sched: Call tick_check_idle before __irq_enter

Commit: d267f87fb8179c6dba03d08b91952e81bc3723c7 upstream
Author: Venkatesh Pallipadi <[email protected]>
AuthorDate: Mon Oct 4 17:03:23 2010 -0700

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 ee5f80a:

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.

LKML-Reference: <[email protected]>

---
 kernel/sched.c   |    2 +-
 kernel/softirq.c |   12 +++++++++---
 2 files changed, 10 insertions(+), 4 deletions(-)

index 4f86094..c7f69fe 100644
@@ -1872,8 +1872,8 @@ 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;
 	/*

index 0a617de..04a0252 100644
@@ -296,10 +296,16 @@ 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
-		__irq_enter();
+		_local_bh_enable();
+	}
+
+	__irq_enter();
 }
 
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED

1.7.4