From ea08eeccae9297f7aabd2ef7f0c2517ac4549acc Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:18:26 +0000
Subject: [PATCH] write in 30M
---
kernel/block/bfq-cgroup.c | 676 ++++++++++++++++++++++++++++++++++++++------------------
1 files changed, 460 insertions(+), 216 deletions(-)
diff --git a/kernel/block/bfq-cgroup.c b/kernel/block/bfq-cgroup.c
index ecd3d0e..1f9ccc6 100644
--- a/kernel/block/bfq-cgroup.c
+++ b/kernel/block/bfq-cgroup.c
@@ -1,15 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* cgroups support for the BFQ I/O scheduler.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of the
- * License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
*/
#include <linux/module.h>
#include <linux/slab.h>
@@ -24,7 +15,83 @@
#include "bfq-iosched.h"
-#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
+static int bfq_stat_init(struct bfq_stat *stat, gfp_t gfp)
+{
+ int ret;
+
+ ret = percpu_counter_init(&stat->cpu_cnt, 0, gfp);
+ if (ret)
+ return ret;
+
+ atomic64_set(&stat->aux_cnt, 0);
+ return 0;
+}
+
+static void bfq_stat_exit(struct bfq_stat *stat)
+{
+ percpu_counter_destroy(&stat->cpu_cnt);
+}
+
+/**
+ * bfq_stat_add - add a value to a bfq_stat
+ * @stat: target bfq_stat
+ * @val: value to add
+ *
+ * Add @val to @stat. The caller must ensure that IRQ on the same CPU
+ * don't re-enter this function for the same counter.
+ */
+static inline void bfq_stat_add(struct bfq_stat *stat, uint64_t val)
+{
+ percpu_counter_add_batch(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH);
+}
+
+/**
+ * bfq_stat_read - read the current value of a bfq_stat
+ * @stat: bfq_stat to read
+ */
+static inline uint64_t bfq_stat_read(struct bfq_stat *stat)
+{
+ return percpu_counter_sum_positive(&stat->cpu_cnt);
+}
+
+/**
+ * bfq_stat_reset - reset a bfq_stat
+ * @stat: bfq_stat to reset
+ */
+static inline void bfq_stat_reset(struct bfq_stat *stat)
+{
+ percpu_counter_set(&stat->cpu_cnt, 0);
+ atomic64_set(&stat->aux_cnt, 0);
+}
+
+/**
+ * bfq_stat_add_aux - add a bfq_stat into another's aux count
+ * @to: the destination bfq_stat
+ * @from: the source
+ *
+ * Add @from's count including the aux one to @to's aux count.
+ */
+static inline void bfq_stat_add_aux(struct bfq_stat *to,
+ struct bfq_stat *from)
+{
+ atomic64_add(bfq_stat_read(from) + atomic64_read(&from->aux_cnt),
+ &to->aux_cnt);
+}
+
+/**
+ * blkg_prfill_stat - prfill callback for bfq_stat
+ * @sf: seq_file to print to
+ * @pd: policy private data of interest
+ * @off: offset to the bfq_stat in @pd
+ *
+ * prfill callback for printing a bfq_stat.
