411fe24e6b
This restores commit:24b91e360e: ("nohz: Fix collision between tick and other hrtimers") ... which got reverted by commit:558e8e27e7: ('Revert "nohz: Fix collision between tick and other hrtimers"') ... due to a regression where CPUs spuriously stopped ticking. The bug happened when a tick fired too early past its expected expiration: on IRQ exit the tick was scheduled again to the same deadline but skipped reprogramming because ts->next_tick still kept in cache the deadline. This has been fixed now with resetting ts->next_tick from the tick itself. Extra care has also been taken to prevent from obsolete values throughout CPU hotplug operations. When the tick is stopped and an interrupt occurs afterward, we check on that interrupt exit if the next tick needs to be rescheduled. If it doesn't need any update, we don't want to do anything. In order to check if the tick needs an update, we compare it against the clockevent device deadline. Now that's a problem because the clockevent device is at a lower level than the tick itself if it is implemented on top of hrtimer. Every hrtimer share this clockevent device. So comparing the next tick deadline against the clockevent device deadline is wrong because the device may be programmed for another hrtimer whose deadline collides with the tick. As a result we may end up not reprogramming the tick accidentally. In a worst case scenario under full dynticks mode, the tick stops firing as it is supposed to every 1hz, leaving /proc/stat stalled: Task in a full dynticks CPU ---------------------------- * hrtimer A is queued 2 seconds ahead * the tick is stopped, scheduled 1 second ahead * tick fires 1 second later * on tick exit, nohz schedules the tick 1 second ahead but sees the clockevent device is already programmed to that deadline, fooled by hrtimer A, the tick isn't rescheduled. * hrtimer A is cancelled before its deadline * tick never fires again until an interrupt happens... In order to fix this, store the next tick deadline to the tick_sched local structure and reuse that value later to check whether we need to reprogram the clock after an interrupt. On the other hand, ts->sleep_length still wants to know about the next clock event and not just the tick, so we want to improve the related comment to avoid confusion. Reported-and-tested-by: Tim Wright <tim@binbash.co.uk> Reported-and-tested-by: Pavel Machek <pavel@ucw.cz> Reported-by: James Hartsock <hartsjc@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1492783255-5051-2-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
88 lines
2.6 KiB
C
88 lines
2.6 KiB
C
#ifndef _TICK_SCHED_H
|
|
#define _TICK_SCHED_H
|
|
|
|
#include <linux/hrtimer.h>
|
|
|
|
enum tick_device_mode {
|
|
TICKDEV_MODE_PERIODIC,
|
|
TICKDEV_MODE_ONESHOT,
|
|
};
|
|
|
|
struct tick_device {
|
|
struct clock_event_device *evtdev;
|
|
enum tick_device_mode mode;
|
|
};
|
|
|
|
enum tick_nohz_mode {
|
|
NOHZ_MODE_INACTIVE,
|
|
NOHZ_MODE_LOWRES,
|
|
NOHZ_MODE_HIGHRES,
|
|
};
|
|
|
|
/**
|
|
* struct tick_sched - sched tick emulation and no idle tick control/stats
|
|
* @sched_timer: hrtimer to schedule the periodic tick in high
|
|
* resolution mode
|
|
* @last_tick: Store the last tick expiry time when the tick
|
|
* timer is modified for nohz sleeps. This is necessary
|
|
* to resume the tick timer operation in the timeline
|
|
* when the CPU returns from nohz sleep.
|
|
* @next_tick: Next tick to be fired when in dynticks mode.
|
|
* @tick_stopped: Indicator that the idle tick has been stopped
|
|
* @idle_jiffies: jiffies at the entry to idle for idle time accounting
|
|
* @idle_calls: Total number of idle calls
|
|
* @idle_sleeps: Number of idle calls, where the sched tick was stopped
|
|
* @idle_entrytime: Time when the idle call was entered
|
|
* @idle_waketime: Time when the idle was interrupted
|
|
* @idle_exittime: Time when the idle state was left
|
|
* @idle_sleeptime: Sum of the time slept in idle with sched tick stopped
|
|
* @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding
|
|
* @sleep_length: Duration of the current idle sleep
|
|
* @do_timer_lst: CPU was the last one doing do_timer before going idle
|
|
*/
|
|
struct tick_sched {
|
|
struct hrtimer sched_timer;
|
|
unsigned long check_clocks;
|
|
enum tick_nohz_mode nohz_mode;
|
|
ktime_t last_tick;
|
|
ktime_t next_tick;
|
|
int inidle;
|
|
int tick_stopped;
|
|
unsigned long idle_jiffies;
|
|
unsigned long idle_calls;
|
|
unsigned long idle_sleeps;
|
|
int idle_active;
|
|
ktime_t idle_entrytime;
|
|
ktime_t idle_waketime;
|
|
ktime_t idle_exittime;
|
|
ktime_t idle_sleeptime;
|
|
ktime_t iowait_sleeptime;
|
|
ktime_t sleep_length;
|
|
unsigned long last_jiffies;
|
|
u64 next_timer;
|
|
ktime_t idle_expires;
|
|
int do_timer_last;
|
|
atomic_t tick_dep_mask;
|
|
};
|
|
|
|
extern struct tick_sched *tick_get_tick_sched(int cpu);
|
|
|
|
extern void tick_setup_sched_timer(void);
|
|
#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS
|
|
extern void tick_cancel_sched_timer(int cpu);
|
|
#else
|
|
static inline void tick_cancel_sched_timer(int cpu) { }
|
|
#endif
|
|
|
|
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
|
|
extern int __tick_broadcast_oneshot_control(enum tick_broadcast_state state);
|
|
#else
|
|
static inline int
|
|
__tick_broadcast_oneshot_control(enum tick_broadcast_state state)
|
|
{
|
|
return -EBUSY;
|
|
}
|
|
#endif
|
|
|
|
#endif
|