sched, idle: Fix the idle polling state logic

commit ea8117478918a4734586d35ff530721b682425be upstream.

Mike reported that commit 7d1a9417 ("x86: Use generic idle loop")
regressed several workloads and caused excessive reschedule
interrupts.

The patch in question failed to notice that the x86 code had an
inverted sense of the polling state versus the new generic code (x86:
default polling, generic: default !polling).

Fix the two prominent x86 mwait based idle drivers and introduce a few
new generic polling helpers (fixing the wrong smp_mb__after_clear_bit
usage).

Also switch the idle routines to using tif_need_resched() which is an
immediate TIF_NEED_RESCHED test as opposed to need_resched which will
end up being slightly different.

Reported-by: Mike Galbraith <bitbucket@online.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: lenb@kernel.org
Cc: tglx@linutronix.de
Link: http://lkml.kernel.org/n/tip-nc03imb0etuefmzybzj7sprf@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

2 files changed, 11 insertions, 37 deletions

diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index f98dd00b51a9..c7414a545a4f 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -119,17 +119,10 @@ static struct dmi_system_id processor_power_dmi_table[] = {
  */
 static void acpi_safe_halt(void)
 {
-	current_thread_info()->status &= ~TS_POLLING;
-	/*
-	 * TS_POLLING-cleared state must be visible before we
-	 * test NEED_RESCHED:
-	 */
-	smp_mb();
-	if (!need_resched()) {
+	if (!tif_need_resched()) {
 		safe_halt();
 		local_irq_disable();
 	}
-	current_thread_info()->status |= TS_POLLING;
 }
 
 #ifdef ARCH_APICTIMER_STOPS_ON_C3
@@ -737,6 +730,11 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev,
 	if (unlikely(!pr))
 		return -EINVAL;
 
+	if (cx->entry_method == ACPI_CSTATE_FFH) {
+		if (current_set_polling_and_test())
+			return -EINVAL;
+	}
+
 	lapic_timer_state_broadcast(pr, cx, 1);
 	acpi_idle_do_entry(cx);
 
@@ -790,18 +788,9 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
 	if (unlikely(!pr))
 		return -EINVAL;
 
-	if (cx->entry_method != ACPI_CSTATE_FFH) {
-		current_thread_info()->status &= ~TS_POLLING;
-		/*
-		 * TS_POLLING-cleared state must be visible before we test
-		 * NEED_RESCHED:
-		 */
-		smp_mb();
-
-		if (unlikely(need_resched())) {
-			current_thread_info()->status |= TS_POLLING;
+	if (cx->entry_method == ACPI_CSTATE_FFH) {
+		if (current_set_polling_and_test())
 			return -EINVAL;
-		}
 	}
 
 	/*
@@ -819,9 +808,6 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
 
 	sched_clock_idle_wakeup_event(0);
 
-	if (cx->entry_method != ACPI_CSTATE_FFH)
-		current_thread_info()->status |= TS_POLLING;
-
 	lapic_timer_state_broadcast(pr, cx, 0);
 	return index;
 }
@@ -858,18 +844,9 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 		}
 	}
 
-	if (cx->entry_method != ACPI_CSTATE_FFH) {
-		current_thread_info()->status &= ~TS_POLLING;
-		/*
-		 * TS_POLLING-cleared state must be visible before we test
-		 * NEED_RESCHED:
-		 */
-		smp_mb();
-
-		if (unlikely(need_resched())) {
-			current_thread_info()->status |= TS_POLLING;
+	if (cx->entry_method == ACPI_CSTATE_FFH) {
+		if (current_set_polling_and_test())
 			return -EINVAL;
-		}
 	}
 
 	acpi_unlazy_tlb(smp_processor_id());
@@ -915,9 +892,6 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 
 	sched_clock_idle_wakeup_event(0);
 
-	if (cx->entry_method != ACPI_CSTATE_FFH)
-		current_thread_info()->status |= TS_POLLING;
-
 	lapic_timer_state_broadcast(pr, cx, 0);
 	return index;
 }
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index fa6964d8681a..f116d664b473 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -359,7 +359,7 @@ static int intel_idle(struct cpuidle_device *dev,
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
 
-	if (!need_resched()) {
+	if (!current_set_polling_and_test()) {
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
 		smp_mb();