/* *  kernel/sched/core.c * *  Kernel scheduler and related syscalls * *  Copyright (C) 1991-2002  Linus Torvalds * *  1996-12-23  Modified by Dave Grothe to fix bugs in semaphores and *		make semaphores SMP safe *  1998-11-19	Implemented schedule_timeout() and related stuff *		by Andrea Arcangeli *  2002-01-04	New ultra-scalable O(1) scheduler by Ingo Molnar: *		hybrid priority-list and round-robin design with *		an array-switch method of distributing timeslices *		and per-CPU runqueues.  Cleanups and useful suggestions *		by Davide Libenzi, preemptible kernel bits by Robert Love. *  2003-09-03	Interactivity tuning by Con Kolivas. *  2004-04-02	Scheduler domains code by Nick Piggin *  2007-04-15  Work begun on replacing all interactivity tuning with a *              fair scheduling design by Con Kolivas. *  2007-05-05  Load balancing (smp-nice) and other improvements *              by Peter Williams *  2007-05-06  Interactivity improvements to CFS by Mike Galbraith *  2007-07-01  Group scheduling enhancements by Srivatsa Vaddagiri *  2007-11-29  RT balancing improvements by Steven Rostedt, Gregory Haskins, *              Thomas Gleixner, Mike Kravetz */ #include <linux/mm.h>#include <linux/module.h>#include <linux/nmi.h>#include <linux/init.h>#include <linux/uaccess.h>#include <linux/highmem.h>#include <asm/mmu_context.h>#include <linux/interrupt.h>#include <linux/capability.h>#include <linux/completion.h>#include <linux/kernel_stat.h>#include <linux/debug_locks.h>#include <linux/perf_event.h>#include <linux/security.h>#include <linux/notifier.h>#include <linux/profile.h>#include <linux/freezer.h>#include <linux/vmalloc.h>#include <linux/blkdev.h>#include <linux/delay.h>#include <linux/pid_namespace.h>#include <linux/smp.h>#include <linux/threads.h>#include <linux/timer.h>#include <linux/rcupdate.h>#include <linux/cpu.h>#include <linux/cpuset.h>#include <linux/percpu.h>#include <linux/proc_fs.h>#include <linux/seq_file.h>#include <linux/sysctl.h>#include <linux/syscalls.h>#include <linux/times.h>#include <linux/tsacct_kern.h>#include <linux/kprobes.h>#include <linux/delayacct.h>#include <linux/unistd.h>#include <linux/pagemap.h>#include <linux/hrtimer.h>#include <linux/tick.h>#include <linux/debugfs.h>#include <linux/ctype.h>#include <linux/ftrace.h>#include <linux/slab.h>#include <linux/init_task.h>#include <linux/binfmts.h>#include <linux/context_tracking.h>#include <linux/compiler.h> #include <asm/switch_to.h>#include <asm/tlb.h>#include <asm/irq_regs.h>#include <asm/mutex.h>#ifdef CONFIG_PARAVIRT#include <asm/paravirt.h>#endif #include "sched.h"#include "../workqueue_internal.h"#include "../smpboot.h" #define CREATE_TRACE_POINTS#include <trace/events/sched.h> DEFINE_MUTEX(sched_domains_mutex);DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); static void update_rq_clock_task(struct rq *rq, s64 delta); void update_rq_clock(struct rq *rq){	s64 delta; 	lockdep_assert_held(&rq->lock); 	if (rq->clock_skip_update & RQCF_ACT_SKIP)		return; 	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;	if (delta < 0)		return;	rq->clock += delta;	update_rq_clock_task(rq, delta);} /* * Debugging: various feature bits */ #define SCHED_FEAT(name, enabled)	\	(1UL << __SCHED_FEAT_##name) * enabled | const_debug unsigned int sysctl_sched_features =#include "features.h"	0; #undef SCHED_FEAT #ifdef CONFIG_SCHED_DEBUG#define SCHED_FEAT(name, enabled)	\	#name , static const char * const sched_feat_names[] = {#include "features.h"}; #undef SCHED_FEAT static int sched_feat_show(struct seq_file *m, void *v){	int i; 	for (i = 0; i < __SCHED_FEAT_NR; i++) {		if (!(sysctl_sched_features & (1UL << i)))			seq_puts(m, "NO_");		seq_printf(m, "%s ", sched_feat_names[i]);	}	seq_puts(m, "\n"); 	return 0;} #ifdef HAVE_JUMP_LABEL #define jump_label_key__true  STATIC_KEY_INIT_TRUE#define jump_label_key__false STATIC_KEY_INIT_FALSE #define SCHED_FEAT(name, enabled)	\	jump_label_key__##enabled , struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {#include "features.h"}; #undef SCHED_FEAT static void sched_feat_disable(int i){	if (static_key_enabled(&sched_feat_keys[i]))		static_key_slow_dec(&sched_feat_keys[i]);} static void sched_feat_enable(int i){	if (!static_key_enabled(&sched_feat_keys[i]))		static_key_slow_inc(&sched_feat_keys[i]);}#elsestatic void sched_feat_disable(int i) { };static void sched_feat_enable(int i) { };#endif /* HAVE_JUMP_LABEL */ static int sched_feat_set(char *cmp){	int i;	int neg = 0; 	if (strncmp(cmp, "NO_", 3) == 0) {		neg = 1;		cmp += 3;	} 	for (i = 0; i < __SCHED_FEAT_NR; i++) {		if (strcmp(cmp, sched_feat_names[i]) == 0) {			if (neg) {				sysctl_sched_features &= ~(1UL << i);				sched_feat_disable(i);			} else {				sysctl_sched_features |= (1UL << i);				sched_feat_enable(i);			}			break;		}	} 	return i;} static ssize_tsched_feat_write(struct file *filp, const char __user *ubuf,		size_t cnt, loff_t *ppos){	char buf[64];	char *cmp;	int i;	struct inode *inode; 	if (cnt > 63)		cnt = 63; 	if (copy_from_user(&buf, ubuf, cnt))		return -EFAULT; 	buf[cnt] = 0;	cmp = strstrip(buf); 	/* Ensure the static_key remains in a consistent state */	inode = file_inode(filp);	mutex_lock(&inode->i_mutex);	i = sched_feat_set(cmp);	mutex_unlock(&inode->i_mutex);	if (i == __SCHED_FEAT_NR)		return -EINVAL; 	*ppos += cnt; 	return cnt;} static int sched_feat_open(struct inode *inode, struct file *filp){	return single_open(filp, sched_feat_show, NULL);} static const struct file_operations sched_feat_fops = {	.open		= sched_feat_open,	.write		= sched_feat_write,	.read		= seq_read,	.llseek		= seq_lseek,	.release	= single_release,}; static __init int sched_init_debug(void){	debugfs_create_file("sched_features", 0644, NULL, NULL,			&sched_feat_fops); 	return 0;}late_initcall(sched_init_debug);#endif /* CONFIG_SCHED_DEBUG */ /* * Number of tasks to iterate in a single balance run. * Limited because this is done with IRQs disabled. */const_debug unsigned int sysctl_sched_nr_migrate = 32; /* * period over which we average the RT time consumption, measured * in ms. * * default: 1s */const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC; /* * period over which we measure -rt task cpu usage in us. * default: 1s */unsigned int sysctl_sched_rt_period = 1000000; __read_mostly int scheduler_running; /* * part of the period that we allow rt tasks to run in us. * default: 0.95s */int sysctl_sched_rt_runtime = 950000; /* cpus with isolated domains */cpumask_var_t cpu_isolated_map; /* * this_rq_lock - lock this runqueue and disable interrupts. */static struct rq *this_rq_lock(void)	__acquires(rq->lock){	struct rq *rq; 	local_irq_disable();	rq = this_rq();	raw_spin_lock(&rq->lock); 	return rq;} #ifdef CONFIG_SCHED_HRTICK/* * Use HR-timers to deliver accurate preemption points. */ static void hrtick_clear(struct rq *rq){	if (hrtimer_active(&rq->hrtick_timer))		hrtimer_cancel(&rq->hrtick_timer);} /* * High-resolution timer tick. * Runs from hardirq context with interrupts disabled. */static enum hrtimer_restart hrtick(struct hrtimer *timer){	struct rq *rq = container_of(timer, struct rq, hrtick_timer); 	WARN_ON_ONCE(cpu_of(rq) != smp_processor_id()); 	raw_spin_lock(&rq->lock);	update_rq_clock(rq);	rq->curr->sched_class->task_tick(rq, rq->curr, 1);	raw_spin_unlock(&rq->lock); 	return HRTIMER_NORESTART;} #ifdef CONFIG_SMP static void __hrtick_restart(struct rq *rq){	struct hrtimer *timer = &rq->hrtick_timer; 	hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);} /* * called from hardirq (IPI) context */static void __hrtick_start(void *arg){	struct rq *rq = arg; 	raw_spin_lock(&rq->lock);	__hrtick_restart(rq);	rq->hrtick_csd_pending = 0;	raw_spin_unlock(&rq->lock);} /* * Called to set the hrtick timer state. * * called with rq->lock held and irqs disabled */void hrtick_start(struct rq *rq, u64 delay){	struct hrtimer *timer = &rq->hrtick_timer;	ktime_t time;	s64 delta; 	/*	 * Don't schedule slices shorter than 10000ns, that just	 * doesn't make sense and can cause timer DoS.	 */	delta = max_t(s64, delay, 10000LL);	time = ktime_add_ns(timer->base->get_time(), delta); 	hrtimer_set_expires(timer, time); 	if (rq == this_rq()) {		__hrtick_restart(rq);	} else if (!rq->hrtick_csd_pending) {		smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);		rq->hrtick_csd_pending = 1;	}} static inthotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu){	int cpu = (int)(long)hcpu; 	switch (action) {	case CPU_UP_CANCELED:	case CPU_UP_CANCELED_FROZEN:	case CPU_DOWN_PREPARE:	case CPU_DOWN_PREPARE_FROZEN:	case CPU_DEAD:	case CPU_DEAD_FROZEN:		hrtick_clear(cpu_rq(cpu));		return NOTIFY_OK;	} 	return NOTIFY_DONE;} static __init void init_hrtick(void){	hotcpu_notifier(hotplug_hrtick, 0);}#else/* * Called to set the hrtick timer state. * * called with rq->lock held and irqs disabled */void hrtick_start(struct rq *rq, u64 delay){	/*	 * Don't schedule slices shorter than 10000ns, that just	 * doesn't make sense. Rely on vruntime for fairness.	 */	delay = max_t(u64, delay, 10000LL);	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),		      HRTIMER_MODE_REL_PINNED);} static inline void init_hrtick(void){}#endif /* CONFIG_SMP */ static void init_rq_hrtick(struct rq *rq){#ifdef CONFIG_SMP	rq->hrtick_csd_pending = 0; 	rq->hrtick_csd.flags = 0;	rq->hrtick_csd.func = __hrtick_start;	rq->hrtick_csd.info = rq;#endif 	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);	rq->hrtick_timer.function = hrtick;}#else	/* CONFIG_SCHED_HRTICK */static inline void hrtick_clear(struct rq *rq){} static inline void init_rq_hrtick(struct rq *rq){} static inline void init_hrtick(void){}#endif	/* CONFIG_SCHED_HRTICK */ /* * cmpxchg based fetch_or, macro so it works for different integer types */#define fetch_or(ptr, val)						\({	typeof(*(ptr)) __old, __val = *(ptr);				\ 	for (;;) {							\ 		__old = cmpxchg((ptr), __val, __val | (val));		\ 		if (__old == __val)					\ 			break;						\ 		__val = __old;						\ 	}								\ 	__old;								\}) #if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)/* * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, * this avoids any races wrt polling state changes and thereby avoids * spurious IPIs. */static bool set_nr_and_not_polling(struct task_struct *p){	struct thread_info *ti = task_thread_info(p);	return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);} /* * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set. * * If this returns true, then the idle task promises to call * sched_ttwu_pending() and reschedule soon. */static bool set_nr_if_polling(struct task_struct *p){	struct thread_info *ti = task_thread_info(p);	typeof(ti->flags) old, val = READ_ONCE(ti->flags); 	for (;;) {		if (!(val & _TIF_POLLING_NRFLAG))			return false;		if (val & _TIF_NEED_RESCHED)			return true;		old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED);

Lines 1–500 of 8460. Load more