summaryrefslogtreecommitdiff
path: root/kernel/posix-cpu-timers.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/posix-cpu-timers.c')
-rw-r--r--kernel/posix-cpu-timers.c733
1 files changed, 322 insertions, 411 deletions
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 05bb7173850e..c7f31aa272f7 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -9,6 +9,9 @@
#include <asm/uaccess.h>
#include <linux/kernel_stat.h>
#include <trace/events/timer.h>
+#include <linux/random.h>
+#include <linux/tick.h>
+#include <linux/workqueue.h>
/*
* Called after updating RLIMIT_CPU to run cpu timer and update
@@ -48,72 +51,28 @@ static int check_clock(const clockid_t which_clock)
return error;
}
-static inline union cpu_time_count
+static inline unsigned long long
timespec_to_sample(const clockid_t which_clock, const struct timespec *tp)
{
- union cpu_time_count ret;
- ret.sched = 0; /* high half always zero when .cpu used */
+ unsigned long long ret;
+
+ ret = 0; /* high half always zero when .cpu used */
if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
- ret.sched = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec;
+ ret = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec;
} else {
- ret.cpu = timespec_to_cputime(tp);
+ ret = cputime_to_expires(timespec_to_cputime(tp));
}
return ret;
}
static void sample_to_timespec(const clockid_t which_clock,
- union cpu_time_count cpu,
+ unsigned long long expires,
struct timespec *tp)
{
if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED)
- *tp = ns_to_timespec(cpu.sched);
+ *tp = ns_to_timespec(expires);
else
- cputime_to_timespec(cpu.cpu, tp);
-}
-
-static inline int cpu_time_before(const clockid_t which_clock,
- union cpu_time_count now,
- union cpu_time_count then)
-{
- if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
- return now.sched < then.sched;
- } else {
- return cputime_lt(now.cpu, then.cpu);
- }
-}
-static inline void cpu_time_add(const clockid_t which_clock,
- union cpu_time_count *acc,
- union cpu_time_count val)
-{
- if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
- acc->sched += val.sched;
- } else {
- acc->cpu = cputime_add(acc->cpu, val.cpu);
- }
-}
-static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock,
- union cpu_time_count a,
- union cpu_time_count b)
-{
- if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
- a.sched -= b.sched;
- } else {
- a.cpu = cputime_sub(a.cpu, b.cpu);
- }
- return a;
-}
-
-/*
- * Divide and limit the result to res >= 1
- *
- * This is necessary to prevent signal delivery starvation, when the result of
- * the division would be rounded down to 0.
- */
-static inline cputime_t cputime_div_non_zero(cputime_t time, unsigned long div)
-{
- cputime_t res = cputime_div(time, div);
-
- return max_t(cputime_t, res, 1);
+ cputime_to_timespec((__force cputime_t)expires, tp);
}
/*
@@ -121,62 +80,68 @@ static inline cputime_t cputime_div_non_zero(cputime_t time, unsigned long div)
* given the current clock sample.
*/
static void bump_cpu_timer(struct k_itimer *timer,
- union cpu_time_count now)
+ unsigned long long now)
{
int i;
+ unsigned long long delta, incr;
- if (timer->it.cpu.incr.sched == 0)
+ if (timer->it.cpu.incr == 0)
return;
- if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
- unsigned long long delta, incr;
+ if (now < timer->it.cpu.expires)
+ return;
- if (now.sched < timer->it.cpu.expires.sched)
- return;
- incr = timer->it.cpu.incr.sched;
- delta = now.sched + incr - timer->it.cpu.expires.sched;
- /* 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.expires.sched += incr;
- timer->it_overrun += 1 << i;
- delta -= incr;
- }
- } else {
- cputime_t delta, incr;
+ incr = timer->it.cpu.incr;
+ delta = now + incr - timer->it.cpu.expires;
- if (cputime_lt(now.cpu, timer->it.cpu.expires.cpu))
- return;
- incr = timer->it.cpu.incr.cpu;
- delta = cputime_sub(cputime_add(now.cpu, incr),
- timer->it.cpu.expires.cpu);
- /* Don't use (incr*2 < delta), incr*2 might overflow. */
- for (i = 0; cputime_lt(incr, cputime_sub(delta, incr)); i++)
- incr = cputime_add(incr, incr);
- for (; i >= 0; incr = cputime_halve(incr), i--) {
- if (cputime_lt(delta, incr))
- continue;
- timer->it.cpu.expires.cpu =
- cputime_add(timer->it.cpu.expires.cpu, incr);
- timer->it_overrun += 1 << i;
- delta = cputime_sub(delta, incr);
- }
+ /* 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.expires += incr;
+ timer->it_overrun += 1 << i;
+ delta -= incr;
}
}
-static inline cputime_t prof_ticks(struct task_struct *p)
+/**
+ * task_cputime_zero - Check a task_cputime struct for all zero fields.
+ *
+ * @cputime: The struct to compare.
+ *
+ * Checks @cputime to see if all fields are zero. Returns true if all fields
+ * are zero, false if any field is nonzero.
+ */
+static inline int task_cputime_zero(const struct task_cputime *cputime)
+{
+ if (!cputime->utime && !cputime->stime && !cputime->sum_exec_runtime)
+ return 1;
+ return 0;
+}
+
+static inline unsigned long long prof_ticks(struct task_struct *p)
{
- return cputime_add(p->utime, p->stime);
+ cputime_t utime, stime;
+
+ task_cputime(p, &utime, &stime);
+
+ return cputime_to_expires(utime + stime);
}
-static inline cputime_t virt_ticks(struct task_struct *p)
+static inline unsigned long long virt_ticks(struct task_struct *p)
{
- return p->utime;
+ cputime_t utime;
+
+ task_cputime(p, &utime, NULL);
+
+ return cputime_to_expires(utime);
}
-int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
+static int
+posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
{
int error = check_clock(which_clock);
if (!error) {
@@ -194,7 +159,8 @@ int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
return error;
}
-int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
+static int
+posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
{
/*
* You can never reset a CPU clock, but we check for other errors
@@ -212,54 +178,30 @@ int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
* Sample a per-thread clock for the given task.
*/
static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
- union cpu_time_count *cpu)
+ unsigned long long *sample)
{
switch (CPUCLOCK_WHICH(which_clock)) {
default:
return -EINVAL;
case CPUCLOCK_PROF:
- cpu->cpu = prof_ticks(p);
+ *sample = prof_ticks(p);
break;
case CPUCLOCK_VIRT:
- cpu->cpu = virt_ticks(p);
+ *sample = virt_ticks(p);
break;
case CPUCLOCK_SCHED:
- cpu->sched = task_sched_runtime(p);
+ *sample = task_sched_runtime(p);
break;
}
return 0;
}
-void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
-{
- struct signal_struct *sig = tsk->signal;
- struct task_struct *t;
-
- times->utime = sig->utime;
- times->stime = sig->stime;
- times->sum_exec_runtime = sig->sum_sched_runtime;
-
- rcu_read_lock();
- /* make sure we can trust tsk->thread_group list */
- if (!likely(pid_alive(tsk)))
- goto out;
-
- t = tsk;
- do {
- times->utime = cputime_add(times->utime, t->utime);
- times->stime = cputime_add(times->stime, t->stime);
- times->sum_exec_runtime += t->se.sum_exec_runtime;
- } while_each_thread(tsk, t);
-out:
- rcu_read_unlock();
-}
-
static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
{
- if (cputime_gt(b->utime, a->utime))
+ if (b->utime > a->utime)
a->utime = b->utime;
- if (cputime_gt(b->stime, a->stime))
+ if (b->stime > a->stime)
a->stime = b->stime;
if (b->sum_exec_runtime > a->sum_exec_runtime)
@@ -272,9 +214,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
struct task_cputime sum;
unsigned long flags;
- spin_lock_irqsave(&cputimer->lock, flags);
if (!cputimer->running) {
- cputimer->running = 1;
/*
* The POSIX timer interface allows for absolute time expiry
* values through the TIMER_ABSTIME flag, therefore we have
@@ -282,10 +222,13 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
* it.
*/
thread_group_cputime(tsk, &sum);
+ raw_spin_lock_irqsave(&cputimer->lock, flags);
+ cputimer->running = 1;
update_gt_cputime(&cputimer->cputime, &sum);
- }
+ } else
+ raw_spin_lock_irqsave(&cputimer->lock, flags);
*times = cputimer->cputime;
- spin_unlock_irqrestore(&cputimer->lock, flags);
+ raw_spin_unlock_irqrestore(&cputimer->lock, flags);
}
/*
@@ -294,7 +237,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
*/
static int cpu_clock_sample_group(const clockid_t which_clock,
struct task_struct *p,
- union cpu_time_count *cpu)
+ unsigned long long *sample)
{
struct task_cputime cputime;
@@ -303,25 +246,26 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
return -EINVAL;
case CPUCLOCK_PROF:
thread_group_cputime(p, &cputime);
- cpu->cpu = cputime_add(cputime.utime, cputime.stime);
+ *sample = cputime_to_expires(cputime.utime + cputime.stime);
break;
case CPUCLOCK_VIRT:
thread_group_cputime(p, &cputime);
- cpu->cpu = cputime.utime;
+ *sample = cputime_to_expires(cputime.utime);
break;
case CPUCLOCK_SCHED:
- cpu->sched = thread_group_sched_runtime(p);
+ thread_group_cputime(p, &cputime);
+ *sample = cputime.sum_exec_runtime;
break;
}
return 0;
}
-int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
+static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
{
const pid_t pid = CPUCLOCK_PID(which_clock);
int error = -EINVAL;
- union cpu_time_count rtn;
+ unsigned long long rtn;
if (pid == 0) {
/*
@@ -379,7 +323,7 @@ int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
* 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)
+static int posix_cpu_timer_create(struct k_itimer *new_timer)
{
int ret = 0;
const pid_t pid = CPUCLOCK_PID(new_timer->it_clock);
@@ -425,7 +369,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
* 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.)
*/
-int posix_cpu_timer_del(struct k_itimer *timer)
+static int posix_cpu_timer_del(struct k_itimer *timer)
{
struct task_struct *p = timer->it.cpu.task;
int ret = 0;
@@ -455,6 +399,15 @@ int posix_cpu_timer_del(struct k_itimer *timer)
return ret;
}
+static void cleanup_timers_list(struct list_head *head,
+ unsigned long long curr)
+{
+ struct cpu_timer_list *timer, *next;
+
+ list_for_each_entry_safe(timer, next, head, entry)
+ list_del_init(&timer->entry);
+}
+
/*
* Clean out CPU timers still ticking when a thread exited. The task
* pointer is cleared, and the expiry time is replaced with the residual
@@ -465,39 +418,12 @@ static void cleanup_timers(struct list_head *head,
cputime_t utime, cputime_t stime,
unsigned long long sum_exec_runtime)
{
- struct cpu_timer_list *timer, *next;
- cputime_t ptime = cputime_add(utime, stime);
- list_for_each_entry_safe(timer, next, head, entry) {
- list_del_init(&timer->entry);
- if (cputime_lt(timer->expires.cpu, ptime)) {
- timer->expires.cpu = cputime_zero;
- } else {
- timer->expires.cpu = cputime_sub(timer->expires.cpu,
- ptime);
- }
- }
-
- ++head;
- list_for_each_entry_safe(timer, next, head, entry) {
- list_del_init(&timer->entry);
- if (cputime_lt(timer->expires.cpu, utime)) {
- timer->expires.cpu = cputime_zero;
- } else {
- timer->expires.cpu = cputime_sub(timer->expires.cpu,
- utime);
- }
- }
+ cputime_t ptime = utime + stime;
- ++head;
- list_for_each_entry_safe(timer, next, head, entry) {
- list_del_init(&timer->entry);
- if (timer->expires.sched < sum_exec_runtime) {
- timer->expires.sched = 0;
- } else {
- timer->expires.sched -= sum_exec_runtime;
- }
- }
+ cleanup_timers_list(head, cputime_to_expires(ptime));
+ cleanup_timers_list(++head, cputime_to_expires(utime));
+ cleanup_timers_list(++head, sum_exec_runtime);
}
/*
@@ -507,37 +433,46 @@ static void cleanup_timers(struct list_head *head,
*/
void posix_cpu_timers_exit(struct task_struct *tsk)
{
+ cputime_t utime, stime;
+
+ add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
+ sizeof(unsigned long long));
+ task_cputime(tsk, &utime, &stime);
cleanup_timers(tsk->cpu_timers,
- tsk->utime, tsk->stime, tsk->se.sum_exec_runtime);
+ utime, stime, tsk->se.sum_exec_runtime);
}
void posix_cpu_timers_exit_group(struct task_struct *tsk)
{
struct signal_struct *const sig = tsk->signal;
+ cputime_t utime, stime;
+ task_cputime(tsk, &utime, &stime);
cleanup_timers(tsk->signal->cpu_timers,
- cputime_add(tsk->utime, sig->utime),
- cputime_add(tsk->stime, sig->stime),
+ utime + sig->utime, 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)
+static void clear_dead_task(struct k_itimer *itimer, unsigned long long now)
{
+ struct cpu_timer_list *timer = &itimer->it.cpu;
+
/*
* That's all for this thread or process.
* We leave our residual in expires to be reported.
*/
- put_task_struct(timer->it.cpu.task);
- timer->it.cpu.task = NULL;
- timer->it.cpu.expires = cpu_time_sub(timer->it_clock,
- timer->it.cpu.expires,
- now);
+ put_task_struct(timer->task);
+ timer->task = NULL;
+ if (timer->expires < now) {
+ timer->expires = 0;
+ } else {
+ timer->expires -= now;
+ }
}
static inline int expires_gt(cputime_t expires, cputime_t new_exp)
{
- return cputime_eq(expires, cputime_zero) ||
- cputime_gt(expires, new_exp);
+ return expires == 0 || expires > new_exp;
}
/*
@@ -564,14 +499,14 @@ static void arm_timer(struct k_itimer *timer)
listpos = head;
list_for_each_entry(next, head, entry) {
- if (cpu_time_before(timer->it_clock, nt->expires, next->expires))
+ if (nt->expires < next->expires)
break;
listpos = &next->entry;
}
list_add(&nt->entry, listpos);
if (listpos == head) {
- union cpu_time_count *exp = &nt->expires;
+ unsigned long long exp = nt->expires;
/*
* We are the new earliest-expiring POSIX 1.b timer, hence
@@ -582,17 +517,17 @@ static void arm_timer(struct k_itimer *timer)
switch (CPUCLOCK_WHICH(timer->it_clock)) {
case CPUCLOCK_PROF:
- if (expires_gt(cputime_expires->prof_exp, exp->cpu))
- cputime_expires->prof_exp = exp->cpu;
+ if (expires_gt(cputime_expires->prof_exp, expires_to_cputime(exp)))
+ cputime_expires->prof_exp = expires_to_cputime(exp);
break;
case CPUCLOCK_VIRT:
- if (expires_gt(cputime_expires->virt_exp, exp->cpu))
- cputime_expires->virt_exp = exp->cpu;
+ if (expires_gt(cputime_expires->virt_exp, expires_to_cputime(exp)))
+ cputime_expires->virt_exp = expires_to_cputime(exp);
break;
case CPUCLOCK_SCHED:
if (cputime_expires->sched_exp == 0 ||
- cputime_expires->sched_exp > exp->sched)
- cputime_expires->sched_exp = exp->sched;
+ cputime_expires->sched_exp > exp)
+ cputime_expires->sched_exp = exp;
break;
}
}
@@ -607,20 +542,20 @@ static void cpu_timer_fire(struct k_itimer *timer)
/*
* User don't want any signal.
