The patch titled
dynticks: fix hrtimer rounding error in next_timer_interrupt()
has been added to the -mm tree. Its filename is
dynticks-fix-hrtimer-rounding-error-in.patch
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: dynticks: fix hrtimer rounding error in next_timer_interrupt()
From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
The rework of next_timer_interrupt() fixed the timer wheel bugs, but
invented a rounding error versus the next hrtimer event. This is caused by
the conversion of the hrtimer internal representation to relative jiffies.
This causes bug #8100:
http://bugzilla.kernel.org/show_bug.cgi?id=8100
next_timer_interrupt() returns "now" in such a case and causes the code in
tick_nohz_stop_sched_tick() to trigger the timer softirq, which is bogus as
no timer is due for expiry. This results in an endless context switching
between idle and ksoftirqd until a timer is due for expiry.
Modify the hrtimer evaluation so that, it returns now + 1, when the
conversion results in a delta < 1 jiffie.
It's confirmed to resolve bug #8100
Reported-by: Emil Karlson <jkarlson@xxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Adrian Bunk <bunk@xxxxxxxxx>
Cc: john stultz <johnstul@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
kernel/timer.c | 19 ++++++++++++++++---
1 file changed, 16 insertions(+), 3 deletions(-)
diff -puN kernel/timer.c~dynticks-fix-hrtimer-rounding-error-in kernel/timer.c
--- a/kernel/timer.c~dynticks-fix-hrtimer-rounding-error-in
+++ a/kernel/timer.c
@@ -695,15 +695,28 @@ static unsigned long cmp_next_hrtimer_ev
{
ktime_t hr_delta = hrtimer_get_next_event();
struct timespec tsdelta;
+ unsigned long delta;
if (hr_delta.tv64 == KTIME_MAX)
return expires;
- if (hr_delta.tv64 <= TICK_NSEC)
- return now;
+ /*
+ * Expired timer available, let it expire in the next tick
+ */
+ if (hr_delta.tv64 <= 0)
+ return now + 1;
tsdelta = ktime_to_timespec(hr_delta);
- now += timespec_to_jiffies(&tsdelta);
+ delta = timespec_to_jiffies(&tsdelta);
+ /*
+ * Take rounding errors in to account and make sure, that it
+ * expires in the next tick. Otherwise we go into an endless
+ * ping pong due to tick_nohz_stop_sched_tick() retriggering
+ * the timer softirq
+ */
+ if (delta < 1)
+ delta = 1;
+ now += delta;
if (time_before(now, expires))
return now;
return expires;
_
Patches currently in -mm which might be from tglx@xxxxxxxxxxxxx are
origin.patch
time-fix-formatting-in-proc-timer_list.patch
correct-slow-acpi_pm-rating.patch
i386-prevent-early-access-to-tsc-to-avoid-crash-on.patch
dynticks-fix-hrtimer-rounding-error-in.patch
git-ieee1394.patch
log-reason-why-tsc-was-marked-unstable.patch
optimize-timespec_trunc.patch
sched-fix-idle-load-balancing-in-softirqd-context.patch
sched-dynticks-idle-load-balancing-v3.patch
mm-only-hrtimers-debug-patch.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
