Merge branch 'IKS-rebase' into integration-linaro-vexpresstracking-integration-linaro-vexpress-ll-20130520.1

10 files changed, 635 insertions, 93 deletions

diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index 90942150e6ca..6df8aa550c57 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -173,7 +173,8 @@ static u32 cci_pmu_get_max_counters(void)
 	return n_cnts + 1;
 }
 
-static struct pmu_hw_events *cci_pmu_get_hw_events(void)
+static struct pmu_hw_events *cci_pmu_get_hw_events(
+	struct arm_pmu *__always_unused pmu)
 {
 	return &cci_hw_events;
 }
@@ -250,7 +251,7 @@ static int cci_pmu_request_irq(struct arm_pmu *cci_pmu, irq_handler_t handler)
 static irqreturn_t cci_pmu_handle_irq(int irq_num, void *dev)
 {
 	struct arm_pmu *cci_pmu = (struct arm_pmu *)dev;
-	struct pmu_hw_events *events = cci_pmu->get_hw_events();
+	struct pmu_hw_events *events = cci_pmu->get_hw_events(cci_pmu);
 	struct perf_sample_data data;
 	struct pt_regs *regs;
 	int idx;
@@ -302,7 +303,7 @@ static void cci_pmu_enable_event(struct perf_event *event)
 {
 	unsigned long flags;
 	struct arm_pmu *cci_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = cci_pmu->get_hw_events();
+	struct pmu_hw_events *events = cci_pmu->get_hw_events(cci_pmu);
 	struct hw_perf_event *hw_counter = &event->hw;
 	int idx = hw_counter->idx;
 
@@ -326,7 +327,7 @@ static void cci_pmu_disable_event(struct perf_event *event)
 {
 	unsigned long flags;
 	struct arm_pmu *cci_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = cci_pmu->get_hw_events();
+	struct pmu_hw_events *events = cci_pmu->get_hw_events(cci_pmu);
 	struct hw_perf_event *hw_counter = &event->hw;
 	int idx = hw_counter->idx;
 
@@ -346,7 +347,7 @@ static void cci_pmu_start(struct arm_pmu *cci_pmu)
 {
 	u32 val;
 	unsigned long flags;
-	struct pmu_hw_events *events = cci_pmu->get_hw_events();
+	struct pmu_hw_events *events = cci_pmu->get_hw_events(cci_pmu);
 
 	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
@@ -361,7 +362,7 @@ static void cci_pmu_stop(struct arm_pmu *cci_pmu)
 {
 	u32 val;
 	unsigned long flags;
-	struct pmu_hw_events *events = cci_pmu->get_hw_events();
+	struct pmu_hw_events *events = cci_pmu->get_hw_events(cci_pmu);
 
 	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
diff --git a/drivers/clk/versatile/clk-vexpress-spc.c b/drivers/clk/versatile/clk-vexpress-spc.c
index b701ae41475c..a83e1873e930 100644
--- a/drivers/clk/versatile/clk-vexpress-spc.c
+++ b/drivers/clk/versatile/clk-vexpress-spc.c
@@ -102,7 +102,7 @@ struct clk *vexpress_clk_register_spc(const char *name, int cluster_id)
 #if defined(CONFIG_OF)
 void __init vexpress_clk_of_register_spc(void)
 {
-	char name[14] = "cpu-cluster.";
+	char name[14] = "cpu-cluster.X";
 	struct device_node *node = NULL;
 	struct clk *clk;
 	const u32 *val;
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index 5d7f53fcd6f5..7c2be81f7dcb 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -24,27 +24,140 @@
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
 #include <linux/export.h>
+#include <linux/mutex.h>
 #include <linux/of_platform.h>
 #include <linux/opp.h>
 #include <linux/slab.h>
 #include <linux/topology.h>
 #include <linux/types.h>
+#include <asm/bL_switcher.h>
 
 #include "arm_big_little.h"
 
-/* Currently we support only two clusters */
-#define MAX_CLUSTERS	2
+#ifdef CONFIG_BL_SWITCHER
+bool bL_switching_enabled;
+#endif
+
+#define ACTUAL_FREQ(cluster, freq)	((cluster == A7_CLUSTER) ? freq << 1 : freq)
+#define VIRT_FREQ(cluster, freq)	((cluster == A7_CLUSTER) ? freq >> 1 : freq)
 
