| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1243546984.29511.525.camel@jstultz-laptop>
Date: Thu, 28 May 2009 14:43:04 -0700
From: John Stultz <johnstul@...ibm.com>
To: Jon Hunter <jon-hunter@...com>
Cc: Thomas Gleixner <tglx@...utronix.de>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
Ingo Molnar <mingo@...e.hu>
Subject: Re: [PATCH 1/2] Dynamic Tick: Prevent clocksource wrapping during
idle
On Thu, 2009-05-28 at 16:10 -0500, Jon Hunter wrote:
> Thomas Gleixner wrote:
> > Please make this a real function. There is no reason to stick this
> > into a header file. The only user is clocksource.c anyway, so please
> > put it there as a static function and let the compiler decide what
> > to do with it.
>
> No problem. Please see below. Let me know if this is ok and there is
> anything else.
>
> Cheers
> Jon
>
> The dynamic tick allows the kernel to sleep for periods longer
> than a single tick. This patch prevents that the kernel from
> sleeping for a period longer than the maximum time that the
> current clocksource can count. This ensures that the kernel will
> not lose track of time. This patch adds a function called
> "clocksource_max_deferment()" that calculates the maximum time the
> kernel can sleep for a given clocksource and function called
> "timekeeping_max_deferment()" that returns maximum time the kernel
> can sleep for the current clocksource.
>
> Signed-off-by: Jon Hunter <jon-hunter@...com>
Thanks for putting up with my apparent misdirections and going around
and around on this. :)
Acked-by: John Stultz <johnstul@...ibm.com>
> ---
> include/linux/clocksource.h | 2 +
> include/linux/time.h | 1 +
> kernel/time/clocksource.c | 47
> +++++++++++++++++++++++++++++++++++++++++++
> kernel/time/tick-sched.c | 36 ++++++++++++++++++++++----------
> kernel/time/timekeeping.c | 11 ++++++++++
> 5 files changed, 86 insertions(+), 11 deletions(-)
>
> diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
> index 5a40d14..465af22 100644
> --- a/include/linux/clocksource.h
> +++ b/include/linux/clocksource.h
> @@ -151,6 +151,7 @@ extern u64 timecounter_cyc2time(struct timecounter *tc,
> * @mult: cycle to nanosecond multiplier (adjusted by NTP)
> * @mult_orig: cycle to nanosecond multiplier (unadjusted by NTP)
> * @shift: cycle to nanosecond divisor (power of two)
> + * @max_idle_ns: max idle time permitted by the clocksource (nsecs)
> * @flags: flags describing special properties
> * @vread: vsyscall based read
> * @resume: resume function for the clocksource, if necessary
> @@ -171,6 +172,7 @@ struct clocksource {
> u32 mult;
> u32 mult_orig;
> u32 shift;
> + s64 max_idle_ns;
> unsigned long flags;
> cycle_t (*vread)(void);
> void (*resume)(void);
> diff --git a/include/linux/time.h b/include/linux/time.h
> index 242f624..090be07 100644
> --- a/include/linux/time.h
> +++ b/include/linux/time.h
> @@ -130,6 +130,7 @@ extern void monotonic_to_bootbased(struct timespec *ts);
>
> extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
> extern int timekeeping_valid_for_hres(void);
> +extern s64 timekeeping_max_deferment(void);
> extern void update_wall_time(void);
> extern void update_xtime_cache(u64 nsec);
>
> diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
> index ecfd7b5..18d2b9f 100644
> --- a/kernel/time/clocksource.c
> +++ b/kernel/time/clocksource.c
> @@ -321,6 +321,50 @@ void clocksource_touch_watchdog(void)
> }
>
> /**
> + * clocksource_max_deferment - Returns max time the clocksource can be
> deferred
> + * @cs: Pointer to clocksource
> + *
> + */
> +static s64 clocksource_max_deferment(struct clocksource *cs)
> +{
> + s64 max_nsecs;
> + u64 max_cycles;
> +
> + /*
> + * Calculate the maximum number of cycles that we can pass to the
> + * cyc2ns function without overflowing a 64-bit signed result. The
> + * maximum number of cycles is equal to ULLONG_MAX/cs->mult which
> + * is equivalent to the below.
> + * max_cycles < (2^63)/cs->mult
> + * max_cycles < 2^(log2((2^63)/cs->mult))
> + * max_cycles < 2^(log2(2^63) - log2(cs->mult))
> + * max_cycles < 2^(63 - log2(cs->mult))
> + * max_cycles < 1 << (63 - log2(cs->mult))
> + * Please note that we add 1 to the result of the log2 to account for
> + * any rounding errors, ensure the above inequality is satisfied and
> + * no overflow will occur.
> + */
> + max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1));
> +
> + /*
> + * The actual maximum number of cycles we can defer the clocksource is
> + * determined by the minimum of max_cycles and cs->mask.
