Merge tag 'pm2' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc

Pull arm-soc cpuidle enablement for OMAP from Olof Johansson:
 "Coupled cpuidle was meant to merge for 3.5 through Len Brown's tree,
  but didn't go in because the pull request ended up rejected.  So it
  just got merged, and we got this staged branch that enables the
  coupled cpuidle code on OMAP.

  With a stable git workflow from the other maintainer we could have
  staged this earlier, but that wasn't the case so we have had to merge
  it late.

  The alternative is to hold it off until 3.7 but given that the code is
  well-isolated to OMAP and they are eager to see it go in, I didn't
  push back hard in that direction."

* tag 'pm2' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc:
  ARM: OMAP4: CPUidle: Open broadcast clock-event device.
  ARM: OMAP4: CPUidle: add synchronization for coupled idle states
  ARM: OMAP4: CPUidle: Use coupled cpuidle states to implement SMP cpuidle.
  ARM: OMAP: timer: allow gp timer clock-event to be used on both cpus
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index dd0fbf7..dd2db02 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -62,6 +62,7 @@
 	select PM_OPP if PM
 	select USB_ARCH_HAS_EHCI if USB_SUPPORT
 	select ARM_CPU_SUSPEND if PM
+	select ARCH_NEEDS_CPU_IDLE_COUPLED
 
 config SOC_OMAP5
 	bool "TI OMAP5"
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index 02d15bb..ee05e19 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -21,6 +21,7 @@
 #include "common.h"
 #include "pm.h"
 #include "prm.h"
+#include "clockdomain.h"
 
 /* Machine specific information */
 struct omap4_idle_statedata {
@@ -47,10 +48,14 @@
 	},
 };
 
-static struct powerdomain *mpu_pd, *cpu0_pd, *cpu1_pd;
+static struct powerdomain *mpu_pd, *cpu_pd[NR_CPUS];
+static struct clockdomain *cpu_clkdm[NR_CPUS];
+
+static atomic_t abort_barrier;
+static bool cpu_done[NR_CPUS];
 
 /**
- * omap4_enter_idle - Programs OMAP4 to enter the specified state
+ * omap4_enter_idle_coupled_[simple/coupled] - OMAP4 cpuidle entry functions
  * @dev: cpuidle device
  * @drv: cpuidle driver
  * @index: the index of state to be entered
@@ -59,60 +64,84 @@
  * specified low power state selected by the governor.
  * Returns the amount of time spent in the low power state.
  */
-static int omap4_enter_idle(struct cpuidle_device *dev,
+static int omap4_enter_idle_simple(struct cpuidle_device *dev,
+			struct cpuidle_driver *drv,
+			int index)
+{
+	local_fiq_disable();
+	omap_do_wfi();
+	local_fiq_enable();
+
+	return index;
+}
+
+static int omap4_enter_idle_coupled(struct cpuidle_device *dev,
 			struct cpuidle_driver *drv,
 			int index)
 {
 	struct omap4_idle_statedata *cx = &omap4_idle_data[index];
-	u32 cpu1_state;
 	int cpu_id = smp_processor_id();
 
 	local_fiq_disable();
 
 	/*
-	 * CPU0 has to stay ON (i.e in C1) until CPU1 is OFF state.
+	 * CPU0 has to wait and stay ON until CPU1 is OFF state.
 	 * This is necessary to honour hardware recommondation
 	 * of triggeing all the possible low power modes once CPU1 is
 	 * out of coherency and in OFF mode.
-	 * Update dev->last_state so that governor stats reflects right
-	 * data.
 	 */
-	cpu1_state = pwrdm_read_pwrst(cpu1_pd);
-	if (cpu1_state != PWRDM_POWER_OFF) {
-		index = drv->safe_state_index;
-		cx = &omap4_idle_data[index];
+	if (dev->cpu == 0 && cpumask_test_cpu(1, cpu_online_mask)) {
+		while (pwrdm_read_pwrst(cpu_pd[1]) != PWRDM_POWER_OFF) {
+			cpu_relax();
+
+			/*
+			 * CPU1 could have already entered & exited idle
+			 * without hitting off because of a wakeup
+			 * or a failed attempt to hit off mode.  Check for
+			 * that here, otherwise we could spin forever
+			 * waiting for CPU1 off.
+			 */
+			if (cpu_done[1])
+			    goto fail;
+
+		}
 	}
 
-	if (index > 0)
-		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu_id);
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu_id);
 
 	/*
 	 * Call idle CPU PM enter notifier chain so that
 	 * VFP and per CPU interrupt context is saved.
 	 */
-	if (cx->cpu_state == PWRDM_POWER_OFF)
-		cpu_pm_enter();
+	cpu_pm_enter();
 
-	pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state);
-	omap_set_pwrdm_state(mpu_pd, cx->mpu_state);
+	if (dev->cpu == 0) {
+		pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state);
+		omap_set_pwrdm_state(mpu_pd, cx->mpu_state);
 
-	/*
-	 * Call idle CPU cluster PM enter notifier chain
-	 * to save GIC and wakeupgen context.
-	 */
-	if ((cx->mpu_state == PWRDM_POWER_RET) &&
-		(cx->mpu_logic_state == PWRDM_POWER_OFF))
-			cpu_cluster_pm_enter();
+		/*
+		 * Call idle CPU cluster PM enter notifier chain
+		 * to save GIC and wakeupgen context.
+		 */
+		if ((cx->mpu_state == PWRDM_POWER_RET) &&
+			(cx->mpu_logic_state == PWRDM_POWER_OFF))
+				cpu_cluster_pm_enter();
+	}
 
 	omap4_enter_lowpower(dev->cpu, cx->cpu_state);
+	cpu_done[dev->cpu] = true;
+
+	/* Wakeup CPU1 only if it is not offlined */
+	if (dev->cpu == 0 && cpumask_test_cpu(1, cpu_online_mask)) {
+		clkdm_wakeup(cpu_clkdm[1]);
+		clkdm_allow_idle(cpu_clkdm[1]);
+	}
 
