timers: implement usleep_idle_range()

Patch series "mm/damon: Fix fake /proc/loadavg reports", v3.

This patchset fixes DAMON's fake load report issue.  The first patch
makes yet another variant of usleep_range() for this fix, and the second
patch fixes the issue of DAMON by making it using the newly introduced
function.

This patch (of 2):

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.

Link: https://lkml.kernel.org/r/20211126145015.15862-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20211126145015.15862-2-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Suggested-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Cc: John Stultz <john.stultz@linaro.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/delay.h b/include/linux/delay.h
index 8eacf67..039e7e0 100644 (file)
--- 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 e3d2c23..85f1021 100644 (file)
--- 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);