* [PATCH for-v5.15.x 1/2] timers: implement usleep_idle_range()
2021-12-12 8:28 [PATCH for-v5.15.x 0/2] mm/damon/core: Fix fake load reports due to uninterruptible sleeps SeongJae Park
@ 2021-12-12 8:28 ` SeongJae Park
2021-12-12 8:28 ` [PATCH for-v5.15.x 2/2] mm/damon/core: fix fake load reports due to uninterruptible sleeps SeongJae Park
2021-12-12 12:14 ` [PATCH for-v5.15.x 0/2] mm/damon/core: Fix " Greg KH
2 siblings, 0 replies; 4+ messages in thread
From: SeongJae Park @ 2021-12-12 8:28 UTC (permalink / raw)
To: stable, gregkh
Cc: akpm, linux-mm, linux-kernel, SeongJae Park, John Stultz, Linus Torvalds
commit e4779015fd5d2fb8390c258268addff24d6077c7 upstream.
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> # 5.15.x
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
include/linux/delay.h | 14 +++++++++++++-
kernel/time/timer.c | 16 +++++++++-------
2 files changed, 22 insertions(+), 8 deletions(-)
diff --git a/include/linux/delay.h b/include/linux/delay.h
index 1d0e2ce6b6d9..e8607992c68a 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -20,6 +20,7 @@
*/
#include <linux/kernel.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);
--
2.17.1
^ permalink raw reply [flat|nested] 4+ messages in thread* [PATCH for-v5.15.x 2/2] mm/damon/core: fix fake load reports due to uninterruptible sleeps
2021-12-12 8:28 [PATCH for-v5.15.x 0/2] mm/damon/core: Fix fake load reports due to uninterruptible sleeps SeongJae Park
2021-12-12 8:28 ` [PATCH for-v5.15.x 1/2] timers: implement usleep_idle_range() SeongJae Park
@ 2021-12-12 8:28 ` SeongJae Park
2021-12-12 12:14 ` [PATCH for-v5.15.x 0/2] mm/damon/core: Fix " Greg KH
2 siblings, 0 replies; 4+ messages in thread
From: SeongJae Park @ 2021-12-12 8:28 UTC (permalink / raw)
To: stable, gregkh
Cc: akpm, linux-mm, linux-kernel, SeongJae Park, John Stultz,
Thomas Gleixner, Linus Torvalds
commit 70e9274805fccfd175d0431a947bfd11ee7df40e upstream.
Because DAMON sleeps in uninterruptible mode, /proc/loadavg reports fake
load while DAMON is turned on, though it is doing nothing. This can
confuse users[1]. To avoid the case, this commit makes DAMON sleeps in
idle mode.
[1] https://lore.kernel.org/all/11868371.O9o76ZdvQC@natalenko.name/
Link: https://lkml.kernel.org/r/20211126145015.15862-3-sj@kernel.org
Fixes: 2224d8485492 ("mm: introduce Data Access MONitor (DAMON)")
Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: SeongJae Park <sj@kernel.org>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: <stable@vger.kernel.org> # 5.15.x
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
mm/damon/core.c | 14 +++++++++++---
1 file changed, 11 insertions(+), 3 deletions(-)
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 30e9211f494a..7a4912d6e65f 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -357,6 +357,15 @@ int damon_start(struct damon_ctx **ctxs, int nr_ctxs)
return err;
}
+static void kdamond_usleep(unsigned long usecs)
+{
+ /* See Documentation/timers/timers-howto.rst for the thresholds */
+ if (usecs > 20 * 1000)
+ schedule_timeout_idle(usecs_to_jiffies(usecs));
+ else
+ usleep_idle_range(usecs, usecs + 1);
+}
+
/*
* __damon_stop() - Stops monitoring of given context.
* @ctx: monitoring context
@@ -370,8 +379,7 @@ static int __damon_stop(struct damon_ctx *ctx)
ctx->kdamond_stop = true;
mutex_unlock(&ctx->kdamond_lock);
while (damon_kdamond_running(ctx))
- usleep_range(ctx->sample_interval,
- ctx->sample_interval * 2);
+ kdamond_usleep(ctx->sample_interval);
return 0;
}
mutex_unlock(&ctx->kdamond_lock);
@@ -670,7 +678,7 @@ static int kdamond_fn(void *data)
ctx->callback.after_sampling(ctx))
set_kdamond_stop(ctx);
- usleep_range(ctx->sample_interval, ctx->sample_interval + 1);
+ kdamond_usleep(ctx->sample_interval);
if (ctx->primitive.check_accesses)
max_nr_accesses = ctx->primitive.check_accesses(ctx);
--
2.17.1
^ permalink raw reply [flat|nested] 4+ messages in thread