*/
- timer->it.cpu.expires.sched = 0;
+ timer->it.cpu.expires = 0;
} else if (unlikely(timer->sigq == NULL)) {
/*
* This a special case for clock_nanosleep,
* not a normal timer from sys_timer_create.
*/
wake_up_process(timer->it_process);
- timer->it.cpu.expires.sched = 0;
- } else if (timer->it.cpu.incr.sched == 0) {
+ timer->it.cpu.expires = 0;
+ } else if (timer->it.cpu.incr == 0) {
/*
* One-shot timer. Clear it as soon as it's fired.
*/
posix_timer_event(timer, 0);
- timer->it.cpu.expires.sched = 0;
+ timer->it.cpu.expires = 0;
} else if (posix_timer_event(timer, ++timer->it_requeue_pending)) {
/*
* The signal did not get queued because the signal
@@ -638,7 +573,7 @@ static void cpu_timer_fire(struct k_itimer *timer)
*/
static int cpu_timer_sample_group(const clockid_t which_clock,
struct task_struct *p,
- union cpu_time_count *cpu)
+ unsigned long long *sample)
{
struct task_cputime cputime;
@@ -647,29 +582,60 @@ static int cpu_timer_sample_group(const clockid_t which_clock,
default:
return -EINVAL;
case CPUCLOCK_PROF:
- cpu->cpu = cputime_add(cputime.utime, cputime.stime);
+ *sample = cputime_to_expires(cputime.utime + cputime.stime);
break;
case CPUCLOCK_VIRT:
- cpu->cpu = cputime.utime;
+ *sample = cputime_to_expires(cputime.utime);
break;
case CPUCLOCK_SCHED:
- cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
+ *sample = cputime.sum_exec_runtime + task_delta_exec(p);
break;
}
return 0;
}
+#ifdef CONFIG_NO_HZ_FULL
+static void nohz_kick_work_fn(struct work_struct *work)
+{
+ tick_nohz_full_kick_all();
+}
+
+static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn);
+
+/*
+ * We need the IPIs to be sent from sane process context.
+ * The posix cpu timers are always set with irqs disabled.
+ */
+static void posix_cpu_timer_kick_nohz(void)
+{
+ schedule_work(&nohz_kick_work);
+}
+
+bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk)
+{
+ if (!task_cputime_zero(&tsk->cputime_expires))
+ return false;
+
+ if (tsk->signal->cputimer.running)
+ return false;
+
+ return true;
+}
+#else
+static inline void posix_cpu_timer_kick_nohz(void) { }
+#endif
+
/*
* 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.)
*/
-int posix_cpu_timer_set(struct k_itimer *timer, int flags,
- struct itimerspec *new, struct itimerspec *old)
+static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
+ struct itimerspec *new, struct itimerspec *old)
{
struct task_struct *p = timer->it.cpu.task;
- union cpu_time_count old_expires, new_expires, old_incr, val;
+ unsigned long long old_expires, new_expires, old_incr, val;
int ret;
if (unlikely(p == NULL)) {
@@ -724,7 +690,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
}
if (old) {
- if (old_expires.sched == 0) {
+ if (old_expires == 0) {
old->it_value.tv_sec = 0;
old->it_value.tv_nsec = 0;
} else {
@@ -739,11 +705,8 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
* new setting.
*/
bump_cpu_timer(timer, val);
- if (cpu_time_before(timer->it_clock, val,
- timer->it.cpu.expires)) {
- old_expires = cpu_time_sub(
- timer->it_clock,
- timer->it.cpu.expires, val);
+ if (val < timer->it.cpu.expires) {
+ old_expires = timer->it.cpu.expires - val;
sample_to_timespec(timer->it_clock,
old_expires,
&old->it_value);
@@ -766,8 +729,8 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
goto out;
}
- if (new_expires.sched != 0 && !(flags & TIMER_ABSTIME)) {
- cpu_time_add(timer->it_clock, &new_expires, val);
+ if (new_expires != 0 && !(flags & TIMER_ABSTIME)) {
+ new_expires += val;
}
/*
@@ -776,8 +739,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
* arm the timer (we'll just fake it for timer_gettime).
