#include <linux/sched.h>
#include <linux/posix-timers.h>
-#include <asm/uaccess.h>
#include <linux/errno.h>
+#include <linux/math64.h>
+#include <asm/uaccess.h>
static int check_clock(const clockid_t which_clock)
{
return 0;
read_lock(&tasklist_lock);
- p = find_task_by_pid(pid);
- if (!p || (CPUCLOCK_PERTHREAD(which_clock) ?
- p->tgid != current->tgid : p->tgid != pid)) {
+ p = find_task_by_vpid(pid);
+ if (!p || !(CPUCLOCK_PERTHREAD(which_clock) ?
+ same_thread_group(p, current) : thread_group_leader(p))) {
error = -EINVAL;
}
read_unlock(&tasklist_lock);
union cpu_time_count cpu,
struct timespec *tp)
{
- if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
- tp->tv_sec = div_long_long_rem(cpu.sched,
- NSEC_PER_SEC, &tp->tv_nsec);
- } else {
+ if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED)
+ *tp = ns_to_timespec(cpu.sched);
+ else
cputime_to_timespec(cpu.cpu, tp);
- }
}
static inline int cpu_time_before(const clockid_t which_clock,
}
/*
+ * 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);
+}
+
+/*
* Update expiry time from increment, and increase overrun count,
* given the current clock sample.
*/
}
static inline unsigned long long sched_ns(struct task_struct *p)
{
- return (p == current) ? current_sched_time(p) : p->sched_time;
+ return task_sched_runtime(p);
}
int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
} while (t != p);
break;
case CPUCLOCK_SCHED:
- cpu->sched = p->signal->sched_time;
+ cpu->sched = p->signal->sum_sched_runtime;
/* Add in each other live thread. */
while ((t = next_thread(t)) != p) {
- cpu->sched += t->sched_time;
+ cpu->sched += t->se.sum_exec_runtime;
}
cpu->sched += sched_ns(p);
break;
* should be able to see it.
*/
struct task_struct *p;
- read_lock(&tasklist_lock);
- p = find_task_by_pid(pid);
+ rcu_read_lock();
+ p = find_task_by_vpid(pid);
if (p) {
if (CPUCLOCK_PERTHREAD(which_clock)) {
- if (p->tgid == current->tgid) {
+ if (same_thread_group(p, current)) {
error = cpu_clock_sample(which_clock,
p, &rtn);
}
- } else if (p->tgid == pid && p->signal) {
- error = cpu_clock_sample_group(which_clock,
- p, &rtn);
+ } else {
+ read_lock(&tasklist_lock);
+ if (thread_group_leader(p) && p->signal) {
+ error =
+ cpu_clock_sample_group(which_clock,
+ p, &rtn);
+ }
+ read_unlock(&tasklist_lock);
}
}
- read_unlock(&tasklist_lock);
+ rcu_read_unlock();
}
if (error)
if (pid == 0) {
p = current;
} else {
- p = find_task_by_pid(pid);
- if (p && p->tgid != current->tgid)
+ p = find_task_by_vpid(pid);
+ if (p && !same_thread_group(p, current))
p = NULL;
}
} else {
if (pid == 0) {
p = current->group_leader;
} else {
- p = find_task_by_pid(pid);
- if (p && p->tgid != pid)
+ p = find_task_by_vpid(pid);
+ if (p && !thread_group_leader(p))
p = NULL;
}
}
*/
static void cleanup_timers(struct list_head *head,
cputime_t utime, cputime_t stime,
- unsigned long long sched_time)
+ unsigned long long sum_exec_runtime)
{
struct cpu_timer_list *timer, *next;
cputime_t ptime = cputime_add(utime, stime);
++head;
list_for_each_entry_safe(timer, next, head, entry) {
list_del_init(&timer->entry);
- if (timer->expires.sched < sched_time) {
+ if (timer->expires.sched < sum_exec_runtime) {
timer->expires.sched = 0;
} else {
- timer->expires.sched -= sched_time;
+ timer->expires.sched -= sum_exec_runtime;
}
}
}
void posix_cpu_timers_exit(struct task_struct *tsk)
{
cleanup_timers(tsk->cpu_timers,
- tsk->utime, tsk->stime, tsk->sched_time);
+ tsk->utime, tsk->stime, tsk->se.sum_exec_runtime);
}
void posix_cpu_timers_exit_group(struct task_struct *tsk)
cleanup_timers(tsk->signal->cpu_timers,
cputime_add(tsk->utime, tsk->signal->utime),
cputime_add(tsk->stime, tsk->signal->stime),
