#include <linux/math64.h>
#include <asm/uaccess.h>
#include <linux/kernel_stat.h>
+#include <trace/events/timer.h>
/*
- * Called after updating RLIMIT_CPU to set timer expiration if necessary.
+ * Called after updating RLIMIT_CPU to run cpu timer and update
+ * tsk->signal->cputime_expires expiration cache if necessary. Needs
+ * siglock protection since other code may update expiration cache as
+ * well.
*/
void update_rlimit_cpu(unsigned long rlim_new)
{
- cputime_t cputime;
-
- cputime = secs_to_cputime(rlim_new);
- if (cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
- cputime_gt(current->signal->it_prof_expires, cputime)) {
- spin_lock_irq(¤t->sighand->siglock);
- set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
- spin_unlock_irq(¤t->sighand->siglock);
- }
+ cputime_t cputime = secs_to_cputime(rlim_new);
+
+ spin_lock_irq(¤t->sighand->siglock);
+ set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
+ spin_unlock_irq(¤t->sighand->siglock);
}
static int check_clock(const clockid_t which_clock)
/*
* Validate the clockid_t for a new CPU-clock timer, and initialize the timer.
- * This is called from sys_timer_create with the new timer already locked.
+ * This is called from sys_timer_create() and do_cpu_nanosleep() with the
+ * new timer already all-zeros initialized.
*/
int posix_cpu_timer_create(struct k_itimer *new_timer)
{
return -EINVAL;
INIT_LIST_HEAD(&new_timer->it.cpu.entry);
- new_timer->it.cpu.incr.sched = 0;
- new_timer->it.cpu.expires.sched = 0;
read_lock(&tasklist_lock);
if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) {
}
void posix_cpu_timers_exit_group(struct task_struct *tsk)
{
- struct task_cputime cputime;
+ struct signal_struct *const sig = tsk->signal;
- thread_group_cputimer(tsk, &cputime);
cleanup_timers(tsk->signal->cpu_timers,
- cputime.utime, cputime.stime, cputime.sum_exec_runtime);
+ cputime_add(tsk->utime, sig->utime),
+ cputime_add(tsk->stime, sig->stime),
+ tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
}
static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
now);
}
+static inline int expires_gt(cputime_t expires, cputime_t new_exp)
+{
+ return cputime_eq(expires, cputime_zero) ||
+ cputime_gt(expires, new_exp);
+}
+
/*
* Insert the timer on the appropriate list before any timers that
* expire later. This must be called with the tasklist_lock held
* for reading, and interrupts disabled.
*/
-static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
+static void arm_timer(struct k_itimer *timer)
{
struct task_struct *p = timer->it.cpu.task;
struct list_head *head, *listpos;
+ struct task_cputime *cputime_expires;
struct cpu_timer_list *const nt = &timer->it.cpu;
struct cpu_timer_list *next;
- unsigned long i;
- head = (CPUCLOCK_PERTHREAD(timer->it_clock) ?
- p->cpu_timers : p->signal->cpu_timers);
+ if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+ head = p->cpu_timers;
+ cputime_expires = &p->cputime_expires;
+ } else {
+ head = p->signal->cpu_timers;
+ cputime_expires = &p->signal->cputime_expires;
+ }
head += CPUCLOCK_WHICH(timer->it_clock);
BUG_ON(!irqs_disabled());
spin_lock(&p->sighand->siglock);
listpos = head;
- if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
- list_for_each_entry(next, head, entry) {
- if (next->expires.sched > nt->expires.sched)
- break;
- listpos = &next->entry;
- }
- } else {
- list_for_each_entry(next, head, entry) {
- if (cputime_gt(next->expires.cpu, nt->expires.cpu))
- break;
- listpos = &next->entry;
- }
+ list_for_each_entry(next, head, entry) {
+ if (cpu_time_before(timer->it_clock, nt->expires, next->expires))
+ break;
+ listpos = &next->entry;
}
list_add(&nt->entry, listpos);
if (listpos == head) {
+ union cpu_time_count *exp = &nt->expires;
+
/*
- * We are the new earliest-expiring timer.
- * If we are a thread timer, there can always
- * be a process timer telling us to stop earlier.
+ * We are the new earliest-expiring POSIX 1.b timer, hence
+ * need to update expiration cache. Take into account that
+ * for process timers we share expiration cache with itimers
+ * and RLIMIT_CPU and for thread timers with RLIMIT_RTTIME.
*/
- if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
- switch (CPUCLOCK_WHICH(timer->it_clock)) {
- default:
- BUG();
- case CPUCLOCK_PROF:
- if (cputime_eq(p->cputime_expires.prof_exp,
- cputime_zero) ||
- cputime_gt(p->cputime_expires.prof_exp,
- nt->expires.cpu))
- p->cputime_expires.prof_exp =
- nt->expires.cpu;
- break;
- case CPUCLOCK_VIRT:
- if (cputime_eq(p->cputime_expires.virt_exp,
- cputime_zero) ||
- cputime_gt(p->cputime_expires.virt_exp,
- nt->expires.cpu))
- p->cputime_expires.virt_exp =
- nt->expires.cpu;
- break;
- case CPUCLOCK_SCHED:
- if (p->cputime_expires.sched_exp == 0 ||
- p->cputime_expires.sched_exp >
- nt->expires.sched)
- p->cputime_expires.sched_exp =
- nt->expires.sched;
- break;
- }
- } else {
- /*
- * For a process timer, set the cached expiration time.
- */
- switch (CPUCLOCK_WHICH(timer->it_clock)) {
- default:
- BUG();
- case CPUCLOCK_VIRT:
- if (!cputime_eq(p->signal->it_virt_expires,
- cputime_zero) &&
- cputime_lt(p->signal->it_virt_expires,
- timer->it.cpu.expires.cpu))
- break;
- p->signal->cputime_expires.virt_exp =
- timer->it.cpu.expires.cpu;
- break;
- case CPUCLOCK_PROF:
- if (!cputime_eq(p->signal->it_prof_expires,
- cputime_zero) &&
- cputime_lt(p->signal->it_prof_expires,
- timer->it.cpu.expires.cpu))
- break;
- i = p->signal->rlim[RLIMIT_CPU].rlim_cur;
- if (i != RLIM_INFINITY &&
- i <= cputime_to_secs(timer->it.cpu.expires.cpu))
- break;
- p->signal->cputime_expires.prof_exp =
- timer->it.cpu.expires.cpu;
- break;
- case CPUCLOCK_SCHED:
- p->signal->cputime_expires.sched_exp =
- timer->it.cpu.expires.sched;
- break;
- }
+ switch (CPUCLOCK_WHICH(timer->it_clock)) {
+ case CPUCLOCK_PROF:
+ if (expires_gt(cputime_expires->prof_exp, exp->cpu))
+ cputime_expires->prof_exp = exp->cpu;
+ break;
+ case CPUCLOCK_VIRT:
+ if (expires_gt(cputime_expires->virt_exp, exp->cpu))
+ cputime_expires->virt_exp = exp->cpu;
+ break;
+ case CPUCLOCK_SCHED:
+ if (cputime_expires->sched_exp == 0 ||
+ cputime_expires->sched_exp > exp->sched)
+ cputime_expires->sched_exp = exp->sched;
+ break;
}
}
if (new_expires.sched != 0 &&
(timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE &&
cpu_time_before(timer->it_clock, val, new_expires)) {
- arm_timer(timer, val);
+ arm_timer(timer);
}
read_unlock(&tasklist_lock);
int maxfire;
struct list_head *timers = tsk->cpu_timers;
struct signal_struct *const sig = tsk->signal;
+ unsigned long soft;
maxfire = 20;
tsk->cputime_expires.prof_exp = cputime_zero;
/*
* Check for the special case thread timers.
*/
- if (sig->rlim[RLIMIT_RTTIME].rlim_cur != RLIM_INFINITY) {
- unsigned long hard = sig->rlim[RLIMIT_RTTIME].rlim_max;
- unsigned long *soft = &sig->rlim[RLIMIT_RTTIME].rlim_cur;
+ soft = ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur);
+ if (soft != RLIM_INFINITY) {
+ unsigned long hard =
+ ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max);
if (hard != RLIM_INFINITY &&
tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
return;
}
- if (tsk->rt.timeout > DIV_ROUND_UP(*soft, USEC_PER_SEC/HZ)) {
+ if (tsk->rt.timeout > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) {
/*
* At the soft limit, send a SIGXCPU every second.
*/
- if (sig->rlim[RLIMIT_RTTIME].rlim_cur
- < sig->rlim[RLIMIT_RTTIME].rlim_max) {
- sig->rlim[RLIMIT_RTTIME].rlim_cur +=
- USEC_PER_SEC;
+ if (soft < hard) {
+ soft += USEC_PER_SEC;
+ sig->rlim[RLIMIT_RTTIME].rlim_cur = soft;
}
printk(KERN_INFO
"RT Watchdog Timeout: %s[%d]\n",
spin_unlock_irqrestore(&cputimer->lock, flags);
}
+static u32 onecputick;
+
+static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
+ cputime_t *expires, cputime_t cur_time, int signo)
+{
+ if (cputime_eq(it->expires, cputime_zero))
+ return;
+
+ if (cputime_ge(cur_time, it->expires)) {
+ if (!cputime_eq(it->incr, cputime_zero)) {
+ it->expires = cputime_add(it->expires, it->incr);
+ it->error += it->incr_error;
+ if (it->error >= onecputick) {
+ it->expires = cputime_sub(it->expires,
+ cputime_one_jiffy);
+ it->error -= onecputick;
+ }
+ } else {
+ it->expires = cputime_zero;
+ }
+
+ trace_itimer_expire(signo == SIGPROF ?
+ ITIMER_PROF : ITIMER_VIRTUAL,
+ tsk->signal->leader_pid, cur_time);
+ __group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
+ }
+
+ if (!cputime_eq(it->expires, cputime_zero) &&
+ (cputime_eq(*expires, cputime_zero) ||
+ cputime_lt(it->expires, *expires))) {
+ *expires = it->expires;
+ }
+}
+
/*
* Check for any per-thread CPU timers that have fired and move them
* off the tsk->*_timers list onto the firing list. Per-thread timers
unsigned long long sum_sched_runtime, sched_expires;
struct list_head *timers = sig->cpu_timers;
struct task_cputime cputime;
+ unsigned long soft;
/*
* Don't sample the current process CPU clocks if there are no timers.
*/
if (list_empty(&timers[CPUCLOCK_PROF]) &&
- cputime_eq(sig->it_prof_expires, cputime_zero) &&
+ cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) &&
sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
list_empty(&timers[CPUCLOCK_VIRT]) &&
- cputime_eq(sig->it_virt_expires, cputime_zero) &&
+ cputime_eq(sig->it[CPUCLOCK_VIRT].expires, cputime_zero) &&
list_empty(&timers[CPUCLOCK_SCHED])) {
stop_process_timers(tsk);
return;
/*
* Check for the special case process timers.
*/
- if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
- if (cputime_ge(ptime, sig->it_prof_expires)) {
- /* ITIMER_PROF fires and reloads. */
- sig->it_prof_expires = sig->it_prof_incr;
- if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
- sig->it_prof_expires = cputime_add(
- sig->it_prof_expires, ptime);
- }
- __group_send_sig_info(SIGPROF, SEND_SIG_PRIV, tsk);
- }
- if (!cputime_eq(sig->it_prof_expires, cputime_zero) &&
- (cputime_eq(prof_expires, cputime_zero) ||
- cputime_lt(sig->it_prof_expires, prof_expires))) {
- prof_expires = sig->it_prof_expires;
- }
- }
- if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
- if (cputime_ge(utime, sig->it_virt_expires)) {
- /* ITIMER_VIRTUAL fires and reloads. */
- sig->it_virt_expires = sig->it_virt_incr;
- if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
- sig->it_virt_expires = cputime_add(
- sig->it_virt_expires, utime);
- }
- __group_send_sig_info(SIGVTALRM, SEND_SIG_PRIV, tsk);
- }
- if (!cputime_eq(sig->it_virt_expires, cputime_zero) &&
- (cputime_eq(virt_expires, cputime_zero) ||
- cputime_lt(sig->it_virt_expires, virt_expires))) {
- virt_expires = sig->it_virt_expires;
- }
- }
- if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
+ check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], &prof_expires, ptime,
+ SIGPROF);
+ check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime,
+ SIGVTALRM);
+ soft = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
+ if (soft != RLIM_INFINITY) {
unsigned long psecs = cputime_to_secs(ptime);
+ unsigned long hard =
+ ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_max);
cputime_t x;
- if (psecs >= sig->rlim[RLIMIT_CPU].rlim_max) {
+ if (psecs >= hard) {
/*
* At the hard limit, we just die.
* No need to calculate anything else now.
__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
return;
}
- if (psecs >= sig->rlim[RLIMIT_CPU].rlim_cur) {
+ if (psecs >= soft) {
/*
* At the soft limit, send a SIGXCPU every second.
*/
__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
- if (sig->rlim[RLIMIT_CPU].rlim_cur
- < sig->rlim[RLIMIT_CPU].rlim_max) {
- sig->rlim[RLIMIT_CPU].rlim_cur++;
+ if (soft < hard) {
+ soft++;
+ sig->rlim[RLIMIT_CPU].rlim_cur = soft;
}
}
- x = secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
+ x = secs_to_cputime(soft);
if (cputime_eq(prof_expires, cputime_zero) ||
cputime_lt(x, prof_expires)) {
prof_expires = x;
/*
* Now re-arm for the new expiry time.
*/
- arm_timer(timer, now);
+ arm_timer(timer);
out_unlock:
read_unlock(&tasklist_lock);
return 1;
}
- return sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY;
+ return 0;
}
/*
* timer call will interfere.
*/
list_for_each_entry_safe(timer, next, &firing, it.cpu.entry) {
- int firing;
+ int cpu_firing;
+
spin_lock(&timer->it_lock);
list_del_init(&timer->it.cpu.entry);
- firing = timer->it.cpu.firing;
+ cpu_firing = timer->it.cpu.firing;
timer->it.cpu.firing = 0;
/*
* The firing flag is -1 if we collided with a reset
* of the timer, which already reported this
* almost-firing as an overrun. So don't generate an event.
*/
- if (likely(firing >= 0)) {
+ if (likely(cpu_firing >= 0))
cpu_timer_fire(timer);
- }
spin_unlock(&timer->it_lock);
}
}
/*
- * Set one of the process-wide special case CPU timers.
+ * Set one of the process-wide special case CPU timers or RLIMIT_CPU.
* The tsk->sighand->siglock must be held by the caller.
- * The *newval argument is relative and we update it to be absolute, *oldval
- * is absolute and we update it to be relative.
*/
void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
cputime_t *newval, cputime_t *oldval)
{
union cpu_time_count now;
- struct list_head *head;
BUG_ON(clock_idx == CPUCLOCK_SCHED);
cpu_timer_sample_group(clock_idx, tsk, &now);
if (oldval) {
+ /*
+ * We are setting itimer. The *oldval is absolute and we update
+ * it to be relative, *newval argument is relative and we update
+ * it to be absolute.
+ */
if (!cputime_eq(*oldval, cputime_zero)) {
if (cputime_le(*oldval, now.cpu)) {
/* Just about to fire. */
- *oldval = jiffies_to_cputime(1);
+ *oldval = cputime_one_jiffy;
} else {
*oldval = cputime_sub(*oldval, now.cpu);
}
if (cputime_eq(*newval, cputime_zero))
return;
*newval = cputime_add(*newval, now.cpu);
-
- /*
- * If the RLIMIT_CPU timer will expire before the
- * ITIMER_PROF timer, we have nothing else to do.
- */
- if (tsk->signal->rlim[RLIMIT_CPU].rlim_cur
- < cputime_to_secs(*newval))
- return;
}
/*
- * Check whether there are any process timers already set to fire
- * before this one. If so, we don't have anything more to do.
+ * Update expiration cache if we are the earliest timer, or eventually
+ * RLIMIT_CPU limit is earlier than prof_exp cpu timer expire.
*/
- head = &tsk->signal->cpu_timers[clock_idx];
- if (list_empty(head) ||
- cputime_ge(list_first_entry(head,
- struct cpu_timer_list, entry)->expires.cpu,
- *newval)) {
- switch (clock_idx) {
- case CPUCLOCK_PROF:
+ switch (clock_idx) {
+ case CPUCLOCK_PROF:
+ if (expires_gt(tsk->signal->cputime_expires.prof_exp, *newval))
tsk->signal->cputime_expires.prof_exp = *newval;
- break;
- case CPUCLOCK_VIRT:
+ break;
+ case CPUCLOCK_VIRT:
+ if (expires_gt(tsk->signal->cputime_expires.virt_exp, *newval))
tsk->signal->cputime_expires.virt_exp = *newval;
- break;
- }
+ break;
}
}
.nsleep = thread_cpu_nsleep,
.nsleep_restart = thread_cpu_nsleep_restart,
};
+ struct timespec ts;
register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
+ cputime_to_timespec(cputime_one_jiffy, &ts);
+ onecputick = ts.tv_nsec;
+ WARN_ON(ts.tv_sec != 0);
+
return 0;
}
__initcall(init_posix_cpu_timers);