cpuidle: Add new macro to enter a retention idle state

If a CPU is entering a low power idle state where it doesn't lose any
context, then there is no need to call cpu_pm_enter()/cpu_pm_exit().
Add a new macro(CPU_PM_CPU_IDLE_ENTER_RETENTION) to be used by cpuidle
drivers when they are entering retention state. By not calling
cpu_pm_enter and cpu_pm_exit we reduce the latency involved in
entering and exiting the retention idle states.

CPU_PM_CPU_IDLE_ENTER_RETENTION assumes that no state is lost and
hence CPU PM notifiers will not be called. We may need a broader
change if we need to support partial retention states effeciently.

On ARM64 based Qualcomm Server Platform we measured below overhead for
for calling cpu_pm_enter and cpu_pm_exit for retention states.

workload: stress --hdd #CPUs --hdd-bytes 32M  -t 30
        Average overhead of cpu_pm_enter - 1.2us
        Average overhead of cpu_pm_exit  - 3.1us
Acked-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: NSudeep Holla <sudeep.holla@arm.com>
Signed-off-by: NPrashanth Prakash <pprakash@codeaurora.org>
Signed-off-by: NCatalin Marinas <catalin.marinas@arm.com>

include/linux/cpuidle.h

@@ -257,22 +257,30 @@ static inline int cpuidle_register_governor(struct cpuidle_governor *gov)
 {return 0;}
 #endif
 
-#define CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx)	\
-({								\
-	int __ret;						\
-								\
-	if (!idx) {						\
-		cpu_do_idle();					\
-		return idx;					\
-	}							\
-								\
-	__ret = cpu_pm_enter();					\
-	if (!__ret) {						\
-		__ret = low_level_idle_enter(idx);		\
-		cpu_pm_exit();					\
-	}							\
-								\
-	__ret ? -1 : idx;					\
+#define __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, is_retention) \
+({									\
+	int __ret = 0;							\
+									\
+	if (!idx) {							\
+		cpu_do_idle();						\
+		return idx;						\
+	}								\
+									\
+	if (!is_retention)						\
+		__ret =  cpu_pm_enter();				\
+	if (!__ret) {							\
+		__ret = low_level_idle_enter(idx);			\
+		if (!is_retention)					\
+			cpu_pm_exit();					\
+	}								\
+									\
+	__ret ? -1 : idx;						\
 })
 
+#define CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx)	\
+	__CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, 0)
+
+#define CPU_PM_CPU_IDLE_ENTER_RETENTION(low_level_idle_enter, idx)	\
+	__CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx, 1)
+
 #endif /* _LINUX_CPUIDLE_H */