| 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
| ||
|
Date: Fri, 22 May 2009 13:21:40 -0500
From: Jon Hunter <jon-hunter@...com>
To: John Stultz <johnstul@...ibm.com>
CC: Ingo Molnar <mingo@...e.hu>, Thomas Gleixner <tglx@...utronix.de>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: [RFC][PATCH] Dynamic Tick: Allow 32-bit machines to sleep formorethan2.15
seconds
John Stultz wrote:
> So cyc2ns is a very very hot path, so I don't think we want to muck with
> that much.
>
> Instead of catching the overflows, and then trying to handle them, we
> really want to prevent overflows from happening. That is the main point
> of the timekeeping_max_deferrment() interface after all ;)
>
> So thinking about it a bit more, what we really want from
> timekeeping_max_deferrment() is roughly:
>
> /* find the max cycle value that would overflow the mult */
> max_cycles = -1UUL/clocksource->mult;
>
> /* pick the smaller of max_cycles or the mask value */
> max_cycles = min(max_cycles, clocksource->mask);
>
> /* convert max_cycles into ns */
> max_time = cyc2ns(clocksource, max_cycles);
>
> /* take off 5% of the max to make sure we don't show up late */
> max_time = max_time - max_time/20;
>
>
> We should be able to make this reasonably fast via:
> max_cycles = 1<<(64 - ilog2(clocksource->mult) - 1);
> max_cycles = min(max_cycles, clocksource->mask);
> max_time = cyc2ns(clocksource, max_cycles);
> max_time = max_time - max_time >> 4;
>
> Does that seem reasonable?
Yes, good idea. Sorry for the delay in getting back to this. I have
implemented the above and incorporated into the patch below.
Please note that the only modification I made to the above was to add 1
to result of the log2. I found that the result of the log2 was rounded
down and so this was still making max_cycles too big. Therefore to be on
the safe side I add 1 to the result of log2 which will ensure max_cycles
is not too big.
Thanks for the inputs. Let me know your thoughts.
Cheers
Jon
Signed-off-by: Jon Hunter <jon-hunter@...com>
---
include/linux/time.h | 1 +
kernel/time/tick-sched.c | 36 +++++++++++++++++++++++----------
kernel/time/timekeeping.c | 47
+++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 73 insertions(+), 11 deletions(-)
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/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..608fc6f 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -271,6 +271,53 @@ int timekeeping_valid_for_hres(void)
}
/**
+ * timekeeping_max_deferment - Returns max time the clocksource can be
deferred
+ *
+ * IMPORTANT: Must be called with xtime_lock held!
+ */
+s64 timekeeping_max_deferment(void)
+{
+ 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/clock->mult which
+ * is equivalent to the below.
+ * max_cycles < (2^63)/clock->mult
+ * max_cycles < 2^(log2((2^63)/clock->mult))
+ * max_cycles < 2^(log2(2^63) - log2(clock->mult))
+ * max_cycles < 2^(63 - log2(clock->mult))
+ * max_cycles < 1 << (63 - log2(clock->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(clock->mult) + 1));
+
+ /*
+ * The actual maximum number of cycles we can defer the clocksource is
+ * determined by the minimum of max_cycles and clock->mask.
+ */
+ max_cycles = min(max_cycles, clock->mask);
+ max_nsecs = cyc2ns(clock, max_cycles);
+
+ /*
+ * To ensure that the clocksource does not wrap whilst we are idle,
+ * limit the time the clocksource can be deferred by 6.25%. Please
+ * note a margin of 6.25% is used because this can be computed with
+ * a shift, versus say 5% which would require division.
+ */
+ max_nsecs = max_nsecs - (max_nsecs >> 4);
+
+ if (max_nsecs < 0)
+ max_nsecs = 0;
+
+ return max_nsecs;
+}
+
+/**
* read_persistent_clock - Return time in seconds from the persistent
clock.
*
* Weak dummy function for arches that do not yet support it.
--
1.6.1
--
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