diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt index 8d8d8f06cab2..41d0200944f1 100644 --- a/Documentation/block/bfq-iosched.txt +++ b/Documentation/block/bfq-iosched.txt @@ -1,3 +1,6 @@ +[ THIS TREE CONTAINS ALSO THE DEV VERSION OF BFQ. + DETAILS AT THE END OF THIS DOCUMENT. ] + BFQ (Budget Fair Queueing) ========================== @@ -11,6 +14,15 @@ controllers), BFQ's main features are: groups (switching back to time distribution when needed to keep throughput high). +If bfq-mq patches have been applied, then the following three +instances of BFQ are available (otherwise only the first instance): +- bfq: mainline version of BFQ, for blk-mq +- bfq-mq: development version of BFQ for blk-mq; this version contains + also all latest features and fixes not yet landed in mainline, plus many + safety checks +- bfq-sq: BFQ for legacy blk; also this version contains latest features + and fixes, as well as safety checks + In its default configuration, BFQ privileges latency over throughput. So, when needed for achieving a lower latency, BFQ builds schedules that may lead to a lower throughput. If your main or only @@ -22,27 +34,42 @@ latency and throughput, or on how to maximize throughput. BFQ has a non-null overhead, which limits the maximum IOPS that a CPU can process for a device scheduled with BFQ. To give an idea of the -limits on slow or average CPUs, here are, first, the limits of BFQ for -three different CPUs, on, respectively, an average laptop, an old -desktop, and a cheap embedded system, in case full hierarchical -support is enabled (i.e., CONFIG_BFQ_GROUP_IOSCHED is set), but +limits on slow or average CPUs, here are, first, the limits of bfq-mq +and bfq for three different CPUs, on, respectively, an average laptop, +an old desktop, and a cheap embedded system, in case full hierarchical +support is enabled (i.e., CONFIG_MQ_BFQ_GROUP_IOSCHED is set for +bfq-mq, or CONFIG_BFQ_GROUP_IOSCHED is set for bfq), but CONFIG_DEBUG_BLK_CGROUP is not set (Section 4-2): - Intel i7-4850HQ: 400 KIOPS - AMD A8-3850: 250 KIOPS - ARM CortexTM-A53 Octa-core: 80 KIOPS -If CONFIG_DEBUG_BLK_CGROUP is set (and of course full hierarchical -support is enabled), then the sustainable throughput with BFQ -decreases, because all blkio.bfq* statistics are created and updated -(Section 4-2). For BFQ, this leads to the following maximum -sustainable throughputs, on the same systems as above: +As for bfq-sq, it cannot reach the above IOPS, because of the +inherent, lower parallelism of legacy blk and of the components within +it (including bfq-sq itself). In particular, results with +CONFIG_DEBUG_BLK_CGROUP unset are rather fluctuating. The limits +reported below for the case CONFIG_DEBUG_BLK_CGROUP set will however +provide a lower bound to the limits of bfq-sq. + +Turning back to bfq-mq and bfq, If CONFIG_DEBUG_BLK_CGROUP is set (and +of course full hierarchical support is enabled), then the sustainable +throughput with bfq-mq and bfq decreases, because all blkio.bfq* +statistics are created and updated (Section 4-2). For bfq-mq and bfq, +this leads to the following maximum sustainable throughputs, on the +same systems as above: - Intel i7-4850HQ: 310 KIOPS - AMD A8-3850: 200 KIOPS - ARM CortexTM-A53 Octa-core: 56 KIOPS -BFQ works for multi-queue devices too. +Finally, if CONFIG_DEBUG_BLK_CGROUP is set (and full hierarchical +support is enabled), then bfq-sq exhibits the following limits: +- Intel i7-4850HQ: 250 KIOPS +- AMD A8-3850: 170 KIOPS +- ARM CortexTM-A53 Octa-core: 45 KIOPS -The table of contents follow. Impatients can just jump to Section 3. +BFQ works for multi-queue devices too (bfq and bfq-mq instances). + +The table of contents follows. Impatients can just jump to Section 3. CONTENTS @@ -509,25 +536,27 @@ To get proportional sharing of bandwidth with BFQ for a given device, BFQ must of course be the active scheduler for that device. Within each group directory, the names of the files associated with -BFQ-specific cgroup parameters and stats begin with the "bfq." -prefix. So, with cgroups-v1 or cgroups-v2, the full prefix for -BFQ-specific files is "blkio.bfq." or "io.bfq." For example, the group -parameter to set the weight of a group with BFQ is blkio.bfq.weight +BFQ-specific cgroup parameters and stats begin with the "bfq.", +"bfq-sq." or "bfq-mq." prefix, depending on which instance of bfq you +want to use. So, with cgroups-v1 or cgroups-v2, the full prefix for +BFQ-specific files is "blkio.bfqX." or "io.bfqX.", where X can be "" +(i.e., null string), "-sq" or "-mq". For example, the group parameter +to set the weight of a group with the mainline BFQ is blkio.bfq.weight or io.bfq.weight. As for cgroups-v1 (blkio controller), the exact set of stat files -created, and kept up-to-date by bfq, depends on whether -CONFIG_DEBUG_BLK_CGROUP is set. If it is set, then bfq creates all +created, and kept up-to-date by bfq*, depends on whether +CONFIG_DEBUG_BLK_CGROUP is set. If it is set, then bfq* creates all the stat files documented in Documentation/cgroup-v1/blkio-controller.txt. If, instead, -CONFIG_DEBUG_BLK_CGROUP is not set, then bfq creates only the files -blkio.bfq.io_service_bytes -blkio.bfq.io_service_bytes_recursive -blkio.bfq.io_serviced -blkio.bfq.io_serviced_recursive +CONFIG_DEBUG_BLK_CGROUP is not set, then bfq* creates only the files +blkio.bfq*.io_service_bytes +blkio.bfq*.io_service_bytes_recursive +blkio.bfq*.io_serviced +blkio.bfq*.io_serviced_recursive The value of CONFIG_DEBUG_BLK_CGROUP greatly influences the maximum -throughput sustainable with bfq, because updating the blkio.bfq.* +throughput sustainable with bfq*, because updating the blkio.bfq* stats is rather costly, especially for some of the stats enabled by CONFIG_DEBUG_BLK_CGROUP. @@ -536,7 +565,7 @@ Parameters to set For each group, there is only the following parameter to set. -weight (namely blkio.bfq.weight or io.bfq-weight): the weight of the +weight (namely blkio.bfqX.weight or io.bfqX.weight): the weight of the group inside its parent. Available values: 1..10000 (default 100). The linear mapping between ioprio and weights, described at the beginning of the tunable section, is still valid, but all weights higher than @@ -559,3 +588,55 @@ applications. Unset this tunable if you need/want to control weights. Slightly extended version: http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite- results.pdf + +---------------------------------------------------------------------- + +DETAILS ON THE DEV VERSIONS IN THIS TREE + +The dev version of BFQ is available for both the legacy and the +multi-queue block layers, as two additional I/O schedulers, named, +respectively, bfq-sq-iosched and bfq-mq-iosched (the latter is +available if also the changes introducing bfq-mq-iosched have been +applied). In particular, this tree contains the dev version of bfq for +Linux mainline 4.19.0, and has been obtained from the dev version for +Linux 4.18.0. Rebasing from 4.18 to 4.19 involved two manual +interventions. + +First, some conflicts had to be resolved, as follows: + +--------------------------------------------------------------- + +diff --cc Makefile +index 7727c1bf6fa5,69fa5c0310d8..c7cbdf0ad594 +--- a/Makefile ++++ b/Makefile +@@@ -1,9 -1,9 +1,9 @@@ + # SPDX-License-Identifier: GPL-2.0 + VERSION = 4 +- PATCHLEVEL = 18 ++ PATCHLEVEL = 19 + SUBLEVEL = 0 + -EXTRAVERSION = + +EXTRAVERSION = -bfq-mq +- NAME = Merciless Moray ++ NAME = "People's Front" + + # *DOCUMENTATION* + # To see a list of typical targets execute "make help" +diff --cc include/linux/blkdev.h +index 897c63322bd7,6980014357d4..8c4568ea6884 +--- a/include/linux/blkdev.h ++++ b/include/linux/blkdev.h +@@@ -56,7 -54,7 +54,7 @@@ struct blk_stat_callback + * Maximum number of blkcg policies allowed to be registered concurrently. + * Defined here to simplify include dependency. + */ +--#define BLKCG_MAX_POLS 5 +++#define BLKCG_MAX_POLS 7 + + typedef void (rq_end_io_fn)(struct request *, blk_status_t); + +--------------------------------------------------------------- + +Second, the following port commit had to be made: +port commit "block: use ktime_get_ns() instead of sched_clock() for cfq and bfq" diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index e32fc1f274d8..94cb28eb20ba 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -12,6 +12,11 @@ CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_CGROUPS=y +CONFIG_BLK_CGROUP=y +CONFIG_IOSCHED_BFQ_SQ=y +CONFIG_BFQ_SQ_GROUP_IOSCHED=y +CONFIG_MQ_IOSCHED_BFQ=y +CONFIG_MQ_BFQ_GROUP_IOSCHED=y CONFIG_CGROUP_FREEZER=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index a4a8914bf7a4..299a6861fb90 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -40,6 +40,26 @@ config CFQ_GROUP_IOSCHED ---help--- Enable group IO scheduling in CFQ. +config IOSCHED_BFQ_SQ + tristate "BFQ-SQ I/O scheduler" + default n + ---help--- + The BFQ-SQ I/O scheduler (for legacy blk: SQ stands for + SingleQueue) distributes bandwidth among all processes + according to their weights, regardless of the device + parameters and with any workload. It also guarantees a low + latency to interactive and soft real-time applications. + Details in Documentation/block/bfq-iosched.txt + +config BFQ_SQ_GROUP_IOSCHED + bool "BFQ-SQ hierarchical scheduling support" + depends on IOSCHED_BFQ_SQ && BLK_CGROUP + default n + ---help--- + + Enable hierarchical scheduling in BFQ-SQ, using the blkio + (cgroups-v1) or io (cgroups-v2) controller. + choice prompt "Default I/O scheduler" @@ -54,6 +74,16 @@ choice config DEFAULT_CFQ bool "CFQ" if IOSCHED_CFQ=y + config DEFAULT_BFQ_SQ + bool "BFQ-SQ" if IOSCHED_BFQ_SQ=y + help + Selects BFQ-SQ as the default I/O scheduler which will be + used by default for all block devices. + The BFQ-SQ I/O scheduler aims at distributing the bandwidth + as desired, independently of the disk parameters and with + any workload. It also tries to guarantee low latency to + interactive and soft real-time applications. + config DEFAULT_NOOP bool "No-op" @@ -63,8 +93,28 @@ config DEFAULT_IOSCHED string default "deadline" if DEFAULT_DEADLINE default "cfq" if DEFAULT_CFQ + default "bfq-sq" if DEFAULT_BFQ_SQ default "noop" if DEFAULT_NOOP +config MQ_IOSCHED_BFQ + tristate "BFQ-MQ I/O Scheduler" + default y + ---help--- + BFQ I/O scheduler for BLK-MQ. BFQ-MQ distributes bandwidth + among all processes according to their weights, regardless of + the device parameters and with any workload. It also + guarantees a low latency to interactive and soft real-time + applications. Details in Documentation/block/bfq-iosched.txt + +config MQ_BFQ_GROUP_IOSCHED + bool "BFQ-MQ hierarchical scheduling support" + depends on MQ_IOSCHED_BFQ && BLK_CGROUP + default n + ---help--- + + Enable hierarchical scheduling in BFQ-MQ, using the blkio + (cgroups-v1) or io (cgroups-v2) controller. + config MQ_IOSCHED_DEADLINE tristate "MQ deadline I/O scheduler" default y diff --git a/block/Makefile b/block/Makefile index 572b33f32c07..1dd6ffdc2fee 100644 --- a/block/Makefile +++ b/block/Makefile @@ -25,6 +25,8 @@ obj-$(CONFIG_MQ_IOSCHED_DEADLINE) += mq-deadline.o obj-$(CONFIG_MQ_IOSCHED_KYBER) += kyber-iosched.o bfq-y := bfq-iosched.o bfq-wf2q.o bfq-cgroup.o obj-$(CONFIG_IOSCHED_BFQ) += bfq.o +obj-$(CONFIG_IOSCHED_BFQ_SQ) += bfq-sq-iosched.o +obj-$(CONFIG_MQ_IOSCHED_BFQ) += bfq-mq-iosched.o obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o diff --git a/block/bfq-cgroup-included.c b/block/bfq-cgroup-included.c new file mode 100644 index 000000000000..15459e50cd6a --- /dev/null +++ b/block/bfq-cgroup-included.c @@ -0,0 +1,1359 @@ +/* + * BFQ: CGROUPS support. + * + * Based on ideas and code from CFQ: + * Copyright (C) 2003 Jens Axboe + * + * Copyright (C) 2008 Fabio Checconi + * Paolo Valente + * + * Copyright (C) 2015 Paolo Valente + * + * Copyright (C) 2016 Paolo Valente + * + * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ + * file. + */ + +#if defined(BFQ_GROUP_IOSCHED_ENABLED) && defined(CONFIG_DEBUG_BLK_CGROUP) + +/* 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 + +#ifdef BFQ_MQ +/* This should be called with the scheduler lock held. */ +#else +/* This should be called with the queue_lock held. */ +#endif +static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats) +{ + u64 now; + + if (!bfqg_stats_waiting(stats)) + return; + + now = ktime_get_ns(); + if (now > stats->start_group_wait_time) + blkg_stat_add(&stats->group_wait_time, + now - stats->start_group_wait_time); + bfqg_stats_clear_waiting(stats); +} + +#ifdef BFQ_MQ +/* This should be called with the scheduler lock held. */ +#else +/* This should be called with the queue_lock held. */ +#endif +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 = ktime_get_ns(); + bfqg_stats_mark_waiting(stats); +} + +#ifdef BFQ_MQ +/* This should be called with the scheduler lock held. */ +#else +/* This should be called with the queue_lock held. */ +#endif +static void bfqg_stats_end_empty_time(struct bfqg_stats *stats) +{ + u64 now; + + if (!bfqg_stats_empty(stats)) + return; + + now = ktime_get_ns(); + if (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 = ktime_get_ns(); + 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)) { + u64 now = ktime_get_ns(); + + if (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 = ktime_get_ns(); + 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); +} + +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, + u64 start_time_ns, + u64 io_start_time_ns, + unsigned int op) +{ + struct bfqg_stats *stats = &bfqg->stats; + u64 now = ktime_get_ns(); + + if (now > io_start_time_ns) + blkg_rwstat_add(&stats->service_time, op, + now - io_start_time_ns); + if (io_start_time_ns > start_time_ns) + blkg_rwstat_add(&stats->wait_time, op, + io_start_time_ns - start_time_ns); +} + +#else /* BFQ_GROUP_IOSCHED_ENABLED && CONFIG_DEBUG_BLK_CGROUP */ + +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, + u64 start_time_ns, + u64 io_start_time_ns, + 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) { } + +#endif /* BFQ_GROUP_IOSCHED_ENABLED && CONFIG_DEBUG_BLK_CGROUP */ + +#ifdef BFQ_GROUP_IOSCHED_ENABLED +static struct blkcg_policy blkcg_policy_bfq; + +/* + * 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 bfq_group *blkg_to_bfqg(struct blkcg_gq *blkg) +{ + struct blkg_policy_data *pd = blkg_to_pd(blkg, &blkcg_policy_bfq); + + return pd_to_bfqg(pd); +} + +/* + * 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) +{ +#ifdef BFQ_MQ + bfqg->ref++; +#else + blkg_get(bfqg_to_blkg(bfqg)); +#endif +} + +static void bfqg_put(struct bfq_group *bfqg) +{ +#ifdef BFQ_MQ + bfqg->ref--; + + BUG_ON(bfqg->ref < 0); + if (bfqg->ref == 0) + kfree(bfqg); +#else + blkg_put(bfqg_to_blkg(bfqg)); +#endif +} + +#ifdef BFQ_MQ +static void bfqg_and_blkg_get(struct bfq_group *bfqg) +{ + /* see comments in bfq_bic_update_cgroup for why refcounting bfqg */ + bfqg_get(bfqg); + + blkg_get(bfqg_to_blkg(bfqg)); +} + +static void bfqg_and_blkg_put(struct bfq_group *bfqg) +{ + blkg_put(bfqg_to_blkg(bfqg)); + + bfqg_put(bfqg); +} +#endif + +/* @stats = 0 */ +static void bfqg_stats_reset(struct bfqg_stats *stats) +{ +#ifdef CONFIG_DEBUG_BLK_CGROUP + /* 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); +#endif +} + +/* @to += @from */ +static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from) +{ + if (!to || !from) + return; + +#ifdef CONFIG_DEBUG_BLK_CGROUP + /* 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); +#endif +} + +/* + * Transfer @bfqg's stats to its parent's dead_stats 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; +#ifdef BFQ_MQ + /* + * Make sure that bfqg and its associated blkg do not + * disappear before entity. + */ + bfq_log_bfqq(bfqq->bfqd, bfqq, "getting bfqg %p and blkg\n", + bfqg); + + bfqg_and_blkg_get(bfqg); +#else + bfqg_get(bfqg); +#endif + } + entity->parent = bfqg->my_entity; /* NULL for root group */ + entity->sched_data = &bfqg->sched_data; +} + +static void bfqg_stats_exit(struct bfqg_stats *stats) +{ +#ifdef CONFIG_DEBUG_BLK_CGROUP + 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); +#endif +} + +static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp) +{ +#ifdef CONFIG_DEBUG_BLK_CGROUP + 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; + } +#endif + + 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; + } +#ifdef BFQ_MQ + /* see comments in bfq_bic_update_cgroup for why refcounting */ + bfqg_get(bfqg); +#endif + return &bfqg->pd; +} + +static void bfq_pd_init(struct blkg_policy_data *pd) +{ + struct blkcg_gq *blkg; + struct bfq_group *bfqg; + struct bfq_data *bfqd; + struct bfq_entity *entity; + struct bfq_group_data *d; + + blkg = pd_to_blkg(pd); + BUG_ON(!blkg); + bfqg = blkg_to_bfqg(blkg); + bfqd = blkg->q->elevator->elevator_data; + BUG_ON(bfqg == bfqd->root_group); + entity = &bfqg->entity; + 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->active_entities = 0; + 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); +#ifdef BFQ_MQ + bfqg_put(bfqg); +#else + kfree(bfqg); +#endif +} + +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; + + BUG_ON(!parent); + BUG_ON(!bfqg); + BUG_ON(bfqg == parent); + + 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); + BUG_ON(!bfqg); + if (bfqg != bfqd->root_group) { + parent = bfqg_parent(bfqg); + if (!parent) + parent = bfqd->root_group; + BUG_ON(!parent); + 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. + * +#ifdef BFQ_MQ + * Must be called under the scheduler lock, to make sure that the blkg + * owning @bfqg does not disappear (see comments in + * bfq_bic_update_cgroup on guaranteeing the consistency of blkg + * objects). +#else + * 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()). +#endif + */ +static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, + struct bfq_group *bfqg) +{ + struct bfq_entity *entity = &bfqq->entity; + + BUG_ON(!bfq_bfqq_busy(bfqq) && !RB_EMPTY_ROOT(&bfqq->sort_list)); + BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list) && !entity->on_st); + BUG_ON(bfq_bfqq_busy(bfqq) && RB_EMPTY_ROOT(&bfqq->sort_list) + && entity->on_st && + bfqq != bfqd->in_service_queue); + BUG_ON(!bfq_bfqq_busy(bfqq) && bfqq == bfqd->in_service_queue); + + /* 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, BFQ_BFQQ_PREEMPTED); + + BUG_ON(entity->on_st && !bfq_bfqq_busy(bfqq) + && &bfq_entity_service_tree(entity)->idle != + entity->tree); + + BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_busy(bfqq)); + + if (bfq_bfqq_busy(bfqq)) + bfq_deactivate_bfqq(bfqd, bfqq, false, false); + else if (entity->on_st) { + BUG_ON(&bfq_entity_service_tree(entity)->idle != + entity->tree); + bfq_put_idle_entity(bfq_entity_service_tree(entity), entity); + } +#ifdef BFQ_MQ + bfq_log_bfqq(bfqq->bfqd, bfqq, "putting blkg and bfqg %p\n", bfqg); + + bfqg_and_blkg_put(bfqq_group(bfqq)); +#else + bfqg_put(bfqq_group(bfqq)); +#endif + + entity->parent = bfqg->my_entity; + entity->sched_data = &bfqg->sched_data; +#ifdef BFQ_MQ + bfq_log_bfqq(bfqq->bfqd, bfqq, "getting blkg and bfqg %p\n", bfqg); + + /* pin down bfqg and its associated blkg */ + bfqg_and_blkg_get(bfqg); +#else + bfqg_get(bfqg); +#endif + + BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_busy(bfqq)); + 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); + BUG_ON(entity->on_st && !bfq_bfqq_busy(bfqq) + && &bfq_entity_service_tree(entity)->idle != + entity->tree); +} + +/** + * __bfq_bic_change_cgroup - move @bic to @cgroup. + * @bfqd: the queue descriptor. + * @bic: the bic to move. + * @blkcg: the blk-cgroup to move to. + * +#ifdef BFQ_MQ + * Move bic to blkcg, assuming that bfqd->lock is held; which makes + * sure that the reference to cgroup is valid across the call (see + * comments in bfq_bic_update_cgroup on this issue) +#else + * 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. +#endif + * + * 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, + "%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)); +#ifdef BFQ_MQ + /* + * Update blkg_path for bfq_log_* functions. We cache this + * path, and update it here, for the following + * reasons. Operations on blkg objects in blk-cgroup are + * protected with the request_queue lock, and not with the + * lock that protects the instances of this scheduler + * (bfqd->lock). This exposes BFQ to the following sort of + * race. + * + * The blkg_lookup performed in bfq_get_queue, protected + * through rcu, may happen to return the address of a copy of + * the original blkg. If this is the case, then the + * bfqg_and_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. + * + * On the bright side, 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 this instance of the scheduler is attached + * to, we are guaranteed that such a blkg is not destroyed, and + * that all the pointers it contains are consistent, while we + * are holding bfqd->lock. A blkg_lookup performed with + * bfqd->lock held then returns a fully consistent blkg, which + * remains consistent until this lock is held. + * + * Thanks to the last fact, and to the fact that: (1) bfqg has + * been obtained through a blkg_lookup in the above + * assignment, and (2) bfqd->lock is being held, here we can + * safely use the policy data for the involved blkg (i.e., the + * field bfqg->pd) to get to the blkg associated with bfqg, + * and then we can safely use any field of blkg. After we + * release bfqd->lock, even just getting blkg through this + * bfqg may cause dangling references to be traversed, as + * bfqg->pd may not exist any more. + * + * In view of the above facts, here we cache, in the bfqg, any + * blkg data we may need for this bic, and for its associated + * bfq_queue. As of now, we need to cache only the path of the + * blkg, which is used in the bfq_log_* functions. + * + * Finally, note that bfqg itself needs to be protected from + * destruction on the blkg_free of the original blkg (which + * invokes bfq_pd_free). We use an additional private + * refcounter for bfqg, to let it disappear only after no + * bfq_queue refers to it any longer. + */ + blkg_path(bfqg_to_blkg(bfqg), bfqg->blkg_path, sizeof(bfqg->blkg_path)); +#endif + 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); + + BUG_ON(!bfqq); + 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. + */ +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; + struct bfq_data *bfqd; + struct bfq_entity *entity; +#ifdef BFQ_MQ + unsigned long flags; +#endif + int i; + + BUG_ON(!pd); + bfqg = pd_to_bfqg(pd); + BUG_ON(!bfqg); + bfqd = bfqg->bfqd; + BUG_ON(bfqd && !bfqd->root_group); + + entity = bfqg->my_entity; + +#ifdef BFQ_MQ + spin_lock_irqsave(&bfqd->lock, flags); +#endif + + if (!entity) /* root group */ + goto put_async_queues; + + /* + * Empty all service_trees belonging to this group before + * deactivating the group itself. + */ + for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) { + BUG_ON(!bfqg->sched_data.service_tree); + 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. + */ + 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); + BUG_ON(!RB_EMPTY_ROOT(&st->active)); + BUG_ON(!RB_EMPTY_ROOT(&st->idle)); + } + BUG_ON(bfqg->sched_data.next_in_service); + BUG_ON(bfqg->sched_data.in_service_entity); + + __bfq_deactivate_entity(entity, false); + +put_async_queues: + bfq_put_async_queues(bfqd, bfqg); + +#ifdef BFQ_MQ + spin_unlock_irqrestore(&bfqd->lock, flags); +#endif + /* + * @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); + BUG_ON(!bfqg); + + 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; + + ret = bfq_io_set_weight_legacy(of_css(of), NULL, weight); + return ret ?: nbytes; +} + +#ifdef CONFIG_DEBUG_BLK_CGROUP +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 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); +} + +static int bfqg_print_stat_sectors_recursive(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + bfqg_prfill_sectors_recursive, &blkcg_policy_bfq, 0, + false); + return 0; +} + + +static u64 bfqg_prfill_avg_queue_size(struct seq_file *sf, + struct blkg_policy_data *pd, int off) +{ + 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; +} + +/* print avg_queue_size */ +static int bfqg_print_avg_queue_size(struct seq_file *sf, void *v) +{ + blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), + bfqg_prfill_avg_queue_size, &blkcg_policy_bfq, + 0, false); + return 0; +} +#endif /* CONFIG_DEBUG_BLK_CGROUP */ + +static struct bfq_group * +bfq_create_group_hierarchy(struct bfq_data *bfqd, int node) +{ + int ret; + + ret = blkcg_activate_policy(bfqd->queue, &blkcg_policy_bfq); + if (ret) + return NULL; + + return blkg_to_bfqg(bfqd->queue->root_blkg); +} + +#ifdef BFQ_MQ +#define BFQ_CGROUP_FNAME(param) "bfq-mq."#param +#else +#define BFQ_CGROUP_FNAME(param) "bfq-sq."#param +#endif + +static struct cftype bfq_blkcg_legacy_files[] = { + { + .name = BFQ_CGROUP_FNAME(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_CGROUP_FNAME(io_service_bytes), + .private = (unsigned long)&blkcg_policy_bfq, + .seq_show = blkg_print_stat_bytes, + }, + { + .name = BFQ_CGROUP_FNAME(io_serviced), + .private = (unsigned long)&blkcg_policy_bfq, + .seq_show = blkg_print_stat_ios, + }, +#ifdef CONFIG_DEBUG_BLK_CGROUP + { + .name = BFQ_CGROUP_FNAME(time), + .private = offsetof(struct bfq_group, stats.time), + .seq_show = bfqg_print_stat, + }, + { + .name = BFQ_CGROUP_FNAME(sectors), + .seq_show = bfqg_print_stat_sectors, + }, + { + .name = BFQ_CGROUP_FNAME(io_service_time), + .private = offsetof(struct bfq_group, stats.service_time), + .seq_show = bfqg_print_rwstat, + }, + { + .name = BFQ_CGROUP_FNAME(io_wait_time), + .private = offsetof(struct bfq_group, stats.wait_time), + .seq_show = bfqg_print_rwstat, + }, + { + .name = BFQ_CGROUP_FNAME(io_merged), + .private = offsetof(struct bfq_group, stats.merged), + .seq_show = bfqg_print_rwstat, + }, + { + .name = BFQ_CGROUP_FNAME(io_queued), + .private = offsetof(struct bfq_group, stats.queued), + .seq_show = bfqg_print_rwstat, + }, +#endif /* CONFIG_DEBUG_BLK_CGROUP */ + + /* the same statictics which cover the bfqg and its descendants */ + { + .name = BFQ_CGROUP_FNAME(io_service_bytes_recursive), + .private = (unsigned long)&blkcg_policy_bfq, + .seq_show = blkg_print_stat_bytes_recursive, + }, + { + .name = BFQ_CGROUP_FNAME(io_serviced_recursive), + .private = (unsigned long)&blkcg_policy_bfq, + .seq_show = blkg_print_stat_ios_recursive, + }, +#ifdef CONFIG_DEBUG_BLK_CGROUP + { + .name = BFQ_CGROUP_FNAME(time_recursive), + .private = offsetof(struct bfq_group, stats.time), + .seq_show = bfqg_print_stat_recursive, + }, + { + .name = BFQ_CGROUP_FNAME(sectors_recursive), + .seq_show = bfqg_print_stat_sectors_recursive, + }, + { + .name = BFQ_CGROUP_FNAME(io_service_time_recursive), + .private = offsetof(struct bfq_group, stats.service_time), + .seq_show = bfqg_print_rwstat_recursive, + }, + { + .name = BFQ_CGROUP_FNAME(io_wait_time_recursive), + .private = offsetof(struct bfq_group, stats.wait_time), + .seq_show = bfqg_print_rwstat_recursive, + }, + { + .name = BFQ_CGROUP_FNAME(io_merged_recursive), + .private = offsetof(struct bfq_group, stats.merged), + .seq_show = bfqg_print_rwstat_recursive, + }, + { + .name = BFQ_CGROUP_FNAME(io_queued_recursive), + .private = offsetof(struct bfq_group, stats.queued), + .seq_show = bfqg_print_rwstat_recursive, + }, + { + .name = BFQ_CGROUP_FNAME(avg_queue_size), + .seq_show = bfqg_print_avg_queue_size, + }, + { + .name = BFQ_CGROUP_FNAME(group_wait_time), + .private = offsetof(struct bfq_group, stats.group_wait_time), + .seq_show = bfqg_print_stat, + }, + { + .name = BFQ_CGROUP_FNAME(idle_time), + .private = offsetof(struct bfq_group, stats.idle_time), + .seq_show = bfqg_print_stat, + }, + { + .name = BFQ_CGROUP_FNAME(empty_time), + .private = offsetof(struct bfq_group, stats.empty_time), + .seq_show = bfqg_print_stat, + }, + { + .name = BFQ_CGROUP_FNAME(dequeue), + .private = offsetof(struct bfq_group, stats.dequeue), + .seq_show = bfqg_print_stat, + }, +#endif /* CONFIG_DEBUG_BLK_CGROUP */ + { } /* terminate */ +}; + +static struct cftype bfq_blkg_files[] = { + { + .name = BFQ_CGROUP_FNAME(weight), + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = bfq_io_show_weight, + .write = bfq_io_set_weight, + }, + {} /* terminate */ +}; + +#undef BFQ_CGROUP_FNAME + +#else /* BFQ_GROUP_IOSCHED_ENABLED */ + +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); + + 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; + } + 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; +} + +static struct bfq_group * +bfq_create_group_hierarchy(struct bfq_data *bfqd, int node) +{ + 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; +} +#endif diff --git a/block/bfq-ioc.c b/block/bfq-ioc.c new file mode 100644 index 000000000000..fb7bb8f08b75 --- /dev/null +++ b/block/bfq-ioc.c @@ -0,0 +1,36 @@ +/* + * BFQ: I/O context handling. + * + * Based on ideas and code from CFQ: + * Copyright (C) 2003 Jens Axboe + * + * Copyright (C) 2008 Fabio Checconi + * Paolo Valente + * + * Copyright (C) 2010 Paolo Valente + */ + +/** + * 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. + * + * Queue lock must be held. + */ +static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd, + struct io_context *ioc) +{ + if (ioc) + return icq_to_bic(ioc_lookup_icq(ioc, bfqd->queue)); + return NULL; +} diff --git a/block/bfq-mq-iosched.c b/block/bfq-mq-iosched.c new file mode 100644 index 000000000000..47a49d9e6512 --- /dev/null +++ b/block/bfq-mq-iosched.c @@ -0,0 +1,6548 @@ +/* + * Budget Fair Queueing (BFQ) I/O scheduler. + * + * Based on ideas and code from CFQ: + * Copyright (C) 2003 Jens Axboe + * + * Copyright (C) 2008 Fabio Checconi + * Paolo Valente + * + * Copyright (C) 2015 Paolo Valente + * + * Copyright (C) 2017 Paolo Valente + * + * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ + * file. + * + * BFQ is a proportional-share I/O scheduler, with some extra + * low-latency capabilities. BFQ also supports full hierarchical + * scheduling through cgroups. Next paragraphs provide an introduction + * on BFQ inner workings. Details on BFQ benefits and usage can be + * found in Documentation/block/bfq-iosched.txt. + * + * BFQ is a proportional-share storage-I/O scheduling algorithm based + * on the slice-by-slice service scheme of CFQ. But BFQ assigns + * budgets, measured in number of sectors, to processes instead of + * time slices. The device is not granted to the in-service process + * for a given time slice, but until it has exhausted its assigned + * budget. This change from the time to the service domain enables BFQ + * to distribute the device throughput among processes as desired, + * without any distortion due to throughput fluctuations, or to device + * internal queueing. BFQ uses an ad hoc internal scheduler, called + * B-WF2Q+, to schedule processes according to their budgets. More + * precisely, BFQ schedules queues associated with processes. Thanks to + * the accurate policy of B-WF2Q+, BFQ can afford to assign high + * budgets to I/O-bound processes issuing sequential requests (to + * boost the throughput), and yet guarantee a low latency to + * interactive and soft real-time applications. + * + * In particular, BFQ schedules I/O so as to achieve the latter goal-- + * low latency for interactive and soft real-time applications--if the + * low_latency parameter is set (default configuration). To this + * purpose, BFQ constantly tries to detect whether the I/O requests in + * a bfq_queue come from an interactive or a soft real-time + * application. For brevity, in these cases, the queue is said to be + * interactive or soft real-time. In both cases, BFQ privileges the + * service of the queue, over that of non-interactive and + * non-soft-real-time queues. This privileging is performed, mainly, + * by raising the weight of the queue. So, for brevity, we call just + * weight-raising periods the time periods during which a queue is + * privileged, because deemed interactive or soft real-time. + * + * The detection of soft real-time queues/applications is described in + * detail in the comments on the function + * bfq_bfqq_softrt_next_start. On the other hand, the detection of an + * interactive queue works as follows: a queue is deemed interactive + * if it is constantly non empty only for a limited time interval, + * after which it does become empty. The queue may be deemed + * interactive again (for a limited time), if it restarts being + * constantly non empty, provided that this happens only after the + * queue has remained empty for a given minimum idle time. + * + * By default, BFQ computes automatically the above maximum time + * interval, i.e., the time interval after which a constantly + * non-empty queue stops being deemed interactive. Since a queue is + * weight-raised while it is deemed interactive, this maximum time + * interval happens to coincide with the (maximum) duration of the + * weight-raising for interactive queues. + * + * NOTE: if the main or only goal, with a given device, is to achieve + * the maximum-possible throughput at all times, then do switch off + * all low-latency heuristics for that device, by setting low_latency + * to 0. + * + * BFQ is described in [1], where also a reference to the initial, + * more theoretical paper on BFQ can be found. The interested reader + * can find in the latter paper full details on the main algorithm, as + * well as formulas of the guarantees and formal proofs of all the + * properties. With respect to the version of BFQ presented in these + * papers, this implementation adds a few more heuristics, such as the + * one that guarantees a low latency to soft real-time applications, + * and a hierarchical extension based on H-WF2Q+. + * + * B-WF2Q+ is based on WF2Q+, that is described in [2], together with + * H-WF2Q+, while the augmented tree used to implement B-WF2Q+ with O(log N) + * complexity derives from the one introduced with EEVDF in [3]. + * + * [1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O + * Scheduler", Proceedings of the First Workshop on Mobile System + * Technologies (MST-2015), May 2015. + * http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf + * + * http://algogroup.unimo.it/people/paolo/disk_sched/bf1-v1-suite-results.pdf + * + * [2] Jon C.R. Bennett and H. Zhang, ``Hierarchical Packet Fair Queueing + * Algorithms,'' IEEE/ACM Transactions on Networking, 5(5):675-689, + * Oct 1997. + * + * http://www.cs.cmu.edu/~hzhang/papers/TON-97-Oct.ps.gz + * + * [3] I. Stoica and H. Abdel-Wahab, ``Earliest Eligible Virtual Deadline + * First: A Flexible and Accurate Mechanism for Proportional Share + * Resource Allocation,'' technical report. + * + * http://www.cs.berkeley.edu/~istoica/papers/eevdf-tr-95.pdf + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "blk.h" +#include "blk-mq.h" +#include "blk-mq-tag.h" +#include "blk-mq-sched.h" +#include "bfq-mq.h" +#include "blk-wbt.h" + +/* 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 }; + +/* Maximum backwards seek, in KiB. */ +static const int bfq_back_max = (16 * 1024); + +/* Penalty of a backwards seek, in number of sectors. */ +static const int bfq_back_penalty = 2; + +/* Idling period duration, in ns. */ +static u32 bfq_slice_idle = (NSEC_PER_SEC / 125); + +/* Minimum number of assigned budgets for which stats are safe to compute. */ +static const int bfq_stats_min_budgets = 194; + +/* Default maximum budget values, in sectors and number of requests. */ +static const int bfq_default_max_budget = (16 * 1024); + +/* + * When a sync request is dispatched, the queue that contains that + * request, and all the ancestor entities of that queue, are charged + * with the number of sectors of the request. In constrast, if the + * request is async, then the queue and its ancestor entities are + * charged with the number of sectors of the request, multiplied by + * the factor below. This throttles the bandwidth for async I/O, + * w.r.t. to sync I/O, and it is done to counter the tendency of async + * writes to steal I/O throughput to reads. + * + * The current value of this parameter is the result of a tuning with + * several hardware and software configurations. We tried to find the + * lowest value for which writes do not cause noticeable problems to + * reads. In fact, the lower this parameter, the stabler I/O control, + * in the following respect. The lower this parameter is, the less + * the bandwidth enjoyed by a group decreases + * - when the group does writes, w.r.t. to when it does reads; + * - when other groups do reads, w.r.t. to when they do writes. + */ +static const int bfq_async_charge_factor = 3; + +/* Default timeout values, in jiffies, approximating CFQ defaults. */ +static const int bfq_timeout = (HZ / 8); + +/* + * Time limit for merging (see comments in bfq_setup_cooperator). Set + * to the slowest value that, in our tests, proved to be effective in + * removing false positives, while not causing true positives to miss + * queue merging. + * + * As can be deduced from the low time limit below, queue merging, if + * successful, happens at the very beggining of the I/O of the involved + * cooperating processes, as a consequence of the arrival of the very + * first requests from each cooperator. After that, there is very + * little chance to find cooperators. + */ +static const unsigned long bfq_merge_time_limit = HZ/10; + +#define MAX_LENGTH_REASON_NAME 25 + +static const char reason_name[][MAX_LENGTH_REASON_NAME] = {"TOO_IDLE", +"BUDGET_TIMEOUT", "BUDGET_EXHAUSTED", "NO_MORE_REQUESTS", +"PREEMPTED"}; + +static struct kmem_cache *bfq_pool; + +/* Below this threshold (in ns), we consider thinktime immediate. */ +#define BFQ_MIN_TT (2 * NSEC_PER_MSEC) + +/* hw_tag detection: parallel requests threshold and min samples needed. */ +#define BFQ_HW_QUEUE_THRESHOLD 3 +#define BFQ_HW_QUEUE_SAMPLES 32 + +#define BFQQ_SEEK_THR (sector_t)(8 * 100) +#define BFQQ_SECT_THR_NONROT (sector_t)(2 * 32) +#define BFQ_RQ_SEEKY(bfqd, last_pos, rq) \ + (get_sdist(last_pos, rq) > \ + BFQQ_SEEK_THR && \ + (!blk_queue_nonrot(bfqd->queue) || \ + blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT)) +#define BFQQ_CLOSE_THR (sector_t)(8 * 1024) +#define BFQQ_SEEKY(bfqq) (hweight32(bfqq->seek_history) > 19) + +/* Min number of samples required to perform peak-rate update */ +#define BFQ_RATE_MIN_SAMPLES 32 +/* Min observation time interval required to perform a peak-rate update (ns) */ +#define BFQ_RATE_MIN_INTERVAL (300*NSEC_PER_MSEC) +/* Target observation time interval for a peak-rate update (ns) */ +#define BFQ_RATE_REF_INTERVAL NSEC_PER_SEC + +/* + * Shift used for peak-rate fixed precision calculations. + * With + * - the current shift: 16 positions + * - the current type used to store rate: u32 + * - the current unit of measure for rate: [sectors/usec], or, more precisely, + * [(sectors/usec) / 2^BFQ_RATE_SHIFT] to take into account the shift, + * the range of rates that can be stored is + * [1 / 2^BFQ_RATE_SHIFT, 2^(32 - BFQ_RATE_SHIFT)] sectors/usec = + * [1 / 2^16, 2^16] sectors/usec = [15e-6, 65536] sectors/usec = + * [15, 65G] sectors/sec + * Which, assuming a sector size of 512B, corresponds to a range of + * [7.5K, 33T] B/sec + */ +#define BFQ_RATE_SHIFT 16 + +/* + * When configured for computing the duration of the weight-raising + * for interactive queues automatically (see the comments at the + * beginning of this file), BFQ does it using the following formula: + * duration = (ref_rate / r) * ref_wr_duration, + * where r is the peak rate of the device, and ref_rate and + * ref_wr_duration are two reference parameters. In particular, + * ref_rate is the peak rate of the reference storage device (see + * below), and ref_wr_duration is about the maximum time needed, with + * BFQ and while reading two files in parallel, to load typical large + * applications on the reference device (see the comments on + * max_service_from_wr below, for more details on how ref_wr_duration + * is obtained). In practice, the slower/faster the device at hand + * is, the more/less it takes to load applications with respect to the + * reference device. Accordingly, the longer/shorter BFQ grants + * weight raising to interactive applications. + * + * BFQ uses two different reference pairs (ref_rate, ref_wr_duration), + * depending on whether the device is rotational or non-rotational. + * + * In the following definitions, ref_rate[0] and ref_wr_duration[0] + * are the reference values for a rotational device, whereas + * ref_rate[1] and ref_wr_duration[1] are the reference values for a + * non-rotational device. The reference rates are not the actual peak + * rates of the devices used as a reference, but slightly lower + * values. The reason for using slightly lower values is that the + * peak-rate estimator tends to yield slightly lower values than the + * actual peak rate (it can yield the actual peak rate only if there + * is only one process doing I/O, and the process does sequential + * I/O). + * + * The reference peak rates are measured in sectors/usec, left-shifted + * by BFQ_RATE_SHIFT. + */ +static int ref_rate[2] = {14000, 33000}; +/* + * To improve readability, a conversion function is used to initialize + * the following array, which entails that the array can be + * initialized only in a function. + */ +static int ref_wr_duration[2]; + +/* + * BFQ uses the above-detailed, time-based weight-raising mechanism to + * privilege interactive tasks. This mechanism is vulnerable to the + * following false positives: I/O-bound applications that will go on + * doing I/O for much longer than the duration of weight + * raising. These applications have basically no benefit from being + * weight-raised at the beginning of their I/O. On the opposite end, + * while being weight-raised, these applications + * a) unjustly steal throughput to applications that may actually need + * low latency; + * b) make BFQ uselessly perform device idling; device idling results + * in loss of device throughput with most flash-based storage, and may + * increase latencies when used purposelessly. + * + * BFQ tries to reduce these problems, by adopting the following + * countermeasure. To introduce this countermeasure, we need first to + * finish explaining how the duration of weight-raising for + * interactive tasks is computed. + * + * For a bfq_queue deemed as interactive, the duration of weight + * raising is dynamically adjusted, as a function of the estimated + * peak rate of the device, so as to be equal to the time needed to + * execute the 'largest' interactive task we benchmarked so far. By + * largest task, we mean the task for which each involved process has + * to do more I/O than for any of the other tasks we benchmarked. This + * reference interactive task is the start-up of LibreOffice Writer, + * and in this task each process/bfq_queue needs to have at most ~110K + * sectors transferred. + * + * This last piece of information enables BFQ to reduce the actual + * duration of weight-raising for at least one class of I/O-bound + * applications: those doing sequential or quasi-sequential I/O. An + * example is file copy. In fact, once started, the main I/O-bound + * processes of these applications usually consume the above 110K + * sectors in much less time than the processes of an application that + * is starting, because these I/O-bound processes will greedily devote + * almost all their CPU cycles only to their target, + * throughput-friendly I/O operations. This is even more true if BFQ + * happens to be underestimating the device peak rate, and thus + * overestimating the duration of weight raising. But, according to + * our measurements, once transferred 110K sectors, these processes + * have no right to be weight-raised any longer. + * + * Basing on the last consideration, BFQ ends weight-raising for a + * bfq_queue if the latter happens to have received an amount of + * service at least equal to the following constant. The constant is + * set to slightly more than 110K, to have a minimum safety margin. + * + * This early ending of weight-raising reduces the amount of time + * during which interactive false positives cause the two problems + * described at the beginning of these comments. + */ +static const unsigned long max_service_from_wr = 120000; + +#define BFQ_SERVICE_TREE_INIT ((struct bfq_service_tree) \ + { RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 }) + +#define RQ_BIC(rq) icq_to_bic((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, ""); + blk_mq_run_hw_queues(bfqd->queue, true); + } +} + +#define BFQ_MQ +#include "bfq-sched.c" +#include "bfq-cgroup-included.c" + +#define bfq_class_idle(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE) +#define bfq_class_rt(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_RT) + +#define bfq_sample_valid(samples) ((samples) > 80) + +/* + * Lifted from AS - choose which of rq1 and rq2 that is best served now. + * We choose the request that is closesr to the head right now. Distance + * behind the head is penalized and only allowed to a certain extent. + */ +static struct request *bfq_choose_req(struct bfq_data *bfqd, + struct request *rq1, + struct request *rq2, + sector_t last) +{ + sector_t s1, s2, d1 = 0, d2 = 0; + unsigned long back_max; +#define BFQ_RQ1_WRAP 0x01 /* request 1 wraps */ +#define BFQ_RQ2_WRAP 0x02 /* request 2 wraps */ + unsigned int wrap = 0; /* bit mask: requests behind the disk head? */ + + if (!rq1 || rq1 == rq2) + return rq2; + if (!rq2) + return rq1; + + if (rq_is_sync(rq1) && !rq_is_sync(rq2)) + return rq1; + else if (rq_is_sync(rq2) && !rq_is_sync(rq1)) + return rq2; + if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META)) + return rq1; + else if ((rq2->cmd_flags & REQ_META) && !(rq1->cmd_flags & REQ_META)) + return rq2; + + s1 = blk_rq_pos(rq1); + s2 = blk_rq_pos(rq2); + + /* + * By definition, 1KiB is 2 sectors. + */ + back_max = bfqd->bfq_back_max * 2; + + /* + * Strict one way elevator _except_ in the case where we allow + * short backward seeks which are biased as twice the cost of a + * similar forward seek. + */ + if (s1 >= last) + d1 = s1 - last; + else if (s1 + back_max >= last) + d1 = (last - s1) * bfqd->bfq_back_penalty; + else + wrap |= BFQ_RQ1_WRAP; + + if (s2 >= last) + d2 = s2 - last; + else if (s2 + back_max >= last) + d2 = (last - s2) * bfqd->bfq_back_penalty; + else + wrap |= BFQ_RQ2_WRAP; + + /* Found required data */ + + /* + * By doing switch() on the bit mask "wrap" we avoid having to + * check two variables for all permutations: --> faster! + */ + switch (wrap) { + case 0: /* common case for CFQ: rq1 and rq2 not wrapped */ + if (d1 < d2) + return rq1; + else if (d2 < d1) + return rq2; + + if (s1 >= s2) + return rq1; + else + return rq2; + + case BFQ_RQ2_WRAP: + return rq1; + case BFQ_RQ1_WRAP: + return rq2; + case (BFQ_RQ1_WRAP|BFQ_RQ2_WRAP): /* both rqs wrapped */ + default: + /* + * Since both rqs are wrapped, + * start with the one that's further behind head + * (--> only *one* back seek required), + * since back seek takes more time than forward. + */ + if (s1 <= s2) + return rq1; + else + return rq2; + } +} + +/* + * Async I/O can easily starve sync I/O (both sync reads and sync + * writes), by consuming all tags. Similarly, storms of sync writes, + * such as those that sync(2) may trigger, can starve sync reads. + * Limit depths of async I/O and sync writes so as to counter both + * problems. + */ +static void bfq_limit_depth(unsigned int op, struct blk_mq_alloc_data *data) +{ + struct bfq_data *bfqd = data->q->elevator->elevator_data; + + if (op_is_sync(op) && !op_is_write(op)) + return; + + data->shallow_depth = + bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(op)]; + + bfq_log(bfqd, "wr_busy %d sync %d depth %u", + bfqd->wr_busy_queues, op_is_sync(op), + data->shallow_depth); +} + +static struct bfq_queue * +bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root, + sector_t sector, struct rb_node **ret_parent, + struct rb_node ***rb_link) +{ + struct rb_node **p, *parent; + struct bfq_queue *bfqq = NULL; + + parent = NULL; + p = &root->rb_node; + while (*p) { + struct rb_node **n; + + parent = *p; + bfqq = rb_entry(parent, struct bfq_queue, pos_node); + + /* + * Sort strictly based on sector. Smallest to the left, + * largest to the right. + */ + if (sector > blk_rq_pos(bfqq->next_rq)) + n = &(*p)->rb_right; + else if (sector < blk_rq_pos(bfqq->next_rq)) + n = &(*p)->rb_left; + else + break; + p = n; + bfqq = NULL; + } + + *ret_parent = parent; + if (rb_link) + *rb_link = p; + + bfq_log(bfqd, "%llu: returning %d", + (unsigned long long) sector, + bfqq ? bfqq->pid : 0); + + return bfqq; +} + +static bool bfq_too_late_for_merging(struct bfq_queue *bfqq) +{ + return bfqq->service_from_backlogged > 0 && + time_is_before_jiffies(bfqq->first_IO_time + + bfq_merge_time_limit); +} + +static void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq) +{ + struct rb_node **p, *parent; + struct bfq_queue *__bfqq; + + if (bfqq->pos_root) { + rb_erase(&bfqq->pos_node, bfqq->pos_root); + bfqq->pos_root = NULL; + } + + /* + * bfqq cannot be merged any longer (see comments in + * bfq_setup_cooperator): no point in adding bfqq into the + * position tree. + */ + if (bfq_too_late_for_merging(bfqq)) + return; + + if (bfq_class_idle(bfqq)) + return; + if (!bfqq->next_rq) + return; + + bfqq->pos_root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree; + __bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root, + blk_rq_pos(bfqq->next_rq), &parent, &p); + if (!__bfqq) { + rb_link_node(&bfqq->pos_node, parent, p); + rb_insert_color(&bfqq->pos_node, bfqq->pos_root); + } else + bfqq->pos_root = NULL; +} + +/* + * 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_better_to_idle()). + * + * Such a scenario occurs when: + * 1) all active queues have the same weight, + * 2) all active queues belong to the same I/O-priority class, + * 3) all active groups at the same level in the groups tree have the same + * weight, + * 4) 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 last two symmetry sub-conditions above would be quite complex + * and time consuming. Therefore this function evaluates, instead, + * only the following stronger three sub-conditions, for which it is + * much easier to maintain the needed state: + * 1) all active queues have the same weight, + * 2) all active queues belong to the same I/O-priority class, + * 3) there are no active groups. + * In particular, the last condition is always true if hierarchical + * support or 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) +{ + /* + * For queue weights to differ, queue_weights_tree must contain + * at least two nodes. + */ + bool varied_queue_weights = !RB_EMPTY_ROOT(&bfqd->queue_weights_tree) && + (bfqd->queue_weights_tree.rb_node->rb_left || + bfqd->queue_weights_tree.rb_node->rb_right); + + bool multiple_classes_busy = + (bfqd->busy_queues[0] && bfqd->busy_queues[1]) || + (bfqd->busy_queues[0] && bfqd->busy_queues[2]) || + (bfqd->busy_queues[1] && bfqd->busy_queues[2]); + + bfq_log(bfqd, "varied_queue_weights %d mul_classes %d", + varied_queue_weights, multiple_classes_busy); + +#ifdef BFQ_GROUP_IOSCHED_ENABLED + bfq_log(bfqd, "num_groups_with_pending_reqs %u", + bfqd->num_groups_with_pending_reqs); +#endif + + return !(varied_queue_weights || multiple_classes_busy +#ifdef BFQ_GROUP_IOSCHED_ENABLED + || bfqd->num_groups_with_pending_reqs > 0 +#endif + ); +} + +/* + * If the weight-counter tree passed as input contains no counter for + * the weight of the input queue, 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. + */ +static void bfq_weights_tree_add(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + struct rb_root *root) +{ + struct bfq_entity *entity = &bfqq->entity; + struct rb_node **new = &(root->rb_node), *parent = NULL; + + /* + * Do not insert if the queue is already associated with a + * counter, which happens if: + * 1) 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, + * 2) 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 (bfqq->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) { + bfqq->weight_counter = __counter; + goto inc_counter; + } + if (entity->weight < __counter->weight) + new = &((*new)->rb_left); + else + new = &((*new)->rb_right); + } + + bfqq->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 queue to not be + * considered in bfq_symmetric_scenario, which, in its turn, + * causes the scenario to be deemed wrongly symmetric in case + * bfqq's weight would have been the only weight making the + * scenario asymmetric. On the bright side, no unbalance will + * however occur when bfqq becomes inactive again (the + * invocation of this function is triggered by an activation + * of queue). In fact, bfq_weights_tree_remove does nothing + * if !bfqq->weight_counter. + */ + if (unlikely(!bfqq->weight_counter)) + return; + + bfqq->weight_counter->weight = entity->weight; + rb_link_node(&bfqq->weight_counter->weights_node, parent, new); + rb_insert_color(&bfqq->weight_counter->weights_node, root); + +inc_counter: + bfqq->weight_counter->num_active++; + bfqq->ref++; + + bfq_log_bfqq(bfqq->bfqd, bfqq, "refs %d weight %d symmetric %d", + bfqq->ref, + entity->weight, + bfq_symmetric_scenario(bfqd)); +} + +/* + * Decrement the weight counter associated with the queue, 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. + */ +static void __bfq_weights_tree_remove(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + struct rb_root *root) +{ + struct bfq_entity *entity = &bfqq->entity; + + if (!bfqq->weight_counter) + return; + + BUG_ON(RB_EMPTY_ROOT(root)); + BUG_ON(bfqq->weight_counter->weight != entity->weight); + + BUG_ON(!bfqq->weight_counter->num_active); + bfqq->weight_counter->num_active--; + + if (bfqq->weight_counter->num_active > 0) + goto reset_entity_pointer; + + rb_erase(&bfqq->weight_counter->weights_node, root); + kfree(bfqq->weight_counter); + +reset_entity_pointer: + bfqq->weight_counter = NULL; + bfq_log_bfqq(bfqq->bfqd, bfqq, + "refs %d weight %d symmetric %d", + bfqq->ref, + entity->weight, + bfq_symmetric_scenario(bfqd)); + bfq_put_queue(bfqq); +} + +/* + * Invoke __bfq_weights_tree_remove on bfqq and decrement the number + * of active groups for each queue's inactive parent entity. + */ +static void bfq_weights_tree_remove(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + struct bfq_entity *entity = bfqq->entity.parent; + + for_each_entity(entity) { + struct bfq_sched_data *sd = entity->my_sched_data; + + BUG_ON(entity->sched_data == NULL); /* + * It would mean + * that this is + * the root group. + */ + + if (sd->next_in_service || sd->in_service_entity) { + BUG_ON(!entity->in_groups_with_pending_reqs); + /* + * entity is still active, because either + * next_in_service or in_service_entity is not + * NULL (see the comments on the definition of + * next_in_service for details on why + * in_service_entity must be checked too). + * + * As a consequence, its parent entities are + * active as well, and thus this loop must + * stop here. + */ + break; + } + + BUG_ON(!bfqd->num_groups_with_pending_reqs && + entity->in_groups_with_pending_reqs); + /* + * The decrement of num_groups_with_pending_reqs is + * not performed immediately upon the deactivation of + * entity, but it is delayed to when it also happens + * that the first leaf descendant bfqq of entity gets + * all its pending requests completed. The following + * instructions perform this delayed decrement, if + * needed. See the comments on + * num_groups_with_pending_reqs for details. + */ + if (entity->in_groups_with_pending_reqs) { + entity->in_groups_with_pending_reqs = false; + bfqd->num_groups_with_pending_reqs--; + } + bfq_log_bfqq(bfqd, bfqq, "num_groups_with_pending_reqs %u", + bfqd->num_groups_with_pending_reqs); + } + + /* + * Next function is invoked last, because it causes bfqq to be + * freed if the following holds: bfqq is not in service and + * has no dispatched request. DO NOT use bfqq after the next + * function invocation. + */ + __bfq_weights_tree_remove(bfqd, bfqq, + &bfqd->queue_weights_tree); +} + +/* + * Return expired entry, or NULL to just start from scratch in rbtree. + */ +static struct request *bfq_check_fifo(struct bfq_queue *bfqq, + struct request *last) +{ + struct request *rq; + + if (bfq_bfqq_fifo_expire(bfqq)) + return NULL; + + bfq_mark_bfqq_fifo_expire(bfqq); + + rq = rq_entry_fifo(bfqq->fifo.next); + + if (rq == last || ktime_get_ns() < rq->fifo_time) + return NULL; + + bfq_log_bfqq(bfqq->bfqd, bfqq, "returned %p", rq); + BUG_ON(RB_EMPTY_NODE(&rq->rb_node)); + return rq; +} + +static struct request *bfq_find_next_rq(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + struct request *last) +{ + struct rb_node *rbnext = rb_next(&last->rb_node); + struct rb_node *rbprev = rb_prev(&last->rb_node); + struct request *next, *prev = NULL; + + BUG_ON(list_empty(&bfqq->fifo)); + + /* Follow expired path, else get first next available. */ + next = bfq_check_fifo(bfqq, last); + if (next) { + BUG_ON(next == last); + return next; + } + + BUG_ON(RB_EMPTY_NODE(&last->rb_node)); + + if (rbprev) + prev = rb_entry_rq(rbprev); + + if (rbnext) + next = rb_entry_rq(rbnext); + else { + rbnext = rb_first(&bfqq->sort_list); + if (rbnext && rbnext != &last->rb_node) + next = rb_entry_rq(rbnext); + } + + return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last)); +} + +/* see the definition of bfq_async_charge_factor for details */ +static unsigned long bfq_serv_to_charge(struct request *rq, + struct bfq_queue *bfqq) +{ + if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1 || + !bfq_symmetric_scenario(bfqq->bfqd)) + return blk_rq_sectors(rq); + + return blk_rq_sectors(rq) * bfq_async_charge_factor; +} + +/** + * bfq_updated_next_req - update the queue after a new next_rq selection. + * @bfqd: the device data the queue belongs to. + * @bfqq: the queue to update. + * + * If the first request of a queue changes we make sure that the queue + * has enough budget to serve at least its first request (if the + * request has grown). We do this because if the queue has not enough + * budget for its first request, it has to go through two dispatch + * rounds to actually get it dispatched. + */ +static void bfq_updated_next_req(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + struct bfq_entity *entity = &bfqq->entity; + struct bfq_service_tree *st = bfq_entity_service_tree(entity); + struct request *next_rq = bfqq->next_rq; + unsigned long new_budget; + + if (!next_rq) + return; + + if (bfqq == bfqd->in_service_queue) + /* + * In order not to break guarantees, budgets cannot be + * changed after an entity has been selected. + */ + return; + + BUG_ON(entity->tree != &st->active); + BUG_ON(entity == entity->sched_data->in_service_entity); + + new_budget = max_t(unsigned long, + max_t(unsigned long, bfqq->max_budget, + bfq_serv_to_charge(next_rq, bfqq)), + entity->service); + if (entity->budget != new_budget) { + entity->budget = new_budget; + bfq_log_bfqq(bfqd, bfqq, "new budget %lu", + new_budget); + bfq_requeue_bfqq(bfqd, bfqq, false); + } +} + +static unsigned int bfq_wr_duration(struct bfq_data *bfqd) +{ + u64 dur; + + if (bfqd->bfq_wr_max_time > 0) + return bfqd->bfq_wr_max_time; + + dur = bfqd->rate_dur_prod; + do_div(dur, bfqd->peak_rate); + + /* + * Limit duration between 3 and 25 seconds. The upper limit + * has been conservatively set after the following worst case: + * on a QEMU/KVM virtual machine + * - running in a slow PC + * - with a virtual disk stacked on a slow low-end 5400rpm HDD + * - serving a heavy I/O workload, such as the sequential reading + * of several files + * mplayer took 23 seconds to start, if constantly weight-raised. + * + * As for higher values than that accomodating the above bad + * scenario, tests show that higher values would often yield + * the opposite of the desired result, i.e., would worsen + * responsiveness by allowing non-interactive applications to + * preserve weight raising for too long. + * + * On the other end, lower values than 3 seconds make it + * difficult for most interactive tasks to complete their jobs + * before weight-raising finishes. + */ + return clamp_val(dur, msecs_to_jiffies(3000), msecs_to_jiffies(25000)); +} + +/* switch back from soft real-time to interactive weight raising */ +static void switch_back_to_interactive_wr(struct bfq_queue *bfqq, + struct bfq_data *bfqd) +{ + bfqq->wr_coeff = bfqd->bfq_wr_coeff; + bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); + bfqq->last_wr_start_finish = bfqq->wr_start_at_switch_to_srt; +} + +static void +bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd, + struct bfq_io_cq *bic, bool bfq_already_existing) +{ + unsigned int old_wr_coeff; + bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq); + + if (bic->saved_has_short_ttime) + bfq_mark_bfqq_has_short_ttime(bfqq); + else + bfq_clear_bfqq_has_short_ttime(bfqq); + + if (bic->saved_IO_bound) + bfq_mark_bfqq_IO_bound(bfqq); + else + bfq_clear_bfqq_IO_bound(bfqq); + + if (unlikely(busy)) + old_wr_coeff = bfqq->wr_coeff; + + bfqq->ttime = bic->saved_ttime; + bfqq->wr_coeff = bic->saved_wr_coeff; + bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt; + BUG_ON(time_is_after_jiffies(bfqq->wr_start_at_switch_to_srt)); + bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish; + bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time; + BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish)); + + bfq_log_bfqq(bfqq->bfqd, bfqq, + "bic %p wr_coeff %d start_finish %lu max_time %lu", + bic, bfqq->wr_coeff, bfqq->last_wr_start_finish, + bfqq->wr_cur_max_time); + + 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))) { + if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time && + !bfq_bfqq_in_large_burst(bfqq) && + time_is_after_eq_jiffies(bfqq->wr_start_at_switch_to_srt + + bfq_wr_duration(bfqd))) { + switch_back_to_interactive_wr(bfqq, bfqd); + bfq_log_bfqq(bfqq->bfqd, bfqq, + "switching back to interactive"); + } else { + bfqq->wr_coeff = 1; + bfq_log_bfqq(bfqq->bfqd, bfqq, + "switching off wr (%lu + %lu < %lu)", + bfqq->last_wr_start_finish, bfqq->wr_cur_max_time, + jiffies); + } + } + + /* make sure weight will be updated, however we got here */ + bfqq->entity.prio_changed = 1; + + if (likely(!busy)) + return; + + if (old_wr_coeff == 1 && bfqq->wr_coeff > 1) { + bfqd->wr_busy_queues++; + BUG_ON(bfqd->wr_busy_queues > bfq_tot_busy_queues(bfqd)); + } else if (old_wr_coeff > 1 && bfqq->wr_coeff == 1) { + bfqd->wr_busy_queues--; + BUG_ON(bfqd->wr_busy_queues < 0); + } +} + +static int bfqq_process_refs(struct bfq_queue *bfqq) +{ + int process_refs, io_refs; + + lockdep_assert_held(&bfqq->bfqd->lock); + + io_refs = bfqq->allocated; + process_refs = bfqq->ref - io_refs - bfqq->entity.on_st - + (bfqq->weight_counter != NULL); + BUG_ON(process_refs < 0); + return process_refs; +} + +/* Empty burst list and add just bfqq (see comments to 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++; + + bfq_log_bfqq(bfqd, bfqq, "%d", bfqd->burst_size); + + BUG_ON(bfqd->burst_size > bfqd->bfq_large_burst_thresh); + + 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; + bfq_log_bfqq(bfqd, bfqq, "large burst started"); + + /* + * 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_log_bfqq(bfqd, bfqq_item, "marked in large burst"); + } + bfq_mark_bfqq_in_large_burst(bfqq); + bfq_log_bfqq(bfqd, bfqq, "marked in large burst"); + + /* + * 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); + bfq_log_bfqq(bfqd, bfqq, + "late activation or different group"); + 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_log_bfqq(bfqd, bfqq, "marked in 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; + + if (entity->budget < entity->service) { + pr_crit("budget %d service %d\n", + entity->budget, entity->service); + BUG(); + } + return entity->budget - entity->service; +} + +/* + * If enough samples have been computed, return the current max budget + * stored in bfqd, which is dynamically updated according to the + * estimated disk peak rate; otherwise return the default max budget + */ +static int bfq_max_budget(struct bfq_data *bfqd) +{ + if (bfqd->budgets_assigned < bfq_stats_min_budgets) + return bfq_default_max_budget; + else + return bfqd->bfq_max_budget; +} + +/* + * Return min budget, which is a fraction of the current or default + * max budget (trying with 1/32) + */ +static int bfq_min_budget(struct bfq_data *bfqd) +{ + if (bfqd->budgets_assigned < bfq_stats_min_budgets) + return bfq_default_max_budget / 32; + else + 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 + * whether the in-service queue should be expired, by returning + * true. The purpose of expiring the in-service queue is to give bfqq + * the chance to possibly preempt the in-service queue, and the reason + * for preempting the in-service queue is to achieve one of the two + * goals below. + * + * 1. Guarantee to bfqq its reserved bandwidth even if bfqq has + * expired because it has remained idle. In particular, bfqq may have + * expired for one of the following two reasons: + * + * - BFQ_BFQQ_NO_MORE_REQUEST bfqq did not enjoy any device idling and + * did not make it to issue a new request before its last request + * was served; + * + * - BFQ_BFQQ_TOO_IDLE bfqq did enjoy device idling, but did not issue + * a new request before the expiration of the idling-time. + * + * Even if bfqq has expired for one of the above reasons, the process + * associated with the queue may be however issuing requests greedily, + * and thus be sensitive to the bandwidth it receives (bfqq may have + * remained idle for other reasons: CPU high load, bfqq not enjoying + * idling, I/O throttling somewhere in the path from the process to + * the I/O scheduler, ...). But if, after every expiration for one of + * the above two reasons, bfqq has to wait for the service of at least + * one full budget of another queue before being served again, then + * bfqq is likely to get a much lower bandwidth or resource time than + * its reserved ones. To address this issue, two countermeasures need + * to be taken. + * + * First, the budget and the timestamps of bfqq need to be updated in + * a special way on bfqq reactivation: they need to be updated as if + * bfqq did not remain idle and did not expire. In fact, if they are + * computed as if bfqq expired and remained idle until reactivation, + * then the process associated with bfqq is treated as if, instead of + * being greedy, it stopped issuing requests when bfqq remained idle, + * and restarts issuing requests only on this reactivation. In other + * words, the scheduler does not help the process recover the "service + * hole" between bfqq expiration and reactivation. As a consequence, + * the process receives a lower bandwidth than its reserved one. In + * contrast, to recover this hole, the budget must be updated as if + * bfqq was not expired at all before this reactivation, i.e., it must + * be set to the value of the remaining budget when bfqq was + * expired. Along the same line, timestamps need to be assigned the + * value they had the last time bfqq was selected for service, i.e., + * before last expiration. Thus timestamps need to be back-shifted + * with respect to their normal computation (see [1] for more details + * on this tricky aspect). + * + * Secondly, to allow the process to recover the hole, the in-service + * queue must be expired too, to give bfqq the chance to preempt it + * immediately. In fact, if bfqq has to wait for a full budget of the + * in-service queue to be completed, then it may become impossible to + * let the process recover the hole, even if the back-shifted + * timestamps of bfqq are lower than those of the in-service queue. If + * this happens for most or all of the holes, then the process may not + * receive its reserved bandwidth. In this respect, it is worth noting + * that, being the service of outstanding requests unpreemptible, a + * little fraction of the holes may however be unrecoverable, thereby + * causing a little loss of bandwidth. + * + * The last important point is detecting whether bfqq does need this + * bandwidth recovery. In this respect, the next function deems the + * process associated with bfqq greedy, and thus allows it to recover + * the hole, if: 1) the process is waiting for the arrival of a new + * request (which implies that bfqq expired for one of the above two + * reasons), and 2) such a request has arrived soon. The first + * condition is controlled through the flag non_blocking_wait_rq, + * while the second through the flag arrived_in_time. If both + * conditions hold, then the function computes the budget in the + * above-described special way, and signals that the in-service queue + * should be expired. Timestamp back-shifting is done later in + * __bfq_activate_entity. + * + * 2. Reduce latency. Even if timestamps are not backshifted to let + * the process associated with bfqq recover a service hole, bfqq may + * however happen to have, after being (re)activated, a lower finish + * timestamp than the in-service queue. That is, the next budget of + * bfqq may have to be completed before the one of the in-service + * queue. If this is the case, then preempting the in-service queue + * allows this goal to be achieved, apart from the unpreemptible, + * outstanding requests mentioned above. + * + * Unfortunately, regardless of which of the above two goals one wants + * to achieve, service trees need first to be updated to know whether + * the in-service queue must be preempted. To have service trees + * correctly updated, the in-service queue must be expired and + * rescheduled, and bfqq must be scheduled too. This is one of the + * most costly operations (in future versions, the scheduling + * mechanism may be re-designed in such a way to make it possible to + * know whether preemption is needed without needing to update service + * trees). In addition, queue preemptions almost always cause random + * I/O, and thus loss of throughput. Because of these facts, the next + * function adopts the following simple scheme to avoid both costly + * operations and too frequent preemptions: it requests the expiration + * of the in-service queue (unconditionally) only for queues that need + * to recover a hole, or that either are weight-raised or deserve to + * be weight-raised. + */ +static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + bool arrived_in_time, + bool wr_or_deserves_wr) +{ + struct bfq_entity *entity = &bfqq->entity; + + /* + * In the next compound condition, we check also whether there + * is some budget left, because otherwise there is no point in + * trying to go on serving bfqq with this same budget: bfqq + * would be expired immediately after being selected for + * service. This would only cause useless overhead. + */ + if (bfq_bfqq_non_blocking_wait_rq(bfqq) && arrived_in_time && + bfq_bfqq_budget_left(bfqq) > 0) { + /* + * We do not clear the flag non_blocking_wait_rq here, as + * the latter is used in bfq_activate_bfqq to signal + * that timestamps need to be back-shifted (and is + * cleared right after). + */ + + /* + * In next assignment we rely on that either + * entity->service or entity->budget are not updated + * on expiration if bfqq is empty (see + * __bfq_bfqq_recalc_budget). Thus both quantities + * remain unchanged after such an expiration, and the + * following statement therefore assigns to + * entity->budget the remaining budget on such an + * expiration. + */ + BUG_ON(bfqq->max_budget < 0); + entity->budget = min_t(unsigned long, + bfq_bfqq_budget_left(bfqq), + bfqq->max_budget); + + BUG_ON(entity->budget < 0); + + /* + * At this point, we have used entity->service to get + * the budget left (needed for updating + * entity->budget). Thus we finally can, and have to, + * reset entity->service. The latter must be reset + * because bfqq would otherwise be charged again for + * the service it has received during its previous + * service slot(s). + */ + entity->service = 0; + + return true; + } + + /* + * We can finally complete expiration, by setting service to 0. + */ + entity->service = 0; + BUG_ON(bfqq->max_budget < 0); + entity->budget = max_t(unsigned long, bfqq->max_budget, + bfq_serv_to_charge(bfqq->next_rq, bfqq)); + BUG_ON(entity->budget < 0); + + bfq_clear_bfqq_non_blocking_wait_rq(bfqq); + return wr_or_deserves_wr; +} + +/* + * Return the farthest past time instant according to jiffies + * macros. + */ +static unsigned long bfq_smallest_from_now(void) +{ + return jiffies - MAX_JIFFY_OFFSET; +} + +static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + 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) { + /* start a weight-raising period */ + if (interactive) { + bfqq->service_from_wr = 0; + bfqq->wr_coeff = bfqd->bfq_wr_coeff; + bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); + } else { + /* + * No interactive weight raising in progress + * here: assign minus infinity to + * wr_start_at_switch_to_srt, to make sure + * that, at the end of the soft-real-time + * weight raising periods that is starting + * now, no interactive weight-raising period + * may be wrongly considered as still in + * progress (and thus actually started by + * mistake). + */ + bfqq->wr_start_at_switch_to_srt = + bfq_smallest_from_now(); + bfqq->wr_coeff = bfqd->bfq_wr_coeff * + BFQ_SOFTRT_WEIGHT_FACTOR; + bfqq->wr_cur_max_time = + bfqd->bfq_wr_rt_max_time; + } + /* + * If needed, further reduce budget to make sure it is + * close to bfqq's backlog, so as to reduce the + * scheduling-error component due to a too large + * budget. Do not care about throughput consequences, + * but only about latency. Finally, do not assign a + * too small budget either, to avoid increasing + * latency by causing too frequent expirations. + */ + bfqq->entity.budget = min_t(unsigned long, + bfqq->entity.budget, + 2 * bfq_min_budget(bfqd)); + + bfq_log_bfqq(bfqd, bfqq, + "wrais starting at %lu, rais_max_time %u", + jiffies, + jiffies_to_msecs(bfqq->wr_cur_max_time)); + } else if (old_wr_coeff > 1) { + 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 (in_burst) { + bfqq->wr_coeff = 1; + bfq_log_bfqq(bfqd, bfqq, + "wrais ending at %lu, rais_max_time %u", + jiffies, + jiffies_to_msecs(bfqq-> + wr_cur_max_time)); + } else if (soft_rt) { + /* + * The application is now or still meeting the + * requirements for being deemed soft rt. We + * can then correctly and safely (re)charge + * the weight-raising duration for the + * application with the weight-raising + * duration for soft rt applications. + * + * In particular, doing this recharge now, i.e., + * before the weight-raising period for the + * application finishes, reduces the probability + * of the following negative scenario: + * 1) the weight of a soft rt application is + * raised at startup (as for any newly + * created application), + * 2) since the application is not interactive, + * at a certain time weight-raising is + * stopped for the application, + * 3) at that time the application happens to + * still have pending requests, and hence + * is destined to not have a chance to be + * deemed soft rt before these requests are + * completed (see the comments to the + * function bfq_bfqq_softrt_next_start() + * for details on soft rt detection), + * 4) these pending requests experience a high + * latency because the application is not + * weight-raised while they are pending. + */ + if (bfqq->wr_cur_max_time != + bfqd->bfq_wr_rt_max_time) { + bfqq->wr_start_at_switch_to_srt = + bfqq->last_wr_start_finish; + BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish)); + + bfqq->wr_cur_max_time = + bfqd->bfq_wr_rt_max_time; + bfqq->wr_coeff = bfqd->bfq_wr_coeff * + BFQ_SOFTRT_WEIGHT_FACTOR; + bfq_log_bfqq(bfqd, bfqq, + "switching to soft_rt wr"); + } else + bfq_log_bfqq(bfqd, bfqq, + "moving forward soft_rt wr duration"); + bfqq->last_wr_start_finish = jiffies; + } + } +} + +static bool bfq_bfqq_idle_for_long_time(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + return bfqq->dispatched == 0 && + time_is_before_jiffies( + bfqq->budget_timeout + + bfqd->bfq_wr_min_idle_time); +} + +static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + int old_wr_coeff, + struct request *rq, + bool *interactive) +{ + 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 + * bfq_bfqq_update_budg_for_activation for + * details on the usage of the next variable. + */ + arrived_in_time = ktime_get_ns() <= + bfqq->ttime.last_end_request + + bfqd->bfq_slice_idle * 3; + + bfq_log_bfqq(bfqd, bfqq, + "bfq_add_request non-busy: " + "jiffies %lu, in_time %d, idle_long %d busyw %d " + "wr_coeff %u", + jiffies, arrived_in_time, + idle_for_long_time, + bfq_bfqq_non_blocking_wait_rq(bfqq), + old_wr_coeff); + + BUG_ON(bfqq->entity.budget < bfqq->entity.service); + + BUG_ON(bfqq == bfqd->in_service_queue); + + /* + * 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) && + bfqq->dispatched == 0; + *interactive = + !in_burst && + idle_for_long_time; + wr_or_deserves_wr = bfqd->low_latency && + (bfqq->wr_coeff > 1 || + (bfq_bfqq_sync(bfqq) && + bfqq->bic && (*interactive || soft_rt))); + + bfq_log_bfqq(bfqd, bfqq, + "bfq_add_request: " + "in_burst %d, " + "soft_rt %d (next %lu), inter %d, bic %p", + bfq_bfqq_in_large_burst(bfqq), soft_rt, + bfqq->soft_rt_next_start, + *interactive, + bfqq->bic); + + /* + * Using the last flag, update budget and check whether bfqq + * may want to preempt the in-service queue. + */ + bfqq_wants_to_preempt = + bfq_bfqq_update_budg_for_activation(bfqd, 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++; + if (bfqq->requests_within_timer >= + bfqd->bfq_requests_within_timer) + bfq_mark_bfqq_IO_bound(bfqq); + } else + bfqq->requests_within_timer = 0; + bfq_log_bfqq(bfqd, bfqq, "requests in time %d", + bfqq->requests_within_timer); + } + + if (bfqd->low_latency) { + if (unlikely(time_is_after_jiffies(bfqq->split_time))) + /* wraparound */ + bfqq->split_time = + jiffies - bfqd->bfq_wr_min_idle_time - 1; + + if (time_is_before_jiffies(bfqq->split_time + + bfqd->bfq_wr_min_idle_time)) { + bfq_update_bfqq_wr_on_rq_arrival(bfqd, bfqq, + old_wr_coeff, + wr_or_deserves_wr, + *interactive, + in_burst, + soft_rt); + + if (old_wr_coeff != bfqq->wr_coeff) + bfqq->entity.prio_changed = 1; + } + } + + bfqq->last_idle_bklogged = jiffies; + bfqq->service_from_backlogged = 0; + bfq_clear_bfqq_softrt_update(bfqq); + + bfq_add_bfqq_busy(bfqd, bfqq); + + /* + * Expire in-service queue only if preemption may be needed + * for guarantees. In this respect, the function + * next_queue_may_preempt just checks a simple, necessary + * condition, and not a sufficient condition based on + * timestamps. In fact, for the latter condition to be + * evaluated, timestamps would need first to be updated, and + * this operation is quite costly (see the comments on the + * function bfq_bfqq_update_budg_for_activation). + */ + if (bfqd->in_service_queue && bfqq_wants_to_preempt && + bfqd->in_service_queue->wr_coeff < bfqq->wr_coeff && + next_queue_may_preempt(bfqd)) { + struct bfq_queue *in_serv = + bfqd->in_service_queue; + BUG_ON(in_serv == bfqq); + + bfq_bfqq_expire(bfqd, bfqd->in_service_queue, + false, BFQ_BFQQ_PREEMPTED); + } +} + +static void bfq_add_request(struct request *rq) +{ + struct bfq_queue *bfqq = RQ_BFQQ(rq); + struct bfq_data *bfqd = bfqq->bfqd; + struct request *next_rq, *prev; + unsigned int old_wr_coeff = bfqq->wr_coeff; + bool interactive = false; + + bfq_log_bfqq(bfqd, bfqq, "size %u %s", + blk_rq_sectors(rq), rq_is_sync(rq) ? "S" : "A"); + + if (bfqq->wr_coeff > 1) /* queue is being weight-raised */ + bfq_log_bfqq(bfqd, bfqq, + "raising period dur %u/%u msec, old coeff %u, w %d(%d)", + jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish), + jiffies_to_msecs(bfqq->wr_cur_max_time), + bfqq->wr_coeff, + bfqq->entity.weight, bfqq->entity.orig_weight); + + bfqq->queued[rq_is_sync(rq)]++; + bfqd->queued++; + + BUG_ON(!RQ_BFQQ(rq)); + BUG_ON(RQ_BFQQ(rq) != bfqq); + WARN_ON(blk_rq_sectors(rq) == 0); + + elv_rb_add(&bfqq->sort_list, rq); + + /* + * Check if this request is a better next-to-serve candidate. + */ + prev = bfqq->next_rq; + next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position); + BUG_ON(!next_rq); + BUG_ON(!RQ_BFQQ(next_rq)); + BUG_ON(RQ_BFQQ(next_rq) != bfqq); + bfqq->next_rq = next_rq; + + /* + * Adjust priority tree position, if next_rq changes. + */ + if (prev != bfqq->next_rq) + bfq_pos_tree_add_move(bfqd, bfqq); + + if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */ + bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, old_wr_coeff, + rq, &interactive); + else { + if (bfqd->low_latency && old_wr_coeff == 1 && !rq_is_sync(rq) && + time_is_before_jiffies( + bfqq->last_wr_start_finish + + bfqd->bfq_wr_min_inter_arr_async)) { + bfqq->wr_coeff = bfqd->bfq_wr_coeff; + bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); + + bfqd->wr_busy_queues++; + BUG_ON(bfqd->wr_busy_queues > bfq_tot_busy_queues(bfqd)); + bfqq->entity.prio_changed = 1; + bfq_log_bfqq(bfqd, bfqq, + "non-idle wrais starting, " + "wr_max_time %u wr_busy %d", + jiffies_to_msecs(bfqq->wr_cur_max_time), + bfqd->wr_busy_queues); + } + if (prev != bfqq->next_rq) + bfq_updated_next_req(bfqd, bfqq); + } + + /* + * Assign jiffies to last_wr_start_finish in the following + * cases: + * + * . if bfqq is not going to be weight-raised, because, for + * non weight-raised queues, last_wr_start_finish stores the + * arrival time of the last request; as of now, this piece + * of information is used only for deciding whether to + * weight-raise async queues + * + * . if bfqq is not weight-raised, because, if bfqq is now + * switching to weight-raised, then last_wr_start_finish + * stores the time when weight-raising starts + * + * . if bfqq is interactive, because, regardless of whether + * bfqq is currently weight-raised, the weight-raising + * period must start or restart (this case is considered + * separately because it is not detected by the above + * conditions, if bfqq is already weight-raised) + * + * last_wr_start_finish has to be updated also if bfqq is soft + * real-time, because the weight-raising period is constantly + * restarted on idle-to-busy transitions for these queues, but + * this is already done in bfq_bfqq_handle_idle_busy_switch if + * needed. + */ + if (bfqd->low_latency && + (old_wr_coeff == 1 || bfqq->wr_coeff == 1 || interactive)) + bfqq->last_wr_start_finish = jiffies; +} + +static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd, + struct bio *bio, + struct request_queue *q) +{ + struct bfq_queue *bfqq = bfqd->bio_bfqq; + + BUG_ON(!bfqd->bio_bfqq_set); + + if (bfqq) + return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio)); + + return NULL; +} + +static sector_t get_sdist(sector_t last_pos, struct request *rq) +{ + sector_t sdist = 0; + + if (last_pos) { + if (last_pos < blk_rq_pos(rq)) + sdist = blk_rq_pos(rq) - last_pos; + else + sdist = last_pos - blk_rq_pos(rq); + } + + return sdist; +} + +#if 0 /* Still not clear if we can do without next two functions */ +static void bfq_activate_request(struct request_queue *q, struct request *rq) +{ + struct bfq_data *bfqd = q->elevator->elevator_data; + bfqd->rq_in_driver++; +} + +static void bfq_deactivate_request(struct request_queue *q, struct request *rq) +{ + struct bfq_data *bfqd = q->elevator->elevator_data; + + BUG_ON(bfqd->rq_in_driver == 0); + bfqd->rq_in_driver--; +} +#endif + +static void bfq_remove_request(struct request_queue *q, + struct request *rq) +{ + struct bfq_queue *bfqq = RQ_BFQQ(rq); + struct bfq_data *bfqd = bfqq->bfqd; + const int sync = rq_is_sync(rq); + + BUG_ON(bfqq->entity.service > bfqq->entity.budget); + + if (bfqq->next_rq == rq) { + bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq); + if (bfqq->next_rq && !RQ_BFQQ(bfqq->next_rq)) { + pr_crit("no bfqq! for next rq %p bfqq %p\n", + bfqq->next_rq, bfqq); + } + + BUG_ON(bfqq->next_rq && !RQ_BFQQ(bfqq->next_rq)); + if (bfqq->next_rq && RQ_BFQQ(bfqq->next_rq) != bfqq) { + pr_crit( + "wrong bfqq! for next rq %p, rq_bfqq %p bfqq %p\n", + bfqq->next_rq, RQ_BFQQ(bfqq->next_rq), bfqq); + } + BUG_ON(bfqq->next_rq && RQ_BFQQ(bfqq->next_rq) != bfqq); + + bfq_updated_next_req(bfqd, bfqq); + } + + if (rq->queuelist.prev != &rq->queuelist) + list_del_init(&rq->queuelist); + BUG_ON(bfqq->queued[sync] == 0); + bfqq->queued[sync]--; + bfqd->queued--; + elv_rb_del(&bfqq->sort_list, rq); + + elv_rqhash_del(q, rq); + if (q->last_merge == rq) + q->last_merge = NULL; + + if (RB_EMPTY_ROOT(&bfqq->sort_list)) { + bfqq->next_rq = NULL; + + BUG_ON(bfqq->entity.budget < 0); + + if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) { + BUG_ON(bfqq->ref < 2); /* referred by rq and on tree */ + bfq_del_bfqq_busy(bfqd, bfqq, false); + /* + * bfqq emptied. In normal operation, when + * bfqq is empty, bfqq->entity.service and + * bfqq->entity.budget must contain, + * respectively, the service received and the + * budget used last time bfqq emptied. These + * facts do not hold in this case, as at least + * this last removal occurred while bfqq is + * not in service. To avoid inconsistencies, + * reset both bfqq->entity.service and + * bfqq->entity.budget, if bfqq has still a + * process that may issue I/O requests to it. + */ + bfqq->entity.budget = bfqq->entity.service = 0; + } + + /* + * Remove queue from request-position tree as it is empty. + */ + if (bfqq->pos_root) { + rb_erase(&bfqq->pos_node, bfqq->pos_root); + bfqq->pos_root = NULL; + } + } else { + BUG_ON(!bfqq->next_rq); + bfq_pos_tree_add_move(bfqd, bfqq); + } + + if (rq->cmd_flags & REQ_META) { + BUG_ON(bfqq->meta_pending == 0); + bfqq->meta_pending--; + } +} + +static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio) +{ + struct request_queue *q = hctx->queue; + struct bfq_data *bfqd = q->elevator->elevator_data; + struct request *free = NULL; + /* + * bfq_bic_lookup grabs the queue_lock: invoke it now and + * store its return value for later use, to avoid nesting + * queue_lock inside the bfqd->lock. We assume that the bic + * returned by bfq_bic_lookup does not go away before + * bfqd->lock is taken. + */ + struct bfq_io_cq *bic = bfq_bic_lookup(bfqd, current->io_context, q); + bool ret; + + spin_lock_irq(&bfqd->lock); + + if (bic) + bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf)); + else + bfqd->bio_bfqq = NULL; + bfqd->bio_bic = bic; + /* Set next flag just for testing purposes */ + bfqd->bio_bfqq_set = true; + + ret = blk_mq_sched_try_merge(q, bio, &free); + + /* + * XXX Not yet freeing without lock held, to avoid an + * inconsistency with respect to the lock-protected invocation + * of blk_mq_sched_try_insert_merge in bfq_bio_merge. Waiting + * for clarifications from Jens. + */ + if (free) + blk_mq_free_request(free); + bfqd->bio_bfqq_set = false; + spin_unlock_irq(&bfqd->lock); + + return ret; +} + +static int bfq_request_merge(struct request_queue *q, struct request **req, + struct bio *bio) +{ + struct bfq_data *bfqd = q->elevator->elevator_data; + struct request *__rq; + + __rq = bfq_find_rq_fmerge(bfqd, bio, q); + if (__rq && elv_bio_merge_ok(__rq, bio)) { + *req = __rq; + bfq_log(bfqd, "req %p", __rq); + + return ELEVATOR_FRONT_MERGE; + } + + return ELEVATOR_NO_MERGE; +} + +static struct bfq_queue *bfq_init_rq(struct request *rq); + +static void bfq_request_merged(struct request_queue *q, struct request *req, + enum elv_merge type) +{ + BUG_ON(req->rq_flags & RQF_DISP_LIST); + + if (type == ELEVATOR_FRONT_MERGE && + rb_prev(&req->rb_node) && + blk_rq_pos(req) < + blk_rq_pos(container_of(rb_prev(&req->rb_node), + struct request, rb_node))) { + struct bfq_queue *bfqq = bfq_init_rq(req); + struct bfq_data *bfqd = bfqq->bfqd; + struct request *prev, *next_rq; + + /* Reposition request in its sort_list */ + elv_rb_del(&bfqq->sort_list, req); + BUG_ON(!RQ_BFQQ(req)); + BUG_ON(RQ_BFQQ(req) != bfqq); + elv_rb_add(&bfqq->sort_list, req); + + /* Choose next request to be served for bfqq */ + prev = bfqq->next_rq; + next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req, + bfqd->last_position); + BUG_ON(!next_rq); + + bfqq->next_rq = next_rq; + + bfq_log_bfqq(bfqd, bfqq, + "req %p prev %p next_rq %p bfqq %p", + req, prev, next_rq, bfqq); + + /* + * If next_rq changes, update both the queue's budget to + * fit the new request and the queue's position in its + * rq_pos_tree. + */ + if (prev != bfqq->next_rq) { + bfq_updated_next_req(bfqd, bfqq); + bfq_pos_tree_add_move(bfqd, bfqq); + } + } +} + +/* + * This function is called to notify the scheduler that the requests + * rq and 'next' have been merged, with 'next' going away. BFQ + * exploits this hook to address the following issue: if 'next' has a + * fifo_time lower that rq, then the fifo_time of rq must be set to + * the value of 'next', to not forget the greater age of 'next'. + * + * NOTE: in this function we assume that rq is in a bfq_queue, basing + * on that rq is picked from the hash table q->elevator->hash, which, + * in its turn, is filled only with I/O requests present in + * bfq_queues, while BFQ is in use for the request queue q. In fact, + * the function that fills this hash table (elv_rqhash_add) is called + * only by bfq_insert_request. + */ +static void bfq_requests_merged(struct request_queue *q, struct request *rq, + struct request *next) +{ + struct bfq_queue *bfqq = bfq_init_rq(rq), + *next_bfqq = bfq_init_rq(next); + + BUG_ON(!RQ_BFQQ(rq)); + BUG_ON(!RQ_BFQQ(next)); /* this does not imply next is in a bfqq */ + BUG_ON(rq->rq_flags & RQF_DISP_LIST); + BUG_ON(next->rq_flags & RQF_DISP_LIST); + + lockdep_assert_held(&bfqq->bfqd->lock); + + bfq_log_bfqq(bfqq->bfqd, bfqq, + "rq %p next %p bfqq %p next_bfqq %p", + rq, next, bfqq, next_bfqq); + + /* + * If next and rq belong to the same bfq_queue and next is older + * than rq, then reposition rq in the fifo (by substituting next + * with rq). Otherwise, if next and rq belong to different + * bfq_queues, never reposition rq: in fact, we would have to + * reposition it with respect to next's position in its own fifo, + * which would most certainly be too expensive with respect to + * the benefits. + */ + if (bfqq == next_bfqq && + !list_empty(&rq->queuelist) && !list_empty(&next->queuelist) && + next->fifo_time < rq->fifo_time) { + list_del_init(&rq->queuelist); + list_replace_init(&next->queuelist, &rq->queuelist); + rq->fifo_time = next->fifo_time; + } + + if (bfqq->next_rq == next) + bfqq->next_rq = rq; + + bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags); +} + +/* Must be called with bfqq != NULL */ +static void bfq_bfqq_end_wr(struct bfq_queue *bfqq) +{ + BUG_ON(!bfqq); + + if (bfq_bfqq_busy(bfqq)) { + bfqq->bfqd->wr_busy_queues--; + BUG_ON(bfqq->bfqd->wr_busy_queues < 0); + } + bfqq->wr_coeff = 1; + bfqq->wr_cur_max_time = 0; + bfqq->last_wr_start_finish = jiffies; + /* + * Trigger a weight change on the next invocation of + * __bfq_entity_update_weight_prio. + */ + bfqq->entity.prio_changed = 1; + bfq_log_bfqq(bfqq->bfqd, bfqq, + "wrais ending at %lu, rais_max_time %u", + bfqq->last_wr_start_finish, + jiffies_to_msecs(bfqq->wr_cur_max_time)); + bfq_log_bfqq(bfqq->bfqd, bfqq, "wr_busy %d", + bfqq->bfqd->wr_busy_queues); +} + +static void bfq_end_wr_async_queues(struct bfq_data *bfqd, + struct bfq_group *bfqg) +{ + int i, j; + + for (i = 0; i < 2; i++) + for (j = 0; j < IOPRIO_BE_NR; j++) + if (bfqg->async_bfqq[i][j]) + bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]); + if (bfqg->async_idle_bfqq) + bfq_bfqq_end_wr(bfqg->async_idle_bfqq); +} + +static void bfq_end_wr(struct bfq_data *bfqd) +{ + struct bfq_queue *bfqq; + + spin_lock_irq(&bfqd->lock); + + list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) + bfq_bfqq_end_wr(bfqq); + list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) + bfq_bfqq_end_wr(bfqq); + bfq_end_wr_async(bfqd); + + spin_unlock_irq(&bfqd->lock); +} + +static sector_t bfq_io_struct_pos(void *io_struct, bool request) +{ + if (request) + return blk_rq_pos(io_struct); + else + return ((struct bio *)io_struct)->bi_iter.bi_sector; +} + +static int bfq_rq_close_to_sector(void *io_struct, bool request, + sector_t sector) +{ + return abs(bfq_io_struct_pos(io_struct, request) - sector) <= + BFQQ_CLOSE_THR; +} + +static struct bfq_queue *bfqq_find_close(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + sector_t sector) +{ + struct rb_root *root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree; + struct rb_node *parent, *node; + struct bfq_queue *__bfqq; + + if (RB_EMPTY_ROOT(root)) + return NULL; + + /* + * First, if we find a request starting at the end of the last + * request, choose it. + */ + __bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL); + if (__bfqq) + return __bfqq; + + /* + * If the exact sector wasn't found, the parent of the NULL leaf + * will contain the closest sector (rq_pos_tree sorted by + * next_request position). + */ + __bfqq = rb_entry(parent, struct bfq_queue, pos_node); + if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector)) + return __bfqq; + + if (blk_rq_pos(__bfqq->next_rq) < sector) + node = rb_next(&__bfqq->pos_node); + else + node = rb_prev(&__bfqq->pos_node); + if (!node) + return NULL; + + __bfqq = rb_entry(node, struct bfq_queue, pos_node); + if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector)) + return __bfqq; + + return NULL; +} + +static struct bfq_queue *bfq_find_close_cooperator(struct bfq_data *bfqd, + struct bfq_queue *cur_bfqq, + sector_t sector) +{ + struct bfq_queue *bfqq; + + /* + * We shall notice if some of the queues are cooperating, + * e.g., working closely on the same area of the device. In + * that case, we can group them together and: 1) don't waste + * time idling, and 2) serve the union of their requests in + * the best possible order for throughput. + */ + bfqq = bfqq_find_close(bfqd, cur_bfqq, sector); + if (!bfqq || bfqq == cur_bfqq) + return NULL; + + return bfqq; +} + +static struct bfq_queue * +bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) +{ + int process_refs, new_process_refs; + struct bfq_queue *__bfqq; + + /* + * If there are no process references on the new_bfqq, then it is + * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain + * may have dropped their last reference (not just their last process + * reference). + */ + if (!bfqq_process_refs(new_bfqq)) + return NULL; + + /* Avoid a circular list and skip interim queue merges. */ + while ((__bfqq = new_bfqq->new_bfqq)) { + if (__bfqq == bfqq) + return NULL; + new_bfqq = __bfqq; + } + + process_refs = bfqq_process_refs(bfqq); + new_process_refs = bfqq_process_refs(new_bfqq); + /* + * If the process for the bfqq has gone away, there is no + * sense in merging the queues. + */ + if (process_refs == 0 || new_process_refs == 0) + return NULL; + + bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d", + new_bfqq->pid); + + /* + * Merging is just a redirection: the requests of the process + * owning one of the two queues are redirected to the other queue. + * The latter queue, in its turn, is set as shared if this is the + * 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, 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). + * + * 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; + return new_bfqq; +} + +static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq, + struct bfq_queue *new_bfqq) +{ + if (bfq_too_late_for_merging(new_bfqq)) { + bfq_log_bfqq(bfqq->bfqd, bfqq, + "too late for bfq%d to be merged", + new_bfqq->pid); + return false; + } + + if (bfq_class_idle(bfqq) || bfq_class_idle(new_bfqq) || + (bfqq->ioprio_class != new_bfqq->ioprio_class)) + return false; + + /* + * If either of the queues has already been detected as seeky, + * then merging it with the other queue is unlikely to lead to + * sequential I/O. + */ + if (BFQQ_SEEKY(bfqq) || BFQQ_SEEKY(new_bfqq)) + return false; + + /* + * Interleaved I/O is known to be done by (some) applications + * only for reads, so it does not make sense to merge async + * queues. + */ + if (!bfq_bfqq_sync(bfqq) || !bfq_bfqq_sync(new_bfqq)) + return false; + + return true; +} + +/* + * Attempt to schedule a merge of bfqq with the currently in-service + * queue or with a close queue among the scheduled queues. Return + * NULL if no merge was scheduled, a pointer to the shared bfq_queue + * structure otherwise. + * + * The OOM queue is not allowed to participate to cooperation: in fact, since + * the requests temporarily redirected to the OOM queue could be redirected + * again to dedicated queues at any time, the state needed to correctly + * handle merging with the OOM queue would be quite complex and expensive + * to maintain. Besides, in such a critical condition as an out of memory, + * the benefits of queue merging may be little relevant, or even negligible. + * + * WARNING: queue merging may impair fairness among non-weight raised + * queues, for at least two reasons: 1) the original weight of a + * merged queue may change during the merged state, 2) even being the + * weight the same, a merged queue may be bloated with many more + * requests than the ones produced by its originally-associated + * process. + */ +static struct bfq_queue * +bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, + void *io_struct, bool request) +{ + struct bfq_queue *in_service_bfqq, *new_bfqq; + + /* + * Prevent bfqq from being merged if it has been created too + * long ago. The idea is that true cooperating processes, and + * thus their associated bfq_queues, are supposed to be + * created shortly after each other. This is the case, e.g., + * for KVM/QEMU and dump I/O threads. Basing on this + * assumption, the following filtering greatly reduces the + * probability that two non-cooperating processes, which just + * happen to do close I/O for some short time interval, have + * their queues merged by mistake. + */ + if (bfq_too_late_for_merging(bfqq)) { + bfq_log_bfqq(bfqd, bfqq, + "would have looked for coop, but too late"); + return NULL; + } + + if (bfqq->new_bfqq) + return bfqq->new_bfqq; + + if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq)) + return NULL; + + /* If there is only one backlogged queue, don't search. */ + if (bfq_tot_busy_queues(bfqd) == 1) + return NULL; + + in_service_bfqq = bfqd->in_service_queue; + + if (in_service_bfqq && in_service_bfqq != bfqq && + likely(in_service_bfqq != &bfqd->oom_bfqq) && + bfq_rq_close_to_sector(io_struct, request, bfqd->in_serv_last_pos) && + bfqq->entity.parent == in_service_bfqq->entity.parent && + bfq_may_be_close_cooperator(bfqq, in_service_bfqq)) { + new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq); + if (new_bfqq) + return new_bfqq; + } + /* + * Check whether there is a cooperator among currently scheduled + * queues. The only thing we need is that the bio/request is not + * NULL, as we need it to establish whether a cooperator exists. + */ + new_bfqq = bfq_find_close_cooperator(bfqd, bfqq, + bfq_io_struct_pos(io_struct, request)); + + BUG_ON(new_bfqq && bfqq->entity.parent != new_bfqq->entity.parent); + + if (new_bfqq && likely(new_bfqq != &bfqd->oom_bfqq) && + bfq_may_be_close_cooperator(bfqq, new_bfqq)) + return bfq_setup_merge(bfqq, new_bfqq); + + return NULL; +} + +static void bfq_bfqq_save_state(struct bfq_queue *bfqq) +{ + struct bfq_io_cq *bic = bfqq->bic; + + /* + * If !bfqq->bic, the queue is already shared or its requests + * have already been redirected to a shared queue; both idle window + * and weight raising state have already been saved. Do nothing. + */ + if (!bic) + return; + + bic->saved_ttime = bfqq->ttime; + bic->saved_has_short_ttime = bfq_bfqq_has_short_ttime(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); + if (unlikely(bfq_bfqq_just_created(bfqq) && + !bfq_bfqq_in_large_burst(bfqq) && + bfqq->bfqd->low_latency)) { + /* + * bfqq being merged ritgh after being created: bfqq + * would have deserved interactive weight raising, but + * did not make it to be set in a weight-raised state, + * because of this early merge. Store directly the + * weight-raising state that would have been assigned + * to bfqq, so that to avoid that bfqq unjustly fails + * to enjoy weight raising if split soon. + */ + bic->saved_wr_coeff = bfqq->bfqd->bfq_wr_coeff; + bic->saved_wr_cur_max_time = bfq_wr_duration(bfqq->bfqd); + bic->saved_last_wr_start_finish = jiffies; + } else { + 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; + } + BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish)); + bfq_log_bfqq(bfqq->bfqd, bfqq, + "bic %p wr_coeff %d start_finish %lu max_time %lu", + bic, bfqq->wr_coeff, bfqq->last_wr_start_finish, + bfqq->wr_cur_max_time); +} + +static void +bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, + struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) +{ + bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu", + (unsigned long) new_bfqq->pid); + BUG_ON(bfqq->bic && bfqq->bic == new_bfqq->bic); + /* Save weight raising and idle window of the merged queues */ + bfq_bfqq_save_state(bfqq); + bfq_bfqq_save_state(new_bfqq); + + if (bfq_bfqq_IO_bound(bfqq)) + bfq_mark_bfqq_IO_bound(new_bfqq); + bfq_clear_bfqq_IO_bound(bfqq); + + /* + * If bfqq is weight-raised, then let new_bfqq inherit + * weight-raising. To reduce false positives, neglect the case + * 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). 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; + new_bfqq->wr_cur_max_time = bfqq->wr_cur_max_time; + new_bfqq->last_wr_start_finish = bfqq->last_wr_start_finish; + new_bfqq->wr_start_at_switch_to_srt = + bfqq->wr_start_at_switch_to_srt; + if (bfq_bfqq_busy(new_bfqq)) { + bfqd->wr_busy_queues++; + BUG_ON(bfqd->wr_busy_queues > + bfq_tot_busy_queues(bfqd)); + } + + new_bfqq->entity.prio_changed = 1; + bfq_log_bfqq(bfqd, new_bfqq, + "wr start after merge with %d, rais_max_time %u", + bfqq->pid, + jiffies_to_msecs(bfqq->wr_cur_max_time)); + } + + if (bfqq->wr_coeff > 1) { /* bfqq has given its wr to new_bfqq */ + bfqq->wr_coeff = 1; + bfqq->entity.prio_changed = 1; + if (bfq_bfqq_busy(bfqq)) { + bfqd->wr_busy_queues--; + BUG_ON(bfqd->wr_busy_queues < 0); + } + + } + + bfq_log_bfqq(bfqd, new_bfqq, "wr_busy %d", + bfqd->wr_busy_queues); + + /* + * Merge queues (that is, let bic redirect its requests to new_bfqq) + */ + bic_set_bfqq(bic, new_bfqq, 1); + bfq_mark_bfqq_coop(new_bfqq); + /* + * new_bfqq now belongs to at least two bics (it is a shared queue): + * set new_bfqq->bic to NULL. bfqq either: + * - does not belong to any bic any more, and hence bfqq->bic must + * be set to NULL, or + * - is a queue whose owning bics have already been redirected to a + * different queue, hence the queue is destined to not belong to + * any bic soon and bfqq->bic is already NULL (therefore the next + * assignment causes no harm). + */ + new_bfqq->bic = NULL; + bfqq->bic = NULL; + /* release process reference to bfqq */ + bfq_put_queue(bfqq); +} + +static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq, + struct bio *bio) +{ + struct bfq_data *bfqd = q->elevator->elevator_data; + bool is_sync = op_is_sync(bio->bi_opf); + struct bfq_queue *bfqq = bfqd->bio_bfqq, *new_bfqq; + + assert_spin_locked(&bfqd->lock); + /* + * Disallow merge of a sync bio into an async request. + */ + if (is_sync && !rq_is_sync(rq)) + return false; + + /* + * Lookup the bfqq that this bio will be queued with. Allow + * merge only if rq is queued there. + */ + BUG_ON(!bfqd->bio_bfqq_set); + if (!bfqq) + return false; + + /* + * We take advantage of this function to perform an early merge + * of the queues of possible cooperating processes. + */ + new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false); + BUG_ON(new_bfqq == bfqq); + if (new_bfqq) { + /* + * bic still points to bfqq, then it has not yet been + * redirected to some other bfq_queue, and a queue + * merge beween bfqq and new_bfqq can be safely + * fulfillled, i.e., bic can be redirected to new_bfqq + * and bfqq can be put. + */ + bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq, + new_bfqq); + /* + * If we get here, bio will be queued into new_queue, + * so use new_bfqq to decide whether bio and rq can be + * merged. + */ + bfqq = new_bfqq; + + /* + * Change also bqfd->bio_bfqq, as + * bfqd->bio_bic now points to new_bfqq, and + * this function may be invoked again (and then may + * use again bqfd->bio_bfqq). + */ + bfqd->bio_bfqq = bfqq; + } + return bfqq == RQ_BFQQ(rq); +} + +/* + * Set the maximum time for the in-service queue to consume its + * budget. This prevents seeky processes from lowering the throughput. + * In practice, a time-slice service scheme is used with seeky + * processes. + */ +static void bfq_set_budget_timeout(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + unsigned int timeout_coeff; + + if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time) + timeout_coeff = 1; + else + timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight; + + bfqd->last_budget_start = ktime_get(); + + bfqq->budget_timeout = jiffies + + bfqd->bfq_timeout * timeout_coeff; + + bfq_log_bfqq(bfqd, bfqq, "%u", + jiffies_to_msecs(bfqd->bfq_timeout * timeout_coeff)); +} + +static void __bfq_set_in_service_queue(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + if (bfqq) { + bfq_clear_bfqq_fifo_expire(bfqq); + + bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8; + + BUG_ON(bfqq == bfqd->in_service_queue); + BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list)); + + if (time_is_before_jiffies(bfqq->last_wr_start_finish) && + bfqq->wr_coeff > 1 && + bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time && + time_is_before_jiffies(bfqq->budget_timeout)) { + /* + * For soft real-time queues, move the start + * of the weight-raising period forward by the + * time the queue has not received any + * service. Otherwise, a relatively long + * service delay is likely to cause the + * weight-raising period of the queue to end, + * because of the short duration of the + * weight-raising period of a soft real-time + * queue. It is worth noting that this move + * is not so dangerous for the other queues, + * because soft real-time queues are not + * greedy. + * + * To not add a further variable, we use the + * overloaded field budget_timeout to + * determine for how long the queue has not + * received service, i.e., how much time has + * elapsed since the queue expired. However, + * this is a little imprecise, because + * budget_timeout is set to jiffies if bfqq + * not only expires, but also remains with no + * request. + */ + if (time_after(bfqq->budget_timeout, + bfqq->last_wr_start_finish)) + bfqq->last_wr_start_finish += + jiffies - bfqq->budget_timeout; + else + bfqq->last_wr_start_finish = jiffies; + + if (time_is_after_jiffies(bfqq->last_wr_start_finish)) { + pr_crit( + "BFQ WARNING:last %lu budget %lu jiffies %lu", + bfqq->last_wr_start_finish, + bfqq->budget_timeout, + jiffies); + pr_crit("diff %lu", jiffies - + max_t(unsigned long, + bfqq->last_wr_start_finish, + bfqq->budget_timeout)); + bfqq->last_wr_start_finish = jiffies; + } + } + + bfq_set_budget_timeout(bfqd, bfqq); + bfq_log_bfqq(bfqd, bfqq, + "cur-budget = %d prio_class %d", + bfqq->entity.budget, bfqq->ioprio_class); + } else + bfq_log(bfqd, "NULL"); + + bfqd->in_service_queue = bfqq; +} + +/* + * Get and set a new queue for service. + */ +static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd) +{ + struct bfq_queue *bfqq = bfq_get_next_queue(bfqd); + + __bfq_set_in_service_queue(bfqd, bfqq); + return bfqq; +} + +static void bfq_arm_slice_timer(struct bfq_data *bfqd) +{ + struct bfq_queue *bfqq = bfqd->in_service_queue; + u32 sl; + + BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list)); + + bfq_mark_bfqq_wait_request(bfqq); + + /* + * We don't want to idle for seeks, but we do want to allow + * fair distribution of slice time for a process doing back-to-back + * seeks. So allow a little bit of time for him to submit a new rq. + * + * To prevent processes with (partly) seeky workloads from + * being too ill-treated, grant them a small fraction of the + * assigned budget before reducing the waiting time to + * BFQ_MIN_TT. This happened to help reduce latency. + */ + sl = bfqd->bfq_slice_idle; + /* + * 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 asymemtric 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(u32, sl, BFQ_MIN_TT); + + bfqd->last_idling_start = ktime_get(); + hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl), + HRTIMER_MODE_REL); + bfqg_stats_set_start_idle_time(bfqq_group(bfqq)); + bfq_log(bfqd, "arm idle: %ld/%ld ms", + sl / NSEC_PER_MSEC, bfqd->bfq_slice_idle / NSEC_PER_MSEC); +} + +/* + * In autotuning mode, max_budget is dynamically recomputed as the + * amount of sectors transferred in timeout at the estimated peak + * rate. This enables BFQ to utilize a full timeslice with a full + * budget, even if the in-service queue is served at peak rate. And + * this maximises throughput with sequential workloads. + */ +static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd) +{ + return (u64)bfqd->peak_rate * USEC_PER_MSEC * + jiffies_to_msecs(bfqd->bfq_timeout)>>BFQ_RATE_SHIFT; +} + +/* + * Update parameters related to throughput and responsiveness, as a + * function of the estimated peak rate. See comments on + * bfq_calc_max_budget(), and on the ref_wr_duration array. + */ +static void update_thr_responsiveness_params(struct bfq_data *bfqd) +{ + if (bfqd->bfq_user_max_budget == 0) { + bfqd->bfq_max_budget = + bfq_calc_max_budget(bfqd); + BUG_ON(bfqd->bfq_max_budget < 0); + bfq_log(bfqd, "new max_budget = %d", + bfqd->bfq_max_budget); + } +} + +static void bfq_reset_rate_computation(struct bfq_data *bfqd, struct request *rq) +{ + if (rq != NULL) { /* new rq dispatch now, reset accordingly */ + bfqd->last_dispatch = bfqd->first_dispatch = ktime_get_ns() ; + bfqd->peak_rate_samples = 1; + bfqd->sequential_samples = 0; + bfqd->tot_sectors_dispatched = bfqd->last_rq_max_size = + blk_rq_sectors(rq); + } else /* no new rq dispatched, just reset the number of samples */ + bfqd->peak_rate_samples = 0; /* full re-init on next disp. */ + + bfq_log(bfqd, + "at end, sample %u/%u tot_sects %llu", + bfqd->peak_rate_samples, bfqd->sequential_samples, + bfqd->tot_sectors_dispatched); +} + +static void bfq_update_rate_reset(struct bfq_data *bfqd, struct request *rq) +{ + u32 rate, weight, divisor; + + /* + * For the convergence property to hold (see comments on + * bfq_update_peak_rate()) and for the assessment to be + * reliable, a minimum number of samples must be present, and + * a minimum amount of time must have elapsed. If not so, do + * not compute new rate. Just reset parameters, to get ready + * for a new evaluation attempt. + */ + if (bfqd->peak_rate_samples < BFQ_RATE_MIN_SAMPLES || + bfqd->delta_from_first < BFQ_RATE_MIN_INTERVAL) { + bfq_log(bfqd, + "only resetting, delta_first %lluus samples %d", + bfqd->delta_from_first>>10, bfqd->peak_rate_samples); + goto reset_computation; + } + + /* + * If a new request completion has occurred after last + * dispatch, then, to approximate the rate at which requests + * have been served by the device, it is more precise to + * extend the observation interval to the last completion. + */ + bfqd->delta_from_first = + max_t(u64, bfqd->delta_from_first, + bfqd->last_completion - bfqd->first_dispatch); + + BUG_ON(bfqd->delta_from_first == 0); + /* + * Rate computed in sects/usec, and not sects/nsec, for + * precision issues. + */ + rate = div64_ul(bfqd->tot_sectors_dispatched<delta_from_first, NSEC_PER_USEC)); + + bfq_log(bfqd, +"tot_sects %llu delta_first %lluus rate %llu sects/s (%d)", + bfqd->tot_sectors_dispatched, bfqd->delta_from_first>>10, + ((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT), + rate > 20< 20M sectors/sec) + */ + if ((bfqd->sequential_samples < (3 * bfqd->peak_rate_samples)>>2 && + rate <= bfqd->peak_rate) || + rate > 20<peak_rate_samples, bfqd->sequential_samples, + ((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT), + ((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT)); + goto reset_computation; + } else { + bfq_log(bfqd, + "do update, samples %u/%u rate/peak %llu/%llu", + bfqd->peak_rate_samples, bfqd->sequential_samples, + ((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT), + ((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT)); + } + + /* + * We have to update the peak rate, at last! To this purpose, + * we use a low-pass filter. We compute the smoothing constant + * of the filter as a function of the 'weight' of the new + * measured rate. + * + * As can be seen in next formulas, we define this weight as a + * quantity proportional to how sequential the workload is, + * and to how long the observation time interval is. + * + * The weight runs from 0 to 8. The maximum value of the + * weight, 8, yields the minimum value for the smoothing + * constant. At this minimum value for the smoothing constant, + * the measured rate contributes for half of the next value of + * the estimated peak rate. + * + * So, the first step is to compute the weight as a function + * of how sequential the workload is. Note that the weight + * cannot reach 9, because bfqd->sequential_samples cannot + * become equal to bfqd->peak_rate_samples, which, in its + * turn, holds true because bfqd->sequential_samples is not + * incremented for the first sample. + */ + weight = (9 * bfqd->sequential_samples) / bfqd->peak_rate_samples; + + /* + * Second step: further refine the weight as a function of the + * duration of the observation interval. + */ + weight = min_t(u32, 8, + div_u64(weight * bfqd->delta_from_first, + BFQ_RATE_REF_INTERVAL)); + + /* + * Divisor ranging from 10, for minimum weight, to 2, for + * maximum weight. + */ + divisor = 10 - weight; + BUG_ON(divisor == 0); + + /* + * Finally, update peak rate: + * + * peak_rate = peak_rate * (divisor-1) / divisor + rate / divisor + */ + bfqd->peak_rate *= divisor-1; + bfqd->peak_rate /= divisor; + rate /= divisor; /* smoothing constant alpha = 1/divisor */ + + bfq_log(bfqd, + "divisor %d tmp_peak_rate %llu tmp_rate %u", + divisor, + ((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT), + (u32)((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT)); + + BUG_ON(bfqd->peak_rate == 0); + BUG_ON(bfqd->peak_rate > 20<peak_rate += rate; + + /* + * For a very slow device, bfqd->peak_rate can reach 0 (see + * the minimum representable values reported in the comments + * on BFQ_RATE_SHIFT). Push to 1 if this happens, to avoid + * divisions by zero where bfqd->peak_rate is used as a + * divisor. + */ + bfqd->peak_rate = max_t(u32, 1, bfqd->peak_rate); + + update_thr_responsiveness_params(bfqd); + BUG_ON(bfqd->peak_rate > 20<peak_rate_samples == 0) { /* first dispatch */ + bfq_log(bfqd, + "goto reset, samples %d", + bfqd->peak_rate_samples) ; + bfq_reset_rate_computation(bfqd, rq); + goto update_last_values; /* will add one sample */ + } + + /* + * Device idle for very long: the observation interval lasting + * up to this dispatch cannot be a valid observation interval + * for computing a new peak rate (similarly to the late- + * completion event in bfq_completed_request()). Go to + * update_rate_and_reset to have the following three steps + * taken: + * - close the observation interval at the last (previous) + * request dispatch or completion + * - compute rate, if possible, for that observation interval + * - start a new observation interval with this dispatch + */ + if (now_ns - bfqd->last_dispatch > 100*NSEC_PER_MSEC && + bfqd->rq_in_driver == 0) { + bfq_log(bfqd, +"jumping to updating&resetting delta_last %lluus samples %d", + (now_ns - bfqd->last_dispatch)>>10, + bfqd->peak_rate_samples) ; + goto update_rate_and_reset; + } + + /* Update sampling information */ + bfqd->peak_rate_samples++; + + if ((bfqd->rq_in_driver > 0 || + now_ns - bfqd->last_completion < BFQ_MIN_TT) + && !BFQ_RQ_SEEKY(bfqd, bfqd->last_position, rq)) + bfqd->sequential_samples++; + + bfqd->tot_sectors_dispatched += blk_rq_sectors(rq); + + /* Reset max observed rq size every 32 dispatches */ + if (likely(bfqd->peak_rate_samples % 32)) + bfqd->last_rq_max_size = + max_t(u32, blk_rq_sectors(rq), bfqd->last_rq_max_size); + else + bfqd->last_rq_max_size = blk_rq_sectors(rq); + + bfqd->delta_from_first = now_ns - bfqd->first_dispatch; + + bfq_log(bfqd, + "added samples %u/%u tot_sects %llu delta_first %lluus", + bfqd->peak_rate_samples, bfqd->sequential_samples, + bfqd->tot_sectors_dispatched, + bfqd->delta_from_first>>10); + + /* Target observation interval not yet reached, go on sampling */ + if (bfqd->delta_from_first < BFQ_RATE_REF_INTERVAL) + goto update_last_values; + +update_rate_and_reset: + bfq_update_rate_reset(bfqd, rq); +update_last_values: + bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq); + if (RQ_BFQQ(rq) == bfqd->in_service_queue) + bfqd->in_serv_last_pos = bfqd->last_position; + bfqd->last_dispatch = now_ns; + + bfq_log(bfqd, + "delta_first %lluus last_pos %llu peak_rate %llu", + (now_ns - bfqd->first_dispatch)>>10, + (unsigned long long) bfqd->last_position, + ((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT)); + bfq_log(bfqd, + "samples at end %d", bfqd->peak_rate_samples); +} + +/* + * Remove request from internal lists. + */ +static void bfq_dispatch_remove(struct request_queue *q, struct request *rq) +{ + struct bfq_queue *bfqq = RQ_BFQQ(rq); + + /* + * For consistency, the next instruction should have been + * executed after removing the request from the queue and + * dispatching it. We execute instead this instruction before + * bfq_remove_request() (and hence introduce a temporary + * inconsistency), for efficiency. In fact, should this + * dispatch occur for a non in-service bfqq, this anticipated + * increment prevents two counters related to bfqq->dispatched + * from risking to be, first, uselessly decremented, and then + * incremented again when the (new) value of bfqq->dispatched + * happens to be taken into account. + */ + bfqq->dispatched++; + bfq_update_peak_rate(q->elevator->elevator_data, rq); + + bfq_remove_request(q, rq); +} + +static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq) +{ + BUG_ON(bfqq != bfqd->in_service_queue); + + /* + * If this bfqq is shared between multiple processes, check + * to make sure that those processes are still issuing I/Os + * within the mean seek distance. If not, it may be time to + * break the queues apart again. + */ + if (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq)) + bfq_mark_bfqq_split_coop(bfqq); + + if (RB_EMPTY_ROOT(&bfqq->sort_list)) { + if (bfqq->dispatched == 0) + /* + * Overloading budget_timeout field to store + * the time at which the queue remains with no + * backlog and no outstanding request; used by + * the weight-raising mechanism. + */ + bfqq->budget_timeout = jiffies; + + bfq_del_bfqq_busy(bfqd, bfqq, true); + } else { + bfq_requeue_bfqq(bfqd, bfqq, true); + /* + * Resort priority tree of potential close cooperators. + */ + bfq_pos_tree_add_move(bfqd, bfqq); + } + + /* + * All in-service entities must have been properly deactivated + * or requeued before executing the next function, which + * resets all in-service entites as no more in service. + */ + __bfq_bfqd_reset_in_service(bfqd); +} + +/** + * __bfq_bfqq_recalc_budget - try to adapt the budget to the @bfqq behavior. + * @bfqd: device data. + * @bfqq: queue to update. + * @reason: reason for expiration. + * + * Handle the feedback on @bfqq budget at queue expiration. + * See the body for detailed comments. + */ +static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + enum bfqq_expiration reason) +{ + struct request *next_rq; + int budget, min_budget; + + BUG_ON(bfqq != bfqd->in_service_queue); + + min_budget = bfq_min_budget(bfqd); + + if (bfqq->wr_coeff == 1) + budget = bfqq->max_budget; + else /* + * Use a constant, low budget for weight-raised queues, + * to help achieve a low latency. Keep it slightly higher + * than the minimum possible budget, to cause a little + * bit fewer expirations. + */ + budget = 2 * min_budget; + + bfq_log_bfqq(bfqd, bfqq, "last budg %d, budg left %d", + bfqq->entity.budget, bfq_bfqq_budget_left(bfqq)); + bfq_log_bfqq(bfqd, bfqq, "last max_budg %d, min budg %d", + budget, bfq_min_budget(bfqd)); + bfq_log_bfqq(bfqd, bfqq, "sync %d, seeky %d", + bfq_bfqq_sync(bfqq), BFQQ_SEEKY(bfqd->in_service_queue)); + + if (bfq_bfqq_sync(bfqq) && bfqq->wr_coeff == 1) { + switch (reason) { + /* + * Caveat: in all the following cases we trade latency + * for throughput. + */ + case BFQ_BFQQ_TOO_IDLE: + /* + * This is the only case where we may reduce + * the budget: if there is no request of the + * process still waiting for completion, then + * we assume (tentatively) that the timer has + * expired because the batch of requests of + * the process could have been served with a + * smaller budget. Hence, betting that + * process will behave in the same way when it + * becomes backlogged again, we reduce its + * next budget. As long as we guess right, + * this budget cut reduces the latency + * experienced by the process. + * + * However, if there are still outstanding + * requests, then the process may have not yet + * issued its next request just because it is + * still waiting for the completion of some of + * the still outstanding ones. So in this + * subcase we do not reduce its budget, on the + * contrary we increase it to possibly boost + * the throughput, as discussed in the + * comments to the BUDGET_TIMEOUT case. + */ + if (bfqq->dispatched > 0) /* still outstanding reqs */ + budget = min(budget * 2, bfqd->bfq_max_budget); + else { + if (budget > 5 * min_budget) + budget -= 4 * min_budget; + else + budget = min_budget; + } + break; + case BFQ_BFQQ_BUDGET_TIMEOUT: + /* + * We double the budget here because it gives + * the chance to boost the throughput if this + * is not a seeky process (and has bumped into + * this timeout because of, e.g., ZBR). + */ + budget = min(budget * 2, bfqd->bfq_max_budget); + break; + case BFQ_BFQQ_BUDGET_EXHAUSTED: + /* + * The process still has backlog, and did not + * let either the budget timeout or the disk + * idling timeout expire. Hence it is not + * seeky, has a short thinktime and may be + * happy with a higher budget too. So + * definitely increase the budget of this good + * candidate to boost the disk throughput. + */ + budget = min(budget * 4, bfqd->bfq_max_budget); + break; + case BFQ_BFQQ_NO_MORE_REQUESTS: + /* + * For queues that expire for this reason, it + * is particularly important to keep the + * budget close to the actual service they + * need. Doing so reduces the timestamp + * misalignment problem described in the + * comments in the body of + * __bfq_activate_entity. In fact, suppose + * that a queue systematically expires for + * BFQ_BFQQ_NO_MORE_REQUESTS and presents a + * new request in time to enjoy timestamp + * back-shifting. The larger the budget of the + * queue is with respect to the service the + * queue actually requests in each service + * slot, the more times the queue can be + * reactivated with the same virtual finish + * time. It follows that, even if this finish + * time is pushed to the system virtual time + * to reduce the consequent timestamp + * misalignment, the queue unjustly enjoys for + * many re-activations a lower finish time + * than all newly activated queues. + * + * The service needed by bfqq is measured + * quite precisely by bfqq->entity.service. + * Since bfqq does not enjoy device idling, + * bfqq->entity.service is equal to the number + * of sectors that the process associated with + * bfqq requested to read/write before waiting + * for request completions, or blocking for + * other reasons. + */ + budget = max_t(int, bfqq->entity.service, min_budget); + break; + default: + return; + } + } else if (!bfq_bfqq_sync(bfqq)) + /* + * Async queues get always the maximum possible + * budget, as for them we do not care about latency + * (in addition, their ability to dispatch is limited + * by the charging factor). + */ + budget = bfqd->bfq_max_budget; + + bfqq->max_budget = budget; + + if (bfqd->budgets_assigned >= bfq_stats_min_budgets && + !bfqd->bfq_user_max_budget) + bfqq->max_budget = min(bfqq->max_budget, bfqd->bfq_max_budget); + + /* + * If there is still backlog, then assign a new budget, making + * sure that it is large enough for the next request. Since + * the finish time of bfqq must be kept in sync with the + * budget, be sure to call __bfq_bfqq_expire() *after* this + * update. + * + * If there is no backlog, then no need to update the budget; + * it will be updated on the arrival of a new request. + */ + next_rq = bfqq->next_rq; + if (next_rq) { + BUG_ON(reason == BFQ_BFQQ_TOO_IDLE || + reason == BFQ_BFQQ_NO_MORE_REQUESTS); + bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget, + bfq_serv_to_charge(next_rq, bfqq)); + BUG_ON(!bfq_bfqq_busy(bfqq)); + BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list)); + } + + bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %d", + next_rq ? blk_rq_sectors(next_rq) : 0, + bfqq->entity.budget); +} + +/* + * Return true if the process associated with bfqq is "slow". The slow + * flag is used, in addition to the budget timeout, to reduce the + * amount of service provided to seeky processes, and thus reduce + * their chances to lower the throughput. More details in the comments + * on the function bfq_bfqq_expire(). + * + * An important observation is in order: as discussed in the comments + * on the function bfq_update_peak_rate(), with devices with internal + * queues, it is hard if ever possible to know when and for how long + * an I/O request is processed by the device (apart from the trivial + * I/O pattern where a new request is dispatched only after the + * previous one has been completed). This makes it hard to evaluate + * the real rate at which the I/O requests of each bfq_queue are + * served. In fact, for an I/O scheduler like BFQ, serving a + * bfq_queue means just dispatching its requests during its service + * slot (i.e., until the budget of the queue is exhausted, or the + * queue remains idle, or, finally, a timeout fires). But, during the + * service slot of a bfq_queue, around 100 ms at most, the device may + * be even still processing requests of bfq_queues served in previous + * service slots. On the opposite end, the requests of the in-service + * bfq_queue may be completed after the service slot of the queue + * finishes. + * + * Anyway, unless more sophisticated solutions are used + * (where possible), the sum of the sizes of the requests dispatched + * during the service slot of a bfq_queue is probably the only + * approximation available for the service received by the bfq_queue + * during its service slot. And this sum is the quantity used in this + * function to evaluate the I/O speed of a process. + */ +static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq, + bool compensate, enum bfqq_expiration reason, + unsigned long *delta_ms) +{ + ktime_t delta_ktime; + u32 delta_usecs; + bool slow = BFQQ_SEEKY(bfqq); /* if delta too short, use seekyness */ + + if (!bfq_bfqq_sync(bfqq)) + return false; + + if (compensate) + delta_ktime = bfqd->last_idling_start; + else + delta_ktime = ktime_get(); + delta_ktime = ktime_sub(delta_ktime, bfqd->last_budget_start); + delta_usecs = ktime_to_us(delta_ktime); + + /* don't use too short time intervals */ + if (delta_usecs < 1000) { + if (blk_queue_nonrot(bfqd->queue)) + /* + * give same worst-case guarantees as idling + * for seeky + */ + *delta_ms = BFQ_MIN_TT / NSEC_PER_MSEC; + else /* charge at least one seek */ + *delta_ms = bfq_slice_idle / NSEC_PER_MSEC; + + bfq_log(bfqd, "too short %u", delta_usecs); + + return slow; + } + + *delta_ms = delta_usecs / USEC_PER_MSEC; + + /* + * Use only long (> 20ms) intervals to filter out excessive + * spikes in service rate estimation. + */ + if (delta_usecs > 20000) { + /* + * Caveat for rotational devices: processes doing I/O + * in the slower disk zones tend to be slow(er) even + * if not seeky. In this respect, the estimated peak + * rate is likely to be an average over the disk + * surface. Accordingly, to not be too harsh with + * unlucky processes, a process is deemed slow only if + * its rate has been lower than half of the estimated + * peak rate. + */ + slow = bfqq->entity.service < bfqd->bfq_max_budget / 2; + bfq_log(bfqd, "relative rate %d/%d", + bfqq->entity.service, bfqd->bfq_max_budget); + } + + bfq_log_bfqq(bfqd, bfqq, "slow %d", slow); + + return slow; +} + +/* + * To be deemed as soft real-time, an application must meet two + * requirements. First, the application must not require an average + * bandwidth higher than the approximate bandwidth required to playback or + * record a compressed high-definition video. + * The next function is invoked on the completion of the last request of a + * batch, to compute the next-start time instant, soft_rt_next_start, such + * that, if the next request of the application does not arrive before + * soft_rt_next_start, then the above requirement on the bandwidth is met. + * + * The second requirement is that the request pattern of the application is + * isochronous, i.e., that, after issuing a request or a batch of requests, + * the application stops issuing new requests until all its pending requests + * have been completed. After that, the application may issue a new batch, + * and so on. + * For this reason the next function is invoked to compute + * soft_rt_next_start only for applications that meet this requirement, + * whereas soft_rt_next_start is set to infinity for applications that do + * not. + * + * Unfortunately, even a greedy (i.e., I/O-bound) application may + * happen to meet, occasionally or systematically, both the above + * bandwidth and isochrony requirements. This may happen at least in + * the following circumstances. First, if the CPU load is high. The + * application may stop issuing requests while the CPUs are busy + * serving other processes, then restart, then stop again for a while, + * and so on. The other circumstances are related to the storage + * device: the storage device is highly loaded or reaches a low-enough + * throughput with the I/O of the application (e.g., because the I/O + * is random and/or the device is slow). In all these cases, the + * I/O of the application may be simply slowed down enough to meet + * the bandwidth and isochrony requirements. To reduce the probability + * that greedy applications are deemed as soft real-time in these + * corner cases, a further rule is used in the computation of + * soft_rt_next_start: the return value of this function is forced to + * be higher than the maximum between the following two quantities. + * + * (a) Current time plus: (1) the maximum time for which the arrival + * of a request is waited for when a sync queue becomes idle, + * namely bfqd->bfq_slice_idle, and (2) a few extra jiffies. We + * postpone for a moment the reason for adding a few extra + * jiffies; we get back to it after next item (b). Lower-bounding + * the return value of this function with the current time plus + * bfqd->bfq_slice_idle tends to filter out greedy applications, + * because the latter issue their next request as soon as possible + * after the last one has been completed. In contrast, a soft + * real-time application spends some time processing data, after a + * batch of its requests has been completed. + * + * (b) Current value of bfqq->soft_rt_next_start. As pointed out + * above, greedy applications may happen to meet both the + * bandwidth and isochrony requirements under heavy CPU or + * storage-device load. In more detail, in these scenarios, these + * applications happen, only for limited time periods, to do I/O + * slowly enough to meet all the requirements described so far, + * including the filtering in above item (a). These slow-speed + * time intervals are usually interspersed between other time + * intervals during which these applications do I/O at a very high + * speed. Fortunately, exactly because of the high speed of the + * I/O in the high-speed intervals, the values returned by this + * function happen to be so high, near the end of any such + * high-speed interval, to be likely to fall *after* the end of + * the low-speed time interval that follows. These high values are + * stored in bfqq->soft_rt_next_start after each invocation of + * this function. As a consequence, if the last value of + * bfqq->soft_rt_next_start is constantly used to lower-bound the + * next value that this function may return, then, from the very + * beginning of a low-speed interval, bfqq->soft_rt_next_start is + * likely to be constantly kept so high that any I/O request + * issued during the low-speed interval is considered as arriving + * to soon for the application to be deemed as soft + * real-time. Then, in the high-speed interval that follows, the + * application will not be deemed as soft real-time, just because + * it will do I/O at a high speed. And so on. + * + * Getting back to the filtering in item (a), in the following two + * cases this filtering might be easily passed by a greedy + * application, if the reference quantity was just + * bfqd->bfq_slice_idle: + * 1) HZ is so low that the duration of a jiffy is comparable to or + * higher than bfqd->bfq_slice_idle. This happens, e.g., on slow + * devices with HZ=100. The time granularity may be so coarse + * that the approximation, in jiffies, of bfqd->bfq_slice_idle + * is rather lower than the exact value. + * 2) jiffies, instead of increasing at a constant rate, may stop increasing + * for a while, then suddenly 'jump' by several units to recover the lost + * increments. This seems to happen, e.g., inside virtual machines. + * To address this issue, in the filtering in (a) we do not use as a + * reference time interval just bfqd->bfq_slice_idle, but + * bfqd->bfq_slice_idle plus a few jiffies. In particular, we add the + * minimum number of jiffies for which the filter seems to be quite + * precise also in embedded systems and KVM/QEMU virtual machines. + */ +static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + bfq_log_bfqq(bfqd, bfqq, +"service_blkg %lu soft_rate %u sects/sec interval %u", + bfqq->service_from_backlogged, + bfqd->bfq_wr_max_softrt_rate, + jiffies_to_msecs(HZ * bfqq->service_from_backlogged / + bfqd->bfq_wr_max_softrt_rate)); + + return max3(bfqq->soft_rt_next_start, + bfqq->last_idle_bklogged + + HZ * bfqq->service_from_backlogged / + bfqd->bfq_wr_max_softrt_rate, + jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4); +} + +static bool bfq_bfqq_injectable(struct bfq_queue *bfqq) +{ + return BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 && + blk_queue_nonrot(bfqq->bfqd->queue) && + bfqq->bfqd->hw_tag; +} + +/** + * bfq_bfqq_expire - expire a queue. + * @bfqd: device owning the queue. + * @bfqq: the queue to expire. + * @compensate: if true, compensate for the time spent idling. + * @reason: the reason causing the expiration. + * + * If the process associated with bfqq does slow I/O (e.g., because it + * issues random requests), we charge bfqq with the time it has been + * in service instead of the service it has received (see + * bfq_bfqq_charge_time for details on how this goal is achieved). As + * a consequence, bfqq will typically get higher timestamps upon + * reactivation, and hence it will be rescheduled as if it had + * received more service than what it has actually received. In the + * end, bfqq receives less service in proportion to how slowly its + * associated process consumes its budgets (and hence how seriously it + * tends to lower the throughput). In addition, this time-charging + * strategy guarantees time fairness among slow processes. In + * contrast, if the process associated with bfqq is not slow, we + * charge bfqq exactly with the service it has received. + * + * Charging time to the first type of queues and the exact service to + * the other has the effect of using the WF2Q+ policy to schedule the + * 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) +{ + bool slow; + unsigned long delta = 0; + struct bfq_entity *entity = &bfqq->entity; + int ref; + + BUG_ON(bfqq != bfqd->in_service_queue); + + /* + * Check whether the process is slow (see bfq_bfqq_is_slow). + */ + slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta); + + /* + * As above explained, charge slow (typically seeky) and + * timed-out queues with the time and not the service + * received, to favor sequential workloads. + * + * Processes doing I/O in the slower disk zones will tend to + * be slow(er) even if not seeky. Therefore, since the + * estimated peak rate is actually an average over the disk + * surface, these processes may timeout just for bad luck. To + * avoid punishing them, do not charge time to processes that + * succeeded in consuming at least 2/3 of their budget. This + * allows BFQ to preserve enough elasticity to still perform + * bandwidth, and not time, distribution with little unlucky + * or quasi-sequential processes. + */ + if (bfqq->wr_coeff == 1 && + (slow || + (reason == BFQ_BFQQ_BUDGET_TIMEOUT && + bfq_bfqq_budget_left(bfqq) >= entity->budget / 3))) + bfq_bfqq_charge_time(bfqd, bfqq, delta); + + BUG_ON(bfqq->entity.budget < bfqq->entity.service); + + if (reason == BFQ_BFQQ_TOO_IDLE && + entity->service <= 2 * entity->budget / 10) + bfq_clear_bfqq_IO_bound(bfqq); + + if (bfqd->low_latency && bfqq->wr_coeff == 1) + bfqq->last_wr_start_finish = jiffies; + + if (bfqd->low_latency && bfqd->bfq_wr_max_softrt_rate > 0 && + RB_EMPTY_ROOT(&bfqq->sort_list)) { + /* + * If we get here, and there are no outstanding + * requests, then the request pattern is isochronous + * (see the comments on the function + * bfq_bfqq_softrt_next_start()). Thus we can compute + * soft_rt_next_start. And we do it, unless bfqq is in + * interactive weight raising. We do not do it in the + * latter subcase, for the following reason. bfqq may + * be conveying the I/O needed to load a soft + * real-time application. Such an application will + * actually exhibit a soft real-time I/O pattern after + * it finally starts doing its job. But, if + * soft_rt_next_start is computed here for an + * interactive bfqq, and bfqq had received a lot of + * service before remaining with no outstanding + * request (likely to happen on a fast device), then + * soft_rt_next_start would be assigned such a high + * value that, for a very long time, bfqq would be + * prevented from being possibly considered as soft + * real time. + * + * If, instead, the queue still has outstanding + * requests, then we have to wait for the completion + * of all the outstanding requests to discover whether + * the request pattern is actually isochronous. + */ + BUG_ON(bfq_tot_busy_queues(bfqd) < 1); + if (bfqq->dispatched == 0 && + bfqq->wr_coeff != bfqd->bfq_wr_coeff) { + bfqq->soft_rt_next_start = + bfq_bfqq_softrt_next_start(bfqd, bfqq); + bfq_log_bfqq(bfqd, bfqq, "new soft_rt_next %lu", + bfqq->soft_rt_next_start); + } else if (bfqq->dispatched > 0) { + /* + * Schedule an update of soft_rt_next_start to when + * the task may be discovered to be isochronous. + */ + bfq_mark_bfqq_softrt_update(bfqq); + } + } + + bfq_log_bfqq(bfqd, bfqq, + "expire (%s, slow %d, num_disp %d, short %d, weight %d, serv %d/%d)", + reason_name[reason], slow, bfqq->dispatched, + bfq_bfqq_has_short_ttime(bfqq), entity->weight, + entity->service, entity->budget); + + /* + * Increase, decrease or leave budget unchanged according to + * reason. + */ + BUG_ON(bfqq->entity.budget < bfqq->entity.service); + __bfq_bfqq_recalc_budget(bfqd, bfqq, reason); + BUG_ON(bfqq->next_rq == NULL && + bfqq->entity.budget < bfqq->entity.service); + ref = bfqq->ref; + __bfq_bfqq_expire(bfqd, bfqq); + + if (ref == 1) /* bfqq is gone, no more actions on it */ + return; + + BUG_ON(ref > 1 && + !bfq_bfqq_busy(bfqq) && reason == BFQ_BFQQ_BUDGET_EXHAUSTED && + !bfq_class_idle(bfqq)); + + bfqq->injected_service = 0; + + /* mark bfqq as waiting a request only if a bic still points to it */ + if (!bfq_bfqq_busy(bfqq) && + reason != BFQ_BFQQ_BUDGET_TIMEOUT && + reason != BFQ_BFQQ_BUDGET_EXHAUSTED) { + BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list)); + BUG_ON(bfqq->next_rq); + bfq_mark_bfqq_non_blocking_wait_rq(bfqq); + /* + * Not setting service to 0, because, if the next rq + * arrives in time, the queue will go on receiving + * service with this same budget (as if it never expired) + */ + } else { + entity->service = 0; + bfq_log_bfqq(bfqd, bfqq, "resetting service"); + } + + /* + * Reset the received-service counter for every parent entity. + * Differently from what happens with bfqq->entity.service, + * the resetting of this counter never needs to be postponed + * for parent entities. In fact, in case bfqq may have a + * chance to go on being served using the last, partially + * consumed budget, bfqq->entity.service needs to be kept, + * because if bfqq then actually goes on being served using + * the same budget, the last value of bfqq->entity.service is + * needed to properly decrement bfqq->entity.budget by the + * portion already consumed. In contrast, it is not necessary + * to keep entity->service for parent entities too, because + * the bubble up of the new value of bfqq->entity.budget will + * make sure that the budgets of parent entities are correct, + * even in case bfqq and thus parent entities go on receiving + * service with the same budget. + */ + entity = entity->parent; + for_each_entity(entity) + entity->service = 0; +} + +/* + * Budget timeout is not implemented through a dedicated timer, but + * just checked on request arrivals and completions, as well as on + * idle timer expirations. + */ +static bool bfq_bfqq_budget_timeout(struct bfq_queue *bfqq) +{ + return time_is_before_eq_jiffies(bfqq->budget_timeout); +} + +/* + * If we expire a queue that is actively waiting (i.e., with the + * device idled) for the arrival of a new request, then we may incur + * the timestamp misalignment problem described in the body of the + * function __bfq_activate_entity. Hence we return true only if this + * condition does not hold, or if the queue is slow enough to deserve + * only to be kicked off for preserving a high throughput. + */ +static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq) +{ + bfq_log_bfqq(bfqq->bfqd, bfqq, + "wait_request %d left %d timeout %d", + bfq_bfqq_wait_request(bfqq), + bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3, + bfq_bfqq_budget_timeout(bfqq)); + + return (!bfq_bfqq_wait_request(bfqq) || + bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3) + && + bfq_bfqq_budget_timeout(bfqq); +} + +static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + bool rot_without_queueing = + !blk_queue_nonrot(bfqd->queue) && !bfqd->hw_tag, + bfqq_sequential_and_IO_bound, + idling_boosts_thr; + + bfqq_sequential_and_IO_bound = !BFQQ_SEEKY(bfqq) && + bfq_bfqq_IO_bound(bfqq) && bfq_bfqq_has_short_ttime(bfqq); + /* + * The next variable takes into account the cases where idling + * boosts the throughput. + * + * 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 and rotational, or + * (b) regardless of the presence of NCQ, the device is rotational and + * the request pattern for bfqq is I/O-bound and sequential, or + * (c) regardless of whether it is rotational, the device is + * not NCQ-capable 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), (b) or (c) is true, and, in + * particular, happens to be false if bfqd is an NCQ-capable + * flash-based device. + */ + idling_boosts_thr = rot_without_queueing || + ((!blk_queue_nonrot(bfqd->queue) || !bfqd->hw_tag) && + bfqq_sequential_and_IO_bound); + + bfq_log_bfqq(bfqd, bfqq, "idling_boosts_thr %d", idling_boosts_thr); + + /* + * The return value of this function is equal to that of + * idling_boosts_thr, unless a special case holds. In this + * special case, described below, idling may cause problems to + * weight-raised queues. + * + * When the request pool is saturated (e.g., in the presence + * of write hogs), if the processes associated with + * non-weight-raised queues ask for requests at a lower rate, + * then processes associated with weight-raised queues have a + * higher probability to get a request from the pool + * immediately (or at least soon) when they need one. Thus + * they have a higher probability to actually get a fraction + * of the device throughput proportional to their high + * weight. This is especially true with NCQ-capable drives, + * which enqueue several requests in advance, and further + * reorder internally-queued requests. + * + * For this reason, we force to false the return value if + * there are weight-raised busy queues. In this case, and if + * bfqq is not weight-raised, this guarantees that the device + * is not idled for bfqq (if, instead, bfqq is weight-raised, + * then idling will be guaranteed by another variable, see + * below). Combined with the timestamping rules of BFQ (see + * [1] for details), this behavior causes bfqq, and hence any + * sync non-weight-raised queue, to get a lower number of + * requests served, and thus to ask for a lower number of + * requests from the request pool, before the busy + * weight-raised queues get served again. This often mitigates + * starvation problems in the presence of heavy write + * workloads and NCQ, thereby guaranteeing a higher + * application and system responsiveness in these hostile + * scenarios. + */ + return idling_boosts_thr && + bfqd->wr_busy_queues == 0; +} + +/* + * There is 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, entails loss of control on the + * actual request service order. In particular, the critical + * 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 + * determine also the actual throughput distribution among + * these processes. But the drive typically has no notion or + * concern about per-process throughput distribution, and + * makes its decisions only on a per-request basis. Therefore, + * 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) the I/O of each process has the same properties, in + * terms of locality (sequential or random), direction + * (reads or writes), request sizes, greediness + * (from I/O-bound to sporadic), and so on. + * In fact, in such a scenario, the drive tends 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). + * The problem is that idling may significantly reduce + * throughput with certain combinations of types of I/O and + * devices. An important example is sync random I/O, on flash + * storage with command queueing. So, unless bfqq falls in the + * above cases where idling also boosts throughput, it would + * be important to check conditions (i) and (ii) accurately, + * so as to avoid idling when not strictly needed for service + * guarantees. + * + * Unfortunately, it is extremely difficult to thoroughly + * check condition (ii). And, in case there are active groups, + * it becomes very difficult to check condition (i) too. In + * fact, if there are active groups, then, for condition (i) + * to become false, it is enough that an active group contains + * more active processes or sub-groups than some other active + * group. More precisely, for condition (i) to hold because of + * such a group, it is not even necessary that the group is + * (still) active: it is sufficient that, even if the group + * has become inactive, some of its descendant processes still + * have some request already dispatched but still waiting for + * completion. In fact, requests have still to be guaranteed + * their share of the throughput even after being + * dispatched. In this respect, it is easy to show that, if a + * group frequently becomes inactive while still having + * in-flight requests, and if, when this happens, the group is + * not considered in the calculation of whether the scenario + * is asymmetric, then the group may fail to be guaranteed its + * fair share of the throughput (basically because idling may + * not be performed for the descendant processes of the group, + * but it had to be). We address this issue with the + * following bi-modal behavior, implemented in the function + * bfq_symmetric_scenario(). + * + * If there are groups with requests waiting for completion + * (as commented above, some of these groups may even be + * already inactive), then the scenario is tagged as + * asymmetric, conservatively, without checking any of the + * conditions (i) and (ii). So the device is idled for bfqq. + * This behavior matches also the fact that groups are created + * exactly if controlling I/O is a primary concern (to + * preserve bandwidth and latency guarantees). + * + * On the opposite end, if there are no groups with requests + * waiting for completion, then only condition (i) is actually + * controlled, i.e., provided that condition (i) holds, idling + * is not performed, regardless of whether condition (ii) + * holds. In other words, only if condition (i) does not hold, + * then idling is allowed, and the device tends to be + * prevented from queueing many requests, possibly of several + * processes. Since there are no groups with requests waiting + * for completion, then, to control condition (i) it is enough + * to check just whether all the queues with requests waiting + * for completion also have the same weight. + * + * Not checking condition (ii) evidently exposes bfqq to the + * risk of getting less throughput than its fair share. + * However, for queues with the same weight, a further + * mechanism, preemption, mitigates or even eliminates this + * problem. And it does so without consequences on overall + * throughput. This mechanism and its benefits are explained + * in the next three 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. + * + * 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. + * + * The motivation for using preemption instead of idling (for + * queues with the same weight) is that, by not idling, + * service guarantees are preserved (completely or at least in + * part) without minimally sacrificing throughput. And, if + * there is no active group, then the primary expectation for + * this device is probably a high throughput. + * + * We are now left only with explaining the additional + * compound condition that is checked below for deciding + * whether the scenario is asymmetric. To explain this + * compound condition, we need to add that the function + * bfq_symmetric_scenario checks the weights of only + * non-weight-raised queues, for efficiency reasons (see + * comments on bfq_weights_tree_add()). Then the fact that + * bfqq is weight-raised is checked explicitly here. More + * precisely, the compound condition below takes into account + * also the fact that, even if bfqq is being weight-raised, + * the scenario is still symmetric if all queues with requests + * waiting for completion happen to be + * weight-raised. Actually, we should be even more precise + * here, and differentiate between interactive weight raising + * and soft real-time weight raising. + * + * 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 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. + */ +static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + bool asymmetric_scenario = (bfqq->wr_coeff > 1 && + bfqd->wr_busy_queues < + bfq_tot_busy_queues(bfqd)) || + !bfq_symmetric_scenario(bfqd); + + bfq_log_bfqq(bfqd, bfqq, + "wr_coeff %d wr_busy %d busy %d asymmetric %d", + bfqq->wr_coeff, + bfqd->wr_busy_queues, + bfq_tot_busy_queues(bfqd), + asymmetric_scenario); + + return asymmetric_scenario; +} + +/* + * For a queue that becomes empty, device idling is allowed only if + * this function returns true for that queue. As a consequence, since + * device idling plays a critical role for both throughput boosting + * and service guarantees, the return value of this function plays a + * critical role as well. + * + * In a nutshell, this function returns true only if idling is + * beneficial for throughput or, even if detrimental for throughput, + * idling is however necessary to preserve service guarantees (low + * latency, desired throughput distribution, ...). In particular, on + * NCQ-capable devices, this function tries to return false, so as to + * help keep the drives' internal queues full, whenever this helps the + * device boost the throughput without causing any service-guarantee + * issue. + * + * Most of the issues taken into account to get the return value of + * this function are not trivial. We discuss these issues in the two + * functions providing the main pieces of information needed by this + * function. + */ +static bool bfq_better_to_idle(struct bfq_queue *bfqq) +{ + struct bfq_data *bfqd = bfqq->bfqd; + bool idling_boosts_thr_with_no_issue, idling_needed_for_service_guar; + + if (unlikely(bfqd->strict_guarantees)) + return true; + + /* + * Idling is performed only if slice_idle > 0. In addition, we + * do not idle if + * (a) bfqq is async + * (b) bfqq is in the idle io prio class: in this case we do + * not idle because we want to minimize the bandwidth that + * queues in this class can steal to higher-priority queues + */ + if (bfqd->bfq_slice_idle == 0 || !bfq_bfqq_sync(bfqq) || + bfq_class_idle(bfqq)) + return false; + + idling_boosts_thr_with_no_issue = + idling_boosts_thr_without_issues(bfqd, bfqq); + + idling_needed_for_service_guar = + idling_needed_for_service_guarantees(bfqd, bfqq); + + /* + * We have now the two components we need to compute the + * return value of the function, which is true only if idling + * either boosts the throughput (without issues), or is + * necessary to preserve service guarantees. + */ + bfq_log_bfqq(bfqd, bfqq, + "wr_busy %d boosts %d IO-bound %d guar %d", + bfqd->wr_busy_queues, + idling_boosts_thr_with_no_issue, + bfq_bfqq_IO_bound(bfqq), + idling_needed_for_service_guar); + + return idling_boosts_thr_with_no_issue || + idling_needed_for_service_guar; +} + +/* + * If the in-service queue is empty but the function bfq_better_to_idle + * returns true, then: + * 1) the queue must remain in service and cannot be expired, and + * 2) the device must be idled to wait for the possible arrival of a new + * request for the queue. + * See the comments on the function bfq_better_to_idle for the reasons + * why performing device idling is the best choice to boost the throughput + * and preserve service guarantees when bfq_better_to_idle itself + * returns true. + */ +static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq) +{ + return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_better_to_idle(bfqq); +} + +static struct bfq_queue *bfq_choose_bfqq_for_injection(struct bfq_data *bfqd) +{ + struct bfq_queue *bfqq; + + /* + * A linear search; but, with a high probability, very few + * steps are needed to find a candidate queue, i.e., a queue + * with enough budget left for its next request. In fact: + * - BFQ dynamically updates the budget of every queue so as + * to accomodate the expected backlog of the queue; + * - if a queue gets all its requests dispatched as injected + * service, then the queue is removed from the active list + * (and re-added only if it gets new requests, but with + * enough budget for its new backlog). + */ + list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) + if (!RB_EMPTY_ROOT(&bfqq->sort_list) && + bfq_serv_to_charge(bfqq->next_rq, bfqq) <= + bfq_bfqq_budget_left(bfqq)) { + bfq_log_bfqq(bfqd, bfqq, "returned this queue"); + return bfqq; + } + + bfq_log(bfqd, "no queue found"); + return NULL; +} + +/* + * Select a queue for service. If we have a current queue in service, + * check whether to continue servicing it, or retrieve and set a new one. + */ +static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) +{ + struct bfq_queue *bfqq; + struct request *next_rq; + enum bfqq_expiration reason = BFQ_BFQQ_BUDGET_TIMEOUT; + + bfqq = bfqd->in_service_queue; + if (!bfqq) + goto new_queue; + + bfq_log_bfqq(bfqd, bfqq, "already in-service queue"); + + /* + * Do not expire bfqq for budget timeout if bfqq may be about + * to enjoy device idling. The reason why, in this case, we + * prevent bfqq from expiring is the same as in the comments + * on the case where bfq_bfqq_must_idle() returns true, in + * bfq_completed_request(). + */ + if (bfq_may_expire_for_budg_timeout(bfqq) && + !bfq_bfqq_must_idle(bfqq)) + goto expire; + +check_queue: + /* + * This loop is rarely executed more than once. Even when it + * happens, it is much more convenient to re-execute this loop + * than to return NULL and trigger a new dispatch to get a + * request served. + */ + next_rq = bfqq->next_rq; + /* + * If bfqq has requests queued and it has enough budget left to + * serve them, keep the queue, otherwise expire it. + */ + if (next_rq) { + BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list)); + + if (bfq_serv_to_charge(next_rq, bfqq) > + bfq_bfqq_budget_left(bfqq)) { + /* + * Expire the queue for budget exhaustion, + * which makes sure that the next budget is + * enough to serve the next request, even if + * it comes from the fifo expired path. + */ + reason = BFQ_BFQQ_BUDGET_EXHAUSTED; + goto expire; + } else { + /* + * The idle timer may be pending because we may + * not disable disk idling even when a new request + * arrives. + */ + if (bfq_bfqq_wait_request(bfqq)) { + /* + * If we get here: 1) at least a new request + * has arrived but we have not disabled the + * timer because the request was too small, + * 2) then the block layer has unplugged + * the device, causing the dispatch to be + * invoked. + * + * Since the device is unplugged, now the + * requests are probably large enough to + * provide a reasonable throughput. + * So we disable idling. + */ + bfq_clear_bfqq_wait_request(bfqq); + hrtimer_try_to_cancel(&bfqd->idle_slice_timer); + } + goto keep_queue; + } + } + + /* + * No requests pending. However, if the in-service queue is idling + * for a new request, or has requests waiting for a completion and + * may idle after their completion, then keep it anyway. + * + * Yet, to boost throughput, inject service from other queues if + * possible. + */ + if (bfq_bfqq_wait_request(bfqq) || + (bfqq->dispatched != 0 && bfq_better_to_idle(bfqq))) { + if (bfq_bfqq_injectable(bfqq) && + bfqq->injected_service * bfqq->inject_coeff < + bfqq->entity.service * 10) { + bfq_log_bfqq(bfqd, bfqq, "looking for queue for injection"); + bfqq = bfq_choose_bfqq_for_injection(bfqd); + } else { + if (BFQQ_SEEKY(bfqq)) + bfq_log_bfqq(bfqd, bfqq, + "injection saturated %d * %d >= %d * 10", + bfqq->injected_service, bfqq->inject_coeff, + bfqq->entity.service); + bfqq = NULL; + } + goto keep_queue; + } + + reason = BFQ_BFQQ_NO_MORE_REQUESTS; +expire: + bfq_bfqq_expire(bfqd, bfqq, false, reason); +new_queue: + bfqq = bfq_set_in_service_queue(bfqd); + if (bfqq) { + bfq_log_bfqq(bfqd, bfqq, "checking new queue"); + goto check_queue; + } +keep_queue: + if (bfqq) + bfq_log_bfqq(bfqd, bfqq, "returned this queue"); + else + bfq_log(bfqd, "no queue returned"); + + return bfqq; +} + +static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq) +{ + struct bfq_entity *entity = &bfqq->entity; + + if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */ + BUG_ON(bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time && + time_is_after_jiffies(bfqq->last_wr_start_finish)); + + bfq_log_bfqq(bfqd, bfqq, + "raising period dur %u/%u msec, old coeff %u, w %d(%d)", + jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish), + jiffies_to_msecs(bfqq->wr_cur_max_time), + bfqq->wr_coeff, + bfqq->entity.weight, bfqq->entity.orig_weight); + + BUG_ON(bfqq != bfqd->in_service_queue && entity->weight != + entity->orig_weight * bfqq->wr_coeff); + if (entity->prio_changed) + bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change"); + + /* + * 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 (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_bfqq_end_wr(bfqq); + else { + switch_back_to_interactive_wr(bfqq, bfqd); + BUG_ON(time_is_after_jiffies( + bfqq->last_wr_start_finish)); + bfqq->entity.prio_changed = 1; + bfq_log_bfqq(bfqd, bfqq, + "back to interactive wr"); + } + } + if (bfqq->wr_coeff > 1 && + bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time && + bfqq->service_from_wr > max_service_from_wr) { + /* see comments on max_service_from_wr */ + bfq_bfqq_end_wr(bfqq); + bfq_log_bfqq(bfqd, bfqq, + "too much service"); + } + } + /* + * To improve latency (for this or other queues), immediately + * update weight both if it must be raised and if it must be + * lowered. Since, entity may be on some active tree here, and + * might have a pending change of its ioprio class, invoke + * next function with the last parameter unset (see the + * comments on the function). + */ + if ((entity->weight > entity->orig_weight) != (bfqq->wr_coeff > 1)) + __bfq_entity_update_weight_prio(bfq_entity_service_tree(entity), + entity, false); +} + +/* + * Dispatch next request from bfqq. + */ +static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + struct request *rq = bfqq->next_rq; + unsigned long service_to_charge; + + BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list)); + BUG_ON(!rq); + service_to_charge = bfq_serv_to_charge(rq, bfqq); + + BUG_ON(service_to_charge > bfq_bfqq_budget_left(bfqq)); + + BUG_ON(bfqq->entity.budget < bfqq->entity.service); + + bfq_bfqq_served(bfqq, service_to_charge); + + BUG_ON(bfqq->entity.budget < bfqq->entity.service); + + bfq_dispatch_remove(bfqd->queue, rq); + + bfq_log_bfqq(bfqd, bfqq, + "dispatched %u sec req (%llu), budg left %d, new disp_nr %d", + blk_rq_sectors(rq), + (unsigned long long) blk_rq_pos(rq), + bfq_bfqq_budget_left(bfqq), + bfqq->dispatched); + + if (bfqq != bfqd->in_service_queue) { + if (likely(bfqd->in_service_queue)) { + bfqd->in_service_queue->injected_service += + bfq_serv_to_charge(rq, bfqq); + bfq_log_bfqq(bfqd, bfqd->in_service_queue, + "injected_service increased to %d", + bfqd->in_service_queue->injected_service); + } + goto return_rq; + } + + /* + * If weight raising has to terminate for bfqq, then next + * function causes an immediate update of bfqq's weight, + * without waiting for next activation. As a consequence, on + * expiration, bfqq will be timestamped as if has never been + * weight-raised during this service slot, even if it has + * received part or even most of the service as a + * weight-raised queue. This inflates bfqq's timestamps, which + * is beneficial, as bfqq is then more willing to leave the + * device immediately to possible other weight-raised queues. + */ + bfq_update_wr_data(bfqd, bfqq); + + /* + * Expire bfqq, pretending that its budget expired, if bfqq + * belongs to CLASS_IDLE and other queues are waiting for + * service. + */ + if (!(bfq_tot_busy_queues(bfqd) > 1 && bfq_class_idle(bfqq))) + goto return_rq; + + bfq_bfqq_expire(bfqd, bfqq, false, BFQ_BFQQ_BUDGET_EXHAUSTED); + +return_rq: + return rq; +} + +static bool bfq_has_work(struct blk_mq_hw_ctx *hctx) +{ + struct bfq_data *bfqd = hctx->queue->elevator->elevator_data; + + bfq_log(bfqd, "dispatch_non_empty %d busy_queues %d", + !list_empty_careful(&bfqd->dispatch), bfq_tot_busy_queues(bfqd) > 0); + + /* + * Avoiding lock: a race on bfqd->busy_queues should cause at + * most a call to dispatch for nothing + */ + return !list_empty_careful(&bfqd->dispatch) || + bfq_tot_busy_queues(bfqd) > 0; +} + +static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx) +{ + struct bfq_data *bfqd = hctx->queue->elevator->elevator_data; + struct request *rq = NULL; + struct bfq_queue *bfqq = NULL; + + if (!list_empty(&bfqd->dispatch)) { + rq = list_first_entry(&bfqd->dispatch, struct request, + queuelist); + list_del_init(&rq->queuelist); + rq->rq_flags &= ~RQF_DISP_LIST; + + bfq_log(bfqd, + "picked %p from dispatch list", rq); + bfqq = RQ_BFQQ(rq); + + if (bfqq) { + /* + * Increment counters here, because this + * dispatch does not follow the standard + * dispatch flow (where counters are + * incremented) + */ + bfqq->dispatched++; + + /* + * TESTING: reset DISP_LIST flag, because: 1) + * this rq this request has passed through + * bfq_prepare_request, 2) then it will have + * bfq_finish_requeue_request invoked on it, and 3) in + * bfq_finish_requeue_request we use this flag to check + * that bfq_finish_requeue_request is not invoked on + * requests for which bfq_prepare_request has + * been invoked. + */ + rq->rq_flags &= ~RQF_DISP_LIST; + goto inc_in_driver_start_rq; + } + + /* + * We exploit the bfq_finish_requeue_request hook to decrement + * rq_in_driver, but bfq_finish_requeue_request will not be + * invoked on this request. So, to avoid unbalance, + * just start this request, without incrementing + * rq_in_driver. As a negative consequence, + * rq_in_driver is deceptively lower than it should be + * while this request is in service. This may cause + * bfq_schedule_dispatch to be invoked uselessly. + * + * As for implementing an exact solution, the + * bfq_finish_requeue_request hook, if defined, is probably + * invoked also on this request. So, by exploiting + * this hook, we could 1) increment rq_in_driver here, + * and 2) decrement it in bfq_finish_requeue_request. Such a + * solution would let the value of the counter be + * always accurate, but it would entail using an extra + * interface function. This cost seems higher than the + * benefit, being the frequency of non-elevator-private + * requests very low. + */ + goto start_rq; + } + + bfq_log(bfqd, "%d busy queues", bfq_tot_busy_queues(bfqd)); + + if (bfq_tot_busy_queues(bfqd) == 0) + goto exit; + + /* + * Force device to serve one request at a time if + * strict_guarantees is true. Forcing this service scheme is + * currently the ONLY way to guarantee that the request + * service order enforced by the scheduler is respected by a + * queueing device. Otherwise the device is free even to make + * some unlucky request wait for as long as the device + * wishes. + * + * Of course, serving one request at at time may cause loss of + * throughput. + */ + if (bfqd->strict_guarantees && bfqd->rq_in_driver > 0) + goto exit; + + bfqq = bfq_select_queue(bfqd); + if (!bfqq) + goto exit; + + BUG_ON(bfqq == bfqd->in_service_queue && + bfqq->entity.budget < bfqq->entity.service); + + BUG_ON(bfqq == bfqd->in_service_queue && + bfq_bfqq_wait_request(bfqq)); + + rq = bfq_dispatch_rq_from_bfqq(bfqd, bfqq); + + BUG_ON(bfqq->entity.budget < bfqq->entity.service); + + if (rq) { + inc_in_driver_start_rq: + bfqd->rq_in_driver++; + start_rq: + rq->rq_flags |= RQF_STARTED; + if (bfqq) + bfq_log_bfqq(bfqd, bfqq, + "%s request %p, rq_in_driver %d", + bfq_bfqq_sync(bfqq) ? "sync" : "async", + rq, + bfqd->rq_in_driver); + else + bfq_log(bfqd, + "request %p from dispatch list, rq_in_driver %d", + rq, bfqd->rq_in_driver); + } else + bfq_log(bfqd, + "returned NULL request, rq_in_driver %d", + bfqd->rq_in_driver); + +exit: + return rq; +} + + +#if defined(BFQ_GROUP_IOSCHED_ENABLED) && defined(CONFIG_DEBUG_BLK_CGROUP) +static void bfq_update_dispatch_stats(struct request_queue *q, + struct request *rq, + struct bfq_queue *in_serv_queue, + bool idle_timer_disabled) +{ + struct bfq_queue *bfqq = rq ? RQ_BFQQ(rq) : NULL; + + if (!idle_timer_disabled && !bfqq) + return; + + /* + * rq and bfqq are guaranteed to exist until this function + * ends, for the following reasons. First, rq can be + * dispatched to the device, and then can be completed and + * freed, only after this function ends. Second, rq cannot be + * merged (and thus freed because of a merge) any longer, + * because it has already started. Thus rq cannot be freed + * before this function ends, and, since rq has a reference to + * bfqq, the same guarantee holds for bfqq too. + * + * In addition, the following queue lock guarantees that + * bfqq_group(bfqq) exists as well. + */ + spin_lock_irq(q->queue_lock); + if (idle_timer_disabled) + /* + * Since the idle timer has been disabled, + * in_serv_queue contained some request when + * __bfq_dispatch_request was invoked above, which + * implies that rq was picked exactly from + * in_serv_queue. Thus in_serv_queue == bfqq, and is + * therefore guaranteed to exist because of the above + * arguments. + */ + bfqg_stats_update_idle_time(bfqq_group(in_serv_queue)); + if (bfqq) { + struct bfq_group *bfqg = bfqq_group(bfqq); + + bfqg_stats_update_avg_queue_size(bfqg); + bfqg_stats_set_start_empty_time(bfqg); + bfqg_stats_update_io_remove(bfqg, rq->cmd_flags); + } + spin_unlock_irq(q->queue_lock); +} +#else +static inline void bfq_update_dispatch_stats(struct request_queue *q, + struct request *rq, + struct bfq_queue *in_serv_queue, + bool idle_timer_disabled) {} +#endif +static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx) +{ + struct bfq_data *bfqd = hctx->queue->elevator->elevator_data; + struct request *rq; + struct bfq_queue *in_serv_queue; + bool waiting_rq, idle_timer_disabled; + + spin_lock_irq(&bfqd->lock); + + in_serv_queue = bfqd->in_service_queue; + waiting_rq = in_serv_queue && bfq_bfqq_wait_request(in_serv_queue); + + rq = __bfq_dispatch_request(hctx); + + idle_timer_disabled = + waiting_rq && !bfq_bfqq_wait_request(in_serv_queue); + + spin_unlock_irq(&bfqd->lock); + + bfq_update_dispatch_stats(hctx->queue, rq, in_serv_queue, + idle_timer_disabled); + + return rq; +} + +/* + * Task holds one reference to the queue, dropped when task exits. Each rq + * in-flight on this queue also holds a reference, dropped when rq is freed. + * + * 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) +{ +#ifdef BFQ_GROUP_IOSCHED_ENABLED + struct bfq_group *bfqg = bfqq_group(bfqq); +#endif + + assert_spin_locked(&bfqq->bfqd->lock); + + BUG_ON(bfqq->ref <= 0); + + if (bfqq->bfqd) + bfq_log_bfqq(bfqq->bfqd, bfqq, "%p %d", bfqq, bfqq->ref); + + bfqq->ref--; + if (bfqq->ref) + return; + + BUG_ON(rb_first(&bfqq->sort_list)); + BUG_ON(bfqq->allocated != 0); + BUG_ON(bfqq->entity.tree); + BUG_ON(bfq_bfqq_busy(bfqq)); + + if (!hlist_unhashed(&bfqq->burst_list_node)) { + hlist_del_init(&bfqq->burst_list_node); + /* + * Decrement also burst size after the removal, if the + * process associated with bfqq is exiting, and thus + * does not contribute to the burst any longer. This + * decrement helps filter out false positives of large + * bursts, when some short-lived process (often due to + * the execution of commands by some service) happens + * to start and exit while a complex application is + * starting, and thus spawning several processes that + * do I/O (and that *must not* be treated as a large + * burst, see comments on bfq_handle_burst). + * + * In particular, the decrement is performed only if: + * 1) bfqq is not a merged queue, because, if it is, + * then this free of bfqq is not triggered by the exit + * of the process bfqq is associated with, but exactly + * by the fact that bfqq has just been merged. + * 2) burst_size is greater than 0, to handle + * unbalanced decrements. Unbalanced decrements may + * happen in te following case: bfqq is inserted into + * the current burst list--without incrementing + * bust_size--because of a split, but the current + * burst list is not the burst list bfqq belonged to + * (see comments on the case of a split in + * bfq_set_request). + */ + if (bfqq->bic && bfqq->bfqd->burst_size > 0) + bfqq->bfqd->burst_size--; + } + + if (bfqq->bfqd) + bfq_log_bfqq(bfqq->bfqd, bfqq, "%p freed", bfqq); + +#ifdef BFQ_GROUP_IOSCHED_ENABLED + bfq_log_bfqq(bfqq->bfqd, bfqq, "putting blkg and bfqg %p\n", bfqg); + bfqg_and_blkg_put(bfqg); +#endif + kmem_cache_free(bfq_pool, bfqq); +} + +static void bfq_put_cooperator(struct bfq_queue *bfqq) +{ + struct bfq_queue *__bfqq, *next; + + /* + * If this queue was scheduled to merge with another queue, be + * sure to drop the reference taken on that queue (and others in + * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs. + */ + __bfqq = bfqq->new_bfqq; + while (__bfqq) { + if (__bfqq == bfqq) + break; + next = __bfqq->new_bfqq; + bfq_put_queue(__bfqq); + __bfqq = next; + } +} + +static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq) +{ + if (bfqq == bfqd->in_service_queue) { + __bfq_bfqq_expire(bfqd, bfqq); + bfq_schedule_dispatch(bfqd); + } + + bfq_log_bfqq(bfqd, bfqq, "%p, %d", bfqq, bfqq->ref); + + bfq_put_cooperator(bfqq); + + bfq_put_queue(bfqq); /* release process reference */ +} + +static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync) +{ + struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync); + struct bfq_data *bfqd; + + if (bfqq) + bfqd = bfqq->bfqd; /* NULL if scheduler already exited */ + + if (bfqq && bfqd) { + unsigned long flags; + + spin_lock_irqsave(&bfqd->lock, flags); + bfq_exit_bfqq(bfqd, bfqq); + bic_set_bfqq(bic, NULL, is_sync); + spin_unlock_irqrestore(&bfqd->lock, flags); + } +} + +static void bfq_exit_icq(struct io_cq *icq) +{ + struct bfq_io_cq *bic = icq_to_bic(icq); + + BUG_ON(!bic); + bfq_exit_icq_bfqq(bic, true); + bfq_exit_icq_bfqq(bic, false); +} + +/* + * Update the entity prio values; note that the new values will not + * be used until the next (re)activation. + */ +static void bfq_set_next_ioprio_data(struct bfq_queue *bfqq, + struct bfq_io_cq *bic) +{ + struct task_struct *tsk = current; + int ioprio_class; + struct bfq_data *bfqd = bfqq->bfqd; + + WARN_ON(!bfqd); + if (!bfqd) + return; + + ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio); + switch (ioprio_class) { + default: + dev_err(bfqq->bfqd->queue->backing_dev_info->dev, + "bfq: bad prio class %d\n", ioprio_class); + case IOPRIO_CLASS_NONE: + /* + * No prio set, inherit CPU scheduling settings. + */ + bfqq->new_ioprio = task_nice_ioprio(tsk); + bfqq->new_ioprio_class = task_nice_ioclass(tsk); + break; + case IOPRIO_CLASS_RT: + bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio); + bfqq->new_ioprio_class = IOPRIO_CLASS_RT; + break; + case IOPRIO_CLASS_BE: + bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio); + bfqq->new_ioprio_class = IOPRIO_CLASS_BE; + break; + case IOPRIO_CLASS_IDLE: + bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE; + bfqq->new_ioprio = 7; + break; + } + + if (bfqq->new_ioprio >= IOPRIO_BE_NR) { + pr_crit("bfq_set_next_ioprio_data: new_ioprio %d\n", + bfqq->new_ioprio); + BUG(); + } + + bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio); + bfqq->entity.prio_changed = 1; + bfq_log_bfqq(bfqq->bfqd, bfqq, + "bic_class %d prio %d class %d", + ioprio_class, bfqq->new_ioprio, bfqq->new_ioprio_class); +} + +static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio) +{ + struct bfq_data *bfqd = bic_to_bfqd(bic); + struct bfq_queue *bfqq; + unsigned long uninitialized_var(flags); + int ioprio = bic->icq.ioc->ioprio; + + /* + * This condition may trigger on a newly created bic, be sure to + * drop the lock before returning. + */ + if (unlikely(!bfqd) || likely(bic->ioprio == ioprio)) + return; + + bic->ioprio = ioprio; + + bfqq = bic_to_bfqq(bic, false); + if (bfqq) { + /* release process reference on this queue */ + bfq_put_queue(bfqq); + bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic); + bic_set_bfqq(bic, bfqq, false); + bfq_log_bfqq(bfqd, bfqq, + "bfqq %p %d", + bfqq, bfqq->ref); + } + + bfqq = bic_to_bfqq(bic, true); + if (bfqq) + bfq_set_next_ioprio_data(bfqq, bic); +} + +static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, + struct bfq_io_cq *bic, pid_t pid, int is_sync) +{ + RB_CLEAR_NODE(&bfqq->entity.rb_node); + INIT_LIST_HEAD(&bfqq->fifo); + INIT_HLIST_NODE(&bfqq->burst_list_node); + BUG_ON(!hlist_unhashed(&bfqq->burst_list_node)); + + bfqq->ref = 0; + bfqq->bfqd = bfqd; + + if (bic) + bfq_set_next_ioprio_data(bfqq, bic); + + if (is_sync) { + /* + * No need to mark as has_short_ttime if in + * idle_class, because no device idling is performed + * for queues in idle class + */ + if (!bfq_class_idle(bfqq)) + /* tentatively mark as has_short_ttime */ + bfq_mark_bfqq_has_short_ttime(bfqq); + bfq_mark_bfqq_sync(bfqq); + bfq_mark_bfqq_just_created(bfqq); + /* + * Aggressively inject a lot of service: up to 90%. + * This coefficient remains constant during bfqq life, + * but this behavior might be changed, after enough + * testing and tuning. + */ + bfqq->inject_coeff = 1; + } else + bfq_clear_bfqq_sync(bfqq); + + bfqq->ttime.last_end_request = ktime_get_ns() - (1ULL<<32); + + bfq_mark_bfqq_IO_bound(bfqq); + + /* Tentative initial value to trade off between thr and lat */ + bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3; + bfqq->pid = pid; + + bfqq->wr_coeff = 1; + bfqq->last_wr_start_finish = jiffies; + bfqq->wr_start_at_switch_to_srt = bfq_smallest_from_now(); + bfqq->budget_timeout = bfq_smallest_from_now(); + bfqq->split_time = bfq_smallest_from_now(); + + /* + * To not forget the possibly high bandwidth consumed by a + * process/queue in the recent past, + * bfq_bfqq_softrt_next_start() returns a value at least equal + * to the current value of bfqq->soft_rt_next_start (see + * comments on bfq_bfqq_softrt_next_start). Set + * soft_rt_next_start to now, to mean that bfqq has consumed + * no bandwidth so far. + */ + bfqq->soft_rt_next_start = jiffies; + + /* first request is almost certainly seeky */ + bfqq->seek_history = 1; +} + +static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd, + struct bfq_group *bfqg, + int ioprio_class, int ioprio) +{ + switch (ioprio_class) { + case IOPRIO_CLASS_RT: + return &bfqg->async_bfqq[0][ioprio]; + case IOPRIO_CLASS_NONE: + ioprio = IOPRIO_NORM; + /* fall through */ + case IOPRIO_CLASS_BE: + return &bfqg->async_bfqq[1][ioprio]; + case IOPRIO_CLASS_IDLE: + return &bfqg->async_idle_bfqq; + default: + BUG(); + } +} + +static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, + struct bio *bio, bool is_sync, + struct bfq_io_cq *bic) +{ + const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio); + const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio); + struct bfq_queue **async_bfqq = NULL; + struct bfq_queue *bfqq; + struct bfq_group *bfqg; + + rcu_read_lock(); + + bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio)); + if (!bfqg) { + bfqq = &bfqd->oom_bfqq; + goto out; + } + + if (!is_sync) { + async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class, + ioprio); + bfqq = *async_bfqq; + if (bfqq) + goto out; + } + + bfqq = kmem_cache_alloc_node(bfq_pool, + GFP_NOWAIT | __GFP_ZERO | __GFP_NOWARN, + bfqd->queue->node); + + if (bfqq) { + bfq_init_bfqq(bfqd, bfqq, bic, current->pid, + is_sync); + bfq_init_entity(&bfqq->entity, bfqg); + bfq_log_bfqq(bfqd, bfqq, "allocated"); + } else { + bfqq = &bfqd->oom_bfqq; + bfq_log_bfqq(bfqd, bfqq, "using oom bfqq"); + goto out; + } + + /* + * Pin the queue now that it's allocated, scheduler exit will + * prune it. + */ + if (async_bfqq) { + bfqq->ref++; /* + * Extra group reference, w.r.t. sync + * queue. This extra reference is removed + * only if bfqq->bfqg disappears, to + * guarantee that this queue is not freed + * until its group goes away. + */ + bfq_log_bfqq(bfqd, bfqq, "bfqq not in async: %p, %d", + bfqq, bfqq->ref); + *async_bfqq = bfqq; + } + +out: + bfqq->ref++; /* get a process reference to this queue */ + bfq_log_bfqq(bfqd, bfqq, "at end: %p, %d", bfqq, bfqq->ref); + rcu_read_unlock(); + return bfqq; +} + +static void bfq_update_io_thinktime(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + struct bfq_ttime *ttime = &bfqq->ttime; + u64 elapsed = ktime_get_ns() - bfqq->ttime.last_end_request; + + elapsed = min_t(u64, elapsed, 2 * bfqd->bfq_slice_idle); + + ttime->ttime_samples = (7*bfqq->ttime.ttime_samples + 256) / 8; + ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed, 8); + ttime->ttime_mean = div64_ul(ttime->ttime_total + 128, + ttime->ttime_samples); +} + +static void +bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq, + struct request *rq) +{ + bfqq->seek_history <<= 1; + bfqq->seek_history |= BFQ_RQ_SEEKY(bfqd, bfqq->last_request_pos, rq); +} + +static void bfq_update_has_short_ttime(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + struct bfq_io_cq *bic) +{ + bool has_short_ttime = true; + + /* + * No need to update has_short_ttime if bfqq is async or in + * idle io prio class, or if bfq_slice_idle is zero, because + * no device idling is performed for bfqq in this case. + */ + if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq) || + bfqd->bfq_slice_idle == 0) + return; + + /* Idle window just restored, statistics are meaningless. */ + if (time_is_after_eq_jiffies(bfqq->split_time + + bfqd->bfq_wr_min_idle_time)) + return; + + /* Think time is infinite if no process is linked to + * bfqq. Otherwise check average think time to + * decide whether to mark as has_short_ttime + */ + if (atomic_read(&bic->icq.ioc->active_ref) == 0 || + (bfq_sample_valid(bfqq->ttime.ttime_samples) && + bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle)) + has_short_ttime = false; + + bfq_log_bfqq(bfqd, bfqq, "has_short_ttime %d", + has_short_ttime); + + if (has_short_ttime) + bfq_mark_bfqq_has_short_ttime(bfqq); + else + bfq_clear_bfqq_has_short_ttime(bfqq); +} + +/* + * Called when a new fs request (rq) is added to bfqq. Check if there's + * something we should do about it. + */ +static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq, + struct request *rq) +{ + struct bfq_io_cq *bic = RQ_BIC(rq); + + if (rq->cmd_flags & REQ_META) + bfqq->meta_pending++; + + bfq_update_io_thinktime(bfqd, bfqq); + bfq_update_has_short_ttime(bfqd, bfqq, bic); + bfq_update_io_seektime(bfqd, bfqq, rq); + + bfq_log_bfqq(bfqd, bfqq, + "has_short_ttime=%d (seeky %d)", + bfq_bfqq_has_short_ttime(bfqq), BFQQ_SEEKY(bfqq)); + + bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq); + + if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) { + bool small_req = bfqq->queued[rq_is_sync(rq)] == 1 && + blk_rq_sectors(rq) < 32; + bool budget_timeout = bfq_bfqq_budget_timeout(bfqq); + + /* + * There is just this request queued: if + * - the request is small, and + * - we are idling to boost throughput, and + * - the queue is not to be expired, + * then just exit. + * + * In this way, if the device is being idled to wait + * for a new request from the in-service queue, we + * avoid unplugging the device and committing the + * device to serve just a small request. In contrast + * we wait for the block layer to decide when to + * unplug the device: hopefully, new requests will be + * merged to this one quickly, then the device will be + * unplugged and larger requests will be dispatched. + */ + if (small_req && idling_boosts_thr_without_issues(bfqd, bfqq) && + !budget_timeout) + return; + + /* + * A large enough request arrived, or idling is being + * performed to preserve service guarantees, or + * finally the queue is to be expired: in all these + * cases disk idling is to be stopped, so clear + * wait_request flag and reset timer. + */ + bfq_clear_bfqq_wait_request(bfqq); + hrtimer_try_to_cancel(&bfqd->idle_slice_timer); + + /* + * The queue is not empty, because a new request just + * arrived. Hence we can safely expire the queue, in + * case of budget timeout, without risking that the + * timestamps of the queue are not updated correctly. + * See [1] for more details. + */ + if (budget_timeout) + bfq_bfqq_expire(bfqd, bfqq, false, + BFQ_BFQQ_BUDGET_TIMEOUT); + } +} + +/* returns true if it causes the idle timer to be disabled */ +static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq) +{ + struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq; + bool waiting, idle_timer_disabled = false; + BUG_ON(!bfqq); + + assert_spin_locked(&bfqd->lock); + + bfq_log_bfqq(bfqd, bfqq, "rq %p bfqq %p", rq, bfqq); + + /* + * An unplug may trigger a requeue of a request from the device + * driver: make sure we are in process context while trying to + * merge two bfq_queues. + */ + if (!in_interrupt()) { + new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true); + if (new_bfqq) { + BUG_ON(bic_to_bfqq(RQ_BIC(rq), 1) != bfqq); + /* + * Release the request's reference to the old bfqq + * and make sure one is taken to the shared queue. + */ + new_bfqq->allocated++; + bfqq->allocated--; + bfq_log_bfqq(bfqd, bfqq, + "new allocated %d", bfqq->allocated); + bfq_log_bfqq(bfqd, new_bfqq, + "new_bfqq new allocated %d", + bfqq->allocated); + + new_bfqq->ref++; + /* + * If the bic associated with the process + * issuing this request still points to bfqq + * (and thus has not been already redirected + * to new_bfqq or even some other bfq_queue), + * then complete the merge and redirect it to + * new_bfqq. + */ + if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq) + bfq_merge_bfqqs(bfqd, RQ_BIC(rq), + bfqq, new_bfqq); + + bfq_clear_bfqq_just_created(bfqq); + /* + * rq is about to be enqueued into new_bfqq, + * release rq reference on bfqq + */ + bfq_put_queue(bfqq); + rq->elv.priv[1] = new_bfqq; + bfqq = new_bfqq; + } + } + + waiting = bfqq && bfq_bfqq_wait_request(bfqq); + bfq_add_request(rq); + idle_timer_disabled = waiting && !bfq_bfqq_wait_request(bfqq); + + rq->fifo_time = ktime_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)]; + list_add_tail(&rq->queuelist, &bfqq->fifo); + + bfq_rq_enqueued(bfqd, bfqq, rq); + + return idle_timer_disabled; +} + +#if defined(BFQ_GROUP_IOSCHED_ENABLED) && defined(CONFIG_DEBUG_BLK_CGROUP) +static void bfq_update_insert_stats(struct request_queue *q, + struct bfq_queue *bfqq, + bool idle_timer_disabled, + unsigned int cmd_flags) +{ + if (!bfqq) + return; + + /* + * bfqq still exists, because it can disappear only after + * either it is merged with another queue, or the process it + * is associated with exits. But both actions must be taken by + * the same process currently executing this flow of + * instructions. + * + * In addition, the following queue lock guarantees that + * bfqq_group(bfqq) exists as well. + */ + spin_lock_irq(q->queue_lock); + bfqg_stats_update_io_add(bfqq_group(bfqq), bfqq, cmd_flags); + if (idle_timer_disabled) + bfqg_stats_update_idle_time(bfqq_group(bfqq)); + spin_unlock_irq(q->queue_lock); +} +#else +static inline void bfq_update_insert_stats(struct request_queue *q, + struct bfq_queue *bfqq, + bool idle_timer_disabled, + unsigned int cmd_flags) {} +#endif + +static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, + bool at_head) +{ + struct request_queue *q = hctx->queue; + struct bfq_data *bfqd = q->elevator->elevator_data; + struct bfq_queue *bfqq; + bool idle_timer_disabled = false; + unsigned int cmd_flags; + + spin_lock_irq(&bfqd->lock); + if (blk_mq_sched_try_insert_merge(q, rq)) { + spin_unlock_irq(&bfqd->lock); + return; + } + + spin_unlock_irq(&bfqd->lock); + + blk_mq_sched_request_inserted(rq); + + spin_lock_irq(&bfqd->lock); + + bfqq = bfq_init_rq(rq); + BUG_ON(!bfqq && !(at_head || blk_rq_is_passthrough(rq))); + BUG_ON(bfqq && bic_to_bfqq(RQ_BIC(rq), rq_is_sync(rq)) != bfqq); + + if (at_head || blk_rq_is_passthrough(rq)) { + if (at_head) + list_add(&rq->queuelist, &bfqd->dispatch); + else + list_add_tail(&rq->queuelist, &bfqd->dispatch); + + rq->rq_flags |= RQF_DISP_LIST; + if (bfqq) + bfq_log_bfqq(bfqd, bfqq, + "%p in disp: at_head %d", + rq, at_head); + else + bfq_log(bfqd, + "%p in disp: at_head %d", + rq, at_head); + } else { /* bfqq is assumed to be non null here */ + BUG_ON(!bfqq); + BUG_ON(!(rq->rq_flags & RQF_GOT)); + rq->rq_flags &= ~RQF_GOT; + + idle_timer_disabled = __bfq_insert_request(bfqd, rq); + /* + * Update bfqq, because, if a queue merge has occurred + * in __bfq_insert_request, then rq has been + * redirected into a new queue. + */ + bfqq = RQ_BFQQ(rq); + + if (rq_mergeable(rq)) { + elv_rqhash_add(q, rq); + if (!q->last_merge) + q->last_merge = rq; + } + } + + /* + * Cache cmd_flags before releasing scheduler lock, because rq + * may disappear afterwards (for example, because of a request + * merge). + */ + cmd_flags = rq->cmd_flags; + + spin_unlock_irq(&bfqd->lock); + bfq_update_insert_stats(q, bfqq, idle_timer_disabled, + cmd_flags); +} + +static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx, + struct list_head *list, bool at_head) +{ + while (!list_empty(list)) { + struct request *rq; + + rq = list_first_entry(list, struct request, queuelist); + list_del_init(&rq->queuelist); + bfq_insert_request(hctx, rq, at_head); + } +} + +static void bfq_update_hw_tag(struct bfq_data *bfqd) +{ + struct bfq_queue *bfqq = bfqd->in_service_queue; + + bfqd->max_rq_in_driver = max_t(int, bfqd->max_rq_in_driver, + bfqd->rq_in_driver); + + if (bfqd->hw_tag == 1) + return; + + /* + * This sample is valid if the number of outstanding requests + * is large enough to allow a queueing behavior. Note that the + * sum is not exact, as it's not taking into account deactivated + * requests. + */ + if (bfqd->rq_in_driver + bfqd->queued <= BFQ_HW_QUEUE_THRESHOLD) + return; + + /* + * If active queue hasn't enough requests and can idle, bfq might not + * dispatch sufficient requests to hardware. Don't zero hw_tag in this + * case + */ + if (bfqq && bfq_bfqq_has_short_ttime(bfqq) && + bfqq->dispatched + bfqq->queued[0] + bfqq->queued[1] < + BFQ_HW_QUEUE_THRESHOLD && bfqd->rq_in_driver < BFQ_HW_QUEUE_THRESHOLD) + return; + + if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES) + return; + + bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD; + bfqd->max_rq_in_driver = 0; + bfqd->hw_tag_samples = 0; +} + +static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd) +{ + u64 now_ns; + u32 delta_us; + + bfq_update_hw_tag(bfqd); + + BUG_ON(!bfqd->rq_in_driver); + BUG_ON(!bfqq->dispatched); + bfqd->rq_in_driver--; + bfqq->dispatched--; + + bfq_log_bfqq(bfqd, bfqq, + "new disp %d, new rq_in_driver %d", + bfqq->dispatched, bfqd->rq_in_driver); + + if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) { + BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list)); + /* + * Set budget_timeout (which we overload to store the + * time at which the queue remains with no backlog and + * no outstanding request; used by the weight-raising + * mechanism). + */ + bfqq->budget_timeout = jiffies; + + bfq_weights_tree_remove(bfqd, bfqq); + } + + now_ns = ktime_get_ns(); + + bfqq->ttime.last_end_request = now_ns; + + /* + * Using us instead of ns, to get a reasonable precision in + * computing rate in next check. + */ + delta_us = div_u64(now_ns - bfqd->last_completion, NSEC_PER_USEC); + + bfq_log_bfqq(bfqd, bfqq, + "delta %uus/%luus max_size %u rate %llu/%llu", + delta_us, BFQ_MIN_TT/NSEC_PER_USEC, bfqd->last_rq_max_size, + delta_us > 0 ? + (USEC_PER_SEC* + (u64)((bfqd->last_rq_max_size<>BFQ_RATE_SHIFT : + (USEC_PER_SEC* + (u64)(bfqd->last_rq_max_size<>BFQ_RATE_SHIFT, + (USEC_PER_SEC*(u64)(1UL<<(BFQ_RATE_SHIFT-10)))>>BFQ_RATE_SHIFT); + + /* + * If the request took rather long to complete, and, according + * to the maximum request size recorded, this completion latency + * implies that the request was certainly served at a very low + * rate (less than 1M sectors/sec), then the whole observation + * interval that lasts up to this time instant cannot be a + * valid time interval for computing a new peak rate. Invoke + * bfq_update_rate_reset to have the following three steps + * taken: + * - close the observation interval at the last (previous) + * request dispatch or completion + * - compute rate, if possible, for that observation interval + * - reset to zero samples, which will trigger a proper + * re-initialization of the observation interval on next + * dispatch + */ + if (delta_us > BFQ_MIN_TT/NSEC_PER_USEC && + (bfqd->last_rq_max_size<last_completion = now_ns; + + /* + * If we are waiting to discover whether the request pattern + * of the task associated with the queue is actually + * isochronous, and both requisites for this condition to hold + * are now satisfied, then compute soft_rt_next_start (see the + * comments on the function bfq_bfqq_softrt_next_start()). We + * do not compute soft_rt_next_start if bfqq is in interactive + * weight raising (see the comments in bfq_bfqq_expire() for + * an explanation). We schedule this delayed update when bfqq + * expires, if it still has in-flight requests. + */ + if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 && + RB_EMPTY_ROOT(&bfqq->sort_list) && + bfqq->wr_coeff != bfqd->bfq_wr_coeff) + bfqq->soft_rt_next_start = + bfq_bfqq_softrt_next_start(bfqd, bfqq); + + /* + * If this is the in-service queue, check if it needs to be expired, + * or if we want to idle in case it has no pending requests. + */ + if (bfqd->in_service_queue == bfqq) { + if (bfq_bfqq_must_idle(bfqq)) { + if (bfqq->dispatched == 0) + bfq_arm_slice_timer(bfqd); + /* + * If we get here, we do not expire bfqq, even + * if bfqq was in budget timeout or had no + * more requests (as controlled in the next + * conditional instructions). The reason for + * not expiring bfqq is as follows. + * + * Here bfqq->dispatched > 0 holds, but + * bfq_bfqq_must_idle() returned true. This + * implies that, even if no request arrives + * for bfqq before bfqq->dispatched reaches 0, + * bfqq will, however, not be expired on the + * completion event that causes bfqq->dispatch + * to reach zero. In contrast, on this event, + * bfqq will start enjoying device idling + * (I/O-dispatch plugging). + * + * But, if we expired bfqq here, bfqq would + * not have the chance to enjoy device idling + * when bfqq->dispatched finally reaches + * zero. This would expose bfqq to violation + * of its reserved service guarantees. + */ + return; + } else if (bfq_may_expire_for_budg_timeout(bfqq)) + bfq_bfqq_expire(bfqd, bfqq, false, + BFQ_BFQQ_BUDGET_TIMEOUT); + else if (RB_EMPTY_ROOT(&bfqq->sort_list) && + (bfqq->dispatched == 0 || + !bfq_better_to_idle(bfqq))) + bfq_bfqq_expire(bfqd, bfqq, false, + BFQ_BFQQ_NO_MORE_REQUESTS); + } +} + +static void bfq_finish_requeue_request_body(struct bfq_queue *bfqq) +{ + bfq_log_bfqq(bfqq->bfqd, bfqq, + "allocated %d", bfqq->allocated); + BUG_ON(!bfqq->allocated); + bfqq->allocated--; + + bfq_put_queue(bfqq); +} + +/* + * Handle either a requeue or a finish for rq. The things to do are + * the same in both cases: all references to rq are to be dropped. In + * particular, rq is considered completed from the point of view of + * the scheduler. + */ +static void bfq_finish_requeue_request(struct request *rq) +{ + struct bfq_queue *bfqq; + struct bfq_data *bfqd; + struct bfq_io_cq *bic; + + BUG_ON(!rq); + + bfqq = RQ_BFQQ(rq); + + /* + * Requeue and finish hooks are invoked in blk-mq without + * checking whether the involved request is actually still + * referenced in the scheduler. To handle this fact, the + * following two checks make this function exit in case of + * spurious invocations, for which there is nothing to do. + * + * First, check whether rq has nothing to do with an elevator. + */ + if (unlikely(!(rq->rq_flags & RQF_ELVPRIV))) + return; + + /* + * rq either is not associated with any icq, or is an already + * requeued request that has not (yet) been re-inserted into + * a bfq_queue. + */ + if (!rq->elv.icq || !bfqq) + return; + + bic = RQ_BIC(rq); + BUG_ON(!bic); + + bfqd = bfqq->bfqd; + BUG_ON(!bfqd); + + if (rq->rq_flags & RQF_DISP_LIST) { + pr_crit("putting disp rq %p for %d", rq, bfqq->pid); + BUG(); + } + BUG_ON(rq->rq_flags & RQF_QUEUED); + + bfq_log_bfqq(bfqd, bfqq, + "putting rq %p with %u sects left, STARTED %d", + rq, blk_rq_sectors(rq), + rq->rq_flags & RQF_STARTED); + + if (rq->rq_flags & RQF_STARTED) + bfqg_stats_update_completion(bfqq_group(bfqq), + rq->start_time_ns, + rq->io_start_time_ns, + rq->cmd_flags); + + WARN_ON(blk_rq_sectors(rq) == 0 && !(rq->rq_flags & RQF_STARTED)); + + if (likely(rq->rq_flags & RQF_STARTED)) { + unsigned long flags; + + spin_lock_irqsave(&bfqd->lock, flags); + + bfq_completed_request(bfqq, bfqd); + bfq_finish_requeue_request_body(bfqq); + + spin_unlock_irqrestore(&bfqd->lock, flags); + } else { + /* + * Request rq may be still/already in the scheduler, + * in which case we need to remove it (this should + * never happen in case of requeue). And we cannot + * defer such a check and removal, to avoid + * inconsistencies in the time interval from the end + * of this function to the start of the deferred work. + * This situation seems to occur only in process + * context, as a consequence of a merge. In the + * current version of the code, this implies that the + * lock is held. + */ + BUG_ON(in_interrupt()); + + assert_spin_locked(&bfqd->lock); + if (!RB_EMPTY_NODE(&rq->rb_node)) { + bfq_remove_request(rq->q, rq); + bfqg_stats_update_io_remove(bfqq_group(bfqq), + rq->cmd_flags); + } + bfq_finish_requeue_request_body(bfqq); + } + + /* + * Reset private fields. In case of a requeue, this allows + * this function to correctly do nothing if it is spuriously + * invoked again on this same request (see the check at the + * beginning of the function). Probably, a better general + * design would be to prevent blk-mq from invoking the requeue + * or finish hooks of an elevator, for a request that is not + * referred by that elevator. + * + * Resetting the following fields would break the + * request-insertion logic if rq is re-inserted into a bfq + * internal queue, without a re-preparation. Here we assume + * that re-insertions of requeued requests, without + * re-preparation, can happen only for pass_through or at_head + * requests (which are not re-inserted into bfq internal + * queues). + */ + rq->elv.priv[0] = NULL; + rq->elv.priv[1] = NULL; +} + +/* + * Returns NULL if a new bfqq should be allocated, or the old bfqq if this + * was the last process referring to that bfqq. + */ +static struct bfq_queue * +bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq) +{ + bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue"); + + if (bfqq_process_refs(bfqq) == 1) { + bfqq->pid = current->pid; + bfq_clear_bfqq_coop(bfqq); + bfq_clear_bfqq_split_coop(bfqq); + return bfqq; + } + + bic_set_bfqq(bic, NULL, 1); + + bfq_put_cooperator(bfqq); + + bfq_put_queue(bfqq); + return NULL; +} + +static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd, + struct bfq_io_cq *bic, + struct bio *bio, + bool split, bool is_sync, + bool *new_queue) +{ + struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync); + + if (likely(bfqq && bfqq != &bfqd->oom_bfqq)) + return bfqq; + + if (new_queue) + *new_queue = true; + + if (bfqq) + bfq_put_queue(bfqq); + bfqq = bfq_get_queue(bfqd, bio, is_sync, bic); + BUG_ON(!hlist_unhashed(&bfqq->burst_list_node)); + + bic_set_bfqq(bic, bfqq, is_sync); + if (split && is_sync) { + bfq_log_bfqq(bfqd, bfqq, + "get_request: was_in_list %d " + "was_in_large_burst %d " + "large burst in progress %d", + bic->was_in_burst_list, + bic->saved_in_large_burst, + bfqd->large_burst); + + if ((bic->was_in_burst_list && bfqd->large_burst) || + bic->saved_in_large_burst) { + bfq_log_bfqq(bfqd, bfqq, + "get_request: marking in " + "large burst"); + bfq_mark_bfqq_in_large_burst(bfqq); + } else { + bfq_log_bfqq(bfqd, bfqq, + "get_request: clearing in " + "large burst"); + bfq_clear_bfqq_in_large_burst(bfqq); + if (bic->was_in_burst_list) + /* + * If bfqq was in the current + * burst list before being + * merged, then we have to add + * it back. And we do not need + * to increase burst_size, as + * we did not decrement + * burst_size when we removed + * bfqq from the burst list as + * a consequence of a merge + * (see comments in + * bfq_put_queue). In this + * respect, it would be rather + * costly to know whether the + * current burst list is still + * the same burst list from + * which bfqq was removed on + * the merge. To avoid this + * cost, if bfqq was in a + * burst list, then we add + * bfqq to the current burst + * list without any further + * check. This can cause + * inappropriate insertions, + * but rarely enough to not + * harm the detection of large + * bursts significantly. + */ + hlist_add_head(&bfqq->burst_list_node, + &bfqd->burst_list); + } + bfqq->split_time = jiffies; + } + + return bfqq; +} + +/* + * Only reset private fields. The actual request preparation will be + * performed by bfq_init_rq, when rq is either inserted or merged. See + * comments on bfq_init_rq for the reason behind this delayed + * preparation. +*/ +static void bfq_prepare_request(struct request *rq, struct bio *bio) +{ + /* + * Regardless of whether we have an icq attached, we have to + * clear the scheduler pointers, as they might point to + * previously allocated bic/bfqq structs. + */ + rq->elv.priv[0] = rq->elv.priv[1] = NULL; +} + +/* + * If needed, init rq, allocate bfq data structures associated with + * rq, and increment reference counters in the destination bfq_queue + * for rq. Return the destination bfq_queue for rq, or NULL is rq is + * not associated with any bfq_queue. + * + * This function is invoked by the functions that perform rq insertion + * or merging. One may have expected the above preparation operations + * to be performed in bfq_prepare_request, and not delayed to when rq + * is inserted or merged. The rationale behind this delayed + * preparation is that, after the prepare_request hook is invoked for + * rq, rq may still be transformed into a request with no icq, i.e., a + * request not associated with any queue. No bfq hook is invoked to + * signal this tranformation. As a consequence, should these + * preparation operations be performed when the prepare_request hook + * is invoked, and should rq be transformed one moment later, bfq + * would end up in an inconsistent state, because it would have + * incremented some queue counters for an rq destined to + * transformation, without any chance to correctly lower these + * counters back. In contrast, no transformation can still happen for + * rq after rq has been inserted or merged. So, it is safe to execute + * these preparation operations when rq is finally inserted or merged. + */ +static struct bfq_queue *bfq_init_rq(struct request *rq) +{ + struct request_queue *q = rq->q; + struct bio *bio = rq->bio; + struct bfq_data *bfqd = q->elevator->elevator_data; + struct bfq_io_cq *bic; + const int is_sync = rq_is_sync(rq); + struct bfq_queue *bfqq; + bool bfqq_already_existing = false, split = false; + bool new_queue = false; + + if (unlikely(!rq->elv.icq)) + return NULL; + + /* + * Assuming that elv.priv[1] is set only if everything is set + * for this rq. This holds true, because this function is + * invoked only for insertion or merging, and, after such + * events, a request cannot be manipulated any longer before + * being removed from bfq. + */ + if (rq->elv.priv[1]) { + BUG_ON(!(rq->rq_flags & RQF_ELVPRIV)); + return rq->elv.priv[1]; + } + + bic = icq_to_bic(rq->elv.icq); + + bfq_check_ioprio_change(bic, bio); + + bfq_bic_update_cgroup(bic, bio); + + bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync, + &new_queue); + + if (likely(!new_queue)) { + /* If the queue was seeky for too long, break it apart. */ + if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) { + BUG_ON(!is_sync); + 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); + split = true; + + if (!bfqq) + bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, + true, is_sync, + NULL); + else + bfqq_already_existing = true; + + BUG_ON(!bfqq); + BUG_ON(bfqq == &bfqd->oom_bfqq); + } + } + + bfqq->allocated++; + bfq_log_bfqq(bfqq->bfqd, bfqq, + "new allocated %d", bfqq->allocated); + + bfqq->ref++; + bfq_log_bfqq(bfqd, bfqq, "%p: bfqq %p, %d", rq, bfqq, bfqq->ref); + + rq->elv.priv[0] = bic; + rq->elv.priv[1] = bfqq; + rq->rq_flags &= ~RQF_DISP_LIST; + + /* + * If a bfq_queue has only one process reference, it is owned + * by only this bic: we can then set bfqq->bic = bic. in + * addition, if the queue has also just been split, we have to + * resume its state. + */ + if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) { + bfqq->bic = bic; + if (split) { + /* + * The queue has just been split from a shared + * queue: restore the idle window and the + * possible weight raising period. + */ + bfq_bfqq_resume_state(bfqq, bfqd, bic, + bfqq_already_existing); + } + } + + if (unlikely(bfq_bfqq_just_created(bfqq))) + bfq_handle_burst(bfqd, bfqq); + + rq->rq_flags |= RQF_GOT; + + return bfqq; +} + +static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq) +{ + struct bfq_data *bfqd = bfqq->bfqd; + enum bfqq_expiration reason; + unsigned long flags; + + BUG_ON(!bfqd); + spin_lock_irqsave(&bfqd->lock, flags); + + bfq_log_bfqq(bfqd, bfqq, "handling slice_timer expiration"); + bfq_clear_bfqq_wait_request(bfqq); + + if (bfqq != bfqd->in_service_queue) { + spin_unlock_irqrestore(&bfqd->lock, flags); + return; + } + + if (bfq_bfqq_budget_timeout(bfqq)) + /* + * Also here the queue can be safely expired + * for budget timeout without wasting + * guarantees + */ + reason = BFQ_BFQQ_BUDGET_TIMEOUT; + else if (bfqq->queued[0] == 0 && bfqq->queued[1] == 0) + /* + * The queue may not be empty upon timer expiration, + * because we may not disable the timer when the + * first request of the in-service queue arrives + * during disk idling. + */ + reason = BFQ_BFQQ_TOO_IDLE; + else + goto schedule_dispatch; + + bfq_bfqq_expire(bfqd, bfqq, true, reason); + +schedule_dispatch: + spin_unlock_irqrestore(&bfqd->lock, flags); + bfq_schedule_dispatch(bfqd); +} + +/* + * Handler of the expiration of the timer running if the in-service queue + * is idling inside its time slice. + */ +static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer) +{ + struct bfq_data *bfqd = container_of(timer, struct bfq_data, + idle_slice_timer); + struct bfq_queue *bfqq = bfqd->in_service_queue; + + bfq_log(bfqd, "expired"); + + /* + * Theoretical race here: the in-service queue can be NULL or + * different from the queue that was idling if a new request + * arrives for the current queue and there is a full dispatch + * cycle that changes the in-service queue. This can hardly + * happen, but in the worst case we just expire a queue too + * early. + */ + if (bfqq) + bfq_idle_slice_timer_body(bfqq); + + return HRTIMER_NORESTART; +} + +static void __bfq_put_async_bfqq(struct bfq_data *bfqd, + struct bfq_queue **bfqq_ptr) +{ + struct bfq_group *root_group = bfqd->root_group; + struct bfq_queue *bfqq = *bfqq_ptr; + + bfq_log(bfqd, "%p", bfqq); + if (bfqq) { + bfq_bfqq_move(bfqd, bfqq, root_group); + bfq_log_bfqq(bfqd, bfqq, "putting %p, %d", + bfqq, bfqq->ref); + bfq_put_queue(bfqq); + *bfqq_ptr = NULL; + } +} + +/* + * Release all the bfqg references to its async queues. If we are + * deallocating the group these queues may still contain requests, so + * 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) +{ + int i, j; + + for (i = 0; i < 2; i++) + for (j = 0; j < IOPRIO_BE_NR; j++) + __bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]); + + __bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq); +} + +/* + * See the comments on bfq_limit_depth for the purpose of + * the depths set in the function. Return minimum shallow depth we'll use. + */ +static unsigned int bfq_update_depths(struct bfq_data *bfqd, + struct sbitmap_queue *bt) +{ + unsigned int i, j, min_shallow = UINT_MAX; + + /* + * In-word depths if no bfq_queue is being weight-raised: + * leaving 25% of tags only for sync reads. + * + * In next formulas, right-shift the value + * (1U<sb.shift), instead of computing directly + * (1U<<(bt->sb.shift - something)), to be robust against + * any possible value of bt->sb.shift, without having to + * limit 'something'. + */ + /* no more than 50% of tags for async I/O */ + bfqd->word_depths[0][0] = max((1U<sb.shift)>>1, 1U); + /* + * no more than 75% of tags for sync writes (25% extra tags + * w.r.t. async I/O, to prevent async I/O from starving sync + * writes) + */ + bfqd->word_depths[0][1] = max(((1U<sb.shift) * 3)>>2, 1U); + + /* + * In-word depths in case some bfq_queue is being weight- + * raised: leaving ~63% of tags for sync reads. This is the + * highest percentage for which, in our tests, application + * start-up times didn't suffer from any regression due to tag + * shortage. + */ + /* no more than ~18% of tags for async I/O */ + bfqd->word_depths[1][0] = max(((1U<sb.shift) * 3)>>4, 1U); + /* no more than ~37% of tags for sync writes (~20% extra tags) */ + bfqd->word_depths[1][1] = max(((1U<sb.shift) * 6)>>4, 1U); + + for (i = 0; i < 2; i++) + for (j = 0; j < 2; j++) + min_shallow = min(min_shallow, bfqd->word_depths[i][j]); + + return min_shallow; +} + +static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx) +{ + struct bfq_data *bfqd = hctx->queue->elevator->elevator_data; + struct blk_mq_tags *tags = hctx->sched_tags; + unsigned int min_shallow; + + min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags); + sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow); +} + +static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index) +{ + bfq_depth_updated(hctx); + return 0; +} + +static void bfq_exit_queue(struct elevator_queue *e) +{ + struct bfq_data *bfqd = e->elevator_data; + struct bfq_queue *bfqq, *n; + + bfq_log(bfqd, "starting ..."); + + hrtimer_cancel(&bfqd->idle_slice_timer); + + BUG_ON(bfqd->in_service_queue); + BUG_ON(!list_empty(&bfqd->active_list)); + + spin_lock_irq(&bfqd->lock); + list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list) + bfq_deactivate_bfqq(bfqd, bfqq, false, false); + spin_unlock_irq(&bfqd->lock); + + hrtimer_cancel(&bfqd->idle_slice_timer); + + BUG_ON(hrtimer_active(&bfqd->idle_slice_timer)); + +#ifdef BFQ_GROUP_IOSCHED_ENABLED + /* release oom-queue reference to root group */ + bfqg_and_blkg_put(bfqd->root_group); + + blkcg_deactivate_policy(bfqd->queue, &blkcg_policy_bfq); +#else + spin_lock_irq(&bfqd->lock); + bfq_put_async_queues(bfqd, bfqd->root_group); + kfree(bfqd->root_group); + spin_unlock_irq(&bfqd->lock); +#endif + + bfq_log(bfqd, "finished ..."); + kfree(bfqd); +} + +static void bfq_init_root_group(struct bfq_group *root_group, + struct bfq_data *bfqd) +{ + int i; + +#ifdef BFQ_GROUP_IOSCHED_ENABLED + root_group->entity.parent = NULL; + root_group->my_entity = NULL; + root_group->bfqd = bfqd; +#endif + root_group->rq_pos_tree = RB_ROOT; + for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) + root_group->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT; + root_group->sched_data.bfq_class_idle_last_service = jiffies; +} + +static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) +{ + struct bfq_data *bfqd; + struct elevator_queue *eq; + + eq = elevator_alloc(q, e); + if (!eq) + return -ENOMEM; + + bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node); + if (!bfqd) { + kobject_put(&eq->kobj); + return -ENOMEM; + } + eq->elevator_data = bfqd; + + spin_lock_irq(q->queue_lock); + q->elevator = eq; + spin_unlock_irq(q->queue_lock); + + /* + * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues. + * Grab a permanent reference to it, so that the normal code flow + * will not attempt to free it. + */ + bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, NULL, 1, 0); + bfqd->oom_bfqq.ref++; + bfqd->oom_bfqq.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO; + 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 + * class won't be changed any more. + */ + bfqd->oom_bfqq.entity.prio_changed = 1; + + bfqd->queue = q; + INIT_LIST_HEAD(&bfqd->dispatch); + + hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); + bfqd->idle_slice_timer.function = bfq_idle_slice_timer; + + bfqd->queue_weights_tree = RB_ROOT; + bfqd->num_groups_with_pending_reqs = 0; + + INIT_LIST_HEAD(&bfqd->active_list); + INIT_LIST_HEAD(&bfqd->idle_list); + INIT_HLIST_HEAD(&bfqd->burst_list); + + bfqd->hw_tag = -1; + + bfqd->bfq_max_budget = bfq_default_max_budget; + + bfqd->bfq_fifo_expire[0] = bfq_fifo_expire[0]; + bfqd->bfq_fifo_expire[1] = bfq_fifo_expire[1]; + bfqd->bfq_back_max = bfq_back_max; + bfqd->bfq_back_penalty = bfq_back_penalty; + bfqd->bfq_slice_idle = bfq_slice_idle; + bfqd->bfq_timeout = bfq_timeout; + + bfqd->bfq_requests_within_timer = 120; + + bfqd->bfq_large_burst_thresh = 8; + bfqd->bfq_burst_interval = msecs_to_jiffies(180); + + bfqd->low_latency = true; + + /* + * Trade-off between responsiveness and fairness. + */ + bfqd->bfq_wr_coeff = 30; + bfqd->bfq_wr_rt_max_time = msecs_to_jiffies(300); + bfqd->bfq_wr_max_time = 0; + bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000); + bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500); + bfqd->bfq_wr_max_softrt_rate = 7000; /* + * Approximate rate required + * to playback or record a + * high-definition compressed + * video. + */ + bfqd->wr_busy_queues = 0; + + /* + * Begin by assuming, optimistically, that the device peak + * rate is equal to 2/3 of the highest reference rate. + */ + bfqd->rate_dur_prod = ref_rate[blk_queue_nonrot(bfqd->queue)] * + ref_wr_duration[blk_queue_nonrot(bfqd->queue)]; + bfqd->peak_rate = ref_rate[blk_queue_nonrot(bfqd->queue)] * 2 / 3; + + spin_lock_init(&bfqd->lock); + + /* + * The invocation of the next bfq_create_group_hierarchy + * function is the head of a chain of function calls + * (bfq_create_group_hierarchy->blkcg_activate_policy-> + * blk_mq_freeze_queue) that may lead to the invocation of the + * has_work hook function. For this reason, + * bfq_create_group_hierarchy is invoked only after all + * scheduler data has been initialized, apart from the fields + * that can be initialized only after invoking + * bfq_create_group_hierarchy. This, in particular, enables + * has_work to correctly return false. Of course, to avoid + * other inconsistencies, the blk-mq stack must then refrain + * from invoking further scheduler hooks before this init + * function is finished. + */ + bfqd->root_group = bfq_create_group_hierarchy(bfqd, q->node); + if (!bfqd->root_group) + goto out_free; + bfq_init_root_group(bfqd->root_group, bfqd); + bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group); + + wbt_disable_default(q); + return 0; + +out_free: + kfree(bfqd); + kobject_put(&eq->kobj); + return -ENOMEM; +} + +static void bfq_slab_kill(void) +{ + kmem_cache_destroy(bfq_pool); +} + +static int __init bfq_slab_setup(void) +{ + bfq_pool = KMEM_CACHE(bfq_queue, 0); + if (!bfq_pool) + return -ENOMEM; + return 0; +} + +static ssize_t bfq_var_show(unsigned int var, char *page) +{ + return sprintf(page, "%u\n", var); +} + +static ssize_t bfq_var_store(unsigned long *var, const char *page, + size_t count) +{ + unsigned long new_val; + int ret = kstrtoul(page, 10, &new_val); + + if (ret == 0) + *var = new_val; + + return count; +} + +static ssize_t bfq_wr_max_time_show(struct elevator_queue *e, char *page) +{ + struct bfq_data *bfqd = e->elevator_data; + + return sprintf(page, "%d\n", bfqd->bfq_wr_max_time > 0 ? + jiffies_to_msecs(bfqd->bfq_wr_max_time) : + jiffies_to_msecs(bfq_wr_duration(bfqd))); +} + +static ssize_t bfq_weights_show(struct elevator_queue *e, char *page) +{ + struct bfq_queue *bfqq; + struct bfq_data *bfqd = e->elevator_data; + ssize_t num_char = 0; + + num_char += sprintf(page + num_char, "Tot reqs queued %d\n\n", + bfqd->queued); + + spin_lock_irq(&bfqd->lock); + + num_char += sprintf(page + num_char, "Active:\n"); + list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) { + num_char += sprintf(page + num_char, + "pid%d: weight %hu, nr_queued %d %d, ", + bfqq->pid, + bfqq->entity.weight, + bfqq->queued[0], + bfqq->queued[1]); + num_char += sprintf(page + num_char, + "dur %d/%u\n", + jiffies_to_msecs( + jiffies - + bfqq->last_wr_start_finish), + jiffies_to_msecs(bfqq->wr_cur_max_time)); + } + + num_char += sprintf(page + num_char, "Idle:\n"); + list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) { + num_char += sprintf(page + num_char, + "pid%d: weight %hu, dur %d/%u\n", + bfqq->pid, + bfqq->entity.weight, + jiffies_to_msecs(jiffies - + bfqq->last_wr_start_finish), + jiffies_to_msecs(bfqq->wr_cur_max_time)); + } + + spin_unlock_irq(&bfqd->lock); + + return num_char; +} + +#define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \ +static ssize_t __FUNC(struct elevator_queue *e, char *page) \ +{ \ + struct bfq_data *bfqd = e->elevator_data; \ + u64 __data = __VAR; \ + if (__CONV == 1) \ + __data = jiffies_to_msecs(__data); \ + else if (__CONV == 2) \ + __data = div_u64(__data, NSEC_PER_MSEC); \ + return bfq_var_show(__data, (page)); \ +} +SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 2); +SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 2); +SHOW_FUNCTION(bfq_back_seek_max_show, bfqd->bfq_back_max, 0); +SHOW_FUNCTION(bfq_back_seek_penalty_show, bfqd->bfq_back_penalty, 0); +SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 2); +SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0); +SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout, 1); +SHOW_FUNCTION(bfq_strict_guarantees_show, bfqd->strict_guarantees, 0); +SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0); +SHOW_FUNCTION(bfq_wr_coeff_show, bfqd->bfq_wr_coeff, 0); +SHOW_FUNCTION(bfq_wr_rt_max_time_show, bfqd->bfq_wr_rt_max_time, 1); +SHOW_FUNCTION(bfq_wr_min_idle_time_show, bfqd->bfq_wr_min_idle_time, 1); +SHOW_FUNCTION(bfq_wr_min_inter_arr_async_show, bfqd->bfq_wr_min_inter_arr_async, + 1); +SHOW_FUNCTION(bfq_wr_max_softrt_rate_show, bfqd->bfq_wr_max_softrt_rate, 0); +#undef SHOW_FUNCTION + +#define USEC_SHOW_FUNCTION(__FUNC, __VAR) \ +static ssize_t __FUNC(struct elevator_queue *e, char *page) \ +{ \ + struct bfq_data *bfqd = e->elevator_data; \ + u64 __data = __VAR; \ + __data = div_u64(__data, NSEC_PER_USEC); \ + return bfq_var_show(__data, (page)); \ +} +USEC_SHOW_FUNCTION(bfq_slice_idle_us_show, bfqd->bfq_slice_idle); +#undef USEC_SHOW_FUNCTION + +#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ +static ssize_t \ +__FUNC(struct elevator_queue *e, const char *page, size_t count) \ +{ \ + struct bfq_data *bfqd = e->elevator_data; \ + unsigned long uninitialized_var(__data); \ + int ret = bfq_var_store(&__data, (page), count); \ + if (__data < (MIN)) \ + __data = (MIN); \ + else if (__data > (MAX)) \ + __data = (MAX); \ + if (__CONV == 1) \ + *(__PTR) = msecs_to_jiffies(__data); \ + else if (__CONV == 2) \ + *(__PTR) = (u64)__data * NSEC_PER_MSEC; \ + else \ + *(__PTR) = __data; \ + return ret; \ +} +STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1, + INT_MAX, 2); +STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1, + INT_MAX, 2); +STORE_FUNCTION(bfq_back_seek_max_store, &bfqd->bfq_back_max, 0, INT_MAX, 0); +STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1, + INT_MAX, 0); +STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 2); +STORE_FUNCTION(bfq_wr_coeff_store, &bfqd->bfq_wr_coeff, 1, INT_MAX, 0); +STORE_FUNCTION(bfq_wr_max_time_store, &bfqd->bfq_wr_max_time, 0, INT_MAX, 1); +STORE_FUNCTION(bfq_wr_rt_max_time_store, &bfqd->bfq_wr_rt_max_time, 0, INT_MAX, + 1); +STORE_FUNCTION(bfq_wr_min_idle_time_store, &bfqd->bfq_wr_min_idle_time, 0, + INT_MAX, 1); +STORE_FUNCTION(bfq_wr_min_inter_arr_async_store, + &bfqd->bfq_wr_min_inter_arr_async, 0, INT_MAX, 1); +STORE_FUNCTION(bfq_wr_max_softrt_rate_store, &bfqd->bfq_wr_max_softrt_rate, 0, + INT_MAX, 0); +#undef STORE_FUNCTION + +#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX) \ +static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)\ +{ \ + struct bfq_data *bfqd = e->elevator_data; \ + unsigned long uninitialized_var(__data); \ + int ret = bfq_var_store(&__data, (page), count); \ + if (__data < (MIN)) \ + __data = (MIN); \ + else if (__data > (MAX)) \ + __data = (MAX); \ + *(__PTR) = (u64)__data * NSEC_PER_USEC; \ + return ret; \ +} +USEC_STORE_FUNCTION(bfq_slice_idle_us_store, &bfqd->bfq_slice_idle, 0, + UINT_MAX); +#undef USEC_STORE_FUNCTION + +/* do nothing for the moment */ +static ssize_t bfq_weights_store(struct elevator_queue *e, + const char *page, size_t count) +{ + return count; +} + +static ssize_t bfq_max_budget_store(struct elevator_queue *e, + const char *page, size_t count) +{ + struct bfq_data *bfqd = e->elevator_data; + unsigned long uninitialized_var(__data); + int ret = bfq_var_store(&__data, (page), count); + + if (__data == 0) + bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd); + else { + if (__data > INT_MAX) + __data = INT_MAX; + bfqd->bfq_max_budget = __data; + } + + bfqd->bfq_user_max_budget = __data; + + return ret; +} + +/* + * Leaving this name to preserve name compatibility with cfq + * parameters, but this timeout is used for both sync and async. + */ +static ssize_t bfq_timeout_sync_store(struct elevator_queue *e, + const char *page, size_t count) +{ + struct bfq_data *bfqd = e->elevator_data; + unsigned long uninitialized_var(__data); + int ret = bfq_var_store(&__data, (page), count); + + if (__data < 1) + __data = 1; + else if (__data > INT_MAX) + __data = INT_MAX; + + bfqd->bfq_timeout = msecs_to_jiffies(__data); + if (bfqd->bfq_user_max_budget == 0) + bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd); + + return ret; +} + +static ssize_t bfq_strict_guarantees_store(struct elevator_queue *e, + const char *page, size_t count) +{ + struct bfq_data *bfqd = e->elevator_data; + unsigned long uninitialized_var(__data); + int ret = bfq_var_store(&__data, (page), count); + + if (__data > 1) + __data = 1; + if (!bfqd->strict_guarantees && __data == 1 + && bfqd->bfq_slice_idle < 8 * NSEC_PER_MSEC) + bfqd->bfq_slice_idle = 8 * NSEC_PER_MSEC; + + bfqd->strict_guarantees = __data; + + return ret; +} + +static ssize_t bfq_low_latency_store(struct elevator_queue *e, + const char *page, size_t count) +{ + struct bfq_data *bfqd = e->elevator_data; + unsigned long uninitialized_var(__data); + int ret = bfq_var_store(&__data, (page), count); + + if (__data > 1) + __data = 1; + if (__data == 0 && bfqd->low_latency != 0) + bfq_end_wr(bfqd); + bfqd->low_latency = __data; + + return ret; +} + +#define BFQ_ATTR(name) \ + __ATTR(name, S_IRUGO|S_IWUSR, bfq_##name##_show, bfq_##name##_store) + +static struct elv_fs_entry bfq_attrs[] = { + BFQ_ATTR(fifo_expire_sync), + BFQ_ATTR(fifo_expire_async), + BFQ_ATTR(back_seek_max), + BFQ_ATTR(back_seek_penalty), + BFQ_ATTR(slice_idle), + BFQ_ATTR(slice_idle_us), + BFQ_ATTR(max_budget), + BFQ_ATTR(timeout_sync), + BFQ_ATTR(strict_guarantees), + BFQ_ATTR(low_latency), + BFQ_ATTR(wr_coeff), + BFQ_ATTR(wr_max_time), + BFQ_ATTR(wr_rt_max_time), + BFQ_ATTR(wr_min_idle_time), + BFQ_ATTR(wr_min_inter_arr_async), + BFQ_ATTR(wr_max_softrt_rate), + BFQ_ATTR(weights), + __ATTR_NULL +}; + +static struct elevator_type iosched_bfq_mq = { + .ops.mq = { + .limit_depth = bfq_limit_depth, + .prepare_request = bfq_prepare_request, + .requeue_request = bfq_finish_requeue_request, + .finish_request = bfq_finish_requeue_request, + .exit_icq = bfq_exit_icq, + .insert_requests = bfq_insert_requests, + .dispatch_request = bfq_dispatch_request, + .next_request = elv_rb_latter_request, + .former_request = elv_rb_former_request, + .allow_merge = bfq_allow_bio_merge, + .bio_merge = bfq_bio_merge, + .request_merge = bfq_request_merge, + .requests_merged = bfq_requests_merged, + .request_merged = bfq_request_merged, + .has_work = bfq_has_work, + .depth_updated = bfq_depth_updated, + .init_hctx = bfq_init_hctx, + .init_sched = bfq_init_queue, + .exit_sched = bfq_exit_queue, + }, + + .uses_mq = true, + .icq_size = sizeof(struct bfq_io_cq), + .icq_align = __alignof__(struct bfq_io_cq), + .elevator_attrs = bfq_attrs, + .elevator_name = "bfq-mq", + .elevator_owner = THIS_MODULE, +}; + +#ifdef BFQ_GROUP_IOSCHED_ENABLED +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; + char msg[60] = "BFQ I/O-scheduler: v9"; + +#ifdef BFQ_GROUP_IOSCHED_ENABLED + ret = blkcg_policy_register(&blkcg_policy_bfq); + if (ret) + return ret; +#endif + + ret = -ENOMEM; + if (bfq_slab_setup()) + goto err_pol_unreg; + + /* + * Times to load large popular applications for the typical + * systems installed on the reference devices (see the + * comments before the definition of the next + * array). Actually, we use slightly lower values, as the + * estimated peak rate tends to be smaller than the actual + * peak rate. The reason for this last fact is that estimates + * are computed over much shorter time intervals than the long + * intervals typically used for benchmarking. Why? First, to + * adapt more quickly to variations. Second, because an I/O + * scheduler cannot rely on a peak-rate-evaluation workload to + * be run for a long time. + */ + ref_wr_duration[0] = msecs_to_jiffies(7000); /* actually 8 sec */ + ref_wr_duration[1] = msecs_to_jiffies(2500); /* actually 3 sec */ + + ret = elv_register(&iosched_bfq_mq); + if (ret) + goto slab_kill; + +#ifdef BFQ_GROUP_IOSCHED_ENABLED + strcat(msg, " (with cgroups support)"); +#endif + pr_info("%s", msg); + + return 0; + +slab_kill: + bfq_slab_kill(); +err_pol_unreg: +#ifdef BFQ_GROUP_IOSCHED_ENABLED + blkcg_policy_unregister(&blkcg_policy_bfq); +#endif + return ret; +} + +static void __exit bfq_exit(void) +{ + elv_unregister(&iosched_bfq_mq); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + blkcg_policy_unregister(&blkcg_policy_bfq); +#endif + bfq_slab_kill(); +} + +module_init(bfq_init); +module_exit(bfq_exit); + +MODULE_AUTHOR("Paolo Valente"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("MQ Budget Fair Queueing I/O Scheduler"); diff --git a/block/bfq-mq.h b/block/bfq-mq.h new file mode 100644 index 000000000000..ceb291132a1a --- /dev/null +++ b/block/bfq-mq.h @@ -0,0 +1,1077 @@ +/* + * BFQ v9: data structures and common functions prototypes. + * + * Based on ideas and code from CFQ: + * Copyright (C) 2003 Jens Axboe + * + * Copyright (C) 2008 Fabio Checconi + * Paolo Valente + * + * Copyright (C) 2015 Paolo Valente + * + * Copyright (C) 2017 Paolo Valente + */ + +#ifndef _BFQ_H +#define _BFQ_H + +#include +#include + +/* see comments on CONFIG_BFQ_GROUP_IOSCHED in bfq.h */ +#ifdef CONFIG_MQ_BFQ_GROUP_IOSCHED +#define BFQ_GROUP_IOSCHED_ENABLED +#endif + +#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; + + struct bfq_entity *first_idle; /* idle entity with minimum F_i */ + struct bfq_entity *last_idle; /* idle entity with maximum F_i */ + + u64 vtime; /* scheduler virtual time */ + /* 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 in a hierarchical setup. + * + * 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+. + * + * The schedule is implemented by the service trees, plus the field + * @next_in_service, which points to the entity on the active trees + * that will be served next, if 1) no changes in the schedule occurs + * before the current in-service entity is expired, 2) the in-service + * queue becomes idle when it expires, and 3) if the entity pointed by + * in_service_entity is not a queue, then the in-service child entity + * of the entity pointed by in_service_entity becomes idle on + * expiration. This peculiar definition allows for the following + * optimization, not yet exploited: while a given entity is still in + * service, we already know which is the best candidate for next + * service among the other active entitities in the same parent + * entity. We can then quickly compare the timestamps of the + * in-service entity with those of such best candidate. + * + * All the fields are protected by the queue lock of the containing + * bfqd. + */ +struct bfq_sched_data { + struct bfq_entity *in_service_entity; /* entity in service */ + /* head-of-the-line entity in the scheduler (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 queues + * with a given weight. + */ +struct bfq_weight_counter { + unsigned int weight; /* weight of the queues this counter refers to */ + unsigned int num_active; /* nr of active queues with this weight */ + /* + * Weights tree member (see bfq_data's @queue_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 { + struct rb_node rb_node; /* service_tree member */ + + /* + * 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; + + u64 finish; /* B-WF2Q+ finish timestamp (aka F_i) */ + u64 start; /* B-WF2Q+ start timestamp (aka S_i) */ + + /* 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; + + unsigned int weight; /* weight of the queue */ + unsigned int new_weight; /* next weight if a change is in progress */ + + /* original weight, used to implement weight boosting */ + unsigned 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; + + /* flag, set if the entity is counted in groups_with_pending_reqs */ + bool in_groups_with_pending_reqs; +}; + +struct bfq_group; + +/** + * struct bfq_ttime - per process thinktime stats. + */ +struct bfq_ttime { + u64 last_end_request; /* completion time of last request */ + + u64 ttime_total; /* total process thinktime */ + unsigned long ttime_samples; /* number of thinktime samples */ + u64 ttime_mean; /* average process thinktime */ + +}; + +/** + * 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; + + /* pointer to the weight counter associated with this queue */ + struct bfq_weight_counter *weight_counter; + + /* 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; + + unsigned int flags; /* status 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; + /* + * Cumulative service received from the @bfq_queue since its + * last transition to weight-raised state. + */ + unsigned long service_from_wr; + /* + * 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 */ + unsigned long first_IO_time; /* time of first I/O for this queue */ + + /* max service rate measured so far */ + u32 max_service_rate; + /* + * Ratio between the service received by bfqq while it is in + * service, and the cumulative service (of requests of other + * queues) that may be injected while bfqq is empty but still + * in service. To increase precision, the coefficient is + * measured in tenths of unit. Here are some example of (1) + * ratios, (2) resulting percentages of service injected + * w.r.t. to the total service dispatched while bfqq is in + * service, and (3) corresponding values of the coefficient: + * 1 (50%) -> 10 + * 2 (33%) -> 20 + * 10 (9%) -> 100 + * 9.9 (9%) -> 99 + * 1.5 (40%) -> 15 + * 0.5 (66%) -> 5 + * 0.1 (90%) -> 1 + * + * So, if the coefficient is lower than 10, then + * injected service is more than bfqq service. + */ + unsigned int inject_coeff; + /* amount of service injected in current service slot */ + unsigned int injected_service; +}; + +/** + * 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 BFQ_GROUP_IOSCHED_ENABLED + uint64_t blkcg_serial_nr; /* the current blkcg serial */ +#endif + + /* + * Snapshot of the has_short_time flag before merging; taken + * to remember its value while the queue is merged, so as to + * be able to restore it in case of split. + */ + bool saved_has_short_ttime; + /* + * 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; +}; + +/** + * 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; + + /* + * Number of groups with at least one descendant process that + * has at least one request waiting for completion. Note that + * this accounts for also requests already dispatched, but not + * yet completed. Therefore this number of groups may differ + * (be larger) than the number of active groups, as a group is + * considered active only if its corresponding entity has + * descendant queues with at least one request queued. This + * number is used to decide whether a scenario is symmetric. + * For a detailed explanation see comments on the computation + * of the variable asymmetric_scenario in the function + * bfq_better_to_idle(). + * + * However, it is hard to compute this number exactly, for + * groups with multiple descendant processes. Consider a group + * that is inactive, i.e., that has no descendant process with + * pending I/O inside BFQ queues. Then suppose that + * num_groups_with_pending_reqs is still accounting for this + * group, because the group has descendant processes with some + * I/O request still in flight. num_groups_with_pending_reqs + * should be decremented when the in-flight request of the + * last descendant process is finally completed (assuming that + * nothing else has changed for the group in the meantime, in + * terms of composition of the group and active/inactive state of child + * groups and processes). To accomplish this, an additional + * pending-request counter must be added to entities, and must + * be updated correctly. To avoid this additional field and operations, + * we resort to the following tradeoff between simplicity and + * accuracy: for an inactive group that is still counted in + * num_groups_with_pending_reqs, we decrement + * num_groups_with_pending_reqs when the first descendant + * process of the group remains with no request waiting for + * completion. + * + * Even this simpler decrement strategy requires a little + * carefulness: to avoid multiple decrements, we flag a group, + * more precisely an entity representing a group, as still + * counted in num_groups_with_pending_reqs when it becomes + * inactive. Then, when the first descendant queue of the + * entity remains with no request waiting for completion, + * num_groups_with_pending_reqs is decremented, and this flag + * is reset. After this flag is reset for the entity, + * num_groups_with_pending_reqs won't be decremented any + * longer in case a new descendant queue of the entity remains + * with no request waiting for completion. + */ + unsigned int num_groups_with_pending_reqs; + + /* + * Per-class (RT, BE, IDLE) number of bfq_queues containing + * requests (including the queue in service, even if it is + * idling). + */ + unsigned int busy_queues[3]; + /* 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; + + /* position of the last served request for the in-service queue */ + sector_t in_serv_last_pos; + + /* 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 + * [(sectors/usec) / 2^BFQ_RATE_SHIFT]. 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 ref_rate*ref_wr_duration, used + * for computing the maximum duration of weight raising + * automatically. + */ + u64 rate_dur_prod; + + /* 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; + /* Extra flag used only for TESTING */ + bool bio_bfqq_set; + + /* + * Depth limits used in bfq_limit_depth (see comments on the + * function) + */ + unsigned int word_depths[2][2]; +}; + +enum bfqq_state_flags { + BFQ_BFQQ_FLAG_just_created = 0, /* queue just allocated */ + BFQ_BFQQ_FLAG_busy, /* has requests or is in service */ + BFQ_BFQQ_FLAG_wait_request, /* waiting for a request */ + BFQ_BFQQ_FLAG_non_blocking_wait_rq, /* + * waiting for a request + * without idling the device + */ + BFQ_BFQQ_FLAG_fifo_expire, /* FIFO checked in this slice */ + BFQ_BFQQ_FLAG_has_short_ttime, /* queue has a short think time */ + BFQ_BFQQ_FLAG_sync, /* synchronous queue */ + BFQ_BFQQ_FLAG_IO_bound, /* + * bfqq has timed-out at least once + * having consumed at most 2/10 of + * its budget + */ + BFQ_BFQQ_FLAG_in_large_burst, /* + * bfqq activated in a large burst, + * see comments to bfq_handle_burst. + */ + BFQ_BFQQ_FLAG_softrt_update, /* + * may need softrt-next-start + * update + */ + BFQ_BFQQ_FLAG_coop, /* bfqq is shared */ + BFQ_BFQQ_FLAG_split_coop /* shared bfqq will be split */ +}; + +#define BFQ_BFQQ_FNS(name) \ +static void bfq_mark_bfqq_##name(struct bfq_queue *bfqq) \ +{ \ + (bfqq)->flags |= (1 << BFQ_BFQQ_FLAG_##name); \ +} \ +static void bfq_clear_bfqq_##name(struct bfq_queue *bfqq) \ +{ \ + (bfqq)->flags &= ~(1 << BFQ_BFQQ_FLAG_##name); \ +} \ +static int bfq_bfqq_##name(const struct bfq_queue *bfqq) \ +{ \ + return ((bfqq)->flags & (1 << BFQ_BFQQ_FLAG_##name)) != 0; \ +} + +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(has_short_ttime); +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_REDIRECT_TO_CONSOLE + +static const char *checked_dev_name(const struct device *dev) +{ + static const char nodev[] = "nodev"; + + if (dev) + return dev_name(dev); + + return nodev; +} + +#ifdef BFQ_GROUP_IOSCHED_ENABLED +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 { \ + pr_crit("%s bfq%d%c %s [%s] " fmt "\n", \ + checked_dev_name((bfqd)->queue->backing_dev_info->dev), \ + (bfqq)->pid, \ + bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \ + bfqq_group(bfqq)->blkg_path, __func__, ##args); \ +} while (0) + +#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do { \ + pr_crit("%s %s [%s] " fmt "\n", \ + checked_dev_name((bfqd)->queue->backing_dev_info->dev), \ + bfqg->blkg_path, __func__, ##args); \ +} while (0) + +#else /* BFQ_GROUP_IOSCHED_ENABLED */ + +#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \ + pr_crit("%s bfq%d%c [%s] " fmt "\n", \ + checked_dev_name((bfqd)->queue->backing_dev_info->dev), \ + (bfqq)->pid, bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \ + __func__, ##args) +#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do {} while (0) + +#endif /* BFQ_GROUP_IOSCHED_ENABLED */ + +#define bfq_log(bfqd, fmt, args...) \ + pr_crit("%s bfq [%s] " fmt "\n", \ + checked_dev_name((bfqd)->queue->backing_dev_info->dev), \ + __func__, ##args) + +#else /* CONFIG_BFQ_REDIRECT_TO_CONSOLE */ + +#if !defined(CONFIG_BLK_DEV_IO_TRACE) + +/* Avoid possible "unused-variable" warning. See commit message. */ + +#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) ((void) (bfqq)) + +#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) ((void) (bfqg)) + +#define bfq_log(bfqd, fmt, args...) do {} while (0) + +#else /* CONFIG_BLK_DEV_IO_TRACE */ + +#include + +#ifdef BFQ_GROUP_IOSCHED_ENABLED +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 { \ + blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s [%s] " fmt, \ + (bfqq)->pid, \ + bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \ + bfqq_group(bfqq)->blkg_path, __func__, ##args); \ +} while (0) + +#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do { \ + blk_add_trace_msg((bfqd)->queue, "%s [%s] " fmt, bfqg->blkg_path, \ + __func__, ##args);\ +} while (0) + +#else /* BFQ_GROUP_IOSCHED_ENABLED */ + +#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \ + blk_add_trace_msg((bfqd)->queue, "bfq%d%c [%s] " fmt, (bfqq)->pid, \ + bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \ + __func__, ##args) +#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do {} while (0) + +#endif /* BFQ_GROUP_IOSCHED_ENABLED */ + +#define bfq_log(bfqd, fmt, args...) \ + blk_add_trace_msg((bfqd)->queue, "bfq [%s] " fmt, __func__, ##args) + +#endif /* CONFIG_BLK_DEV_IO_TRACE */ +#endif /* CONFIG_BFQ_REDIRECT_TO_CONSOLE */ + +/* Expiration reasons. */ +enum bfqq_expiration { + BFQ_BFQQ_TOO_IDLE = 0, /* + * queue has been idling for + * too long + */ + BFQ_BFQQ_BUDGET_TIMEOUT, /* budget took too long to be used */ + BFQ_BFQQ_BUDGET_EXHAUSTED, /* budget consumed */ + BFQ_BFQQ_NO_MORE_REQUESTS, /* the queue has no more requests */ + BFQ_BFQQ_PREEMPTED /* preemption in progress */ +}; + + +struct bfqg_stats { +#if defined(BFQ_GROUP_IOSCHED_ENABLED) && defined(CONFIG_DEBUG_BLK_CGROUP) + /* 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 */ + u64 start_group_wait_time; + u64 start_idle_time; + u64 start_empty_time; + uint16_t flags; +#endif /* BFQ_GROUP_IOSCHED_ENABLED && CONFIG_DEBUG_BLK_CGROUP */ +}; + +#ifdef BFQ_GROUP_IOSCHED_ENABLED +/* + * 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. + * @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; + + /* 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 + +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 unsigned int bfq_tot_busy_queues(struct bfq_data *bfqd) +{ + return bfqd->busy_queues[0] + bfqd->busy_queues[1] + + bfqd->busy_queues[2]; +} + +static struct bfq_service_tree * +bfq_entity_service_tree(struct bfq_entity *entity) +{ + struct bfq_sched_data *sched_data = entity->sched_data; + struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); + unsigned int idx = bfq_class_idx(entity); + + BUG_ON(idx >= BFQ_IOPRIO_CLASSES); + BUG_ON(sched_data == NULL); + + if (bfqq) + bfq_log_bfqq(bfqq->bfqd, bfqq, + "%p %d", + sched_data->service_tree + idx, idx); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + else { + struct bfq_group *bfqg = + container_of(entity, struct bfq_group, entity); + + bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, + "%p %d", + sched_data->service_tree + idx, idx); + } +#endif + 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 BFQ_GROUP_IOSCHED_ENABLED + +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); +#ifdef BFQ_GROUP_IOSCHED_ENABLED +static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg); +#endif +static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq); + +#endif /* _BFQ_H */ diff --git a/block/bfq-sched.c b/block/bfq-sched.c new file mode 100644 index 000000000000..7a4923231106 --- /dev/null +++ b/block/bfq-sched.c @@ -0,0 +1,2077 @@ +/* + * BFQ: Hierarchical B-WF2Q+ scheduler. + * + * Based on ideas and code from CFQ: + * Copyright (C) 2003 Jens Axboe + * + * Copyright (C) 2008 Fabio Checconi + * Paolo Valente + * + * Copyright (C) 2015 Paolo Valente + * + * Copyright (C) 2016 Paolo Valente + */ + +static struct bfq_group *bfqq_group(struct bfq_queue *bfqq); + +/** + * 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, + bool expiration); + +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. + * @expiration: id true, this function is being invoked after the + * expiration of the in-service entity + * + * 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, + bool expiration) +{ + struct bfq_entity *next_in_service = sd->next_in_service; + struct bfq_queue *bfqq; + bool parent_sched_may_change = false; + bool change_without_lookup = 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 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. + */ + change_without_lookup = true; + + /* + * If there is already a next_in_service candidate + * entity, then compare 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; + + change_without_lookup = + (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)); + } + + if (change_without_lookup) { + next_in_service = new_entity; + bfqq = bfq_entity_to_bfqq(next_in_service); + + if (bfqq) + bfq_log_bfqq(bfqq->bfqd, bfqq, + "chose without lookup"); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + else { + struct bfq_group *bfqg = + container_of(next_in_service, + struct bfq_group, entity); + + bfq_log_bfqg((struct bfq_data*)bfqg->bfqd, bfqg, + "chose without lookup"); + } +#endif + } + } + + if (!change_without_lookup) /* lookup needed */ + next_in_service = bfq_lookup_next_entity(sd, expiration); + + if (next_in_service) { + bool new_budget_triggers_change = + bfq_update_parent_budget(next_in_service); + + parent_sched_may_change = !sd->next_in_service || + new_budget_triggers_change; + } + + sd->next_in_service = next_in_service; + + if (!next_in_service) + return parent_sched_may_change; + + bfqq = bfq_entity_to_bfqq(next_in_service); + if (bfqq) + bfq_log_bfqq(bfqq->bfqd, bfqq, + "chosen this queue"); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + else { + struct bfq_group *bfqg = + container_of(next_in_service, + struct bfq_group, entity); + + bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, + "chosen this entity"); + } +#endif + return parent_sched_may_change; +} + +#ifdef BFQ_GROUP_IOSCHED_ENABLED +/* 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; + + BUG_ON(!next_in_service); + + 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; + bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, + "old budg: %d, new budg: %d", + bfqg_entity->budget, next_in_service->budget); + bfqg_entity->budget = next_in_service->budget; + } + + return ret; +} + +/* + * This function tells whether entity stops being a candidate for next + * service, according to the restrictive definition of the field + * next_in_service. In particular, this function is invoked for an + * entity that is about to be set in service. + * + * If entity is a queue, then the entity is no longer a candidate for + * next service according to the that definition, because entity is + * about to become the in-service queue. This function then returns + * true if entity is a queue. + * + * In contrast, entity could still be a candidate for next service if + * it is not a queue, and has more than one active child. In fact, + * even if one of its children is about to be set in service, other + * active children may still be the next to serve, for the parent + * entity, even according to the above definition. As a consequence, a + * non-queue entity is not a candidate for next-service only if it has + * only one active child. And only if this condition holds, then this + * function returns true for a non-queue entity. + */ +static bool bfq_no_longer_next_in_service(struct bfq_entity *entity) +{ + struct bfq_group *bfqg; + + if (bfq_entity_to_bfqq(entity)) + return true; + + bfqg = container_of(entity, struct bfq_group, entity); + + BUG_ON(bfqg == ((struct bfq_data *)(bfqg->bfqd))->root_group); + BUG_ON(bfqg->active_entities == 0); + /* + * The field active_entities does not always contain the + * actual number of active children entities: it happens to + * not account for the in-service entity in case the latter is + * removed from its active tree (which may get done after + * invoking the function bfq_no_longer_next_in_service in + * bfq_get_next_queue). Fortunately, here, i.e., while + * bfq_no_longer_next_in_service is not yet completed in + * bfq_get_next_queue, bfq_active_extract has not yet been + * invoked, and thus active_entities still coincides with the + * actual number of active entities. + */ + if (bfqg->active_entities == 1) + return true; + + return false; +} + +#else /* BFQ_GROUP_IOSCHED_ENABLED */ +#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 /* BFQ_GROUP_IOSCHED_ENABLED */ + +/* + * 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; + + BUG_ON(!entity); + + 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); + unsigned long long start, finish, delta; + + BUG_ON(entity->weight == 0); + + entity->finish = entity->start + + bfq_delta(service, entity->weight); + + start = ((entity->start>>10)*1000)>>12; + finish = ((entity->finish>>10)*1000)>>12; + delta = ((bfq_delta(service, entity->weight)>>10)*1000)>>12; + + if (bfqq) { + bfq_log_bfqq(bfqq->bfqd, bfqq, + "serv %lu, w %d", + service, entity->weight); + bfq_log_bfqq(bfqq->bfqd, bfqq, + "start %llu, finish %llu, delta %llu", + start, finish, delta); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + } else { + struct bfq_group *bfqg = + container_of(entity, struct bfq_group, entity); + + bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, + "group: serv %lu, w %d", + service, entity->weight); + bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, + "group: start %llu, finish %llu, delta %llu", + start, finish, delta); +#endif + } +} + +/** + * 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) +{ + BUG_ON(entity->tree != root); + + 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; + + BUG_ON(entity->tree != &st->idle); + + 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; + + BUG_ON(entity->tree); + + 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); + struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); + + entity->min_start = entity->start; + bfq_update_min(entity, node->rb_right); + bfq_update_min(entity, node->rb_left); + + if (bfqq) { + bfq_log_bfqq(bfqq->bfqd, bfqq, + "new min_start %llu", + ((entity->min_start>>10)*1000)>>12); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + } else { + struct bfq_group *bfqg = + container_of(entity, struct bfq_group, entity); + + bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, + "new min_start %llu", + ((entity->min_start>>10)*1000)>>12); +#endif + } +} + +/** + * 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; +} + +static void bfq_weights_tree_add(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + struct rb_root *root); + +static void __bfq_weights_tree_remove(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + struct rb_root *root); + +static void bfq_weights_tree_remove(struct bfq_data *bfqd, + struct bfq_queue *bfqq); + + +/** + * 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 BFQ_GROUP_IOSCHED_ENABLED + 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 BFQ_GROUP_IOSCHED_ENABLED + sd = entity->sched_data; + bfqg = container_of(sd, struct bfq_group, sched_data); + BUG_ON(!bfqg); + bfqd = (struct bfq_data *)bfqg->bfqd; +#endif + if (bfqq) + list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + if (bfqg != bfqd->root_group) { + BUG_ON(!bfqg); + BUG_ON(!bfqd); + bfqg->active_entities++; + } +#endif +} + +/** + * 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) +{ + BUG_ON(ioprio < 0 || ioprio >= IOPRIO_BE_NR); + 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) +{ + BUG_ON(weight < BFQ_MIN_WEIGHT || weight > BFQ_MAX_WEIGHT); + return IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - weight < 0 ? + 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, "%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 BFQ_GROUP_IOSCHED_ENABLED + 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 BFQ_GROUP_IOSCHED_ENABLED + sd = entity->sched_data; + bfqg = container_of(sd, struct bfq_group, sched_data); + BUG_ON(!bfqg); + bfqd = (struct bfq_data *)bfqg->bfqd; +#endif + if (bfqq) + list_del(&bfqq->bfqq_list); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + if (bfqg != bfqd->root_group) { + BUG_ON(!bfqg); + BUG_ON(!bfqd); + BUG_ON(!bfqg->active_entities); + bfqg->active_entities--; + } +#endif +} + +/** + * 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); + BUG_ON(!entity->on_st); + + entity->on_st = false; + st->wsum -= entity->weight; + if (bfqq && !is_in_service) { + bfq_log_bfqq(bfqq->bfqd, bfqq, "(before): %p %d", + bfqq, bfqq->ref); + 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); +} + +/* + * Update weight and priority of entity. If update_class_too is true, + * then update the ioprio_class of entity too. + * + * The reason why the update of ioprio_class is controlled through the + * last parameter is as follows. Changing the ioprio class of an + * entity implies changing the destination service trees for that + * entity. If such a change occurred when the entity is already on one + * of the service trees for its previous class, then the state of the + * entity would become more complex: none of the new possible service + * trees for the entity, according to bfq_entity_service_tree(), would + * match any of the possible service trees on which the entity + * is. Complex operations involving these trees, such as entity + * activations and deactivations, should take into account this + * additional complexity. To avoid this issue, this function is + * invoked with update_class_too unset in the points in the code where + * entity may happen to be on some tree. + */ +static struct bfq_service_tree * +__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st, + struct bfq_entity *entity, + bool update_class_too) +{ + 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; + struct rb_root *root; +#ifdef BFQ_GROUP_IOSCHED_ENABLED + struct bfq_sched_data *sd; + struct bfq_group *bfqg; +#endif + + if (bfqq) + bfqd = bfqq->bfqd; +#ifdef BFQ_GROUP_IOSCHED_ENABLED + else { + sd = entity->my_sched_data; + bfqg = container_of(sd, struct bfq_group, sched_data); + BUG_ON(!bfqg); + bfqd = (struct bfq_data *)bfqg->bfqd; + BUG_ON(!bfqd); + } +#endif + + BUG_ON(entity->tree && update_class_too); + BUG_ON(old_st->wsum < entity->weight); + 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 && update_class_too) + bfqq->ioprio_class = bfqq->new_ioprio_class; + + /* + * Reset prio_changed only if the ioprio_class change + * is not pending any longer. + */ + 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); + /* + * If the weight of the entity changes and the entity is a + * queue, remove the entity from its old weight counter (if + * there is a counter associated with the entity). + */ + if (prev_weight != new_weight && bfqq) { + bfq_log_bfqq(bfqq->bfqd, bfqq, + "weight changed %d %d(%d %d)", + prev_weight, new_weight, + entity->orig_weight, + bfqq->wr_coeff); + + root = &bfqd->queue_weights_tree; + __bfq_weights_tree_remove(bfqd, bfqq, root); + } + entity->weight = new_weight; + /* + * Add the entity, if it is not a weight-raised queue, to the + * counter associated with its new weight. + */ + if (prev_weight != new_weight && bfqq && bfqq->wr_coeff == 1) { + /* If we get here, root has been initialized. */ + bfq_weights_tree_add(bfqd, bfqq, root); + } + + new_st->wsum += entity->weight; + + if (new_st != old_st) { + BUG_ON(!update_class_too); + entity->start = new_st->vtime; + } + } + + return new_st; +} + +#ifdef BFQ_GROUP_IOSCHED_ENABLED +static void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg); +#endif + +/** + * 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; + + if (!bfqq->service_from_backlogged) + bfqq->first_IO_time = jiffies; + + if (bfqq->wr_coeff > 1) + bfqq->service_from_wr += served; + + bfqq->service_from_backlogged += served; + for_each_entity(entity) { + st = bfq_entity_service_tree(entity); + + entity->service += served; + + BUG_ON(st->wsum == 0); + + st->vtime += bfq_delta(served, st->wsum); + bfq_forget_idle(st); + } +#ifndef BFQ_MQ +#ifdef BFQ_GROUP_IOSCHED_ENABLED + bfqg_stats_set_start_empty_time(bfqq_group(bfqq)); +#endif +#endif + st = bfq_entity_service_tree(&bfqq->entity); + bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %d secs, vtime %llu on %p", + served, ((st->vtime>>10)*1000)>>12, st); +} + +/** + * 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; + unsigned long timeout_ms = jiffies_to_msecs(bfq_timeout); + unsigned long bounded_time_ms = min(time_ms, timeout_ms); + int serv_to_charge_for_time = + (bfqd->bfq_max_budget * bounded_time_ms) / timeout_ms; + int tot_serv_to_charge = max(serv_to_charge_for_time, entity->service); + + bfq_log_bfqq(bfqq->bfqd, bfqq, + "%lu/%lu ms, %d/%d/%d/%d sectors", + time_ms, timeout_ms, + entity->service, + tot_serv_to_charge, + bfqd->bfq_max_budget, + entity->budget); + + /* 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); + struct bfq_sched_data *sd = entity->sched_data; + + /* + * When this function is invoked, entity is not in any service + * tree, then it is safe to invoke next function with the last + * parameter set (see the comments on the function). + */ + BUG_ON(entity->tree); + st = __bfq_entity_update_weight_prio(st, entity, true); + 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; + + if (bfqq) { + bfq_log_bfqq(bfqq->bfqd, bfqq, + "new queue finish %llu", + ((entity->finish>>10)*1000)>>12); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + } else { + struct bfq_group *bfqg = + container_of(entity, struct bfq_group, entity); + + bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, + "new group finish %llu", + ((entity->finish>>10)*1000)>>12); +#endif + } + } + + bfq_active_insert(st, entity); + + if (bfqq) { + bfq_log_bfqq(bfqq->bfqd, bfqq, + "queue %seligible in st %p", + entity->start <= st->vtime ? "" : "non ", st); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + } else { + struct bfq_group *bfqg = + container_of(entity, struct bfq_group, entity); + + bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, + "group %seligible in st %p", + entity->start <= st->vtime ? "" : "non ", st); +#endif + } + BUG_ON(RB_EMPTY_ROOT(&st->active)); + BUG_ON(&st->active != &sd->service_tree->active && + &st->active != &(sd->service_tree+1)->active && + &st->active != &(sd->service_tree+2)->active); +} + +/** + * __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, after possibly extracting it + * from its idle tree. + */ +static void __bfq_activate_entity(struct bfq_entity *entity, + bool non_blocking_wait_rq) +{ + struct bfq_sched_data *sd = entity->sched_data; + struct bfq_service_tree *st = bfq_entity_service_tree(entity); + struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); + bool backshifted = false; + unsigned long long min_vstart; + + BUG_ON(!sd); + BUG_ON(!st); + + /* 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); + BUG_ON(entity->tree); + entity->start = bfq_gt(min_vstart, entity->finish) ? + min_vstart : entity->finish; + } else { + BUG_ON(entity->tree); + /* + * 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); + + BUG_ON(entity->on_st && bfqq); + +#ifdef BFQ_GROUP_IOSCHED_ENABLED + if (entity->on_st && !bfqq) { + struct bfq_group *bfqg = + container_of(entity, struct bfq_group, + entity); + + bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, + bfqg, + "activate bug, class %d in_service %p", + bfq_class_idx(entity), sd->in_service_entity); + } +#endif + BUG_ON(entity->on_st && !bfqq); + entity->on_st = true; + } + +#ifdef BFQ_GROUP_IOSCHED_ENABLED + if (!bfq_entity_to_bfqq(entity)) { /* bfq_group */ + struct bfq_group *bfqg = + container_of(entity, struct bfq_group, entity); + struct bfq_data *bfqd = bfqg->bfqd; + + BUG_ON(!bfqd); + if (!entity->in_groups_with_pending_reqs) { + entity->in_groups_with_pending_reqs = true; + bfqd->num_groups_with_pending_reqs++; + } + bfq_log_bfqg(bfqd, bfqg, "num_groups_with_pending_reqs %u", + bfqd->num_groups_with_pending_reqs); + } +#endif + + 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); + + BUG_ON(!sd); + BUG_ON(!st); + + BUG_ON(entity != sd->in_service_entity && + entity->tree != &st->active); + + 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; + BUG_ON(entity->tree && entity->tree == &st->idle); + BUG_ON(entity->tree && entity->tree != &st->active); + /* + * In addition, if the entity had more than one child + * when set in service, then it 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_requeue_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 + * @expiration: true if this function is being invoked in the expiration path + * of the in-service queue + */ +static void bfq_activate_requeue_entity(struct bfq_entity *entity, + bool non_blocking_wait_rq, + bool requeue, bool expiration) +{ + struct bfq_sched_data *sd; + + for_each_entity(entity) { + BUG_ON(!entity); + sd = entity->sched_data; + __bfq_activate_requeue_entity(entity, sd, non_blocking_wait_rq); + + BUG_ON(RB_EMPTY_ROOT(&sd->service_tree->active) && + RB_EMPTY_ROOT(&(sd->service_tree+1)->active) && + RB_EMPTY_ROOT(&(sd->service_tree+2)->active)); + + if (!bfq_update_next_in_service(sd, entity, expiration) && + !requeue) { + BUG_ON(!sd->next_in_service); + break; + } + BUG_ON(!sd->next_in_service); + } +} + +/** + * __bfq_deactivate_entity - update sched_data and service trees for + * entity, so as to represent entity as inactive + * @entity: the entity being deactivated. + * @ins_into_idle_tree: if false, the entity will not be put into the + * idle tree. + * + * If necessary and allowed, puts entity into the idle tree. NOTE: + * entity may be on no tree if in service. + */ +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; + bool is_in_service; + + if (!entity->on_st) { /* entity never activated, or already inactive */ + BUG_ON(sd && entity == sd->in_service_entity); + return false; + } + + /* + * If we get here, then entity is active, which implies that + * bfq_group_set_parent has already been invoked for the group + * represented by entity. Therefore, the field + * entity->sched_data has been set, and we can safely use it. + */ + st = bfq_entity_service_tree(entity); + is_in_service = entity == sd->in_service_entity; + + BUG_ON(is_in_service && entity->tree && entity->tree != &st->active); + + bfq_calc_finish(entity, entity->service); + + if (is_in_service) { + sd->in_service_entity = NULL; + } else + /* + * Non in-service entity: nobody will take care of + * resetting its service counter on expiration. Do it + * now. + */ + entity->service = 0; + + if (entity->tree == &st->active) + bfq_active_extract(st, entity); + else if (!is_in_service && entity->tree == &st->idle) + bfq_idle_extract(st, entity); + else if (entity->tree) + BUG(); + + 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 into the idle tree + * @expiration: true if this function is being invoked in the expiration path + * of the in-service queue + */ +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; + + BUG_ON(sd == NULL); /* + * It would mean that this is the + * root group. + */ + + BUG_ON(expiration && entity != sd->in_service_entity); + + BUG_ON(entity != sd->in_service_entity && + entity->tree == + &bfq_entity_service_tree(entity)->active && + !sd->next_in_service); + + 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). + */ + BUG_ON(expiration); /* + * entity cannot be already out of + * any tree + */ + 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, expiration); + + if (sd->next_in_service || sd->in_service_entity) { + /* + * The parent entity is still active, because + * either next_in_service or in_service_entity + * 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. + * + * NOTE If in_service_entity is not NULL, then + * next_in_service may happen to be NULL, + * although the parent entity is evidently + * active. This happens if 1) the entity + * pointed by in_service_entity is the only + * active entity in the parent entity, and 2) + * according to the definition of + * next_in_service, the in_service_entity + * cannot be considered as + * next_in_service. See the comments on the + * definition of next_in_service for details. + */ + BUG_ON(sd->next_in_service == entity); + BUG_ON(sd->in_service_entity == entity); + 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) { + struct bfq_queue *bfqq = bfq_entity_to_bfqq(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; + BUG_ON(expiration && sd->in_service_entity != entity); + + if (bfqq) + bfq_log_bfqq(bfqq->bfqd, bfqq, + "invoking udpdate_next for this queue"); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + else { + struct bfq_group *bfqg = + container_of(entity, + struct bfq_group, entity); + + bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, + "invoking udpdate_next for this entity"); + } +#endif + if (!bfq_update_next_in_service(sd, entity, expiration) && + !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)) { + struct bfq_queue *bfqq = bfq_entity_to_bfqq(root_entity); + + if (bfqq) + bfq_log_bfqq(bfqq->bfqd, bfqq, + "new value %llu", + ((root_entity->min_start>>10)*1000)>>12); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + else { + struct bfq_group *bfqg = + container_of(root_entity, struct bfq_group, + entity); + + bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, + "new value %llu", + ((root_entity->min_start>>10)*1000)>>12); + } +#endif + 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; + + BUG_ON(bfq_gt(entry->min_start, vtime)); + + 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; + } + + BUG_ON(!first && !RB_EMPTY_ROOT(&st->active)); + 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; + struct bfq_queue *bfqq; + + 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); + BUG_ON(bfq_gt(entity->start, new_vtime)); + + /* Log some information */ + bfqq = bfq_entity_to_bfqq(entity); + if (bfqq) + bfq_log_bfqq(bfqq->bfqd, bfqq, + "start %llu vtime %llu st %p", + ((entity->start>>10)*1000)>>12, + ((new_vtime>>10)*1000)>>12, st); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + else { + struct bfq_group *bfqg = + container_of(entity, struct bfq_group, entity); + + bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, + "start %llu vtime %llu (%llu) st %p", + ((entity->start>>10)*1000)>>12, + ((st->vtime>>10)*1000)>>12, + ((new_vtime>>10)*1000)>>12, st); + } +#endif + + BUG_ON(!entity); + + return entity; +} + +/** + * bfq_lookup_next_entity - return the first eligible entity in @sd. + * @sd: the sched_data. + * @expiration: true if we are on the expiration path of the in-service queue + * + * This function is invoked when there has been a change in the trees + * for sd, and we need to know what is the new next entity to serve + * after this change. + */ +static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd, + bool expiration) +{ + 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; + struct bfq_queue *bfqq; + int class_idx = 0; + + BUG_ON(!sd); + BUG_ON(!st); + /* + * 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++) { + /* + * If expiration is true, then bfq_lookup_next_entity + * is being invoked as a part of the expiration path + * of the in-service queue. In this case, even if + * sd->in_service_entity is not NULL, + * sd->in_service_entiy at this point is actually not + * in service any more, and, if needed, has already + * been properly queued or requeued into the right + * tree. The reason why sd->in_service_entity is still + * not NULL here, even if expiration is true, is that + * sd->in_service_entiy is reset as a last step in the + * expiration path. So, if expiration is true, tell + * __bfq_lookup_next_entity that there is no + * sd->in_service_entity. + */ + entity = __bfq_lookup_next_entity(st + class_idx, + sd->in_service_entity && + !expiration); + + if (entity) + break; + } + + BUG_ON(!entity && + (!RB_EMPTY_ROOT(&st->active) || !RB_EMPTY_ROOT(&(st+1)->active) || + !RB_EMPTY_ROOT(&(st+2)->active))); + + if (!entity) + return NULL; + + /* Log some information */ + bfqq = bfq_entity_to_bfqq(entity); + if (bfqq) + bfq_log_bfqq(bfqq->bfqd, bfqq, "chosen from st %p %d", + st + class_idx, class_idx); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + else { + struct bfq_group *bfqg = + container_of(entity, struct bfq_group, entity); + + bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, + "chosen from st %p %d", + st + class_idx, class_idx); + } +#endif + + 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; + + BUG_ON(bfqd->in_service_queue); + + if (bfq_tot_busy_queues(bfqd) == 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) { +#ifdef BFQ_GROUP_IOSCHED_ENABLED + if (entity) { + struct bfq_group *bfqg = + container_of(entity, struct bfq_group, entity); + + bfq_log_bfqg(bfqd, bfqg, + "lookup in this group"); + if (!sd->next_in_service) + pr_crit("lookup in this group"); + } else { + bfq_log_bfqg(bfqd, bfqd->root_group, + "lookup in root group"); + if (!sd->next_in_service) + pr_crit("lookup in root group"); + } +#endif + + BUG_ON(!sd->next_in_service); + + /* + * 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; + + /* + * If entity is no longer a candidate for next + * service, then it must be extracted from its active + * tree, so as to make sure that it won't be + * considered when computing next_in_service. See the + * comments on the function + * bfq_no_longer_next_in_service() for details. + */ + if (bfq_no_longer_next_in_service(entity)) + bfq_active_extract(bfq_entity_service_tree(entity), + entity); + + /* + * Even if entity is not to be extracted according to + * the above check, a descendant entity may get + * extracted in one of the next iterations of this + * loop. Such an event could cause a change in + * next_in_service for the level of the descendant + * entity, and thus possibly back to this level. + * + * However, we cannot perform the resulting needed + * update of next_in_service for this level before the + * end of the whole 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. + */ + + /* Log some information */ + bfqq = bfq_entity_to_bfqq(entity); + if (bfqq) + bfq_log_bfqq(bfqd, bfqq, + "this queue, finish %llu", + (((entity->finish>>10)*1000)>>10)>>2); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + else { + struct bfq_group *bfqg = + container_of(entity, struct bfq_group, entity); + + bfq_log_bfqg(bfqd, bfqg, + "this entity, finish %llu", + (((entity->finish>>10)*1000)>>10)>>2); + } +#endif + + } + + BUG_ON(!entity); + bfqq = bfq_entity_to_bfqq(entity); + BUG_ON(!bfqq); + + /* + * 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, false)) + 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; + +#ifndef BFQ_MQ + if (bfqd->in_service_bic) { + put_io_context(bfqd->in_service_bic->icq.ioc); + bfqd->in_service_bic = NULL; + } +#endif + + 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; + struct bfq_service_tree *st = bfq_entity_service_tree(entity); + + BUG_ON(bfqq == bfqd->in_service_queue); + BUG_ON(entity->tree != &st->active && entity->tree != &st->idle && + entity->on_st); + + bfq_activate_requeue_entity(entity, bfq_bfqq_non_blocking_wait_rq(bfqq), + false, false); + bfq_clear_bfqq_non_blocking_wait_rq(bfqq); +} + +static void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, + bool expiration) +{ + struct bfq_entity *entity = &bfqq->entity; + + bfq_activate_requeue_entity(entity, false, + bfqq == bfqd->in_service_queue, expiration); +} + +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) +{ + BUG_ON(!bfq_bfqq_busy(bfqq)); + BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list)); + + bfq_log_bfqq(bfqd, bfqq, "del from busy"); + + bfq_clear_bfqq_busy(bfqq); + + BUG_ON(bfq_tot_busy_queues(bfqd) == 0); + bfqd->busy_queues[bfqq->ioprio_class - 1]--; + + if (bfqq->wr_coeff > 1) { + bfqd->wr_busy_queues--; + BUG_ON(bfqd->wr_busy_queues < 0); + } + + bfqg_stats_update_dequeue(bfqq_group(bfqq)); + + BUG_ON(bfqq->entity.budget < 0); + + bfq_deactivate_bfqq(bfqd, bfqq, true, expiration); + if (!bfqq->dispatched) + bfq_weights_tree_remove(bfqd, bfqq); +} + +/* + * Called when an inactive queue receives a new request. + */ +static void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq) +{ + BUG_ON(bfq_bfqq_busy(bfqq)); + BUG_ON(bfqq == bfqd->in_service_queue); + + bfq_log_bfqq(bfqd, bfqq, "add to busy"); + + bfq_activate_bfqq(bfqd, bfqq); + + bfq_mark_bfqq_busy(bfqq); + bfqd->busy_queues[bfqq->ioprio_class - 1]++; + + if (!bfqq->dispatched) + if (bfqq->wr_coeff == 1) + bfq_weights_tree_add(bfqd, bfqq, + &bfqd->queue_weights_tree); + + if (bfqq->wr_coeff > 1) { + bfqd->wr_busy_queues++; + BUG_ON(bfqd->wr_busy_queues > bfq_tot_busy_queues(bfqd)); + } + +} diff --git a/block/bfq-sq-iosched.c b/block/bfq-sq-iosched.c new file mode 100644 index 000000000000..6da94eef0cf1 --- /dev/null +++ b/block/bfq-sq-iosched.c @@ -0,0 +1,5957 @@ +/* + * Budget Fair Queueing (BFQ) I/O scheduler. + * + * Based on ideas and code from CFQ: + * Copyright (C) 2003 Jens Axboe + * + * Copyright (C) 2008 Fabio Checconi + * Paolo Valente + * + * Copyright (C) 2015 Paolo Valente + * + * Copyright (C) 2017 Paolo Valente + * + * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ + * file. + * + * BFQ is a proportional-share I/O scheduler, with some extra + * low-latency capabilities. BFQ also supports full hierarchical + * scheduling through cgroups. Next paragraphs provide an introduction + * on BFQ inner workings. Details on BFQ benefits and usage can be + * found in Documentation/block/bfq-iosched.txt. + * + * BFQ is a proportional-share storage-I/O scheduling algorithm based + * on the slice-by-slice service scheme of CFQ. But BFQ assigns + * budgets, measured in number of sectors, to processes instead of + * time slices. The device is not granted to the in-service process + * for a given time slice, but until it has exhausted its assigned + * budget. This change from the time to the service domain enables BFQ + * to distribute the device throughput among processes as desired, + * without any distortion due to throughput fluctuations, or to device + * internal queueing. BFQ uses an ad hoc internal scheduler, called + * B-WF2Q+, to schedule processes according to their budgets. More + * precisely, BFQ schedules queues associated with processes. Thanks to + * the accurate policy of B-WF2Q+, BFQ can afford to assign high + * budgets to I/O-bound processes issuing sequential requests (to + * boost the throughput), and yet guarantee a low latency to + * interactive and soft real-time applications. + * + * In particular, BFQ schedules I/O so as to achieve the latter goal-- + * low latency for interactive and soft real-time applications--if the + * low_latency parameter is set (default configuration). To this + * purpose, BFQ constantly tries to detect whether the I/O requests in + * a bfq_queue come from an interactive or a soft real-time + * application. For brevity, in these cases, the queue is said to be + * interactive or soft real-time. In both cases, BFQ privileges the + * service of the queue, over that of non-interactive and + * non-soft-real-time queues. This privileging is performed, mainly, + * by raising the weight of the queue. So, for brevity, we call just + * weight-raising periods the time periods during which a queue is + * privileged, because deemed interactive or soft real-time. + * + * The detection of soft real-time queues/applications is described in + * detail in the comments on the function + * bfq_bfqq_softrt_next_start. On the other hand, the detection of an + * interactive queue works as follows: a queue is deemed interactive + * if it is constantly non empty only for a limited time interval, + * after which it does become empty. The queue may be deemed + * interactive again (for a limited time), if it restarts being + * constantly non empty, provided that this happens only after the + * queue has remained empty for a given minimum idle time. + * + * By default, BFQ computes automatically the above maximum time + * interval, i.e., the time interval after which a constantly + * non-empty queue stops being deemed interactive. Since a queue is + * weight-raised while it is deemed interactive, this maximum time + * interval happens to coincide with the (maximum) duration of the + * weight-raising for interactive queues. + * + * NOTE: if the main or only goal, with a given device, is to achieve + * the maximum-possible throughput at all times, then do switch off + * all low-latency heuristics for that device, by setting low_latency + * to 0. + * + * BFQ is described in [1], where also a reference to the initial, + * more theoretical paper on BFQ can be found. The interested reader + * can find in the latter paper full details on the main algorithm, as + * well as formulas of the guarantees and formal proofs of all the + * properties. With respect to the version of BFQ presented in these + * papers, this implementation adds a few more heuristics, such as the + * one that guarantees a low latency to soft real-time applications, + * and a hierarchical extension based on H-WF2Q+. + * + * B-WF2Q+ is based on WF2Q+, that is described in [2], together with + * H-WF2Q+, while the augmented tree used to implement B-WF2Q+ with O(log N) + * complexity derives from the one introduced with EEVDF in [3]. + * + * [1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O + * Scheduler", Proceedings of the First Workshop on Mobile System + * Technologies (MST-2015), May 2015. + * http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf + * + * http://algogroup.unimo.it/people/paolo/disk_sched/bf1-v1-suite-results.pdf + * + * [2] Jon C.R. Bennett and H. Zhang, ``Hierarchical Packet Fair Queueing + * Algorithms,'' IEEE/ACM Transactions on Networking, 5(5):675-689, + * Oct 1997. + * + * http://www.cs.cmu.edu/~hzhang/papers/TON-97-Oct.ps.gz + * + * [3] I. Stoica and H. Abdel-Wahab, ``Earliest Eligible Virtual Deadline + * First: A Flexible and Accurate Mechanism for Proportional Share + * Resource Allocation,'' technical report. + * + * http://www.cs.berkeley.edu/~istoica/papers/eevdf-tr-95.pdf + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include "blk.h" +#include "bfq.h" +#include "blk-wbt.h" + +/* 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 }; + +/* Maximum backwards seek, in KiB. */ +static const int bfq_back_max = (16 * 1024); + +/* Penalty of a backwards seek, in number of sectors. */ +static const int bfq_back_penalty = 2; + +/* Idling period duration, in ns. */ +static u32 bfq_slice_idle = (NSEC_PER_SEC / 125); + +/* Minimum number of assigned budgets for which stats are safe to compute. */ +static const int bfq_stats_min_budgets = 194; + +/* Default maximum budget values, in sectors and number of requests. */ +static const int bfq_default_max_budget = (16 * 1024); + +/* + * When a sync request is dispatched, the queue that contains that + * request, and all the ancestor entities of that queue, are charged + * with the number of sectors of the request. In constrast, if the + * request is async, then the queue and its ancestor entities are + * charged with the number of sectors of the request, multiplied by + * the factor below. This throttles the bandwidth for async I/O, + * w.r.t. to sync I/O, and it is done to counter the tendency of async + * writes to steal I/O throughput to reads. + * + * The current value of this parameter is the result of a tuning with + * several hardware and software configurations. We tried to find the + * lowest value for which writes do not cause noticeable problems to + * reads. In fact, the lower this parameter, the stabler I/O control, + * in the following respect. The lower this parameter is, the less + * the bandwidth enjoyed by a group decreases + * - when the group does writes, w.r.t. to when it does reads; + * - when other groups do reads, w.r.t. to when they do writes. + */ +static const int bfq_async_charge_factor = 3; + +/* Default timeout values, in jiffies, approximating CFQ defaults. */ +static const int bfq_timeout = (HZ / 8); + +/* + * Time limit for merging (see comments in bfq_setup_cooperator). Set + * to the slowest value that, in our tests, proved to be effective in + * removing false positives, while not causing true positives to miss + * queue merging. + * + * As can be deduced from the low time limit below, queue merging, if + * successful, happens at the very beggining of the I/O of the involved + * cooperating processes, as a consequence of the arrival of the very + * first requests from each cooperator. After that, there is very + * little chance to find cooperators. + */ +static const unsigned long bfq_merge_time_limit = HZ/10; + +#define MAX_LENGTH_REASON_NAME 25 + +static const char reason_name[][MAX_LENGTH_REASON_NAME] = {"TOO_IDLE", +"BUDGET_TIMEOUT", "BUDGET_EXHAUSTED", "NO_MORE_REQUESTS", +"PREEMPTED"}; + +static struct kmem_cache *bfq_pool; + +/* Below this threshold (in ns), we consider thinktime immediate. */ +#define BFQ_MIN_TT (2 * NSEC_PER_MSEC) + +/* hw_tag detection: parallel requests threshold and min samples needed. */ +#define BFQ_HW_QUEUE_THRESHOLD 3 +#define BFQ_HW_QUEUE_SAMPLES 32 + +#define BFQQ_SEEK_THR (sector_t)(8 * 100) +#define BFQQ_SECT_THR_NONROT (sector_t)(2 * 32) +#define BFQ_RQ_SEEKY(bfqd, last_pos, rq) \ + (get_sdist(last_pos, rq) > \ + BFQQ_SEEK_THR && \ + (!blk_queue_nonrot(bfqd->queue) || \ + blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT)) +#define BFQQ_CLOSE_THR (sector_t)(8 * 1024) +#define BFQQ_SEEKY(bfqq) (hweight32(bfqq->seek_history) > 19) + +/* Min number of samples required to perform peak-rate update */ +#define BFQ_RATE_MIN_SAMPLES 32 +/* Min observation time interval required to perform a peak-rate update (ns) */ +#define BFQ_RATE_MIN_INTERVAL (300*NSEC_PER_MSEC) +/* Target observation time interval for a peak-rate update (ns) */ +#define BFQ_RATE_REF_INTERVAL NSEC_PER_SEC + +/* + * Shift used for peak-rate fixed precision calculations. + * With + * - the current shift: 16 positions + * - the current type used to store rate: u32 + * - the current unit of measure for rate: [sectors/usec], or, more precisely, + * [(sectors/usec) / 2^BFQ_RATE_SHIFT] to take into account the shift, + * the range of rates that can be stored is + * [1 / 2^BFQ_RATE_SHIFT, 2^(32 - BFQ_RATE_SHIFT)] sectors/usec = + * [1 / 2^16, 2^16] sectors/usec = [15e-6, 65536] sectors/usec = + * [15, 65G] sectors/sec + * Which, assuming a sector size of 512B, corresponds to a range of + * [7.5K, 33T] B/sec + */ +#define BFQ_RATE_SHIFT 16 + +/* + * When configured for computing the duration of the weight-raising + * for interactive queues automatically (see the comments at the + * beginning of this file), BFQ does it using the following formula: + * duration = (ref_rate / r) * ref_wr_duration, + * where r is the peak rate of the device, and ref_rate and + * ref_wr_duration are two reference parameters. In particular, + * ref_rate is the peak rate of the reference storage device (see + * below), and ref_wr_duration is about the maximum time needed, with + * BFQ and while reading two files in parallel, to load typical large + * applications on the reference device (see the comments on + * max_service_from_wr below, for more details on how ref_wr_duration + * is obtained). In practice, the slower/faster the device at hand + * is, the more/less it takes to load applications with respect to the + * reference device. Accordingly, the longer/shorter BFQ grants + * weight raising to interactive applications. + * + * BFQ uses two different reference pairs (ref_rate, ref_wr_duration), + * depending on whether the device is rotational or non-rotational. + * + * In the following definitions, ref_rate[0] and ref_wr_duration[0] + * are the reference values for a rotational device, whereas + * ref_rate[1] and ref_wr_duration[1] are the reference values for a + * non-rotational device. The reference rates are not the actual peak + * rates of the devices used as a reference, but slightly lower + * values. The reason for using slightly lower values is that the + * peak-rate estimator tends to yield slightly lower values than the + * actual peak rate (it can yield the actual peak rate only if there + * is only one process doing I/O, and the process does sequential + * I/O). + * + * The reference peak rates are measured in sectors/usec, left-shifted + * by BFQ_RATE_SHIFT. + */ +static int ref_rate[2] = {14000, 33000}; +/* + * To improve readability, a conversion function is used to initialize + * the following array, which entails that the array can be + * initialized only in a function. + */ +static int ref_wr_duration[2]; + +/* + * BFQ uses the above-detailed, time-based weight-raising mechanism to + * privilege interactive tasks. This mechanism is vulnerable to the + * following false positives: I/O-bound applications that will go on + * doing I/O for much longer than the duration of weight + * raising. These applications have basically no benefit from being + * weight-raised at the beginning of their I/O. On the opposite end, + * while being weight-raised, these applications + * a) unjustly steal throughput to applications that may actually need + * low latency; + * b) make BFQ uselessly perform device idling; device idling results + * in loss of device throughput with most flash-based storage, and may + * increase latencies when used purposelessly. + * + * BFQ tries to reduce these problems, by adopting the following + * countermeasure. To introduce this countermeasure, we need first to + * finish explaining how the duration of weight-raising for + * interactive tasks is computed. + * + * For a bfq_queue deemed as interactive, the duration of weight + * raising is dynamically adjusted, as a function of the estimated + * peak rate of the device, so as to be equal to the time needed to + * execute the 'largest' interactive task we benchmarked so far. By + * largest task, we mean the task for which each involved process has + * to do more I/O than for any of the other tasks we benchmarked. This + * reference interactive task is the start-up of LibreOffice Writer, + * and in this task each process/bfq_queue needs to have at most ~110K + * sectors transfered. + * + * This last piece of information enables BFQ to reduce the actual + * duration of weight-raising for at least one class of I/O-bound + * applications: those doing sequential or quasi-sequential I/O. An + * example is file copy. In fact, once started, the main I/O-bound + * processes of these applications usually consume the above 110K + * sectors in much less time than the processes of an application that + * is starting, because these I/O-bound processes will greedily devote + * almost all their CPU cycles only to their target, + * throughput-friendly I/O operations. This is even more true if BFQ + * happens to be underestimating the device peak rate, and thus + * overestimating the duration of weight raising. But, according to + * our measurements, once transferred 110K sectors, these processes + * have no right to be weight-raised any longer. + * + * Basing on the last consideration, BFQ ends weight-raising for a + * bfq_queue if the latter happens to have received an amount of + * service at least equal to the following constant. The constant is + * set to slightly more than 110K, to have a minimum safety margin. + * + * This early ending of weight-raising reduces the amount of time + * during which interactive false positives cause the two problems + * described at the beginning of these comments. + */ +static const unsigned long max_service_from_wr = 120000; + +#define BFQ_SERVICE_TREE_INIT ((struct bfq_service_tree) \ + { RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 }) + +#define RQ_BIC(rq) icq_to_bic((rq)->elv.priv[0]) +#define RQ_BFQQ(rq) ((rq)->elv.priv[1]) + +static void bfq_schedule_dispatch(struct bfq_data *bfqd); + +#include "bfq-ioc.c" +#include "bfq-sched.c" +#include "bfq-cgroup-included.c" + +#define bfq_class_idle(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE) +#define bfq_class_rt(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_RT) + +#define bfq_sample_valid(samples) ((samples) > 80) + +/* + * 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, ""); + kblockd_schedule_work(&bfqd->unplug_work); + } +} + +/* + * Lifted from AS - choose which of rq1 and rq2 that is best served now. + * We choose the request that is closesr to the head right now. Distance + * behind the head is penalized and only allowed to a certain extent. + */ +static struct request *bfq_choose_req(struct bfq_data *bfqd, + struct request *rq1, + struct request *rq2, + sector_t last) +{ + sector_t s1, s2, d1 = 0, d2 = 0; + unsigned long back_max; +#define BFQ_RQ1_WRAP 0x01 /* request 1 wraps */ +#define BFQ_RQ2_WRAP 0x02 /* request 2 wraps */ + unsigned int wrap = 0; /* bit mask: requests behind the disk head? */ + + if (!rq1 || rq1 == rq2) + return rq2; + if (!rq2) + return rq1; + + if (rq_is_sync(rq1) && !rq_is_sync(rq2)) + return rq1; + else if (rq_is_sync(rq2) && !rq_is_sync(rq1)) + return rq2; + if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META)) + return rq1; + else if ((rq2->cmd_flags & REQ_META) && !(rq1->cmd_flags & REQ_META)) + return rq2; + + s1 = blk_rq_pos(rq1); + s2 = blk_rq_pos(rq2); + + /* + * By definition, 1KiB is 2 sectors. + */ + back_max = bfqd->bfq_back_max * 2; + + /* + * Strict one way elevator _except_ in the case where we allow + * short backward seeks which are biased as twice the cost of a + * similar forward seek. + */ + if (s1 >= last) + d1 = s1 - last; + else if (s1 + back_max >= last) + d1 = (last - s1) * bfqd->bfq_back_penalty; + else + wrap |= BFQ_RQ1_WRAP; + + if (s2 >= last) + d2 = s2 - last; + else if (s2 + back_max >= last) + d2 = (last - s2) * bfqd->bfq_back_penalty; + else + wrap |= BFQ_RQ2_WRAP; + + /* Found required data */ + + /* + * By doing switch() on the bit mask "wrap" we avoid having to + * check two variables for all permutations: --> faster! + */ + switch (wrap) { + case 0: /* common case for CFQ: rq1 and rq2 not wrapped */ + if (d1 < d2) + return rq1; + else if (d2 < d1) + return rq2; + + if (s1 >= s2) + return rq1; + else + return rq2; + + case BFQ_RQ2_WRAP: + return rq1; + case BFQ_RQ1_WRAP: + return rq2; + case (BFQ_RQ1_WRAP|BFQ_RQ2_WRAP): /* both rqs wrapped */ + default: + /* + * Since both rqs are wrapped, + * start with the one that's further behind head + * (--> only *one* back seek required), + * since back seek takes more time than forward. + */ + if (s1 <= s2) + return rq1; + else + return rq2; + } +} + +static struct bfq_queue * +bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root, + sector_t sector, struct rb_node **ret_parent, + struct rb_node ***rb_link) +{ + struct rb_node **p, *parent; + struct bfq_queue *bfqq = NULL; + + parent = NULL; + p = &root->rb_node; + while (*p) { + struct rb_node **n; + + parent = *p; + bfqq = rb_entry(parent, struct bfq_queue, pos_node); + + /* + * Sort strictly based on sector. Smallest to the left, + * largest to the right. + */ + if (sector > blk_rq_pos(bfqq->next_rq)) + n = &(*p)->rb_right; + else if (sector < blk_rq_pos(bfqq->next_rq)) + n = &(*p)->rb_left; + else + break; + p = n; + bfqq = NULL; + } + + *ret_parent = parent; + if (rb_link) + *rb_link = p; + + bfq_log(bfqd, "%llu: returning %d", + (unsigned long long) sector, + bfqq ? bfqq->pid : 0); + + return bfqq; +} + +static bool bfq_too_late_for_merging(struct bfq_queue *bfqq) +{ + return bfqq->service_from_backlogged > 0 && + time_is_before_jiffies(bfqq->first_IO_time + + bfq_merge_time_limit); +} + +static void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq) +{ + struct rb_node **p, *parent; + struct bfq_queue *__bfqq; + + if (bfqq->pos_root) { + rb_erase(&bfqq->pos_node, bfqq->pos_root); + bfqq->pos_root = NULL; + } + + /* + * bfqq cannot be merged any longer (see comments in + * bfq_setup_cooperator): no point in adding bfqq into the + * position tree. + */ + if (bfq_too_late_for_merging(bfqq)) + return; + + if (bfq_class_idle(bfqq)) + return; + if (!bfqq->next_rq) + return; + + bfqq->pos_root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree; + __bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root, + blk_rq_pos(bfqq->next_rq), &parent, &p); + if (!__bfqq) { + rb_link_node(&bfqq->pos_node, parent, p); + rb_insert_color(&bfqq->pos_node, bfqq->pos_root); + } else + bfqq->pos_root = NULL; +} + +/* + * 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_better_to_idle()). + * + * Such a scenario occurs when: + * 1) all active queues have the same weight, + * 2) all active queues belong to the same I/O-priority class, + * 3) all active groups at the same level in the groups tree have the same + * weight, + * 4) 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 last two symmetry sub-conditions above would be quite complex + * and time consuming. Therefore this function evaluates, instead, + * only the following stronger three sub-conditions, for which it is + * much easier to maintain the needed state: + * 1) all active queues have the same weight, + * 2) all active queues belong to the same I/O-priority class, + * 3) there are no active groups. + * In particular, the last condition is always true if hierarchical + * support or 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) +{ + /* + * For queue weights to differ, queue_weights_tree must contain + * at least two nodes. + */ + bool varied_queue_weights = !RB_EMPTY_ROOT(&bfqd->queue_weights_tree) && + (bfqd->queue_weights_tree.rb_node->rb_left || + bfqd->queue_weights_tree.rb_node->rb_right); + + bool multiple_classes_busy = + (bfqd->busy_queues[0] && bfqd->busy_queues[1]) || + (bfqd->busy_queues[0] && bfqd->busy_queues[2]) || + (bfqd->busy_queues[1] && bfqd->busy_queues[2]); + + bfq_log(bfqd, "varied_queue_weights %d mul_classes %d", + varied_queue_weights, multiple_classes_busy); + +#ifdef BFQ_GROUP_IOSCHED_ENABLED + bfq_log(bfqd, "num_groups_with_pending_reqs %u", + bfqd->num_groups_with_pending_reqs); +#endif + + return !(varied_queue_weights || multiple_classes_busy +#ifdef BFQ_GROUP_IOSCHED_ENABLED + || bfqd->num_groups_with_pending_reqs > 0 +#endif + ); +} + +/* + * If the weight-counter tree passed as input contains no counter for + * the weight of the input queue, 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. + */ +static void bfq_weights_tree_add(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + struct rb_root *root) +{ + struct bfq_entity *entity = &bfqq->entity; + struct rb_node **new = &(root->rb_node), *parent = NULL; + + /* + * Do not insert if the queue is already associated with a + * counter, which happens if: + * 1) 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, + * 2) 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 (bfqq->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) { + bfqq->weight_counter = __counter; + goto inc_counter; + } + if (entity->weight < __counter->weight) + new = &((*new)->rb_left); + else + new = &((*new)->rb_right); + } + + bfqq->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 queue to not be + * considered in bfq_symmetric_scenario, which, in its turn, + * causes the scenario to be deemed wrongly symmetric in case + * bfqq's weight would have been the only weight making the + * scenario asymmetric. On the bright side, no unbalance will + * however occur when bfqq becomes inactive again (the + * invocation of this function is triggered by an activation + * of queue). In fact, bfq_weights_tree_remove does nothing + * if !bfqq->weight_counter. + */ + if (unlikely(!bfqq->weight_counter)) + return; + + bfqq->weight_counter->weight = entity->weight; + rb_link_node(&bfqq->weight_counter->weights_node, parent, new); + rb_insert_color(&bfqq->weight_counter->weights_node, root); + +inc_counter: + bfqq->weight_counter->num_active++; + bfqq->ref++; + + bfq_log_bfqq(bfqq->bfqd, bfqq, "refs %d weight %d symmetric %d", + bfqq->ref, + entity->weight, + bfq_symmetric_scenario(bfqd)); +} + +/* + * Decrement the weight counter associated with the queue, 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. + */ +static void __bfq_weights_tree_remove(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + struct rb_root *root) +{ + struct bfq_entity *entity = &bfqq->entity; + + if (!bfqq->weight_counter) + return; + + BUG_ON(RB_EMPTY_ROOT(root)); + BUG_ON(bfqq->weight_counter->weight != entity->weight); + + BUG_ON(!bfqq->weight_counter->num_active); + bfqq->weight_counter->num_active--; + + if (bfqq->weight_counter->num_active > 0) + goto reset_entity_pointer; + + rb_erase(&bfqq->weight_counter->weights_node, root); + kfree(bfqq->weight_counter); + +reset_entity_pointer: + bfqq->weight_counter = NULL; + bfq_log_bfqq(bfqq->bfqd, bfqq, + "refs %d weight %d symmetric %d", + bfqq->ref, + entity->weight, + bfq_symmetric_scenario(bfqd)); + bfq_put_queue(bfqq); +} + +/* + * Invoke __bfq_weights_tree_remove on bfqq and decrement the number + * of active groups for each queue's inactive parent entity. + */ +static void bfq_weights_tree_remove(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + struct bfq_entity *entity = bfqq->entity.parent; + + for_each_entity(entity) { + struct bfq_sched_data *sd = entity->my_sched_data; + + BUG_ON(entity->sched_data == NULL); /* + * It would mean + * that this is + * the root group. + */ + + if (sd->next_in_service || sd->in_service_entity) { + BUG_ON(!entity->in_groups_with_pending_reqs); + /* + * entity is still active, because either + * next_in_service or in_service_entity is not + * NULL (see the comments on the definition of + * next_in_service for details on why + * in_service_entity must be checked too). + * + * As a consequence, its parent entities are + * active as well, and thus this loop must + * stop here. + */ + break; + } + + BUG_ON(!bfqd->num_groups_with_pending_reqs && + entity->in_groups_with_pending_reqs); + /* + * The decrement of num_groups_with_pending_reqs is + * not performed immediately upon the deactivation of + * entity, but it is delayed to when it also happens + * that the first leaf descendant bfqq of entity gets + * all its pending requests completed. The following + * instructions perform this delayed decrement, if + * needed. See the comments on + * num_groups_with_pending_reqs for details. + */ + if (entity->in_groups_with_pending_reqs) { + entity->in_groups_with_pending_reqs = false; + bfqd->num_groups_with_pending_reqs--; + } + bfq_log_bfqq(bfqd, bfqq, "num_groups_with_pending_reqs %u", + bfqd->num_groups_with_pending_reqs); + } + + /* + * Next function is invoked last, because it causes bfqq to be + * freed if the following holds: bfqq is not in service and + * has no dispatched request. DO NOT use bfqq after the next + * function invocation. + */ + __bfq_weights_tree_remove(bfqd, bfqq, + &bfqd->queue_weights_tree); +} + +/* + * Return expired entry, or NULL to just start from scratch in rbtree. + */ +static struct request *bfq_check_fifo(struct bfq_queue *bfqq, + struct request *last) +{ + struct request *rq; + + if (bfq_bfqq_fifo_expire(bfqq)) + return NULL; + + bfq_mark_bfqq_fifo_expire(bfqq); + + rq = rq_entry_fifo(bfqq->fifo.next); + + if (rq == last || ktime_get_ns() < rq->fifo_time) + return NULL; + + bfq_log_bfqq(bfqq->bfqd, bfqq, "returned %p", rq); + BUG_ON(RB_EMPTY_NODE(&rq->rb_node)); + return rq; +} + +static struct request *bfq_find_next_rq(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + struct request *last) +{ + struct rb_node *rbnext = rb_next(&last->rb_node); + struct rb_node *rbprev = rb_prev(&last->rb_node); + struct request *next, *prev = NULL; + + BUG_ON(list_empty(&bfqq->fifo)); + + /* Follow expired path, else get first next available. */ + next = bfq_check_fifo(bfqq, last); + if (next) { + BUG_ON(next == last); + return next; + } + + BUG_ON(RB_EMPTY_NODE(&last->rb_node)); + + if (rbprev) + prev = rb_entry_rq(rbprev); + + if (rbnext) + next = rb_entry_rq(rbnext); + else { + rbnext = rb_first(&bfqq->sort_list); + if (rbnext && rbnext != &last->rb_node) + next = rb_entry_rq(rbnext); + } + + return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last)); +} + +/* see the definition of bfq_async_charge_factor for details */ +static unsigned long bfq_serv_to_charge(struct request *rq, + struct bfq_queue *bfqq) +{ + if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1 || + !bfq_symmetric_scenario(bfqq->bfqd)) + return blk_rq_sectors(rq); + + return blk_rq_sectors(rq) * bfq_async_charge_factor; +} + +/** + * bfq_updated_next_req - update the queue after a new next_rq selection. + * @bfqd: the device data the queue belongs to. + * @bfqq: the queue to update. + * + * If the first request of a queue changes we make sure that the queue + * has enough budget to serve at least its first request (if the + * request has grown). We do this because if the queue has not enough + * budget for its first request, it has to go through two dispatch + * rounds to actually get it dispatched. + */ +static void bfq_updated_next_req(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + struct bfq_entity *entity = &bfqq->entity; + struct bfq_service_tree *st = bfq_entity_service_tree(entity); + struct request *next_rq = bfqq->next_rq; + unsigned long new_budget; + + if (!next_rq) + return; + + if (bfqq == bfqd->in_service_queue) + /* + * In order not to break guarantees, budgets cannot be + * changed after an entity has been selected. + */ + return; + + BUG_ON(entity->tree != &st->active); + BUG_ON(entity == entity->sched_data->in_service_entity); + + new_budget = max_t(unsigned long, + max_t(unsigned long, bfqq->max_budget, + bfq_serv_to_charge(next_rq, bfqq)), + entity->service); + if (entity->budget != new_budget) { + entity->budget = new_budget; + bfq_log_bfqq(bfqd, bfqq, "new budget %lu", + new_budget); + bfq_requeue_bfqq(bfqd, bfqq, false); + } +} + +static unsigned int bfq_wr_duration(struct bfq_data *bfqd) +{ + u64 dur; + + if (bfqd->bfq_wr_max_time > 0) + return bfqd->bfq_wr_max_time; + + dur = bfqd->rate_dur_prod; + do_div(dur, bfqd->peak_rate); + + /* + * Limit duration between 3 and 25 seconds. The upper limit + * has been conservatively set after the following worst case: + * on a QEMU/KVM virtual machine + * - running in a slow PC + * - with a virtual disk stacked on a slow low-end 5400rpm HDD + * - serving a heavy I/O workload, such as the sequential reading + * of several files + * mplayer took 23 seconds to start, if constantly weight-raised. + * + * As for higher values than that accomodating the above bad + * scenario, tests show that higher values would often yield + * the opposite of the desired result, i.e., would worsen + * responsiveness by allowing non-interactive applications to + * preserve weight raising for too long. + * + * On the other end, lower values than 3 seconds make it + * difficult for most interactive tasks to complete their jobs + * before weight-raising finishes. + */ + return clamp_val(dur, msecs_to_jiffies(3000), msecs_to_jiffies(25000)); +} + +/* switch back from soft real-time to interactive weight raising */ +static void switch_back_to_interactive_wr(struct bfq_queue *bfqq, + struct bfq_data *bfqd) +{ + bfqq->wr_coeff = bfqd->bfq_wr_coeff; + bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); + bfqq->last_wr_start_finish = bfqq->wr_start_at_switch_to_srt; +} + +static void +bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd, + struct bfq_io_cq *bic, bool bfq_already_existing) +{ + unsigned int old_wr_coeff; + bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq); + + if (bic->saved_has_short_ttime) + bfq_mark_bfqq_has_short_ttime(bfqq); + else + bfq_clear_bfqq_has_short_ttime(bfqq); + + if (bic->saved_IO_bound) + bfq_mark_bfqq_IO_bound(bfqq); + else + bfq_clear_bfqq_IO_bound(bfqq); + + if (unlikely(busy)) + old_wr_coeff = bfqq->wr_coeff; + + bfqq->wr_coeff = bic->saved_wr_coeff; + bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt; + BUG_ON(time_is_after_jiffies(bfqq->wr_start_at_switch_to_srt)); + bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish; + bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time; + BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish)); + + bfq_log_bfqq(bfqq->bfqd, bfqq, + "bic %p wr_coeff %d start_finish %lu max_time %lu", + bic, bfqq->wr_coeff, bfqq->last_wr_start_finish, + bfqq->wr_cur_max_time); + + 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))) { + if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time && + !bfq_bfqq_in_large_burst(bfqq) && + time_is_after_eq_jiffies(bfqq->wr_start_at_switch_to_srt + + bfq_wr_duration(bfqd))) { + switch_back_to_interactive_wr(bfqq, bfqd); + bfq_log_bfqq(bfqq->bfqd, bfqq, + "switching back to interactive"); + } else { + bfqq->wr_coeff = 1; + bfq_log_bfqq(bfqq->bfqd, bfqq, + "switching off wr (%lu + %lu < %lu)", + bfqq->last_wr_start_finish, bfqq->wr_cur_max_time, + jiffies); + } + } + + /* make sure weight will be updated, however we got here */ + bfqq->entity.prio_changed = 1; + + if (likely(!busy)) + return; + + if (old_wr_coeff == 1 && bfqq->wr_coeff > 1) { + bfqd->wr_busy_queues++; + BUG_ON(bfqd->wr_busy_queues > bfq_tot_busy_queues(bfqd)); + } else if (old_wr_coeff > 1 && bfqq->wr_coeff == 1) { + bfqd->wr_busy_queues--; + BUG_ON(bfqd->wr_busy_queues < 0); + } +} + +static int bfqq_process_refs(struct bfq_queue *bfqq) +{ + int process_refs, io_refs; + + lockdep_assert_held(bfqq->bfqd->queue->queue_lock); + + io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE]; + process_refs = bfqq->ref - io_refs - bfqq->entity.on_st - + (bfqq->weight_counter != NULL); + BUG_ON(process_refs < 0); + return process_refs; +} + +/* Empty burst list and add just bfqq (see comments to 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++; + + bfq_log_bfqq(bfqd, bfqq, "%d", bfqd->burst_size); + + BUG_ON(bfqd->burst_size > bfqd->bfq_large_burst_thresh); + + 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; + bfq_log_bfqq(bfqd, bfqq, "large burst started"); + + /* + * 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_log_bfqq(bfqd, bfqq_item, "marked in large burst"); + } + bfq_mark_bfqq_in_large_burst(bfqq); + bfq_log_bfqq(bfqd, bfqq, "marked in large burst"); + + /* + * 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); + bfq_log_bfqq(bfqd, bfqq, + "late activation or different group"); + 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_log_bfqq(bfqd, bfqq, "marked in 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; + + if (entity->budget < entity->service) { + pr_crit("budget %d service %d\n", + entity->budget, entity->service); + BUG(); + } + return entity->budget - entity->service; +} + +/* + * If enough samples have been computed, return the current max budget + * stored in bfqd, which is dynamically updated according to the + * estimated disk peak rate; otherwise return the default max budget + */ +static int bfq_max_budget(struct bfq_data *bfqd) +{ + if (bfqd->budgets_assigned < bfq_stats_min_budgets) + return bfq_default_max_budget; + else + return bfqd->bfq_max_budget; +} + +/* + * Return min budget, which is a fraction of the current or default + * max budget (trying with 1/32) + */ +static int bfq_min_budget(struct bfq_data *bfqd) +{ + if (bfqd->budgets_assigned < bfq_stats_min_budgets) + return bfq_default_max_budget / 32; + else + 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 + * whether the in-service queue should be expired, by returning + * true. The purpose of expiring the in-service queue is to give bfqq + * the chance to possibly preempt the in-service queue, and the reason + * for preempting the in-service queue is to achieve one of the two + * goals below. + * + * 1. Guarantee to bfqq its reserved bandwidth even if bfqq has + * expired because it has remained idle. In particular, bfqq may have + * expired for one of the following two reasons: + * + * - BFQ_BFQQ_NO_MORE_REQUEST bfqq did not enjoy any device idling and + * did not make it to issue a new request before its last request + * was served; + * + * - BFQ_BFQQ_TOO_IDLE bfqq did enjoy device idling, but did not issue + * a new request before the expiration of the idling-time. + * + * Even if bfqq has expired for one of the above reasons, the process + * associated with the queue may be however issuing requests greedily, + * and thus be sensitive to the bandwidth it receives (bfqq may have + * remained idle for other reasons: CPU high load, bfqq not enjoying + * idling, I/O throttling somewhere in the path from the process to + * the I/O scheduler, ...). But if, after every expiration for one of + * the above two reasons, bfqq has to wait for the service of at least + * one full budget of another queue before being served again, then + * bfqq is likely to get a much lower bandwidth or resource time than + * its reserved ones. To address this issue, two countermeasures need + * to be taken. + * + * First, the budget and the timestamps of bfqq need to be updated in + * a special way on bfqq reactivation: they need to be updated as if + * bfqq did not remain idle and did not expire. In fact, if they are + * computed as if bfqq expired and remained idle until reactivation, + * then the process associated with bfqq is treated as if, instead of + * being greedy, it stopped issuing requests when bfqq remained idle, + * and restarts issuing requests only on this reactivation. In other + * words, the scheduler does not help the process recover the "service + * hole" between bfqq expiration and reactivation. As a consequence, + * the process receives a lower bandwidth than its reserved one. In + * contrast, to recover this hole, the budget must be updated as if + * bfqq was not expired at all before this reactivation, i.e., it must + * be set to the value of the remaining budget when bfqq was + * expired. Along the same line, timestamps need to be assigned the + * value they had the last time bfqq was selected for service, i.e., + * before last expiration. Thus timestamps need to be back-shifted + * with respect to their normal computation (see [1] for more details + * on this tricky aspect). + * + * Secondly, to allow the process to recover the hole, the in-service + * queue must be expired too, to give bfqq the chance to preempt it + * immediately. In fact, if bfqq has to wait for a full budget of the + * in-service queue to be completed, then it may become impossible to + * let the process recover the hole, even if the back-shifted + * timestamps of bfqq are lower than those of the in-service queue. If + * this happens for most or all of the holes, then the process may not + * receive its reserved bandwidth. In this respect, it is worth noting + * that, being the service of outstanding requests unpreemptible, a + * little fraction of the holes may however be unrecoverable, thereby + * causing a little loss of bandwidth. + * + * The last important point is detecting whether bfqq does need this + * bandwidth recovery. In this respect, the next function deems the + * process associated with bfqq greedy, and thus allows it to recover + * the hole, if: 1) the process is waiting for the arrival of a new + * request (which implies that bfqq expired for one of the above two + * reasons), and 2) such a request has arrived soon. The first + * condition is controlled through the flag non_blocking_wait_rq, + * while the second through the flag arrived_in_time. If both + * conditions hold, then the function computes the budget in the + * above-described special way, and signals that the in-service queue + * should be expired. Timestamp back-shifting is done later in + * __bfq_activate_entity. + * + * 2. Reduce latency. Even if timestamps are not backshifted to let + * the process associated with bfqq recover a service hole, bfqq may + * however happen to have, after being (re)activated, a lower finish + * timestamp than the in-service queue. That is, the next budget of + * bfqq may have to be completed before the one of the in-service + * queue. If this is the case, then preempting the in-service queue + * allows this goal to be achieved, apart from the unpreemptible, + * outstanding requests mentioned above. + * + * Unfortunately, regardless of which of the above two goals one wants + * to achieve, service trees need first to be updated to know whether + * the in-service queue must be preempted. To have service trees + * correctly updated, the in-service queue must be expired and + * rescheduled, and bfqq must be scheduled too. This is one of the + * most costly operations (in future versions, the scheduling + * mechanism may be re-designed in such a way to make it possible to + * know whether preemption is needed without needing to update service + * trees). In addition, queue preemptions almost always cause random + * I/O, and thus loss of throughput. Because of these facts, the next + * function adopts the following simple scheme to avoid both costly + * operations and too frequent preemptions: it requests the expiration + * of the in-service queue (unconditionally) only for queues that need + * to recover a hole, or that either are weight-raised or deserve to + * be weight-raised. + */ +static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + bool arrived_in_time, + bool wr_or_deserves_wr) +{ + struct bfq_entity *entity = &bfqq->entity; + + /* + * In the next compound condition, we check also whether there + * is some budget left, because otherwise there is no point in + * trying to go on serving bfqq with this same budget: bfqq + * would be expired immediately after being selected for + * service. This would only cause useless overhead. + */ + if (bfq_bfqq_non_blocking_wait_rq(bfqq) && arrived_in_time && + bfq_bfqq_budget_left(bfqq) > 0) { + /* + * We do not clear the flag non_blocking_wait_rq here, as + * the latter is used in bfq_activate_bfqq to signal + * that timestamps need to be back-shifted (and is + * cleared right after). + */ + + /* + * In next assignment we rely on that either + * entity->service or entity->budget are not updated + * on expiration if bfqq is empty (see + * __bfq_bfqq_recalc_budget). Thus both quantities + * remain unchanged after such an expiration, and the + * following statement therefore assigns to + * entity->budget the remaining budget on such an + * expiration. + */ + BUG_ON(bfqq->max_budget < 0); + entity->budget = min_t(unsigned long, + bfq_bfqq_budget_left(bfqq), + bfqq->max_budget); + + BUG_ON(entity->budget < 0); + + /* + * At this point, we have used entity->service to get + * the budget left (needed for updating + * entity->budget). Thus we finally can, and have to, + * reset entity->service. The latter must be reset + * because bfqq would otherwise be charged again for + * the service it has received during its previous + * service slot(s). + */ + entity->service = 0; + + return true; + } + + /* + * We can finally complete expiration, by setting service to 0. + */ + entity->service = 0; + BUG_ON(bfqq->max_budget < 0); + entity->budget = max_t(unsigned long, bfqq->max_budget, + bfq_serv_to_charge(bfqq->next_rq, bfqq)); + BUG_ON(entity->budget < 0); + + bfq_clear_bfqq_non_blocking_wait_rq(bfqq); + return wr_or_deserves_wr; +} + +/* + * Return the farthest past time instant according to jiffies + * macros. + */ +static unsigned long bfq_smallest_from_now(void) +{ + return jiffies - MAX_JIFFY_OFFSET; +} + +static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + 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) { + /* start a weight-raising period */ + if (interactive) { + bfqq->service_from_wr = 0; + bfqq->wr_coeff = bfqd->bfq_wr_coeff; + bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); + } else { + /* + * No interactive weight raising in progress + * here: assign minus infinity to + * wr_start_at_switch_to_srt, to make sure + * that, at the end of the soft-real-time + * weight raising periods that is starting + * now, no interactive weight-raising period + * may be wrongly considered as still in + * progress (and thus actually started by + * mistake). + */ + bfqq->wr_start_at_switch_to_srt = + bfq_smallest_from_now(); + bfqq->wr_coeff = bfqd->bfq_wr_coeff * + BFQ_SOFTRT_WEIGHT_FACTOR; + bfqq->wr_cur_max_time = + bfqd->bfq_wr_rt_max_time; + } + /* + * If needed, further reduce budget to make sure it is + * close to bfqq's backlog, so as to reduce the + * scheduling-error component due to a too large + * budget. Do not care about throughput consequences, + * but only about latency. Finally, do not assign a + * too small budget either, to avoid increasing + * latency by causing too frequent expirations. + */ + bfqq->entity.budget = min_t(unsigned long, + bfqq->entity.budget, + 2 * bfq_min_budget(bfqd)); + + bfq_log_bfqq(bfqd, bfqq, + "wrais starting at %lu, rais_max_time %u", + jiffies, + jiffies_to_msecs(bfqq->wr_cur_max_time)); + } else if (old_wr_coeff > 1) { + 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 (in_burst) { + bfqq->wr_coeff = 1; + bfq_log_bfqq(bfqd, bfqq, + "wrais ending at %lu, rais_max_time %u", + jiffies, + jiffies_to_msecs(bfqq-> + wr_cur_max_time)); + } else if (soft_rt) { + /* + * The application is now or still meeting the + * requirements for being deemed soft rt. We + * can then correctly and safely (re)charge + * the weight-raising duration for the + * application with the weight-raising + * duration for soft rt applications. + * + * In particular, doing this recharge now, i.e., + * before the weight-raising period for the + * application finishes, reduces the probability + * of the following negative scenario: + * 1) the weight of a soft rt application is + * raised at startup (as for any newly + * created application), + * 2) since the application is not interactive, + * at a certain time weight-raising is + * stopped for the application, + * 3) at that time the application happens to + * still have pending requests, and hence + * is destined to not have a chance to be + * deemed soft rt before these requests are + * completed (see the comments to the + * function bfq_bfqq_softrt_next_start() + * for details on soft rt detection), + * 4) these pending requests experience a high + * latency because the application is not + * weight-raised while they are pending. + */ + if (bfqq->wr_cur_max_time != + bfqd->bfq_wr_rt_max_time) { + bfqq->wr_start_at_switch_to_srt = + bfqq->last_wr_start_finish; + BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish)); + + bfqq->wr_cur_max_time = + bfqd->bfq_wr_rt_max_time; + bfqq->wr_coeff = bfqd->bfq_wr_coeff * + BFQ_SOFTRT_WEIGHT_FACTOR; + bfq_log_bfqq(bfqd, bfqq, + "switching to soft_rt wr"); + } else + bfq_log_bfqq(bfqd, bfqq, + "moving forward soft_rt wr duration"); + bfqq->last_wr_start_finish = jiffies; + } + } +} + +static bool bfq_bfqq_idle_for_long_time(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + return bfqq->dispatched == 0 && + time_is_before_jiffies( + bfqq->budget_timeout + + bfqd->bfq_wr_min_idle_time); +} + +static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + int old_wr_coeff, + struct request *rq, + bool *interactive) +{ + 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 + * bfq_bfqq_update_budg_for_activation for + * details on the usage of the next variable. + */ + arrived_in_time = ktime_get_ns() <= + RQ_BIC(rq)->ttime.last_end_request + + bfqd->bfq_slice_idle * 3; + + bfq_log_bfqq(bfqd, bfqq, + "bfq_add_request non-busy: " + "jiffies %lu, in_time %d, idle_long %d busyw %d " + "wr_coeff %u", + jiffies, arrived_in_time, + idle_for_long_time, + bfq_bfqq_non_blocking_wait_rq(bfqq), + old_wr_coeff); + + BUG_ON(bfqq->entity.budget < bfqq->entity.service); + + BUG_ON(bfqq == bfqd->in_service_queue); + bfqg_stats_update_io_add(bfqq_group(RQ_BFQQ(rq)), bfqq, rq->cmd_flags); + + /* + * 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) && + bfqq->dispatched == 0; + *interactive = + !in_burst && + idle_for_long_time; + wr_or_deserves_wr = bfqd->low_latency && + (bfqq->wr_coeff > 1 || + (bfq_bfqq_sync(bfqq) && + bfqq->bic && (*interactive || soft_rt))); + + bfq_log_bfqq(bfqd, bfqq, + "bfq_add_request: " + "in_burst %d, " + "soft_rt %d (next %lu), inter %d, bic %p", + bfq_bfqq_in_large_burst(bfqq), soft_rt, + bfqq->soft_rt_next_start, + *interactive, + bfqq->bic); + + /* + * Using the last flag, update budget and check whether bfqq + * may want to preempt the in-service queue. + */ + bfqq_wants_to_preempt = + bfq_bfqq_update_budg_for_activation(bfqd, 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++; + if (bfqq->requests_within_timer >= + bfqd->bfq_requests_within_timer) + bfq_mark_bfqq_IO_bound(bfqq); + } else + bfqq->requests_within_timer = 0; + bfq_log_bfqq(bfqd, bfqq, "requests in time %d", + bfqq->requests_within_timer); + } + + if (bfqd->low_latency) { + if (unlikely(time_is_after_jiffies(bfqq->split_time))) + /* wraparound */ + bfqq->split_time = + jiffies - bfqd->bfq_wr_min_idle_time - 1; + + if (time_is_before_jiffies(bfqq->split_time + + bfqd->bfq_wr_min_idle_time)) { + bfq_update_bfqq_wr_on_rq_arrival(bfqd, bfqq, + old_wr_coeff, + wr_or_deserves_wr, + *interactive, + in_burst, + soft_rt); + + if (old_wr_coeff != bfqq->wr_coeff) + bfqq->entity.prio_changed = 1; + } + } + + bfqq->last_idle_bklogged = jiffies; + bfqq->service_from_backlogged = 0; + bfq_clear_bfqq_softrt_update(bfqq); + + bfq_add_bfqq_busy(bfqd, bfqq); + + /* + * Expire in-service queue only if preemption may be needed + * for guarantees. In this respect, the function + * next_queue_may_preempt just checks a simple, necessary + * condition, and not a sufficient condition based on + * timestamps. In fact, for the latter condition to be + * evaluated, timestamps would need first to be updated, and + * this operation is quite costly (see the comments on the + * function bfq_bfqq_update_budg_for_activation). + */ + if (bfqd->in_service_queue && bfqq_wants_to_preempt && + bfqd->in_service_queue->wr_coeff < bfqq->wr_coeff && + next_queue_may_preempt(bfqd)) { + struct bfq_queue *in_serv = + bfqd->in_service_queue; + BUG_ON(in_serv == bfqq); + + bfq_bfqq_expire(bfqd, bfqd->in_service_queue, + false, BFQ_BFQQ_PREEMPTED); + } +} + +static void bfq_add_request(struct request *rq) +{ + struct bfq_queue *bfqq = RQ_BFQQ(rq); + struct bfq_data *bfqd = bfqq->bfqd; + struct request *next_rq, *prev; + unsigned int old_wr_coeff = bfqq->wr_coeff; + bool interactive = false; + + bfq_log_bfqq(bfqd, bfqq, "size %u %s", + blk_rq_sectors(rq), rq_is_sync(rq) ? "S" : "A"); + + if (bfqq->wr_coeff > 1) /* queue is being weight-raised */ + bfq_log_bfqq(bfqd, bfqq, + "raising period dur %u/%u msec, old coeff %u, w %d(%d)", + jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish), + jiffies_to_msecs(bfqq->wr_cur_max_time), + bfqq->wr_coeff, + bfqq->entity.weight, bfqq->entity.orig_weight); + + bfqq->queued[rq_is_sync(rq)]++; + bfqd->queued++; + + elv_rb_add(&bfqq->sort_list, rq); + + /* + * Check if this request is a better next-to-serve candidate. + */ + prev = bfqq->next_rq; + next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position); + BUG_ON(!next_rq); + bfqq->next_rq = next_rq; + + /* + * Adjust priority tree position, if next_rq changes. + */ + if (prev != bfqq->next_rq) + bfq_pos_tree_add_move(bfqd, bfqq); + + if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */ + bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, old_wr_coeff, + rq, &interactive); + else { + if (bfqd->low_latency && old_wr_coeff == 1 && !rq_is_sync(rq) && + time_is_before_jiffies( + bfqq->last_wr_start_finish + + bfqd->bfq_wr_min_inter_arr_async)) { + bfqq->wr_coeff = bfqd->bfq_wr_coeff; + bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); + + bfqd->wr_busy_queues++; + BUG_ON(bfqd->wr_busy_queues > bfq_tot_busy_queues(bfqd)); + bfqq->entity.prio_changed = 1; + bfq_log_bfqq(bfqd, bfqq, + "non-idle wrais starting, " + "wr_max_time %u wr_busy %d", + jiffies_to_msecs(bfqq->wr_cur_max_time), + bfqd->wr_busy_queues); + } + if (prev != bfqq->next_rq) + bfq_updated_next_req(bfqd, bfqq); + } + + /* + * Assign jiffies to last_wr_start_finish in the following + * cases: + * + * . if bfqq is not going to be weight-raised, because, for + * non weight-raised queues, last_wr_start_finish stores the + * arrival time of the last request; as of now, this piece + * of information is used only for deciding whether to + * weight-raise async queues + * + * . if bfqq is not weight-raised, because, if bfqq is now + * switching to weight-raised, then last_wr_start_finish + * stores the time when weight-raising starts + * + * . if bfqq is interactive, because, regardless of whether + * bfqq is currently weight-raised, the weight-raising + * period must start or restart (this case is considered + * separately because it is not detected by the above + * conditions, if bfqq is already weight-raised) + * + * last_wr_start_finish has to be updated also if bfqq is soft + * real-time, because the weight-raising period is constantly + * restarted on idle-to-busy transitions for these queues, but + * this is already done in bfq_bfqq_handle_idle_busy_switch if + * needed. + */ + if (bfqd->low_latency && + (old_wr_coeff == 1 || bfqq->wr_coeff == 1 || interactive)) + bfqq->last_wr_start_finish = jiffies; +} + +static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd, + struct bio *bio) +{ + struct task_struct *tsk = current; + struct bfq_io_cq *bic; + struct bfq_queue *bfqq; + + bic = bfq_bic_lookup(bfqd, tsk->io_context); + if (!bic) + return NULL; + + bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf)); + if (bfqq) + return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio)); + + return NULL; +} + +static sector_t get_sdist(sector_t last_pos, struct request *rq) +{ + sector_t sdist = 0; + + if (last_pos) { + if (last_pos < blk_rq_pos(rq)) + sdist = blk_rq_pos(rq) - last_pos; + else + sdist = last_pos - blk_rq_pos(rq); + } + + return sdist; +} + +static void bfq_activate_request(struct request_queue *q, struct request *rq) +{ + struct bfq_data *bfqd = q->elevator->elevator_data; + bfqd->rq_in_driver++; +} + +static void bfq_deactivate_request(struct request_queue *q, struct request *rq) +{ + struct bfq_data *bfqd = q->elevator->elevator_data; + + BUG_ON(bfqd->rq_in_driver == 0); + bfqd->rq_in_driver--; +} + +static void bfq_remove_request(struct request *rq) +{ + struct bfq_queue *bfqq = RQ_BFQQ(rq); + struct bfq_data *bfqd = bfqq->bfqd; + const int sync = rq_is_sync(rq); + + /* + * NOTE: + * (bfqq->entity.service > bfqq->entity.budget) may hold here, + * in case of forced dispatches. + */ + + if (bfqq->next_rq == rq) { + bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq); + bfq_updated_next_req(bfqd, bfqq); + } + + if (rq->queuelist.prev != &rq->queuelist) + list_del_init(&rq->queuelist); + BUG_ON(bfqq->queued[sync] == 0); + bfqq->queued[sync]--; + bfqd->queued--; + elv_rb_del(&bfqq->sort_list, rq); + + if (RB_EMPTY_ROOT(&bfqq->sort_list)) { + bfqq->next_rq = NULL; + + BUG_ON(bfqq->entity.budget < 0); + + if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) { + BUG_ON(bfqq->ref < 2); /* referred by rq and on tree */ + bfq_del_bfqq_busy(bfqd, bfqq, false); + /* + * bfqq emptied. In normal operation, when + * bfqq is empty, bfqq->entity.service and + * bfqq->entity.budget must contain, + * respectively, the service received and the + * budget used last time bfqq emptied. These + * facts do not hold in this case, as at least + * this last removal occurred while bfqq is + * not in service. To avoid inconsistencies, + * reset both bfqq->entity.service and + * bfqq->entity.budget, if bfqq has still a + * process that may issue I/O requests to it. + */ + bfqq->entity.budget = bfqq->entity.service = 0; + } + + /* + * Remove queue from request-position tree as it is empty. + */ + if (bfqq->pos_root) { + rb_erase(&bfqq->pos_node, bfqq->pos_root); + bfqq->pos_root = NULL; + } + } else { + BUG_ON(!bfqq->next_rq); + bfq_pos_tree_add_move(bfqd, bfqq); + } + + if (rq->cmd_flags & REQ_META) { + BUG_ON(bfqq->meta_pending == 0); + bfqq->meta_pending--; + } + bfqg_stats_update_io_remove(bfqq_group(bfqq), rq->cmd_flags); +} + +static enum elv_merge bfq_merge(struct request_queue *q, struct request **req, + struct bio *bio) +{ + struct bfq_data *bfqd = q->elevator->elevator_data; + struct request *__rq; + + __rq = bfq_find_rq_fmerge(bfqd, bio); + if (__rq && elv_bio_merge_ok(__rq, bio)) { + *req = __rq; + return ELEVATOR_FRONT_MERGE; + } + + return ELEVATOR_NO_MERGE; +} + +static void bfq_merged_request(struct request_queue *q, struct request *req, + enum elv_merge type) +{ + if (type == ELEVATOR_FRONT_MERGE && + rb_prev(&req->rb_node) && + blk_rq_pos(req) < + blk_rq_pos(container_of(rb_prev(&req->rb_node), + struct request, rb_node))) { + struct bfq_queue *bfqq = RQ_BFQQ(req); + struct bfq_data *bfqd = bfqq->bfqd; + struct request *prev, *next_rq; + + /* Reposition request in its sort_list */ + elv_rb_del(&bfqq->sort_list, req); + elv_rb_add(&bfqq->sort_list, req); + /* Choose next request to be served for bfqq */ + prev = bfqq->next_rq; + next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req, + bfqd->last_position); + BUG_ON(!next_rq); + bfqq->next_rq = next_rq; + /* + * If next_rq changes, update both the queue's budget to + * fit the new request and the queue's position in its + * rq_pos_tree. + */ + if (prev != bfqq->next_rq) { + bfq_updated_next_req(bfqd, bfqq); + bfq_pos_tree_add_move(bfqd, bfqq); + } + } +} + +#ifdef BFQ_GROUP_IOSCHED_ENABLED +static void bfq_bio_merged(struct request_queue *q, struct request *req, + struct bio *bio) +{ + bfqg_stats_update_io_merged(bfqq_group(RQ_BFQQ(req)), bio->bi_opf); +} +#endif + +static void bfq_merged_requests(struct request_queue *q, struct request *rq, + struct request *next) +{ + struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next); + + /* + * If next and rq belong to the same bfq_queue and next is older + * than rq, then reposition rq in the fifo (by substituting next + * with rq). Otherwise, if next and rq belong to different + * bfq_queues, never reposition rq: in fact, we would have to + * reposition it with respect to next's position in its own fifo, + * which would most certainly be too expensive with respect to + * the benefits. + */ + if (bfqq == next_bfqq && + !list_empty(&rq->queuelist) && !list_empty(&next->queuelist) && + next->fifo_time < rq->fifo_time) { + list_del_init(&rq->queuelist); + list_replace_init(&next->queuelist, &rq->queuelist); + rq->fifo_time = next->fifo_time; + } + + if (bfqq->next_rq == next) + bfqq->next_rq = rq; + + bfq_remove_request(next); + bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags); +} + +/* Must be called with bfqq != NULL */ +static void bfq_bfqq_end_wr(struct bfq_queue *bfqq) +{ + BUG_ON(!bfqq); + + if (bfq_bfqq_busy(bfqq)) { + bfqq->bfqd->wr_busy_queues--; + BUG_ON(bfqq->bfqd->wr_busy_queues < 0); + } + bfqq->wr_coeff = 1; + bfqq->wr_cur_max_time = 0; + bfqq->last_wr_start_finish = jiffies; + /* + * Trigger a weight change on the next invocation of + * __bfq_entity_update_weight_prio. + */ + bfqq->entity.prio_changed = 1; + bfq_log_bfqq(bfqq->bfqd, bfqq, + "wrais ending at %lu, rais_max_time %u", + bfqq->last_wr_start_finish, + jiffies_to_msecs(bfqq->wr_cur_max_time)); + bfq_log_bfqq(bfqq->bfqd, bfqq, "wr_busy %d", + bfqq->bfqd->wr_busy_queues); +} + +static void bfq_end_wr_async_queues(struct bfq_data *bfqd, + struct bfq_group *bfqg) +{ + int i, j; + + for (i = 0; i < 2; i++) + for (j = 0; j < IOPRIO_BE_NR; j++) + if (bfqg->async_bfqq[i][j]) + bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]); + if (bfqg->async_idle_bfqq) + bfq_bfqq_end_wr(bfqg->async_idle_bfqq); +} + +static void bfq_end_wr(struct bfq_data *bfqd) +{ + struct bfq_queue *bfqq; + + spin_lock_irq(bfqd->queue->queue_lock); + + list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) + bfq_bfqq_end_wr(bfqq); + list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) + bfq_bfqq_end_wr(bfqq); + bfq_end_wr_async(bfqd); + + spin_unlock_irq(bfqd->queue->queue_lock); +} + +static sector_t bfq_io_struct_pos(void *io_struct, bool request) +{ + if (request) + return blk_rq_pos(io_struct); + else + return ((struct bio *)io_struct)->bi_iter.bi_sector; +} + +static int bfq_rq_close_to_sector(void *io_struct, bool request, + sector_t sector) +{ + return abs(bfq_io_struct_pos(io_struct, request) - sector) <= + BFQQ_CLOSE_THR; +} + +static struct bfq_queue *bfqq_find_close(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + sector_t sector) +{ + struct rb_root *root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree; + struct rb_node *parent, *node; + struct bfq_queue *__bfqq; + + if (RB_EMPTY_ROOT(root)) + return NULL; + + /* + * First, if we find a request starting at the end of the last + * request, choose it. + */ + __bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL); + if (__bfqq) + return __bfqq; + + /* + * If the exact sector wasn't found, the parent of the NULL leaf + * will contain the closest sector (rq_pos_tree sorted by + * next_request position). + */ + __bfqq = rb_entry(parent, struct bfq_queue, pos_node); + if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector)) + return __bfqq; + + if (blk_rq_pos(__bfqq->next_rq) < sector) + node = rb_next(&__bfqq->pos_node); + else + node = rb_prev(&__bfqq->pos_node); + if (!node) + return NULL; + + __bfqq = rb_entry(node, struct bfq_queue, pos_node); + if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector)) + return __bfqq; + + return NULL; +} + +static struct bfq_queue *bfq_find_close_cooperator(struct bfq_data *bfqd, + struct bfq_queue *cur_bfqq, + sector_t sector) +{ + struct bfq_queue *bfqq; + + /* + * We shall notice if some of the queues are cooperating, + * e.g., working closely on the same area of the device. In + * that case, we can group them together and: 1) don't waste + * time idling, and 2) serve the union of their requests in + * the best possible order for throughput. + */ + bfqq = bfqq_find_close(bfqd, cur_bfqq, sector); + if (!bfqq || bfqq == cur_bfqq) + return NULL; + + return bfqq; +} + +static struct bfq_queue * +bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) +{ + int process_refs, new_process_refs; + struct bfq_queue *__bfqq; + + /* + * If there are no process references on the new_bfqq, then it is + * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain + * may have dropped their last reference (not just their last process + * reference). + */ + if (!bfqq_process_refs(new_bfqq)) + return NULL; + + /* Avoid a circular list and skip interim queue merges. */ + while ((__bfqq = new_bfqq->new_bfqq)) { + if (__bfqq == bfqq) + return NULL; + new_bfqq = __bfqq; + } + + process_refs = bfqq_process_refs(bfqq); + new_process_refs = bfqq_process_refs(new_bfqq); + /* + * If the process for the bfqq has gone away, there is no + * sense in merging the queues. + */ + if (process_refs == 0 || new_process_refs == 0) + return NULL; + + bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d", + new_bfqq->pid); + + /* + * Merging is just a redirection: the requests of the process + * owning one of the two queues are redirected to the other queue. + * The latter queue, in its turn, is set as shared if this is the + * 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. + * + * 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. + */ + bfqq->new_bfqq = new_bfqq; + new_bfqq->ref += process_refs; + return new_bfqq; +} + +static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq, + struct bfq_queue *new_bfqq) +{ + if (bfq_too_late_for_merging(new_bfqq)) { + bfq_log_bfqq(bfqq->bfqd, bfqq, + "too late for bfq%d to be merged", + new_bfqq->pid); + return false; + } + + if (bfq_class_idle(bfqq) || bfq_class_idle(new_bfqq) || + (bfqq->ioprio_class != new_bfqq->ioprio_class)) + return false; + + /* + * If either of the queues has already been detected as seeky, + * then merging it with the other queue is unlikely to lead to + * sequential I/O. + */ + if (BFQQ_SEEKY(bfqq) || BFQQ_SEEKY(new_bfqq)) + return false; + + /* + * Interleaved I/O is known to be done by (some) applications + * only for reads, so it does not make sense to merge async + * queues. + */ + if (!bfq_bfqq_sync(bfqq) || !bfq_bfqq_sync(new_bfqq)) + return false; + + return true; +} + +/* + * Attempt to schedule a merge of bfqq with the currently in-service + * queue or with a close queue among the scheduled queues. Return + * NULL if no merge was scheduled, a pointer to the shared bfq_queue + * structure otherwise. + * + * The OOM queue is not allowed to participate to cooperation: in fact, since + * the requests temporarily redirected to the OOM queue could be redirected + * again to dedicated queues at any time, the state needed to correctly + * handle merging with the OOM queue would be quite complex and expensive + * to maintain. Besides, in such a critical condition as an out of memory, + * the benefits of queue merging may be little relevant, or even negligible. + * + * WARNING: queue merging may impair fairness among non-weight raised + * queues, for at least two reasons: 1) the original weight of a + * merged queue may change during the merged state, 2) even being the + * weight the same, a merged queue may be bloated with many more + * requests than the ones produced by its originally-associated + * process. + */ +static struct bfq_queue * +bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, + void *io_struct, bool request) +{ + struct bfq_queue *in_service_bfqq, *new_bfqq; + + /* + * Prevent bfqq from being merged if it has been created too + * long ago. The idea is that true cooperating processes, and + * thus their associated bfq_queues, are supposed to be + * created shortly after each other. This is the case, e.g., + * for KVM/QEMU and dump I/O threads. Basing on this + * assumption, the following filtering greatly reduces the + * probability that two non-cooperating processes, which just + * happen to do close I/O for some short time interval, have + * their queues merged by mistake. + */ + if (bfq_too_late_for_merging(bfqq)) { + bfq_log_bfqq(bfqd, bfqq, + "would have looked for coop, but too late"); + return NULL; + } + + if (bfqq->new_bfqq) + return bfqq->new_bfqq; + + if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq)) + return NULL; + + /* If there is only one backlogged queue, don't search. */ + if (bfq_tot_busy_queues(bfqd) == 1) + return NULL; + + in_service_bfqq = bfqd->in_service_queue; + + if (in_service_bfqq && in_service_bfqq != bfqq && + likely(in_service_bfqq != &bfqd->oom_bfqq) && + bfq_rq_close_to_sector(io_struct, request, bfqd->in_serv_last_pos) && + bfqq->entity.parent == in_service_bfqq->entity.parent && + bfq_may_be_close_cooperator(bfqq, in_service_bfqq)) { + new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq); + if (new_bfqq) + return new_bfqq; + } + /* + * Check whether there is a cooperator among currently scheduled + * queues. The only thing we need is that the bio/request is not + * NULL, as we need it to establish whether a cooperator exists. + */ + new_bfqq = bfq_find_close_cooperator(bfqd, bfqq, + bfq_io_struct_pos(io_struct, request)); + + BUG_ON(new_bfqq && bfqq->entity.parent != new_bfqq->entity.parent); + + if (new_bfqq && likely(new_bfqq != &bfqd->oom_bfqq) && + bfq_may_be_close_cooperator(bfqq, new_bfqq)) + return bfq_setup_merge(bfqq, new_bfqq); + + return NULL; +} + +static void bfq_bfqq_save_state(struct bfq_queue *bfqq) +{ + struct bfq_io_cq *bic = bfqq->bic; + + /* + * If !bfqq->bic, the queue is already shared or its requests + * have already been redirected to a shared queue; both idle window + * and weight raising state have already been saved. Do nothing. + */ + if (!bic) + return; + + bic->saved_has_short_ttime = bfq_bfqq_has_short_ttime(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); + if (unlikely(bfq_bfqq_just_created(bfqq) && + !bfq_bfqq_in_large_burst(bfqq) && + bfqq->bfqd->low_latency)) { + /* + * bfqq being merged ritgh after being created: bfqq + * would have deserved interactive weight raising, but + * did not make it to be set in a weight-raised state, + * because of this early merge. Store directly the + * weight-raising state that would have been assigned + * to bfqq, so that to avoid that bfqq unjustly fails + * to enjoy weight raising if split soon. + */ + bic->saved_wr_coeff = bfqq->bfqd->bfq_wr_coeff; + bic->saved_wr_cur_max_time = bfq_wr_duration(bfqq->bfqd); + bic->saved_last_wr_start_finish = jiffies; + } else { + 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; + } + BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish)); +} + +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) +{ + bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu", + (unsigned long) new_bfqq->pid); + /* Save weight raising and idle window of the merged queues */ + bfq_bfqq_save_state(bfqq); + bfq_bfqq_save_state(new_bfqq); + if (bfq_bfqq_IO_bound(bfqq)) + bfq_mark_bfqq_IO_bound(new_bfqq); + bfq_clear_bfqq_IO_bound(bfqq); + + /* + * If bfqq is weight-raised, then let new_bfqq inherit + * weight-raising. To reduce false positives, neglect the case + * 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). 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; + new_bfqq->wr_cur_max_time = bfqq->wr_cur_max_time; + new_bfqq->last_wr_start_finish = bfqq->last_wr_start_finish; + new_bfqq->wr_start_at_switch_to_srt = + bfqq->wr_start_at_switch_to_srt; + if (bfq_bfqq_busy(new_bfqq)) { + bfqd->wr_busy_queues++; + BUG_ON(bfqd->wr_busy_queues > + bfq_tot_busy_queues(bfqd)); + } + + new_bfqq->entity.prio_changed = 1; + bfq_log_bfqq(bfqd, new_bfqq, + "wr start after merge with %d, rais_max_time %u", + bfqq->pid, + jiffies_to_msecs(bfqq->wr_cur_max_time)); + } + + if (bfqq->wr_coeff > 1) { /* bfqq has given its wr to new_bfqq */ + bfqq->wr_coeff = 1; + bfqq->entity.prio_changed = 1; + if (bfq_bfqq_busy(bfqq)) { + bfqd->wr_busy_queues--; + BUG_ON(bfqd->wr_busy_queues < 0); + } + + } + + bfq_log_bfqq(bfqd, new_bfqq, "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) + */ + bic_set_bfqq(bic, new_bfqq, 1); + bfq_mark_bfqq_coop(new_bfqq); + /* + * new_bfqq now belongs to at least two bics (it is a shared queue): + * set new_bfqq->bic to NULL. bfqq either: + * - does not belong to any bic any more, and hence bfqq->bic must + * be set to NULL, or + * - is a queue whose owning bics have already been redirected to a + * different queue, hence the queue is destined to not belong to + * any bic soon and bfqq->bic is already NULL (therefore the next + * assignment causes no harm). + */ + new_bfqq->bic = NULL; + bfqq->bic = NULL; + /* release process reference to bfqq */ + bfq_put_queue(bfqq); +} + +static int bfq_allow_bio_merge(struct request_queue *q, struct request *rq, + struct bio *bio) +{ + struct bfq_data *bfqd = q->elevator->elevator_data; + bool is_sync = op_is_sync(bio->bi_opf); + struct bfq_io_cq *bic; + struct bfq_queue *bfqq, *new_bfqq; + + /* + * Disallow merge of a sync bio into an async request. + */ + if (is_sync && !rq_is_sync(rq)) + return false; + + /* + * Lookup the bfqq that this bio will be queued with. Allow + * merge only if rq is queued there. + * Queue lock is held here. + */ + bic = bfq_bic_lookup(bfqd, current->io_context); + if (!bic) + return false; + + bfqq = bic_to_bfqq(bic, is_sync); + /* + * We take advantage of this function to perform an early merge + * of the queues of possible cooperating processes. + */ + if (bfqq) { + new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false); + if (new_bfqq) { + bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq); + /* + * If we get here, the bio will be queued in the + * shared queue, i.e., new_bfqq, so use new_bfqq + * to decide whether bio and rq can be merged. + */ + bfqq = new_bfqq; + } + } + + return bfqq == RQ_BFQQ(rq); +} + +static int bfq_allow_rq_merge(struct request_queue *q, struct request *rq, + struct request *next) +{ + return RQ_BFQQ(rq) == RQ_BFQQ(next); +} + +/* + * Set the maximum time for the in-service queue to consume its + * budget. This prevents seeky processes from lowering the throughput. + * In practice, a time-slice service scheme is used with seeky + * processes. + */ +static void bfq_set_budget_timeout(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + unsigned int timeout_coeff; + + if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time) + timeout_coeff = 1; + else + timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight; + + bfqd->last_budget_start = ktime_get(); + + bfqq->budget_timeout = jiffies + + bfqd->bfq_timeout * timeout_coeff; + + bfq_log_bfqq(bfqd, bfqq, "%u", + jiffies_to_msecs(bfqd->bfq_timeout * timeout_coeff)); +} + +static void __bfq_set_in_service_queue(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + if (bfqq) { + bfqg_stats_update_avg_queue_size(bfqq_group(bfqq)); + bfq_mark_bfqq_must_alloc(bfqq); + bfq_clear_bfqq_fifo_expire(bfqq); + + bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8; + + BUG_ON(bfqq == bfqd->in_service_queue); + BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list)); + + if (time_is_before_jiffies(bfqq->last_wr_start_finish) && + bfqq->wr_coeff > 1 && + bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time && + time_is_before_jiffies(bfqq->budget_timeout)) { + /* + * For soft real-time queues, move the start + * of the weight-raising period forward by the + * time the queue has not received any + * service. Otherwise, a relatively long + * service delay is likely to cause the + * weight-raising period of the queue to end, + * because of the short duration of the + * weight-raising period of a soft real-time + * queue. It is worth noting that this move + * is not so dangerous for the other queues, + * because soft real-time queues are not + * greedy. + * + * To not add a further variable, we use the + * overloaded field budget_timeout to + * determine for how long the queue has not + * received service, i.e., how much time has + * elapsed since the queue expired. However, + * this is a little imprecise, because + * budget_timeout is set to jiffies if bfqq + * not only expires, but also remains with no + * request. + */ + if (time_after(bfqq->budget_timeout, + bfqq->last_wr_start_finish)) + bfqq->last_wr_start_finish += + jiffies - bfqq->budget_timeout; + else + bfqq->last_wr_start_finish = jiffies; + + if (time_is_after_jiffies(bfqq->last_wr_start_finish)) { + pr_crit( + "BFQ WARNING:last %lu budget %lu jiffies %lu", + bfqq->last_wr_start_finish, + bfqq->budget_timeout, + jiffies); + pr_crit("diff %lu", jiffies - + max_t(unsigned long, + bfqq->last_wr_start_finish, + bfqq->budget_timeout)); + bfqq->last_wr_start_finish = jiffies; + } + } + + bfq_set_budget_timeout(bfqd, bfqq); + bfq_log_bfqq(bfqd, bfqq, + "cur-budget = %d prio_class %d", + bfqq->entity.budget, bfqq->ioprio_class); + } else + bfq_log(bfqd, "NULL"); + + bfqd->in_service_queue = bfqq; +} + +/* + * Get and set a new queue for service. + */ +static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd) +{ + struct bfq_queue *bfqq = bfq_get_next_queue(bfqd); + + __bfq_set_in_service_queue(bfqd, bfqq); + return 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; + + BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list)); + + /* 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); + + /* + * We don't want to idle for seeks, but we do want to allow + * fair distribution of slice time for a process doing back-to-back + * seeks. So allow a little bit of time for him to submit a new rq. + * + * To prevent processes with (partly) seeky workloads from + * being too ill-treated, grant them a small fraction of the + * assigned budget before reducing the waiting time to + * BFQ_MIN_TT. This happened to help reduce latency. + */ + sl = bfqd->bfq_slice_idle; + /* + * 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 asymemtric 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(u32, sl, BFQ_MIN_TT); + + bfqd->last_idling_start = ktime_get(); + hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl), + HRTIMER_MODE_REL); + bfqg_stats_set_start_idle_time(bfqq_group(bfqq)); + bfq_log(bfqd, "arm idle: %ld/%ld ms", + sl / NSEC_PER_MSEC, bfqd->bfq_slice_idle / NSEC_PER_MSEC); +} + +/* + * In autotuning mode, max_budget is dynamically recomputed as the + * amount of sectors transferred in timeout at the estimated peak + * rate. This enables BFQ to utilize a full timeslice with a full + * budget, even if the in-service queue is served at peak rate. And + * this maximises throughput with sequential workloads. + */ +static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd) +{ + return (u64)bfqd->peak_rate * USEC_PER_MSEC * + jiffies_to_msecs(bfqd->bfq_timeout)>>BFQ_RATE_SHIFT; +} + +/* + * Update parameters related to throughput and responsiveness, as a + * function of the estimated peak rate. See comments on + * bfq_calc_max_budget(), and on the ref_wr_duration array. + */ +static void update_thr_responsiveness_params(struct bfq_data *bfqd) +{ + if (bfqd->bfq_user_max_budget == 0) { + bfqd->bfq_max_budget = + bfq_calc_max_budget(bfqd); + BUG_ON(bfqd->bfq_max_budget < 0); + bfq_log(bfqd, "new max_budget = %d", + bfqd->bfq_max_budget); + } +} + +static void bfq_reset_rate_computation(struct bfq_data *bfqd, struct request *rq) +{ + if (rq != NULL) { /* new rq dispatch now, reset accordingly */ + bfqd->last_dispatch = bfqd->first_dispatch = ktime_get_ns() ; + bfqd->peak_rate_samples = 1; + bfqd->sequential_samples = 0; + bfqd->tot_sectors_dispatched = bfqd->last_rq_max_size = + blk_rq_sectors(rq); + } else /* no new rq dispatched, just reset the number of samples */ + bfqd->peak_rate_samples = 0; /* full re-init on next disp. */ + + bfq_log(bfqd, + "at end, sample %u/%u tot_sects %llu", + bfqd->peak_rate_samples, bfqd->sequential_samples, + bfqd->tot_sectors_dispatched); +} + +static void bfq_update_rate_reset(struct bfq_data *bfqd, struct request *rq) +{ + u32 rate, weight, divisor; + + /* + * For the convergence property to hold (see comments on + * bfq_update_peak_rate()) and for the assessment to be + * reliable, a minimum number of samples must be present, and + * a minimum amount of time must have elapsed. If not so, do + * not compute new rate. Just reset parameters, to get ready + * for a new evaluation attempt. + */ + if (bfqd->peak_rate_samples < BFQ_RATE_MIN_SAMPLES || + bfqd->delta_from_first < BFQ_RATE_MIN_INTERVAL) { + bfq_log(bfqd, + "only resetting, delta_first %lluus samples %d", + bfqd->delta_from_first>>10, bfqd->peak_rate_samples); + goto reset_computation; + } + + /* + * If a new request completion has occurred after last + * dispatch, then, to approximate the rate at which requests + * have been served by the device, it is more precise to + * extend the observation interval to the last completion. + */ + bfqd->delta_from_first = + max_t(u64, bfqd->delta_from_first, + bfqd->last_completion - bfqd->first_dispatch); + + BUG_ON(bfqd->delta_from_first == 0); + /* + * Rate computed in sects/usec, and not sects/nsec, for + * precision issues. + */ + rate = div64_ul(bfqd->tot_sectors_dispatched<delta_from_first, NSEC_PER_USEC)); + + bfq_log(bfqd, +"tot_sects %llu delta_first %lluus rate %llu sects/s (%d)", + bfqd->tot_sectors_dispatched, bfqd->delta_from_first>>10, + ((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT), + rate > 20< 20M sectors/sec) + */ + if ((bfqd->sequential_samples < (3 * bfqd->peak_rate_samples)>>2 && + rate <= bfqd->peak_rate) || + rate > 20<peak_rate_samples, bfqd->sequential_samples, + ((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT), + ((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT)); + goto reset_computation; + } else { + bfq_log(bfqd, + "do update, samples %u/%u rate/peak %llu/%llu", + bfqd->peak_rate_samples, bfqd->sequential_samples, + ((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT), + ((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT)); + } + + /* + * We