[patch 16/20] timer: Optimize collect timers for NOHZ

[Thomas Gleixner]

From: Anna-Maria Gleixner <anna-maria@xxxxxxxxxxxxx>

After a NOHZ idle sleep the wheel must be forwarded to current jiffies. There
might be expired timers so the current code loops and checks the epxired
buckets for timers. This can take quite some time for long NOHZ idle periods.

The pending bitmask in the timer base allows us to do a quick search for the
next expiring timer and therefor a fast forward of the base time which
prevents pointless long lasting loops.

For a 3 second idle sleep this reduces the catchup time from ~1ms to 5us.

Signed-off-by: Anna-Maria Gleixner <anna-maria@xxxxxxxxxxxxx>
Cc: rt@xxxxxxxxxxxxx
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

---
 kernel/time/timer.c |   48 ++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 40 insertions(+), 8 deletions(-)

--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1235,8 +1235,8 @@ static void expire_timers(struct timer_b
 	}
 }
 
-static int collect_expired_timers(struct timer_base *base,
-				  struct hlist_head *heads)
+static int __collect_expired_timers(struct timer_base *base,
+				    struct hlist_head *heads)
 {
 	unsigned long clock = base->clk;
 	struct hlist_head tmp, *vec;
@@ -1282,9 +1282,9 @@ static int collect_expired_timers(struct
 
 #ifdef CONFIG_NO_HZ_COMMON
 /*
- * Find the next pending bucket of a level. Search from @offset + @clk upwards
- * and if nothing there, search from start of the level (@offset) up to
- * @offset + clk.
+ * Find the next pending bucket of a level. Search from level start (@offset)
+ * + @clk upwards and if nothing there, search from start of the level
+ * (@offset) up to @offset + clk.
  */
 static int next_pending_bucket(struct timer_base *base, unsigned offset,
 			       unsigned clk)
@@ -1301,7 +1301,8 @@ static int next_pending_bucket(struct ti
 }
 
 /*
- * Search the first expiring timer in the various clock levels.
+ * Search the first expiring timer in the various clock levels. Caller must
+ * hold base->lock.
  *
  * Note: This implementation might be suboptimal vs. timers enqueued in the
  *	 cascade level because we do not look at the timers to figure out when
@@ -1314,7 +1315,6 @@ static unsigned long __next_timer_interr
 	unsigned long clk, next, adj;
 	unsigned lvl, offset = 0;
 
-	spin_lock(&base->lock);
 	clk = base->clk;
 	next = clk + NEXT_TIMER_MAX_DELTA;
 	for (lvl = 0; lvl < LVL_DEPTH; lvl++, offset += LVL_SIZE) {
@@ -1367,7 +1367,6 @@ static unsigned long __next_timer_interr
 		clk >>= LVL_CLK_SHIFT;
 		clk += adj;
 	}
-	spin_unlock(&base->lock);
 	return next;
 }
 
@@ -1425,7 +1424,10 @@ u64 get_next_timer_interrupt(unsigned lo
 	if (cpu_is_offline(smp_processor_id()))
 		return expires;
 
+	spin_lock(&base->lock);
 	nextevt = __next_timer_interrupt(base);
+	spin_unlock(&base->lock);
+
 	if (time_before_eq(nextevt, basej))
 		expires = basem;
 	else
@@ -1433,6 +1435,36 @@ u64 get_next_timer_interrupt(unsigned lo
 
 	return cmp_next_hrtimer_event(basem, expires);
 }
+
+static int collect_expired_timers(struct timer_base *base,
+				  struct hlist_head *heads)
+{
+	/*
+	 * NOHZ optimization. After a long idle sleep we need to forward the
+	 * base to current jiffies. Avoid a loop by searching the bitfield for
+	 * the next expiring timer.
+	 */
+	if ((jiffies - base->clk) > 1) {
+		unsigned long next = __next_timer_interrupt(base);
+
+		/*
+		 * If the next timer is ahead of time forward to current
+		 * jiffies, otherwise forward to the next expiry time.
+		 */
+		if (time_after(next, jiffies)) {
+			base->clk = jiffies;
+			return 0;
+		}
+		base->clk = next;
+	}
+	return __collect_expired_timers(base, heads);
+}
+#else
+static inline int collect_expired_timers(struct timer_base *base,
+					 struct hlist_head *heads)
+{
+	return __collect_expired_timers(base, heads);
+}
 #endif
 
 /*