linux-stable/include/linux/sched/topology.h
Patrick Bellasi 69842cba9a sched/uclamp: Add CPU's clamp buckets refcounting
Utilization clamping allows to clamp the CPU's utilization within a
[util_min, util_max] range, depending on the set of RUNNABLE tasks on
that CPU. Each task references two "clamp buckets" defining its minimum
and maximum (util_{min,max}) utilization "clamp values". A CPU's clamp
bucket is active if there is at least one RUNNABLE tasks enqueued on
that CPU and refcounting that bucket.

When a task is {en,de}queued {on,from} a rq, the set of active clamp
buckets on that CPU can change. If the set of active clamp buckets
changes for a CPU a new "aggregated" clamp value is computed for that
CPU. This is because each clamp bucket enforces a different utilization
clamp value.

Clamp values are always MAX aggregated for both util_min and util_max.
This ensures that no task can affect the performance of other
co-scheduled tasks which are more boosted (i.e. with higher util_min
clamp) or less capped (i.e. with higher util_max clamp).

A task has:
   task_struct::uclamp[clamp_id]::bucket_id
to track the "bucket index" of the CPU's clamp bucket it refcounts while
enqueued, for each clamp index (clamp_id).

A runqueue has:
   rq::uclamp[clamp_id]::bucket[bucket_id].tasks
to track how many RUNNABLE tasks on that CPU refcount each
clamp bucket (bucket_id) of a clamp index (clamp_id).
It also has a:
   rq::uclamp[clamp_id]::bucket[bucket_id].value
to track the clamp value of each clamp bucket (bucket_id) of a clamp
index (clamp_id).

The rq::uclamp::bucket[clamp_id][] array is scanned every time it's
needed to find a new MAX aggregated clamp value for a clamp_id. This
operation is required only when it's dequeued the last task of a clamp
bucket tracking the current MAX aggregated clamp value. In this case,
the CPU is either entering IDLE or going to schedule a less boosted or
more clamped task.
The expected number of different clamp values configured at build time
is small enough to fit the full unordered array into a single cache
line, for configurations of up to 7 buckets.

Add to struct rq the basic data structures required to refcount the
number of RUNNABLE tasks for each clamp bucket. Add also the max
aggregation required to update the rq's clamp value at each
enqueue/dequeue event.

Use a simple linear mapping of clamp values into clamp buckets.
Pre-compute and cache bucket_id to avoid integer divisions at
enqueue/dequeue time.

Signed-off-by: Patrick Bellasi <patrick.bellasi@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alessio Balsini <balsini@android.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Perret <quentin.perret@arm.com>
Cc: Rafael J . Wysocki <rafael.j.wysocki@intel.com>
Cc: Steve Muckle <smuckle@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Todd Kjos <tkjos@google.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Link: https://lkml.kernel.org/r/20190621084217.8167-2-patrick.bellasi@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-06-24 19:23:44 +02:00

223 lines
6 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SCHED_TOPOLOGY_H
#define _LINUX_SCHED_TOPOLOGY_H
#include <linux/topology.h>
#include <linux/sched/idle.h>
/*
* sched-domains (multiprocessor balancing) declarations:
*/
#ifdef CONFIG_SMP
#define SD_LOAD_BALANCE 0x0001 /* Do load balancing on this domain. */
#define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */
#define SD_BALANCE_EXEC 0x0004 /* Balance on exec */
#define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */
#define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */
#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */
#define SD_ASYM_CPUCAPACITY 0x0040 /* Domain members have different CPU capacities */
#define SD_SHARE_CPUCAPACITY 0x0080 /* Domain members share CPU capacity */
#define SD_SHARE_POWERDOMAIN 0x0100 /* Domain members share power domain */
#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share CPU pkg resources */
#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */
#define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */
#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */
#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */
#define SD_NUMA 0x4000 /* cross-node balancing */
#ifdef CONFIG_SCHED_SMT
static inline int cpu_smt_flags(void)
{
return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
}
#endif
#ifdef CONFIG_SCHED_MC
static inline int cpu_core_flags(void)
{
return SD_SHARE_PKG_RESOURCES;
}
#endif
#ifdef CONFIG_NUMA
static inline int cpu_numa_flags(void)
{
return SD_NUMA;
}
#endif
extern int arch_asym_cpu_priority(int cpu);
struct sched_domain_attr {
int relax_domain_level;
};
#define SD_ATTR_INIT (struct sched_domain_attr) { \
.relax_domain_level = -1, \
}
extern int sched_domain_level_max;
struct sched_group;
struct sched_domain_shared {
atomic_t ref;
atomic_t nr_busy_cpus;
int has_idle_cores;
};
struct sched_domain {
/* These fields must be setup */
struct sched_domain __rcu *parent; /* top domain must be null terminated */
struct sched_domain __rcu *child; /* bottom domain must be null terminated */
struct sched_group *groups; /* the balancing groups of the domain */
unsigned long min_interval; /* Minimum balance interval ms */
unsigned long max_interval; /* Maximum balance interval ms */
unsigned int busy_factor; /* less balancing by factor if busy */
unsigned int imbalance_pct; /* No balance until over watermark */
unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */
int nohz_idle; /* NOHZ IDLE status */
int flags; /* See SD_* */
int level;
/* Runtime fields. */
unsigned long last_balance; /* init to jiffies. units in jiffies */
unsigned int balance_interval; /* initialise to 1. units in ms. */
unsigned int nr_balance_failed; /* initialise to 0 */
/* idle_balance() stats */
u64 max_newidle_lb_cost;
unsigned long next_decay_max_lb_cost;
u64 avg_scan_cost; /* select_idle_sibling */
#ifdef CONFIG_SCHEDSTATS
/* load_balance() stats */
unsigned int lb_count[CPU_MAX_IDLE_TYPES];
unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES];
/* Active load balancing */
unsigned int alb_count;
unsigned int alb_failed;
unsigned int alb_pushed;
/* SD_BALANCE_EXEC stats */
unsigned int sbe_count;
unsigned int sbe_balanced;
unsigned int sbe_pushed;
/* SD_BALANCE_FORK stats */
unsigned int sbf_count;
unsigned int sbf_balanced;
unsigned int sbf_pushed;
/* try_to_wake_up() stats */
unsigned int ttwu_wake_remote;
unsigned int ttwu_move_affine;
unsigned int ttwu_move_balance;
#endif
#ifdef CONFIG_SCHED_DEBUG
char *name;
#endif
union {
void *private; /* used during construction */
struct rcu_head rcu; /* used during destruction */
};
struct sched_domain_shared *shared;
unsigned int span_weight;
/*
* Span of all CPUs in this domain.
*
* NOTE: this field is variable length. (Allocated dynamically
* by attaching extra space to the end of the structure,
* depending on how many CPUs the kernel has booted up with)
*/
unsigned long span[0];
};
static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
{
return to_cpumask(sd->span);
}
extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new);
/* Allocate an array of sched domains, for partition_sched_domains(). */
cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
bool cpus_share_cache(int this_cpu, int that_cpu);
typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
typedef int (*sched_domain_flags_f)(void);
#define SDTL_OVERLAP 0x01
struct sd_data {
struct sched_domain *__percpu *sd;
struct sched_domain_shared *__percpu *sds;
struct sched_group *__percpu *sg;
struct sched_group_capacity *__percpu *sgc;
};
struct sched_domain_topology_level {
sched_domain_mask_f mask;
sched_domain_flags_f sd_flags;
int flags;
int numa_level;
struct sd_data data;
#ifdef CONFIG_SCHED_DEBUG
char *name;
#endif
};
extern void set_sched_topology(struct sched_domain_topology_level *tl);
#ifdef CONFIG_SCHED_DEBUG
# define SD_INIT_NAME(type) .name = #type
#else
# define SD_INIT_NAME(type)
#endif
#else /* CONFIG_SMP */
struct sched_domain_attr;
static inline void
partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new)
{
}
static inline bool cpus_share_cache(int this_cpu, int that_cpu)
{
return true;
}
#endif /* !CONFIG_SMP */
#ifndef arch_scale_cpu_capacity
static __always_inline
unsigned long arch_scale_cpu_capacity(int cpu)
{
return SCHED_CAPACITY_SCALE;
}
#endif
static inline int task_node(const struct task_struct *p)
{
return cpu_to_node(task_cpu(p));
}
#endif /* _LINUX_SCHED_TOPOLOGY_H */