- tsk->sched_time + tsk->signal->sched_time);
+ tsk->se.sum_exec_runtime + tsk->signal->sum_sched_runtime);
}
BUG();
break;
case CPUCLOCK_PROF:
- left = cputime_div(cputime_sub(expires.cpu, val.cpu),
- nthreads);
+ left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu),
+ nthreads);
do {
if (likely(!(t->flags & PF_EXITING))) {
ticks = cputime_add(prof_ticks(t), left);
} while (t != p);
break;
case CPUCLOCK_VIRT:
- left = cputime_div(cputime_sub(expires.cpu, val.cpu),
- nthreads);
+ left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu),
+ nthreads);
do {
if (likely(!(t->flags & PF_EXITING))) {
ticks = cputime_add(virt_ticks(t), left);
case CPUCLOCK_SCHED:
nsleft = expires.sched - val.sched;
do_div(nsleft, nthreads);
+ nsleft = max_t(unsigned long long, nsleft, 1);
do {
if (likely(!(t->flags & PF_EXITING))) {
- ns = t->sched_time + nsleft;
+ ns = t->se.sum_exec_runtime + nsleft;
if (t->it_sched_expires == 0 ||
t->it_sched_expires > ns) {
t->it_sched_expires = ns;
struct cpu_timer_list *next;
unsigned long i;
- if (CPUCLOCK_PERTHREAD(timer->it_clock) && (p->flags & PF_EXITING))
- return;
-
head = (CPUCLOCK_PERTHREAD(timer->it_clock) ?
p->cpu_timers : p->signal->cpu_timers);
head += CPUCLOCK_WHICH(timer->it_clock);
{
int maxfire;
struct list_head *timers = tsk->cpu_timers;
+ struct signal_struct *const sig = tsk->signal;
maxfire = 20;
tsk->it_prof_expires = cputime_zero;
while (!list_empty(timers)) {
- struct cpu_timer_list *t = list_entry(timers->next,
+ struct cpu_timer_list *t = list_first_entry(timers,
struct cpu_timer_list,
entry);
if (!--maxfire || cputime_lt(prof_ticks(tsk), t->expires.cpu)) {
maxfire = 20;
tsk->it_virt_expires = cputime_zero;
while (!list_empty(timers)) {
- struct cpu_timer_list *t = list_entry(timers->next,
+ struct cpu_timer_list *t = list_first_entry(timers,
struct cpu_timer_list,
entry);
if (!--maxfire || cputime_lt(virt_ticks(tsk), t->expires.cpu)) {
maxfire = 20;
tsk->it_sched_expires = 0;
while (!list_empty(timers)) {
- struct cpu_timer_list *t = list_entry(timers->next,
+ struct cpu_timer_list *t = list_first_entry(timers,
struct cpu_timer_list,
entry);
- if (!--maxfire || tsk->sched_time < t->expires.sched) {
+ if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) {
tsk->it_sched_expires = t->expires.sched;
break;
}
t->firing = 1;
list_move_tail(&t->entry, firing);
}
+
+ /*
+ * 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;
+
+ if (hard != RLIM_INFINITY &&
+ tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
+ /*
+ * 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 (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;
+ }
+ __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
+ }
+ }
}
/*
int maxfire;
struct signal_struct *const sig = tsk->signal;
cputime_t utime, stime, ptime, virt_expires, prof_expires;
- unsigned long long sched_time, sched_expires;
+ unsigned long long sum_sched_runtime, sched_expires;
struct task_struct *t;
struct list_head *timers = sig->cpu_timers;
*/
utime = sig->utime;
stime = sig->stime;
- sched_time = sig->sched_time;
+ sum_sched_runtime = sig->sum_sched_runtime;
t = tsk;
do {
utime = cputime_add(utime, t->utime);
stime = cputime_add(stime, t->stime);
- sched_time += t->sched_time;
+ sum_sched_runtime += t->se.sum_exec_runtime;
t = next_thread(t);
} while (t != tsk);
ptime = cputime_add(utime, stime);
maxfire = 20;
prof_expires = cputime_zero;
while (!list_empty(timers)) {
- struct cpu_timer_list *t = list_entry(timers->next,
+ struct cpu_timer_list *tl = list_first_entry(timers,
struct cpu_timer_list,
entry);
- if (!--maxfire || cputime_lt(ptime, t->expires.cpu)) {
- prof_expires = t->expires.cpu;
