[PATCH] sched: resched and cpu_idle rework

Make some changes to the NEED_RESCHED and POLLING_NRFLAG to reduce
confusion, and make their semantics rigid.  Improves efficiency of
resched_task and some cpu_idle routines.

* In resched_task:
- TIF_NEED_RESCHED is only cleared with the task's runqueue lock held,
  and as we hold it during resched_task, then there is no need for an
  atomic test and set there. The only other time this should be set is
  when the task's quantum expires, in the timer interrupt - this is
  protected against because the rq lock is irq-safe.

- If TIF_NEED_RESCHED is set, then we don't need to do anything. It
  won't get unset until the task get's schedule()d off.

- If we are running on the same CPU as the task we resched, then set
  TIF_NEED_RESCHED and no further action is required.

- If we are running on another CPU, and TIF_POLLING_NRFLAG is *not* set
  after TIF_NEED_RESCHED has been set, then we need to send an IPI.

Using these rules, we are able to remove the test and set operation in
resched_task, and make clear the previously vague semantics of
POLLING_NRFLAG.

* In idle routines:
- Enter cpu_idle with preempt disabled. When the need_resched() condition
  becomes true, explicitly call schedule(). This makes things a bit clearer
  (IMO), but haven't updated all architectures yet.

- Many do a test and clear of TIF_NEED_RESCHED for some reason. According
  to the resched_task rules, this isn't needed (and actually breaks the
  assumption that TIF_NEED_RESCHED is only cleared with the runqueue lock
  held). So remove that. Generally one less locked memory op when switching
  to the idle thread.

- Many idle routines clear TIF_POLLING_NRFLAG, and only set it in the inner
  most polling idle loops. The above resched_task semantics allow it to be
  set until before the last time need_resched() is checked before going into
  a halt requiring interrupt wakeup.

  Many idle routines simply never enter such a halt, and so POLLING_NRFLAG
  can be always left set, completely eliminating resched IPIs when rescheduling
  the idle task.

  POLLING_NRFLAG width can be increased, to reduce the chance of resched IPIs.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Con Kolivas <kernel@kolivas.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 47 insertions, 37 deletions

diff --git a/arch/i386/kernel/apm.c b/arch/i386/kernel/apm.c
index 86e80c551478..003548b8735f 100644
--- a/arch/i386/kernel/apm.c
+++ b/arch/i386/kernel/apm.c
@@ -769,8 +769,26 @@ static int set_system_power_state(u_short state)
 static int apm_do_idle(void)
 {
 	u32	eax;
+	u8	ret = 0;
+	int	idled = 0;
+	int	polling;
+
+	polling = test_thread_flag(TIF_POLLING_NRFLAG);
+	if (polling) {
+		clear_thread_flag(TIF_POLLING_NRFLAG);
+		smp_mb__after_clear_bit();
+	}
+	if (!need_resched()) {
+		idled = 1;
+		ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax);
+	}
+	if (polling)
+		set_thread_flag(TIF_POLLING_NRFLAG);
+
+	if (!idled)
+		return 0;
 
-	if (apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax)) {
+	if (ret) {
 		static unsigned long t;
 
 		/* This always fails on some SMP boards running UP kernels.
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index 5296e284ea36..1cb261f225d5 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -99,14 +99,22 @@ EXPORT_SYMBOL(enable_hlt);
  */
 void default_idle(void)
 {
+	local_irq_enable();
+
 	if (!hlt_counter && boot_cpu_data.hlt_works_ok) {
-		local_irq_disable();
-		if (!need_resched())
-			safe_halt();
-		else
-			local_irq_enable();
+		clear_thread_flag(TIF_POLLING_NRFLAG);
+		smp_mb__after_clear_bit();
+		while (!need_resched()) {
+			local_irq_disable();
+			if (!need_resched())
+				safe_halt();
+			else
+				local_irq_enable();
+		}
+		set_thread_flag(TIF_POLLING_NRFLAG);
 	} else {
-		cpu_relax();
+		while (!need_resched())
+			cpu_relax();
 	}
 }
 #ifdef CONFIG_APM_MODULE
@@ -120,29 +128,14 @@ EXPORT_SYMBOL(default_idle);
  */
 static void poll_idle (void)
 {
-	int oldval;
-
 	local_irq_enable();
 
-	/*
-	 * Deal with another CPU just having chosen a thread to
-	 * run here:
-	 */
-	oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);
-
-	if (!oldval) {
-		set_thread_flag(TIF_POLLING_NRFLAG);
-		asm volatile(
-			"2:"
-			"testl %0, %1;"
-			"rep; nop;"
-			"je 2b;"
-			: : "i"(_TIF_NEED_RESCHED), "m" (current_thread_info()->flags));
-
-		clear_thread_flag(TIF_POLLING_NRFLAG);
-	} else {
-		set_need_resched();
-	}
+	asm volatile(
+		"2:"
+		"testl %0, %1;"
+		"rep; nop;"
+		"je 2b;"
+		: : "i"(_TIF_NEED_RESCHED), "m" (current_thread_info()->flags));
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -181,6 +174,8 @@ void cpu_idle(void)
 {
 	int cpu = smp_processor_id();
 
+	set_thread_flag(TIF_POLLING_NRFLAG);
+
 	/* endless idle loop with no priority at all */
 	while (1) {
 		while (!need_resched()) {
@@ -246,15 +241,12 @@ static void mwait_idle(void)
 {
 	local_irq_enable();
 
-	if (!need_resched()) {
-		set_thread_flag(TIF_POLLING_NRFLAG);
-		do {
-			__monitor((void *)&current_thread_info()->flags, 0, 0);
-			if (need_resched())
-				break;
-			__mwait(0, 0);
-		} while (!need_resched());
-		clear_thread_flag(TIF_POLLING_NRFLAG);
+	while (!need_resched()) {
+		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		smp_mb();
+		if (need_resched())
+			break;
+		__mwait(0, 0);
 	}
 }