path: root/kernel/sched/syscalls.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 *  kernel/sched/syscalls.c
 *
 *  Core kernel scheduler syscalls related code
 *
 *  Copyright (C) 1991-2002  Linus Torvalds
 *  Copyright (C) 1998-2024  Ingo Molnar, Red Hat
 */
#include <linux/sched.h>
#include <linux/cpuset.h>
#include <linux/sched/debug.h>

#include <uapi/linux/sched/types.h>

#include "sched.h"
#include "autogroup.h"

static inline int __normal_prio(int policy, int rt_prio, int nice)
{
	int prio;

	if (dl_policy(policy))
		prio = MAX_DL_PRIO - 1;
	else if (rt_policy(policy))
		prio = MAX_RT_PRIO - 1 - rt_prio;
	else
		prio = NICE_TO_PRIO(nice);

	return prio;
}

/*
 * Calculate the expected normal priority: i.e. priority
 * without taking RT-inheritance into account. Might be
 * boosted by interactivity modifiers. Changes upon fork,
 * setprio syscalls, and whenever the interactivity
 * estimator recalculates.
 */
static inline int normal_prio(struct task_struct *p)
{
	return __normal_prio(p->policy, p->rt_priority, PRIO_TO_NICE(p->static_prio));
}

/*
 * Calculate the current priority, i.e. the priority
 * taken into account by the scheduler. This value might
 * be boosted by RT tasks, or might be boosted by
 * interactivity modifiers. Will be RT if the task got
 * RT-boosted. If not then it returns p->normal_prio.
 */
static int effective_prio(struct task_struct *p)
{
	p->normal_prio = normal_prio(p);
	/*
	 * If we are RT tasks or we were boosted to RT priority,
	 * keep the priority unchanged. Otherwise, update priority
	 * to the normal priority:
	 */
	if (!rt_or_dl_prio(p->prio))
		return p->normal_prio;
	return p->prio;
}

void set_user_nice(struct task_struct *p, long nice)
{
	int old_prio;

	if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
		return;
	/*
	 * We have to be careful, if called from sys_setpriority(),
	 * the task might be in the middle of scheduling on another CPU.
	 */
	guard(task_rq_lock)(p);

	/*
	 * The RT priorities are set via sched_setscheduler(), but we still
	 * allow the 'normal' nice value to be set - but as expected
	 * it won't have any effect on scheduling until the task is
	 * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR:
	 */
	if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
		p->static_prio = NICE_TO_PRIO(nice);
		return;
	}

	scoped_guard (sched_change, p, DEQUEUE_SAVE) {
		p->static_prio = NICE_TO_PRIO(nice);
		set_load_weight(p, true);
		old_prio = p->prio;
		p->prio = effective_prio(p);
	}
}
EXPORT_SYMBOL(set_user_nice);

/*
 * is_nice_reduction - check if nice value is an actual reduction
 *
 * Similar to can_nice() but does not perform a capability check.
 *
 * @p: task
 * @nice: nice value
 */
static bool is_nice_reduction(const struct task_struct *p, const int nice)
{
	/* Convert nice value [19,-20] to rlimit style value [1,40]: */
	int nice_rlim = nice_to_rlimit(nice);

	return (nice_rlim <= task_rlimit(p, RLIMIT_NICE));
}

/*
 * can_nice - check if a task can reduce its nice value
 * @p: task
 * @nice: nice value
 */
int can_nice(const struct task_struct *p, const int nice)
{
	return is_nice_reduction(p, nice) || capable(CAP_SYS_NICE);
}

#ifdef __ARCH_WANT_SYS_NICE

/*
 * sys_nice - change the priority of the current process.
 * @increment: priority increment
 *
 * sys_setpriority is a more generic, but much slower function that
 * does similar things.
 */
SYSCALL_DEFINE1(nice, int, increment)
{
	long nice, retval;

	/*
	 * Setpriority might change our priority at the same moment.
	 * We don't have to worry. Conceptually one call occurs first
	 * and we have a single winner.
	 */
	increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH);
	nice = task_nice(current) + increment;

	nice = clamp_val(nice, MIN_NICE, MAX_NICE);
	if (increment < 0 && !can_nice(current, nice))
		return -EPERM;

	retval = security_task_setnice(current, nice);
	if (retval)
		return retval;

	set_user_nice(current, nice);
	return 0;
}

#endif /* __ARCH_WANT_SYS_NICE */

/**
 * task_prio - return the priority value of a given task.
 * @p: the task in question.
 *
 * Return: The priority value as seen by users in /proc.
 *
 * sched policy         return value   kernel prio    user prio/nice
 *
 * normal, batch, idle     [0 ... 39]  [100 ... 139]          0/[-20 ... 19]
 * fifo, rr             [-2 ... -100]     [98 ... 0]  [1 ... 99]
 * deadline                     -101             -1           0
 */
int task_prio(const struct task_struct *p)
{
	return p->prio - MAX_RT_PRIO;
}

/**
 * idle_cpu - is a given CPU idle currently?
 * @cpu: the processor in question.
 *
 * Return: 1 if the CPU is currently idle. 0 otherwise.
 */
int idle_cpu(int cpu)
{
	return idle_rq(cpu_rq(cpu));
}

/**
 * idle_task - return the idle task for a given CPU.
 * @cpu: the processor in question.
 *
 * Return: The idle task for the CPU @cpu.
 */
struct task_struct *idle_task(int cpu)
{
	return cpu_rq(cpu)->idle;
}

#ifdef CONFIG_SCHED_CORE
int sched_core_idle_cpu(int cpu)
{
	struct rq *rq = cpu_rq(cpu);

	if (sched_core_enabled(rq) && rq->curr == rq->idle)
		return 1;

	return idle_cpu(cpu);
}
#endif /* CONFIG_SCHED_CORE */

/**
 * find_process_by_pid - find a process with a matching PID value.
 * @pid: the pid in question.
 *
 * The task of @pid, if found. %NULL otherwise.
 */
static struct task_struct *find_process_by_pid(pid_t pid)
{
	return pid ? find_task_by_vpid(pid) : current;
}

static struct task_struct *find_get_task(pid_t pid)
{
	struct task_struct *p;
	guard(rcu)();

	p = find_process_by_pid(pid);
	if (likely(p))
		get_task_struct(p);

	return p;
}

DEFINE_CLASS(find_get_task, struct task_struct *, if (_T) put_task_struct(_T),
	     find_get_task(pid), pid_t pid)

/*
 * sched_setparam() passes in -1 for its policy, to let the functions
 * it calls know not to change it.
 */
#define SETPARAM_POLICY	-1

static void __setscheduler_params(struct task_struct *p,
		const struct sched_attr *attr)
{
	int policy = attr->sched_policy;

	if (policy == SETPARAM_POLICY)
		policy = p->policy;

	p->policy = policy;

	if (dl_policy(policy))
		__setparam_dl(p, attr);
	else if (fair_policy(policy))
		__setparam_fair(p, attr);

	/* rt-policy tasks do not have a timerslack */
	if (rt_or_dl_task_policy(p)) {
		p->timer_slack_ns = 0