clocksource: Avoid selecting mult values that might overflow when adjusted
For some frequencies, the clocks_calc_mult_shift() function will
unfortunately select mult values very close to 0xffffffff. This
has the potential to overflow when NTP adjusts the clock, adding
to the mult value.
This patch adds a clocksource.maxadj value, which provides
an approximation of an 11% adjustment(NTP limits adjustments to
500ppm and the tick adjustment is limited to 10%), which could
be made to the clocksource.mult value. This is then used to both
check that the current mult value won't overflow/underflow, as
well as warning us if the timekeeping_adjust() code pushes over
that 11% boundary.
v2: Fix max_adjustment calculation, and improve WARN_ONCE
messages.
v3: Don't warn before maxadj has actually been set
CC: Yong Zhang <yong.zhang0@gmail.com>
CC: David Daney <ddaney.cavm@gmail.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Chen Jie <chenj@lemote.com>
CC: zhangfx <zhangfx@lemote.com>
CC: stable@kernel.org
Reported-by: Chen Jie <chenj@lemote.com>
Reported-by: zhangfx <zhangfx@lemote.com>
Tested-by: Yong Zhang <yong.zhang0@gmail.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index cf52fda..cfc65e1 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -492,6 +492,22 @@
}
/**
+ * clocksource_max_adjustment- Returns max adjustment amount
+ * @cs: Pointer to clocksource
+ *
+ */
+static u32 clocksource_max_adjustment(struct clocksource *cs)
+{
+ u64 ret;
+ /*
+ * We won't try to correct for more then 11% adjustments (110,000 ppm),
+ */
+ ret = (u64)cs->mult * 11;
+ do_div(ret,100);
+ return (u32)ret;
+}
+
+/**
* clocksource_max_deferment - Returns max time the clocksource can be deferred
* @cs: Pointer to clocksource
*
@@ -503,25 +519,28 @@
/*
* 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))
+ * maximum number of cycles is equal to ULLONG_MAX/(cs->mult+cs->maxadj)
+ * which is equivalent to the below.
+ * max_cycles < (2^63)/(cs->mult + cs->maxadj)
+ * max_cycles < 2^(log2((2^63)/(cs->mult + cs->maxadj)))
+ * max_cycles < 2^(log2(2^63) - log2(cs->mult + cs->maxadj))
+ * max_cycles < 2^(63 - log2(cs->mult + cs->maxadj))
+ * max_cycles < 1 << (63 - log2(cs->mult + cs->maxadj))
* 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));
+ max_cycles = 1ULL << (63 - (ilog2(cs->mult + cs->maxadj) + 1));
/*
* The actual maximum number of cycles we can defer the clocksource is
* determined by the minimum of max_cycles and cs->mask.
+ * Note: Here we subtract the maxadj to make sure we don't sleep for
+ * too long if there's a large negative adjustment.
*/
max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
- max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift);
+ max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult - cs->maxadj,
+ cs->shift);
/*
* To ensure that the clocksource does not wrap whilst we are idle,
@@ -640,7 +659,6 @@
void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
{
u64 sec;
-
/*
* Calc the maximum number of seconds which we can run before
* wrapping around. For clocksources which have a mask > 32bit
@@ -661,6 +679,20 @@
clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
NSEC_PER_SEC / scale, sec * scale);
+
+ /*
+ * for clocksources that have large mults, to avoid overflow.
+ * Since mult may be adjusted by ntp, add an safety extra margin
+ *
+ */
+ cs->maxadj = clocksource_max_adjustment(cs);
+ while ((cs->mult + cs->maxadj < cs->mult)
+ || (cs->mult - cs->maxadj > cs->mult)) {
+ cs->mult >>= 1;
+ cs->shift--;
+ cs->maxadj = clocksource_max_adjustment(cs);
+ }
+
cs->max_idle_ns = clocksource_max_deferment(cs);
}
EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
@@ -701,6 +733,12 @@
*/
int clocksource_register(struct clocksource *cs)
{
+ /* calculate max adjustment for given mult/shift */
+ cs->maxadj = clocksource_max_adjustment(cs);
+ WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
+ "Clocksource %s might overflow on 11%% adjustment\n",
+ cs->name);
+
/* calculate max idle time permitted for this clocksource */
cs->max_idle_ns = clocksource_max_deferment(cs);