 	/*
 	 * Call idle CPU PM exit notifier chain to restore
-	 * VFP and per CPU IRQ context. Only CPU0 state is
-	 * considered since CPU1 is managed by CPU hotplug.
+	 * VFP and per CPU IRQ context.
 	 */
-	if (pwrdm_read_prev_pwrst(cpu0_pd) == PWRDM_POWER_OFF)
-		cpu_pm_exit();
+	cpu_pm_exit();
 
 	/*
 	 * Call idle CPU cluster PM exit notifier chain
@@ -121,8 +150,11 @@
 	if (omap4_mpuss_read_prev_context_state())
 		cpu_cluster_pm_exit();
 
-	if (index > 0)
-		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu_id);
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu_id);
+
+fail:
+	cpuidle_coupled_parallel_barrier(dev, &abort_barrier);
+	cpu_done[dev->cpu] = false;
 
 	local_fiq_enable();
 
@@ -141,7 +173,7 @@
 			.exit_latency = 2 + 2,
 			.target_residency = 5,
 			.flags = CPUIDLE_FLAG_TIME_VALID,
-			.enter = omap4_enter_idle,
+			.enter = omap4_enter_idle_simple,
 			.name = "C1",
 			.desc = "MPUSS ON"
 		},
@@ -149,8 +181,8 @@
                         /* C2 - CPU0 OFF + CPU1 OFF + MPU CSWR */
 			.exit_latency = 328 + 440,
 			.target_residency = 960,
-			.flags = CPUIDLE_FLAG_TIME_VALID,
-			.enter = omap4_enter_idle,
+			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED,
+			.enter = omap4_enter_idle_coupled,
 			.name = "C2",
 			.desc = "MPUSS CSWR",
 		},
@@ -158,8 +190,8 @@
 			/* C3 - CPU0 OFF + CPU1 OFF + MPU OSWR */
 			.exit_latency = 460 + 518,
 			.target_residency = 1100,
-			.flags = CPUIDLE_FLAG_TIME_VALID,
-			.enter = omap4_enter_idle,
+			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED,
+			.enter = omap4_enter_idle_coupled,
 			.name = "C3",
 			.desc = "MPUSS OSWR",
 		},
@@ -168,6 +200,16 @@
 	.safe_state_index = 0,
 };
 
+/*
+ * For each cpu, setup the broadcast timer because local timers
+ * stops for the states above C1.
+ */
+static void omap_setup_broadcast_timer(void *arg)
+{
+	int cpu = smp_processor_id();
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ON, &cpu);
+}
+
 /**
  * omap4_idle_init - Init routine for OMAP4 idle
  *
@@ -180,19 +222,30 @@
 	unsigned int cpu_id = 0;
 
 	mpu_pd = pwrdm_lookup("mpu_pwrdm");
-	cpu0_pd = pwrdm_lookup("cpu0_pwrdm");
-	cpu1_pd = pwrdm_lookup("cpu1_pwrdm");
-	if ((!mpu_pd) || (!cpu0_pd) || (!cpu1_pd))
+	cpu_pd[0] = pwrdm_lookup("cpu0_pwrdm");
+	cpu_pd[1] = pwrdm_lookup("cpu1_pwrdm");
+	if ((!mpu_pd) || (!cpu_pd[0]) || (!cpu_pd[1]))
 		return -ENODEV;
 
-	dev = &per_cpu(omap4_idle_dev, cpu_id);
-	dev->cpu = cpu_id;
+	cpu_clkdm[0] = clkdm_lookup("mpu0_clkdm");
+	cpu_clkdm[1] = clkdm_lookup("mpu1_clkdm");
+	if (!cpu_clkdm[0] || !cpu_clkdm[1])
+		return -ENODEV;
 
-	cpuidle_register_driver(&omap4_idle_driver);
+	/* Configure the broadcast timer on each cpu */
+	on_each_cpu(omap_setup_broadcast_timer, NULL, 1);
 
-	if (cpuidle_register_device(dev)) {
-		pr_err("%s: CPUidle register device failed\n", __func__);
-		return -EIO;
+	for_each_cpu(cpu_id, cpu_online_mask) {
+		dev = &per_cpu(omap4_idle_dev, cpu_id);
+		dev->cpu = cpu_id;
+		dev->coupled_cpus = *cpu_online_mask;
+
+		cpuidle_register_driver(&omap4_idle_driver);
+
+		if (cpuidle_register_device(dev)) {
+			pr_err("%s: CPUidle register failed\n", __func__);
+			return -EIO;
+		}
 	}
 
 	return 0;
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 13d20c8..2ff6d41 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -130,6 +130,7 @@
 	.name		= "gp_timer",
 	.features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
 	.shift		= 32,
+	.rating		= 300,
 	.set_next_event	= omap2_gp_timer_set_next_event,
 	.set_mode	= omap2_gp_timer_set_mode,
 };
@@ -223,7 +224,8 @@
 		clockevent_delta2ns(3, &clockevent_gpt);
 		/* Timer internal resynch latency. */
 
-	clockevent_gpt.cpumask = cpumask_of(0);
+	clockevent_gpt.cpumask = cpu_possible_mask;
+	clockevent_gpt.irq = omap_dm_timer_get_irq(&clkev);
 	clockevents_register_device(&clockevent_gpt);
 
 	pr_info("OMAP clockevent source: GPTIMER%d at %lu Hz\n",