path: root/kernel/time/posix-cpu-timers.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Implement CPU time clocks for the POSIX clock interface.
 */

#include <linux/sched/signal.h>
#include <linux/sched/cputime.h>
#include <linux/posix-timers.h>
#include <linux/errno.h>
#include <linux/math64.h>
#include <linux/uaccess.h>
#include <linux/kernel_stat.h>
#include <trace/events/timer.h>
#include <linux/tick.h>
#include <linux/workqueue.h>
#include <linux/compat.h>
#include <linux/sched/deadline.h>

#include "posix-timers.h"

static void posix_cpu_timer_rearm(struct k_itimer *timer);

void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit)
{
	posix_cputimers_init(pct);
	if (cpu_limit != RLIM_INFINITY) {
		pct->bases[CPUCLOCK_PROF].nextevt = cpu_limit * NSEC_PER_SEC;
		pct->timers_active = true;
	}
}

/*
 * Called after updating RLIMIT_CPU to run cpu timer and update
 * tsk->signal->posix_cputimers.bases[clock].nextevt expiration cache if
 * necessary. Needs siglock protection since other code may update the
 * expiration cache as well.
 */
void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new)
{
	u64 nsecs = rlim_new * NSEC_PER_SEC;

	spin_lock_irq(&task->sighand->siglock);
	set_process_cpu_timer(task, CPUCLOCK_PROF, &nsecs, NULL);
	spin_unlock_irq(&task->sighand->siglock);
}

/*
 * Functions for validating access to tasks.
 */
static struct pid *pid_for_clock(const clockid_t clock, bool gettime)
{
	const bool thread = !!CPUCLOCK_PERTHREAD(clock);
	const pid_t upid = CPUCLOCK_PID(clock);
	struct pid *pid;

	if (CPUCLOCK_WHICH(clock) >= CPUCLOCK_MAX)
		return NULL;

	/*
	 * If the encoded PID is 0, then the timer is targeted at current
	 * or the process to which current belongs.
	 */
	if (upid == 0)
		return thread ? task_pid(current) : task_tgid(current);

	pid = find_vpid(upid);
	if (!pid)
		return NULL;

	if (thread) {
		struct task_struct *tsk = pid_task(pid, PIDTYPE_PID);
		return (tsk && same_thread_group(tsk, current)) ? pid : NULL;
	}

	/*
	 * For clock_gettime(PROCESS) allow finding the process by
	 * with the pid of the current task.  The code needs the tgid
	 * of the process so that pid_task(pid, PIDTYPE_TGID) can be
	 * used to find the process.
	 */
	if (gettime && (pid == task_pid(current)))
		return task_tgid(current);

	/*
	 * For processes require that pid identifies a process.
	 */
	return pid_has_task(pid, PIDTYPE_TGID) ? pid : NULL;
}

static inline int validate_clock_permissions(const clockid_t clock)
{
	int ret;

	rcu_read_lock();
	ret = pid_for_clock(clock, false) ? 0 : -EINVAL;
	rcu_read_unlock();

	return ret;
}

static inline enum pid_type clock_pid_type(const clockid_t clock)
{
	return CPUCLOCK_PERTHREAD(clock) ? PIDTYPE_PID : PIDTYPE_TGID;
}

static inline struct task_struct *cpu_timer_task_rcu(struct k_itimer *timer)
{
	return pid_task(timer->it.cpu.pid, clock_pid_type(timer->it_clock));
}

/*
 * Update expiry time from increment, and increase overrun count,
 * given the current clock sample.
 */
static u64 bump_cpu_timer(struct k_itimer *timer, u64 now)
{
	u64 delta, incr, expires = timer->it.cpu.node.expires;
	int i;

	if (!timer->it_interval)
		return expires;

	if (now < expires)
		return expires;

	incr = timer->it_interval;
	delta = now + incr - expires;

	/* Don't use (incr*2 < delta), incr*2 might overflow. */
	for (i = 0; incr < delta - incr; i++)
		incr = incr << 1;

	for (; i >= 0; incr >>= 1, i--) {
		if (delta < incr)
			continue;

		timer->it.cpu.node.expires += incr;
		timer->it_overrun += 1LL << i;
		delta -= incr;
	}
	return timer->it.cpu.node.expires;
}

/* Check whether all cache entries contain U64_MAX, i.e. eternal expiry time */
static inline bool expiry_cache_is_inactive(const struct posix_cputimers *pct)
{
	return !(~pct->bases[CPUCLOCK_PROF].nextevt |
		 ~pct->bases[CPUCLOCK_VIRT].nextevt |
		 ~pct->bases[CPUCLOCK_SCHED].nextevt);
}

static int
posix_cpu_clock_getres(const clockid_t which_clock, struct timespec64 *tp)
{
	int error = validate_clock_permissions(which_clock);

	if (!error) {
		tp->tv_sec = 0;
		tp->tv_nsec = ((NSEC_PER_SEC + HZ - 1) / HZ);
		if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
			/*
			 * If sched_clock is using a cycle counter, we
			 * don't have any idea of its true resolution
			 * exported, but it is much more than 1s/HZ.
			 */
			tp->tv_nsec = 1;
		}
	}
	return error;
}

static int
posix_cpu_clock_set(const clockid_t clock, const struct timespec64 *tp)
{
	int error = validate_clock_permissions(clock);

	/*
	 * You can never reset a CPU clock, but we check for other errors
	 * in the call before failing with EPERM.
	 */
	return error ? : -EPERM;
}

/*
 * Sample a per-thread clock for the given task. clkid is validated.
 */
static u64 cpu_clock_sample(const clockid_t clkid, struct task_struct *p)
{
	u64 utime, stime;

	if (clkid == CPUCLOCK_SCHED)
		return task_sched_runtime(p);

	task_cputime(p, &utime, &stime);

	switch (clkid) {
	case CPUCLOCK_PROF:
		return utime + stime;
	case CPUCLOCK_VIRT:
		return utime;
	default:
		WARN_ON_ONCE(1);
	}
	return 0;
}

static inline void store_samples(u64 *samples, u64 stime, u64 utime, u64 rtime)
{
	samples[CPUCLOCK_PROF] = stime + utime;
	samples[CPUCLOCK_VIRT] = utime;
	samples[CPUCLOCK_SCHED] = rtime;
}

static void task_sample_cputime(struct task_struct *p, u64 *samples)
{
	u64 stime, utime;

	task_cputime(p, &utime, &stime);
	store_samples(samples, stime, utime, p->se.sum_exec_runtime);
}

static void proc_sample_cputime_atomic(struct task_cputime_atomic *at,
				       u64 *samples)
{
	u64 stime, utime, rtime;

	utime = atomic64_read(&at->utime);
	stime = atomic64_read(&at->stime);
	rtime = atomic64_read(&at->sum_exec_runtime);
	store_samples(samples, stime, utime, rtime);
}

/*
 * Set cputime to sum_cputime if sum_cputime > cputime. Use cmpxchg
 * to avoid race conditions with concurrent updates to cputime.
 */
static inline void __update_gt_cputime(atomic64_t *cputime, u64 sum_cputime)
{
	u64 curr_cputime;
retry:
	curr_cputime = atomic64_read(cputime);
	if (sum_cputime > curr_cputime) {
		if (atomic64_cmpxchg(cputime, curr_cputime, sum_cputime) != curr_cputime)
			goto retry;
	}
}

static void update_gt_cputime(stru