Commit d267f87f authored Oct 04, 2010 by Venkatesh Pallipadi Committed by Ingo Molnar Oct 18, 2010

sched: Call tick_check_idle before __irq_enter



When CPU is idle and on first interrupt, irq_enter calls tick_check_idle()
to notify interruption from idle. But, there is a problem if this call
is done after __irq_enter, as all routines in __irq_enter may find
stale time due to yet to be done tick_check_idle.

Specifically, trace calls in __irq_enter when they use global clock and also
account_system_vtime change in this patch as it wants to use sched_clock_cpu()
to do proper irq timing.

But, tick_check_idle was moved after __irq_enter intentionally to
prevent problem of unneeded ksoftirqd wakeups by the commit ee5f80a9:

    irq: call __irq_enter() before calling the tick_idle_check
    Impact: avoid spurious ksoftirqd wakeups

Moving tick_check_idle() before __irq_enter and wrapping it with
local_bh_enable/disable would solve both the problems.

Fixed-by: Yong Zhang <yong.zhang0@gmail.com>
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-9-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

parent aa483808

kernel/sched.c

+1 −1

Original line number	Diff line number	Diff line
		@@ -1974,8 +1974,8 @@ void account_system_vtime(struct task_struct *curr)

		local_irq_save(flags);

		now = sched_clock();
		cpu = smp_processor_id();
		now = sched_clock_cpu(cpu);
		delta = now - per_cpu(irq_start_time, cpu);
		per_cpu(irq_start_time, cpu) = now;
		/*

kernel/softirq.c

+9 −3

Original line number	Diff line number	Diff line
		@@ -296,9 +296,15 @@ void irq_enter(void)

		rcu_irq_enter();
		if (idle_cpu(cpu) && !in_interrupt()) {
		__irq_enter();
		/*
		* Prevent raise_softirq from needlessly waking up ksoftirqd
		* here, as softirq will be serviced on return from interrupt.
		*/
		local_bh_disable();
		tick_check_idle(cpu);
		} else
		_local_bh_enable();
		}

		__irq_enter();
		}

Admin message