[RFC,v2,1/5] tick/nohz: Introduce tick_get_sleep_length()

Commit Message

Peter Zijlstra Aug. 2, 2023, 1:24 p.m. UTC

Add a variant of tick_nohz_get_sleep_length() that conditionally does
the NOHZ part.

tick_get_sleep_length(false) returns the delta_next return value of
tick_nohz_get_sleep_length(), while tick_get_sleep_length(true)
returns the regular return of tick_nohz_get_sleep_length().

This allows eliding tick_nohz_next_event() -- which is going to be
expensive with timer-pull.

Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
---
 include/linux/tick.h     |    5 +++++
 kernel/time/tick-sched.c |   35 +++++++++++++++++++++++------------
 2 files changed, 28 insertions(+), 12 deletions(-)

Patch

--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -136,6 +136,7 @@  extern void tick_nohz_irq_exit(void);
 extern bool tick_nohz_idle_got_tick(void);
 extern ktime_t tick_nohz_get_next_hrtimer(void);
 extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next);
+extern ktime_t tick_get_sleep_length(bool nohz);
 extern unsigned long tick_nohz_get_idle_calls(void);
 extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu);
 extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
@@ -168,6 +169,10 @@  static inline ktime_t tick_nohz_get_slee
 	*delta_next = TICK_NSEC;
 	return *delta_next;
 }
+static inline ktime_t tick_get_sleep_length(bool nohz)
+{
+	return TICK_NSEC;
+}
 static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
 static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
 
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1218,17 +1218,7 @@  ktime_t tick_nohz_get_next_hrtimer(void)
 	return __this_cpu_read(tick_cpu_device.evtdev)->next_event;
 }
 
-/**
- * tick_nohz_get_sleep_length - return the expected length of the current sleep
- * @delta_next: duration until the next event if the tick cannot be stopped
- *
- * Called from power state control code with interrupts disabled.
- *
- * The return value of this function and/or the value returned by it through the
- * @delta_next pointer can be negative which must be taken into account by its
- * callers.
- */
-ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
+static ktime_t __tick_nohz_get_sleep_length(ktime_t *delta_next, bool nohz)
 {
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
@@ -1244,7 +1234,7 @@  ktime_t tick_nohz_get_sleep_length(ktime
 
 	*delta_next = ktime_sub(dev->next_event, now);
 
-	if (!can_stop_idle_tick(cpu, ts))
+	if (!nohz || !can_stop_idle_tick(cpu, ts))
 		return *delta_next;
 
 	next_event = tick_nohz_next_event(ts, cpu);
@@ -1262,6 +1252,27 @@  ktime_t tick_nohz_get_sleep_length(ktime
 }
 
 /**
+ * tick_nohz_get_sleep_length - return the expected length of the current sleep
+ * @delta_next: duration until the next event if the tick cannot be stopped
+ *
+ * Called from power state control code with interrupts disabled.
+ *
+ * The return value of this function and/or the value returned by it through the
+ * @delta_next pointer can be negative which must be taken into account by its
+ * callers.
+ */
+ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
+{
+	return __tick_nohz_get_sleep_length(delta_next, true);
+}
+
+ktime_t tick_get_sleep_length(bool nohz)
+{
+	ktime_t delta;
+	return __tick_nohz_get_sleep_length(&delta, nohz);
+}
+
+/**
  * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value
  * for a particular CPU.
  *