 static struct cpufreq_arm_bL_ops *arm_bL_ops;
 static struct clk *clk[MAX_CLUSTERS];
-static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS];
-static atomic_t cluster_usage[MAX_CLUSTERS] = {ATOMIC_INIT(0), ATOMIC_INIT(0)};
+static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS + 1];
+static atomic_t cluster_usage[MAX_CLUSTERS + 1] = {ATOMIC_INIT(0),
+	ATOMIC_INIT(0)};
+
+static unsigned int clk_big_min;	/* (Big) clock frequencies */
+static unsigned int clk_little_max;	/* Maximum clock frequency (Little) */
+
+static DEFINE_PER_CPU(unsigned int, physical_cluster);
+static DEFINE_PER_CPU(unsigned int, cpu_last_req_freq);
+
+static struct mutex cluster_lock[MAX_CLUSTERS];
+
+static unsigned int find_cluster_maxfreq(int cluster)
+{
+	int j;
+	u32 max_freq = 0, cpu_freq;
+
+	for_each_online_cpu(j) {
+		cpu_freq = per_cpu(cpu_last_req_freq, j);
+
+		if ((cluster == per_cpu(physical_cluster, j)) &&
+				(max_freq < cpu_freq))
+			max_freq = cpu_freq;
+	}
+
+	pr_debug("%s: cluster: %d, max freq: %d\n", __func__, cluster,
+			max_freq);
+
+	return max_freq;
+}
+
+static unsigned int clk_get_cpu_rate(unsigned int cpu)
+{
+	u32 cur_cluster = per_cpu(physical_cluster, cpu);
+	u32 rate = clk_get_rate(clk[cur_cluster]) / 1000;
+
+	/* For switcher we use virtual A15 clock rates */
+	if (is_bL_switching_enabled())
+		rate = VIRT_FREQ(cur_cluster, rate);
+
+	pr_debug("%s: cpu: %d, cluster: %d, freq: %u\n", __func__, cpu,
+			cur_cluster, rate);
+
+	return rate;
+}
+
+static unsigned int bL_cpufreq_get_rate(unsigned int cpu)
+{
+	pr_debug("%s: freq: %d\n", __func__, per_cpu(cpu_last_req_freq, cpu));
+
+	return per_cpu(cpu_last_req_freq, cpu);
+}
 
-static unsigned int bL_cpufreq_get(unsigned int cpu)
+static unsigned int
+bL_cpufreq_set_rate(u32 cpu, u32 old_cluster, u32 new_cluster, u32 rate)
 {
-	u32 cur_cluster = cpu_to_cluster(cpu);
+	u32 new_rate, prev_rate;
+	int ret;
+
+	mutex_lock(&cluster_lock[new_cluster]);
+
+	prev_rate = per_cpu(cpu_last_req_freq, cpu);
+	per_cpu(cpu_last_req_freq, cpu) = rate;
+	per_cpu(physical_cluster, cpu) = new_cluster;
+
+	if (is_bL_switching_enabled()) {
+		new_rate = find_cluster_maxfreq(new_cluster);
+		new_rate = ACTUAL_FREQ(new_cluster, new_rate);
+	} else {
+		new_rate = rate;
+	}
+
+	pr_debug("%s: cpu: %d, old cluster: %d, new cluster: %d, freq: %d\n",
+			__func__, cpu, old_cluster, new_cluster, new_rate);
+
+	ret = clk_set_rate(clk[new_cluster], new_rate * 1000);
+	if (WARN_ON(ret)) {
+		pr_err("clk_set_rate failed: %d, new cluster: %d\n", ret,
+				new_cluster);
+		per_cpu(cpu_last_req_freq, cpu) = prev_rate;
+		per_cpu(physical_cluster, cpu) = old_cluster;
+
+		mutex_unlock(&cluster_lock[new_cluster]);
+
+		return ret;
+	}
 
-	return clk_get_rate(clk[cur_cluster]) / 1000;
+	mutex_unlock(&cluster_lock[new_cluster]);
+
+	/* Recalc freq for old cluster when switching clusters */
+	if (old_cluster != new_cluster) {
+		pr_debug("%s: cpu: %d, old cluster: %d, new cluster: %d\n",
+				__func__, cpu, old_cluster, new_cluster);
+
+		/* Switch cluster */
+		bL_switch_request(cpu, new_cluster);
+
+		mutex_lock(&cluster_lock[old_cluster]);
+
+		/* Set freq of old cluster if there are cpus left on it */
+		new_rate = find_cluster_maxfreq(old_cluster);
+		new_rate = ACTUAL_FREQ(old_cluster, new_rate);
+
+		if (new_rate) {
+			pr_debug("%s: Updating rate of old cluster: %d, to freq: %d\n",
+					__func__, old_cluster, new_rate);
+
+			if (clk_set_rate(clk[old_cluster], new_rate * 1000))
+				pr_err("%s: clk_set_rate failed: %d, old cluster: %d\n",
+						__func__, ret, old_cluster);
+		}
+		mutex_unlock(&cluster_lock[old_cluster]);
+	}
+
+	return 0;
 }
 
 /* Validate policy frequency range */
@@ -60,12 +173,14 @@ static int bL_cpufreq_set_target(struct cpufreq_policy *policy,
 		unsigned int target_freq, unsigned int relation)
 {
 	struct cpufreq_freqs freqs;
-	u32 cpu = policy->cpu, freq_tab_idx, cur_cluster;
+	u32 cpu = policy->cpu, freq_tab_idx, cur_cluster, new_cluster,
+	    actual_cluster;
 	int ret = 0;
 
-	cur_cluster = cpu_to_cluster(policy->cpu);
+	cur_cluster = cpu_to_cluster(cpu);
+	new_cluster = actual_cluster = per_cpu(physical_cluster, cpu);
 
-	freqs.old = bL_cpufreq_get(policy->cpu);
+	freqs.old = bL_cpufreq_get_rate(cpu);
 
 	/* Determine valid target frequency using freq_table */
 	cpufreq_frequency_table_target(policy, freq_table[cur_cluster],
@@ -79,13 +194,21 @@ static int bL_cpufreq_set_target(struct cpufreq_policy *policy,
 	if (freqs.old == freqs.new)
 		return 0;
 
+	if (is_bL_switching_enabled()) {
+		if ((actual_cluster == A15_CLUSTER) &&
+				(freqs.new < clk_big_min)) {
+			new_cluster = A7_CLUSTER;
+		} else if ((actual_cluster == A7_CLUSTER) &&
+				(freqs.new > clk_little_max)) {
+			new_cluster = A15_CLUSTER;
+		}
+	}
+
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
-	ret = clk_set_rate(clk[cur_cluster], freqs.new * 1000);
-	if (ret) {
-		pr_err("clk_set_rate failed: %d\n", ret);
+	ret = bL_cpufreq_set_rate(cpu, actual_cluster, new_cluster, freqs.new);
+	if (ret)
 		return ret;
-	}
 
 	policy->cur = freqs.new;
 
@@ -94,7 +217,73 @@ static int bL_cpufreq_set_target(struct cpufreq_policy *policy,
 	return ret;
 }
 
-static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
+static inline u32 get_table_count(struct cpufreq_frequency_table *table)
+{
+	int count;
+
+	for (count = 0; table[count].frequency != CPUFREQ_TABLE_END; count++)
+		;
+
+	return count;
+}
+
+/* get the minimum frequency in the cpufreq_frequency_table */
+static inline u32 get_table_min(struct cpufreq_frequency_table *table)
+{
+	int i;
+	uint32_t min_freq = ~0;
+	for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++)
+		if (table[i].frequency < min_freq)
+			min_freq = table[i].frequency;
+	return min_freq;
+}
+
+/* get the maximum frequency in the cpufreq_frequency_table */
+static inline u32 get_table_max(struct cpufreq_frequency_table *table)
+{
+	int i;
+	uint32_t max_freq = 0;
+	for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++)
+		if (table[i].frequency > max_freq)
+			max_freq = table[i].frequency;
+	return max_freq;
+}
+
+static int merge_cluster_tables(void)
+{
+	int i, j, k = 0, count = 1;
+	struct cpufreq_frequency_table *table;
+
+	for (i = 0; i < MAX_CLUSTERS; i++)
+		count += get_table_count(freq_table[i]);
+
+	table = kzalloc(sizeof(*table) * count, GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
+
+	freq_table[MAX_CLUSTERS] = table;
+
+	/* Add in reverse order to get freqs in increasing order */
+	for (i = MAX_CLUSTERS - 1; i >= 0; i--) {
+		for (j = 0; freq_table[i][j].frequency != CPUFREQ_TABLE_END;
+				j++) {
+			table[k].frequency = VIRT_FREQ(i,
+					freq_table[i][j].frequency);
+			pr_debug("%s: index: %d, freq: %d\n", __func__, k,
+					table[k].frequency);
+			k++;
+		}
+	}
+
+	table[k].index = k;
+	table[k].frequency = CPUFREQ_TABLE_END;
+
+	pr_debug("%s: End, table: %p, count: %d\n", __func__, table, k);
+
+	return 0;
+}
+
+static void _put_cluster_clk_and_freq_table(struct device *cpu_dev)
 {
 	u32 cluster = cpu_to_cluster(cpu_dev->id);
 
@@ -105,10 +294,35 @@ static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
 	}
 }
 
-static int get_cluster_clk_and_freq_table(struct device *cpu_dev)
+static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
 {
 	u32 cluster = cpu_to_cluster(cpu_dev->id);
-	char name[14] = "cpu-cluster.";
+	int i;
+
+	if (cluster < MAX_CLUSTERS)
+		return _put_cluster_clk_and_freq_table(cpu_dev);
+
+	if (atomic_dec_return(&cluster_usage[MAX_CLUSTERS]))
+		return;
+
+	for (i = 0; i < MAX_CLUSTERS; i++) {
+		struct device *cdev = get_cpu_device(i);
+		if (!cdev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__, i);
+			return;
+		}
+
+		_put_cluster_clk_and_freq_table(cdev);
+	}
+
+	/* free virtual table */
+	kfree(freq_table[MAX_CLUSTERS]);
+}
+
+static int _get_cluster_clk_and_freq_table(struct device *cpu_dev)
+{
+	u32 cluster = cpu_to_cluster(cpu_dev->id);
+	char name[14] = "cpu-cluster.X";
 	int ret;
 
 	if (atomic_inc_return(&cluster_usage[cluster]) != 1)
@@ -149,6 +363,62 @@ atomic_dec:
 	return ret;
 }
 
+static int get_cluster_clk_and_freq_table(struct device *cpu_dev)
+{
+	u32 cluster = cpu_to_cluster(cpu_dev->id);
+	int i, ret;
+
+	if (cluster < MAX_CLUSTERS)
+		return _get_cluster_clk_and_freq_table(cpu_dev);
+
+	if (atomic_inc_return(&cluster_usage[MAX_CLUSTERS]) != 1)
+		return 0;
+
+	/*
+	 * Get data for all clusters and fill virtual cluster with a merge of
+	 * both
+	 */
+	for (i = 0; i < MAX_CLUSTERS; i++) {
+		struct device *cdev = get_cpu_device(i);
+		if (!cdev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__, i);
+			return -ENODEV;
+		}
+
+		ret = _get_cluster_clk_and_freq_table(cdev);
+		if (ret)
+			goto put_clusters;
+	}
+
+	ret = merge_cluster_tables();
+	if (ret)
+		goto put_clusters;
+
+	/* Assuming 2 cluster, set clk_big_min and clk_little_max */
+	clk_big_min = get_table_min(freq_table[0]);
+	clk_little_max = VIRT_FREQ(1, get_table_max(freq_table[1]));
+
+	pr_debug("%s: cluster: %d, clk_big_min: %d, clk_little_max: %d\n",
+			__func__, cluster, clk_big_min, clk_little_max);
+
+	return 0;
+
+put_clusters:
+	while (i--) {
+		struct device *cdev = get_cpu_device(i);
+		if (!cdev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__, i);
+			return -ENODEV;
+		}
+
+		_put_cluster_clk_and_freq_table(cdev);
+	}
+
+	atomic_dec(&cluster_usage[MAX_CLUSTERS]);
+
+	return ret;
+}
+
 /* Per-CPU initialization */
 static int bL_cpufreq_init(struct cpufreq_policy *policy)
 {
@@ -177,37 +447,28 @@ static int bL_cpufreq_init(struct cpufreq_policy *policy)
 
 	cpufreq_frequency_table_get_attr(freq_table[cur_cluster], policy->cpu);
 
+	if (cur_cluster < MAX_CLUSTERS) {
+		cpumask_copy(policy->cpus, topology_core_cpumask(policy->cpu));
+
+		per_cpu(physical_cluster, policy->cpu) = cur_cluster;
+	} else {
+		/* Assumption: during init, we are always running on A15 */
+		per_cpu(physical_cluster, policy->cpu) = A15_CLUSTER;
+	}
+
 	if (arm_bL_ops->get_transition_latency)
 		policy->cpuinfo.transition_latency =
 			arm_bL_ops->get_transition_latency(cpu_dev);
 	else
 		policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 
-	policy->cur = bL_cpufreq_get(policy->cpu);
-
-	cpumask_copy(policy->cpus, topology_core_cpumask(policy->cpu));
+	policy->cur = clk_get_cpu_rate(policy->cpu);
+	per_cpu(cpu_last_req_freq, policy->cpu) = policy->cur;
 
 	dev_info(cpu_dev, "%s: CPU %d initialized\n", __func__, policy->cpu);
 	return 0;
 }
 
-static int bL_cpufreq_exit(struct cpufreq_policy *policy)
-{
-	struct device *cpu_dev;
-
-	cpu_dev = get_cpu_device(policy->cpu);
-	if (!cpu_dev) {
-		pr_err("%s: failed to get cpu%d device\n", __func__,
-				policy->cpu);
-		return -ENODEV;
-	}
-
-	put_cluster_clk_and_freq_table(cpu_dev);
-	dev_dbg(cpu_dev, "%s: Exited, cpu: %d\n", __func__, policy->cpu);
-
-	return 0;
-}
-
 /* Export freq_table to sysfs */
 static struct freq_attr *bL_cpufreq_attr[] = {
 	&cpufreq_freq_attr_scaling_available_freqs,
@@ -219,16 +480,47 @@ static struct cpufreq_driver bL_cpufreq_driver = {
 	.flags			= CPUFREQ_STICKY,
 	.verify			= bL_cpufreq_verify_policy,
 	.target			= bL_cpufreq_set_target,
-	.get			= bL_cpufreq_get,
+	.get			= bL_cpufreq_get_rate,
 	.init			= bL_cpufreq_init,
-	.exit			= bL_cpufreq_exit,
 	.have_governor_per_policy = true,
 	.attr			= bL_cpufreq_attr,
 };
 
+static int bL_cpufreq_switcher_notifier(struct notifier_block *nfb,
+					unsigned long action, void *_arg)
+{
+	pr_debug("%s: action: %ld\n", __func__, action);
+
+	switch (action) {
+	case BL_NOTIFY_PRE_ENABLE:
+	case BL_NOTIFY_PRE_DISABLE:
+		cpufreq_unregister_driver(&bL_cpufreq_driver);
+		break;
+
+	case BL_NOTIFY_POST_ENABLE:
+		set_switching_enabled(true);
+		cpufreq_register_driver(&bL_cpufreq_driver);
+		break;
+
+	case BL_NOTIFY_POST_DISABLE:
+		set_switching_enabled(false);
+		cpufreq_register_driver(&bL_cpufreq_driver);
+		break;
+
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block bL_switcher_notifier = {
+	.notifier_call = bL_cpufreq_switcher_notifier,
+};
+
 int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 {
-	int ret;
+	int ret, i;
 
 	if (arm_bL_ops) {
 		pr_debug("%s: Already registered: %s, exiting\n", __func__,
@@ -243,16 +535,29 @@ int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 
 	arm_bL_ops = ops;
 
+	ret = bL_switcher_get_enabled();
+	set_switching_enabled(ret);
+
+	for (i = 0; i < MAX_CLUSTERS; i++)
+		mutex_init(&cluster_lock[i]);
+
 	ret = cpufreq_register_driver(&bL_cpufreq_driver);
 	if (ret) {
 		pr_info("%s: Failed registering platform driver: %s, err: %d\n",
 				__func__, ops->name, ret);
 		arm_bL_ops = NULL;
 	} else {
-		pr_info("%s: Registered platform driver: %s\n", __func__,
-				ops->name);
+		ret = bL_switcher_register_notifier(&bL_switcher_notifier);
+		if (ret) {
+			cpufreq_unregister_driver(&bL_cpufreq_driver);
+			arm_bL_ops = NULL;
+		} else {
+			pr_info("%s: Registered platform driver: %s\n",
+					__func__, ops->name);
+		}
 	}
 
+	bL_switcher_put_enabled();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(bL_cpufreq_register);
@@ -265,9 +570,31 @@ void bL_cpufreq_unregister(struct cpufreq_arm_bL_ops *ops)
 		return;
 	}
 
+	bL_switcher_get_enabled();
+	bL_switcher_unregister_notifier(&bL_switcher_notifier);
 	cpufreq_unregister_driver(&bL_cpufreq_driver);
+	bL_switcher_put_enabled();
 	pr_info("%s: Un-registered platform driver: %s\n", __func__,
 			arm_bL_ops->name);
+
+	/* For saving table get/put on every cpu in/out */
+	if (is_bL_switching_enabled()) {
+		put_cluster_clk_and_freq_table(get_cpu_device(0));
+	} else {
+		int i;
+
+		for (i = 0; i < MAX_CLUSTERS; i++) {
+			struct device *cdev = get_cpu_device(i);
+			if (!cdev) {
+				pr_err("%s: failed to get cpu%d device\n",
+						__func__, i);
+				return;
+			}
+
+			put_cluster_clk_and_freq_table(cdev);
+		}
+	}
+
 	arm_bL_ops = NULL;
 }
 EXPORT_SYMBOL_GPL(bL_cpufreq_unregister);
diff --git a/drivers/cpufreq/arm_big_little.h b/drivers/cpufreq/arm_big_little.h
index 79b2ce17884d..4f5a03d3aef6 100644
--- a/drivers/cpufreq/arm_big_little.h
+++ b/drivers/cpufreq/arm_big_little.h
@@ -23,6 +23,20 @@
 #include <linux/device.h>
 #include <linux/types.h>
 
+/* Currently we support only two clusters */
+#define A15_CLUSTER	0
+#define A7_CLUSTER	1
+#define MAX_CLUSTERS	2
+
+#ifdef CONFIG_BL_SWITCHER
+extern bool bL_switching_enabled;
+#define is_bL_switching_enabled()		bL_switching_enabled
+#define set_switching_enabled(x) 		(bL_switching_enabled = (x))
+#else
+#define is_bL_switching_enabled()		false
+#define set_switching_enabled(x) 		do { } while (0)
+#endif
+
 struct cpufreq_arm_bL_ops {
 	char name[CPUFREQ_NAME_LEN];
 	int (*get_transition_latency)(struct device *cpu_dev);
@@ -36,7 +50,8 @@ struct cpufreq_arm_bL_ops {
 
 static inline int cpu_to_cluster(int cpu)
 {
-	return topology_physical_package_id(cpu);
+	return is_bL_switching_enabled() ? MAX_CLUSTERS:
+		topology_physical_package_id(cpu);
 }
 
 int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops);
diff --git a/drivers/cpufreq/arm_big_little_dt.c b/drivers/cpufreq/arm_big_little_dt.c
index 173ed059d95f..27e2f45ccdd5 100644
--- a/drivers/cpufreq/arm_big_little_dt.c
+++ b/drivers/cpufreq/arm_big_little_dt.c
@@ -19,6 +19,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/device.h>
 #include <linux/export.h>
@@ -29,60 +30,63 @@
 #include <linux/types.h>
 #include "arm_big_little.h"
 
-static int dt_init_opp_table(struct device *cpu_dev)
+/* get cpu node with valid operating-points */
+static struct device_node *get_cpu_node_with_valid_op(int cpu)
 {
-	struct device_node *np, *parent;
-	int count = 0, ret;
+	struct device_node *np = NULL, *parent;
+	int count = 0;
 
 	parent = of_find_node_by_path("/cpus");
 	if (!parent) {
 		pr_err("failed to find OF /cpus\n");
-		return -ENOENT;
+		return NULL;
 	}
 
 	for_each_child_of_node(parent, np) {
-		if (count++ != cpu_dev->id)
+		if (count++ != cpu)
 			continue;
 		if (!of_get_property(np, "operating-points", NULL)) {
-			ret = -ENODATA;
-		} else {
-			cpu_dev->of_node = np;
-			ret = of_init_opp_table(cpu_dev);
+			of_node_put(np);
+			np = NULL;
 		}
-		of_node_put(np);
-		of_node_put(parent);
 
-		return ret;
+		break;
 	}
 
-	return -ENODEV;
+	of_node_put(parent);
+	return np;
+}
+
+static int dt_init_opp_table(struct device *cpu_dev)
+{
+	struct device_node *np;
+	int ret;
+
+	np = get_cpu_node_with_valid_op(cpu_dev->id);
+	if (!np)
+		return -ENODATA;
+
+	cpu_dev->of_node = np;
+	ret = of_init_opp_table(cpu_dev);
+	of_node_put(np);
+
+	return ret;
 }
 
 static int dt_get_transition_latency(struct device *cpu_dev)
 {
-	struct device_node *np, *parent;
+	struct device_node *np;
 	u32 transition_latency = CPUFREQ_ETERNAL;
-	int count = 0;
 
-	parent = of_find_node_by_path("/cpus");
-	if (!parent) {
-		pr_info("Failed to find OF /cpus. Use CPUFREQ_ETERNAL transition latency\n");
+	np = get_cpu_node_with_valid_op(cpu_dev->id);
+	if (!np)
 		return CPUFREQ_ETERNAL;
-	}
-
-	for_each_child_of_node(parent, np) {
-		if (count++ != cpu_dev->id)
-			continue;
-
-		of_property_read_u32(np, "clock-latency", &transition_latency);
-		of_node_put(np);
-		of_node_put(parent);
 
-		return transition_latency;
-	}
+	of_property_read_u32(np, "clock-latency", &transition_latency);
+	of_node_put(np);
 
-	pr_info("clock-latency isn't found, use CPUFREQ_ETERNAL transition latency\n");
-	return CPUFREQ_ETERNAL;
+	pr_debug("%s: clock-latency: %d\n", __func__, transition_latency);
+	return transition_latency;
 }
 
 static struct cpufreq_arm_bL_ops dt_bL_ops = {
@@ -93,6 +97,13 @@ static struct cpufreq_arm_bL_ops dt_bL_ops = {
 
 static int generic_bL_init(void)
 {
+	struct device_node *np;
+
+	np = get_cpu_node_with_valid_op(0);
+	if (!np)
+		return -ENODEV;
+
+	of_node_put(np);
 	return bL_cpufreq_register(&dt_bL_ops);
 }
 module_init(generic_bL_init);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 1b8a48eaf90f..b7acfd153bf9 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1075,14 +1075,14 @@ static int __cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif
 				__func__, cpu_dev->id, cpu);
 	}
 
+	if ((cpus == 1) && (cpufreq_driver->target))
+		__cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
+
 	pr_debug("%s: removing link, cpu: %d\n", __func__, cpu);
 	cpufreq_cpu_put(data);
 
 	/* If cpu is last user of policy, free policy */
 	if (cpus == 1) {
-		if (cpufreq_driver->target)
-			__cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
-
 		lock_policy_rwsem_read(cpu);
 		kobj = &data->kobj;
 		cmp = &data->kobj_unregister;
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 443442df113b..5af40ad82d23 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -255,6 +255,7 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		if (have_governor_per_policy()) {
 			WARN_ON(dbs_data);
 		} else if (dbs_data) {
+			dbs_data->usage_count++;
 			policy->governor_data = dbs_data;
 			return 0;
 		}
@@ -266,6 +267,7 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		}
 
 		dbs_data->cdata = cdata;
+		dbs_data->usage_count = 1;
 		rc = cdata->init(dbs_data);
 		if (rc) {
 			pr_err("%s: POLICY_INIT: init() failed\n", __func__);
@@ -294,7 +296,8 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		set_sampling_rate(dbs_data, max(dbs_data->min_sampling_rate,
 					latency * LATENCY_MULTIPLIER));
 
-		if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
+		if ((cdata->governor == GOV_CONSERVATIVE) &&
+				(!policy->governor->initialized)) {
 			struct cs_ops *cs_ops = dbs_data->cdata->gov_ops;
 
 			cpufreq_register_notifier(cs_ops->notifier_block,
@@ -306,12 +309,12 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 
 		return 0;
 	case CPUFREQ_GOV_POLICY_EXIT:
-		if ((policy->governor->initialized == 1) ||
-				have_governor_per_policy()) {
+		if (!--dbs_data->usage_count) {
 			sysfs_remove_group(get_governor_parent_kobj(policy),
 					get_sysfs_attr(dbs_data));
 
-			if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
+			if ((dbs_data->cdata->governor == GOV_CONSERVATIVE) &&
+				(policy->governor->initialized == 1)) {
 				struct cs_ops *cs_ops = dbs_data->cdata->gov_ops;
 
 				cpufreq_unregister_notifier(cs_ops->notifier_block,
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index 8ac33538d0bd..e16a96130cb3 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -211,6 +211,7 @@ struct common_dbs_data {
 struct dbs_data {
 	struct common_dbs_data *cdata;
 	unsigned int min_sampling_rate;
+	int usage_count;
 	void *tuners;
 
 	/* dbs_mutex protects dbs_enable in governor start/stop */
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 6c287ae7bbba..7dc9c4efbcfb 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -21,6 +21,7 @@
 #include <linux/spinlock.h>
 #include <linux/notifier.h>
 #include <asm/cputime.h>
+#include <asm/bL_switcher.h>
 
 static spinlock_t cpufreq_stats_lock;
 
@@ -403,7 +404,7 @@ static struct notifier_block notifier_trans_block = {
 	.notifier_call = cpufreq_stat_notifier_trans
 };
 
-static int __init cpufreq_stats_init(void)
+static int cpufreq_stats_setup(void)
 {
 	int ret;
 	unsigned int cpu;
@@ -431,7 +432,8 @@ static int __init cpufreq_stats_init(void)
 
 	return 0;
 }
-static void __exit cpufreq_stats_exit(void)
+
+static void cpufreq_stats_cleanup(void)
 {
 	unsigned int cpu;
 
@@ -446,6 +448,49 @@ static void __exit cpufreq_stats_exit(void)
 	}
 }
 
+static int cpufreq_stats_switcher_notifier(struct notifier_block *nfb,
+					unsigned long action, void *_arg)
+{
+	switch (action) {
+	case BL_NOTIFY_PRE_ENABLE:
+	case BL_NOTIFY_PRE_DISABLE:
+		cpufreq_stats_cleanup();
+		break;
+
+	case BL_NOTIFY_POST_ENABLE:
+	case BL_NOTIFY_POST_DISABLE:
+		cpufreq_stats_setup();
+		break;
+
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block switcher_notifier = {
+	.notifier_call = cpufreq_stats_switcher_notifier,
+};
+
+static int __init cpufreq_stats_init(void)
+{
+	int ret;
+	spin_lock_init(&cpufreq_stats_lock);
+
+	ret = cpufreq_stats_setup();
+	if (!ret)
+		bL_switcher_register_notifier(&switcher_notifier);
+
+	return ret;
+}
+
+static void __exit cpufreq_stats_exit(void)
+{
+	bL_switcher_unregister_notifier(&switcher_notifier);
+	cpufreq_stats_cleanup();
+}
+
 MODULE_AUTHOR("Zou Nan hai <nanhai.zou@intel.com>");
 MODULE_DESCRIPTION("'cpufreq_stats' - A driver to export cpufreq stats "
 				"through sysfs filesystem");
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index b66049fde51d..2fa2632be9fe 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -253,10 +253,9 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
+	raw_spin_lock(&irq_controller_lock);
 	mask = 0xff << shift;
 	bit = gic_cpu_map[cpu] << shift;
-
-	raw_spin_lock(&irq_controller_lock);
 	val = readl_relaxed(reg) & ~mask;
 	writel_relaxed(val | bit, reg);
 	raw_spin_unlock(&irq_controller_lock);
@@ -652,7 +651,9 @@ static void __init gic_pm_init(struct gic_chip_data *gic)
 void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 {
 	int cpu;
-	unsigned long map = 0;
+	unsigned long flags, map = 0;
+
+	raw_spin_lock_irqsave(&irq_controller_lock, flags);
 
 	/* Convert our logical CPU mask into a physical one. */
 	for_each_cpu(cpu, mask)
@@ -666,9 +667,145 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 
 	/* this always happens on GIC0 */
 	writel_relaxed(map << 16 | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
+
+	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
 }
 #endif
 
+#ifdef CONFIG_BL_SWITCHER
+/*
+ * gic_send_sgi - send a SGI directly to given CPU interface number
+ *
+ * cpu_id: the ID for the destination CPU interface
+ * irq: the IPI number to send a SGI for
+ */
+void gic_send_sgi(unsigned int cpu_id, unsigned int irq)
+{
+	BUG_ON(cpu_id >= NR_GIC_CPU_IF);
+	cpu_id = 1 << cpu_id;
+	/* this always happens on GIC0 */
+	writel_relaxed((cpu_id << 16) | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
+}
+
+/*
+ * gic_get_cpu_id - get the CPU interface ID for the specified CPU
+ *
+ * @cpu: the logical CPU number to get the GIC ID for.
+ *
+ * Return the CPU interface ID for the given logical CPU number,
+ * or -1 if the CPU number is too large or the interface ID is
+ * unknown (more than one bit set).
+ */
+int gic_get_cpu_id(unsigned int cpu)
+{
+	unsigned int cpu_bit;
+
+	if (cpu >= NR_GIC_CPU_IF)
+		return -1;
+	cpu_bit = gic_cpu_map[cpu];
+	if (cpu_bit & (cpu_bit - 1))
+	       return -1;
+	return __ffs(cpu_bit);
+}
+
+/*
+ * gic_migrate_target - migrate IRQs to another PU interface
+ *
+ * @new_cpu_id: the CPU target ID to migrate IRQs to
+ *
+ * Migrate all peripheral interrupts with a target matching the current CPU
+ * to the interface corresponding to @new_cpu_id.  The CPU interface mapping
+ * is also updated.  Targets to other CPU interfaces are unchanged.
+ * This must be called with IRQs locally disabled.
+ */
+void gic_migrate_target(unsigned int new_cpu_id)
+{
+	unsigned int old_cpu_id, gic_irqs, gic_nr = 0;
+	void __iomem *dist_base;
+	int i, ror_val, cpu = smp_processor_id();
+	u32 val, old_mask, active_mask;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	dist_base = gic_data_dist_base(&gic_data[gic_nr]);
+	if (!dist_base)
+		return;
+	gic_irqs = gic_data[gic_nr].gic_irqs;
+
+	old_cpu_id = __ffs(gic_cpu_map[cpu]);
+	old_mask = 0x01010101 << old_cpu_id;
+	ror_val = (old_cpu_id - new_cpu_id) & 31;
+
+	raw_spin_lock(&irq_controller_lock);
+
+	gic_cpu_map[cpu] = 1 << new_cpu_id;
+
+	for (i = 8; i < DIV_ROUND_UP(gic_irqs, 4); i++) {
+		val = readl_relaxed(dist_base + GIC_DIST_TARGET + i * 4);
+		active_mask = val & old_mask;
+		if (active_mask) {
+			val &= ~active_mask;
+			val |= ror32(active_mask, ror_val);
+			writel_relaxed(val, dist_base + GIC_DIST_TARGET + i * 4);
+		}
+	}
+
+	raw_spin_unlock(&irq_controller_lock);
+
+	/*
+	 * Now let's migrate and clear any potential SGIs that might be
+	 * pending for us (old_cpu_id).  Since GIC_DIST_SGI_PENDING_SET
+	 * is a banked register, we can only forward the SGI using
+	 * GIC_DIST_SOFTINT.  The original SGI source is lost but Linux
+	 * doesn't use that information anyway.
+	 *
+	 * For the same reason we do not adjust SGI source information
+	 * for previously sent SGIs by us to other CPUs either.
+	 */
+	for (i = 0; i < 16; i += 4) {
+		int j;
+		val = readl_relaxed(dist_base + GIC_DIST_SGI_PENDING_SET + i);
+		if (!val)
+			continue;
+		writel_relaxed(val, dist_base + GIC_DIST_SGI_PENDING_CLEAR + i);
+		for (j = i; j < i + 4; j++) {
+			if (val & 0xff)
+				writel_relaxed((1 << (new_cpu_id + 16)) | j,
+						dist_base + GIC_DIST_SOFTINT);
+			val >>= 8;
+		}
+	}
+}
+
+/*
+ * gic_get_sgir_physaddr - get the physical address for the SGI register
+ *
+ * REturn the physical address of the SGI register to be used
+ * by some early assembly code when the kernel is not yet available.
+ */
+static unsigned long gic_dist_physaddr;
+
+unsigned long gic_get_sgir_physaddr(void)
+{
+	if (!gic_dist_physaddr)
+		return 0;
+	return gic_dist_physaddr + GIC_DIST_SOFTINT;
+}
+
+void __init gic_init_physaddr(struct device_node *node)
+{
+	struct resource res;
+	if (of_address_to_resource(node, 0, &res) == 0) {
+		gic_dist_physaddr = res.start;
+		pr_info("GIC physical location is %#lx\n", gic_dist_physaddr);
+	}
+}
+
+#else
+#define gic_init_physaddr(node)  do { } while(0)
+#endif
+
 static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 				irq_hw_number_t hw)
 {
@@ -850,6 +987,8 @@ int __init gic_of_init(struct device_node *node, struct device_node *parent)
 		percpu_offset = 0;
 
 	gic_init_bases(gic_cnt, -1, dist_base, cpu_base, percpu_offset, node);
+	if (!gic_cnt)
+		gic_init_physaddr(node);
 
 	if (parent) {
 		irq = irq_of_parse_and_map(node, 0);