mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-24 09:50:04 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
Pull scheduler updates from Ingo Molnar: - MAINTAINERS: Add Mark Rutland as perf submaintainer, Juri Lelli and Vincent Guittot as scheduler submaintainers. Add Dietmar Eggemann, Steven Rostedt, Ben Segall and Mel Gorman as scheduler reviewers. As perf and the scheduler is getting bigger and more complex, document the status quo of current responsibilities and interests, and spread the review pain^H^H^H^H fun via an increase in the Cc: linecount generated by scripts/get_maintainer.pl. :-) - Add another series of patches that brings the -rt (PREEMPT_RT) tree closer to mainline: split the monolithic CONFIG_PREEMPT dependencies into a new CONFIG_PREEMPTION category that will allow the eventual introduction of CONFIG_PREEMPT_RT. Still a few more hundred patches to go though. - Extend the CPU cgroup controller with uclamp.min and uclamp.max to allow the finer shaping of CPU bandwidth usage. - Micro-optimize energy-aware wake-ups from O(CPUS^2) to O(CPUS). - Improve the behavior of high CPU count, high thread count applications running under cpu.cfs_quota_us constraints. - Improve balancing with SCHED_IDLE (SCHED_BATCH) tasks present. - Improve CPU isolation housekeeping CPU allocation NUMA locality. - Fix deadline scheduler bandwidth calculations and logic when cpusets rebuilds the topology, or when it gets deadline-throttled while it's being offlined. - Convert the cpuset_mutex to percpu_rwsem, to allow it to be used from setscheduler() system calls without creating global serialization. Add new synchronization between cpuset topology-changing events and the deadline acceptance tests in setscheduler(), which were broken before. - Rework the active_mm state machine to be less confusing and more optimal. - Rework (simplify) the pick_next_task() slowpath. - Improve load-balancing on AMD EPYC systems. - ... and misc cleanups, smaller fixes and improvements - please see the Git log for more details. * 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits) sched/psi: Correct overly pessimistic size calculation sched/fair: Speed-up energy-aware wake-ups sched/uclamp: Always use 'enum uclamp_id' for clamp_id values sched/uclamp: Update CPU's refcount on TG's clamp changes sched/uclamp: Use TG's clamps to restrict TASK's clamps sched/uclamp: Propagate system defaults to the root group sched/uclamp: Propagate parent clamps sched/uclamp: Extend CPU's cgroup controller sched/topology: Improve load balancing on AMD EPYC systems arch, ia64: Make NUMA select SMP sched, perf: MAINTAINERS update, add submaintainers and reviewers sched/fair: Use rq_lock/unlock in online_fair_sched_group cpufreq: schedutil: fix equation in comment sched: Rework pick_next_task() slow-path sched: Allow put_prev_task() to drop rq->lock sched/fair: Expose newidle_balance() sched: Add task_struct pointer to sched_class::set_curr_task sched: Rework CPU hotplug task selection sched/{rt,deadline}: Fix set_next_task vs pick_next_task sched: Fix kerneldoc comment for ia64_set_curr_task ...
231 lines
5.5 KiB
C
231 lines
5.5 KiB
C
/*
|
|
* include/linux/topology.h
|
|
*
|
|
* Written by: Matthew Dobson, IBM Corporation
|
|
*
|
|
* Copyright (C) 2002, IBM Corp.
|
|
*
|
|
* All rights reserved.
|
|
*
|
|
* 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, GOOD TITLE or
|
|
* NON INFRINGEMENT. See the GNU General Public License for more
|
|
* details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write to the Free Software
|
|
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|
*
|
|
* Send feedback to <colpatch@us.ibm.com>
|
|
*/
|
|
#ifndef _LINUX_TOPOLOGY_H
|
|
#define _LINUX_TOPOLOGY_H
|
|
|
|
#include <linux/arch_topology.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/bitops.h>
|
|
#include <linux/mmzone.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/percpu.h>
|
|
#include <asm/topology.h>
|
|
|
|
#ifndef nr_cpus_node
|
|
#define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node))
|
|
#endif
|
|
|
|
#define for_each_node_with_cpus(node) \
|
|
for_each_online_node(node) \
|
|
if (nr_cpus_node(node))
|
|
|
|
int arch_update_cpu_topology(void);
|
|
|
|
/* Conform to ACPI 2.0 SLIT distance definitions */
|
|
#define LOCAL_DISTANCE 10
|
|
#define REMOTE_DISTANCE 20
|
|
#ifndef node_distance
|
|
#define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE)
|
|
#endif
|
|
#ifndef RECLAIM_DISTANCE
|
|
/*
|
|
* If the distance between nodes in a system is larger than RECLAIM_DISTANCE
|
|
* (in whatever arch specific measurement units returned by node_distance())
|
|
* and node_reclaim_mode is enabled then the VM will only call node_reclaim()
|
|
* on nodes within this distance.
|
|
*/
|
|
#define RECLAIM_DISTANCE 30
|
|
#endif
|
|
|
|
/*
|
|
* The following tunable allows platforms to override the default node
|
|
* reclaim distance (RECLAIM_DISTANCE) if remote memory accesses are
|
|
* sufficiently fast that the default value actually hurts
|
|
* performance.
|
|
*
|
|
* AMD EPYC machines use this because even though the 2-hop distance
|
|
* is 32 (3.2x slower than a local memory access) performance actually
|
|
* *improves* if allowed to reclaim memory and load balance tasks
|
|
* between NUMA nodes 2-hops apart.
|
|
*/
|
|
extern int __read_mostly node_reclaim_distance;
|
|
|
|
#ifndef PENALTY_FOR_NODE_WITH_CPUS
|
|
#define PENALTY_FOR_NODE_WITH_CPUS (1)
|
|
#endif
|
|
|
|
#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
|
|
DECLARE_PER_CPU(int, numa_node);
|
|
|
|
#ifndef numa_node_id
|
|
/* Returns the number of the current Node. */
|
|
static inline int numa_node_id(void)
|
|
{
|
|
return raw_cpu_read(numa_node);
|
|
}
|
|
#endif
|
|
|
|
#ifndef cpu_to_node
|
|
static inline int cpu_to_node(int cpu)
|
|
{
|
|
return per_cpu(numa_node, cpu);
|
|
}
|
|
#endif
|
|
|
|
#ifndef set_numa_node
|
|
static inline void set_numa_node(int node)
|
|
{
|
|
this_cpu_write(numa_node, node);
|
|
}
|
|
#endif
|
|
|
|
#ifndef set_cpu_numa_node
|
|
static inline void set_cpu_numa_node(int cpu, int node)
|
|
{
|
|
per_cpu(numa_node, cpu) = node;
|
|
}
|
|
#endif
|
|
|
|
#else /* !CONFIG_USE_PERCPU_NUMA_NODE_ID */
|
|
|
|
/* Returns the number of the current Node. */
|
|
#ifndef numa_node_id
|
|
static inline int numa_node_id(void)
|
|
{
|
|
return cpu_to_node(raw_smp_processor_id());
|
|
}
|
|
#endif
|
|
|
|
#endif /* [!]CONFIG_USE_PERCPU_NUMA_NODE_ID */
|
|
|
|
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
|
|
|
|
/*
|
|
* N.B., Do NOT reference the '_numa_mem_' per cpu variable directly.
|
|
* It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined.
|
|
* Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem().
|
|
*/
|
|
DECLARE_PER_CPU(int, _numa_mem_);
|
|
extern int _node_numa_mem_[MAX_NUMNODES];
|
|
|
|
#ifndef set_numa_mem
|
|
static inline void set_numa_mem(int node)
|
|
{
|
|
this_cpu_write(_numa_mem_, node);
|
|
_node_numa_mem_[numa_node_id()] = node;
|
|
}
|
|
#endif
|
|
|
|
#ifndef node_to_mem_node
|
|
static inline int node_to_mem_node(int node)
|
|
{
|
|
return _node_numa_mem_[node];
|
|
}
|
|
#endif
|
|
|
|
#ifndef numa_mem_id
|
|
/* Returns the number of the nearest Node with memory */
|
|
static inline int numa_mem_id(void)
|
|
{
|
|
return raw_cpu_read(_numa_mem_);
|
|
}
|
|
#endif
|
|
|
|
#ifndef cpu_to_mem
|
|
static inline int cpu_to_mem(int cpu)
|
|
{
|
|
return per_cpu(_numa_mem_, cpu);
|
|
}
|
|
#endif
|
|
|
|
#ifndef set_cpu_numa_mem
|
|
static inline void set_cpu_numa_mem(int cpu, int node)
|
|
{
|
|
per_cpu(_numa_mem_, cpu) = node;
|
|
_node_numa_mem_[cpu_to_node(cpu)] = node;
|
|
}
|
|
#endif
|
|
|
|
#else /* !CONFIG_HAVE_MEMORYLESS_NODES */
|
|
|
|
#ifndef numa_mem_id
|
|
/* Returns the number of the nearest Node with memory */
|
|
static inline int numa_mem_id(void)
|
|
{
|
|
return numa_node_id();
|
|
}
|
|
#endif
|
|
|
|
#ifndef node_to_mem_node
|
|
static inline int node_to_mem_node(int node)
|
|
{
|
|
return node;
|
|
}
|
|
#endif
|
|
|
|
#ifndef cpu_to_mem
|
|
static inline int cpu_to_mem(int cpu)
|
|
{
|
|
return cpu_to_node(cpu);
|
|
}
|
|
#endif
|
|
|
|
#endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */
|
|
|
|
#ifndef topology_physical_package_id
|
|
#define topology_physical_package_id(cpu) ((void)(cpu), -1)
|
|
#endif
|
|
#ifndef topology_die_id
|
|
#define topology_die_id(cpu) ((void)(cpu), -1)
|
|
#endif
|
|
#ifndef topology_core_id
|
|
#define topology_core_id(cpu) ((void)(cpu), 0)
|
|
#endif
|
|
#ifndef topology_sibling_cpumask
|
|
#define topology_sibling_cpumask(cpu) cpumask_of(cpu)
|
|
#endif
|
|
#ifndef topology_core_cpumask
|
|
#define topology_core_cpumask(cpu) cpumask_of(cpu)
|
|
#endif
|
|
#ifndef topology_die_cpumask
|
|
#define topology_die_cpumask(cpu) cpumask_of(cpu)
|
|
#endif
|
|
|
|
#ifdef CONFIG_SCHED_SMT
|
|
static inline const struct cpumask *cpu_smt_mask(int cpu)
|
|
{
|
|
return topology_sibling_cpumask(cpu);
|
|
}
|
|
#endif
|
|
|
|
static inline const struct cpumask *cpu_cpu_mask(int cpu)
|
|
{
|
|
return cpumask_of_node(cpu_to_node(cpu));
|
|
}
|
|
|
|
|
|
#endif /* _LINUX_TOPOLOGY_H */
|