[PATCH] x86: Don't use nested idle loops

Currently the idle loop has two nested loops -- one high level
in cpu_idle and in some low level idle functions another one.

Looping in the low level idle functions breaks the idle notifiers
because interrupts waking up sleep states need to execute
exit_idle() which is only in cpu_idle().

So don't do that, only loop in cpu_idle(). This only removes
code.

In some cases e.g. poll_idle the idle loop is a little longer
now because cpu_idle checks more things. I hope that isn't a problem
ACPI idle doesn't change behaviour because it never looped anyways.

Cc: len.brown@intel.com
Cc: eranian@hpl.hp.com
Signed-off-by: Andi Kleen <ak@suse.de>

2 files changed, 18 insertions, 42 deletions

diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index 8749b10d380..8f42659ef9d 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -100,22 +100,18 @@ EXPORT_SYMBOL(enable_hlt);
  */
 void default_idle(void)
 {
-	local_irq_enable();
-
 	if (!hlt_counter && boot_cpu_data.hlt_works_ok) {
 		current_thread_info()->status &= ~TS_POLLING;
 		smp_mb__after_clear_bit();
-		while (!need_resched()) {
-			local_irq_disable();
-			if (!need_resched())
-				safe_halt();
-			else
-				local_irq_enable();
-		}
+		local_irq_disable();
+		if (!need_resched())
+			safe_halt();	/* enables interrupts racelessly */
+		else
+			local_irq_enable();
 		current_thread_info()->status |= TS_POLLING;
 	} else {
-		while (!need_resched())
-			cpu_relax();
+		/* loop is done by the caller */
+		cpu_relax();
 	}
 }
 #ifdef CONFIG_APM_MODULE
@@ -129,14 +125,7 @@ EXPORT_SYMBOL(default_idle);
  */
 static void poll_idle (void)
 {
-	local_irq_enable();
-
-	asm volatile(
-		"2:"
-		"testl %0, %1;"
-		"rep; nop;"
-		"je 2b;"
-		: : "i"(_TIF_NEED_RESCHED), "m" (current_thread_info()->flags));
+	cpu_relax();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -257,8 +246,7 @@ void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
 static void mwait_idle(void)
 {
 	local_irq_enable();
-	while (!need_resched())
-		mwait_idle_with_hints(0, 0);
+	mwait_idle_with_hints(0, 0);
 }
 
 void __devinit select_idle_routine(const struct cpuinfo_x86 *c)
diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 7451a4c43c1..0b7b4caa4f7 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -108,17 +108,15 @@ void exit_idle(void)
  */
 static void default_idle(void)
 {
-	local_irq_enable();
-
 	current_thread_info()->status &= ~TS_POLLING;
 	smp_mb__after_clear_bit();
-	while (!need_resched()) {
-		local_irq_disable();
-		if (!need_resched())
-			safe_halt();
-		else
-			local_irq_enable();
-	}
+	local_irq_disable();
+	if (!need_resched()) {
+		/* Enables interrupts one instruction before HLT.
+		   x86 special cases this so there is no race. */
+		safe_halt();
+	} else
+		local_irq_enable();
 	current_thread_info()->status |= TS_POLLING;
 }
 
@@ -129,16 +127,7 @@ static void default_idle(void)
  */
 static void poll_idle (void)
 {
-	local_irq_enable();
-
-	asm volatile(
-		"2:"
-		"testl %0,%1;"
-		"rep; nop;"
-		"je 2b;"
-		: :
-		"i" (_TIF_NEED_RESCHED),
-		"m" (current_thread_info()->flags));
+	cpu_relax();
 }
 
 void cpu_idle_wait(void)
@@ -257,8 +246,7 @@ void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
 static void mwait_idle(void)
 {
 	local_irq_enable();
-	while (!need_resched())
-		mwait_idle_with_hints(0,0);
+	mwait_idle_with_hints(0,0);
 }
 
 void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)