/* * 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. * * Returns 0 on success, -ESRCH on failure. Can fail if the task is exiting and * we cannot lock_task_sighand. Cannot fail if task is current.
*/ int update_rlimit_cpu(struct task_struct *task, unsignedlong rlim_new)
{
u64 nsecs = rlim_new * NSEC_PER_SEC; unsignedlong irq_fl;
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);
/* * 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;
}
staticinlineint validate_clock_permissions(const clockid_t clock)
{ int ret;
rcu_read_lock();
ret = pid_for_clock(clock, false) ? 0 : -EINVAL;
rcu_read_unlock();
/* * 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;
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;
}
/* * Set cputime to sum_cputime if sum_cputime > cputime. Use cmpxchg * to avoid race conditions with concurrent updates to cputime.
*/ staticinlinevoid __update_gt_cputime(atomic64_t *cputime, u64 sum_cputime)
{
u64 curr_cputime = atomic64_read(cputime);
do { if (sum_cputime <= curr_cputime) return;
} while (!atomic64_try_cmpxchg(cputime, &curr_cputime, sum_cputime));
}
/** * thread_group_sample_cputime - Sample cputime for a given task * @tsk: Task for which cputime needs to be started * @samples: Storage for time samples * * Called from sys_getitimer() to calculate the expiry time of an active * timer. That means group cputime accounting is already active. Called * with task sighand lock held. * * Updates @times with an uptodate sample of the thread group cputimes.
*/ void thread_group_sample_cputime(struct task_struct *tsk, u64 *samples)
{ struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; struct posix_cputimers *pct = &tsk->signal->posix_cputimers;
/** * thread_group_start_cputime - Start cputime and return a sample * @tsk: Task for which cputime needs to be started * @samples: Storage for time samples * * The thread group cputime accounting is avoided when there are no posix * CPU timers armed. Before starting a timer it's required to check whether * the time accounting is active. If not, a full update of the atomic * accounting store needs to be done and the accounting enabled. * * Updates @times with an uptodate sample of the thread group cputimes.
*/ staticvoid thread_group_start_cputime(struct task_struct *tsk, u64 *samples)
{ struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; struct posix_cputimers *pct = &tsk->signal->posix_cputimers;
lockdep_assert_task_sighand_held(tsk);
/* Check if cputimer isn't running. This is accessed without locking. */ if (!READ_ONCE(pct->timers_active)) { struct task_cputime sum;
/* * The POSIX timer interface allows for absolute time expiry * values through the TIMER_ABSTIME flag, therefore we have * to synchronize the timer to the clock every time we start it.
*/
thread_group_cputime(tsk, &sum);
update_gt_cputime(&cputimer->cputime_atomic, &sum);
/* * We're setting timers_active without a lock. Ensure this * only gets written to in one operation. We set it after * update_gt_cputime() as a small optimization, but * barriers are not required because update_gt_cputime() * can handle concurrent updates.
*/
WRITE_ONCE(pct->timers_active, true);
}
proc_sample_cputime_atomic(&cputimer->cputime_atomic, samples);
}
/* * Sample a process (thread group) clock for the given task clkid. If the * group's cputime accounting is already enabled, read the atomic * store. Otherwise a full update is required. clkid is already validated.
*/ static u64 cpu_clock_sample_group(const clockid_t clkid, struct task_struct *p, bool start)
{ struct thread_group_cputimer *cputimer = &p->signal->cputimer; struct posix_cputimers *pct = &p->signal->posix_cputimers;
u64 samples[CPUCLOCK_MAX];
if (!READ_ONCE(pct->timers_active)) { if (start)
thread_group_start_cputime(p, samples); else
__thread_group_cputime(p, samples);
} else {
proc_sample_cputime_atomic(&cputimer->cputime_atomic, samples);
}
if (CPUCLOCK_PERTHREAD(clock))
t = cpu_clock_sample(clkid, tsk); else
t = cpu_clock_sample_group(clkid, tsk, false);
rcu_read_unlock();
*tp = ns_to_timespec64(t); return 0;
}
/* * Validate the clockid_t for a new CPU-clock timer, and initialize the timer. * This is called from sys_timer_create() and do_cpu_nanosleep() with the * new timer already all-zeros initialized.
