From: Daniel Lezcano The idle_balance modifies the idle_stamp field of the rq, making this information to be shared across core.c and fair.c. As we can know if the cpu is going to idle or not with the previous patch, let's encapsulate the idle_stamp information in core.c by moving it up to the caller. The idle_balance function returns true in case a balancing occured and the cpu won't be idle, false if no balance happened and the cpu is going idle. Cc: mingo@kernel.org Cc: alex.shi@linaro.org Cc: peterz@infradead.org Signed-off-by: Daniel Lezcano Signed-off-by: Peter Zijlstra --- kernel/sched/core.c | 11 +++++++++-- kernel/sched/fair.c | 14 ++++++-------- kernel/sched/sched.h | 2 +- 3 files changed, 16 insertions(+), 11 deletions(-) --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2681,8 +2681,15 @@ static void __sched __schedule(void) pre_schedule(rq, prev); - if (unlikely(!rq->nr_running)) - idle_balance(rq); + if (unlikely(!rq->nr_running)) { + /* + * We must set idle_stamp _before_ calling idle_balance(), such + * that we measure the duration of idle_balance() as idle time. + */ + rq->idle_stamp = rq_clock(rq); + if (idle_balance(rq)) + rq->idle_stamp = 0; + } put_prev_task(rq, prev); next = pick_next_task(rq); --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6535,7 +6535,7 @@ static int load_balance(int this_cpu, st * idle_balance is called by schedule() if this_cpu is about to become * idle. Attempts to pull tasks from other CPUs. */ -void idle_balance(struct rq *this_rq) +int idle_balance(struct rq *this_rq) { struct sched_domain *sd; int pulled_task = 0; @@ -6543,10 +6543,8 @@ void idle_balance(struct rq *this_rq) u64 curr_cost = 0; int this_cpu = this_rq->cpu; - this_rq->idle_stamp = rq_clock(this_rq); - if (this_rq->avg_idle < sysctl_sched_migration_cost) - return; + return 0; /* * Drop the rq->lock, but keep IRQ/preempt disabled. @@ -6584,10 +6582,8 @@ void idle_balance(struct rq *this_rq) interval = msecs_to_jiffies(sd->balance_interval); if (time_after(next_balance, sd->last_balance + interval)) next_balance = sd->last_balance + interval; - if (pulled_task) { - this_rq->idle_stamp = 0; + if (pulled_task) break; - } } rcu_read_unlock(); @@ -6598,7 +6594,7 @@ void idle_balance(struct rq *this_rq) * A task could have be enqueued in the meantime */ if (this_rq->nr_running && !pulled_task) - return; + return 1; if (pulled_task || time_after(jiffies, this_rq->next_balance)) { /* @@ -6610,6 +6606,8 @@ void idle_balance(struct rq *this_rq) if (curr_cost > this_rq->max_idle_balance_cost) this_rq->max_idle_balance_cost = curr_cost; + + return pulled_task; } /* --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1176,7 +1176,7 @@ extern const struct sched_class idle_sch extern void update_group_power(struct sched_domain *sd, int cpu); extern void trigger_load_balance(struct rq *rq); -extern void idle_balance(struct rq *this_rq); +extern int idle_balance(struct rq *this_rq); extern void idle_enter_fair(struct rq *this_rq); extern void idle_exit_fair(struct rq *this_rq); -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/