*/
timer->it.cpu.expires = new_expires;
- if (new_expires.sched != 0 &&
- cpu_time_before(timer->it_clock, val, new_expires)) {
+ if (new_expires != 0 && val < new_expires) {
arm_timer(timer);
}
@@ -801,8 +763,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
timer->it_overrun_last = 0;
timer->it_overrun = -1;
- if (new_expires.sched != 0 &&
- !cpu_time_before(timer->it_clock, val, new_expires)) {
+ if (new_expires != 0 && !(val < new_expires)) {
/*
* The designated time already passed, so we notify
* immediately, even if the thread never runs to
@@ -817,12 +778,14 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
sample_to_timespec(timer->it_clock,
old_incr, &old->it_interval);
}
+ if (!ret)
+ posix_cpu_timer_kick_nohz();
return ret;
}
-void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
+static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
{
- union cpu_time_count now;
+ unsigned long long now;
struct task_struct *p = timer->it.cpu.task;
int clear_dead;
@@ -832,7 +795,7 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
sample_to_timespec(timer->it_clock,
timer->it.cpu.incr, &itp->it_interval);
- if (timer->it.cpu.expires.sched == 0) { /* Timer not armed at all. */
+ if (timer->it.cpu.expires == 0) { /* Timer not armed at all. */
itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
return;
}
@@ -864,7 +827,7 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
*/
put_task_struct(p);
timer->it.cpu.task = NULL;
- timer->it.cpu.expires.sched = 0;
+ timer->it.cpu.expires = 0;
read_unlock(&tasklist_lock);
goto dead;
} else {
@@ -885,10 +848,9 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
goto dead;
}
- if (cpu_time_before(timer->it_clock, now, timer->it.cpu.expires)) {
+ if (now < timer->it.cpu.expires) {
sample_to_timespec(timer->it_clock,
- cpu_time_sub(timer->it_clock,
- timer->it.cpu.expires, now),
+ timer->it.cpu.expires - now,
&itp->it_value);
} else {
/*
@@ -900,6 +862,28 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
}
}
+static unsigned long long
+check_timers_list(struct list_head *timers,
+ struct list_head *firing,
+ unsigned long long curr)
+{
+ int maxfire = 20;
+
+ while (!list_empty(timers)) {
+ struct cpu_timer_list *t;
+
+ t = list_first_entry(timers, struct cpu_timer_list, entry);
+
+ if (!--maxfire || curr < t->expires)
+ return t->expires;
+
+ t->firing = 1;
+ list_move_tail(&t->entry, firing);
+ }
+
+ return 0;
+}
+
/*
* 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
@@ -908,54 +892,20 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
static void check_thread_timers(struct task_struct *tsk,
struct list_head *firing)
{
- int maxfire;
struct list_head *timers = tsk->cpu_timers;
struct signal_struct *const sig = tsk->signal;
+ struct task_cputime *tsk_expires = &tsk->cputime_expires;
+ unsigned long long expires;
unsigned long soft;
- maxfire = 20;
- tsk->cputime_expires.prof_exp = cputime_zero;
- while (!list_empty(timers)) {
- struct cpu_timer_list *t = list_first_entry(timers,
- struct cpu_timer_list,
- entry);
- if (!--maxfire || cputime_lt(prof_ticks(tsk), t->expires.cpu)) {
- tsk->cputime_expires.prof_exp = t->expires.cpu;
- break;
- }
- t->firing = 1;
- list_move_tail(&t->entry, firing);
- }
+ expires = check_timers_list(timers, firing, prof_ticks(tsk));
+ tsk_expires->prof_exp = expires_to_cputime(expires);
- ++timers;
- maxfire = 20;
- tsk->cputime_expires.virt_exp = cputime_zero;
- while (!list_empty(timers)) {
- struct cpu_timer_list *t = list_first_entry(timers,
- struct cpu_timer_list,
- entry);
- if (!--maxfire || cputime_lt(virt_ticks(tsk), t->expires.cpu)) {
- tsk->cputime_expires.virt_exp = t->expires.cpu;
- break;
- }
- t->firing = 1;
- list_move_tail(&t->entry, firing);
- }
+ expires = check_timers_list(++timers, firing, virt_ticks(tsk));
+ tsk_expires->virt_exp = expires_to_cputime(expires);
- ++timers;
- maxfire = 20;
- tsk->cputime_expires.sched_exp = 0;
- while (!list_empty(timers)) {
- struct cpu_timer_list *t = list_first_entry(timers,
- struct cpu_timer_list,
- entry);
- if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) {
- tsk->cputime_expires.sched_exp = t->expires.sched;
- break;
- }
- t->firing = 1;
- list_move_tail(&t->entry, firing);
- }
+ tsk_expires->sched_exp = check_timers_list(++timers, firing,
+ tsk->se.sum_exec_runtime);
/*
* Check for the special case thread timers.
@@ -995,30 +945,30 @@ static void stop_process_timers(struct signal_struct *sig)
struct thread_group_cputimer *cputimer = &sig->cputimer;
unsigned long flags;
- spin_lock_irqsave(&cputimer->lock, flags);
+ raw_spin_lock_irqsave(&cputimer->lock, flags);
cputimer->running = 0;
- spin_unlock_irqrestore(&cputimer->lock, flags);
+ raw_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)
+ unsigned long long *expires,
+ unsigned long long cur_time, int signo)
{
- if (cputime_eq(it->expires, cputime_zero))
+ if (!it->expires)
return;
- if (cputime_ge(cur_time, it->expires)) {
- if (!cputime_eq(it->incr, cputime_zero)) {
- it->expires = cputime_add(it->expires, it->incr);
+ if (cur_time >= it->expires) {
+ if (it->incr) {
+ it->expires += it->incr;
it->error += it->incr_error;
if (it->error >= onecputick) {
- it->expires = cputime_sub(it->expires,
- cputime_one_jiffy);
+ it->expires -= cputime_one_jiffy;
it->error -= onecputick;
}
} else {
- it->expires = cputime_zero;
+ it->expires = 0;
}
trace_itimer_expire(signo == SIGPROF ?
@@ -1027,30 +977,11 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
__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))) {
+ if (it->expires && (!*expires || it->expires < *expires)) {
*expires = it->expires;
}
}
-/**
- * task_cputime_zero - Check a task_cputime struct for all zero fields.
- *
- * @cputime: The struct to compare.
- *
- * Checks @cputime to see if all fields are zero. Returns true if all fields
- * are zero, false if any field is nonzero.
- */
-static inline int task_cputime_zero(const struct task_cputime *cputime)
-{
- if (cputime_eq(cputime->utime, cputime_zero) &&
- cputime_eq(cputime->stime, cputime_zero) &&
- cputime->sum_exec_runtime == 0)
- return 1;
- return 0;
-}
-
/*
* 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
@@ -1059,9 +990,8 @@ static inline int task_cputime_zero(const struct task_cputime *cputime)
static void check_process_timers(struct task_struct *tsk,
struct list_head *firing)
{
- int maxfire;
struct signal_struct *const sig = tsk->signal;
- cputime_t utime, ptime, virt_expires, prof_expires;
+ unsigned long long utime, ptime, virt_expires, prof_expires;
unsigned long long sum_sched_runtime, sched_expires;
struct list_head *timers = sig->cpu_timers;
struct task_cputime cputime;
@@ -1071,52 +1001,13 @@ static void check_process_timers(struct task_struct *tsk,
* Collect the current process totals.
*/
thread_group_cputimer(tsk, &cputime);
- utime = cputime.utime;
- ptime = cputime_add(utime, cputime.stime);
+ utime = cputime_to_expires(cputime.utime);
+ ptime = utime + cputime_to_expires(cputime.stime);
sum_sched_runtime = cputime.sum_exec_runtime;
- maxfire = 20;
- prof_expires = cputime_zero;
- while (!list_empty(timers)) {
- struct cpu_timer_list *tl = list_first_entry(timers,
- struct cpu_timer_list,
- entry);
- if (!--maxfire || cputime_lt(ptime, tl->expires.cpu)) {
- prof_expires = tl->expires.cpu;
- break;
- }
- tl->firing = 1;
- list_move_tail(&tl->entry, firing);
- }
-
- ++timers;
- maxfire = 20;
- virt_expires = cputime_zero;
- while (!list_empty(timers)) {
- struct cpu_timer_list *tl = list_first_entry(timers,
- struct cpu_timer_list,
- entry);
- if (!--maxfire || cputime_lt(utime, tl->expires.cpu)) {
- virt_expires = tl->expires.cpu;
- break;
- }
- tl->firing = 1;
- list_move_tail(&tl->entry, firing);
- }
- ++timers;
- maxfire = 20;
- sched_expires = 0;
- while (!list_empty(timers)) {
- struct cpu_timer_list *tl = list_first_entry(timers,
- struct cpu_timer_list,
- entry);
- if (!--maxfire || sum_sched_runtime < tl->expires.sched) {
- sched_expires = tl->expires.sched;
- break;
- }
- tl->firing = 1;
- list_move_tail(&tl->entry, firing);
- }
+ prof_expires = check_timers_list(timers, firing, ptime);
+ virt_expires = check_timers_list(++timers, firing, utime);
+ sched_expires = check_timers_list(++timers, firing, sum_sched_runtime);
/*
* Check for the special case process timers.
@@ -1150,14 +1041,13 @@ static void check_process_timers(struct task_struct *tsk,
}
}
x = secs_to_cputime(soft);
- if (cputime_eq(prof_expires, cputime_zero) ||
- cputime_lt(x, prof_expires)) {
+ if (!prof_expires || x < prof_expires) {
prof_expires = x;
}
}
- sig->cputime_expires.prof_exp = prof_expires;
- sig->cputime_expires.virt_exp = virt_expires;
+ sig->cputime_expires.prof_exp = expires_to_cputime(prof_expires);
+ sig->cputime_expires.virt_exp = expires_to_cputime(virt_expires);
sig->cputime_expires.sched_exp = sched_expires;
if (task_cputime_zero(&sig->cputime_expires))
stop_process_timers(sig);
@@ -1170,7 +1060,7 @@ static void check_process_timers(struct task_struct *tsk,
void posix_cpu_timer_schedule(struct k_itimer *timer)
{
struct task_struct *p = timer->it.cpu.task;
- union cpu_time_count now;
+ unsigned long long now;
if (unlikely(p == NULL))
/*
@@ -1199,7 +1089,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
*/
put_task_struct(p);
timer->it.cpu.task = p = NULL;
- timer->it.cpu.expires.sched = 0;
+ timer->it.cpu.expires = 0;
goto out_unlock;
} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
/*
@@ -1207,6 +1097,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
* not yet reaped. Take this opportunity to
* drop our task ref.
*/
+ cpu_timer_sample_group(timer->it_clock, p, &now);
clear_dead_task(timer, now);
goto out_unlock;
}
@@ -1245,12 +1136,9 @@ out:
static inline int task_cputime_expired(const struct task_cputime *sample,
const struct task_cputime *expires)
{
- if (!cputime_eq(expires->utime, cputime_zero) &&
- cputime_ge(sample->utime, expires->utime))
+ if (expires->utime && sample->utime >= expires->utime)
return 1;
- if (!cputime_eq(expires->stime, cputime_zero) &&
- cputime_ge(cputime_add(sample->utime, sample->stime),
- expires->stime))
+ if (expires->stime && sample->utime + sample->stime >= expires->stime)
return 1;
if (expires->sum_exec_runtime != 0 &&
sample->sum_exec_runtime >= expires->sum_exec_runtime)
@@ -1271,11 +1159,14 @@ static inline int task_cputime_expired(const struct task_cputime *sample,
static inline int fastpath_timer_check(struct task_struct *tsk)
{
struct signal_struct *sig;
+ cputime_t utime, stime;
+
+ task_cputime(tsk, &utime, &stime);
if (!task_cputime_zero(&tsk->cputime_expires)) {
struct task_cputime task_sample = {
- .utime = tsk->utime,
- .stime = tsk->stime,
+ .utime = utime,
+ .stime = stime,
.sum_exec_runtime = tsk->se.sum_exec_runtime
};
@@ -1287,9 +1178,9 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
if (sig->cputimer.running) {
struct task_cputime group_sample;
- spin_lock(&sig->cputimer.lock);
+ raw_spin_lock(&sig->cputimer.lock);
group_sample = sig->cputimer.cputime;
- spin_unlock(&sig->cputimer.lock);
+ raw_spin_unlock(&sig->cputimer.lock);
if (task_cputime_expired(&group_sample, &sig->cputime_expires))
return 1;
@@ -1345,7 +1236,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
/*
* Now that all the timers on our list have the firing flag,
- * noone will touch their list entries but us. We'll take
+ * 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.
*/
@@ -1365,6 +1256,13 @@ void run_posix_cpu_timers(struct task_struct *tsk)
cpu_timer_fire(timer);
spin_unlock(&timer->it_lock);
}
+
+ /*
+ * In case some timers were rescheduled after the queue got emptied,
+ * wake up full dynticks CPUs.
+ */
+ if (tsk->signal->cputimer.running)
+ posix_cpu_timer_kick_nohz();
}
/*
@@ -1374,7 +1272,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
cputime_t *newval, cputime_t *oldval)
{
- union cpu_time_count now;
+ unsigned long long now;
BUG_ON(clock_idx == CPUCLOCK_SCHED);
cpu_timer_sample_group(clock_idx, tsk, &now);
@@ -1385,18 +1283,18 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
* 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)) {
+ if (*oldval) {
+ if (*oldval <= now) {
/* Just about to fire. */
*oldval = cputime_one_jiffy;
} else {
- *oldval = cputime_sub(*oldval, now.cpu);
+ *oldval -= now;
}
}
- if (cputime_eq(*newval, cputime_zero))
- return;
- *newval = cputime_add(*newval, now.cpu);
+ if (!*newval)
+ goto out;
+ *newval += now;
}
/*
@@ -1413,6 +1311,8 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
tsk->signal->cputime_expires.virt_exp = *newval;
break;
}
+out:
+ posix_cpu_timer_kick_nohz();
}
static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
@@ -1444,10 +1344,12 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
}
while (!signal_pending(current)) {
- if (timer.it.cpu.expires.sched == 0) {
+ if (timer.it.cpu.expires == 0) {
/*
- * Our timer fired and was reset.
+ * Our timer fired and was reset, below
+ * deletion can not fail.
*/
+ posix_cpu_timer_del(&timer);
spin_unlock_irq(&timer.it_lock);
return 0;
}
@@ -1465,9 +1367,26 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
* We were interrupted by a signal.
*/
sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp);
- posix_cpu_timer_set(&timer, 0, &zero_it, it);
+ 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);
+ }
spin_unlock_irq(&timer.it_lock);
+ while (error == TIMER_RETRY) {
+ /*
+ * We need to handle case when timer was or is in the
+ * middle of firing. In other cases we already freed
+ * resources.
+ */
+ spin_lock_irq(&timer.it_lock);
+ 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.
@@ -1481,11 +1400,13 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
return error;
}
-int posix_cpu_nsleep(const clockid_t which_clock, int flags,
- struct timespec *rqtp, struct timespec __user *rmtp)
+static long posix_cpu_nsleep_restart(struct restart_block *restart_block);
+
+static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
+ struct timespec *rqtp, struct timespec __user *rmtp)
{
struct restart_block *restart_block =
- &current_thread_info()->restart_block;
+ &current_thread_info()->restart_block;
struct itimerspec it;
int error;
@@ -1501,56 +1422,47 @@ int posix_cpu_nsleep(const clockid_t which_clock, int flags,
if (error == -ERESTART_RESTARTBLOCK) {
- if (flags & TIMER_ABSTIME)
+ if (flags & TIMER_ABSTIME)
return -ERESTARTNOHAND;
/*
- * Report back to the user the time still remaining.
- */
- if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+ * Report back to the user the time still remaining.
+ */
+ if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
return -EFAULT;
restart_block->fn = posix_cpu_nsleep_restart;
- restart_block->arg0 = which_clock;
- restart_block->arg1 = (unsigned long) rmtp;
- restart_block->arg2 = rqtp->tv_sec;
- restart_block->arg3 = rqtp->tv_nsec;
+ restart_block->nanosleep.clockid = which_clock;
+ restart_block->nanosleep.rmtp = rmtp;
+ restart_block->nanosleep.expires = timespec_to_ns(rqtp);
}
return error;
}
-long posix_cpu_nsleep_restart(struct restart_block *restart_block)
+static long posix_cpu_nsleep_restart(struct restart_block *restart_block)
{
- clockid_t which_clock = restart_block->arg0;
- struct timespec __user *rmtp;
+ clockid_t which_clock = restart_block->nanosleep.clockid;
struct timespec t;
struct itimerspec it;
int error;
- rmtp = (struct timespec __user *) restart_block->arg1;
- t.tv_sec = restart_block->arg2;
- t.tv_nsec = restart_block->arg3;
+ t = ns_to_timespec(restart_block->nanosleep.expires);
- restart_block->fn = do_no_restart_syscall;
error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it);
if (error == -ERESTART_RESTARTBLOCK) {
+ struct timespec __user *rmtp = restart_block->nanosleep.rmtp;
/*
- * Report back to the user the time still remaining.
- */
- if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+ * Report back to the user the time still remaining.
+ */
+ if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
return -EFAULT;
- restart_block->fn = posix_cpu_nsleep_restart;
- restart_block->arg0 = which_clock;
- restart_block->arg1 = (unsigned long) rmtp;
- restart_block->arg2 = t.tv_sec;
- restart_block->arg3 = t.tv_nsec;
+ restart_block->nanosleep.expires = timespec_to_ns(&t);
}
return error;
}
-
#define PROCESS_CLOCK MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED)
#define THREAD_CLOCK MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED)
@@ -1594,38 +1506,37 @@ static int thread_cpu_timer_create(struct k_itimer *timer)
timer->it_clock = THREAD_CLOCK;
return posix_cpu_timer_create(timer);
}
-static int thread_cpu_nsleep(const clockid_t which_clock, int flags,
- struct timespec *rqtp, struct timespec __user *rmtp)
-{
- return -EINVAL;
-}
-static long thread_cpu_nsleep_restart(struct restart_block *restart_block)
-{
- return -EINVAL;
-}
+
+struct k_clock clock_posix_cpu = {
+ .clock_getres = posix_cpu_clock_getres,
+ .clock_set = posix_cpu_clock_set,
+ .clock_get = posix_cpu_clock_get,
+ .timer_create = posix_cpu_timer_create,
+ .nsleep = posix_cpu_nsleep,
+ .nsleep_restart = posix_cpu_nsleep_restart,
+ .timer_set = posix_cpu_timer_set,
+ .timer_del = posix_cpu_timer_del,
+ .timer_get = posix_cpu_timer_get,
+};
static __init int init_posix_cpu_timers(void)
{
struct k_clock process = {
- .clock_getres = process_cpu_clock_getres,
- .clock_get = process_cpu_clock_get,
- .clock_set = do_posix_clock_nosettime,
- .timer_create = process_cpu_timer_create,
- .nsleep = process_cpu_nsleep,
- .nsleep_restart = process_cpu_nsleep_restart,
+ .clock_getres = process_cpu_clock_getres,
+ .clock_get = process_cpu_clock_get,
+ .timer_create = process_cpu_timer_create,
+ .nsleep = process_cpu_nsleep,
+ .nsleep_restart = process_cpu_nsleep_restart,
};
struct k_clock thread = {
- .clock_getres = thread_cpu_clock_getres,
- .clock_get = thread_cpu_clock_get,
- .clock_set = do_posix_clock_nosettime,
- .timer_create = thread_cpu_timer_create,
- .nsleep = thread_cpu_nsleep,
- .nsleep_restart = thread_cpu_nsleep_restart,
+ .clock_getres = thread_cpu_clock_getres,
+ .clock_get = thread_cpu_clock_get,
+ .timer_create = thread_cpu_timer_create,
};
struct timespec ts;
- register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
- register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
+ posix_timers_register_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
+ posix_timers_register_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
cputime_to_timespec(cputime_one_jiffy, &ts);
onecputick = ts.tv_nsec;