nohz: Prevent clocksource wrapping during idle

The dynamic tick allows the kernel to sleep for periods longer than a
single tick, but it does not limit the sleep time currently. In the
worst case the kernel could sleep longer than the wrap around time of
the time keeping clock source which would result in losing track of
time.

Prevent this by limiting it to the safe maximum sleep time of the
current time keeping clock source. The value is calculated when the
clock source is registered.

[ tglx: simplified the code a bit and massaged the commit msg ]

Signed-off-by: Jon Hunter <jon-hunter@ti.com>
Cc: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <1250617512-23567-2-git-send-email-jon-hunter@ti.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 44 insertions, 0 deletions

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 407c0894ef3..b65b242f04d 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -469,6 +469,47 @@ void clocksource_touch_watchdog(void)
 #ifdef CONFIG_GENERIC_TIME
 
 /**
+ * clocksource_max_deferment - Returns max time the clocksource can be deferred
+ * @cs:         Pointer to clocksource
+ *
+ */
+static u64 clocksource_max_deferment(struct clocksource *cs)
+{
+        u64 max_nsecs, 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_t(u64, max_cycles, (u64) cs->mask);
+        max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift);
+
+        /*
+         * 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.
+         */
+        return max_nsecs - (max_nsecs >> 5);
+}
+
+/**
  * clocksource_select - Select the best clocksource available
  *
  * Private function. Must hold clocksource_mutex when called.
@@ -564,6 +605,9 @@ static void clocksource_enqueue(struct clocksource *cs)
  */
 int clocksource_register(struct clocksource *cs)
 {
+        /* calculate max idle time permitted for this clocksource */
+        cs->max_idle_ns = clocksource_max_deferment(cs);
+
         mutex_lock(&clocksource_mutex);
         clocksource_enqueue(cs);
         clocksource_select();