hrtimer: turn hrtimers into range timers

this patch turns hrtimers into range timers; they have 2 expire points
1) the soft expire point
2) the hard expire point

the kernel will do it's regular best effort attempt to get the timer run
at the hard expire point. However, if some other time fires after the soft
expire point, the kernel now has the freedom to fire this timer at this point,
and thus grouping the events and preventing a power-expensive wakeup in the
future.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>

1 files changed, 52 insertions, 4 deletions

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index ae307feec74..01483004183 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1309,7 +1309,20 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
 			timer = rb_entry(node, struct hrtimer, node);
 
-			if (basenow.tv64 < hrtimer_get_expires_tv64(timer)) {
+			/*
+			 * The immediate goal for using the softexpires is
+			 * minimizing wakeups, not running timers at the
+			 * earliest interrupt after their soft expiration.
+			 * This allows us to avoid using a Priority Search
+			 * Tree, which can answer a stabbing querry for
+			 * overlapping intervals and instead use the simple
+			 * BST we already have.
+			 * We don't add extra wakeups by delaying timers that
+			 * are right-of a not yet expired timer, because that
+			 * timer will have to trigger a wakeup anyway.
+			 */
+
+			if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
 				ktime_t expires;
 
 				expires = ktime_sub(hrtimer_get_expires(timer),
@@ -1681,14 +1694,20 @@ void __init hrtimers_init(void)
 }
 
 /**
- * schedule_hrtimeout - sleep until timeout
+ * schedule_hrtimeout_range - sleep until timeout
  * @expires:	timeout value (ktime_t)
+ * @delta:	slack in expires timeout (ktime_t)
  * @mode:	timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
  *
  * Make the current task sleep until the given expiry time has
  * elapsed. The routine will return immediately unless
  * the current task state has been set (see set_current_state()).
  *
+ * The @delta argument gives the kernel the freedom to schedule the
+ * actual wakeup to a time that is both power and performance friendly.
+ * The kernel give the normal best effort behavior for "@expires+@delta",
+ * but may decide to fire the timer earlier, but no earlier than @expires.
+ *
  * You can set the task state as follows -
  *
  * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
@@ -1702,7 +1721,7 @@ void __init hrtimers_init(void)
  *
  * Returns 0 when the timer has expired otherwise -EINTR
  */
-int __sched schedule_hrtimeout(ktime_t *expires,
+int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
 			       const enum hrtimer_mode mode)
 {
 	struct hrtimer_sleeper t;
@@ -1726,7 +1745,7 @@ int __sched schedule_hrtimeout(ktime_t *expires,
 	}
 
 	hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode);
-	hrtimer_set_expires(&t.timer, *expires);
+	hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
 
 	hrtimer_init_sleeper(&t, current);
 
@@ -1744,4 +1763,33 @@ int __sched schedule_hrtimeout(ktime_t *expires,
 
 	return !t.task ? 0 : -EINTR;
 }
+EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);
+
+/**
+ * schedule_hrtimeout - sleep until timeout
+ * @expires:	timeout value (ktime_t)
+ * @mode:	timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ *
+ * Make the current task sleep until the given expiry time has
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
+ * pass before the routine returns.
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task.
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Returns 0 when the timer has expired otherwise -EINTR
+ */
+int __sched schedule_hrtimeout(ktime_t *expires,
+			       const enum hrtimer_mode mode)
+{
+	return schedule_hrtimeout_range(expires, 0, mode);
+}
 EXPORT_SYMBOL_GPL(schedule_hrtimeout);