struct blkcg_policy
struct blkcg_policy {
int plid;
/* cgroup files for the policy */
struct cftype *dfl_cftypes;
struct cftype *legacy_cftypes;
/* operations */
blkcg_pol_alloc_cpd_fn *cpd_alloc_fn;
blkcg_pol_init_cpd_fn *cpd_init_fn;
blkcg_pol_free_cpd_fn *cpd_free_fn;
blkcg_pol_bind_cpd_fn *cpd_bind_fn;
blkcg_pol_alloc_pd_fn *pd_alloc_fn;
blkcg_pol_init_pd_fn *pd_init_fn;
blkcg_pol_online_pd_fn *pd_online_fn;
blkcg_pol_offline_pd_fn *pd_offline_fn;
blkcg_pol_free_pd_fn *pd_free_fn;
blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn;
};
static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */
int blkcg_policy_register(struct blkcg_policy *pol)
void blkcg_policy_unregister(struct blkcg_policy *pol)
int blkcg_activate_policy(struct request_queue *q,
const struct blkcg_policy *pol)
void blkcg_deactivate_policy(struct request_queue *q,
const struct blkcg_policy *pol)
/**
* blkcg_policy_register - register a blkcg policy
* @pol: blkcg policy to register
*
* Register @pol with blkcg core. Might sleep and @pol may be modified on
* successful registration. Returns 0 on success and -errno on failure.
*/
int blkcg_policy_register(struct blkcg_policy *pol)
{
struct blkcg *blkcg;
int i, ret;
mutex_lock(&blkcg_pol_register_mutex);
mutex_lock(&blkcg_pol_mutex);
/* find an empty slot */
ret = -ENOSPC;
for (i = 0; i < BLKCG_MAX_POLS; i++)
if (!blkcg_policy[i])
break;
if (i >= BLKCG_MAX_POLS)
goto err_unlock;
/* register @pol */
pol->plid = i;
blkcg_policy[pol->plid] = pol;
/* allocate and install cpd's */
if (pol->cpd_alloc_fn) {
list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
struct blkcg_policy_data *cpd;
cpd = pol->cpd_alloc_fn(GFP_KERNEL);
if (!cpd)
goto err_free_cpds;
blkcg->cpd[pol->plid] = cpd;
cpd->blkcg = blkcg;
cpd->plid = pol->plid;
pol->cpd_init_fn(cpd);
}
}
mutex_unlock(&blkcg_pol_mutex);
/* everything is in place, add intf files for the new policy */
if (pol->dfl_cftypes)
WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys,
pol->dfl_cftypes));
if (pol->legacy_cftypes)
WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys,
pol->legacy_cftypes));
mutex_unlock(&blkcg_pol_register_mutex);
return 0;
err_free_cpds:
if (pol->cpd_alloc_fn) {
list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
if (blkcg->cpd[pol->plid]) {
pol->cpd_free_fn(blkcg->cpd[pol->plid]);
blkcg->cpd[pol->plid] = NULL;
}
}
}
blkcg_policy[pol->plid] = NULL;
err_unlock:
mutex_unlock(&blkcg_pol_mutex);
mutex_unlock(&blkcg_pol_register_mutex);
return ret;
}
blk_throtl_init:
int blk_throtl_init(struct request_queue *q)
{
struct throtl_data *td;
int ret;
td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
if (!td)
return -ENOMEM;
INIT_WORK(&td->dispatch_work, blk_throtl_dispatch_work_fn);
throtl_service_queue_init(&td->service_queue);
q->td = td;
td->queue = q;
/* activate policy */
ret = blkcg_activate_policy(q, &blkcg_policy_throtl);
if (ret)
kfree(td);
return ret;
}
cfq_init_queue:
static int cfq_init_queue(struct request_queue *q, struct elevator_type *e)
{
struct cfq_data *cfqd;
struct blkcg_gq *blkg __maybe_unused;
int i, ret;
struct elevator_queue *eq;
eq = elevator_alloc(q, e);
if (!eq)
return -ENOMEM;
cfqd = kzalloc_node(sizeof(*cfqd), GFP_KERNEL, q->node);
if (!cfqd) {
kobject_put(&eq->kobj);
return -ENOMEM;
}
eq->elevator_data = cfqd;
cfqd->queue = q;
spin_lock_irq(q->queue_lock);
q->elevator = eq;
spin_unlock_irq(q->queue_lock);
/* Init root service tree */
cfqd->grp_service_tree = CFQ_RB_ROOT;
/* Init root group and prefer root group over other groups by default */
#ifdef CONFIG_CFQ_GROUP_IOSCHED
ret = blkcg_activate_policy(q, &blkcg_policy_cfq);
if (ret)
goto out_free;
cfqd->root_group = blkg_to_cfqg(q->root_blkg);
#else
ret = -ENOMEM;
cfqd->root_group = kzalloc_node(sizeof(*cfqd->root_group),
GFP_KERNEL, cfqd->queue->node);
if (!cfqd->root_group)
goto out_free;
cfq_init_cfqg_base(cfqd->root_group);
cfqd->root_group->weight = 2 * CFQ_WEIGHT_LEGACY_DFL;
cfqd->root_group->leaf_weight = 2 * CFQ_WEIGHT_LEGACY_DFL;
#endif
/*
* Not strictly needed (since RB_ROOT just clears the node and we
* zeroed cfqd on alloc), but better be safe in case someone decides
* to add magic to the rb code
*/
for (i = 0; i < CFQ_PRIO_LISTS; i++)
cfqd->prio_trees[i] = RB_ROOT;
/*
* Our fallback cfqq if cfq_get_queue() runs into OOM issues.
* Grab a permanent reference to it, so that the normal code flow
* will not attempt to free it. oom_cfqq is linked to root_group
* but shouldn't hold a reference as it'll never be unlinked. Lose
* the reference from linking right away.
*/
cfq_init_cfqq(cfqd, &cfqd->oom_cfqq, 1, 0);
cfqd->oom_cfqq.ref++;
spin_lock_irq(q->queue_lock);
cfq_link_cfqq_cfqg(&cfqd->oom_cfqq, cfqd->root_group);
cfqg_put(cfqd->root_group);
spin_unlock_irq(q->queue_lock);
hrtimer_init(&cfqd->idle_slice_timer, CLOCK_MONOTONIC,
HRTIMER_MODE_REL);
cfqd->idle_slice_timer.function = cfq_idle_slice_timer;
INIT_WORK(&cfqd->unplug_work, cfq_kick_queue);
cfqd->cfq_quantum = cfq_quantum;
cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0];
cfqd->cfq_fifo_expire[1] = cfq_fifo_expire[1];
cfqd->cfq_back_max = cfq_back_max;
cfqd->cfq_back_penalty = cfq_back_penalty;
cfqd->cfq_slice[0] = cfq_slice_async;
cfqd->cfq_slice[1] = cfq_slice_sync;
cfqd->cfq_target_latency = cfq_target_latency;
cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
cfqd->cfq_slice_idle = cfq_slice_idle;
cfqd->cfq_group_idle = cfq_group_idle;
cfqd->cfq_latency = 1;
cfqd->hw_tag = -1;
/*
* we optimistically start assuming sync ops weren't delayed in last
* second, in order to have larger depth for async operations.
*/
cfqd->last_delayed_sync = ktime_get_ns() - NSEC_PER_SEC;
return 0;
out_free:
kfree(cfqd);
kobject_put(&eq->kobj);
return ret;
}