> + */
> + max_cycles = min(max_cycles, cs->mask);
> + max_nsecs = cyc2ns(cs, max_cycles);
> +
> + /*
> + * To ensure that the clocksource does not wrap whilst we are idle,
> + * limit the time the clocksource can be deferred by 12.5%. Please
> + * note a margin of 12.5% is used because this can be computed with
> + * a shift, versus say 10% which would require division.
> + */
> + max_nsecs = max_nsecs - (max_nsecs >> 5);
> +
> + return max_nsecs;
> +}
> +
> +/**
> * clocksource_get_next - Returns the selected clocksource
> *
> */
> @@ -405,6 +449,9 @@ int clocksource_register(struct clocksource *c)
> /* save mult_orig on registration */
> c->mult_orig = c->mult;
>
> + /* calculate max idle time permitted for this clocksource */
> + c->max_idle_ns = clocksource_max_deferment(c);
> +
> spin_lock_irqsave(&clocksource_lock, flags);
> ret = clocksource_enqueue(c);
> if (!ret)
> diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
> index d3f1ef4..f0155ae 100644
> --- a/kernel/time/tick-sched.c
> +++ b/kernel/time/tick-sched.c
> @@ -217,6 +217,7 @@ void tick_nohz_stop_sched_tick(int inidle)
> ktime_t last_update, expires, now;
> struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
> int cpu;
> + s64 time_delta, max_time_delta;
>
> local_irq_save(flags);
>
> @@ -264,6 +265,7 @@ void tick_nohz_stop_sched_tick(int inidle)
> seq = read_seqbegin(&xtime_lock);
> last_update = last_jiffies_update;
> last_jiffies = jiffies;
> + max_time_delta = timekeeping_max_deferment();
> } while (read_seqretry(&xtime_lock, seq));
>
> /* Get the next timer wheel timer */
> @@ -283,11 +285,22 @@ void tick_nohz_stop_sched_tick(int inidle)
> if ((long)delta_jiffies >= 1) {
>
> /*
> - * calculate the expiry time for the next timer wheel
> - * timer
> - */
> - expires = ktime_add_ns(last_update, tick_period.tv64 *
> - delta_jiffies);
> + * Calculate the time delta for the next timer event.
> + * If the time delta exceeds the maximum time delta
> + * permitted by the current clocksource then adjust
> + * the time delta accordingly to ensure the
> + * clocksource does not wrap.
> + */
> + time_delta = tick_period.tv64 * delta_jiffies;
> +
> + if (time_delta > max_time_delta)
> + time_delta = max_time_delta;
> +
> + /*
> + * calculate the expiry time for the next timer wheel
> + * timer
> + */
> + expires = ktime_add_ns(last_update, time_delta);
>
> /*
> * If this cpu is the one which updates jiffies, then
> @@ -300,7 +313,7 @@ void tick_nohz_stop_sched_tick(int inidle)
> if (cpu == tick_do_timer_cpu)
> tick_do_timer_cpu = TICK_DO_TIMER_NONE;
>
> - if (delta_jiffies > 1)
> + if (time_delta > tick_period.tv64)
> cpumask_set_cpu(cpu, nohz_cpu_mask);
>
> /* Skip reprogram of event if its not changed */
> @@ -332,12 +345,13 @@ void tick_nohz_stop_sched_tick(int inidle)
> ts->idle_sleeps++;
>
> /*
> - * delta_jiffies >= NEXT_TIMER_MAX_DELTA signals that
> - * there is no timer pending or at least extremly far
> - * into the future (12 days for HZ=1000). In this case
> - * we simply stop the tick timer:
> + * time_delta >= (tick_period.tv64 * NEXT_TIMER_MAX_DELTA)
> + * signals that there is no timer pending or at least
> + * extremely far into the future (12 days for HZ=1000).
> + * In this case we simply stop the tick timer:
> */
> - if (unlikely(delta_jiffies >= NEXT_TIMER_MAX_DELTA)) {
> + if (unlikely(time_delta >=
> + (tick_period.tv64 * NEXT_TIMER_MAX_DELTA))) {
> ts->idle_expires.tv64 = KTIME_MAX;
> if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
> hrtimer_cancel(&ts->sched_timer);
> diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
> index 687dff4..659cae3 100644
> --- a/kernel/time/timekeeping.c
> +++ b/kernel/time/timekeeping.c
> @@ -271,6 +271,17 @@ int timekeeping_valid_for_hres(void)
> }
>
> /**
> + * timekeeping_max_deferment - Returns max time the clocksource can be
> deferred
> + *
> + * IMPORTANT: Caller must observe xtime_lock via
> read_seqbegin/read_seqretry
> + * to ensure that the clocksource does not change!
> + */
> +s64 timekeeping_max_deferment(void)
> +{
> + return clock->max_idle_ns;
> +}
> +
> +/**
> * read_persistent_clock - Return time in seconds from the persistent
> clock.
> *
> * Weak dummy function for arches that do not yet support it.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists