buf.dirent = dirent;
error = vfs_readdir(file, compat_fillonedir, &buf);
- if (error >= 0)
+ if (buf.result)
error = buf.result;
fput(file);
buf.error = 0;
error = vfs_readdir(file, compat_filldir, &buf);
- if (error < 0)
- goto out_putf;
- error = buf.error;
+ if (error >= 0)
+ error = buf.error;
lastdirent = buf.previous;
if (lastdirent) {
if (put_user(file->f_pos, &lastdirent->d_off))
else
error = count - buf.count;
}
-
-out_putf:
fput(file);
out:
return error;
buf.error = 0;
error = vfs_readdir(file, compat_filldir64, &buf);
- if (error < 0)
- goto out_putf;
- error = buf.error;
+ if (error >= 0)
+ error = buf.error;
lastdirent = buf.previous;
if (lastdirent) {
typeof(lastdirent->d_off) d_off = file->f_pos;
- error = -EFAULT;
if (__put_user_unaligned(d_off, &lastdirent->d_off))
- goto out_putf;
- error = count - buf.count;
+ error = -EFAULT;
+ else
+ error = count - buf.count;
}
-
-out_putf:
fput(file);
out:
return error;
#define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t))
+ static int poll_select_copy_remaining(struct timespec *end_time, void __user *p,
+ int timeval, int ret)
+ {
+ struct timespec ts;
+
+ if (!p)
+ return ret;
+
+ if (current->personality & STICKY_TIMEOUTS)
+ goto sticky;
+
+ /* No update for zero timeout */
+ if (!end_time->tv_sec && !end_time->tv_nsec)
+ return ret;
+
+ ktime_get_ts(&ts);
+ ts = timespec_sub(*end_time, ts);
+ if (ts.tv_sec < 0)
+ ts.tv_sec = ts.tv_nsec = 0;
+
+ if (timeval) {
+ struct compat_timeval rtv;
+
+ rtv.tv_sec = ts.tv_sec;
+ rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
+
+ if (!copy_to_user(p, &rtv, sizeof(rtv)))
+ return ret;
+ } else {
+ struct compat_timespec rts;
+
+ rts.tv_sec = ts.tv_sec;
+ rts.tv_nsec = ts.tv_nsec;
+
+ if (!copy_to_user(p, &rts, sizeof(rts)))
+ return ret;
+ }
+ /*
+ * If an application puts its timeval in read-only memory, we
+ * don't want the Linux-specific update to the timeval to
+ * cause a fault after the select has completed
+ * successfully. However, because we're not updating the
+ * timeval, we can't restart the system call.
+ */
+
+ sticky:
+ if (ret == -ERESTARTNOHAND)
+ ret = -EINTR;
+ return ret;
+ }
+
/*
* Ooo, nasty. We need here to frob 32-bit unsigned longs to
* 64-bit unsigned longs.
((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1)
int compat_core_sys_select(int n, compat_ulong_t __user *inp,
- compat_ulong_t __user *outp, compat_ulong_t __user *exp, s64 *timeout)
+ compat_ulong_t __user *outp, compat_ulong_t __user *exp,
+ struct timespec *end_time)
{
fd_set_bits fds;
void *bits;
zero_fd_set(n, fds.res_out);
zero_fd_set(n, fds.res_ex);
- ret = do_select(n, &fds, timeout);
+ ret = do_select(n, &fds, end_time);
if (ret < 0)
goto out;
compat_ulong_t __user *outp, compat_ulong_t __user *exp,
struct compat_timeval __user *tvp)
{
- s64 timeout = -1;
+ struct timespec end_time, *to = NULL;
struct compat_timeval tv;
int ret;
if (copy_from_user(&tv, tvp, sizeof(tv)))
return -EFAULT;
- if (tv.tv_sec < 0 || tv.tv_usec < 0)
+ to = &end_time;
+ if (poll_select_set_timeout(to, tv.tv_sec,
+ tv.tv_usec * NSEC_PER_USEC))
return -EINVAL;
-
- /* Cast to u64 to make GCC stop complaining */
- if ((u64)tv.tv_sec >= (u64)MAX_INT64_SECONDS)
- timeout = -1; /* infinite */
- else {
- timeout = DIV_ROUND_UP(tv.tv_usec, 1000000/HZ);
- timeout += tv.tv_sec * HZ;
- }
}
- ret = compat_core_sys_select(n, inp, outp, exp, &timeout);
-
- if (tvp) {
- struct compat_timeval rtv;
-
- if (current->personality & STICKY_TIMEOUTS)
- goto sticky;
- rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
- rtv.tv_sec = timeout;
- if (compat_timeval_compare(&rtv, &tv) >= 0)
- rtv = tv;
- if (copy_to_user(tvp, &rtv, sizeof(rtv))) {
- sticky:
- /*
- * If an application puts its timeval in read-only
- * memory, we don't want the Linux-specific update to
- * the timeval to cause a fault after the select has
- * completed successfully. However, because we're not
- * updating the timeval, we can't restart the system
- * call.
- */
- if (ret == -ERESTARTNOHAND)
- ret = -EINTR;
- }
- }
+ ret = compat_core_sys_select(n, inp, outp, exp, to);
+ ret = poll_select_copy_remaining(&end_time, tvp, 1, ret);
return ret;
}
{
compat_sigset_t ss32;
sigset_t ksigmask, sigsaved;
- s64 timeout = MAX_SCHEDULE_TIMEOUT;
struct compat_timespec ts;
+ struct timespec end_time, *to = NULL;
int ret;
if (tsp) {
if (copy_from_user(&ts, tsp, sizeof(ts)))
return -EFAULT;
- if (ts.tv_sec < 0 || ts.tv_nsec < 0)
+ to = &end_time;
+ if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
return -EINVAL;
}
sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
}
- do {
- if (tsp) {
- if ((unsigned long)ts.tv_sec < MAX_SELECT_SECONDS) {
- timeout = DIV_ROUND_UP(ts.tv_nsec, 1000000000/HZ);
- timeout += ts.tv_sec * (unsigned long)HZ;
- ts.tv_sec = 0;
- ts.tv_nsec = 0;
- } else {
- ts.tv_sec -= MAX_SELECT_SECONDS;
- timeout = MAX_SELECT_SECONDS * HZ;
- }
- }
-
- ret = compat_core_sys_select(n, inp, outp, exp, &timeout);
-
- } while (!ret && !timeout && tsp && (ts.tv_sec || ts.tv_nsec));
-
- if (tsp) {
- struct compat_timespec rts;
-
- if (current->personality & STICKY_TIMEOUTS)
- goto sticky;
-
- rts.tv_sec = timeout / HZ;
- rts.tv_nsec = (timeout % HZ) * (NSEC_PER_SEC/HZ);
- if (rts.tv_nsec >= NSEC_PER_SEC) {
- rts.tv_sec++;
- rts.tv_nsec -= NSEC_PER_SEC;
- }
- if (compat_timespec_compare(&rts, &ts) >= 0)
- rts = ts;
- if (copy_to_user(tsp, &rts, sizeof(rts))) {
- sticky:
- /*
- * If an application puts its timeval in read-only
- * memory, we don't want the Linux-specific update to
- * the timeval to cause a fault after the select has
- * completed successfully. However, because we're not
- * updating the timeval, we can't restart the system
- * call.
- */
- if (ret == -ERESTARTNOHAND)
- ret = -EINTR;
- }
- }
+ ret = compat_core_sys_select(n, inp, outp, exp, to);
+ ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
if (ret == -ERESTARTNOHAND) {
/*
compat_sigset_t ss32;
sigset_t ksigmask, sigsaved;
struct compat_timespec ts;
- s64 timeout = -1;
+ struct timespec end_time, *to = NULL;
int ret;
if (tsp) {
if (copy_from_user(&ts, tsp, sizeof(ts)))
return -EFAULT;
- /* We assume that ts.tv_sec is always lower than
- the number of seconds that can be expressed in
- an s64. Otherwise the compiler bitches at us */
- timeout = DIV_ROUND_UP(ts.tv_nsec, 1000000000/HZ);
- timeout += ts.tv_sec * HZ;
+ to = &end_time;
+ if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
+ return -EINVAL;
}
if (sigmask) {
sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
}
- ret = do_sys_poll(ufds, nfds, &timeout);
+ ret = do_sys_poll(ufds, nfds, to);
/* We can restart this syscall, usually */
if (ret == -EINTR) {
} else if (sigmask)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
- if (tsp && timeout >= 0) {
- struct compat_timespec rts;
-
- if (current->personality & STICKY_TIMEOUTS)
- goto sticky;
- /* Yes, we know it's actually an s64, but it's also positive. */
- rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) *
- 1000;
- rts.tv_sec = timeout;
- if (compat_timespec_compare(&rts, &ts) >= 0)
- rts = ts;
- if (copy_to_user(tsp, &rts, sizeof(rts))) {
- sticky:
- /*
- * If an application puts its timeval in read-only
- * memory, we don't want the Linux-specific update to
- * the timeval to cause a fault after the select has
- * completed successfully. However, because we're not
- * updating the timeval, we can't restart the system
- * call.
- */
- if (ret == -ERESTARTNOHAND && timeout >= 0)
- ret = -EINTR;
- }
- }
+ ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
return ret;
}
now = hrtimer_cb_get_time(&rt_b->rt_period_timer);
hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period);
- hrtimer_start(&rt_b->rt_period_timer,
- rt_b->rt_period_timer.expires,
- HRTIMER_MODE_ABS);
+ hrtimer_start_expires(&rt_b->rt_period_timer,
+ HRTIMER_MODE_ABS);
}
spin_unlock(&rt_b->rt_runtime_lock);
}
*/
unsigned int sysctl_sched_shares_ratelimit = 250000;
+/*
+ * Inject some fuzzyness into changing the per-cpu group shares
+ * this avoids remote rq-locks at the expense of fairness.
+ * default: 4
+ */
+unsigned int sysctl_sched_shares_thresh = 4;
+
/*
* period over which we measure -rt task cpu usage in us.
* default: 1s
struct hrtimer *timer = &rq->hrtick_timer;
ktime_t time = ktime_add_ns(timer->base->get_time(), delay);
- timer->expires = time;
+ hrtimer_set_expires(timer, time);
if (rq == this_rq()) {
hrtimer_restart(timer);
* Calculate and set the cpu's group shares.
*/
static void
-__update_group_shares_cpu(struct task_group *tg, int cpu,
- unsigned long sd_shares, unsigned long sd_rq_weight)
+update_group_shares_cpu(struct task_group *tg, int cpu,
+ unsigned long sd_shares, unsigned long sd_rq_weight)
{
int boost = 0;
unsigned long shares;
*
*/
shares = (sd_shares * rq_weight) / (sd_rq_weight + 1);
+ shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
- /*
- * record the actual number of shares, not the boosted amount.
- */
- tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
- tg->cfs_rq[cpu]->rq_weight = rq_weight;
+ if (abs(shares - tg->se[cpu]->load.weight) >
+ sysctl_sched_shares_thresh) {
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long flags;
- if (shares < MIN_SHARES)
- shares = MIN_SHARES;
- else if (shares > MAX_SHARES)
- shares = MAX_SHARES;
+ spin_lock_irqsave(&rq->lock, flags);
+ /*
+ * record the actual number of shares, not the boosted amount.
+ */
+ tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
+ tg->cfs_rq[cpu]->rq_weight = rq_weight;
- __set_se_shares(tg->se[cpu], shares);
+ __set_se_shares(tg->se[cpu], shares);
+ spin_unlock_irqrestore(&rq->lock, flags);
+ }
}
/*
if (!rq_weight)
rq_weight = cpus_weight(sd->span) * NICE_0_LOAD;
- for_each_cpu_mask(i, sd->span) {
- struct rq *rq = cpu_rq(i);
- unsigned long flags;
-
- spin_lock_irqsave(&rq->lock, flags);
- __update_group_shares_cpu(tg, i, shares, rq_weight);
- spin_unlock_irqrestore(&rq->lock, flags);
- }
+ for_each_cpu_mask(i, sd->span)
+ update_group_shares_cpu(tg, i, shares, rq_weight);
return 0;
}
if (sched_feat(HRTICK))
hrtick_clear(rq);
- /*
- * Do the rq-clock update outside the rq lock:
- */
- local_irq_disable();
+ spin_lock_irq(&rq->lock);
update_rq_clock(rq);
- spin_lock(&rq->lock);
clear_tsk_need_resched(prev);
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {