Commit 46e0d28b authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull scheduler updates from Ingo Molnar:
 "The main scheduler changes in this cycle were:

   - NUMA balancing improvements (Mel Gorman)

   - Further load tracking improvements (Patrick Bellasi)

   - Various NOHZ balancing cleanups and optimizations (Peter Zijlstra)

   - Improve blocked load handling, in particular we can now reduce and
     eventually stop periodic load updates on 'very idle' CPUs. (Vincent
     Guittot)

   - On isolated CPUs offload the final 1Hz scheduler tick as well, plus
     related cleanups and reorganization. (Frederic Weisbecker)

   - Core scheduler code cleanups (Ingo Molnar)"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (45 commits)
  sched/core: Update preempt_notifier_key to modern API
  sched/cpufreq: Rate limits for SCHED_DEADLINE
  sched/fair: Update util_est only on util_avg updates
  sched/cpufreq/schedutil: Use util_est for OPP selection
  sched/fair: Use util_est in LB and WU paths
  sched/fair: Add util_est on top of PELT
  sched/core: Remove TASK_ALL
  sched/completions: Use bool in try_wait_for_completion()
  sched/fair: Update blocked load when newly idle
  sched/fair: Move idle_balance()
  sched/nohz: Merge CONFIG_NO_HZ_COMMON blocks
  sched/fair: Move rebalance_domains()
  sched/nohz: Optimize nohz_idle_balance()
  sched/fair: Reduce the periodic update duration
  sched/nohz: Stop NOHZ stats when decayed
  sched/cpufreq: Provide migration hint
  sched/nohz: Clean up nohz enter/exit
  sched/fair: Update blocked load from NEWIDLE
  sched/fair: Add NOHZ stats balancing
  sched/fair: Restructure nohz_balance_kick()
  ...
parents 86bbbeba b7203428

Documentation/admin-guide/kernel-parameters.txt

+11 −0
Original line number Diff line number Diff line
@@ -1766,6 +1766,17 @@ 


			nohz

			  Disable the tick when a single task runs.



			  A residual 1Hz tick is offloaded to workqueues, which you

			  need to affine to housekeeping through the global

			  workqueue's affinity configured via the

			  /sys/devices/virtual/workqueue/cpumask sysfs file, or

			  by using the 'domain' flag described below.



			  NOTE: by default the global workqueue runs on all CPUs,

			  so to protect individual CPUs the 'cpumask' file has to

			  be configured manually after bootup.



			domain

			  Isolate from the general SMP balancing and scheduling

			  algorithms. Note that performing domain isolation this way

include/linux/sched.h

+29 −1
Original line number Diff line number Diff line
@@ -93,7 +93,6 @@ struct task_group; 


/* Convenience macros for the sake of wake_up(): */

#define TASK_NORMAL			(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)

#define TASK_ALL			(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)



/* get_task_state(): */

#define TASK_REPORT			(TASK_RUNNING | TASK_INTERRUPTIBLE | \
@@ -275,6 +274,34 @@ struct load_weight { 
	u32				inv_weight;

};



/**

 * struct util_est - Estimation utilization of FAIR tasks

 * @enqueued: instantaneous estimated utilization of a task/cpu

 * @ewma:     the Exponential Weighted Moving Average (EWMA)

 *            utilization of a task

 *

 * Support data structure to track an Exponential Weighted Moving Average

 * (EWMA) of a FAIR task's utilization. New samples are added to the moving

 * average each time a task completes an activation. Sample's weight is chosen

 * so that the EWMA will be relatively insensitive to transient changes to the

 * task's workload.

 *

 * The enqueued attribute has a slightly different meaning for tasks and cpus:

 * - task:   the task's util_avg at last task dequeue time

 * - cfs_rq: the sum of util_est.enqueued for each RUNNABLE task on that CPU

 * Thus, the util_est.enqueued of a task represents the contribution on the

 * estimated utilization of the CPU where that task is currently enqueued.

 *

 * Only for tasks we track a moving average of the past instantaneous

 * estimated utilization. This allows to absorb sporadic drops in utilization

 * of an otherwise almost periodic task.

 */

struct util_est {

	unsigned int			enqueued;

	unsigned int			ewma;

#define UTIL_EST_WEIGHT_SHIFT		2

};



/*

 * The load_avg/util_avg accumulates an infinite geometric series

 * (see __update_load_avg() in kernel/sched/fair.c).
@@ -336,6 +363,7 @@ struct sched_avg { 
	unsigned long			load_avg;

	unsigned long			runnable_load_avg;

	unsigned long			util_avg;

	struct util_est			util_est;

};



struct sched_statistics {

include/linux/sched/cpufreq.h

+2 −3
Original line number Diff line number Diff line
@@ -8,9 +8,8 @@ 
 * Interface between cpufreq drivers and the scheduler:

 */



#define SCHED_CPUFREQ_RT	(1U << 0)

#define SCHED_CPUFREQ_DL	(1U << 1)

#define SCHED_CPUFREQ_IOWAIT	(1U << 2)

#define SCHED_CPUFREQ_IOWAIT	(1U << 0)

#define SCHED_CPUFREQ_MIGRATION	(1U << 1)



#ifdef CONFIG_CPU_FREQ

struct update_util_data {

include/linux/sched/deadline.h

+0 −6
Original line number Diff line number Diff line 
/* SPDX-License-Identifier: GPL-2.0 */

#ifndef _LINUX_SCHED_DEADLINE_H

#define _LINUX_SCHED_DEADLINE_H



#include <linux/sched.h>



/*

 * SCHED_DEADLINE tasks has negative priorities, reflecting
@@ -28,5 +24,3 @@ static inline bool dl_time_before(u64 a, u64 b) 
{

	return (s64)(a - b) < 0;

}
 


#endif /* _LINUX_SCHED_DEADLINE_H */

include/linux/sched/isolation.h

+1 −0
Original line number Diff line number Diff line
@@ -12,6 +12,7 @@ enum hk_flags { 
	HK_FLAG_SCHED		= (1 << 3),

	HK_FLAG_TICK		= (1 << 4),

	HK_FLAG_DOMAIN		= (1 << 5),

	HK_FLAG_WQ		= (1 << 6),

};



#ifdef CONFIG_CPU_ISOLATION

CRA Git | Maintained and supported by SUSTech CRA and CCSE