[v3,1/2] timers: Implement usleep_idle_range()

Commit Message

SeongJae Park Nov. 26, 2021, 2:50 p.m. UTC

Some kernel threads such as DAMON could need to repeatedly sleep in
micro seconds level.  Because usleep_range() sleeps in uninterruptible
state, however, such threads would make /proc/loadavg reports fake load.

To help such cases, this commit implements a variant of usleep_range()
called usleep_idle_range().  It is same to usleep_range() but sets the
state of the current task as TASK_IDLE while sleeping.

Suggested-by: Andrew Morton <[e-mail]>
Signed-off-by: SeongJae Park <[e-mail]>
---
 include/linux/delay.h | 14 +++++++++++++-
 kernel/time/timer.c   | 16 +++++++++-------
 2 files changed, 22 insertions(+), 8 deletions(-)

Comments

Thomas Gleixner Nov. 26, 2021, 9:26 p.m. UTC | #1

On Fri, Nov 26 2021 at 14:50, SeongJae Park wrote:
> Some kernel threads such as DAMON could need to repeatedly sleep in
> micro seconds level.  Because usleep_range() sleeps in uninterruptible
> state, however, such threads would make /proc/loadavg reports fake load.
>
> To help such cases, this commit implements a variant of usleep_range()
> called usleep_idle_range().  It is same to usleep_range() but sets the
> state of the current task as TASK_IDLE while sleeping.
>
> Suggested-by: Andrew Morton <[e-mail]>
> Signed-off-by: SeongJae Park <[e-mail]>

Andrew, I assume you want to pick that up along with the mm fix, right?

Reviewed-by: Thomas Gleixner <[e-mail]>

Patch

diff --git a/include/linux/delay.h b/include/linux/delay.h
index 8eacf67eb212..039e7e0c7378 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -20,6 +20,7 @@ 
  */
 
 #include <linux/math.h>
+#include <linux/sched.h>
 
 extern unsigned long loops_per_jiffy;
 
@@ -58,7 +59,18 @@  void calibrate_delay(void);
 void __attribute__((weak)) calibration_delay_done(void);
 void msleep(unsigned int msecs);
 unsigned long msleep_interruptible(unsigned int msecs);
-void usleep_range(unsigned long min, unsigned long max);
+void usleep_range_state(unsigned long min, unsigned long max,
+			unsigned int state);
+
+static inline void usleep_range(unsigned long min, unsigned long max)
+{
+	usleep_range_state(min, max, TASK_UNINTERRUPTIBLE);
+}
+
+static inline void usleep_idle_range(unsigned long min, unsigned long max)
+{
+	usleep_range_state(min, max, TASK_IDLE);
+}
 
 static inline void ssleep(unsigned int seconds)
 {
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index e3d2c23c413d..85f1021ad459 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -2054,26 +2054,28 @@  unsigned long msleep_interruptible(unsigned int msecs)
 EXPORT_SYMBOL(msleep_interruptible);
 
 /**
- * usleep_range - Sleep for an approximate time
- * @min: Minimum time in usecs to sleep
- * @max: Maximum time in usecs to sleep
+ * usleep_range_state - Sleep for an approximate time in a given state
+ * @min:	Minimum time in usecs to sleep
+ * @max:	Maximum time in usecs to sleep
+ * @state:	State of the current task that will be while sleeping
  *
  * In non-atomic context where the exact wakeup time is flexible, use
- * usleep_range() instead of udelay().  The sleep improves responsiveness
+ * usleep_range_state() 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)
+void __sched usleep_range_state(unsigned long min, unsigned long max,
+				unsigned int state)
 {
 	ktime_t exp = ktime_add_us(ktime_get(), min);
 	u64 delta = (u64)(max - min) * NSEC_PER_USEC;
 
 	for (;;) {
-		__set_current_state(TASK_UNINTERRUPTIBLE);
+		__set_current_state(state);
 		/* Do not return before the requested sleep time has elapsed */
 		if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS))
 			break;
 	}
 }
-EXPORT_SYMBOL(usleep_range);
+EXPORT_SYMBOL(usleep_range_state);