+ */
+static u64 blkg_prfill_stat(struct seq_file *sf, struct blkg_policy_data *pd,
+ int off)
+{
+ return __blkg_prfill_u64(sf, pd, bfq_stat_read((void *)pd + off));
+}
/* bfqg stats flags */
enum bfqg_stats_flags {
@@ -62,7 +129,7 @@
now = ktime_get_ns();
if (now > stats->start_group_wait_time)
- blkg_stat_add(&stats->group_wait_time,
+ bfq_stat_add(&stats->group_wait_time,
now - stats->start_group_wait_time);
bfqg_stats_clear_waiting(stats);
}
@@ -91,14 +158,14 @@
now = ktime_get_ns();
if (now > stats->start_empty_time)
- blkg_stat_add(&stats->empty_time,
+ bfq_stat_add(&stats->empty_time,
now - stats->start_empty_time);
bfqg_stats_clear_empty(stats);
}
void bfqg_stats_update_dequeue(struct bfq_group *bfqg)
{
- blkg_stat_add(&bfqg->stats.dequeue, 1);
+ bfq_stat_add(&bfqg->stats.dequeue, 1);
}
void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg)
@@ -128,7 +195,7 @@
u64 now = ktime_get_ns();
if (now > stats->start_idle_time)
- blkg_stat_add(&stats->idle_time,
+ bfq_stat_add(&stats->idle_time,
now - stats->start_idle_time);
bfqg_stats_clear_idling(stats);
}
@@ -146,9 +213,9 @@
{
struct bfqg_stats *stats = &bfqg->stats;
- blkg_stat_add(&stats->avg_queue_size_sum,
+ bfq_stat_add(&stats->avg_queue_size_sum,
blkg_rwstat_total(&stats->queued));
- blkg_stat_add(&stats->avg_queue_size_samples, 1);
+ bfq_stat_add(&stats->avg_queue_size_samples, 1);
bfqg_stats_update_group_wait_time(stats);
}
@@ -185,7 +252,7 @@
io_start_time_ns - start_time_ns);
}
-#else /* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */
+#else /* CONFIG_BFQ_CGROUP_DEBUG */
void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
unsigned int op) { }
@@ -199,7 +266,7 @@
void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { }
void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { }
-#endif /* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */
+#endif /* CONFIG_BFQ_CGROUP_DEBUG */
#ifdef CONFIG_BFQ_GROUP_IOSCHED
@@ -280,21 +347,32 @@
bfqg_put(bfqg);
}
+void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq)
+{
+ struct bfq_group *bfqg = blkg_to_bfqg(rq->bio->bi_blkg);
+
+ if (!bfqg)
+ return;
+
+ blkg_rwstat_add(&bfqg->stats.bytes, rq->cmd_flags, blk_rq_bytes(rq));
+ blkg_rwstat_add(&bfqg->stats.ios, rq->cmd_flags, 1);
+}
+
/* @stats = 0 */
static void bfqg_stats_reset(struct bfqg_stats *stats)
{
-#ifdef CONFIG_DEBUG_BLK_CGROUP
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
/* 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);
+ bfq_stat_reset(&stats->time);
+ bfq_stat_reset(&stats->avg_queue_size_sum);
+ bfq_stat_reset(&stats->avg_queue_size_samples);
+ bfq_stat_reset(&stats->dequeue);
+ bfq_stat_reset(&stats->group_wait_time);
+ bfq_stat_reset(&stats->idle_time);
+ bfq_stat_reset(&stats->empty_time);
#endif
}
@@ -304,19 +382,19 @@
if (!to || !from)
return;
-#ifdef CONFIG_DEBUG_BLK_CGROUP
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
/* 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,
+ bfq_stat_add_aux(&from->time, &from->time);
+ bfq_stat_add_aux(&to->avg_queue_size_sum, &from->avg_queue_size_sum);
+ bfq_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);
+ bfq_stat_add_aux(&to->dequeue, &from->dequeue);
+ bfq_stat_add_aux(&to->group_wait_time, &from->group_wait_time);
+ bfq_stat_add_aux(&to->idle_time, &from->idle_time);
+ bfq_stat_add_aux(&to->empty_time, &from->empty_time);
#endif
}
@@ -334,7 +412,7 @@
parent = bfqg_parent(bfqg);
- lockdep_assert_held(bfqg_to_blkg(bfqg)->q->queue_lock);
+ lockdep_assert_held(&bfqg_to_blkg(bfqg)->q->queue_lock);
if (unlikely(!parent))
return;
@@ -364,35 +442,41 @@
static void bfqg_stats_exit(struct bfqg_stats *stats)
{
-#ifdef CONFIG_DEBUG_BLK_CGROUP
+ blkg_rwstat_exit(&stats->bytes);
+ blkg_rwstat_exit(&stats->ios);
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
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);
+ bfq_stat_exit(&stats->time);
+ bfq_stat_exit(&stats->avg_queue_size_sum);
+ bfq_stat_exit(&stats->avg_queue_size_samples);
+ bfq_stat_exit(&stats->dequeue);
+ bfq_stat_exit(&stats->group_wait_time);
+ bfq_stat_exit(&stats->idle_time);
+ bfq_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->bytes, gfp) ||
+ blkg_rwstat_init(&stats->ios, gfp))
+ return -ENOMEM;
+
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
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)) {
+ bfq_stat_init(&stats->time, gfp) ||
+ bfq_stat_init(&stats->avg_queue_size_sum, gfp) ||
+ bfq_stat_init(&stats->avg_queue_size_samples, gfp) ||
+ bfq_stat_init(&stats->dequeue, gfp) ||
+ bfq_stat_init(&stats->group_wait_time, gfp) ||
+ bfq_stat_init(&stats->idle_time, gfp) ||
+ bfq_stat_init(&stats->empty_time, gfp)) {
bfqg_stats_exit(stats);
return -ENOMEM;
}
@@ -434,11 +518,12 @@
kfree(cpd_to_bfqgd(cpd));
}
-static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node)
+static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, struct request_queue *q,
+ struct blkcg *blkcg)
{
struct bfq_group *bfqg;
- bfqg = kzalloc_node(sizeof(*bfqg), gfp, node);
+ bfqg = kzalloc_node(sizeof(*bfqg), gfp, q->node);
if (!bfqg)
return NULL;
@@ -468,6 +553,7 @@
*/
bfqg->bfqd = bfqd;
bfqg->active_entities = 0;
+ bfqg->online = true;
bfqg->rq_pos_tree = RB_ROOT;
}
@@ -496,27 +582,10 @@
entity->sched_data = &parent->sched_data;
}
-static struct bfq_group *bfq_lookup_bfqg(struct bfq_data *bfqd,
- struct blkcg *blkcg)
+static void bfq_link_bfqg(struct bfq_data *bfqd, struct bfq_group *bfqg)
{
- struct blkcg_gq *blkg;
-
- blkg = blkg_lookup(blkcg, bfqd->queue);
- if (likely(blkg))
- return blkg_to_bfqg(blkg);
- return NULL;
-}
-
-struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
- struct blkcg *blkcg)
-{
- struct bfq_group *bfqg, *parent;
+ struct bfq_group *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
@@ -534,8 +603,28 @@
bfq_group_set_parent(curr_bfqg, parent);
}
}
+}
- return bfqg;
+struct bfq_group *bfq_bio_bfqg(struct bfq_data *bfqd, struct bio *bio)
+{
+ struct blkcg_gq *blkg = bio->bi_blkg;
+ struct bfq_group *bfqg;
+
+ while (blkg) {
+ if (!blkg->online) {
+ blkg = blkg->parent;
+ continue;
+ }
+ bfqg = blkg_to_bfqg(blkg);
+ if (bfqg->online) {
+ bio_associate_blkg_from_css(bio, &blkg->blkcg->css);
+ return bfqg;
+ }
+ blkg = blkg->parent;
+ }
+ bio_associate_blkg_from_css(bio,
+ &bfqg_to_blkg(bfqd->root_group)->blkcg->css);
+ return bfqd->root_group;
}
/**
@@ -557,6 +646,18 @@
{
struct bfq_entity *entity = &bfqq->entity;
+ /*
+ * oom_bfqq is not allowed to move, oom_bfqq will hold ref to root_group
+ * until elevator exit.
+ */
+ if (bfqq == &bfqd->oom_bfqq)
+ return;
+ /*
+ * Get extra reference to prevent bfqq from being freed in
+ * next possible expire or deactivate.
+ */
+ bfqq->ref++;
+
/* 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
@@ -569,7 +670,7 @@
if (bfq_bfqq_busy(bfqq))
bfq_deactivate_bfqq(bfqd, bfqq, false, false);
- else if (entity->on_st)
+ else if (entity->on_st_or_in_serv)
bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
bfqg_and_blkg_put(bfqq_group(bfqq));
@@ -579,12 +680,15 @@
bfqg_and_blkg_get(bfqg);
if (bfq_bfqq_busy(bfqq)) {
- bfq_pos_tree_add_move(bfqd, bfqq);
+ if (unlikely(!bfqd->nonrot_with_queueing))
+ 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);
+ /* release extra ref taken above, bfqq may happen to be freed now */
+ bfq_put_queue(bfqq);
}
/**
@@ -596,41 +700,58 @@
* 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)
- *
- * 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)
+static void *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
+ struct bfq_io_cq *bic,
+ struct bfq_group *bfqg)
{
- 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_queue *async_bfqq = bic_to_bfqq(bic, false);
+ struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, true);
struct bfq_entity *entity;
-
- bfqg = bfq_find_set_group(bfqd, blkcg);
-
- if (unlikely(!bfqg))
- bfqg = bfqd->root_group;
if (async_bfqq) {
entity = &async_bfqq->entity;
if (entity->sched_data != &bfqg->sched_data) {
- bic_set_bfqq(bic, NULL, 0);
- bfq_log_bfqq(bfqd, async_bfqq,
- "bic_change_group: %p %d",
- async_bfqq, async_bfqq->ref);
- bfq_put_queue(async_bfqq);
+ bic_set_bfqq(bic, NULL, false);
+ bfq_release_process_ref(bfqd, async_bfqq);
}
}
if (sync_bfqq) {
- entity = &sync_bfqq->entity;
- if (entity->sched_data != &bfqg->sched_data)
- bfq_bfqq_move(bfqd, sync_bfqq, bfqg);
+ if (!sync_bfqq->new_bfqq && !bfq_bfqq_coop(sync_bfqq)) {
+ /* We are the only user of this bfqq, just move it */
+ if (sync_bfqq->entity.sched_data != &bfqg->sched_data)
+ bfq_bfqq_move(bfqd, sync_bfqq, bfqg);
+ } else {
+ struct bfq_queue *bfqq;
+
+ /*
+ * The queue was merged to a different queue. Check
+ * that the merge chain still belongs to the same
+ * cgroup.
+ */
+ for (bfqq = sync_bfqq; bfqq; bfqq = bfqq->new_bfqq)
+ if (bfqq->entity.sched_data !=
+ &bfqg->sched_data)
+ break;
+ if (bfqq) {
+ /*
+ * Some queue changed cgroup so the merge is
+ * not valid anymore. We cannot easily just
+ * cancel the merge (by clearing new_bfqq) as
+ * there may be other processes using this
+ * queue and holding refs to all queues below
+ * sync_bfqq->new_bfqq. Similarly if the merge
+ * already happened, we need to detach from
+ * bfqq now so that we cannot merge bio to a
+ * request from the old cgroup.
+ */
+ bfq_put_cooperator(sync_bfqq);
+ bic_set_bfqq(bic, NULL, true);
+ bfq_release_process_ref(bfqd, sync_bfqq);
+ }
+ }
}
return bfqg;
@@ -639,20 +760,24 @@
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;
+ struct bfq_group *bfqg = bfq_bio_bfqg(bfqd, bio);
uint64_t serial_nr;
- rcu_read_lock();
- serial_nr = bio_blkcg(bio)->css.serial_nr;
+ serial_nr = bfqg_to_blkg(bfqg)->blkcg->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;
+ return;
- bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio));
+ /*
+ * New cgroup for this process. Make sure it is linked to bfq internal
+ * cgroup hierarchy.
+ */
+ bfq_link_bfqg(bfqd, bfqg);
+ __bfq_bic_change_cgroup(bfqd, bic, bfqg);
/*
* Update blkg_path for bfq_log_* functions. We cache this
* path, and update it here, for the following
@@ -705,8 +830,6 @@
*/
blkg_path(bfqg_to_blkg(bfqg), bfqg->blkg_path, sizeof(bfqg->blkg_path));
bic->blkcg_serial_nr = serial_nr;
-out:
- rcu_read_unlock();
}
/**
@@ -724,39 +847,53 @@
/**
* 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.
+ * @entity: the entity to move, if entity is a leaf; or the parent entity
+ * of an active leaf entity to move, if entity is not a leaf.
*/
static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
- struct bfq_entity *entity)
+ struct bfq_entity *entity,
+ int ioprio_class)
{
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+ struct bfq_queue *bfqq;
+ struct bfq_entity *child_entity = entity;
+ while (child_entity->my_sched_data) { /* leaf not reached yet */
+ struct bfq_sched_data *child_sd = child_entity->my_sched_data;
+ struct bfq_service_tree *child_st = child_sd->service_tree +
+ ioprio_class;
+ struct rb_root *child_active = &child_st->active;
+
+ child_entity = bfq_entity_of(rb_first(child_active));
+
+ if (!child_entity)
+ child_entity = child_sd->in_service_entity;
+ }
+
+ bfqq = bfq_entity_to_bfqq(child_entity);
bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
}
/**
- * bfq_reparent_active_entities - move to the root group all active
- * entities.
+ * bfq_reparent_active_queues - move to the root group all active queues.
* @bfqd: the device data structure with the root group.
* @bfqg: the group to move from.
- * @st: the service tree with the entities.
+ * @st: the service tree to start the search from.
*/
-static void bfq_reparent_active_entities(struct bfq_data *bfqd,
- struct bfq_group *bfqg,
- struct bfq_service_tree *st)
+static void bfq_reparent_active_queues(struct bfq_data *bfqd,
+ struct bfq_group *bfqg,
+ struct bfq_service_tree *st,
+ int ioprio_class)
{
struct rb_root *active = &st->active;
- struct bfq_entity *entity = NULL;
+ struct bfq_entity *entity;
- 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);
+ while ((entity = bfq_entity_of(rb_first(active))))
+ bfq_reparent_leaf_entity(bfqd, entity, ioprio_class);
if (bfqg->sched_data.in_service_entity)
bfq_reparent_leaf_entity(bfqd,
- bfqg->sched_data.in_service_entity);
+ bfqg->sched_data.in_service_entity,
+ ioprio_class);
}
/**
@@ -789,13 +926,6 @@
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
@@ -807,13 +937,27 @@
* There is no need to put the sync queues, as the
* scheduler has taken no reference.
*/
- bfq_reparent_active_entities(bfqd, bfqg, st);
+ bfq_reparent_active_queues(bfqd, bfqg, st, 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. In addition, even
+ * bfq_reparent_active_queues() may happen to add some
+ * entities to the idle tree. It happens if, in some
+ * of the calls to bfq_bfqq_move() performed by
+ * bfq_reparent_active_queues(), the queue to move is
+ * empty and gets expired.
+ */
+ bfq_flush_idle_tree(st);
}
__bfq_deactivate_entity(entity, false);
put_async_queues:
bfq_put_async_queues(bfqd, bfqg);
+ bfqg->online = false;
spin_unlock_irqrestore(&bfqd->lock, flags);
/*
@@ -837,7 +981,7 @@
bfq_end_wr_async_queues(bfqd, bfqd->root_group);
}
-static int bfq_io_show_weight(struct seq_file *sf, void *v)
+static int bfq_io_show_weight_legacy(struct seq_file *sf, void *v)
{
struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
@@ -849,6 +993,60 @@
seq_printf(sf, "%u\n", val);
return 0;
+}
+
+static u64 bfqg_prfill_weight_device(struct seq_file *sf,
+ struct blkg_policy_data *pd, int off)
+{
+ struct bfq_group *bfqg = pd_to_bfqg(pd);
+
+ if (!bfqg->entity.dev_weight)
+ return 0;
+ return __blkg_prfill_u64(sf, pd, bfqg->entity.dev_weight);
+}
+
+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);
+
+ seq_printf(sf, "default %u\n", bfqgd->weight);
+ blkcg_print_blkgs(sf, blkcg, bfqg_prfill_weight_device,
+ &blkcg_policy_bfq, 0, false);
+ return 0;
+}
+
+static void bfq_group_set_weight(struct bfq_group *bfqg, u64 weight, u64 dev_weight)
+{
+ weight = dev_weight ?: weight;
+
+ bfqg->entity.dev_weight = dev_weight;
+ /*
+ * 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)weight != bfqg->entity.new_weight) {
+ bfqg->entity.new_weight = (unsigned short)weight;
+ /*
+ * 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;
+ }
}
static int bfq_io_set_weight_legacy(struct cgroup_subsys_state *css,
@@ -869,61 +1067,70 @@
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;
- }
+ if (bfqg)
+ bfq_group_set_weight(bfqg, val, 0);
}
spin_unlock_irq(&blkcg->lock);
return ret;
}
+static ssize_t bfq_io_set_device_weight(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ int ret;
+ struct blkg_conf_ctx ctx;
+ struct blkcg *blkcg = css_to_blkcg(of_css(of));
+ struct bfq_group *bfqg;
+ u64 v;
+
+ ret = blkg_conf_prep(blkcg, &blkcg_policy_bfq, buf, &ctx);
+ if (ret)
+ return ret;
+
+ if (sscanf(ctx.body, "%llu", &v) == 1) {
+ /* require "default" on dfl */
+ ret = -ERANGE;
+ if (!v)
+ goto out;
+ } else if (!strcmp(strim(ctx.body), "default")) {
+ v = 0;
+ } else {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ bfqg = blkg_to_bfqg(ctx.blkg);
+
+ ret = -ERANGE;
+ if (!v || (v >= BFQ_MIN_WEIGHT && v <= BFQ_MAX_WEIGHT)) {
+ bfq_group_set_weight(bfqg, bfqg->entity.weight, v);
+ ret = 0;
+ }
+out:
+ blkg_conf_finish(&ctx);
+ return ret ?: nbytes;
+}
+
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);
+ char *endp;
+ int ret;
+ u64 v;
- if (ret)
- return ret;
+ buf = strim(buf);
- ret = bfq_io_set_weight_legacy(of_css(of), NULL, weight);
- return ret ?: nbytes;
-}
+ /* "WEIGHT" or "default WEIGHT" sets the default weight */
+ v = simple_strtoull(buf, &endp, 0);
+ if (*endp == '\0' || sscanf(buf, "default %llu", &v) == 1) {
+ ret = bfq_io_set_weight_legacy(of_css(of), NULL, v);
+ 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;
+ return bfq_io_set_device_weight(of, buf, nbytes, off);
}
static int bfqg_print_rwstat(struct seq_file *sf, void *v)
@@ -933,29 +1140,13 @@
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);
-}
+ struct blkg_rwstat_sample 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;
+ blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off, &sum);
+ return __blkg_prfill_rwstat(sf, pd, &sum);
}
static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
@@ -966,10 +1157,52 @@
return 0;
}
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
+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 u64 bfqg_prfill_stat_recursive(struct seq_file *sf,
+ struct blkg_policy_data *pd, int off)
+{
+ struct blkcg_gq *blkg = pd_to_blkg(pd);
+ struct blkcg_gq *pos_blkg;
+ struct cgroup_subsys_state *pos_css;
+ u64 sum = 0;
+
+ lockdep_assert_held(&blkg->q->queue_lock);
+
+ rcu_read_lock();
+ blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
+ struct bfq_stat *stat;
+
+ if (!pos_blkg->online)
+ continue;
+
+ stat = (void *)blkg_to_pd(pos_blkg, &blkcg_policy_bfq) + off;
+ sum += bfq_stat_read(stat) + atomic64_read(&stat->aux_cnt);
+ }
+ rcu_read_unlock();
+
+ return __blkg_prfill_u64(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 u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd,
int off)
{
- u64 sum = blkg_rwstat_total(&pd->blkg->stat_bytes);
+ struct bfq_group *bfqg = blkg_to_bfqg(pd->blkg);
+ u64 sum = blkg_rwstat_total(&bfqg->stats.bytes);
return __blkg_prfill_u64(sf, pd, sum >> 9);
}
@@ -984,12 +1217,13 @@
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]);
+ struct blkg_rwstat_sample tmp;
- return __blkg_prfill_u64(sf, pd, sum >> 9);
+ blkg_rwstat_recursive_sum(pd->blkg, &blkcg_policy_bfq,
+ offsetof(struct bfq_group, stats.bytes), &tmp);
+
+ return __blkg_prfill_u64(sf, pd,
+ (tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]) >> 9);
}
static int bfqg_print_stat_sectors_recursive(struct seq_file *sf, void *v)
@@ -1004,11 +1238,11 @@
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 samples = bfq_stat_read(&bfqg->stats.avg_queue_size_samples);
u64 v = 0;
if (samples) {
- v = blkg_stat_read(&bfqg->stats.avg_queue_size_sum);
+ v = bfq_stat_read(&bfqg->stats.avg_queue_size_sum);
v = div64_u64(v, samples);
}
__blkg_prfill_u64(sf, pd, v);
@@ -1023,7 +1257,7 @@
0, false);
return 0;
}
-#endif /* CONFIG_DEBUG_BLK_CGROUP */
+#endif /* CONFIG_BFQ_CGROUP_DEBUG */
struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
{
@@ -1056,22 +1290,28 @@
{
.name = "bfq.weight",
.flags = CFTYPE_NOT_ON_ROOT,
- .seq_show = bfq_io_show_weight,
+ .seq_show = bfq_io_show_weight_legacy,
.write_u64 = bfq_io_set_weight_legacy,
+ },
+ {
+ .name = "bfq.weight_device",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = bfq_io_show_weight,
+ .write = bfq_io_set_weight,
},
/* statistics, covers only the tasks in the bfqg */
{
.name = "bfq.io_service_bytes",
- .private = (unsigned long)&blkcg_policy_bfq,
- .seq_show = blkg_print_stat_bytes,
+ .private = offsetof(struct bfq_group, stats.bytes),
+ .seq_show = bfqg_print_rwstat,
},
{
.name = "bfq.io_serviced",
- .private = (unsigned long)&blkcg_policy_bfq,
- .seq_show = blkg_print_stat_ios,
+ .private = offsetof(struct bfq_group, stats.ios),
+ .seq_show = bfqg_print_rwstat,
},
-#ifdef CONFIG_DEBUG_BLK_CGROUP
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
{
.name = "bfq.time",
.private = offsetof(struct bfq_group, stats.time),
@@ -1101,20 +1341,20 @@
.private = offsetof(struct bfq_group, stats.queued),
.seq_show = bfqg_print_rwstat,
},
-#endif /* CONFIG_DEBUG_BLK_CGROUP */
+#endif /* CONFIG_BFQ_CGROUP_DEBUG */
- /* the same statictics which cover the bfqg and its descendants */
+ /* the same statistics which cover the bfqg and its descendants */
{
.name = "bfq.io_service_bytes_recursive",
- .private = (unsigned long)&blkcg_policy_bfq,
- .seq_show = blkg_print_stat_bytes_recursive,
+ .private = offsetof(struct bfq_group, stats.bytes),
+ .seq_show = bfqg_print_rwstat_recursive,
},
{
.name = "bfq.io_serviced_recursive",
- .private = (unsigned long)&blkcg_policy_bfq,
- .seq_show = blkg_print_stat_ios_recursive,
+ .private = offsetof(struct bfq_group, stats.ios),
+ .seq_show = bfqg_print_rwstat_recursive,
},
-#ifdef CONFIG_DEBUG_BLK_CGROUP
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
{
.name = "bfq.time_recursive",
.private = offsetof(struct bfq_group, stats.time),
@@ -1168,7 +1408,7 @@
.private = offsetof(struct bfq_group, stats.dequeue),
.seq_show = bfqg_print_stat,
},
-#endif /* CONFIG_DEBUG_BLK_CGROUP */
+#endif /* CONFIG_BFQ_CGROUP_DEBUG */
{ } /* terminate */
};
@@ -1207,7 +1447,7 @@
bfq_end_wr_async_queues(bfqd, bfqd->root_group);
}
-struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, struct blkcg *blkcg)
+struct bfq_group *bfq_bio_bfqg(struct bfq_data *bfqd, struct bio *bio)
{
return bfqd->root_group;
}
@@ -1217,6 +1457,10 @@
return bfqq->bfqd->root_group;
}
+void bfqg_and_blkg_get(struct bfq_group *bfqg) {}
+
+void bfqg_and_blkg_put(struct bfq_group *bfqg) {}
+
struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
{
struct bfq_group *bfqg;
--
Gitblit v1.6.2