+ if (!--maxfire || cputime_lt(ptime, tl->expires.cpu)) {
+ prof_expires = tl->expires.cpu;
break;
}
- t->firing = 1;
- list_move_tail(&t->entry, firing);
+ tl->firing = 1;
+ list_move_tail(&tl->entry, firing);
}
++timers;
maxfire = 20;
virt_expires = cputime_zero;
while (!list_empty(timers)) {
- struct cpu_timer_list *t = list_entry(timers->next,
+ struct cpu_timer_list *tl = list_first_entry(timers,
struct cpu_timer_list,
entry);
- if (!--maxfire || cputime_lt(utime, t->expires.cpu)) {
- virt_expires = t->expires.cpu;
+ if (!--maxfire || cputime_lt(utime, tl->expires.cpu)) {
+ virt_expires = tl->expires.cpu;
break;
}
- t->firing = 1;
- list_move_tail(&t->entry, firing);
+ tl->firing = 1;
+ list_move_tail(&tl->entry, firing);
}
++timers;
maxfire = 20;
sched_expires = 0;
while (!list_empty(timers)) {
- struct cpu_timer_list *t = list_entry(timers->next,
+ struct cpu_timer_list *tl = list_first_entry(timers,
struct cpu_timer_list,
entry);
- if (!--maxfire || sched_time < t->expires.sched) {
- sched_expires = t->expires.sched;
+ if (!--maxfire || sum_sched_runtime < tl->expires.sched) {
+ sched_expires = tl->expires.sched;
break;
}
- t->firing = 1;
- list_move_tail(&t->entry, firing);
+ tl->firing = 1;
+ list_move_tail(&tl->entry, firing);
}
/*
prof_left = cputime_sub(prof_expires, utime);
prof_left = cputime_sub(prof_left, stime);
- prof_left = cputime_div(prof_left, nthreads);
+ prof_left = cputime_div_non_zero(prof_left, nthreads);
virt_left = cputime_sub(virt_expires, utime);
- virt_left = cputime_div(virt_left, nthreads);
+ virt_left = cputime_div_non_zero(virt_left, nthreads);
if (sched_expires) {
- sched_left = sched_expires - sched_time;
+ sched_left = sched_expires - sum_sched_runtime;
do_div(sched_left, nthreads);
+ sched_left = max_t(unsigned long long, sched_left, 1);
} else {
sched_left = 0;
}
t->it_virt_expires = ticks;
}
- sched = t->sched_time + sched_left;
+ sched = t->se.sum_exec_runtime + sched_left;
if (sched_expires && (t->it_sched_expires == 0 ||
t->it_sched_expires > sched)) {
t->it_sched_expires = sched;
if (UNEXPIRED(prof) && UNEXPIRED(virt) &&
(tsk->it_sched_expires == 0 ||
- tsk->sched_time < tsk->it_sched_expires))
+ tsk->se.sum_exec_runtime < tsk->it_sched_expires))
return;
#undef UNEXPIRED
- BUG_ON(tsk->exit_state);
-
/*
* Double-check with locks held.
*/
read_lock(&tasklist_lock);
- spin_lock(&tsk->sighand->siglock);
+ if (likely(tsk->signal != NULL)) {
+ spin_lock(&tsk->sighand->siglock);
- /*
- * Here we take off tsk->cpu_timers[N] and tsk->signal->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);
+ /*
+ * Here we take off tsk->cpu_timers[N] and tsk->signal->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);
- /*
- * We must release these locks 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.
- */
- spin_unlock(&tsk->sighand->siglock);
+ /*
+ * We must release these locks 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.
+ */
+ spin_unlock(&tsk->sighand->siglock);
+ }
read_unlock(&tasklist_lock);
/*
*/
head = &tsk->signal->cpu_timers[clock_idx];
if (list_empty(head) ||
- cputime_ge(list_entry(head->next,
+ cputime_ge(list_first_entry(head,
struct cpu_timer_list, entry)->expires.cpu,
*newval)) {
/*
}
}
-static long posix_cpu_clock_nanosleep_restart(struct restart_block *);
-
-int posix_cpu_nsleep(const clockid_t which_clock, int flags,
- struct timespec *rqtp, struct timespec __user *rmtp)
+static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
+ struct timespec *rqtp, struct itimerspec *it)
{
- struct restart_block *restart_block =
- ¤t_thread_info()->restart_block;
struct k_itimer timer;
int error;
/*
- * Diagnose required errors first.
- */
- if (CPUCLOCK_PERTHREAD(which_clock) &&
- (CPUCLOCK_PID(which_clock) == 0 ||
- CPUCLOCK_PID(which_clock) == current->pid))
- return -EINVAL;
-
- /*
* Set up a temporary timer and then wait for it to go off.
*/
memset(&timer, 0, sizeof timer);
timer.it_process = current;
if (!error) {
static struct itimerspec zero_it;
- struct itimerspec it = { .it_value = *rqtp,
- .it_interval = {} };
+
+ memset(it, 0, sizeof *it);
+ it->it_value = *rqtp;
spin_lock_irq(&timer.it_lock);
- error = posix_cpu_timer_set(&timer, flags, &it, NULL);
+ error = posix_cpu_timer_set(&timer, flags, it, NULL);
if (error) {
spin_unlock_irq(&timer.it_lock);
return error;
* 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);
+ posix_cpu_timer_set(&timer, 0, &zero_it, it);
spin_unlock_irq(&timer.it_lock);
- if ((it.it_value.tv_sec | it.it_value.tv_nsec) == 0) {
+ if ((it->it_value.tv_sec | it->it_value.tv_nsec) == 0) {
/*
* It actually did fire already.
*/
return 0;
}
+ error = -ERESTART_RESTARTBLOCK;
+ }
+
+ return error;
+}
+
+int posix_cpu_nsleep(const clockid_t which_clock, int flags,
+ struct timespec *rqtp, struct timespec __user *rmtp)
+{
+ struct restart_block *restart_block =
+ ¤t_thread_info()->restart_block;
+ struct itimerspec it;
+ int error;
+
+ /*
+ * Diagnose required errors first.
+ */
+ if (CPUCLOCK_PERTHREAD(which_clock) &&
+ (CPUCLOCK_PID(which_clock) == 0 ||
+ CPUCLOCK_PID(which_clock) == current->pid))
+ return -EINVAL;
+
+ error = do_cpu_nanosleep(which_clock, flags, rqtp, &it);
+
+ if (error == -ERESTART_RESTARTBLOCK) {
+
+ if (flags & TIMER_ABSTIME)
+ return -ERESTARTNOHAND;
/*
- * Report back to the user the time still remaining.
- */
- if (rmtp != NULL && !(flags & TIMER_ABSTIME) &&
- copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+ * Report back to the user the time still remaining.
+ */
+ if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
return -EFAULT;
- restart_block->fn = posix_cpu_clock_nanosleep_restart;
- /* Caller already set restart_block->arg1 */
+ 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;
-
- error = -ERESTART_RESTARTBLOCK;
}
-
return error;
}
-static long
-posix_cpu_clock_nanosleep_restart(struct restart_block *restart_block)
+long posix_cpu_nsleep_restart(struct restart_block *restart_block)
{
clockid_t which_clock = restart_block->arg0;
struct timespec __user *rmtp;
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;
restart_block->fn = do_no_restart_syscall;
- return posix_cpu_nsleep(which_clock, TIMER_ABSTIME, &t, rmtp);
+ error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it);
+
+ if (error == -ERESTART_RESTARTBLOCK) {
+ /*
+ * Report back to the user the time still remaining.
+ */
+ if (rmtp != NULL && 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;
+ }
+ return error;
+
}
{
return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp, rmtp);
}
+static long process_cpu_nsleep_restart(struct restart_block *restart_block)
+{
+ return -EINVAL;
+}
static int thread_cpu_clock_getres(const clockid_t which_clock,
struct timespec *tp)
{
{
return -EINVAL;
}
+static long thread_cpu_nsleep_restart(struct restart_block *restart_block)
+{
+ return -EINVAL;
+}
static __init int init_posix_cpu_timers(void)
{
.clock_set = do_posix_clock_nosettime,
.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_set = do_posix_clock_nosettime,
.timer_create = thread_cpu_timer_create,
.nsleep = thread_cpu_nsleep,
+ .nsleep_restart = thread_cpu_nsleep_restart,
};
register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff