[PATCH] Fix idle notifiers

Previously exit_idle would be called more often than enter_idle

Now instead of using complicated tests just keep track of it
using the per CPU variable as a flip flop.  I moved the idle state into the
PDA to make the access more efficient.

Original bug report and an initial patch from Stephane Eranian,
but redone by AK.

Cc: Stephane Eranian <eranian@hpl.hp.com>

Signed-off-by: Andi Kleen <ak@suse.de>

2 files changed, 11 insertions, 7 deletions

diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 885c318..458006a 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -80,25 +80,25 @@ void idle_notifier_unregister(struct notifier_block *n)
 }
 EXPORT_SYMBOL(idle_notifier_unregister);
 
-enum idle_state { CPU_IDLE, CPU_NOT_IDLE };
-static DEFINE_PER_CPU(enum idle_state, idle_state) = CPU_NOT_IDLE;
-
 void enter_idle(void)
 {
-	__get_cpu_var(idle_state) = CPU_IDLE;
+	write_pda(isidle, 1);
 	atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
 }
 
 static void __exit_idle(void)
 {
-	__get_cpu_var(idle_state) = CPU_NOT_IDLE;
+	if (read_pda(isidle) == 0)
+		return;
+	write_pda(isidle, 0);
 	atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
 }
 
 /* Called from interrupts to signify idle end */
 void exit_idle(void)
 {
-	if (current->pid | read_pda(irqcount))
+	/* idle loop has pid 0 */
+	if (current->pid)
 		return;
 	__exit_idle();
 }
@@ -220,6 +220,9 @@ void cpu_idle (void)
 				play_dead();
 			enter_idle();
 			idle();
+			/* In many cases the interrupt that ended idle
+			   has already called exit_idle. But some idle
+			   loops can be woken up without interrupt. */
 			__exit_idle();
 		}
 
diff --git a/include/asm-x86_64/pda.h b/include/asm-x86_64/pda.h
index 531f48a..14996d9 100644
--- a/include/asm-x86_64/pda.h
+++ b/include/asm-x86_64/pda.h
@@ -25,7 +25,8 @@ struct x8664_pda {
 	int nodenumber;		    /* number of current node */
 	unsigned int __softirq_pending;
 	unsigned int __nmi_count;	/* number of NMI on this CPUs */
-	int mmu_state;     
+	short mmu_state;
+	short isidle;
 	struct mm_struct *active_mm;
 	unsigned apic_timer_irqs;
 } ____cacheline_aligned_in_smp;