have to update the peak rate, at last! To this purpose, + * we use a low-pass filter. We compute the smoothing constant + * of the filter as a function of the 'weight' of the new + * measured rate. + * + * As can be seen in next formulas, we define this weight as a + * quantity proportional to how sequential the workload is, + * and to how long the observation time interval is. + * + * The weight runs from 0 to 8. The maximum value of the + * weight, 8, yields the minimum value for the smoothing + * constant. At this minimum value for the smoothing constant, + * the measured rate contributes for half of the next value of + * the estimated peak rate. + * + * So, the first step is to compute the weight as a function + * of how sequential the workload is. Note that the weight + * cannot reach 9, because bfqd->sequential_samples cannot + * become equal to bfqd->peak_rate_samples, which, in its + * turn, holds true because bfqd->sequential_samples is not + * incremented for the first sample. + */ + weight = (9 * bfqd->sequential_samples) / bfqd->peak_rate_samples; + + /* + * Second step: further refine the weight as a function of the + * duration of the observation interval. + */ + weight = min_t(u32, 8, + div_u64(weight * bfqd->delta_from_first, + BFQ_RATE_REF_INTERVAL)); + + /* + * Divisor ranging from 10, for minimum weight, to 2, for + * maximum weight. + */ + divisor = 10 - weight; + BUG_ON(divisor == 0); + + /* + * Finally, update peak rate: + * + * peak_rate = peak_rate * (divisor-1) / divisor + rate / divisor + */ + bfqd->peak_rate *= divisor-1; + bfqd->peak_rate /= divisor; + rate /= divisor; /* smoothing constant alpha = 1/divisor */ + + bfq_log(bfqd, + "divisor %d tmp_peak_rate %llu tmp_rate %u", + divisor, + ((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT), + (u32)((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT)); + + BUG_ON(bfqd->peak_rate == 0); + BUG_ON(bfqd->peak_rate > 20<peak_rate += rate; + + /* + * For a very slow device, bfqd->peak_rate can reach 0 (see + * the minimum representable values reported in the comments + * on BFQ_RATE_SHIFT). Push to 1 if this happens, to avoid + * divisions by zero where bfqd->peak_rate is used as a + * divisor. + */ + bfqd->peak_rate = max_t(u32, 1, bfqd->peak_rate); + + update_thr_responsiveness_params(bfqd); + BUG_ON(bfqd->peak_rate > 20<peak_rate_samples == 0) { /* first dispatch */ + bfq_log(bfqd, + "goto reset, samples %d", + bfqd->peak_rate_samples) ; + bfq_reset_rate_computation(bfqd, rq); + goto update_last_values; /* will add one sample */ + } + + /* + * Device idle for very long: the observation interval lasting + * up to this dispatch cannot be a valid observation interval + * for computing a new peak rate (similarly to the late- + * completion event in bfq_completed_request()). Go to + * update_rate_and_reset to have the following three steps + * taken: + * - close the observation interval at the last (previous) + * request dispatch or completion + * - compute rate, if possible, for that observation interval + * - start a new observation interval with this dispatch + */ + if (now_ns - bfqd->last_dispatch > 100*NSEC_PER_MSEC && + bfqd->rq_in_driver == 0) { + bfq_log(bfqd, +"jumping to updating&resetting delta_last %lluus samples %d", + (now_ns - bfqd->last_dispatch)>>10, + bfqd->peak_rate_samples) ; + goto update_rate_and_reset; + } + + /* Update sampling information */ + bfqd->peak_rate_samples++; + + if ((bfqd->rq_in_driver > 0 || + now_ns - bfqd->last_completion < BFQ_MIN_TT) + && !BFQ_RQ_SEEKY(bfqd, bfqd->last_position, rq)) + bfqd->sequential_samples++; + + bfqd->tot_sectors_dispatched += blk_rq_sectors(rq); + + /* Reset max observed rq size every 32 dispatches */ + if (likely(bfqd->peak_rate_samples % 32)) + bfqd->last_rq_max_size = + max_t(u32, blk_rq_sectors(rq), bfqd->last_rq_max_size); + else + bfqd->last_rq_max_size = blk_rq_sectors(rq); + + bfqd->delta_from_first = now_ns - bfqd->first_dispatch; + + bfq_log(bfqd, + "added samples %u/%u tot_sects %llu delta_first %lluus", + bfqd->peak_rate_samples, bfqd->sequential_samples, + bfqd->tot_sectors_dispatched, + bfqd->delta_from_first>>10); + + /* Target observation interval not yet reached, go on sampling */ + if (bfqd->delta_from_first < BFQ_RATE_REF_INTERVAL) + goto update_last_values; + +update_rate_and_reset: + bfq_update_rate_reset(bfqd, rq); +update_last_values: + bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq); + if (RQ_BFQQ(rq) == bfqd->in_service_queue) + bfqd->in_serv_last_pos = bfqd->last_position; + bfqd->last_dispatch = now_ns; + + bfq_log(bfqd, + "delta_first %lluus last_pos %llu peak_rate %llu", + (now_ns - bfqd->first_dispatch)>>10, + (unsigned long long) bfqd->last_position, + ((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT)); + bfq_log(bfqd, + "samples at end %d", bfqd->peak_rate_samples); +} + +/* + * Move request from internal lists to the dispatch list of the request queue + */ +static void bfq_dispatch_insert(struct request_queue *q, struct request *rq) +{ + struct bfq_queue *bfqq = RQ_BFQQ(rq); + + /* + * For consistency, the next instruction should have been executed + * after removing the request from the queue and dispatching it. + * We execute instead this instruction before bfq_remove_request() + * (and hence introduce a temporary inconsistency), for efficiency. + * In fact, in a forced_dispatch, this prevents two counters related + * to bfqq->dispatched to risk to be uselessly decremented if bfqq + * is not in service, and then to be incremented again after + * incrementing bfqq->dispatched. + */ + bfqq->dispatched++; + bfq_update_peak_rate(q->elevator->elevator_data, rq); + + bfq_remove_request(rq); + elv_dispatch_sort(q, rq); +} + +static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq) +{ + BUG_ON(bfqq != bfqd->in_service_queue); + + /* + * If this bfqq is shared between multiple processes, check + * to make sure that those processes are still issuing I/Os + * within the mean seek distance. If not, it may be time to + * break the queues apart again. + */ + if (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq)) + bfq_mark_bfqq_split_coop(bfqq); + + if (RB_EMPTY_ROOT(&bfqq->sort_list)) { + if (bfqq->dispatched == 0) + /* + * Overloading budget_timeout field to store + * the time at which the queue remains with no + * backlog and no outstanding request; used by + * the weight-raising mechanism. + */ + bfqq->budget_timeout = jiffies; + + bfq_del_bfqq_busy(bfqd, bfqq, true); + } else { + bfq_requeue_bfqq(bfqd, bfqq, true); + /* + * Resort priority tree of potential close cooperators. + */ + bfq_pos_tree_add_move(bfqd, bfqq); + } + + /* + * All in-service entities must have been properly deactivated + * or requeued before executing the next function, which + * resets all in-service entites as no more in service. + */ + __bfq_bfqd_reset_in_service(bfqd); +} + +/** + * __bfq_bfqq_recalc_budget - try to adapt the budget to the @bfqq behavior. + * @bfqd: device data. + * @bfqq: queue to update. + * @reason: reason for expiration. + * + * Handle the feedback on @bfqq budget at queue expiration. + * See the body for detailed comments. + */ +static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + enum bfqq_expiration reason) +{ + struct request *next_rq; + int budget, min_budget; + + BUG_ON(bfqq != bfqd->in_service_queue); + + min_budget = bfq_min_budget(bfqd); + + if (bfqq->wr_coeff == 1) + budget = bfqq->max_budget; + else /* + * Use a constant, low budget for weight-raised queues, + * to help achieve a low latency. Keep it slightly higher + * than the minimum possible budget, to cause a little + * bit fewer expirations. + */ + budget = 2 * min_budget; + + bfq_log_bfqq(bfqd, bfqq, "last budg %d, budg left %d", + bfqq->entity.budget, bfq_bfqq_budget_left(bfqq)); + bfq_log_bfqq(bfqd, bfqq, "last max_budg %d, min budg %d", + budget, bfq_min_budget(bfqd)); + bfq_log_bfqq(bfqd, bfqq, "sync %d, seeky %d", + bfq_bfqq_sync(bfqq), BFQQ_SEEKY(bfqd->in_service_queue)); + + if (bfq_bfqq_sync(bfqq) && bfqq->wr_coeff == 1) { + switch (reason) { + /* + * Caveat: in all the following cases we trade latency + * for throughput. + */ + case BFQ_BFQQ_TOO_IDLE: + /* + * This is the only case where we may reduce + * the budget: if there is no request of the + * process still waiting for completion, then + * we assume (tentatively) that the timer has + * expired because the batch of requests of + * the process could have been served with a + * smaller budget. Hence, betting that + * process will behave in the same way when it + * becomes backlogged again, we reduce its + * next budget. As long as we guess right, + * this budget cut reduces the latency + * experienced by the process. + * + * However, if there are still outstanding + * requests, then the process may have not yet + * issued its next request just because it is + * still waiting for the completion of some of + * the still outstanding ones. So in this + * subcase we do not reduce its budget, on the + * contrary we increase it to possibly boost + * the throughput, as discussed in the + * comments to the BUDGET_TIMEOUT case. + */ + if (bfqq->dispatched > 0) /* still outstanding reqs */ + budget = min(budget * 2, bfqd->bfq_max_budget); + else { + if (budget > 5 * min_budget) + budget -= 4 * min_budget; + else + budget = min_budget; + } + break; + case BFQ_BFQQ_BUDGET_TIMEOUT: + /* + * We double the budget here because it gives + * the chance to boost the throughput if this + * is not a seeky process (and has bumped into + * this timeout because of, e.g., ZBR). + */ + budget = min(budget * 2, bfqd->bfq_max_budget); + break; + case BFQ_BFQQ_BUDGET_EXHAUSTED: + /* + * The process still has backlog, and did not + * let either the budget timeout or the disk + * idling timeout expire. Hence it is not + * seeky, has a short thinktime and may be + * happy with a higher budget too. So + * definitely increase the budget of this good + * candidate to boost the disk throughput. + */ + budget = min(budget * 4, bfqd->bfq_max_budget); + break; + case BFQ_BFQQ_NO_MORE_REQUESTS: + /* + * For queues that expire for this reason, it + * is particularly important to keep the + * budget close to the actual service they + * need. Doing so reduces the timestamp + * misalignment problem described in the + * comments in the body of + * __bfq_activate_entity. In fact, suppose + * that a queue systematically expires for + * BFQ_BFQQ_NO_MORE_REQUESTS and presents a + * new request in time to enjoy timestamp + * back-shifting. The larger the budget of the + * queue is with respect to the service the + * queue actually requests in each service + * slot, the more times the queue can be + * reactivated with the same virtual finish + * time. It follows that, even if this finish + * time is pushed to the system virtual time + * to reduce the consequent timestamp + * misalignment, the queue unjustly enjoys for + * many re-activations a lower finish time + * than all newly activated queues. + * + * The service needed by bfqq is measured + * quite precisely by bfqq->entity.service. + * Since bfqq does not enjoy device idling, + * bfqq->entity.service is equal to the number + * of sectors that the process associated with + * bfqq requested to read/write before waiting + * for request completions, or blocking for + * other reasons. + */ + budget = max_t(int, bfqq->entity.service, min_budget); + break; + default: + return; + } + } else if (!bfq_bfqq_sync(bfqq)) + /* + * Async queues get always the maximum possible + * budget, as for them we do not care about latency + * (in addition, their ability to dispatch is limited + * by the charging factor). + */ + budget = bfqd->bfq_max_budget; + + bfqq->max_budget = budget; + + if (bfqd->budgets_assigned >= bfq_stats_min_budgets && + !bfqd->bfq_user_max_budget) + bfqq->max_budget = min(bfqq->max_budget, bfqd->bfq_max_budget); + + /* + * If there is still backlog, then assign a new budget, making + * sure that it is large enough for the next request. Since + * the finish time of bfqq must be kept in sync with the + * budget, be sure to call __bfq_bfqq_expire() *after* this + * update. + * + * If there is no backlog, then no need to update the budget; + * it will be updated on the arrival of a new request. + */ + next_rq = bfqq->next_rq; + if (next_rq) { + BUG_ON(reason == BFQ_BFQQ_TOO_IDLE || + reason == BFQ_BFQQ_NO_MORE_REQUESTS); + bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget, + bfq_serv_to_charge(next_rq, bfqq)); + BUG_ON(!bfq_bfqq_busy(bfqq)); + BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list)); + } + + bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %d", + next_rq ? blk_rq_sectors(next_rq) : 0, + bfqq->entity.budget); +} + +/* + * Return true if the process associated with bfqq is "slow". The slow + * flag is used, in addition to the budget timeout, to reduce the + * amount of service provided to seeky processes, and thus reduce + * their chances to lower the throughput. More details in the comments + * on the function bfq_bfqq_expire(). + * + * An important observation is in order: as discussed in the comments + * on the function bfq_update_peak_rate(), with devices with internal + * queues, it is hard if ever possible to know when and for how long + * an I/O request is processed by the device (apart from the trivial + * I/O pattern where a new request is dispatched only after the + * previous one has been completed). This makes it hard to evaluate + * the real rate at which the I/O requests of each bfq_queue are + * served. In fact, for an I/O scheduler like BFQ, serving a + * bfq_queue means just dispatching its requests during its service + * slot (i.e., until the budget of the queue is exhausted, or the + * queue remains idle, or, finally, a timeout fires). But, during the + * service slot of a bfq_queue, around 100 ms at most, the device may + * be even still processing requests of bfq_queues served in previous + * service slots. On the opposite end, the requests of the in-service + * bfq_queue may be completed after the service slot of the queue + * finishes. + * + * Anyway, unless more sophisticated solutions are used + * (where possible), the sum of the sizes of the requests dispatched + * during the service slot of a bfq_queue is probably the only + * approximation available for the service received by the bfq_queue + * during its service slot. And this sum is the quantity used in this + * function to evaluate the I/O speed of a process. + */ +static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq, + bool compensate, enum bfqq_expiration reason, + unsigned long *delta_ms) +{ + ktime_t delta_ktime; + u32 delta_usecs; + bool slow = BFQQ_SEEKY(bfqq); /* if delta too short, use seekyness */ + + if (!bfq_bfqq_sync(bfqq)) + return false; + + if (compensate) + delta_ktime = bfqd->last_idling_start; + else + delta_ktime = ktime_get(); + delta_ktime = ktime_sub(delta_ktime, bfqd->last_budget_start); + delta_usecs = ktime_to_us(delta_ktime); + + /* don't use too short time intervals */ + if (delta_usecs < 1000) { + if (blk_queue_nonrot(bfqd->queue)) + /* + * give same worst-case guarantees as idling + * for seeky + */ + *delta_ms = BFQ_MIN_TT / NSEC_PER_MSEC; + else /* charge at least one seek */ + *delta_ms = bfq_slice_idle / NSEC_PER_MSEC; + + bfq_log(bfqd, "too short %u", delta_usecs); + + return slow; + } + + *delta_ms = delta_usecs / USEC_PER_MSEC; + + /* + * Use only long (> 20ms) intervals to filter out excessive + * spikes in service rate estimation. + */ + if (delta_usecs > 20000) { + /* + * Caveat for rotational devices: processes doing I/O + * in the slower disk zones tend to be slow(er) even + * if not seeky. In this respect, the estimated peak + * rate is likely to be an average over the disk + * surface. Accordingly, to not be too harsh with + * unlucky processes, a process is deemed slow only if + * its rate has been lower than half of the estimated + * peak rate. + */ + slow = bfqq->entity.service < bfqd->bfq_max_budget / 2; + bfq_log(bfqd, "relative rate %d/%d", + bfqq->entity.service, bfqd->bfq_max_budget); + } + + bfq_log_bfqq(bfqd, bfqq, "slow %d", slow); + + return slow; +} + +/* + * To be deemed as soft real-time, an application must meet two + * requirements. First, the application must not require an average + * bandwidth higher than the approximate bandwidth required to playback or + * record a compressed high-definition video. + * The next function is invoked on the completion of the last request of a + * batch, to compute the next-start time instant, soft_rt_next_start, such + * that, if the next request of the application does not arrive before + * soft_rt_next_start, then the above requirement on the bandwidth is met. + * + * The second requirement is that the request pattern of the application is + * isochronous, i.e., that, after issuing a request or a batch of requests, + * the application stops issuing new requests until all its pending requests + * have been completed. After that, the application may issue a new batch, + * and so on. + * For this reason the next function is invoked to compute + * soft_rt_next_start only for applications that meet this requirement, + * whereas soft_rt_next_start is set to infinity for applications that do + * not. + * + * Unfortunately, even a greedy (i.e., I/O-bound) application may + * happen to meet, occasionally or systematically, both the above + * bandwidth and isochrony requirements. This may happen at least in + * the following circumstances. First, if the CPU load is high. The + * application may stop issuing requests while the CPUs are busy + * serving other processes, then restart, then stop again for a while, + * and so on. The other circumstances are related to the storage + * device: the storage device is highly loaded or reaches a low-enough + * throughput with the I/O of the application (e.g., because the I/O + * is random and/or the device is slow). In all these cases, the + * I/O of the application may be simply slowed down enough to meet + * the bandwidth and isochrony requirements. To reduce the probability + * that greedy applications are deemed as soft real-time in these + * corner cases, a further rule is used in the computation of + * soft_rt_next_start: the return value of this function is forced to + * be higher than the maximum between the following two quantities. + * + * (a) Current time plus: (1) the maximum time for which the arrival + * of a request is waited for when a sync queue becomes idle, + * namely bfqd->bfq_slice_idle, and (2) a few extra jiffies. We + * postpone for a moment the reason for adding a few extra + * jiffies; we get back to it after next item (b). Lower-bounding + * the return value of this function with the current time plus + * bfqd->bfq_slice_idle tends to filter out greedy applications, + * because the latter issue their next request as soon as possible + * after the last one has been completed. In contrast, a soft + * real-time application spends some time processing data, after a + * batch of its requests has been completed. + * + * (b) Current value of bfqq->soft_rt_next_start. As pointed out + * above, greedy applications may happen to meet both the + * bandwidth and isochrony requirements under heavy CPU or + * storage-device load. In more detail, in these scenarios, these + * applications happen, only for limited time periods, to do I/O + * slowly enough to meet all the requirements described so far, + * including the filtering in above item (a). These slow-speed + * time intervals are usually interspersed between other time + * intervals during which these applications do I/O at a very high + * speed. Fortunately, exactly because of the high speed of the + * I/O in the high-speed intervals, the values returned by this + * function happen to be so high, near the end of any such + * high-speed interval, to be likely to fall *after* the end of + * the low-speed time interval that follows. These high values are + * stored in bfqq->soft_rt_next_start after each invocation of + * this function. As a consequence, if the last value of + * bfqq->soft_rt_next_start is constantly used to lower-bound the + * next value that this function may return, then, from the very + * beginning of a low-speed interval, bfqq->soft_rt_next_start is + * likely to be constantly kept so high that any I/O request + * issued during the low-speed interval is considered as arriving + * to soon for the application to be deemed as soft + * real-time. Then, in the high-speed interval that follows, the + * application will not be deemed as soft real-time, just because + * it will do I/O at a high speed. And so on. + * + * Getting back to the filtering in item (a), in the following two + * cases this filtering might be easily passed by a greedy + * application, if the reference quantity was just + * bfqd->bfq_slice_idle: + * 1) HZ is so low that the duration of a jiffy is comparable to or + * higher than bfqd->bfq_slice_idle. This happens, e.g., on slow + * devices with HZ=100. The time granularity may be so coarse + * that the approximation, in jiffies, of bfqd->bfq_slice_idle + * is rather lower than the exact value. + * 2) jiffies, instead of increasing at a constant rate, may stop increasing + * for a while, then suddenly 'jump' by several units to recover the lost + * increments. This seems to happen, e.g., inside virtual machines. + * To address this issue, in the filtering in (a) we do not use as a + * reference time interval just bfqd->bfq_slice_idle, but + * bfqd->bfq_slice_idle plus a few jiffies. In particular, we add the + * minimum number of jiffies for which the filter seems to be quite + * precise also in embedded systems and KVM/QEMU virtual machines. + */ +static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + bfq_log_bfqq(bfqd, bfqq, +"service_blkg %lu soft_rate %u sects/sec interval %u", + bfqq->service_from_backlogged, + bfqd->bfq_wr_max_softrt_rate, + jiffies_to_msecs(HZ * bfqq->service_from_backlogged / + bfqd->bfq_wr_max_softrt_rate)); + + return max3(bfqq->soft_rt_next_start, + bfqq->last_idle_bklogged + + HZ * bfqq->service_from_backlogged / + bfqd->bfq_wr_max_softrt_rate, + jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4); +} + +static bool bfq_bfqq_injectable(struct bfq_queue *bfqq) +{ + return BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 && + blk_queue_nonrot(bfqq->bfqd->queue) && + bfqq->bfqd->hw_tag; +} + +/** + * bfq_bfqq_expire - expire a queue. + * @bfqd: device owning the queue. + * @bfqq: the queue to expire. + * @compensate: if true, compensate for the time spent idling. + * @reason: the reason causing the expiration. + * + * If the process associated with bfqq does slow I/O (e.g., because it + * issues random requests), we charge bfqq with the time it has been + * in service instead of the service it has received (see + * bfq_bfqq_charge_time for details on how this goal is achieved). As + * a consequence, bfqq will typically get higher timestamps upon + * reactivation, and hence it will be rescheduled as if it had + * received more service than what it has actually received. In the + * end, bfqq receives less service in proportion to how slowly its + * associated process consumes its budgets (and hence how seriously it + * tends to lower the throughput). In addition, this time-charging + * strategy guarantees time fairness among slow processes. In + * contrast, if the process associated with bfqq is not slow, we + * charge bfqq exactly with the service it has received. + * + * Charging time to the first type of queues and the exact service to + * the other has the effect of using the WF2Q+ policy to schedule the + * 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) +{ + bool slow; + unsigned long delta = 0; + struct bfq_entity *entity = &bfqq->entity; + int ref; + + BUG_ON(bfqq != bfqd->in_service_queue); + + /* + * Check whether the process is slow (see bfq_bfqq_is_slow). + */ + slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta); + + /* + * As above explained, charge slow (typically seeky) and + * timed-out queues with the time and not the service + * received, to favor sequential workloads. + * + * Processes doing I/O in the slower disk zones will tend to + * be slow(er) even if not seeky. Therefore, since the + * estimated peak rate is actually an average over the disk + * surface, these processes may timeout just for bad luck. To + * avoid punishing them, do not charge time to processes that + * succeeded in consuming at least 2/3 of their budget. This + * allows BFQ to preserve enough elasticity to still perform + * bandwidth, and not time, distribution with little unlucky + * or quasi-sequential processes. + */ + if (bfqq->wr_coeff == 1 && + (slow || + (reason == BFQ_BFQQ_BUDGET_TIMEOUT && + bfq_bfqq_budget_left(bfqq) >= entity->budget / 3))) + bfq_bfqq_charge_time(bfqd, bfqq, delta); + + BUG_ON(bfqq->entity.budget < bfqq->entity.service); + + if (reason == BFQ_BFQQ_TOO_IDLE && + entity->service <= 2 * entity->budget / 10) + bfq_clear_bfqq_IO_bound(bfqq); + + if (bfqd->low_latency && bfqq->wr_coeff == 1) + bfqq->last_wr_start_finish = jiffies; + + if (bfqd->low_latency && bfqd->bfq_wr_max_softrt_rate > 0 && + RB_EMPTY_ROOT(&bfqq->sort_list)) { + /* + * If we get here, and there are no outstanding + * requests, then the request pattern is isochronous + * (see the comments on the function + * bfq_bfqq_softrt_next_start()). Thus we can compute + * soft_rt_next_start. And we do it, unless bfqq is in + * interactive weight raising. We do not do it in the + * latter subcase, for the following reason. bfqq may + * be conveying the I/O needed to load a soft + * real-time application. Such an application will + * actually exhibit a soft real-time I/O pattern after + * it finally starts doing its job. But, if + * soft_rt_next_start is computed here for an + * interactive bfqq, and bfqq had received a lot of + * service before remaining with no outstanding + * request (likely to happen on a fast device), then + * soft_rt_next_start would be assigned such a high + * value that, for a very long time, bfqq would be + * prevented from being possibly considered as soft + * real time. + * + * If, instead, the queue still has outstanding + * requests, then we have to wait for the completion + * of all the outstanding requests to discover whether + * the request pattern is actually isochronous. + */ + BUG_ON(bfq_tot_busy_queues(bfqd) < 1); + if (bfqq->dispatched == 0 && + bfqq->wr_coeff != bfqd->bfq_wr_coeff) { + bfqq->soft_rt_next_start = + bfq_bfqq_softrt_next_start(bfqd, bfqq); + bfq_log_bfqq(bfqd, bfqq, "new soft_rt_next %lu", + bfqq->soft_rt_next_start); + } else if (bfqq->dispatched > 0) { + /* + * Schedule an update of soft_rt_next_start to when + * the task may be discovered to be isochronous. + */ + bfq_mark_bfqq_softrt_update(bfqq); + } + } + + bfq_log_bfqq(bfqd, bfqq, + "expire (%s, slow %d, num_disp %d, short %d, weight %d, serv %d/%d)", + reason_name[reason], slow, bfqq->dispatched, + bfq_bfqq_has_short_ttime(bfqq), entity->weight, + entity->service, entity->budget); + + /* + * Increase, decrease or leave budget unchanged according to + * reason. + */ + BUG_ON(bfqq->entity.budget < bfqq->entity.service); + __bfq_bfqq_recalc_budget(bfqd, bfqq, reason); + BUG_ON(bfqq->next_rq == NULL && + bfqq->entity.budget < bfqq->entity.service); + ref = bfqq->ref; + __bfq_bfqq_expire(bfqd, bfqq); + + if (ref == 1) /* bfqq is gone, no more actions on it */ + return; + + BUG_ON(ref > 1 && + !bfq_bfqq_busy(bfqq) && reason == BFQ_BFQQ_BUDGET_EXHAUSTED && + !bfq_class_idle(bfqq)); + + bfqq->injected_service = 0; + + /* mark bfqq as waiting a request only if a bic still points to it */ + if (!bfq_bfqq_busy(bfqq) && + reason != BFQ_BFQQ_BUDGET_TIMEOUT && + reason != BFQ_BFQQ_BUDGET_EXHAUSTED) { + BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list)); + BUG_ON(bfqq->next_rq); + bfq_mark_bfqq_non_blocking_wait_rq(bfqq); + /* + * Not setting service to 0, because, if the next rq + * arrives in time, the queue will go on receiving + * service with this same budget (as if it never expired) + */ + } else { + entity->service = 0; + bfq_log_bfqq(bfqd, bfqq, "resetting service"); + } + + /* + * Reset the received-service counter for every parent entity. + * Differently from what happens with bfqq->entity.service, + * the resetting of this counter never needs to be postponed + * for parent entities. In fact, in case bfqq may have a + * chance to go on being served using the last, partially + * consumed budget, bfqq->entity.service needs to be kept, + * because if bfqq then actually goes on being served using + * the same budget, the last value of bfqq->entity.service is + * needed to properly decrement bfqq->entity.budget by the + * portion already consumed. In contrast, it is not necessary + * to keep entity->service for parent entities too, because + * the bubble up of the new value of bfqq->entity.budget will + * make sure that the budgets of parent entities are correct, + * even in case bfqq and thus parent entities go on receiving + * service with the same budget. + */ + entity = entity->parent; + for_each_entity(entity) + entity->service = 0; +} + +/* + * Budget timeout is not implemented through a dedicated timer, but + * just checked on request arrivals and completions, as well as on + * idle timer expirations. + */ +static bool bfq_bfqq_budget_timeout(struct bfq_queue *bfqq) +{ + return time_is_before_eq_jiffies(bfqq->budget_timeout); +} + +/* + * If we expire a queue that is actively waiting (i.e., with the + * device idled) for the arrival of a new request, then we may incur + * the timestamp misalignment problem described in the body of the + * function __bfq_activate_entity. Hence we return true only if this + * condition does not hold, or if the queue is slow enough to deserve + * only to be kicked off for preserving a high throughput. + */ +static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq) +{ + bfq_log_bfqq(bfqq->bfqd, bfqq, + "wait_request %d left %d timeout %d", + bfq_bfqq_wait_request(bfqq), + bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3, + bfq_bfqq_budget_timeout(bfqq)); + + return (!bfq_bfqq_wait_request(bfqq) || + bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3) + && + bfq_bfqq_budget_timeout(bfqq); +} + +static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + bool rot_without_queueing = + !blk_queue_nonrot(bfqd->queue) && !bfqd->hw_tag, + bfqq_sequential_and_IO_bound, + idling_boosts_thr; + + bfqq_sequential_and_IO_bound = !BFQQ_SEEKY(bfqq) && + bfq_bfqq_IO_bound(bfqq) && bfq_bfqq_has_short_ttime(bfqq); + /* + * The next variable takes into account the cases where idling + * boosts the throughput. + * + * 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 and rotational, or + * (b) regardless of the presence of NCQ, the device is rotational and + * the request pattern for bfqq is I/O-bound and sequential, or + * (c) regardless of whether it is rotational, the device is + * not NCQ-capable 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), (b) or (c) is true, and, in + * particular, happens to be false if bfqd is an NCQ-capable + * flash-based device. + */ + idling_boosts_thr = rot_without_queueing || + ((!blk_queue_nonrot(bfqd->queue) || !bfqd->hw_tag) && + bfqq_sequential_and_IO_bound); + + bfq_log_bfqq(bfqd, bfqq, "idling_boosts_thr %d", idling_boosts_thr); + + /* + * The return value of this function is equal to that of + * idling_boosts_thr, unless a special case holds. In this + * special case, described below, idling may cause problems to + * weight-raised queues. + * + * When the request pool is saturated (e.g., in the presence + * of write hogs), if the processes associated with + * non-weight-raised queues ask for requests at a lower rate, + * then processes associated with weight-raised queues have a + * higher probability to get a request from the pool + * immediately (or at least soon) when they need one. Thus + * they have a higher probability to actually get a fraction + * of the device throughput proportional to their high + * weight. This is especially true with NCQ-capable drives, + * which enqueue several requests in advance, and further + * reorder internally-queued requests. + * + * For this reason, we force to false the return value if + * there are weight-raised busy queues. In this case, and if + * bfqq is not weight-raised, this guarantees that the device + * is not idled for bfqq (if, instead, bfqq is weight-raised, + * then idling will be guaranteed by another variable, see + * below). Combined with the timestamping rules of BFQ (see + * [1] for details), this behavior causes bfqq, and hence any + * sync non-weight-raised queue, to get a lower number of + * requests served, and thus to ask for a lower number of + * requests from the request pool, before the busy + * weight-raised queues get served again. This often mitigates + * starvation problems in the presence of heavy write + * workloads and NCQ, thereby guaranteeing a higher + * application and system responsiveness in these hostile + * scenarios. + */ + return idling_boosts_thr && + bfqd->wr_busy_queues == 0; +} + +/* + * There is 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, entails loss of control on the + * actual request service order. In particular, the critical + * 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 + * determine also the actual throughput distribution among + * these processes. But the drive typically has no notion or + * concern about per-process throughput distribution, and + * makes its decisions only on a per-request basis. Therefore, + * 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) the I/O of each process has the same properties, in + * terms of locality (sequential or random), direction + * (reads or writes), request sizes, greediness + * (from I/O-bound to sporadic), and so on. + * In fact, in such a scenario, the drive tends 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). + * The problem is that idling may significantly reduce + * throughput with certain combinations of types of I/O and + * devices. An important example is sync random I/O, on flash + * storage with command queueing. So, unless bfqq falls in the + * above cases where idling also boosts throughput, it would + * be important to check conditions (i) and (ii) accurately, + * so as to avoid idling when not strictly needed for service + * guarantees. + * + * Unfortunately, it is extremely difficult to thoroughly + * check condition (ii). And, in case there are active groups, + * it becomes very difficult to check condition (i) too. In + * fact, if there are active groups, then, for condition (i) + * to become false, it is enough that an active group contains + * more active processes or sub-groups than some other active + * group. More precisely, for condition (i) to hold because of + * such a group, it is not even necessary that the group is + * (still) active: it is sufficient that, even if the group + * has become inactive, some of its descendant processes still + * have some request already dispatched but still waiting for + * completion. In fact, requests have still to be guaranteed + * their share of the throughput even after being + * dispatched. In this respect, it is easy to show that, if a + * group frequently becomes inactive while still having + * in-flight requests, and if, when this happens, the group is + * not considered in the calculation of whether the scenario + * is asymmetric, then the group may fail to be guaranteed its + * fair share of the throughput (basically because idling may + * not be performed for the descendant processes of the group, + * but it had to be). We address this issue with the + * following bi-modal behavior, implemented in the function + * bfq_symmetric_scenario(). + * + * If there are groups with requests waiting for completion + * (as commented above, some of these groups may even be + * already inactive), then the scenario is tagged as + * asymmetric, conservatively, without checking any of the + * conditions (i) and (ii). So the device is idled for bfqq. + * This behavior matches also the fact that groups are created + * exactly if controlling I/O is a primary concern (to + * preserve bandwidth and latency guarantees). + * + * On the opposite end, if there are no groups with requests + * waiting for completion, then only condition (i) is actually + * controlled, i.e., provided that condition (i) holds, idling + * is not performed, regardless of whether condition (ii) + * holds. In other words, only if condition (i) does not hold, + * then idling is allowed, and the device tends to be + * prevented from queueing many requests, possibly of several + * processes. Since there are no groups with requests waiting + * for completion, then, to control condition (i) it is enough + * to check just whether all the queues with requests waiting + * for completion also have the same weight. + * + * Not checking condition (ii) evidently exposes bfqq to the + * risk of getting less throughput than its fair share. + * However, for queues with the same weight, a further + * mechanism, preemption, mitigates or even eliminates this + * problem. And it does so without consequences on overall + * throughput. This mechanism and its benefits are explained + * in the next three 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. + * + * 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. + * + * The motivation for using preemption instead of idling (for + * queues with the same weight) is that, by not idling, + * service guarantees are preserved (completely or at least in + * part) without minimally sacrificing throughput. And, if + * there is no active group, then the primary expectation for + * this device is probably a high throughput. + * + * We are now left only with explaining the additional + * compound condition that is checked below for deciding + * whether the scenario is asymmetric. To explain this + * compound condition, we need to add that the function + * bfq_symmetric_scenario checks the weights of only + * non-weight-raised queues, for efficiency reasons (see + * comments on bfq_weights_tree_add()). Then the fact that + * bfqq is weight-raised is checked explicitly here. More + * precisely, the compound condition below takes into account + * also the fact that, even if bfqq is being weight-raised, + * the scenario is still symmetric if all queues with requests + * waiting for completion happen to be + * weight-raised. Actually, we should be even more precise + * here, and differentiate between interactive weight raising + * and soft real-time weight raising. + * + * 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 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. + */ +static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + bool asymmetric_scenario = (bfqq->wr_coeff > 1 && + bfqd->wr_busy_queues < + bfq_tot_busy_queues(bfqd)) || + !bfq_symmetric_scenario(bfqd); + + bfq_log_bfqq(bfqd, bfqq, + "wr_coeff %d wr_busy %d busy %d asymmetric %d", + bfqq->wr_coeff, + bfqd->wr_busy_queues, + bfq_tot_busy_queues(bfqd), + asymmetric_scenario); + + return asymmetric_scenario; +} + +/* + * For a queue that becomes empty, device idling is allowed only if + * this function returns true for that queue. As a consequence, since + * device idling plays a critical role for both throughput boosting + * and service guarantees, the return value of this function plays a + * critical role as well. + * + * In a nutshell, this function returns true only if idling is + * beneficial for throughput or, even if detrimental for throughput, + * idling is however necessary to preserve service guarantees (low + * latency, desired throughput distribution, ...). In particular, on + * NCQ-capable devices, this function tries to return false, so as to + * help keep the drives' internal queues full, whenever this helps the + * device boost the throughput without causing any service-guarantee + * issue. + * + * Most of the issues taken into account to get the return value of + * this function are not trivial. We discuss these issues in the two + * functions providing the main pieces of information needed by this + * function. + */ +static bool bfq_better_to_idle(struct bfq_queue *bfqq) +{ + struct bfq_data *bfqd = bfqq->bfqd; + bool idling_boosts_thr_with_no_issue, idling_needed_for_service_guar; + + if (unlikely(bfqd->strict_guarantees)) + return true; + + /* + * Idling is performed only if slice_idle > 0. In addition, we + * do not idle if + * (a) bfqq is async + * (b) bfqq is in the idle io prio class: in this case we do + * not idle because we want to minimize the bandwidth that + * queues in this class can steal to higher-priority queues + */ + if (bfqd->bfq_slice_idle == 0 || !bfq_bfqq_sync(bfqq) || + bfq_class_idle(bfqq)) + return false; + + idling_boosts_thr_with_no_issue = + idling_boosts_thr_without_issues(bfqd, bfqq); + + idling_needed_for_service_guar = + idling_needed_for_service_guarantees(bfqd, bfqq); + + /* + * We have now the two components we need to compute the + * return value of the function, which is true only if idling + * either boosts the throughput (without issues), or is + * necessary to preserve service guarantees. + */ + bfq_log_bfqq(bfqd, bfqq, + "wr_busy %d boosts %d IO-bound %d guar %d", + bfqd->wr_busy_queues, + idling_boosts_thr_with_no_issue, + bfq_bfqq_IO_bound(bfqq), + idling_needed_for_service_guar); + + return idling_boosts_thr_with_no_issue || + idling_needed_for_service_guar; +} + +/* + * If the in-service queue is empty but the function bfq_better_to_idle + * returns true, then: + * 1) the queue must remain in service and cannot be expired, and + * 2) the device must be idled to wait for the possible arrival of a new + * request for the queue. + * See the comments on the function bfq_better_to_idle for the reasons + * why performing device idling is the best choice to boost the throughput + * and preserve service guarantees when bfq_better_to_idle itself + * returns true. + */ +static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq) +{ + return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_better_to_idle(bfqq); +} + +static struct bfq_queue *bfq_choose_bfqq_for_injection(struct bfq_data *bfqd) +{ + struct bfq_queue *bfqq; + + /* + * A linear search; but, with a high probability, very few + * steps are needed to find a candidate queue, i.e., a queue + * with enough budget left for its next request. In fact: + * - BFQ dynamically updates the budget of every queue so as + * to accomodate the expected backlog of the queue; + * - if a queue gets all its requests dispatched as injected + * service, then the queue is removed from the active list + * (and re-added only if it gets new requests, but with + * enough budget for its new backlog). + */ + list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) + if (!RB_EMPTY_ROOT(&bfqq->sort_list) && + bfq_serv_to_charge(bfqq->next_rq, bfqq) <= + bfq_bfqq_budget_left(bfqq)) { + bfq_log_bfqq(bfqd, bfqq, "returned this queue"); + return bfqq; + } + + bfq_log(bfqd, "no queue found"); + return NULL; +} + +/* + * Select a queue for service. If we have a current queue in service, + * check whether to continue servicing it, or retrieve and set a new one. + */ +static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) +{ + struct bfq_queue *bfqq; + struct request *next_rq; + enum bfqq_expiration reason = BFQ_BFQQ_BUDGET_TIMEOUT; + + bfqq = bfqd->in_service_queue; + if (!bfqq) + goto new_queue; + + bfq_log_bfqq(bfqd, bfqq, "already in-service queue"); + + /* + * Do not expire bfqq for budget timeout if bfqq may be about + * to enjoy device idling. The reason why, in this case, we + * prevent bfqq from expiring is the same as in the comments + * on the case where bfq_bfqq_must_idle() returns true, in + * bfq_completed_request(). + */ + if (bfq_may_expire_for_budg_timeout(bfqq) && + !bfq_bfqq_must_idle(bfqq)) + goto expire; + +check_queue: + /* + * This loop is rarely executed more than once. Even when it + * happens, it is much more convenient to re-execute this loop + * than to return NULL and trigger a new dispatch to get a + * request served. + */ + next_rq = bfqq->next_rq; + /* + * If bfqq has requests queued and it has enough budget left to + * serve them, keep the queue, otherwise expire it. + */ + if (next_rq) { + BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list)); + + if (bfq_serv_to_charge(next_rq, bfqq) > + bfq_bfqq_budget_left(bfqq)) { + /* + * Expire the queue for budget exhaustion, + * which makes sure that the next budget is + * enough to serve the next request, even if + * it comes from the fifo expired path. + */ + reason = BFQ_BFQQ_BUDGET_EXHAUSTED; + goto expire; + } else { + /* + * The idle timer may be pending because we may + * not disable disk idling even when a new request + * arrives. + */ + if (bfq_bfqq_wait_request(bfqq)) { + BUG_ON(!hrtimer_active(&bfqd->idle_slice_timer)); + /* + * If we get here: 1) at least a new request + * has arrived but we have not disabled the + * timer because the request was too small, + * 2) then the block layer has unplugged + * the device, causing the dispatch to be + * invoked. + * + * Since the device is unplugged, now the + * requests are probably large enough to + * provide a reasonable throughput. + * So we disable idling. + */ + bfq_clear_bfqq_wait_request(bfqq); + hrtimer_try_to_cancel(&bfqd->idle_slice_timer); + bfqg_stats_update_idle_time(bfqq_group(bfqq)); + } + goto keep_queue; + } + } + + /* + * No requests pending. However, if the in-service queue is idling + * for a new request, or has requests waiting for a completion and + * may idle after their completion, then keep it anyway. + * + * Yet, to boost throughput, inject service from other queues if + * possible. + */ + if (hrtimer_active(&bfqd->idle_slice_timer) || + (bfqq->dispatched != 0 && bfq_better_to_idle(bfqq))) { + if (bfq_bfqq_injectable(bfqq) && + bfqq->injected_service * bfqq->inject_coeff < + bfqq->entity.service * 10) { + bfq_log_bfqq(bfqd, bfqq, "looking for queue for injection"); + bfqq = bfq_choose_bfqq_for_injection(bfqd); + } else { + if (BFQQ_SEEKY(bfqq)) + bfq_log_bfqq(bfqd, bfqq, + "injection saturated %d * %d >= %d * 10", + bfqq->injected_service, bfqq->inject_coeff, + bfqq->entity.service); + bfqq = NULL; + } + goto keep_queue; + } + + reason = BFQ_BFQQ_NO_MORE_REQUESTS; +expire: + bfq_bfqq_expire(bfqd, bfqq, false, reason); +new_queue: + bfqq = bfq_set_in_service_queue(bfqd); + if (bfqq) { + bfq_log_bfqq(bfqd, bfqq, "checking new queue"); + goto check_queue; + } +keep_queue: + if (bfqq) + bfq_log_bfqq(bfqd, bfqq, "returned this queue"); + else + bfq_log(bfqd, "no queue returned"); + + return bfqq; +} + +static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq) +{ + struct bfq_entity *entity = &bfqq->entity; + + if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */ + BUG_ON(bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time && + time_is_after_jiffies(bfqq->last_wr_start_finish)); + + bfq_log_bfqq(bfqd, bfqq, + "raising period dur %u/%u msec, old coeff %u, w %d(%d)", + jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish), + jiffies_to_msecs(bfqq->wr_cur_max_time), + bfqq->wr_coeff, + bfqq->entity.weight, bfqq->entity.orig_weight); + + BUG_ON(bfqq != bfqd->in_service_queue && entity->weight != + entity->orig_weight * bfqq->wr_coeff); + if (entity->prio_changed) + bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change"); + + /* + * 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 (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_bfqq_end_wr(bfqq); + else { + switch_back_to_interactive_wr(bfqq, bfqd); + BUG_ON(time_is_after_jiffies( + bfqq->last_wr_start_finish)); + bfqq->entity.prio_changed = 1; + bfq_log_bfqq(bfqd, bfqq, + "back to interactive wr"); + } + } + if (bfqq->wr_coeff > 1 && + bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time && + bfqq->service_from_wr > max_service_from_wr) { + /* see comments on max_service_from_wr */ + bfq_bfqq_end_wr(bfqq); + bfq_log_bfqq(bfqd, bfqq, + "too much service"); + } + } + /* + * To improve latency (for this or other queues), immediately + * update weight both if it must be raised and if it must be + * lowered. Since, entity may be on some active tree here, and + * might have a pending change of its ioprio class, invoke + * next function with the last parameter unset (see the + * comments on the function). + */ + if ((entity->weight > entity->orig_weight) != (bfqq->wr_coeff > 1)) + __bfq_entity_update_weight_prio(bfq_entity_service_tree(entity), + entity, false); +} + +/* + * Dispatch one request from bfqq, moving it to the request queue + * dispatch list. + */ +static int bfq_dispatch_request(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + int dispatched = 0; + struct request *rq = bfqq->next_rq; + unsigned long service_to_charge; + + BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list)); + BUG_ON(!rq); + service_to_charge = bfq_serv_to_charge(rq, bfqq); + + BUG_ON(service_to_charge > bfq_bfqq_budget_left(bfqq)); + + BUG_ON(bfqq->entity.budget < bfqq->entity.service); + + bfq_bfqq_served(bfqq, service_to_charge); + + BUG_ON(bfqq->entity.budget < bfqq->entity.service); + + bfq_dispatch_insert(bfqd->queue, rq); + + bfq_log_bfqq(bfqd, bfqq, + "dispatched %u sec req (%llu), budg left %d, new disp_nr %d", + blk_rq_sectors(rq), + (unsigned long long) blk_rq_pos(rq), + bfq_bfqq_budget_left(bfqq), + bfqq->dispatched); + + dispatched++; + + if (bfqq != bfqd->in_service_queue) { + if (likely(bfqd->in_service_queue)) { + bfqd->in_service_queue->injected_service += + bfq_serv_to_charge(rq, bfqq); + bfq_log_bfqq(bfqd, bfqd->in_service_queue, + "injected_service increased to %d", + bfqd->in_service_queue->injected_service); + } + return dispatched; + } + + /* + * If weight raising has to terminate for bfqq, then next + * function causes an immediate update of bfqq's weight, + * without waiting for next activation. As a consequence, on + * expiration, bfqq will be timestamped as if has never been + * weight-raised during this service slot, even if it has + * received part or even most of the service as a + * weight-raised queue. This inflates bfqq's timestamps, which + * is beneficial, as bfqq is then more willing to leave the + * device immediately to possible other weight-raised queues. + */ + 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); + BUG_ON(!bfqd->in_service_bic); + } + + if (bfq_tot_busy_queues(bfqd) > 1 && bfq_class_idle(bfqq)) + goto expire; + + return dispatched; + +expire: + bfq_bfqq_expire(bfqd, bfqq, false, BFQ_BFQQ_BUDGET_EXHAUSTED); + return dispatched; +} + +static int __bfq_forced_dispatch_bfqq(struct bfq_queue *bfqq) +{ + int dispatched = 0; + + while (bfqq->next_rq) { + bfq_dispatch_insert(bfqq->bfqd->queue, bfqq->next_rq); + dispatched++; + } + + BUG_ON(!list_empty(&bfqq->fifo)); + return dispatched; +} + +/* + * Drain our current requests. + * Used for barriers and when switching io schedulers on-the-fly. + */ +static int bfq_forced_dispatch(struct bfq_data *bfqd) +{ + struct bfq_queue *bfqq, *n; + struct bfq_service_tree *st; + int dispatched = 0; + + bfqq = bfqd->in_service_queue; + if (bfqq) + __bfq_bfqq_expire(bfqd, bfqq); + + /* + * Loop through classes, and be careful to leave the scheduler + * in a consistent state, as feedback mechanisms and vtime + * updates cannot be disabled during the process. + */ + list_for_each_entry_safe(bfqq, n, &bfqd->active_list, bfqq_list) { + st = bfq_entity_service_tree(&bfqq->entity); + + dispatched += __bfq_forced_dispatch_bfqq(bfqq); + + bfqq->max_budget = bfq_max_budget(bfqd); + bfq_forget_idle(st); + } + + BUG_ON(bfq_tot_busy_queues(bfqd) != 0); + + return dispatched; +} + +static int bfq_dispatch_requests(struct request_queue *q, int force) +{ + struct bfq_data *bfqd = q->elevator->elevator_data; + struct bfq_queue *bfqq; + + bfq_log(bfqd, "%d busy queues", bfq_tot_busy_queues(bfqd)); + + if (bfq_tot_busy_queues(bfqd) == 0) + return 0; + + if (unlikely(force)) + return bfq_forced_dispatch(bfqd); + + /* + * Force device to serve one request at a time if + * strict_guarantees is true. Forcing this service scheme is + * currently the ONLY way to guarantee that the request + * service order enforced by the scheduler is respected by a + * queueing device. Otherwise the device is free even to make + * some unlucky request wait for as long as the device + * wishes. + * + * Of course, serving one request at at time may cause loss of + * throughput. + */ + if (bfqd->strict_guarantees && bfqd->rq_in_driver > 0) + return 0; + + bfqq = bfq_select_queue(bfqd); + if (!bfqq) + return 0; + + BUG_ON(bfqq == bfqd->in_service_queue && + bfqq->entity.budget < bfqq->entity.service); + + BUG_ON(bfqq == bfqd->in_service_queue && + bfq_bfqq_wait_request(bfqq)); + + if (!bfq_dispatch_request(bfqd, bfqq)) + return 0; + + bfq_log_bfqq(bfqd, bfqq, "%s request", + bfq_bfqq_sync(bfqq) ? "sync" : "async"); + + BUG_ON(bfqq->next_rq == NULL && + bfqq->entity.budget < bfqq->entity.service); + return 1; +} + +/* + * Task holds one reference to the queue, dropped when task exits. Each rq + * in-flight on this queue also holds a reference, dropped when rq is freed. + * + * Queue 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) +{ +#ifdef BFQ_GROUP_IOSCHED_ENABLED + struct bfq_group *bfqg = bfqq_group(bfqq); +#endif + + BUG_ON(bfqq->ref <= 0); + + bfq_log_bfqq(bfqq->bfqd, bfqq, "%p %d", bfqq, bfqq->ref); + bfqq->ref--; + if (bfqq->ref) + return; + + BUG_ON(rb_first(&bfqq->sort_list)); + BUG_ON(bfqq->allocated[READ] + bfqq->allocated[WRITE] != 0); + BUG_ON(bfqq->entity.tree); + BUG_ON(bfq_bfqq_busy(bfqq)); + + if (!hlist_unhashed(&bfqq->burst_list_node)) { + hlist_del_init(&bfqq->burst_list_node); + /* + * Decrement also burst size after the removal, if the + * process associated with bfqq is exiting, and thus + * does not contribute to the burst any longer. This + * decrement helps filter out false positives of large + * bursts, when some short-lived process (often due to + * the execution of commands by some service) happens + * to start and exit while a complex application is + * starting, and thus spawning several processes that + * do I/O (and that *must not* be treated as a large + * burst, see comments on bfq_handle_burst). + * + * In particular, the decrement is performed only if: + * 1) bfqq is not a merged queue, because, if it is, + * then this free of bfqq is not triggered by the exit + * of the process bfqq is associated with, but exactly + * by the fact that bfqq has just been merged. + * 2) burst_size is greater than 0, to handle + * unbalanced decrements. Unbalanced decrements may + * happen in te following case: bfqq is inserted into + * the current burst list--without incrementing + * bust_size--because of a split, but the current + * burst list is not the burst list bfqq belonged to + * (see comments on the case of a split in + * bfq_set_request). + */ + if (bfqq->bic && bfqq->bfqd->burst_size > 0) + bfqq->bfqd->burst_size--; + } + + bfq_log_bfqq(bfqq->bfqd, bfqq, "%p freed", bfqq); + + kmem_cache_free(bfq_pool, bfqq); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + bfqg_put(bfqg); +#endif +} + +static void bfq_put_cooperator(struct bfq_queue *bfqq) +{ + struct bfq_queue *__bfqq, *next; + + /* + * If this queue was scheduled to merge with another queue, be + * sure to drop the reference taken on that queue (and others in + * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs. + */ + __bfqq = bfqq->new_bfqq; + while (__bfqq) { + if (__bfqq == bfqq) + break; + next = __bfqq->new_bfqq; + bfq_put_queue(__bfqq); + __bfqq = next; + } +} + +static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq) +{ + if (bfqq == bfqd->in_service_queue) { + __bfq_bfqq_expire(bfqd, bfqq); + bfq_schedule_dispatch(bfqd); + } + + bfq_log_bfqq(bfqd, bfqq, "%p, %d", bfqq, bfqq->ref); + + bfq_put_cooperator(bfqq); + + bfq_put_queue(bfqq); /* release process reference */ +} + +static void bfq_init_icq(struct io_cq *icq) +{ + icq_to_bic(icq)->ttime.last_end_request = ktime_get_ns() - (1ULL<<32); +} + +static void bfq_exit_icq(struct io_cq *icq) +{ + struct bfq_io_cq *bic = icq_to_bic(icq); + struct bfq_data *bfqd = bic_to_bfqd(bic); + + if (bic_to_bfqq(bic, false)) { + bfq_exit_bfqq(bfqd, bic_to_bfqq(bic, false)); + bic_set_bfqq(bic, NULL, false); + } + + if (bic_to_bfqq(bic, true)) { + /* + * 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. + */ + if (bfq_bfqq_coop(bic_to_bfqq(bic, true))) + put_io_context(icq->ioc); + bfq_exit_bfqq(bfqd, bic_to_bfqq(bic, true)); + bic_set_bfqq(bic, NULL, true); + } +} + +/* + * Update the entity prio values; note that the new values will not + * be used until the next (re)activation. + */ +static void bfq_set_next_ioprio_data(struct bfq_queue *bfqq, + struct bfq_io_cq *bic) +{ + struct task_struct *tsk = current; + int ioprio_class; + + ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio); + switch (ioprio_class) { + default: + dev_err(bfqq->bfqd->queue->backing_dev_info->dev, + "bfq: bad prio class %d\n", ioprio_class); + case IOPRIO_CLASS_NONE: + /* + * No prio set, inherit CPU scheduling settings. + */ + bfqq->new_ioprio = task_nice_ioprio(tsk); + bfqq->new_ioprio_class = task_nice_ioclass(tsk); + break; + case IOPRIO_CLASS_RT: + bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio); + bfqq->new_ioprio_class = IOPRIO_CLASS_RT; + break; + case IOPRIO_CLASS_BE: + bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio); + bfqq->new_ioprio_class = IOPRIO_CLASS_BE; + break; + case IOPRIO_CLASS_IDLE: + bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE; + bfqq->new_ioprio = 7; + break; + } + + if (bfqq->new_ioprio >= IOPRIO_BE_NR) { + pr_crit("bfq_set_next_ioprio_data: new_ioprio %d\n", + bfqq->new_ioprio); + BUG(); + } + + bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio); + bfqq->entity.prio_changed = 1; + bfq_log_bfqq(bfqq->bfqd, bfqq, + "bic_class %d prio %d class %d", + ioprio_class, bfqq->new_ioprio, bfqq->new_ioprio_class); +} + +static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio) +{ + struct bfq_data *bfqd = bic_to_bfqd(bic); + struct bfq_queue *bfqq; + unsigned long uninitialized_var(flags); + int ioprio = bic->icq.ioc->ioprio; + + /* + * This condition may trigger on a newly created bic, be sure to + * drop the lock before returning. + */ + if (unlikely(!bfqd) || likely(bic->ioprio == ioprio)) + return; + + bic->ioprio = ioprio; + + bfqq = bic_to_bfqq(bic, false); + if (bfqq) { + /* release process reference on this queue */ + bfq_put_queue(bfqq); + bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic); + bic_set_bfqq(bic, bfqq, false); + bfq_log_bfqq(bfqd, bfqq, + "bfqq %p %d", + bfqq, bfqq->ref); + } + + bfqq = bic_to_bfqq(bic, true); + if (bfqq) + bfq_set_next_ioprio_data(bfqq, bic); +} + +static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, + struct bfq_io_cq *bic, pid_t pid, int is_sync) +{ + RB_CLEAR_NODE(&bfqq->entity.rb_node); + INIT_LIST_HEAD(&bfqq->fifo); + INIT_HLIST_NODE(&bfqq->burst_list_node); + BUG_ON(!hlist_unhashed(&bfqq->burst_list_node)); + + bfqq->ref = 0; + bfqq->bfqd = bfqd; + + if (bic) + bfq_set_next_ioprio_data(bfqq, bic); + + if (is_sync) { + /* + * No need to mark as has_short_ttime if in + * idle_class, because no device idling is performed + * for queues in idle class + */ + if (!bfq_class_idle(bfqq)) + /* tentatively mark as has_short_ttime */ + bfq_mark_bfqq_has_short_ttime(bfqq); + bfq_mark_bfqq_sync(bfqq); + bfq_mark_bfqq_just_created(bfqq); + /* + * Aggressively inject a lot of service: up to 90%. + * This coefficient remains constant during bfqq life, + * but this behavior might be changed, after enough + * testing and tuning. + */ + bfqq->inject_coeff = 1; + } else + bfq_clear_bfqq_sync(bfqq); + bfq_mark_bfqq_IO_bound(bfqq); + + /* Tentative initial value to trade off between thr and lat */ + bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3; + bfqq->pid = pid; + + bfqq->wr_coeff = 1; + bfqq->last_wr_start_finish = jiffies; + bfqq->wr_start_at_switch_to_srt = bfq_smallest_from_now(); + bfqq->budget_timeout = bfq_smallest_from_now(); + bfqq->split_time = bfq_smallest_from_now(); + + /* + * To not forget the possibly high bandwidth consumed by a + * process/queue in the recent past, + * bfq_bfqq_softrt_next_start() returns a value at least equal + * to the current value of bfqq->soft_rt_next_start (see + * comments on bfq_bfqq_softrt_next_start). Set + * soft_rt_next_start to now, to mean that bfqq has consumed + * no bandwidth so far. + */ + bfqq->soft_rt_next_start = jiffies; + + /* first request is almost certainly seeky */ + bfqq->seek_history = 1; +} + +static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd, + struct bfq_group *bfqg, + int ioprio_class, int ioprio) +{ + switch (ioprio_class) { + case IOPRIO_CLASS_RT: + return &bfqg->async_bfqq[0][ioprio]; + case IOPRIO_CLASS_NONE: + ioprio = IOPRIO_NORM; + /* fall through */ + case IOPRIO_CLASS_BE: + return &bfqg->async_bfqq[1][ioprio]; + case IOPRIO_CLASS_IDLE: + return &bfqg->async_idle_bfqq; + default: + BUG(); + } +} + +static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, + struct bio *bio, bool is_sync, + struct bfq_io_cq *bic) +{ + const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio); + const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio); + struct bfq_queue **async_bfqq = NULL; + struct bfq_queue *bfqq; + struct bfq_group *bfqg; + + rcu_read_lock(); + + bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio)); + if (!bfqg) { + bfqq = &bfqd->oom_bfqq; + goto out; + } + + if (!is_sync) { + async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class, + ioprio); + bfqq = *async_bfqq; + if (bfqq) + goto out; + } + + bfqq = kmem_cache_alloc_node(bfq_pool, + GFP_NOWAIT | __GFP_ZERO | __GFP_NOWARN, + bfqd->queue->node); + + if (bfqq) { + bfq_init_bfqq(bfqd, bfqq, bic, current->pid, + is_sync); + bfq_init_entity(&bfqq->entity, bfqg); + bfq_log_bfqq(bfqd, bfqq, "allocated"); + } else { + bfqq = &bfqd->oom_bfqq; + bfq_log_bfqq(bfqd, bfqq, "using oom bfqq"); + goto out; + } + + /* + * Pin the queue now that it's allocated, scheduler exit will + * prune it. + */ + if (async_bfqq) { + bfqq->ref++; /* + * Extra group reference, w.r.t. sync + * queue. This extra reference is removed + * only if bfqq->bfqg disappears, to + * guarantee that this queue is not freed + * until its group goes away. + */ + bfq_log_bfqq(bfqd, bfqq, "bfqq not in async: %p, %d", + bfqq, bfqq->ref); + *async_bfqq = bfqq; + } + +out: + bfqq->ref++; /* get a process reference to this queue */ + bfq_log_bfqq(bfqd, bfqq, "at end: %p, %d", bfqq, bfqq->ref); + rcu_read_unlock(); + return bfqq; +} + +static void bfq_update_io_thinktime(struct bfq_data *bfqd, + struct bfq_io_cq *bic) +{ + struct bfq_ttime *ttime = &bic->ttime; + u64 elapsed = ktime_get_ns() - bic->ttime.last_end_request; + + elapsed = min_t(u64, elapsed, 2 * bfqd->bfq_slice_idle); + + ttime->ttime_samples = (7*bic->ttime.ttime_samples + 256) / 8; + ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed, 8); + ttime->ttime_mean = div64_ul(ttime->ttime_total + 128, + ttime->ttime_samples); +} + +static void +bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq, + struct request *rq) +{ + bfqq->seek_history <<= 1; + bfqq->seek_history |= BFQ_RQ_SEEKY(bfqd, bfqq->last_request_pos, rq); +} + +static void bfq_update_has_short_ttime(struct bfq_data *bfqd, + struct bfq_queue *bfqq, + struct bfq_io_cq *bic) +{ + bool has_short_ttime = true; + + /* + * No need to update has_short_ttime if bfqq is async or in + * idle io prio class, or if bfq_slice_idle is zero, because + * no device idling is performed for bfqq in this case. + */ + if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq) || + bfqd->bfq_slice_idle == 0) + return; + + /* Idle window just restored, statistics are meaningless. */ + if (time_is_after_eq_jiffies(bfqq->split_time + + bfqd->bfq_wr_min_idle_time)) + return; + + /* Think time is infinite if no process is linked to + * bfqq. Otherwise check average think time to + * decide whether to mark as has_short_ttime + */ + if (atomic_read(&bic->icq.ioc->active_ref) == 0 || + (bfq_sample_valid(bic->ttime.ttime_samples) && + bic->ttime.ttime_mean > bfqd->bfq_slice_idle)) + has_short_ttime = false; + + bfq_log_bfqq(bfqd, bfqq, "has_short_ttime %d", + has_short_ttime); + + if (has_short_ttime) + bfq_mark_bfqq_has_short_ttime(bfqq); + else + bfq_clear_bfqq_has_short_ttime(bfqq); +} + +/* + * Called when a new fs request (rq) is added to bfqq. Check if there's + * something we should do about it. + */ +static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq, + struct request *rq) +{ + struct bfq_io_cq *bic = RQ_BIC(rq); + + if (rq->cmd_flags & REQ_META) + bfqq->meta_pending++; + + bfq_update_io_thinktime(bfqd, bic); + bfq_update_has_short_ttime(bfqd, bfqq, bic); + bfq_update_io_seektime(bfqd, bfqq, rq); + + bfq_log_bfqq(bfqd, bfqq, + "has_short_ttime=%d (seeky %d)", + bfq_bfqq_has_short_ttime(bfqq), BFQQ_SEEKY(bfqq)); + + bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq); + + if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) { + bool small_req = bfqq->queued[rq_is_sync(rq)] == 1 && + blk_rq_sectors(rq) < 32; + bool budget_timeout = bfq_bfqq_budget_timeout(bfqq); + + /* + * There is just this request queued: if + * - the request is small, and + * - we are idling to boost throughput, and + * - the queue is not to be expired, + * then just exit. + * + * In this way, if the device is being idled to wait + * for a new request from the in-service queue, we + * avoid unplugging the device and committing the + * device to serve just a small request. In contrast + * we wait for the block layer to decide when to + * unplug the device: hopefully, new requests will be + * merged to this one quickly, then the device will be + * unplugged and larger requests will be dispatched. + */ + if (small_req && idling_boosts_thr_without_issues(bfqd, bfqq) && + !budget_timeout) + return; + + /* + * A large enough request arrived, or idling is being + * performed to preserve service guarantees, or + * finally the queue is to be expired: in all these + * cases disk idling is to be stopped, so clear + * wait_request flag and reset timer. + */ + bfq_clear_bfqq_wait_request(bfqq); + hrtimer_try_to_cancel(&bfqd->idle_slice_timer); + bfqg_stats_update_idle_time(bfqq_group(bfqq)); + + /* + * The queue is not empty, because a new request just + * arrived. Hence we can safely expire the queue, in + * case of budget timeout, without risking that the + * timestamps of the queue are not updated correctly. + * See [1] for more details. + */ + if (budget_timeout) + bfq_bfqq_expire(bfqd, bfqq, false, + BFQ_BFQQ_BUDGET_TIMEOUT); + + /* + * Let the request rip immediately, or let a new queue be + * selected if bfqq has just been expired. + */ + __blk_run_queue(bfqd->queue); + } +} + +static void bfq_insert_request(struct request_queue *q, struct request *rq) +{ + struct bfq_data *bfqd = q->elevator->elevator_data; + struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq; + + assert_spin_locked(bfqd->queue->queue_lock); + + /* + * An unplug may trigger a requeue of a request from the device + * driver: make sure we are in process context while trying to + * merge two bfq_queues. + */ + if (!in_interrupt()) { + new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true); + if (new_bfqq) { + if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq) + new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1); + /* + * Release the request's reference to the old bfqq + * and make sure one is taken to the shared queue. + */ + new_bfqq->allocated[rq_data_dir(rq)]++; + bfqq->allocated[rq_data_dir(rq)]--; + new_bfqq->ref++; + if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq) + bfq_merge_bfqqs(bfqd, RQ_BIC(rq), + bfqq, new_bfqq); + + bfq_clear_bfqq_just_created(bfqq); + /* + * rq is about to be enqueued into new_bfqq, + * release rq reference on bfqq + */ + bfq_put_queue(bfqq); + rq->elv.priv[1] = new_bfqq; + bfqq = new_bfqq; + } + } + + bfq_add_request(rq); + + rq->fifo_time = ktime_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)]; + list_add_tail(&rq->queuelist, &bfqq->fifo); + + bfq_rq_enqueued(bfqd, bfqq, rq); +} + +static void bfq_update_hw_tag(struct bfq_data *bfqd) +{ + struct bfq_queue *bfqq = bfqd->in_service_queue; + + bfqd->max_rq_in_driver = max_t(int, bfqd->max_rq_in_driver, + bfqd->rq_in_driver); + + if (bfqd->hw_tag == 1) + return; + + /* + * This sample is valid if the number of outstanding requests + * is large enough to allow a queueing behavior. Note that the + * sum is not exact, as it's not taking into account deactivated + * requests. + */ + if (bfqd->rq_in_driver + bfqd->queued <= BFQ_HW_QUEUE_THRESHOLD) + return; + + /* + * If active queue hasn't enough requests and can idle, bfq might not + * dispatch sufficient requests to hardware. Don't zero hw_tag in this + * case + */ + if (bfqq && bfq_bfqq_has_short_ttime(bfqq) && + bfqq->dispatched + bfqq->queued[0] + bfqq->queued[1] < + BFQ_HW_QUEUE_THRESHOLD && bfqd->rq_in_driver < BFQ_HW_QUEUE_THRESHOLD) + return; + + if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES) + return; + + bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD; + bfqd->max_rq_in_driver = 0; + bfqd->hw_tag_samples = 0; +} + +static void bfq_completed_request(struct request_queue *q, struct request *rq) +{ + struct bfq_queue *bfqq = RQ_BFQQ(rq); + struct bfq_data *bfqd = bfqq->bfqd; + u64 now_ns; + u32 delta_us; + + bfq_log_bfqq(bfqd, bfqq, "completed one req with %u sects left", + blk_rq_sectors(rq)); + + assert_spin_locked(bfqd->queue->queue_lock); + bfq_update_hw_tag(bfqd); + + BUG_ON(!bfqd->rq_in_driver); + BUG_ON(!bfqq->dispatched); + bfqd->rq_in_driver--; + bfqq->dispatched--; + bfqg_stats_update_completion(bfqq_group(bfqq), + rq->start_time_ns, + rq->io_start_time_ns, + rq->cmd_flags); + + if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) { + BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list)); + /* + * Set budget_timeout (which we overload to store the + * time at which the queue remains with no backlog and + * no outstanding request; used by the weight-raising + * mechanism). + */ + bfqq->budget_timeout = jiffies; + + bfq_weights_tree_remove(bfqd, bfqq); + } + + now_ns = ktime_get_ns(); + + RQ_BIC(rq)->ttime.last_end_request = now_ns; + + /* + * Using us instead of ns, to get a reasonable precision in + * computing rate in next check. + */ + delta_us = div_u64(now_ns - bfqd->last_completion, NSEC_PER_USEC); + + bfq_log(bfqd, "delta %uus/%luus max_size %u rate %llu/%llu", + delta_us, BFQ_MIN_TT/NSEC_PER_USEC, bfqd->last_rq_max_size, + delta_us > 0 ? + (USEC_PER_SEC* + (u64)((bfqd->last_rq_max_size<>BFQ_RATE_SHIFT : + (USEC_PER_SEC* + (u64)(bfqd->last_rq_max_size<>BFQ_RATE_SHIFT, + (USEC_PER_SEC*(u64)(1UL<<(BFQ_RATE_SHIFT-10)))>>BFQ_RATE_SHIFT); + + /* + * If the request took rather long to complete, and, according + * to the maximum request size recorded, this completion latency + * implies that the request was certainly served at a very low + * rate (less than 1M sectors/sec), then the whole observation + * interval that lasts up to this time instant cannot be a + * valid time interval for computing a new peak rate. Invoke + * bfq_update_rate_reset to have the following three steps + * taken: + * - close the observation interval at the last (previous) + * request dispatch or completion + * - compute rate, if possible, for that observation interval + * - reset to zero samples, which will trigger a proper + * re-initialization of the observation interval on next + * dispatch + */ + if (delta_us > BFQ_MIN_TT/NSEC_PER_USEC && + (bfqd->last_rq_max_size<last_completion = now_ns; + + /* + * If we are waiting to discover whether the request pattern + * of the task associated with the queue is actually + * isochronous, and both requisites for this condition to hold + * are now satisfied, then compute soft_rt_next_start (see the + * comments on the function bfq_bfqq_softrt_next_start()). We + * do not compute soft_rt_next_start if bfqq is in interactive + * weight raising (see the comments in bfq_bfqq_expire() for + * an explanation). We schedule this delayed update when bfqq + * expires, if it still has in-flight requests. + */ + if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 && + RB_EMPTY_ROOT(&bfqq->sort_list) && + bfqq->wr_coeff != bfqd->bfq_wr_coeff) + bfqq->soft_rt_next_start = + bfq_bfqq_softrt_next_start(bfqd, bfqq); + + /* + * If this is the in-service queue, check if it needs to be expired, + * or if we want to idle in case it has no pending requests. + */ + if (bfqd->in_service_queue == bfqq) { + if (bfq_bfqq_must_idle(bfqq)) { + if (bfqq->dispatched == 0) + bfq_arm_slice_timer(bfqd); + /* + * If we get here, we do not expire bfqq, even + * if bfqq was in budget timeout or had no + * more requests (as controlled in the next + * conditional instructions). The reason for + * not expiring bfqq is as follows. + * + * Here bfqq->dispatched > 0 holds, but + * bfq_bfqq_must_idle() returned true. This + * implies that, even if no request arrives + * for bfqq before bfqq->dispatched reaches 0, + * bfqq will, however, not be expired on the + * completion event that causes bfqq->dispatch + * to reach zero. In contrast, on this event, + * bfqq will start enjoying device idling + * (I/O-dispatch plugging). + * + * But, if we expired bfqq here, bfqq would + * not have the chance to enjoy device idling + * when bfqq->dispatched finally reaches + * zero. This would expose bfqq to violation + * of its reserved service guarantees. + */ + goto out; + } else if (bfq_may_expire_for_budg_timeout(bfqq)) + bfq_bfqq_expire(bfqd, bfqq, false, + BFQ_BFQQ_BUDGET_TIMEOUT); + else if (RB_EMPTY_ROOT(&bfqq->sort_list) && + (bfqq->dispatched == 0 || + !bfq_better_to_idle(bfqq))) + bfq_bfqq_expire(bfqd, bfqq, false, + BFQ_BFQQ_NO_MORE_REQUESTS); + } + + if (!bfqd->rq_in_driver) + bfq_schedule_dispatch(bfqd); + +out: + return; +} + +static int __bfq_may_queue(struct bfq_queue *bfqq) +{ + if (bfq_bfqq_wait_request(bfqq) && bfq_bfqq_must_alloc(bfqq)) { + bfq_clear_bfqq_must_alloc(bfqq); + return ELV_MQUEUE_MUST; + } + + return ELV_MQUEUE_MAY; +} + +static int bfq_may_queue(struct request_queue *q, unsigned int op) +{ + struct bfq_data *bfqd = q->elevator->elevator_data; + struct task_struct *tsk = current; + struct bfq_io_cq *bic; + struct bfq_queue *bfqq; + + /* + * Don't force setup of a queue from here, as a call to may_queue + * does not necessarily imply that a request actually will be + * queued. So just lookup a possibly existing queue, or return + * 'may queue' if that fails. + */ + bic = bfq_bic_lookup(bfqd, tsk->io_context); + if (!bic) + return ELV_MQUEUE_MAY; + + bfqq = bic_to_bfqq(bic, op_is_sync(op)); + if (bfqq) + return __bfq_may_queue(bfqq); + + return ELV_MQUEUE_MAY; +} + +/* + * Queue lock held here. + */ +static void bfq_put_request(struct request *rq) +{ + struct bfq_queue *bfqq = RQ_BFQQ(rq); + + if (bfqq) { + const int rw = rq_data_dir(rq); + + BUG_ON(!bfqq->allocated[rw]); + bfqq->allocated[rw]--; + + rq->elv.priv[0] = NULL; + rq->elv.priv[1] = NULL; + + bfq_log_bfqq(bfqq->bfqd, bfqq, "%p, %d", + bfqq, bfqq->ref); + bfq_put_queue(bfqq); + } +} + +/* + * Returns NULL if a new bfqq should be allocated, or the old bfqq if this + * was the last process referring to that bfqq. + */ +static struct bfq_queue * +bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq) +{ + bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue"); + + put_io_context(bic->icq.ioc); + + if (bfqq_process_refs(bfqq) == 1) { + bfqq->pid = current->pid; + bfq_clear_bfqq_coop(bfqq); + bfq_clear_bfqq_split_coop(bfqq); + return bfqq; + } + + bic_set_bfqq(bic, NULL, 1); + + bfq_put_cooperator(bfqq); + + bfq_put_queue(bfqq); + return NULL; +} + +/* + * Allocate bfq data structures associated with this request. + */ +static int bfq_set_request(struct request_queue *q, struct request *rq, + struct bio *bio, gfp_t gfp_mask) +{ + struct bfq_data *bfqd = q->elevator->elevator_data; + struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq); + const int rw = rq_data_dir(rq); + const int is_sync = rq_is_sync(rq); + struct bfq_queue *bfqq; + unsigned long flags; + bool bfqq_already_existing = false, split = false; + + spin_lock_irqsave(q->queue_lock, flags); + + if (!bic) + goto queue_fail; + + bfq_check_ioprio_change(bic, bio); + + bfq_bic_update_cgroup(bic, bio); + +new_queue: + bfqq = bic_to_bfqq(bic, is_sync); + if (!bfqq || bfqq == &bfqd->oom_bfqq) { + if (bfqq) + bfq_put_queue(bfqq); + bfqq = bfq_get_queue(bfqd, bio, is_sync, bic); + BUG_ON(!hlist_unhashed(&bfqq->burst_list_node)); + + bic_set_bfqq(bic, bfqq, is_sync); + if (split && is_sync) { + bfq_log_bfqq(bfqd, bfqq, + "was_in_list %d " + "was_in_large_burst %d " + "large burst in progress %d", + bic->was_in_burst_list, + bic->saved_in_large_burst, + bfqd->large_burst); + + if ((bic->was_in_burst_list && bfqd->large_burst) || + bic->saved_in_large_burst) { + bfq_log_bfqq(bfqd, bfqq, + "marking in " + "large burst"); + bfq_mark_bfqq_in_large_burst(bfqq); + } else { + bfq_log_bfqq(bfqd, bfqq, + "clearing in " + "large burst"); + bfq_clear_bfqq_in_large_burst(bfqq); + if (bic->was_in_burst_list) + /* + * If bfqq was in the current + * burst list before being + * merged, then we have to add + * it back. And we do not need + * to increase burst_size, as + * we did not decrement + * burst_size when we removed + * bfqq from the burst list as + * a consequence of a merge + * (see comments in + * bfq_put_queue). In this + * respect, it would be rather + * costly to know whether the + * current burst list is still + * the same burst list from + * which bfqq was removed on + * the merge. To avoid this + * cost, if bfqq was in a + * burst list, then we add + * bfqq to the current burst + * list without any further + * check. This can cause + * inappropriate insertions, + * but rarely enough to not + * harm the detection of large + * bursts significantly. + */ + hlist_add_head(&bfqq->burst_list_node, + &bfqd->burst_list); + } + bfqq->split_time = jiffies; + } + } else { + /* 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); + split = true; + if (!bfqq) + goto new_queue; + else + bfqq_already_existing = true; + } + } + + bfqq->allocated[rw]++; + bfqq->ref++; + bfq_log_bfqq(bfqd, bfqq, "bfqq %p, %d", bfqq, bfqq->ref); + + rq->elv.priv[0] = bic; + rq->elv.priv[1] = bfqq; + + /* + * If a bfq_queue has only one process reference, it is owned + * by only one bfq_io_cq: we can set the bic field of the + * bfq_queue to the address of that structure. Also, if the + * queue has just been split, mark a flag so that the + * information is available to the other scheduler hooks. + */ + if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) { + bfqq->bic = bic; + if (split) { + /* + * If the queue has just been split from a shared + * queue, restore the idle window and the possible + * weight raising period. + */ + bfq_bfqq_resume_state(bfqq, bfqd, bic, + bfqq_already_existing); + } + } + + if (unlikely(bfq_bfqq_just_created(bfqq))) + bfq_handle_burst(bfqd, bfqq); + + spin_unlock_irqrestore(q->queue_lock, flags); + + return 0; + +queue_fail: + bfq_schedule_dispatch(bfqd); + spin_unlock_irqrestore(q->queue_lock, flags); + + return 1; +} + +static void bfq_kick_queue(struct work_struct *work) +{ + struct bfq_data *bfqd = + container_of(work, struct bfq_data, unplug_work); + struct request_queue *q = bfqd->queue; + + spin_lock_irq(q->queue_lock); + __blk_run_queue(q); + spin_unlock_irq(q->queue_lock); +} + +/* + * Handler of the expiration of the timer running if the in-service queue + * is idling inside its time slice. + */ +static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer) +{ + struct bfq_data *bfqd = container_of(timer, struct bfq_data, + idle_slice_timer); + struct bfq_queue *bfqq; + unsigned long flags; + enum bfqq_expiration reason; + + spin_lock_irqsave(bfqd->queue->queue_lock, flags); + + bfqq = bfqd->in_service_queue; + /* + * Theoretical race here: the in-service queue can be NULL or + * different from the queue that was idling if the timer handler + * spins on the queue_lock and a new request arrives for the + * current queue and there is a full dispatch cycle that changes + * the in-service queue. This can hardly happen, but in the worst + * case we just expire a queue too early. + */ + if (bfqq) { + bfq_log_bfqq(bfqd, bfqq, "expired"); + bfq_clear_bfqq_wait_request(bfqq); + + if (bfq_bfqq_budget_timeout(bfqq)) + /* + * Also here the queue can be safely expired + * for budget timeout without wasting + * guarantees + */ + reason = BFQ_BFQQ_BUDGET_TIMEOUT; + else if (bfqq->queued[0] == 0 && bfqq->queued[1] == 0) + /* + * The queue may not be empty upon timer expiration, + * because we may not disable the timer when the + * first request of the in-service queue arrives + * during disk idling. + */ + reason = BFQ_BFQQ_TOO_IDLE; + else + goto schedule_dispatch; + + bfq_bfqq_expire(bfqd, bfqq, true, reason); + } + +schedule_dispatch: + bfq_schedule_dispatch(bfqd); + + spin_unlock_irqrestore(bfqd->queue->queue_lock, flags); + return HRTIMER_NORESTART; +} + +static void bfq_shutdown_timer_wq(struct bfq_data *bfqd) +{ + hrtimer_cancel(&bfqd->idle_slice_timer); + cancel_work_sync(&bfqd->unplug_work); +} + +static void __bfq_put_async_bfqq(struct bfq_data *bfqd, + struct bfq_queue **bfqq_ptr) +{ + struct bfq_group *root_group = bfqd->root_group; + struct bfq_queue *bfqq = *bfqq_ptr; + + bfq_log(bfqd, "%p", bfqq); + if (bfqq) { + bfq_bfqq_move(bfqd, bfqq, root_group); + bfq_log_bfqq(bfqd, bfqq, "putting %p, %d", + bfqq, bfqq->ref); + bfq_put_queue(bfqq); + *bfqq_ptr = NULL; + } +} + +/* + * Release all the bfqg references to its async queues. If we are + * deallocating the group these queues may still contain requests, so + * 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) +{ + int i, j; + + for (i = 0; i < 2; i++) + for (j = 0; j < IOPRIO_BE_NR; j++) + __bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]); + + __bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq); +} + +static void bfq_exit_queue(struct elevator_queue *e) +{ + struct bfq_data *bfqd = e->elevator_data; + struct request_queue *q = bfqd->queue; + struct bfq_queue *bfqq, *n; + + bfq_shutdown_timer_wq(bfqd); + + spin_lock_irq(q->queue_lock); + + BUG_ON(bfqd->in_service_queue); + list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list) + bfq_deactivate_bfqq(bfqd, bfqq, false, false); + + spin_unlock_irq(q->queue_lock); + + bfq_shutdown_timer_wq(bfqd); + + BUG_ON(hrtimer_active(&bfqd->idle_slice_timer)); + +#ifdef BFQ_GROUP_IOSCHED_ENABLED + /* release oom-queue reference to root group */ + bfqg_put(bfqd->root_group); + + blkcg_deactivate_policy(q, &blkcg_policy_bfq); +#else + bfq_put_async_queues(bfqd, bfqd->root_group); + kfree(bfqd->root_group); +#endif + + kfree(bfqd); +} + +static void bfq_init_root_group(struct bfq_group *root_group, + struct bfq_data *bfqd) +{ + int i; + +#ifdef BFQ_GROUP_IOSCHED_ENABLED + root_group->entity.parent = NULL; + root_group->my_entity = NULL; + root_group->bfqd = bfqd; +#endif + root_group->rq_pos_tree = RB_ROOT; + for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) + root_group->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT; + root_group->sched_data.bfq_class_idle_last_service = jiffies; +} + +static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) +{ + struct bfq_data *bfqd; + struct elevator_queue *eq; + + eq = elevator_alloc(q, e); + if (!eq) + return -ENOMEM; + + bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node); + if (!bfqd) { + kobject_put(&eq->kobj); + return -ENOMEM; + } + eq->elevator_data = bfqd; + + /* + * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues. + * Grab a permanent reference to it, so that the normal code flow + * will not attempt to free it. + */ + bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, NULL, 1, 0); + bfqd->oom_bfqq.ref++; + bfqd->oom_bfqq.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO; + 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 + * class won't be changed any more. + */ + bfqd->oom_bfqq.entity.prio_changed = 1; + + bfqd->queue = q; + + spin_lock_irq(q->queue_lock); + q->elevator = eq; + spin_unlock_irq(q->queue_lock); + + bfqd->root_group = bfq_create_group_hierarchy(bfqd, q->node); + if (!bfqd->root_group) + goto out_free; + bfq_init_root_group(bfqd->root_group, bfqd); + bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group); + + hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); + bfqd->idle_slice_timer.function = bfq_idle_slice_timer; + + bfqd->queue_weights_tree = RB_ROOT; + bfqd->num_groups_with_pending_reqs = 0; + + INIT_WORK(&bfqd->unplug_work, bfq_kick_queue); + + INIT_LIST_HEAD(&bfqd->active_list); + INIT_LIST_HEAD(&bfqd->idle_list); + INIT_HLIST_HEAD(&bfqd->burst_list); + + bfqd->hw_tag = -1; + + bfqd->bfq_max_budget = bfq_default_max_budget; + + bfqd->bfq_fifo_expire[0] = bfq_fifo_expire[0]; + bfqd->bfq_fifo_expire[1] = bfq_fifo_expire[1]; + bfqd->bfq_back_max = bfq_back_max; + bfqd->bfq_back_penalty = bfq_back_penalty; + bfqd->bfq_slice_idle = bfq_slice_idle; + bfqd->bfq_timeout = bfq_timeout; + + bfqd->bfq_requests_within_timer = 120; + + bfqd->bfq_large_burst_thresh = 8; + bfqd->bfq_burst_interval = msecs_to_jiffies(180); + + bfqd->low_latency = true; + + /* + * Trade-off between responsiveness and fairness. + */ + bfqd->bfq_wr_coeff = 30; + bfqd->bfq_wr_rt_max_time = msecs_to_jiffies(300); + bfqd->bfq_wr_max_time = 0; + bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000); + bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500); + bfqd->bfq_wr_max_softrt_rate = 7000; /* + * Approximate rate required + * to playback or record a + * high-definition compressed + * video. + */ + bfqd->wr_busy_queues = 0; + + /* + * Begin by assuming, optimistically, that the device peak + * rate is equal to 2/3 of the highest reference rate. + */ + bfqd->rate_dur_prod = ref_rate[blk_queue_nonrot(bfqd->queue)] * + ref_wr_duration[blk_queue_nonrot(bfqd->queue)]; + bfqd->peak_rate = ref_rate[blk_queue_nonrot(bfqd->queue)] * 2 / 3; + + return 0; + +out_free: + kfree(bfqd); + kobject_put(&eq->kobj); + return -ENOMEM; +} + +static void bfq_registered_queue(struct request_queue *q) +{ + wbt_disable_default(q); +} + +static void bfq_slab_kill(void) +{ + kmem_cache_destroy(bfq_pool); +} + +static int __init bfq_slab_setup(void) +{ + bfq_pool = KMEM_CACHE(bfq_queue, 0); + if (!bfq_pool) + return -ENOMEM; + return 0; +} + +static ssize_t bfq_var_show(unsigned int var, char *page) +{ + return sprintf(page, "%u\n", var); +} + +static ssize_t bfq_var_store(unsigned long *var, const char *page, + size_t count) +{ + unsigned long new_val; + int ret = kstrtoul(page, 10, &new_val); + + if (ret == 0) + *var = new_val; + + return count; +} + +static ssize_t bfq_wr_max_time_show(struct elevator_queue *e, char *page) +{ + struct bfq_data *bfqd = e->elevator_data; + + return sprintf(page, "%d\n", bfqd->bfq_wr_max_time > 0 ? + jiffies_to_msecs(bfqd->bfq_wr_max_time) : + jiffies_to_msecs(bfq_wr_duration(bfqd))); +} + +static ssize_t bfq_weights_show(struct elevator_queue *e, char *page) +{ + struct bfq_queue *bfqq; + struct bfq_data *bfqd = e->elevator_data; + ssize_t num_char = 0; + + num_char += sprintf(page + num_char, "Tot reqs queued %d\n\n", + bfqd->queued); + + spin_lock_irq(bfqd->queue->queue_lock); + + num_char += sprintf(page + num_char, "Active:\n"); + list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) { + num_char += sprintf(page + num_char, + "pid%d: weight %hu, nr_queued %d %d, ", + bfqq->pid, + bfqq->entity.weight, + bfqq->queued[0], + bfqq->queued[1]); + num_char += sprintf(page + num_char, + "dur %d/%u\n", + jiffies_to_msecs( + jiffies - + bfqq->last_wr_start_finish), + jiffies_to_msecs(bfqq->wr_cur_max_time)); + } + + num_char += sprintf(page + num_char, "Idle:\n"); + list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) { + num_char += sprintf(page + num_char, + "pid%d: weight %hu, dur %d/%u\n", + bfqq->pid, + bfqq->entity.weight, + jiffies_to_msecs(jiffies - + bfqq->last_wr_start_finish), + jiffies_to_msecs(bfqq->wr_cur_max_time)); + } + + spin_unlock_irq(bfqd->queue->queue_lock); + + return num_char; +} + +#define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \ +static ssize_t __FUNC(struct elevator_queue *e, char *page) \ +{ \ + struct bfq_data *bfqd = e->elevator_data; \ + u64 __data = __VAR; \ + if (__CONV == 1) \ + __data = jiffies_to_msecs(__data); \ + else if (__CONV == 2) \ + __data = div_u64(__data, NSEC_PER_MSEC); \ + return bfq_var_show(__data, (page)); \ +} +SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 2); +SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 2); +SHOW_FUNCTION(bfq_back_seek_max_show, bfqd->bfq_back_max, 0); +SHOW_FUNCTION(bfq_back_seek_penalty_show, bfqd->bfq_back_penalty, 0); +SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 2); +SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0); +SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout, 1); +SHOW_FUNCTION(bfq_strict_guarantees_show, bfqd->strict_guarantees, 0); +SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0); +SHOW_FUNCTION(bfq_wr_coeff_show, bfqd->bfq_wr_coeff, 0); +SHOW_FUNCTION(bfq_wr_rt_max_time_show, bfqd->bfq_wr_rt_max_time, 1); +SHOW_FUNCTION(bfq_wr_min_idle_time_show, bfqd->bfq_wr_min_idle_time, 1); +SHOW_FUNCTION(bfq_wr_min_inter_arr_async_show, bfqd->bfq_wr_min_inter_arr_async, + 1); +SHOW_FUNCTION(bfq_wr_max_softrt_rate_show, bfqd->bfq_wr_max_softrt_rate, 0); +#undef SHOW_FUNCTION + +#define USEC_SHOW_FUNCTION(__FUNC, __VAR) \ +static ssize_t __FUNC(struct elevator_queue *e, char *page) \ +{ \ + struct bfq_data *bfqd = e->elevator_data; \ + u64 __data = __VAR; \ + __data = div_u64(__data, NSEC_PER_USEC); \ + return bfq_var_show(__data, (page)); \ +} +USEC_SHOW_FUNCTION(bfq_slice_idle_us_show, bfqd->bfq_slice_idle); +#undef USEC_SHOW_FUNCTION + +#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ +static ssize_t \ +__FUNC(struct elevator_queue *e, const char *page, size_t count) \ +{ \ + struct bfq_data *bfqd = e->elevator_data; \ + unsigned long uninitialized_var(__data); \ + int ret = bfq_var_store(&__data, (page), count); \ + if (__data < (MIN)) \ + __data = (MIN); \ + else if (__data > (MAX)) \ + __data = (MAX); \ + if (__CONV == 1) \ + *(__PTR) = msecs_to_jiffies(__data); \ + else if (__CONV == 2) \ + *(__PTR) = (u64)__data * NSEC_PER_MSEC; \ + else \ + *(__PTR) = __data; \ + return ret; \ +} +STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1, + INT_MAX, 2); +STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1, + INT_MAX, 2); +STORE_FUNCTION(bfq_back_seek_max_store, &bfqd->bfq_back_max, 0, INT_MAX, 0); +STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1, + INT_MAX, 0); +STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 2); +STORE_FUNCTION(bfq_wr_coeff_store, &bfqd->bfq_wr_coeff, 1, INT_MAX, 0); +STORE_FUNCTION(bfq_wr_max_time_store, &bfqd->bfq_wr_max_time, 0, INT_MAX, 1); +STORE_FUNCTION(bfq_wr_rt_max_time_store, &bfqd->bfq_wr_rt_max_time, 0, INT_MAX, + 1); +STORE_FUNCTION(bfq_wr_min_idle_time_store, &bfqd->bfq_wr_min_idle_time, 0, + INT_MAX, 1); +STORE_FUNCTION(bfq_wr_min_inter_arr_async_store, + &bfqd->bfq_wr_min_inter_arr_async, 0, INT_MAX, 1); +STORE_FUNCTION(bfq_wr_max_softrt_rate_store, &bfqd->bfq_wr_max_softrt_rate, 0, + INT_MAX, 0); +#undef STORE_FUNCTION + +#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX) \ +static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)\ +{ \ + struct bfq_data *bfqd = e->elevator_data; \ + unsigned long uninitialized_var(__data); \ + int ret = bfq_var_store(&__data, (page), count); \ + if (__data < (MIN)) \ + __data = (MIN); \ + else if (__data > (MAX)) \ + __data = (MAX); \ + *(__PTR) = (u64)__data * NSEC_PER_USEC; \ + return ret; \ +} +USEC_STORE_FUNCTION(bfq_slice_idle_us_store, &bfqd->bfq_slice_idle, 0, + UINT_MAX); +#undef USEC_STORE_FUNCTION + +/* do nothing for the moment */ +static ssize_t bfq_weights_store(struct elevator_queue *e, + const char *page, size_t count) +{ + return count; +} + +static ssize_t bfq_max_budget_store(struct elevator_queue *e, + const char *page, size_t count) +{ + struct bfq_data *bfqd = e->elevator_data; + unsigned long uninitialized_var(__data); + int ret = bfq_var_store(&__data, (page), count); + + if (__data == 0) + bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd); + else { + if (__data > INT_MAX) + __data = INT_MAX; + bfqd->bfq_max_budget = __data; + } + + bfqd->bfq_user_max_budget = __data; + + return ret; +} + +/* + * Leaving this name to preserve name compatibility with cfq + * parameters, but this timeout is used for both sync and async. + */ +static ssize_t bfq_timeout_sync_store(struct elevator_queue *e, + const char *page, size_t count) +{ + struct bfq_data *bfqd = e->elevator_data; + unsigned long uninitialized_var(__data); + int ret = bfq_var_store(&__data, (page), count); + + if (__data < 1) + __data = 1; + else if (__data > INT_MAX) + __data = INT_MAX; + + bfqd->bfq_timeout = msecs_to_jiffies(__data); + if (bfqd->bfq_user_max_budget == 0) + bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd); + + return ret; +} + +static ssize_t bfq_strict_guarantees_store(struct elevator_queue *e, + const char *page, size_t count) +{ + struct bfq_data *bfqd = e->elevator_data; + unsigned long uninitialized_var(__data); + int ret = bfq_var_store(&__data, (page), count); + + if (__data > 1) + __data = 1; + if (!bfqd->strict_guarantees && __data == 1 + && bfqd->bfq_slice_idle < 8 * NSEC_PER_MSEC) + bfqd->bfq_slice_idle = 8 * NSEC_PER_MSEC; + + bfqd->strict_guarantees = __data; + + return ret; +} + +static ssize_t bfq_low_latency_store(struct elevator_queue *e, + const char *page, size_t count) +{ + struct bfq_data *bfqd = e->elevator_data; + unsigned long uninitialized_var(__data); + int ret = bfq_var_store(&__data, (page), count); + + if (__data > 1) + __data = 1; + if (__data == 0 && bfqd->low_latency != 0) + bfq_end_wr(bfqd); + bfqd->low_latency = __data; + + return ret; +} + +#define BFQ_ATTR(name) \ + __ATTR(name, S_IRUGO|S_IWUSR, bfq_##name##_show, bfq_##name##_store) + +static struct elv_fs_entry bfq_attrs[] = { + BFQ_ATTR(fifo_expire_sync), + BFQ_ATTR(fifo_expire_async), + BFQ_ATTR(back_seek_max), + BFQ_ATTR(back_seek_penalty), + BFQ_ATTR(slice_idle), + BFQ_ATTR(slice_idle_us), + BFQ_ATTR(max_budget), + BFQ_ATTR(timeout_sync), + BFQ_ATTR(strict_guarantees), + BFQ_ATTR(low_latency), + BFQ_ATTR(wr_coeff), + BFQ_ATTR(wr_max_time), + BFQ_ATTR(wr_rt_max_time), + BFQ_ATTR(wr_min_idle_time), + BFQ_ATTR(wr_min_inter_arr_async), + BFQ_ATTR(wr_max_softrt_rate), + BFQ_ATTR(weights), + __ATTR_NULL +}; + +static struct elevator_type iosched_bfq = { + .ops.sq = { + .elevator_merge_fn = bfq_merge, + .elevator_merged_fn = bfq_merged_request, + .elevator_merge_req_fn = bfq_merged_requests, +#ifdef BFQ_GROUP_IOSCHED_ENABLED + .elevator_bio_merged_fn = bfq_bio_merged, +#endif + .elevator_allow_bio_merge_fn = bfq_allow_bio_merge, + .elevator_allow_rq_merge_fn = bfq_allow_rq_merge, + .elevator_dispatch_fn = bfq_dispatch_requests, + .elevator_add_req_fn = bfq_insert_request, + .elevator_activate_req_fn = bfq_activate_request, + .elevator_deactivate_req_fn = bfq_deactivate_request, + .elevator_completed_req_fn = bfq_completed_request, + .elevator_former_req_fn = elv_rb_former_request, + .elevator_latter_req_fn = elv_rb_latter_request, + .elevator_init_icq_fn = bfq_init_icq, + .elevator_exit_icq_fn = bfq_exit_icq, + .elevator_set_req_fn = bfq_set_request, + .elevator_put_req_fn = bfq_put_request, + .elevator_may_queue_fn = bfq_may_queue, + .elevator_init_fn = bfq_init_queue, + .elevator_exit_fn = bfq_exit_queue, + .elevator_registered_fn = bfq_registered_queue, + }, + .icq_size = sizeof(struct bfq_io_cq), + .icq_align = __alignof__(struct bfq_io_cq), + .elevator_attrs = bfq_attrs, + .elevator_name = "bfq-sq", + .elevator_owner = THIS_MODULE, +}; + +#ifdef BFQ_GROUP_IOSCHED_ENABLED +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; + char msg[60] = "BFQ I/O-scheduler: v9"; + +#ifdef BFQ_GROUP_IOSCHED_ENABLED + ret = blkcg_policy_register(&blkcg_policy_bfq); + if (ret) + return ret; +#endif + + ret = -ENOMEM; + if (bfq_slab_setup()) + goto err_pol_unreg; + + /* + * Times to load large popular applications for the typical + * systems installed on the reference devices (see the + * comments before the definition of the next + * array). Actually, we use slightly lower values, as the + * estimated peak rate tends to be smaller than the actual + * peak rate. The reason for this last fact is that estimates + * are computed over much shorter time intervals than the long + * intervals typically used for benchmarking. Why? First, to + * adapt more quickly to variations. Second, because an I/O + * scheduler cannot rely on a peak-rate-evaluation workload to + * be run for a long time. + */ + ref_wr_duration[0] = msecs_to_jiffies(7000); /* actually 8 sec */ + ref_wr_duration[1] = msecs_to_jiffies(2500); /* actually 3 sec */ + + ret = elv_register(&iosched_bfq); + if (ret) + goto slab_kill; + +#ifdef BFQ_GROUP_IOSCHED_ENABLED + strcat(msg, " (with cgroups support)"); +#endif + pr_info("%s", msg); + + return 0; + +slab_kill: + bfq_slab_kill(); +err_pol_unreg: +#ifdef BFQ_GROUP_IOSCHED_ENABLED + blkcg_policy_unregister(&blkcg_policy_bfq); +#endif + return ret; +} + +static void __exit bfq_exit(void) +{ + elv_unregister(&iosched_bfq); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + blkcg_policy_unregister(&blkcg_policy_bfq); +#endif + bfq_slab_kill(); +} + +module_init(bfq_init); +module_exit(bfq_exit); + +MODULE_AUTHOR("Arianna Avanzini, Fabio Checconi, Paolo Valente"); +MODULE_LICENSE("GPL"); diff --git a/block/bfq.h b/block/bfq.h new file mode 100644 index 000000000000..0177fc7205d7 --- /dev/null +++ b/block/bfq.h @@ -0,0 +1,1074 @@ +/* + * BFQ v9: data structures and common functions prototypes. + * + * Based on ideas and code from CFQ: + * Copyright (C) 2003 Jens Axboe + * + * Copyright (C) 2008 Fabio Checconi + * Paolo Valente + * + * Copyright (C) 2015 Paolo Valente + * + * Copyright (C) 2017 Paolo Valente + */ + +#ifndef _BFQ_H +#define _BFQ_H + +#include +#include + +/* + * Define an alternative macro to compile cgroups support. This is one + * of the steps needed to let bfq-mq share the files bfq-sched.c and + * bfq-cgroup.c with bfq-sq. For bfq-mq, the macro + * BFQ_GROUP_IOSCHED_ENABLED will be defined as a function of whether + * the configuration option CONFIG_BFQ_MQ_GROUP_IOSCHED, and not + * CONFIG_BFQ_GROUP_IOSCHED, is defined. + */ +#ifdef CONFIG_BFQ_SQ_GROUP_IOSCHED +#define BFQ_GROUP_IOSCHED_ENABLED +#endif + +#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; + + struct bfq_entity *first_idle; /* idle entity with minimum F_i */ + struct bfq_entity *last_idle; /* idle entity with maximum F_i */ + + u64 vtime; /* scheduler virtual time */ + /* 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 in a hierarchical setup. + * + * 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+. + * + * The schedule is implemented by the service trees, plus the field + * @next_in_service, which points to the entity on the active trees + * that will be served next, if 1) no changes in the schedule occurs + * before the current in-service entity is expired, 2) the in-service + * queue becomes idle when it expires, and 3) if the entity pointed by + * in_service_entity is not a queue, then the in-service child entity + * of the entity pointed by in_service_entity becomes idle on + * expiration. This peculiar definition allows for the following + * optimization, not yet exploited: while a given entity is still in + * service, we already know which is the best candidate for next + * service among the other active entitities in the same parent + * entity. We can then quickly compare the timestamps of the + * in-service entity with those of such best candidate. + * + * All the fields are protected by the queue lock of the containing + * bfqd. + */ +struct bfq_sched_data { + struct bfq_entity *in_service_entity; /* entity in service */ + /* head-of-the-line entity in the scheduler (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 queues + * with a given weight. + */ +struct bfq_weight_counter { + unsigned int weight; /* weight of the queues this counter refers to */ + unsigned int num_active; /* nr of active queues with this weight */ + /* + * Weights tree member (see bfq_data's @queue_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 { + struct rb_node rb_node; /* service_tree member */ + + /* + * 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; + + u64 finish; /* B-WF2Q+ finish timestamp (aka F_i) */ + u64 start; /* B-WF2Q+ start timestamp (aka S_i) */ + + /* 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; + + unsigned int weight; /* weight of the queue */ + unsigned int new_weight; /* next weight if a change is in progress */ + + /* original weight, used to implement weight boosting */ + unsigned 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; + + /* flag, set if the entity is counted in groups_with_pending_reqs */ + bool in_groups_with_pending_reqs; +}; + +struct bfq_group; + +/** + * 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 sync and async requests currently allocated */ + int allocated[2]; + /* 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; + + /* pointer to the weight counter associated with this queue */ + struct bfq_weight_counter *weight_counter; + + /* 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; + + unsigned int flags; /* status flags.*/ + + /* node for active/idle bfqq list inside parent bfqd */ + struct list_head bfqq_list; + + /* 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; + /* + * Cumulative service received from the @bfq_queue since its + * last transition to weight-raised state. + */ + unsigned long service_from_wr; + /* + * 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 */ + + unsigned long first_IO_time; /* time of first I/O for this queue */ + + /* max service rate measured so far */ + u32 max_service_rate; + /* + * Ratio between the service received by bfqq while it is in + * service, and the cumulative service (of requests of other + * queues) that may be injected while bfqq is empty but still + * in service. To increase precision, the coefficient is + * measured in tenths of unit. Here are some example of (1) + * ratios, (2) resulting percentages of service injected + * w.r.t. to the total service dispatched while bfqq is in + * service, and (3) corresponding values of the coefficient: + * 1 (50%) -> 10 + * 2 (33%) -> 20 + * 10 (9%) -> 100 + * 9.9 (9%) -> 99 + * 1.5 (40%) -> 15 + * 0.5 (66%) -> 5 + * 0.1 (90%) -> 1 + * + * So, if the coefficient is lower than 10, then + * injected service is more than bfqq service. + */ + unsigned int inject_coeff; + /* amount of service injected in current service slot */ + unsigned int injected_service; +}; + +/** + * struct bfq_ttime - per process thinktime stats. + */ +struct bfq_ttime { + u64 last_end_request; /* completion time of last request */ + + u64 ttime_total; /* total process thinktime */ + unsigned long ttime_samples; /* number of thinktime samples */ + u64 ttime_mean; /* average process thinktime */ + +}; + +/** + * 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]; + /* associated @bfq_ttime struct */ + struct bfq_ttime ttime; + /* per (request_queue, blkcg) ioprio */ + int ioprio; +#ifdef BFQ_GROUP_IOSCHED_ENABLED + uint64_t blkcg_serial_nr; /* the current blkcg serial */ +#endif + + /* + * Snapshot of the has_short_time flag before merging; taken + * to remember its value while the queue is merged, so as to + * be able to restore it in case of split. + */ + bool saved_has_short_ttime; + /* + * 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_data - per-device data structure. + * + * All the fields are protected by the @queue lock. + */ +struct bfq_data { + /* request queue for the device */ + struct request_queue *queue; + + /* 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; + + /* + * Number of groups with at least one descendant process that + * has at least one request waiting for completion. Note that + * this accounts for also requests already dispatched, but not + * yet completed. Therefore this number of groups may differ + * (be larger) than the number of active groups, as a group is + * considered active only if its corresponding entity has + * descendant queues with at least one request queued. This + * number is used to decide whether a scenario is symmetric. + * For a detailed explanation see comments on the computation + * of the variable asymmetric_scenario in the function + * bfq_better_to_idle(). + * + * However, it is hard to compute this number exactly, for + * groups with multiple descendant processes. Consider a group + * that is inactive, i.e., that has no descendant process with + * pending I/O inside BFQ queues. Then suppose that + * num_groups_with_pending_reqs is still accounting for this + * group, because the group has descendant processes with some + * I/O request still in flight. num_groups_with_pending_reqs + * should be decremented when the in-flight request of the + * last descendant process is finally completed (assuming that + * nothing else has changed for the group in the meantime, in + * terms of composition of the group and active/inactive state of child + * groups and processes). To accomplish this, an additional + * pending-request counter must be added to entities, and must + * be updated correctly. To avoid this additional field and operations, + * we resort to the following tradeoff between simplicity and + * accuracy: for an inactive group that is still counted in + * num_groups_with_pending_reqs, we decrement + * num_groups_with_pending_reqs when the first descendant + * process of the group remains with no request waiting for + * completion. + * + * Even this simpler decrement strategy requires a little + * carefulness: to avoid multiple decrements, we flag a group, + * more precisely an entity representing a group, as still + * counted in num_groups_with_pending_reqs when it becomes + * inactive. Then, when the first descendant queue of the + * entity remains with no request waiting for completion, + * num_groups_with_pending_reqs is decremented, and this flag + * is reset. After this flag is reset for the entity, + * num_groups_with_pending_reqs won't be decremented any + * longer in case a new descendant queue of the entity remains + * with no request waiting for completion. + */ + unsigned int num_groups_with_pending_reqs; + + /* + * Per-class (RT, BE, IDLE) number of bfq_queues containing + * requests (including the queue in service, even if it is + * idling). + */ + unsigned int busy_queues[3]; + /* 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; + /* delayed work to restart dispatching on the request queue */ + struct work_struct unplug_work; + + /* 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; + + /* position of the last served request for the in-service queue */ + sector_t in_serv_last_pos; + + /* 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 + * [(sectors/usec) / 2^BFQ_RATE_SHIFT]. 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 ref_rate*ref_wr_duration, used + * for computing the maximum duration of weight raising + * automatically. + */ + u64 rate_dur_prod; + + /* fallback dummy bfqq for extreme OOM conditions */ + struct bfq_queue oom_bfqq; +}; + +enum bfqq_state_flags { + BFQ_BFQQ_FLAG_just_created = 0, /* queue just allocated */ + BFQ_BFQQ_FLAG_busy, /* has requests or is in service */ + BFQ_BFQQ_FLAG_wait_request, /* waiting for a request */ + BFQ_BFQQ_FLAG_non_blocking_wait_rq, /* + * waiting for a request + * without idling the device + */ + BFQ_BFQQ_FLAG_must_alloc, /* must be allowed rq alloc */ + BFQ_BFQQ_FLAG_fifo_expire, /* FIFO checked in this slice */ + BFQ_BFQQ_FLAG_has_short_ttime, /* queue has a short think time */ + BFQ_BFQQ_FLAG_sync, /* synchronous queue */ + BFQ_BFQQ_FLAG_IO_bound, /* + * bfqq has timed-out at least once + * having consumed at most 2/10 of + * its budget + */ + BFQ_BFQQ_FLAG_in_large_burst, /* + * bfqq activated in a large burst, + * see comments to bfq_handle_burst. + */ + BFQ_BFQQ_FLAG_softrt_update, /* + * may need softrt-next-start + * update + */ + BFQ_BFQQ_FLAG_coop, /* bfqq is shared */ + BFQ_BFQQ_FLAG_split_coop /* shared bfqq will be split */ +}; + +#define BFQ_BFQQ_FNS(name) \ +static void bfq_mark_bfqq_##name(struct bfq_queue *bfqq) \ +{ \ + (bfqq)->flags |= (1 << BFQ_BFQQ_FLAG_##name); \ +} \ +static void bfq_clear_bfqq_##name(struct bfq_queue *bfqq) \ +{ \ + (bfqq)->flags &= ~(1 << BFQ_BFQQ_FLAG_##name); \ +} \ +static int bfq_bfqq_##name(const struct bfq_queue *bfqq) \ +{ \ + return ((bfqq)->flags & (1 << BFQ_BFQQ_FLAG_##name)) != 0; \ +} + +BFQ_BFQQ_FNS(just_created); +BFQ_BFQQ_FNS(busy); +BFQ_BFQQ_FNS(wait_request); +BFQ_BFQQ_FNS(non_blocking_wait_rq); +BFQ_BFQQ_FNS(must_alloc); +BFQ_BFQQ_FNS(fifo_expire); +BFQ_BFQQ_FNS(has_short_ttime); +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_REDIRECT_TO_CONSOLE + +static const char *checked_dev_name(const struct device *dev) +{ + static const char nodev[] = "nodev"; + + if (dev) + return dev_name(dev); + + return nodev; +} + +#ifdef BFQ_GROUP_IOSCHED_ENABLED +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]; \ + \ + assert_spin_locked((bfqd)->queue->queue_lock); \ + blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \ + pr_crit("%s bfq%d%c %s [%s] " fmt "\n", \ + checked_dev_name((bfqd)->queue->backing_dev_info->dev), \ + (bfqq)->pid, \ + bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \ + __pbuf, __func__, ##args); \ +} while (0) + +#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do { \ + char __pbuf[128]; \ + \ + blkg_path(bfqg_to_blkg(bfqg), __pbuf, sizeof(__pbuf)); \ + pr_crit("%s %s [%s] " fmt "\n", \ + checked_dev_name((bfqd)->queue->backing_dev_info->dev), \ + __pbuf, __func__, ##args); \ +} while (0) + +#else /* BFQ_GROUP_IOSCHED_ENABLED */ + +#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \ + pr_crit("%s bfq%d%c [%s] " fmt "\n", \ + checked_dev_name((bfqd)->queue->backing_dev_info->dev), \ + (bfqq)->pid, bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \ + __func__, ##args) +#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do {} while (0) + +#endif /* BFQ_GROUP_IOSCHED_ENABLED */ + +#define bfq_log(bfqd, fmt, args...) \ + pr_crit("%s bfq [%s] " fmt "\n", \ + checked_dev_name((bfqd)->queue->backing_dev_info->dev), \ + __func__, ##args) + +#else /* CONFIG_BFQ_REDIRECT_TO_CONSOLE */ + +#if !defined(CONFIG_BLK_DEV_IO_TRACE) + +/* Avoid possible "unused-variable" warning. See commit message. */ + +#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) ((void) (bfqq)) + +#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) ((void) (bfqg)) + +#define bfq_log(bfqd, fmt, args...) do {} while (0) + +#else /* CONFIG_BLK_DEV_IO_TRACE */ + +#include + +#ifdef BFQ_GROUP_IOSCHED_ENABLED +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]; \ + \ + assert_spin_locked((bfqd)->queue->queue_lock); \ + blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \ + blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s [%s] " fmt, \ + (bfqq)->pid, \ + bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \ + __pbuf, __func__, ##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 [%s] " fmt, __pbuf, \ + __func__, ##args); \ +} while (0) + +#else /* BFQ_GROUP_IOSCHED_ENABLED */ + +#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \ + blk_add_trace_msg((bfqd)->queue, "bfq%d%c [%s] " fmt, (bfqq)->pid, \ + bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \ + __func__, ##args) +#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do {} while (0) + +#endif /* BFQ_GROUP_IOSCHED_ENABLED */ + +#define bfq_log(bfqd, fmt, args...) \ + blk_add_trace_msg((bfqd)->queue, "bfq [%s] " fmt, __func__, ##args) + +#endif /* CONFIG_BLK_DEV_IO_TRACE */ +#endif /* CONFIG_BFQ_REDIRECT_TO_CONSOLE */ + +/* Expiration reasons. */ +enum bfqq_expiration { + BFQ_BFQQ_TOO_IDLE = 0, /* + * queue has been idling for + * too long + */ + BFQ_BFQQ_BUDGET_TIMEOUT, /* budget took too long to be used */ + BFQ_BFQQ_BUDGET_EXHAUSTED, /* budget consumed */ + BFQ_BFQQ_NO_MORE_REQUESTS, /* the queue has no more requests */ + BFQ_BFQQ_PREEMPTED /* preemption in progress */ +}; + + +struct bfqg_stats { +#if defined(BFQ_GROUP_IOSCHED_ENABLED) && defined(CONFIG_DEBUG_BLK_CGROUP) + /* 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 /* BFQ_GROUP_IOSCHED_ENABLED && CONFIG_DEBUG_BLK_CGROUP */ +}; + +#ifdef BFQ_GROUP_IOSCHED_ENABLED +/* + * 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. + * @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; + + 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 + +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 unsigned int bfq_tot_busy_queues(struct bfq_data *bfqd) +{ + return bfqd->busy_queues[0] + bfqd->busy_queues[1] + + bfqd->busy_queues[2]; +} + +static struct bfq_service_tree * +bfq_entity_service_tree(struct bfq_entity *entity) +{ + struct bfq_sched_data *sched_data = entity->sched_data; + struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); + unsigned int idx = bfq_class_idx(entity); + + BUG_ON(idx >= BFQ_IOPRIO_CLASSES); + BUG_ON(sched_data == NULL); + + if (bfqq) + bfq_log_bfqq(bfqq->bfqd, bfqq, + "%p %d", + sched_data->service_tree + idx, idx); +#ifdef BFQ_GROUP_IOSCHED_ENABLED + else { + struct bfq_group *bfqg = + container_of(entity, struct bfq_group, entity); + + bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, + "%p %d", + sched_data->service_tree + idx, idx); + } +#endif + 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 BFQ_GROUP_IOSCHED_ENABLED + +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 void bfq_dispatch_insert(struct request_queue *q, struct request *rq); +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); +#ifdef BFQ_GROUP_IOSCHED_ENABLED +static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg); +#endif +static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq); + +#endif /* _BFQ_H */ diff --git a/block/blk-mq.c b/block/blk-mq.c index e3c39ea8e17b..7a57368841f6 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2878,6 +2878,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) } if (ret) break; + if (q->elevator && q->elevator->type->ops.mq.depth_updated) + q->elevator->type->ops.mq.depth_updated(hctx); } if (!ret) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6980014357d4..8c4568ea6884 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -54,7 +54,7 @@ struct blk_stat_callback; * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 5 +#define BLKCG_MAX_POLS 7 typedef void (rq_end_io_fn)(struct request *, blk_status_t); @@ -127,6 +127,10 @@ typedef __u32 __bitwise req_flags_t; #define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20)) /* ->timeout has been called, don't expire again */ #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) +/* DEBUG: rq in bfq-mq dispatch list */ +#define RQF_DISP_LIST ((__force req_flags_t)(1 << 22)) +/* DEBUG: rq had get_rq_private executed on it */ +#define RQF_GOT ((__force req_flags_t)(1 << 23)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ diff --git a/include/linux/elevator.h b/include/linux/elevator.h index a02deea30185..a2bf4a6b9316 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -99,6 +99,7 @@ struct elevator_mq_ops { void (*exit_sched)(struct elevator_queue *); int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int); void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); + void (*depth_updated)(struct blk_mq_hw_ctx *); bool (*allow_merge)(struct request_queue *, struct request *, struct bio *); bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *);