return LVL_OFFS(lvl) + (expires & LVL_MASK);
}
-static void
-__internal_add_timer(struct timer_base *base, struct timer_list *timer)
+static int calc_wheel_index(unsigned long expires, unsigned long clk)
{
- unsigned long expires = timer->expires;
- unsigned long delta = expires - base->clk;
- struct hlist_head *vec;
+ unsigned long delta = expires - clk;
unsigned int idx;
if (delta < LVL_START(1)) {
} else if (LVL_DEPTH > 8 && delta < LVL_START(8)) {
idx = calc_index(expires, 7);
} else if ((long) delta < 0) {
- idx = base->clk & LVL_MASK;
+ idx = clk & LVL_MASK;
} else {
/*
* Force expire obscene large timeouts to expire at the
idx = calc_index(expires, LVL_DEPTH - 1);
}
- /*
- * Enqueue the timer into the array bucket, mark it pending in
- * the bitmap and store the index in the timer flags.
- */
- vec = base->vectors + idx;
- hlist_add_head(&timer->entry, vec);
+ return idx;
+}
+
+/*
+ * Enqueue the timer into the hash bucket, mark it pending in
+ * the bitmap and store the index in the timer flags.
+ */
+static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
+ unsigned int idx)
+{
+ hlist_add_head(&timer->entry, base->vectors + idx);
__set_bit(idx, base->pending_map);
timer_set_idx(timer, idx);
}
-static void internal_add_timer(struct timer_base *base, struct timer_list *timer)
+static void
+__internal_add_timer(struct timer_base *base, struct timer_list *timer)
{
- __internal_add_timer(base, timer);
+ unsigned int idx;
+ idx = calc_wheel_index(timer->expires, base->clk);
+ enqueue_timer(base, timer, idx);
+}
+
+static void
+trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
+{
if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active)
return;
* wheel:
*/
base->next_expiry = timer->expires;
- wake_up_nohz_cpu(base->cpu);
+ wake_up_nohz_cpu(base->cpu);
+}
+
+static void
+internal_add_timer(struct timer_base *base, struct timer_list *timer)
+{
+ __internal_add_timer(base, timer);
+ trigger_dyntick_cpu(base, timer);
}
#ifdef CONFIG_TIMER_STATS
__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
{
struct timer_base *base, *new_base;
- unsigned long flags;
+ unsigned int idx = UINT_MAX;
+ unsigned long clk = 0, flags;
int ret = 0;
/*
- * TODO: Calculate the array bucket of the timer right here w/o
- * holding the base lock. This allows to check not only
- * timer->expires == expires below, but also whether the timer
- * ends up in the same bucket. If we really need to requeue
- * the timer then we check whether base->clk have
- * advanced between here and locking the timer base. If
- * jiffies advanced we have to recalc the array bucket with the
- * lock held.
- */
-
- /*
- * This is a common optimization triggered by the
- * networking code - if the timer is re-modified
- * to be the same thing then just return:
+ * This is a common optimization triggered by the networking code - if
+ * the timer is re-modified to have the same timeout or ends up in the
+ * same array bucket then just return:
*/
if (timer_pending(timer)) {
if (timer->expires == expires)
return 1;
+ /*
+ * Take the current timer_jiffies of base, but without holding
+ * the lock!
+ */
+ base = get_timer_base(timer->flags);
+ clk = base->clk;
+
+ idx = calc_wheel_index(expires, clk);
+
+ /*
+ * Retrieve and compare the array index of the pending
+ * timer. If it matches set the expiry to the new value so a
+ * subsequent call will exit in the expires check above.
+ */
+ if (idx == timer_get_idx(timer)) {
+ timer->expires = expires;
+ return 1;
+ }
}
timer_stats_timer_set_start_info(timer);
}
timer->expires = expires;
- internal_add_timer(base, timer);
+ /*
+ * If 'idx' was calculated above and the base time did not advance
+ * between calculating 'idx' and taking the lock, only enqueue_timer()
+ * and trigger_dyntick_cpu() is required. Otherwise we need to
+ * (re)calculate the wheel index via internal_add_timer().
+ */
+ if (idx != UINT_MAX && clk == base->clk) {
+ enqueue_timer(base, timer, idx);
+ trigger_dyntick_cpu(base, timer);
+ } else {
+ internal_add_timer(base, timer);
+ }
out_unlock:
spin_unlock_irqrestore(&base->lock, flags);
*/
void run_local_timers(void)
{
+ struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
+
hrtimer_run_queues();
+ /* Raise the softirq only if required. */
+ if (time_before(jiffies, base->clk)) {
+ if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active)
+ return;
+ /* CPU is awake, so check the deferrable base. */
+ base++;
+ if (time_before(jiffies, base->clk))
+ return;
+ }
raise_softirq(TIMER_SOFTIRQ);
}
}
/**
- * usleep_range - Drop in replacement for udelay where wakeup is flexible
+ * usleep_range - Sleep for an approximate time
* @min: Minimum time in usecs to sleep
* @max: Maximum time in usecs to sleep
+ *
+ * In non-atomic context where the exact wakeup time is flexible, use
+ * usleep_range() instead of udelay(). The sleep improves responsiveness
+ * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces
+ * power usage by allowing hrtimers to take advantage of an already-
+ * scheduled interrupt instead of scheduling a new one just for this sleep.
*/
void __sched usleep_range(unsigned long min, unsigned long max)
{