Techwizz/kernel-fxtec-pro1x
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
kernel-fxtec-pro1x/kernel/sched/tune.c

855 lines
22 KiB
C
Raw Blame History

#include <linux/cgroup.h>
#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/printk.h>
#include <linux/rcupdate.h>
#include <linux/slab.h>
#include <trace/events/sched.h>
#include "sched.h"
bool schedtune_initialized = false;
extern struct reciprocal_value schedtune_spc_rdiv;
/* We hold schedtune boost in effect for at least this long */
#define SCHEDTUNE_BOOST_HOLD_NS 50000000ULL
/*
* EAS scheduler tunables for task groups.
*
* When CGroup support is enabled, we have to synchronize two different
* paths:
* - slow path: where CGroups are created/updated/removed
* - fast path: where tasks in a CGroups are accounted
*
* The slow path tracks (a limited number of) CGroups and maps each on a
* "boost_group" index. The fastpath accounts tasks currently RUNNABLE on each
* "boost_group".
*
* Once a new CGroup is created, a boost group idx is assigned and the
* corresponding "boost_group" marked as valid on each CPU.
* Once a CGroup is release, the corresponding "boost_group" is marked as
* invalid on each CPU. The CPU boost value (boost_max) is aggregated by
* considering only valid boost_groups with a non null tasks counter.
*
* .:: Locking strategy
*
* The fast path uses a spin lock for each CPU boost_group which protects the
* tasks counter.
*
* The "valid" and "boost" values of each CPU boost_group is instead
* protected by the RCU lock provided by the CGroups callbacks. Thus, only the
* slow path can access and modify the boost_group attribtues of each CPU.
* The fast path will catch up the most updated values at the next scheduling
* event (i.e. enqueue/dequeue).
*
* |
* SLOW PATH | FAST PATH
* CGroup add/update/remove | Scheduler enqueue/dequeue events
* |
* |
* | DEFINE_PER_CPU(struct boost_groups)
* | +--------------+----+---+----+----+
* | | idle | | | | |
* | | boost_max | | | | |
* | +---->lock | | | | |
* struct schedtune allocated_groups | | | group[ ] | | | | |
* +------------------------------+ +-------+ | | +--+---------+-+----+---+----+----+
* | idx | | | | | | valid |
* | boots / prefer_idle | | | | | | boost |
* | perf_{boost/constraints}_idx | <---------+(*) | | | | tasks | <------------+
* | css | +-------+ | | +---------+ |
* +-+----------------------------+ | | | | | | |
* ^ | | | | | | |
* | +-------+ | | +---------+ |
* | | | | | | | |
* | | | | | | | |
* | +-------+ | | +---------+ |
* | zmalloc | | | | | | |
* | | | | | | | |
* | +-------+ | | +---------+ |
* + BOOSTGROUPS_COUNT | | BOOSTGROUPS_COUNT |
* schedtune_boostgroup_init() | + |
* | schedtune_{en,de}queue_task() |
* | +
* | schedtune_tasks_update()
* |
*/
/* SchdTune tunables for a group of tasks */
struct schedtune {
/* SchedTune CGroup subsystem */
struct cgroup_subsys_state css;
/* Boost group allocated ID */
int idx;
/* Boost value for tasks on that SchedTune CGroup */
int boost;
#ifdef CONFIG_SCHED_WALT
/* Toggle ability to override sched boost enabled */
bool sched_boost_no_override;
/*
* Controls whether a cgroup is eligible for sched boost or not. This
* can temporariliy be disabled by the kernel based on the no_override
* flag above.
*/
bool sched_boost_enabled;
/*
* Controls whether tasks of this cgroup should be colocated with each
* other and tasks of other cgroups that have the same flag turned on.
*/
bool colocate;
/* Controls whether further updates are allowed to the colocate flag */
bool colocate_update_disabled;
#endif /* CONFIG_SCHED_WALT */
/* Hint to bias scheduling of tasks on that SchedTune CGroup
* towards idle CPUs */
int prefer_idle;
};
static inline struct schedtune *css_st(struct cgroup_subsys_state *css)
{
return css ? container_of(css, struct schedtune, css) : NULL;
}
static inline struct schedtune *task_schedtune(struct task_struct *tsk)
{
return css_st(task_css(tsk, schedtune_cgrp_id));
}
static inline struct schedtune *parent_st(struct schedtune *st)
{
return css_st(st->css.parent);
}
/*
* SchedTune root control group
* The root control group is used to defined a system-wide boosting tuning,
* which is applied to all tasks in the system.
* Task specific boost tuning could be specified by creating and
* configuring a child control group under the root one.
* By default, system-wide boosting is disabled, i.e. no boosting is applied
* to tasks which are not into a child control group.
*/
static struct schedtune
root_schedtune = {
.boost = 0,
#ifdef CONFIG_SCHED_WALT
.sched_boost_no_override = false,
.sched_boost_enabled = true,
.colocate = false,
.colocate_update_disabled = false,
#endif
.prefer_idle = 0,
};
/*
* Maximum number of boost groups to support
* When per-task boosting is used we still allow only limited number of
* boost groups for two main reasons:
* 1. on a real system we usually have only few classes of workloads which
* make sense to boost with different values (e.g. background vs foreground
* tasks, interactive vs low-priority tasks)
* 2. a limited number allows for a simpler and more memory/time efficient
* implementation especially for the computation of the per-CPU boost
* value
*/
#define BOOSTGROUPS_COUNT 6
/* Array of configured boostgroups */
static struct schedtune *allocated_group[BOOSTGROUPS_COUNT] = {
&root_schedtune,
NULL,
};
/* SchedTune boost groups
* Keep track of all the boost groups which impact on CPU, for example when a
* CPU has two RUNNABLE tasks belonging to two different boost groups and thus
* likely with different boost values.
* Since on each system we expect only a limited number of boost groups, here
* we use a simple array to keep track of the metrics required to compute the
* maximum per-CPU boosting value.
*/
struct boost_groups {
/* Maximum boost value for all RUNNABLE tasks on a CPU */
int boost_max;
u64 boost_ts;
struct {
/* True when this boost group maps an actual cgroup */
bool valid;
/* The boost for tasks on that boost group */
int boost;
/* Count of RUNNABLE tasks on that boost group */
unsigned tasks;
/* Timestamp of boost activation */
u64 ts;
} group[BOOSTGROUPS_COUNT];
/* CPU's boost group locking */
raw_spinlock_t lock;
};
/* Boost groups affecting each CPU in the system */
DEFINE_PER_CPU(struct boost_groups, cpu_boost_groups);
#ifdef CONFIG_SCHED_WALT
static inline void init_sched_boost(struct schedtune *st)
{
st->sched_boost_no_override = false;
st->sched_boost_enabled = true;
st->colocate = false;
st->colocate_update_disabled = false;
}
void update_cgroup_boost_settings(void)
{
int i;
for (i = 0; i < BOOSTGROUPS_COUNT; i++) {
if (!allocated_group[i])
break;
if (allocated_group[i]->sched_boost_no_override)
continue;
allocated_group[i]->sched_boost_enabled = false;
}
}
void restore_cgroup_boost_settings(void)
{
int i;
for (i = 0; i < BOOSTGROUPS_COUNT; i++) {
if (!allocated_group[i])
break;
allocated_group[i]->sched_boost_enabled = true;
}
}
bool task_sched_boost(struct task_struct *p)
{
struct schedtune *st;
bool sched_boost_enabled;
rcu_read_lock();
st = task_schedtune(p);
sched_boost_enabled = st->sched_boost_enabled;
rcu_read_unlock();
return sched_boost_enabled;
}
static u64
sched_boost_override_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
struct schedtune *st = css_st(css);
return st->sched_boost_no_override;
}
static int sched_boost_override_write(struct cgroup_subsys_state *css,
struct cftype *cft, u64 override)
{
struct schedtune *st = css_st(css);
st->sched_boost_no_override = !!override;
return 0;
}
#endif /* CONFIG_SCHED_WALT */
static inline bool schedtune_boost_timeout(u64 now, u64 ts)
{
return ((now - ts) > SCHEDTUNE_BOOST_HOLD_NS);
}
static inline bool
schedtune_boost_group_active(int idx, struct boost_groups* bg, u64 now)
{
if (bg->group[idx].tasks)
return true;
return !schedtune_boost_timeout(now, bg->group[idx].ts);
}
static void
schedtune_cpu_update(int cpu, u64 now)
{
struct boost_groups *bg = &per_cpu(cpu_boost_groups, cpu);
int boost_max;
u64 boost_ts;
int idx;
/* The root boost group is always active */
boost_max = bg->group[0].boost;
boost_ts = now;
for (idx = 1; idx < BOOSTGROUPS_COUNT; ++idx) {
/* Ignore non boostgroups not mapping a cgroup */
if (!bg->group[idx].valid)
continue;
/*
* A boost group affects a CPU only if it has
* RUNNABLE tasks on that CPU or it has hold
* in effect from a previous task.
*/
if (!schedtune_boost_group_active(idx, bg, now))
continue;
/* This boost group is active */
if (boost_max > bg->group[idx].boost)
continue;
boost_max = bg->group[idx].boost;
boost_ts = bg->group[idx].ts;
}
/* Ensures boost_max is non-negative when all cgroup boost values
* are neagtive. Avoids under-accounting of cpu capacity which may cause
* task stacking and frequency spikes.*/
boost_max = max(boost_max, 0);
bg->boost_max = boost_max;
bg->boost_ts = boost_ts;
}
static int
schedtune_boostgroup_update(int idx, int boost)
{
struct boost_groups *bg;
int cur_boost_max;
int old_boost;
int cpu;
u64 now;
/* Update per CPU boost groups */
for_each_possible_cpu(cpu) {
bg = &per_cpu(cpu_boost_groups, cpu);
/* CGroups are never associated to non active cgroups */
BUG_ON(!bg->group[idx].valid);
/*
* Keep track of current boost values to compute the per CPU
* maximum only when it has been affected by the new value of
* the updated boost group
*/
cur_boost_max = bg->boost_max;
old_boost = bg->group[idx].boost;
/* Update the boost value of this boost group */
bg->group[idx].boost = boost;
/* Check if this update increase current max */
now = sched_clock_cpu(cpu);
if (boost > cur_boost_max &&
schedtune_boost_group_active(idx, bg, now)) {
bg->boost_max = boost;
bg->boost_ts = bg->group[idx].ts;
trace_sched_tune_boostgroup_update(cpu, 1, bg->boost_max);
continue;
}
/* Check if this update has decreased current max */
if (cur_boost_max == old_boost && old_boost > boost) {
schedtune_cpu_update(cpu, now);
trace_sched_tune_boostgroup_update(cpu, -1, bg->boost_max);
continue;
}
trace_sched_tune_boostgroup_update(cpu, 0, bg->boost_max);
}
return 0;
}
#define ENQUEUE_TASK 1
#define DEQUEUE_TASK -1
static inline bool
schedtune_update_timestamp(struct task_struct *p)
{
if (sched_feat(SCHEDTUNE_BOOST_HOLD_ALL))
return true;
return task_has_rt_policy(p);
}
static inline void
schedtune_tasks_update(struct task_struct *p, int cpu, int idx, int task_count)
{
struct boost_groups *bg = &per_cpu(cpu_boost_groups, cpu);
int tasks = bg->group[idx].tasks + task_count;
/* Update boosted tasks count while avoiding to make it negative */
bg->group[idx].tasks = max(0, tasks);
/* Update timeout on enqueue */
if (task_count > 0) {
u64 now = sched_clock_cpu(cpu);
if (schedtune_update_timestamp(p))
bg->group[idx].ts = now;
/* Boost group activation or deactivation on that RQ */
if (bg->group[idx].tasks == 1)
schedtune_cpu_update(cpu, now);
}
trace_sched_tune_tasks_update(p, cpu, tasks, idx,
bg->group[idx].boost, bg->boost_max,
bg->group[idx].ts);
}
/*
* NOTE: This function must be called while holding the lock on the CPU RQ
*/
void schedtune_enqueue_task(struct task_struct *p, int cpu)
{
struct boost_groups *bg = &per_cpu(cpu_boost_groups, cpu);
unsigned long irq_flags;
int idx;
if (unlikely(!schedtune_initialized))
return;
/*
* Boost group accouting is protected by a per-cpu lock and requires
* interrupt to be disabled to avoid race conditions for example on
* do_exit()::cgroup_exit() and task migration.
*/
raw_spin_lock_irqsave(&bg->lock, irq_flags);
idx = p->stune_idx;
schedtune_tasks_update(p, cpu, idx, ENQUEUE_TASK);
raw_spin_unlock_irqrestore(&bg->lock, irq_flags);
}
int schedtune_can_attach(struct cgroup_taskset *tset)
{
return 0;
}
#ifdef CONFIG_SCHED_WALT
static u64 sched_colocate_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
struct schedtune *st = css_st(css);
return st->colocate;
}
static int sched_colocate_write(struct cgroup_subsys_state *css,
struct cftype *cft, u64 colocate)
{
struct schedtune *st = css_st(css);
if (st->colocate_update_disabled)
return -EPERM;
st->colocate = !!colocate;
st->colocate_update_disabled = true;
return 0;
}
bool schedtune_task_colocated(struct task_struct *p)
{
struct schedtune *st;
bool colocated;
if (unlikely(!schedtune_initialized))
return false;
/* Get task boost value */
rcu_read_lock();
st = task_schedtune(p);
colocated = st->colocate;
rcu_read_unlock();
return colocated;
}
#else /* CONFIG_SCHED_WALT */
static inline void init_sched_boost(struct schedtune *st) { }
#endif /* CONFIG_SCHED_WALT */
void schedtune_cancel_attach(struct cgroup_taskset *tset)
{
/* This can happen only if SchedTune controller is mounted with
* other hierarchies ane one of them fails. Since usually SchedTune is
* mouted on its own hierarcy, for the time being we do not implement
* a proper rollback mechanism */
WARN(1, "SchedTune cancel attach not implemented");
}
/*
* NOTE: This function must be called while holding the lock on the CPU RQ
*/
void schedtune_dequeue_task(struct task_struct *p, int cpu)
{
struct boost_groups *bg = &per_cpu(cpu_boost_groups, cpu);
unsigned long irq_flags;
int idx;
if (unlikely(!schedtune_initialized))
return;
/*
* Boost group accouting is protected by a per-cpu lock and requires
* interrupt to be disabled to avoid race conditions on...
*/
raw_spin_lock_irqsave(&bg->lock, irq_flags);
idx = p->stune_idx;
schedtune_tasks_update(p, cpu, idx, DEQUEUE_TASK);
raw_spin_unlock_irqrestore(&bg->lock, irq_flags);
}
int schedtune_cpu_boost_with(int cpu, struct task_struct *p)
{
struct boost_groups *bg;
u64 now;
int task_boost = p ? schedtune_task_boost(p) : -100;
bg = &per_cpu(cpu_boost_groups, cpu);
now = sched_clock_cpu(cpu);
/* Check to see if we have a hold in effect */
if (schedtune_boost_timeout(now, bg->boost_ts))
schedtune_cpu_update(cpu, now);
return max(bg->boost_max, task_boost);
}
int schedtune_task_boost(struct task_struct *p)
{
struct schedtune *st;
int task_boost;
if (unlikely(!schedtune_initialized))
return 0;
/* Get task boost value */
rcu_read_lock();
st = task_schedtune(p);
task_boost = st->boost;
rcu_read_unlock();
return task_boost;
}
int schedtune_prefer_idle(struct task_struct *p)
{
struct schedtune *st;
int prefer_idle;
if (unlikely(!schedtune_initialized))
return 0;
/* Get prefer_idle value */
rcu_read_lock();
st = task_schedtune(p);
prefer_idle = st->prefer_idle;
rcu_read_unlock();
return prefer_idle;
}
static u64
prefer_idle_read(struct cgroup_subsys_state *css, struct cftype *cft)
{
struct schedtune *st = css_st(css);
return st->prefer_idle;
}
static int
prefer_idle_write(struct cgroup_subsys_state *css, struct cftype *cft,
u64 prefer_idle)
{
struct schedtune *st = css_st(css);
st->prefer_idle = !!prefer_idle;
return 0;
}
static s64
boost_read(struct cgroup_subsys_state *css, struct cftype *cft)
{
struct schedtune *st = css_st(css);
return st->boost;
}
static void schedtune_attach(struct cgroup_taskset *tset)
{
struct task_struct *task;
struct cgroup_subsys_state *css;
struct boost_groups *bg;
struct rq_flags rq_flags;
unsigned int cpu;
struct rq *rq;
int src_idx; /* Source boost group index */
int dst_idx; /* Destination boost group index */
int tasks;
u64 now;
#ifdef CONFIG_SCHED_WALT
struct schedtune *st;
bool colocate;
cgroup_taskset_first(tset, &css);
st = css_st(css);
colocate = st->colocate;
cgroup_taskset_for_each(task, css, tset)
sync_cgroup_colocation(task, colocate);
#endif
cgroup_taskset_for_each(task, css, tset) {
/*
* Lock the CPU's RQ the task is enqueued to avoid race
* conditions with migration code while the task is being
* accounted
*/
rq = task_rq_lock(task, &rq_flags);
/*
* Boost group accouting is protected by a per-cpu lock and
* requires interrupt to be disabled to avoid race conditions
* on...
*/
cpu = cpu_of(rq);
bg = &per_cpu(cpu_boost_groups, cpu);
raw_spin_lock(&bg->lock);
dst_idx = task_schedtune(task)->idx;
src_idx = task->stune_idx;
/*
* Current task is not changing boostgroup, which can
* happen when the new hierarchy is in use.
*/
if (unlikely(dst_idx == src_idx)) {
raw_spin_unlock(&bg->lock);
task_rq_unlock(rq, task, &rq_flags);
continue;
}
task->stune_idx = dst_idx;
if (!task_on_rq_queued(task)) {
raw_spin_unlock(&bg->lock);
task_rq_unlock(rq, task, &rq_flags);
continue;
}
/*
* This is the case of a RUNNABLE task which is switching its
* current boost group.
*/
/* Move task from src to dst boost group */
tasks = bg->group[src_idx].tasks - 1;
bg->group[src_idx].tasks = max(0, tasks);
bg->group[dst_idx].tasks += 1;
/* Update boost hold start for this group */
now = sched_clock_cpu(cpu);
bg->group[dst_idx].ts = now;
/* Force boost group re-evaluation at next boost check */
bg->boost_ts = now - SCHEDTUNE_BOOST_HOLD_NS;
raw_spin_unlock(&bg->lock);
task_rq_unlock(rq, task, &rq_flags);
}
}
static int
boost_write(struct cgroup_subsys_state *css, struct cftype *cft,
s64 boost)
{
struct schedtune *st = css_st(css);
if (boost < 0 || boost > 100)
return -EINVAL;
st->boost = boost;
/* Update CPU boost */
schedtune_boostgroup_update(st->idx, st->boost);
return 0;
}
static struct cftype files[] = {
#ifdef CONFIG_SCHED_WALT
{
.name = "sched_boost_no_override",
.read_u64 = sched_boost_override_read,
.write_u64 = sched_boost_override_write,
},
{
.name = "colocate",
.read_u64 = sched_colocate_read,
.write_u64 = sched_colocate_write,
},
#endif
{
.name = "boost",
.read_s64 = boost_read,
.write_s64 = boost_write,
},
{
.name = "prefer_idle",
.read_u64 = prefer_idle_read,
.write_u64 = prefer_idle_write,
},
{ } /* terminate */
};
static void
schedtune_boostgroup_init(struct schedtune *st, int idx)
{
struct boost_groups *bg;
int cpu;
/* Initialize per CPUs boost group support */
for_each_possible_cpu(cpu) {
bg = &per_cpu(cpu_boost_groups, cpu);
bg->group[idx].boost = 0;
bg->group[idx].valid = true;
bg->group[idx].ts = 0;
}
/* Keep track of allocated boost groups */
allocated_group[idx] = st;
st->idx = idx;
}
static struct cgroup_subsys_state *
schedtune_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct schedtune *st;
int idx;
if (!parent_css)
return &root_schedtune.css;
/* Allow only single level hierachies */
if (parent_css != &root_schedtune.css) {
pr_err("Nested SchedTune boosting groups not allowed\n");
return ERR_PTR(-ENOMEM);
}
/* Allow only a limited number of boosting groups */
for (idx = 1; idx < BOOSTGROUPS_COUNT; ++idx)
if (!allocated_group[idx])
break;
if (idx == BOOSTGROUPS_COUNT) {
pr_err("Trying to create more than %d SchedTune boosting groups\n",
BOOSTGROUPS_COUNT);
return ERR_PTR(-ENOSPC);
}
st = kzalloc(sizeof(*st), GFP_KERNEL);
if (!st)
goto out;
/* Initialize per CPUs boost group support */
init_sched_boost(st);
schedtune_boostgroup_init(st, idx);
return &st->css;
out:
return ERR_PTR(-ENOMEM);
}
static void
schedtune_boostgroup_release(struct schedtune *st)
{
struct boost_groups *bg;
int cpu;
/* Reset per CPUs boost group support */
for_each_possible_cpu(cpu) {
bg = &per_cpu(cpu_boost_groups, cpu);
bg->group[st->idx].valid = false;
bg->group[st->idx].boost = 0;
}
/* Keep track of allocated boost groups */
allocated_group[st->idx] = NULL;
}
static void
schedtune_css_free(struct cgroup_subsys_state *css)
{
struct schedtune *st = css_st(css);
/* Release per CPUs boost group support */
schedtune_boostgroup_release(st);
kfree(st);
}
struct cgroup_subsys schedtune_cgrp_subsys = {
.css_alloc = schedtune_css_alloc,
.css_free = schedtune_css_free,
.attach = schedtune_attach,
.can_attach = schedtune_can_attach,
.cancel_attach = schedtune_cancel_attach,
.legacy_cftypes = files,
.early_init = 1,
};
static inline void
schedtune_init_cgroups(void)
{
struct boost_groups *bg;
int cpu;
/* Initialize the per CPU boost groups */
for_each_possible_cpu(cpu) {
bg = &per_cpu(cpu_boost_groups, cpu);
memset(bg, 0, sizeof(struct boost_groups));
bg->group[0].valid = true;
raw_spin_lock_init(&bg->lock);
}
pr_info("schedtune: configured to support %d boost groups\n",
BOOSTGROUPS_COUNT);
schedtune_initialized = true;
}
/*
* Initialize the cgroup structures
*/
static int
schedtune_init(void)
{
schedtune_spc_rdiv = reciprocal_value(100);
schedtune_init_cgroups();
return 0;
}
postcore_initcall(schedtune_init);
Reference in a new issue View git blame Copy permalink