From 9501b6cf5541f0d576d566a463f1e7d3eaaab4eb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Mar 2007 14:31:17 +0200 Subject: [PATCH] dynticks: fix hrtimer rounding error in next_timer_interrupt 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 Signed-off-by: Thomas Gleixner Signed-off-by: Linus Torvalds --- kernel/timer.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'kernel/timer.c') diff --git a/kernel/timer.c b/kernel/timer.c index 797cccb8643..440048acaea 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -695,15 +695,28 @@ static unsigned long cmp_next_hrtimer_event(unsigned long now, { 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; -- cgit v1.2.3-70-g09d2 From 995f054f2a342f8505fed4f8395d12c0f5966414 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 7 Apr 2007 12:05:00 +0200 Subject: [PATCH] high-res timers: resume fix Soeren Sonnenburg reported that upon resume he is getting this backtrace: [] smp_apic_timer_interrupt+0x57/0x90 [] retrigger_next_event+0x0/0xb0 [] apic_timer_interrupt+0x28/0x30 [] retrigger_next_event+0x0/0xb0 [] __kfifo_put+0x8/0x90 [] on_each_cpu+0x35/0x60 [] clock_was_set+0x18/0x20 [] timekeeping_resume+0x7c/0xa0 [] __sysdev_resume+0x11/0x80 [] sysdev_resume+0x47/0x80 [] device_power_up+0x5/0x10 it turns out that on resume we mistakenly re-enable interrupts too early. Do the timer retrigger only on the current CPU. Signed-off-by: Ingo Molnar Acked-by: Thomas Gleixner Acked-by: Soeren Sonnenburg Signed-off-by: Linus Torvalds --- include/linux/hrtimer.h | 3 +++ kernel/hrtimer.c | 12 ++++++++++++ kernel/timer.c | 2 +- 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'kernel/timer.c') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 5bdbc744e77..17c29dca835 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -206,6 +206,7 @@ struct hrtimer_cpu_base { struct clock_event_device; extern void clock_was_set(void); +extern void hres_timers_resume(void); extern void hrtimer_interrupt(struct clock_event_device *dev); /* @@ -236,6 +237,8 @@ static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer) */ static inline void clock_was_set(void) { } +static inline void hres_timers_resume(void) { } + /* * In non high resolution mode the time reference is taken from * the base softirq time variable. diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 067ba2c0532..b74860aaf5f 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -458,6 +458,18 @@ void clock_was_set(void) on_each_cpu(retrigger_next_event, NULL, 0, 1); } +/* + * During resume we might have to reprogram the high resolution timer + * interrupt (on the local CPU): + */ +void hres_timers_resume(void) +{ + WARN_ON_ONCE(num_online_cpus() > 1); + + /* Retrigger the CPU local events: */ + retrigger_next_event(NULL); +} + /* * Check, whether the timer is on the callback pending list */ diff --git a/kernel/timer.c b/kernel/timer.c index 440048acaea..dd6c2c1c561 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1016,7 +1016,7 @@ static int timekeeping_resume(struct sys_device *dev) clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL); /* Resume hrtimers */ - clock_was_set(); + hres_timers_resume(); return 0; } -- cgit v1.2.3-70-g09d2