sched/loadavg: Use {READ,WRITE}_ONCE() for sample window

'calc_load_update' is accessed without any kind of locking and there's
a clear assumption in the code that only a single value is read or
written.

Make this explicit by using READ_ONCE() and WRITE_ONCE(), and avoid
unintentionally seeing multiple values, or having the load/stores
split.

Technically the loads in calc_global_*() don't require this since
those are the only functions that update 'calc_load_update', but I've
added the READ_ONCE() for consistency.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Link: http://lkml.kernel.org/r/20170217120731.11868-3-matt@codeblueprint.co.uk
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index 3a55f3f9ffe4e576cdeb76088862c76541f8197b..f15fb2bdbc0dee60d770da951424f8cf0635f5f6 100644 (file)
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -169,7 +169,7 @@ static inline int calc_load_write_idx(void)
         * If the folding window started, make sure we start writing in the
         * next idle-delta.
         */
-       if (!time_before(jiffies, calc_load_update))
+       if (!time_before(jiffies, READ_ONCE(calc_load_update)))
                idx++;
 
        return idx & 1;
@@ -204,7 +204,7 @@ void calc_load_exit_idle(void)
        /*
         * If we're still before the pending sample window, we're done.
         */
-       this_rq->calc_load_update = calc_load_update;
+       this_rq->calc_load_update = READ_ONCE(calc_load_update);
        if (time_before(jiffies, this_rq->calc_load_update))
                return;
 
@@ -308,13 +308,15 @@ calc_load_n(unsigned long load, unsigned long exp,
  */
 static void calc_global_nohz(void)
 {
+       unsigned long sample_window;
        long delta, active, n;
 
-       if (!time_before(jiffies, calc_load_update + 10)) {
+       sample_window = READ_ONCE(calc_load_update);
+       if (!time_before(jiffies, sample_window + 10)) {
                /*
                 * Catch-up, fold however many we are behind still
                 */
-               delta = jiffies - calc_load_update - 10;
+               delta = jiffies - sample_window - 10;
                n = 1 + (delta / LOAD_FREQ);
 
                active = atomic_long_read(&calc_load_tasks);
@@ -324,7 +326,7 @@ static void calc_global_nohz(void)
                avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
                avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
 
-               calc_load_update += n * LOAD_FREQ;
+               WRITE_ONCE(calc_load_update, sample_window + n * LOAD_FREQ);
        }
 
        /*
@@ -352,9 +354,11 @@ static inline void calc_global_nohz(void) { }
  */
 void calc_global_load(unsigned long ticks)
 {
+       unsigned long sample_window;
        long active, delta;
 
-       if (time_before(jiffies, calc_load_update + 10))
+       sample_window = READ_ONCE(calc_load_update);
+       if (time_before(jiffies, sample_window + 10))
                return;
 
        /*
@@ -371,7 +375,7 @@ void calc_global_load(unsigned long ticks)
        avenrun[1] = calc_load(avenrun[1], EXP_5, active);
        avenrun[2] = calc_load(avenrun[2], EXP_15, active);
 
-       calc_load_update += LOAD_FREQ;
+       WRITE_ONCE(calc_load_update, sample_window + LOAD_FREQ);
 
        /*
         * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.