaro.org> Tested-by: Tomas Konir <tomas.konir@gmail.com> Tested-by: Lee Tibbert <lee.tibbert@gmail.com> Tested-by: Marco Piazza <mpiazza@gmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-06-05 08:11:15 +00:00
bfqq_group(bfqq)->blkg_path, ##args); \
} while (0)
block, bfq: access and cache blkg data only when safe In blk-cgroup, operations on blkg objects are protected with the request_queue lock. This is no more the lock that protects I/O-scheduler operations in blk-mq. In fact, the latter are now protected with a finer-grained per-scheduler-instance lock. As a consequence, although blkg lookups are also rcu-protected, blk-mq I/O schedulers may see inconsistent data when they access blkg and blkg-related objects. BFQ does access these objects, and does incur this problem, in the following case. The blkg_lookup performed in bfq_get_queue, being protected (only) through rcu, may happen to return the address of a copy of the original blkg. If this is the case, then the blkg_get performed in bfq_get_queue, to pin down the blkg, is useless: it does not prevent blk-cgroup code from destroying both the original blkg and all objects directly or indirectly referred by the copy of the blkg. BFQ accesses these objects, which typically causes a crash for NULL-pointer dereference of memory-protection violation. Some additional protection mechanism should be added to blk-cgroup to address this issue. In the meantime, this commit provides a quick temporary fix for BFQ: cache (when safe) blkg data that might disappear right after a blkg_lookup. In particular, this commit exploits the following facts to achieve its goal without introducing further locks. Destroy operations on a blkg invoke, as a first step, hooks of the scheduler associated with the blkg. And these hooks are executed with bfqd->lock held for BFQ. As a consequence, for any blkg associated with the request queue an instance of BFQ is attached to, we are guaranteed that such a blkg is not destroyed, and that all the pointers it contains are consistent, while that instance is holding its bfqd->lock. A blkg_lookup performed with bfqd->lock held then returns a fully consistent blkg, which remains consistent until this lock is held. In more detail, this holds even if the returned blkg is a copy of the original one. Finally, also the object describing a group inside BFQ needs to be protected from destruction on the blkg_free of the original blkg (which invokes bfq_pd_free). This commit adds private refcounting for this object, to let it disappear only after no bfq_queue refers to it any longer. This commit also removes or updates some stale comments on locking issues related to blk-cgroup operations. Reported-by: Tomas Konir <tomas.konir@gmail.com> Reported-by: Lee Tibbert <lee.tibbert@gmail.com> Reported-by: Marco Piazza <mpiazza@gmail.com> Signed-off-by: Paolo Valente <paolo.valente@linaro.org> Tested-by: Tomas Konir <tomas.konir@gmail.com> Tested-by: Lee Tibbert <lee.tibbert@gmail.com> Tested-by: Marco Piazza <mpiazza@gmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-06-05 08:11:15 +00:00
#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) \
blk_add_trace_msg((bfqd)->queue, "%s " fmt, (bfqg)->blkg_path, ##args)
#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)
#endif /* _BFQ_H */