Commit 79071638 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 changes from Ingo Molnar:
 "The biggest change is a performance improvement on SMP systems:

  | 4 socket 40 core + SMT Westmere box, single 30 sec tbench
  | runs, higher is better:
  |
  | clients     1       2       4        8       16       32       64      128
  |..........................................................................
  | pre        30      41     118      645     3769     6214    12233    14312
  | post      299     603    1211     2418     4697     6847    11606    14557
  |
  | A nice increase in performance.

  which speedup is particularly noticeable on heavily interacting
  few-tasks workloads, so the changes should help desktop-style Xorg
  workloads and interactivity as well, on multi-core CPUs.

  There are also cpuset suspend behavior fixes/restructuring and various
  smaller tweaks."

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: Fix race in task_group()
  sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task
  sched: Reset loop counters if all tasks are pinned and we need to redo load balance
  sched: Reorder 'struct lb_env' members to reduce its size
  sched: Improve scalability via 'CPU buddies', which withstand random perturbations
  cpusets: Remove/update outdated comments
  cpusets, hotplug: Restructure functions that are invoked during hotplug
  cpusets, hotplug: Implement cpuset tree traversal in a helper function
  CPU hotplug, cpusets, suspend: Don't modify cpusets during suspend/resume
  sched/x86: Remove broken power estimation
parents 44a6b844 8323f26c

arch/x86/kernel/cpu/Makefile

+1 −1
Original line number Diff line number Diff line
@@ -14,7 +14,7 @@ CFLAGS_common.o := $(nostackp) 


obj-y			:= intel_cacheinfo.o scattered.o topology.o

obj-y			+= proc.o capflags.o powerflags.o common.o

obj-y			+= vmware.o hypervisor.o sched.o mshyperv.o

obj-y			+= vmware.o hypervisor.o mshyperv.o

obj-y			+= rdrand.o

obj-y			+= match.o

arch/x86/kernel/cpu/sched.c

deleted100644 → 0
+0 −55
Original line number Diff line number Diff line 
#include <linux/sched.h>

#include <linux/math64.h>

#include <linux/percpu.h>

#include <linux/irqflags.h>



#include <asm/cpufeature.h>

#include <asm/processor.h>



#ifdef CONFIG_SMP



static DEFINE_PER_CPU(struct aperfmperf, old_perf_sched);



static unsigned long scale_aperfmperf(void)

{

	struct aperfmperf val, *old = &__get_cpu_var(old_perf_sched);

	unsigned long ratio, flags;



	local_irq_save(flags);

	get_aperfmperf(&val);

	local_irq_restore(flags);



	ratio = calc_aperfmperf_ratio(old, &val);

	*old = val;



	return ratio;

}



unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)

{

	/*

	 * do aperf/mperf on the cpu level because it includes things

	 * like turbo mode, which are relevant to full cores.

	 */

	if (boot_cpu_has(X86_FEATURE_APERFMPERF))

		return scale_aperfmperf();



	/*

	 * maybe have something cpufreq here

	 */



	return default_scale_freq_power(sd, cpu);

}



unsigned long arch_scale_smt_power(struct sched_domain *sd, int cpu)

{

	/*

	 * aperf/mperf already includes the smt gain

	 */

	if (boot_cpu_has(X86_FEATURE_APERFMPERF))

		return SCHED_LOAD_SCALE;



	return default_scale_smt_power(sd, cpu);

}



#endif

include/linux/cpuset.h

+2 −2
Original line number Diff line number Diff line
@@ -20,7 +20,7 @@ extern int number_of_cpusets; /* How many cpusets are defined in system? */ 


extern int cpuset_init(void);

extern void cpuset_init_smp(void);

extern void cpuset_update_active_cpus(void);

extern void cpuset_update_active_cpus(bool cpu_online);

extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);

extern void cpuset_cpus_allowed_fallback(struct task_struct *p);

extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
@@ -124,7 +124,7 @@ static inline void set_mems_allowed(nodemask_t nodemask) 
static inline int cpuset_init(void) { return 0; }

static inline void cpuset_init_smp(void) {}



static inline void cpuset_update_active_cpus(void)

static inline void cpuset_update_active_cpus(bool cpu_online)

{

	partition_sched_domains(1, NULL, NULL);

}

include/linux/init_task.h

+11 −1
Original line number Diff line number Diff line
@@ -123,6 +123,15 @@ extern struct group_info init_groups; 


extern struct cred init_cred;



extern struct task_group root_task_group;



#ifdef CONFIG_CGROUP_SCHED

# define INIT_CGROUP_SCHED(tsk)						\

	.sched_task_group = &root_task_group,

#else

# define INIT_CGROUP_SCHED(tsk)

#endif



#ifdef CONFIG_PERF_EVENTS

# define INIT_PERF_EVENTS(tsk)						\

	.perf_event_mutex = 						\
@@ -161,6 +170,7 @@ extern struct cred init_cred; 
	},								\

	.tasks		= LIST_HEAD_INIT(tsk.tasks),			\

	INIT_PUSHABLE_TASKS(tsk)					\

	INIT_CGROUP_SCHED(tsk)						\

	.ptraced	= LIST_HEAD_INIT(tsk.ptraced),			\

	.ptrace_entry	= LIST_HEAD_INIT(tsk.ptrace_entry),		\

	.real_parent	= &tsk,						\

include/linux/sched.h

+5 −1
Original line number Diff line number Diff line
@@ -949,6 +949,7 @@ struct sched_domain { 
	unsigned int smt_gain;

	int flags;			/* See SD_* */

	int level;

	int idle_buddy;			/* cpu assigned to select_idle_sibling() */



	/* Runtime fields. */

	unsigned long last_balance;	/* init to jiffies. units in jiffies */
@@ -1244,6 +1245,9 @@ struct task_struct { 
	const struct sched_class *sched_class;

	struct sched_entity se;

	struct sched_rt_entity rt;

#ifdef CONFIG_CGROUP_SCHED

	struct task_group *sched_task_group;

#endif



#ifdef CONFIG_PREEMPT_NOTIFIERS

	/* list of struct preempt_notifier: */
@@ -2721,7 +2725,7 @@ extern int sched_group_set_rt_period(struct task_group *tg, 
extern long sched_group_rt_period(struct task_group *tg);

extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);

#endif

#endif

#endif /* CONFIG_CGROUP_SCHED */



extern int task_can_switch_user(struct user_struct *up,

					struct task_struct *tsk);

CRA Git | Maintained and supported by SUSTech CRA and CCSE