*/ staticint posix_cpu_timer_create(struct k_itimer *new_timer)
{ staticstruct lock_class_key posix_cpu_timers_key; struct pid *pid;
/* * If posix timer expiry is handled in task work context then * timer::it_lock can be taken without disabling interrupts as all * other locking happens in task context. This requires a separate * lock class key otherwise regular posix timer expiry would record * the lock class being taken in interrupt context and generate a * false positive warning.
*/ if (IS_ENABLED(CONFIG_POSIX_CPU_TIMERS_TASK_WORK))
lockdep_set_class(&new_timer->it_lock, &posix_cpu_timers_key);
/* * Force recalculating the base earliest expiration on the next tick. * This will also re-evaluate the need to keep around the process wide * cputime counter and tick dependency and eventually shut these down * if necessary.
*/ staticvoid trigger_base_recalc_expires(struct k_itimer *timer, struct task_struct *tsk)
{ struct posix_cputimer_base *base = timer_base(timer, tsk);
base->nextevt = 0;
}
/* * Dequeue the timer and reset the base if it was its earliest expiration. * It makes sure the next tick recalculates the base next expiration so we * don't keep the costly process wide cputime counter around for a random * amount of time, along with the tick dependency. * * If another timer gets queued between this and the next tick, its * expiration will update the base next event if necessary on the next * tick.
*/ staticvoid disarm_timer(struct k_itimer *timer, struct task_struct *p)
{ struct cpu_timer *ctmr = &timer->it.cpu; struct posix_cputimer_base *base;
if (!cpu_timer_dequeue(ctmr)) return;
base = timer_base(timer, p); if (cpu_timer_getexpires(ctmr) == base->nextevt)
trigger_base_recalc_expires(timer, p);
}
/* * Clean up a CPU-clock timer that is about to be destroyed. * This is called from timer deletion with the timer already locked. * If we return TIMER_RETRY, it's necessary to release the timer's lock * and try again. (This happens when the timer is in the middle of firing.)
*/ staticint posix_cpu_timer_del(struct k_itimer *timer)
{ struct cpu_timer *ctmr = &timer->it.cpu; struct sighand_struct *sighand; struct task_struct *p; unsignedlong flags; int ret = 0;
rcu_read_lock();
p = cpu_timer_task_rcu(timer); if (!p) goto out;
/* * Protect against sighand release/switch in exit/exec and process/ * thread timer list entry concurrent read/writes.
*/
sighand = lock_task_sighand(p, &flags); if (unlikely(sighand == NULL)) { /* * This raced with the reaping of the task. The exit cleanup * should have removed this timer from the timer queue.
*/
WARN_ON_ONCE(ctmr->head || timerqueue_node_queued(&ctmr->node));
} else { if (timer->it.cpu.firing) { /* * Prevent signal delivery. The timer cannot be dequeued * because it is on the firing list which is not protected * by sighand->lock. The delivery path is waiting for * the timer lock. So go back, unlock and retry.
*/
timer->it.cpu.firing = false;
ret = TIMER_RETRY;
} else {
disarm_timer(timer, p);
}
unlock_task_sighand(p, &flags);
}
/* * Clean out CPU timers which are still armed when a thread exits. The * timers are only removed from the list. No other updates are done. The * corresponding posix timers are still accessible, but cannot be rearmed. * * This must be called with the siglock held.
*/ staticvoid cleanup_timers(struct posix_cputimers *pct)
{
cleanup_timerqueue(&pct->bases[CPUCLOCK_PROF].tqhead);
cleanup_timerqueue(&pct->bases[CPUCLOCK_VIRT].tqhead);
cleanup_timerqueue(&pct->bases[CPUCLOCK_SCHED].tqhead);
}
/* * These are both called with the siglock held, when the current thread * is being reaped. When the final (leader) thread in the group is reaped, * posix_cpu_timers_exit_group will be called after posix_cpu_timers_exit.
*/ void posix_cpu_timers_exit(struct task_struct *tsk)
{
cleanup_timers(&tsk->posix_cputimers);
} void posix_cpu_timers_exit_group(struct task_struct *tsk)
{
cleanup_timers(&tsk->signal->posix_cputimers);
}
/* * Insert the timer on the appropriate list before any timers that * expire later. This must be called with the sighand lock held.
*/ staticvoid arm_timer(struct k_itimer *timer, struct task_struct *p)
{ struct posix_cputimer_base *base = timer_base(timer, p); struct cpu_timer *ctmr = &timer->it.cpu;
u64 newexp = cpu_timer_getexpires(ctmr);
timer->it_status = POSIX_TIMER_ARMED; if (!cpu_timer_enqueue(&base->tqhead, ctmr)) return;
/* * 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 (newexp < base->nextevt)
base->nextevt = newexp;
if (CPUCLOCK_PERTHREAD(timer->it_clock))
tick_dep_set_task(p, TICK_DEP_BIT_POSIX_TIMER); else
tick_dep_set_signal(p, TICK_DEP_BIT_POSIX_TIMER);
}
/* * The timer is locked, fire it and arrange for its reload.
*/ staticvoid cpu_timer_fire(struct k_itimer *timer)
{ struct cpu_timer *ctmr = &timer->it.cpu;
timer->it_status = POSIX_TIMER_DISARMED;
if (unlikely(ctmr->nanosleep)) { /* * This a special case for clock_nanosleep, * not a normal timer from sys_timer_create.
*/
wake_up_process(timer->it_process);
cpu_timer_setexpires(ctmr, 0);
} else {
posix_timer_queue_signal(timer); /* Disable oneshot timers */ if (!timer->it_interval)
cpu_timer_setexpires(ctmr, 0);
}
}
/* * Guts of sys_timer_settime for CPU timers. * This is called with the timer locked and interrupts disabled. * If we return TIMER_RETRY, it's necessary to release the timer's lock * and try again. (This happens when the timer is in the middle of firing.)
*/ staticint posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, struct itimerspec64 *new, struct itimerspec64 *old)
{ bool sigev_none = timer->it_sigev_notify == SIGEV_NONE;
clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); struct cpu_timer *ctmr = &timer->it.cpu;
u64 old_expires, new_expires, now; struct sighand_struct *sighand; struct task_struct *p; unsignedlong flags; int ret = 0;
rcu_read_lock();
p = cpu_timer_task_rcu(timer); if (!p) { /* * If p has just been reaped, we can no * longer get any information about it at all.
*/
rcu_read_unlock(); return -ESRCH;
}
/* * Use the to_ktime conversion because that clamps the maximum * value to KTIME_MAX and avoid multiplication overflows.
*/
new_expires = ktime_to_ns(timespec64_to_ktime(new->it_value));
/* * Protect against sighand release/switch in exit/exec and p->cpu_timers * and p->signal->cpu_timers read/write in arm_timer()
*/
sighand = lock_task_sighand(p, &flags); /* * If p has just been reaped, we can no * longer get any information about it at all.
*/ if (unlikely(sighand == NULL)) {
rcu_read_unlock(); return -ESRCH;
}
/* Retrieve the current expiry time before disarming the timer */
old_expires = cpu_timer_getexpires(ctmr);
if (unlikely(timer->it.cpu.firing)) { /* * Prevent signal delivery. The timer cannot be dequeued * because it is on the firing list which is not protected * by sighand->lock. The delivery path is waiting for * the timer lock. So go back, unlock and retry.
*/
timer->it.cpu.firing = false;
ret = TIMER_RETRY;
} else {
cpu_timer_dequeue(ctmr);
timer->it_status = POSIX_TIMER_DISARMED;
}
/* * Sample the current clock for saving the previous setting * and for rearming the timer.
*/ if (CPUCLOCK_PERTHREAD(timer->it_clock))
now = cpu_clock_sample(clkid, p); else
now = cpu_clock_sample_group(clkid, p, !sigev_none);
/* Retrieve the previous expiry value if requested. */ if (old) {
old->it_value = (struct timespec64){ }; if (old_expires)
__posix_cpu_timer_get(timer, old, now);
}
/* Retry if the timer expiry is running concurrently */ if (unlikely(ret)) {
unlock_task_sighand(p, &flags); goto out;
}
/* Convert relative expiry time to absolute */ if (new_expires && !(timer_flags & TIMER_ABSTIME))
new_expires += now;
/* Set the new expiry time (might be 0) */
cpu_timer_setexpires(ctmr, new_expires);
/* * Arm the timer if it is not disabled, the new expiry value has * not yet expired and the timer requires signal delivery. * SIGEV_NONE timers are never armed. In case the timer is not * armed, enforce the reevaluation of the timer base so that the * process wide cputime counter can be disabled eventually.
*/ if (likely(!sigev_none)) { if (new_expires && now < new_expires)
arm_timer(timer, p); else
trigger_base_recalc_expires(timer, p);
}
unlock_task_sighand(p, &flags);
posix_timer_set_common(timer, new);
/* * If the new expiry time was already in the past the timer was not * queued. Fire it immediately even if the thread never runs to * accumulate more time on this clock.
*/ if (!sigev_none && new_expires && now >= new_expires)
cpu_timer_fire(timer);
out:
rcu_read_unlock(); return ret;
}
/* * Make sure that interval timers are moved forward for the * following cases: * - SIGEV_NONE timers which are never armed * - Timers which expired, but the signal has not yet been * delivered
*/ if (iv && timer->it_status != POSIX_TIMER_ARMED)
expires = bump_cpu_timer(timer, now); else
expires = cpu_timer_getexpires(&timer->it.cpu);
/* * Expired interval timers cannot have a remaining time <= 0. * The kernel has to move them forward so that the next * timer expiry is > @now.
*/ if (now < expires) {
itp->it_value = ns_to_timespec64(expires - now);
} else { /* * A single shot SIGEV_NONE timer must return 0, when it is * expired! Timers which have a real signal delivery mode * must return a remaining time greater than 0 because the * signal has not yet been delivered.
*/ if (!sigev_none)
itp->it_value.tv_nsec = 1;
}
}
static u64 collect_timerqueue(struct timerqueue_head *head, struct list_head *firing, u64 now)
{ struct timerqueue_node *next; int i = 0;
while ((next = timerqueue_getnext(head))) { struct cpu_timer *ctmr;
u64 expires;
ctmr = container_of(next, struct cpu_timer, node);
expires = cpu_timer_getexpires(ctmr); /* Limit the number of timers to expire at once */ if (++i == MAX_COLLECTED || now < expires) return expires;
/* * Check for any per-thread CPU timers that have fired and move them off * the tsk->cpu_timers[N] list onto the firing list. Here we update the * tsk->it_*_expires values to reflect the remaining thread CPU timers.
*/ staticvoid check_thread_timers(struct task_struct *tsk, struct list_head *firing)
{ struct posix_cputimers *pct = &tsk->posix_cputimers;
u64 samples[CPUCLOCK_MAX]; unsignedlong soft;
/* * Check for the special case thread timers.
*/
soft = task_rlimit(tsk, RLIMIT_RTTIME); if (soft != RLIM_INFINITY) { /* Task RT timeout is accounted in jiffies. RTTIME is usec */ unsignedlong rttime = tsk->rt.timeout * (USEC_PER_SEC / HZ); unsignedlong hard = task_rlimit_max(tsk, RLIMIT_RTTIME);
/* At the hard limit, send SIGKILL. No further action. */ if (hard != RLIM_INFINITY &&
check_rlimit(rttime, hard, SIGKILL, true, true)) return;
/* At the soft limit, send a SIGXCPU every second */ if (check_rlimit(rttime, soft, SIGXCPU, true, false)) {
soft += USEC_PER_SEC;
tsk->signal->rlim[RLIMIT_RTTIME].rlim_cur = soft;
}
}
if (expiry_cache_is_inactive(pct))
tick_dep_clear_task(tsk, TICK_DEP_BIT_POSIX_TIMER);
}
/* Turn off the active flag. This is done without locking. */
WRITE_ONCE(pct->timers_active, false);
tick_dep_clear_signal(sig, TICK_DEP_BIT_POSIX_TIMER);
}
staticvoid check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
u64 *expires, u64 cur_time, int signo)
{ if (!it->expires) return;
if (cur_time >= it->expires) { if (it->incr)
it->expires += it->incr; else
it->expires = 0;
if (it->expires && 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 * have already been taken off.
*/ staticvoid check_process_timers(struct task_struct *tsk, struct list_head *firing)
{ struct signal_struct *const sig = tsk->signal; struct posix_cputimers *pct = &sig->posix_cputimers;
u64 samples[CPUCLOCK_MAX]; unsignedlong soft;
/* * If there are no active process wide timers (POSIX 1.b, itimers, * RLIMIT_CPU) nothing to check. Also skip the process wide timer * processing when there is already another task handling them.
*/ if (!READ_ONCE(pct->timers_active) || pct->expiry_active) return;
/* * Signify that a thread is checking for process timers. * Write access to this field is protected by the sighand lock.
*/
pct->expiry_active = true;
/* * Collect the current process totals. Group accounting is active * so the sample can be taken directly.
*/
proc_sample_cputime_atomic(&sig->cputimer.cputime_atomic, samples);
collect_posix_cputimers(pct, samples, firing);
/* * Check for the special case process timers.
*/
check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF],
&pct->bases[CPUCLOCK_PROF].nextevt,
samples[CPUCLOCK_PROF], SIGPROF);
check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT],
&pct->bases[CPUCLOCK_VIRT].nextevt,
samples[CPUCLOCK_VIRT], SIGVTALRM);
soft = task_rlimit(tsk, RLIMIT_CPU); if (soft != RLIM_INFINITY) { /* RLIMIT_CPU is in seconds. Samples are nanoseconds */ unsignedlong hard = task_rlimit_max(tsk, RLIMIT_CPU);
u64 ptime = samples[CPUCLOCK_PROF];
u64 softns = (u64)soft * NSEC_PER_SEC;
u64 hardns = (u64)hard * NSEC_PER_SEC;
/* At the hard limit, send SIGKILL. No further action. */ if (hard != RLIM_INFINITY &&
check_rlimit(ptime, hardns, SIGKILL, false, true)) return;
/* At the soft limit, send a SIGXCPU every second */ if (check_rlimit(ptime, softns, SIGXCPU, false, false)) {
sig->rlim[RLIMIT_CPU].rlim_cur = soft + 1;
softns += NSEC_PER_SEC;
}
/* Update the expiry cache */ if (softns < pct->bases[CPUCLOCK_PROF].nextevt)
pct->bases[CPUCLOCK_PROF].nextevt = softns;
}
if (expiry_cache_is_inactive(pct))
stop_process_timers(sig);
pct->expiry_active = false;
}
/* * This is called from the signal code (via posixtimer_rearm) * when the last timer signal was delivered and we have to reload the timer.
*/ staticvoid posix_cpu_timer_rearm(struct k_itimer *timer)
{
clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); struct task_struct *p; struct sighand_struct *sighand; unsignedlong flags;
u64 now;
rcu_read_lock();
p = cpu_timer_task_rcu(timer); if (!p) goto out;
/* Protect timer list r/w in arm_timer() */
sighand = lock_task_sighand(p, &flags); if (unlikely(sighand == NULL)) goto out;
/* * Fetch the current sample and update the timer's expiry time.
*/ if (CPUCLOCK_PERTHREAD(timer->it_clock))
now = cpu_clock_sample(clkid, p); else
now = cpu_clock_sample_group(clkid, p, true);
bump_cpu_timer(timer, now);
/* * Now re-arm for the new expiry time.
*/
arm_timer(timer, p);
unlock_task_sighand(p, &flags);
out:
rcu_read_unlock();
}
/** * task_cputimers_expired - Check whether posix CPU timers are expired * * @samples: Array of current samples for the CPUCLOCK clocks * @pct: Pointer to a posix_cputimers container * * Returns true if any member of @samples is greater than the corresponding * member of @pct->bases[CLK].nextevt. False otherwise
*/ staticinlinebool
task_cputimers_expired(const u64 *samples, struct posix_cputimers *pct)
{ int i;
for (i = 0; i < CPUCLOCK_MAX; i++) { if (samples[i] >= pct->bases[i].nextevt) returntrue;
} returnfalse;
}
/** * fastpath_timer_check - POSIX CPU timers fast path. * * @tsk: The task (thread) being checked. * * Check the task and thread group timers. If both are zero (there are no * timers set) return false. Otherwise snapshot the task and thread group * timers and compare them with the corresponding expiration times. Return * true if a timer has expired, else return false.
*/ staticinlinebool fastpath_timer_check(struct task_struct *tsk)
{ struct posix_cputimers *pct = &tsk->posix_cputimers; struct signal_struct *sig;
if (!expiry_cache_is_inactive(pct)) {
u64 samples[CPUCLOCK_MAX];
task_sample_cputime(tsk, samples); if (task_cputimers_expired(samples, pct)) returntrue;
}
sig = tsk->signal;
pct = &sig->posix_cputimers; /* * Check if thread group timers expired when timers are active and * no other thread in the group is already handling expiry for * thread group cputimers. These fields are read without the * sighand lock. However, this is fine because this is meant to be * a fastpath heuristic to determine whether we should try to * acquire the sighand lock to handle timer expiry. * * In the worst case scenario, if concurrently timers_active is set * or expiry_active is cleared, but the current thread doesn't see * the change yet, the timer checks are delayed until the next * thread in the group gets a scheduler interrupt to handle the * timer. This isn't an issue in practice because these types of * delays with signals actually getting sent are expected.
*/ if (READ_ONCE(pct->timers_active) && !READ_ONCE(pct->expiry_active)) {
u64 samples[CPUCLOCK_MAX];
/* * Invoked from the posix-timer core when a cancel operation failed because * the timer is marked firing. The caller holds rcu_read_lock(), which * protects the timer and the task which is expiring it from being freed.
*/ staticvoid posix_cpu_timer_wait_running(struct k_itimer *timr)
{ struct task_struct *tsk = rcu_dereference(timr->it.cpu.handling);
/* Has the handling task completed expiry already? */ if (!tsk) return;
/* Ensure that the task cannot go away */
get_task_struct(tsk); /* Now drop the RCU protection so the mutex can be locked */
rcu_read_unlock(); /* Wait on the expiry mutex */
mutex_lock(&tsk->posix_cputimers_work.mutex); /* Release it immediately again. */
mutex_unlock(&tsk->posix_cputimers_work.mutex); /* Drop the task reference. */
put_task_struct(tsk); /* Relock RCU so the callsite is balanced */
rcu_read_lock();
}
staticvoid posix_cpu_timer_wait_running_nsleep(struct k_itimer *timr)
{ /* Ensure that timr->it.cpu.handling task cannot go away */
rcu_read_lock();
spin_unlock_irq(&timr->it_lock);
posix_cpu_timer_wait_running(timr);
rcu_read_unlock(); /* @timr is on stack and is valid */
spin_lock_irq(&timr->it_lock);
}
/* * Clear existing posix CPU timers task work.
*/ void clear_posix_cputimers_work(struct task_struct *p)
{ /* * A copied work entry from the old task is not meaningful, clear it. * N.B. init_task_work will not do this.
*/
memset(&p->posix_cputimers_work.work, 0, sizeof(p->posix_cputimers_work.work));
init_task_work(&p->posix_cputimers_work.work,
posix_cpu_timers_work);
mutex_init(&p->posix_cputimers_work.mutex);
p->posix_cputimers_work.scheduled = false;
}
/* * Initialize posix CPU timers task work in init task. Out of line to * keep the callback static and to avoid header recursion hell.
*/ void __init posix_cputimers_init_work(void)
{
clear_posix_cputimers_work(current);
}
/* * Note: All operations on tsk->posix_cputimer_work.scheduled happen either * in hard interrupt context or in task context with interrupts * disabled. Aside of that the writer/reader interaction is always in the * context of the current task, which means they are strict per CPU.
*/ staticinlinebool posix_cpu_timers_work_scheduled(struct task_struct *tsk)
{ return tsk->posix_cputimers_work.scheduled;
}
staticinlinevoid __run_posix_cpu_timers(struct task_struct *tsk)
{ if (WARN_ON_ONCE(tsk->posix_cputimers_work.scheduled)) return;
/* Schedule task work to actually expire the timers */
tsk->posix_cputimers_work.scheduled = true;
task_work_add(tsk, &tsk->posix_cputimers_work.work, TWA_RESUME);
}
/* * On !RT kernels interrupts are disabled while collecting expired * timers, so no tick can happen and the fast path check can be * reenabled without further checks.
*/ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
tsk->posix_cputimers_work.scheduled = false; returntrue;
}
/* * On RT enabled kernels ticks can happen while the expired timers * are collected under sighand lock. But any tick which observes * the CPUTIMERS_WORK_SCHEDULED bit set, does not run the fastpath * checks. So reenabling the tick work has do be done carefully: * * Disable interrupts and run the fast path check if jiffies have * advanced since the collecting of expired timers started. If * jiffies have not advanced or the fast path check did not find * newly expired timers, reenable the fast path check in the timer * interrupt. If there are newly expired timers, return false and * let the collection loop repeat.
*/
local_irq_disable(); if (start != jiffies && fastpath_timer_check(tsk))
ret = false; else
tsk->posix_cputimers_work.scheduled = false;
local_irq_enable();
do { /* * On RT locking sighand lock does not disable interrupts, * so this needs to be careful vs. ticks. Store the current * jiffies value.
*/
start = READ_ONCE(jiffies);
barrier();
/* * Here we take off tsk->signal->cpu_timers[N] and * tsk->cpu_timers[N] all the timers that are firing, and * put them on the firing list.
*/
check_thread_timers(tsk, &firing);
check_process_timers(tsk, &firing);
/* * The above timer checks have updated the expiry cache and * because nothing can have queued or modified timers after * sighand lock was taken above it is guaranteed to be * consistent. So the next timer interrupt fastpath check * will find valid data. * * If timer expiry runs in the timer interrupt context then * the loop is not relevant as timers will be directly * expired in interrupt context. The stub function below * returns always true which allows the compiler to * optimize the loop out. * * If timer expiry is deferred to task work context then * the following rules apply: * * - On !RT kernels no tick can have happened on this CPU * after sighand lock was acquired because interrupts are * disabled. So reenabling task work before dropping * sighand lock and reenabling interrupts is race free. * * - On RT kernels ticks might have happened but the tick * work ignored posix CPU timer handling because the * CPUTIMERS_WORK_SCHEDULED bit is set. Reenabling work * must be done very carefully including a check whether * ticks have happened since the start of the timer * expiry checks. posix_cpu_timers_enable_work() takes * care of that and eventually lets the expiry checks * run again.
*/
} while (!posix_cpu_timers_enable_work(tsk, start));
/* * We must release sighand lock before taking any timer's lock. * There is a potential race with timer deletion here, as the * siglock now protects our private firing list. We have set * the firing flag in each timer, so that a deletion attempt * that gets the timer lock before we do will give it up and * spin until we've taken care of that timer below.
*/
unlock_task_sighand(tsk, &flags);
/* * Now that all the timers on our list have the firing flag, * no one will touch their list entries but us. We'll take * each timer's lock before clearing its firing flag, so no * timer call will interfere.
*/
list_for_each_entry_safe(timer, next, &firing, it.cpu.elist) { bool cpu_firing;
/* * spin_lock() is sufficient here even independent of the * expiry context. If expiry happens in hard interrupt * context it's obvious. For task work context it's safe * because all other operations on timer::it_lock happen in * task context (syscall or exit).
*/
spin_lock(&timer->it_lock);
list_del_init(&timer->it.cpu.elist);
cpu_firing = timer->it.cpu.firing;
timer->it.cpu.firing = false; /* * If the firing flag is cleared then this raced with a * timer rearm/delete operation. So don't generate an * event.
*/ if (likely(cpu_firing))
cpu_timer_fire(timer); /* See posix_cpu_timer_wait_running() */
rcu_assign_pointer(timer->it.cpu.handling, NULL);
spin_unlock(&timer->it_lock);
}
}
/* * This is called from the timer interrupt handler. The irq handler has * already updated our counts. We need to check if any timers fire now. * Interrupts are disabled.
*/ void run_posix_cpu_timers(void)
{ struct task_struct *tsk = current;
lockdep_assert_irqs_disabled();
/* * Ensure that release_task(tsk) can't happen while * handle_posix_cpu_timers() is running. Otherwise, a concurrent * posix_cpu_timer_del() may fail to lock_task_sighand(tsk) and * miss timer->it.cpu.firing != 0.
*/ if (tsk->exit_state) return;
/* * If the actual expiry is deferred to task work context and the * work is already scheduled there is no point to do anything here.
*/ if (posix_cpu_timers_work_scheduled(tsk)) return;
/* * The fast path checks that there are no expired thread or thread * group timers. If that's so, just return.
*/ if (!fastpath_timer_check(tsk)) return;
__run_posix_cpu_timers(tsk);
}
/* * Set one of the process-wide special case CPU timers or RLIMIT_CPU. * The tsk->sighand->siglock must be held by the caller.
*/ void set_process_cpu_timer(struct task_struct *tsk, unsignedint clkid,
u64 *newval, u64 *oldval)
{
u64 now, *nextevt;
if (WARN_ON_ONCE(clkid >= CPUCLOCK_SCHED)) return;
nextevt = &tsk->signal->posix_cputimers.bases[clkid].nextevt;
now = cpu_clock_sample_group(clkid, tsk, true);
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 (*oldval) { if (*oldval <= now) { /* Just about to fire. */
*oldval = TICK_NSEC;
} else {
*oldval -= now;
}
}
if (*newval)
*newval += now;
}
/* * Update expiration cache if this is the earliest timer. CPUCLOCK_PROF * expiry cache is also used by RLIMIT_CPU!.
*/ if (*newval < *nextevt)
*nextevt = *newval;
staticint do_cpu_nanosleep(const clockid_t which_clock, int flags, conststruct timespec64 *rqtp)
{ struct itimerspec64 it; struct k_itimer timer;
u64 expires; int error;
/* * Set up a temporary timer and then wait for it to go off.
*/
memset(&timer, 0, sizeof timer);
spin_lock_init(&timer.it_lock);
timer.it_clock = which_clock;
timer.it_overrun = -1;
error = posix_cpu_timer_create(&timer);
timer.it_process = current;
timer.it.cpu.nanosleep = true;
if (!error) { staticstruct itimerspec64 zero_it; struct restart_block *restart;
while (!signal_pending(current)) { if (!cpu_timer_getexpires(&timer.it.cpu)) { /* * Our timer fired and was reset, below * deletion can not fail.
*/
posix_cpu_timer_del(&timer);
spin_unlock_irq(&timer.it_lock); return 0;
}
/* * Block until cpu_timer_fire (or a signal) wakes us.
*/
__set_current_state(TASK_INTERRUPTIBLE);
spin_unlock_irq(&timer.it_lock);
schedule();
spin_lock_irq(&timer.it_lock);
}
/* * We were interrupted by a signal.
*/
expires = cpu_timer_getexpires(&timer.it.cpu);
error = posix_cpu_timer_set(&timer, 0, &zero_it, &it); if (!error) { /* Timer is now unarmed, deletion can not fail. */
posix_cpu_timer_del(&timer);
} else { while (error == TIMER_RETRY) {
posix_cpu_timer_wait_running_nsleep(&timer);
error = posix_cpu_timer_del(&timer);
}
}
spin_unlock_irq(&timer.it_lock);
if ((it.it_value.tv_sec | it.it_value.tv_nsec) == 0) { /* * It actually did fire already.
*/ return 0;
}
error = -ERESTART_RESTARTBLOCK; /* * Report back to the user the time still remaining.
*/
restart = ¤t->restart_block;
restart->nanosleep.expires = expires; if (restart->nanosleep.type != TT_NONE)
error = nanosleep_copyout(restart, &it.it_value);
}
¤ Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.0.20Bemerkung:
(vorverarbeitet)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.