Merge tag 'lsk-v4.4-16.07-android'

[firefly-linux-kernel-4.4.55.git] / kernel / sched / fair.c

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 67629fa15d58e44b72c428afdb37cf31024381d5..c51be77f93930c5558d9d50237cdb78f2540b0c6 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2684,6 +2684,23 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
 
 static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
 
+/*
+ * Unsigned subtract and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define sub_positive(_ptr, _val) do {                          \
+       typeof(_ptr) ptr = (_ptr);                              \
+       typeof(*ptr) val = (_val);                              \
+       typeof(*ptr) res, var = READ_ONCE(*ptr);                \
+       res = var - val;                                        \
+       if (res > var)                                          \
+               res = 0;                                        \
+       WRITE_ONCE(*ptr, res);                                  \
+} while (0)
+
 /* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
 static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 {
@@ -2692,15 +2709,15 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 
        if (atomic_long_read(&cfs_rq->removed_load_avg)) {
                s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
-               sa->load_avg = max_t(long, sa->load_avg - r, 0);
-               sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
+               sub_positive(&sa->load_avg, r);
+               sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
                removed = 1;
        }
 
        if (atomic_long_read(&cfs_rq->removed_util_avg)) {
                long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
-               sa->util_avg = max_t(long, sa->util_avg - r, 0);
-               sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
+               sub_positive(&sa->util_avg, r);
+               sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
        }
 
        decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
@@ -2770,10 +2787,10 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
                          &se->avg, se->on_rq * scale_load_down(se->load.weight),
                          cfs_rq->curr == se, NULL);
 
-       cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
-       cfs_rq->avg.load_sum = max_t(s64,  cfs_rq->avg.load_sum - se->avg.load_sum, 0);
-       cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
-       cfs_rq->avg.util_sum = max_t(s32,  cfs_rq->avg.util_sum - se->avg.util_sum, 0);
+       sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
+       sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
+       sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
+       sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
 }
 
 /* Add the load generated by se into cfs_rq's load average */