cpuidle, OMAP4: Push RCU-idle into driver

Doing RCU-idle outside the driver, only to then temporarily enable it
again, some *four* times, before going idle is suboptimal.

Notably three times explicitly using RCU_NONIDLE() and once implicitly
through cpu_pm_*().
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Tony Lindgren <tony@atomide.com>
Tested-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Tony Lindgren <tony@atomide.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/20230112195540.007918454@infradead.org

arch/arm/mach-omap2/cpuidle44xx.c

@@ -105,7 +105,9 @@ static int omap_enter_idle_smp(struct cpuidle_device *dev,
 	}
 	raw_spin_unlock_irqrestore(&mpu_lock, flag);
 
+	ct_idle_enter();
 	omap4_enter_lowpower(dev->cpu, cx->cpu_state);
+	ct_idle_exit();
 
 	raw_spin_lock_irqsave(&mpu_lock, flag);
 	if (cx->mpu_state_vote == num_online_cpus())
@@ -151,10 +153,10 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 				 (cx->mpu_logic_state == PWRDM_POWER_OFF);
 
 	/* Enter broadcast mode for periodic timers */
-	RCU_NONIDLE(tick_broadcast_enable());
+	tick_broadcast_enable();
 
 	/* Enter broadcast mode for one-shot timers */
-	RCU_NONIDLE(tick_broadcast_enter());
+	tick_broadcast_enter();
 
 	/*
 	 * Call idle CPU PM enter notifier chain so that
@@ -166,7 +168,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 
 	if (dev->cpu == 0) {
 		pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state);
-		RCU_NONIDLE(omap_set_pwrdm_state(mpu_pd, cx->mpu_state));
+		omap_set_pwrdm_state(mpu_pd, cx->mpu_state);
 
 		/*
 		 * Call idle CPU cluster PM enter notifier chain
@@ -178,14 +180,16 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 				index = 0;
 				cx = state_ptr + index;
 				pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state);
-				RCU_NONIDLE(omap_set_pwrdm_state(mpu_pd, cx->mpu_state));
+				omap_set_pwrdm_state(mpu_pd, cx->mpu_state);
 				mpuss_can_lose_context = 0;
 			}
 		}
 	}
 
+	ct_idle_enter();
 	omap4_enter_lowpower(dev->cpu, cx->cpu_state);
 	cpu_done[dev->cpu] = true;
+	ct_idle_exit();
 
 	/* Wakeup CPU1 only if it is not offlined */
 	if (dev->cpu == 0 && cpumask_test_cpu(1, cpu_online_mask)) {
@@ -194,9 +198,9 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 		    mpuss_can_lose_context)
 			gic_dist_disable();
 
-		RCU_NONIDLE(clkdm_deny_idle(cpu_clkdm[1]));
-		RCU_NONIDLE(omap_set_pwrdm_state(cpu_pd[1], PWRDM_POWER_ON));
-		RCU_NONIDLE(clkdm_allow_idle(cpu_clkdm[1]));
+		clkdm_deny_idle(cpu_clkdm[1]);
+		omap_set_pwrdm_state(cpu_pd[1], PWRDM_POWER_ON);
+		clkdm_allow_idle(cpu_clkdm[1]);
 
 		if (IS_PM44XX_ERRATUM(PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD) &&
 		    mpuss_can_lose_context) {
@@ -222,7 +226,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 	cpu_pm_exit();
 
 cpu_pm_out:
-	RCU_NONIDLE(tick_broadcast_exit());
+	tick_broadcast_exit();
 
 fail:
 	cpuidle_coupled_parallel_barrier(dev, &abort_barrier);
@@ -247,7 +251,8 @@ static struct cpuidle_driver omap4_idle_driver = {
 			/* C2 - CPU0 OFF + CPU1 OFF + MPU CSWR */
 			.exit_latency = 328 + 440,
 			.target_residency = 960,
-			.flags = CPUIDLE_FLAG_COUPLED,
+			.flags = CPUIDLE_FLAG_COUPLED |
+				 CPUIDLE_FLAG_RCU_IDLE,
 			.enter = omap_enter_idle_coupled,
 			.name = "C2",
 			.desc = "CPUx OFF, MPUSS CSWR",
@@ -256,7 +261,8 @@ static struct cpuidle_driver omap4_idle_driver = {
 			/* C3 - CPU0 OFF + CPU1 OFF + MPU OSWR */
 			.exit_latency = 460 + 518,
 			.target_residency = 1100,
-			.flags = CPUIDLE_FLAG_COUPLED,
+			.flags = CPUIDLE_FLAG_COUPLED |
+				 CPUIDLE_FLAG_RCU_IDLE,
 			.enter = omap_enter_idle_coupled,
 			.name = "C3",
 			.desc = "CPUx OFF, MPUSS OSWR",
@@ -282,7 +288,8 @@ static struct cpuidle_driver omap5_idle_driver = {
 			/* C2 - CPU0 RET + CPU1 RET + MPU CSWR */
 			.exit_latency = 48 + 60,
 			.target_residency = 100,
-			.flags = CPUIDLE_FLAG_TIMER_STOP,
+			.flags = CPUIDLE_FLAG_TIMER_STOP |
+				 CPUIDLE_FLAG_RCU_IDLE,
 			.enter = omap_enter_idle_smp,
 			.name = "C2",
 			.desc = "CPUx CSWR, MPUSS CSWR",