diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 5859c8bc727c..2ee8a17d2b01 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -169,6 +169,11 @@ void __init arm_dt_init_cpu_maps(void)
 	}
 }
 
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+	return (phys_id & MPIDR_HWID_BITMASK) == cpu_logical_map(cpu);
+}
+
 /**
  * setup_machine_fdt - Machine setup when an dtb was passed to the kernel
  * @dt_phys: physical address of dt blob
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index c5a59546a256..85a87370f144 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -74,12 +74,8 @@ struct cpu_efficiency table_efficiency[] = {
 	{NULL, },
 };
 
-struct cpu_capacity {
-	unsigned long hwid;
-	unsigned long capacity;
-};
-
-struct cpu_capacity *cpu_capacity;
+unsigned long *__cpu_capacity;
+#define cpu_capacity(cpu)	__cpu_capacity[cpu]
 
 unsigned long middle_capacity = 1;
 
@@ -100,15 +96,19 @@ static void __init parse_dt_topology(void)
 	unsigned long capacity = 0;
 	int alloc_size, cpu = 0;
 
-	alloc_size = nr_cpu_ids * sizeof(struct cpu_capacity);
-	cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);
+	alloc_size = nr_cpu_ids * sizeof(*__cpu_capacity);
+	__cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);
 
-	while ((cn = of_find_node_by_type(cn, "cpu"))) {
-		const u32 *rate, *reg;
+	for_each_possible_cpu(cpu) {
+		const u32 *rate;
 		int len;
 
-		if (cpu >= num_possible_cpus())
-			break;
+		/* too early to use cpu->of_node */
+		cn = of_get_cpu_node(cpu, NULL);
+		if (!cn) {
+			pr_err("missing device node for CPU %d\n", cpu);
+			continue;
+		}
 
 		for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++)
 			if (of_device_is_compatible(cn, cpu_eff->compatible))
@@ -124,12 +124,6 @@ static void __init parse_dt_topology(void)
 			continue;
 		}
 
-		reg = of_get_property(cn, "reg", &len);
-		if (!reg || len != 4) {
-			pr_err("%s missing reg property\n", cn->full_name);
-			continue;
-		}
-
 		capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency;
 
 		/* Save min capacity of the system */
@@ -140,13 +134,9 @@ static void __init parse_dt_topology(void)
 		if (capacity > max_capacity)
 			max_capacity = capacity;
 
-		cpu_capacity[cpu].capacity = capacity;
-		cpu_capacity[cpu++].hwid = be32_to_cpup(reg);
+		cpu_capacity(cpu) = capacity;
 	}
 
-	if (cpu < num_possible_cpus())
-		cpu_capacity[cpu].hwid = (unsigned long)(-1);
-
 	/* If min and max capacities are equals, we bypass the update of the
 	 * cpu_scale because all CPUs have the same capacity. Otherwise, we
 	 * compute a middle_capacity factor that will ensure that the capacity
@@ -154,9 +144,7 @@ static void __init parse_dt_topology(void)
 	 * SCHED_POWER_SCALE, which is the default value, but with the
 	 * constraint explained near table_efficiency[].
 	 */
-	if (min_capacity == max_capacity)
-		cpu_capacity[0].hwid = (unsigned long)(-1);
-	else if (4*max_capacity < (3*(max_capacity + min_capacity)))
+	if (4*max_capacity < (3*(max_capacity + min_capacity)))
 		middle_capacity = (min_capacity + max_capacity)
 				>> (SCHED_POWER_SHIFT+1);
 	else
@@ -170,23 +158,12 @@ static void __init parse_dt_topology(void)
  * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
  * function returns directly for SMP system.
  */
-void update_cpu_power(unsigned int cpu, unsigned long hwid)
+void update_cpu_power(unsigned int cpu)
 {
-	unsigned int idx = 0;
-
-	/* look for the cpu's hwid in the cpu capacity table */
-	for (idx = 0; idx < num_possible_cpus(); idx++) {
-		if (cpu_capacity[idx].hwid == hwid)
-			break;
-
-		if (cpu_capacity[idx].hwid == -1)
-			return;
-	}
-
-	if (idx == num_possible_cpus())
+	if (!cpu_capacity(cpu))
 		return;
 
-	set_power_scale(cpu, cpu_capacity[idx].capacity / middle_capacity);
+	set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity);
 
 	printk(KERN_INFO "CPU%u: update cpu_power %lu\n",
 		cpu, arch_scale_freq_power(NULL, cpu));
@@ -194,7 +171,7 @@ void update_cpu_power(unsigned int cpu, unsigned long hwid)
 
 #else
 static inline void parse_dt_topology(void) {}
-static inline void update_cpu_power(unsigned int cpuid, unsigned int mpidr) {}
+static inline void update_cpu_power(unsigned int cpuid) {}
 #endif
 
  /*
@@ -281,7 +258,7 @@ void store_cpu_topology(unsigned int cpuid)
 
 	update_siblings_masks(cpuid);
 
-	update_cpu_power(cpuid, mpidr & MPIDR_HWID_BITMASK);
+	update_cpu_power(cpuid);
 
 	printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n",
 		cpuid, cpu_topology[cpuid].thread_id,
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index 7be13f8e69a0..a02f275a198d 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -254,13 +254,12 @@ static void __init imx6q_opp_init(struct device *cpu_dev)
 {
 	struct device_node *np;
 
-	np = of_find_node_by_path("/cpus/cpu@0");
+	np = of_node_get(cpu_dev->of_node);
 	if (!np) {
 		pr_warn("failed to find cpu0 node\n");
 		return;
 	}
 
-	cpu_dev->of_node = np;
 	if (of_init_opp_table(cpu_dev)) {
 		pr_warn("failed to init OPP table\n");
 		goto put_node;
diff --git a/arch/arm/mach-mvebu/platsmp.c b/arch/arm/mach-mvebu/platsmp.c
index ce81d3031405..594b63db4215 100644
--- a/arch/arm/mach-mvebu/platsmp.c
+++ b/arch/arm/mach-mvebu/platsmp.c
@@ -29,45 +29,40 @@
 #include "pmsu.h"
 #include "coherency.h"
 
+static struct clk *__init get_cpu_clk(int cpu)
+{
+	struct clk *cpu_clk;
+	struct device_node *np = of_get_cpu_node(cpu, NULL);
+
+	if (WARN(!np, "missing cpu node\n"))
+		return NULL;
+	cpu_clk = of_clk_get(np, 0);
+	if (WARN_ON(IS_ERR(cpu_clk)))
+		return NULL;
+	return cpu_clk;
+}
+
 void __init set_secondary_cpus_clock(void)
 {
-	int thiscpu;
+	int thiscpu, cpu;
 	unsigned long rate;
-	struct clk *cpu_clk = NULL;
-	struct device_node *np = NULL;
+	struct clk *cpu_clk;
 
 	thiscpu = smp_processor_id();
-	for_each_node_by_type(np, "cpu") {
-		int err;
-		int cpu;
-
-		err = of_property_read_u32(np, "reg", &cpu);
-		if (WARN_ON(err))
-			return;
-
-		if (cpu == thiscpu) {
-			cpu_clk = of_clk_get(np, 0);
-			break;
-		}
-	}
-	if (WARN_ON(IS_ERR(cpu_clk)))
+	cpu_clk = get_cpu_clk(thiscpu);
+	if (!cpu_clk)
 		return;
 	clk_prepare_enable(cpu_clk);
 	rate = clk_get_rate(cpu_clk);
 
 	/* set all the other CPU clk to the same rate than the boot CPU */
-	for_each_node_by_type(np, "cpu") {
-		int err;
-		int cpu;
-
-		err = of_property_read_u32(np, "reg", &cpu);
-		if (WARN_ON(err))
+	for_each_possible_cpu(cpu) {
+		if (cpu == thiscpu)
+			continue;
+		cpu_clk = get_cpu_clk(cpu);
+		if (!cpu_clk)
 			return;
-
-		if (cpu != thiscpu) {
-			cpu_clk = of_clk_get(np, 0);
-			clk_set_rate(cpu_clk, rate);
-		}
+		clk_set_rate(cpu_clk, rate);
 	}
 }
 
diff --git a/arch/microblaze/include/asm/prom.h b/arch/microblaze/include/asm/prom.h
index 20c5e8e5121b..9977816c5ad3 100644
--- a/arch/microblaze/include/asm/prom.h
+++ b/arch/microblaze/include/asm/prom.h
@@ -50,9 +50,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 
 extern void kdump_move_device_tree(void);
 
-/* CPU OF node matching */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
-
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 
diff --git a/arch/openrisc/include/asm/prom.h b/arch/openrisc/include/asm/prom.h
index bbb34e5343a2..eb59bfe23e85 100644
--- a/arch/openrisc/include/asm/prom.h
+++ b/arch/openrisc/include/asm/prom.h
@@ -44,9 +44,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 
 extern void kdump_move_device_tree(void);
 
-/* CPU OF node matching */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
-
 /* Get the MAC address */
 extern const void *of_get_mac_address(struct device_node *np);
 
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index bc2da154f68b..ac204e022922 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -43,9 +43,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 
 extern void kdump_move_device_tree(void);
 
-/* CPU OF node matching */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
-
 /* cache lookup */
 struct device_node *of_find_next_cache_node(struct device_node *np);
 
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index eb23ac92abb9..1c14cd4a5e05 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -865,49 +865,10 @@ static int __init prom_reconfig_setup(void)
 __initcall(prom_reconfig_setup);
 #endif
 
-/* Find the device node for a given logical cpu number, also returns the cpu
- * local thread number (index in ibm,interrupt-server#s) if relevant and
- * asked for (non NULL)
- */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 {
-	int hardid;
-	struct device_node *np;
-
-	hardid = get_hard_smp_processor_id(cpu);
-
-	for_each_node_by_type(np, "cpu") {
-		const u32 *intserv;
-		unsigned int plen, t;
-
-		/* Check for ibm,ppc-interrupt-server#s. If it doesn't exist
-		 * fallback to "reg" property and assume no threads
-		 */
-		intserv = of_get_property(np, "ibm,ppc-interrupt-server#s",
-				&plen);
-		if (intserv == NULL) {
-			const u32 *reg = of_get_property(np, "reg", NULL);
-			if (reg == NULL)
-				continue;
-			if (*reg == hardid) {
-				if (thread)
-					*thread = 0;
-				return np;
-			}
-		} else {
-			plen /= sizeof(u32);
-			for (t = 0; t < plen; t++) {
-				if (hardid == intserv[t]) {
-					if (thread)
-						*thread = t;
-					return np;
-				}
-			}
-		}
-	}
-	return NULL;
+	return (int)phys_id == get_hard_smp_processor_id(cpu);
 }
-EXPORT_SYMBOL(of_get_cpu_node);
 
 #if defined(CONFIG_DEBUG_FS) && defined(DEBUG)
 static struct debugfs_blob_wrapper flat_dt_blob;
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 4c358bc44c72..4cf071764be3 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/percpu.h>
 #include <linux/acpi.h>
+#include <linux/of.h>
 
 #include "base.h"
 
@@ -289,6 +290,7 @@ int register_cpu(struct cpu *cpu, int num)
 	cpu->dev.release = cpu_device_release;
 	cpu->dev.offline_disabled = !cpu->hotpluggable;
 	cpu->dev.offline = !cpu_online(num);
+	cpu->dev.of_node = of_get_cpu_node(num, NULL);
 #ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
 	cpu->dev.bus->uevent = arch_cpu_uevent;
 #endif
diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index 733288967d4d..200926699778 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -122,17 +122,8 @@ EXPORT_SYMBOL_GPL(cci_ace_get_port);
 
 static void __init cci_ace_init_ports(void)
 {
-	int port, ac, cpu;
-	u64 hwid;
-	const u32 *cell;
-	struct device_node *cpun, *cpus;
-
-	cpus = of_find_node_by_path("/cpus");
-	if (WARN(!cpus, "Missing cpus node, bailing out\n"))
-		return;
-
-	if (WARN_ON(of_property_read_u32(cpus, "#address-cells", &ac)))
-		ac = of_n_addr_cells(cpus);
+	int port, cpu;
+	struct device_node *cpun;
 
 	/*
 	 * Port index look-up speeds up the function disabling ports by CPU,
@@ -141,18 +132,13 @@ static void __init cci_ace_init_ports(void)
 	 * The stashed index array is initialized for all possible CPUs
 	 * at probe time.
 	 */
-	for_each_child_of_node(cpus, cpun) {
-		if (of_node_cmp(cpun->type, "cpu"))
-			continue;
-		cell = of_get_property(cpun, "reg", NULL);
-		if (WARN(!cell, "%s: missing reg property\n", cpun->full_name))
+	for_each_possible_cpu(cpu) {
+		/* too early to use cpu->of_node */
+		cpun = of_get_cpu_node(cpu, NULL);
+
+		if (WARN(!cpun, "Missing cpu device node\n"))
 			continue;
 
-		hwid = of_read_number(cell, ac);
-		cpu = get_logical_index(hwid & MPIDR_HWID_BITMASK);
-
-		if (cpu < 0 || !cpu_possible(cpu))
-			continue;
 		port = __cci_ace_get_port(cpun, ACE_PORT);
 		if (port < 0)
 			continue;
diff --git a/drivers/cpufreq/arm_big_little_dt.c b/drivers/cpufreq/arm_big_little_dt.c
index fd9e3ea6a480..480c0bd0468d 100644
--- a/drivers/cpufreq/arm_big_little_dt.c
+++ b/drivers/cpufreq/arm_big_little_dt.c
@@ -19,12 +19,11 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/device.h>
 #include <linux/export.h>
 #include <linux/module.h>
-#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/opp.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
@@ -34,27 +33,13 @@
 /* get cpu node with valid operating-points */
 static struct device_node *get_cpu_node_with_valid_op(int cpu)
 {
-	struct device_node *np = NULL, *parent;
-	int count = 0;
+	struct device_node *np = of_cpu_device_node_get(cpu);
 
-	parent = of_find_node_by_path("/cpus");
-	if (!parent) {
-		pr_err("failed to find OF /cpus\n");
-		return NULL;
+	if (!of_get_property(np, "operating-points", NULL)) {
+		of_node_put(np);
+		np = NULL;
 	}
 
-	for_each_child_of_node(parent, np) {
-		if (count++ != cpu)
-			continue;
-		if (!of_get_property(np, "operating-points", NULL)) {
-			of_node_put(np);
-			np = NULL;
-		}
-
-		break;
-	}
-
-	of_node_put(parent);
 	return np;
 }
 
@@ -63,11 +48,12 @@ 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;
+	np = of_node_get(cpu_dev->of_node);
+	if (!np) {
+		pr_err("failed to find cpu%d node\n", cpu_dev->id);
+		return -ENOENT;
+	}
 
-	cpu_dev->of_node = np;
 	ret = of_init_opp_table(cpu_dev);
 	of_node_put(np);
 
@@ -79,9 +65,11 @@ static int dt_get_transition_latency(struct device *cpu_dev)
 	struct device_node *np;
 	u32 transition_latency = CPUFREQ_ETERNAL;
 
-	np = get_cpu_node_with_valid_op(cpu_dev->id);
-	if (!np)
+	np = of_node_get(cpu_dev->of_node);
+	if (!np) {
+		pr_info("Failed to find cpu node. Use CPUFREQ_ETERNAL transition latency\n");
 		return CPUFREQ_ETERNAL;
+	}
 
 	of_property_read_u32(np, "clock-latency", &transition_latency);
 	of_node_put(np);
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index 09cd3a76fb2e..bad620e996e5 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -174,29 +174,17 @@ static struct cpufreq_driver cpu0_cpufreq_driver = {
 
 static int cpu0_cpufreq_probe(struct platform_device *pdev)
 {
-	struct device_node *np, *parent;
+	struct device_node *np;
 	int ret;
 
-	parent = of_find_node_by_path("/cpus");
-	if (!parent) {
-		pr_err("failed to find OF /cpus\n");
-		return -ENOENT;
-	}
-
-	for_each_child_of_node(parent, np) {
-		if (of_get_property(np, "operating-points", NULL))
-			break;
-	}
+	cpu_dev = &pdev->dev;
 
+	np = of_node_get(cpu_dev->of_node);
 	if (!np) {
 		pr_err("failed to find cpu0 node\n");
-		ret = -ENOENT;
-		goto out_put_parent;
+		return -ENOENT;
 	}
 
-	cpu_dev = &pdev->dev;
-	cpu_dev->of_node = np;
-
 	cpu_reg = devm_regulator_get(cpu_dev, "cpu0");
 	if (IS_ERR(cpu_reg)) {
 		/*
@@ -268,15 +256,12 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 	}
 
 	of_node_put(np);
-	of_node_put(parent);
 	return 0;
 
 out_free_table:
 	opp_free_cpufreq_table(cpu_dev, &freq_table);
 out_put_node:
 	of_node_put(np);
-out_put_parent:
-	of_node_put(parent);
 	return ret;
 }
 
diff --git a/drivers/cpufreq/highbank-cpufreq.c b/drivers/cpufreq/highbank-cpufreq.c
index b61b5a3fad64..794123fcf3e3 100644
--- a/drivers/cpufreq/highbank-cpufreq.c
+++ b/drivers/cpufreq/highbank-cpufreq.c
@@ -69,24 +69,18 @@ static int hb_cpufreq_driver_init(void)
 	if (!of_machine_is_compatible("calxeda,highbank"))
 		return -ENODEV;
 
-	for_each_child_of_node(of_find_node_by_path("/cpus"), np)
-		if (of_get_property(np, "operating-points", NULL))
-			break;
+	cpu_dev = get_cpu_device(0);
+	if (!cpu_dev) {
+		pr_err("failed to get highbank cpufreq device\n");
+		return -ENODEV;
+	}
 
+	np = of_node_get(cpu_dev->of_node);
 	if (!np) {
 		pr_err("failed to find highbank cpufreq node\n");
 		return -ENOENT;
 	}
 
-	cpu_dev = get_cpu_device(0);
-	if (!cpu_dev) {
-		pr_err("failed to get highbank cpufreq device\n");
-		ret = -ENODEV;
-		goto out_put_node;
-	}
-
-	cpu_dev->of_node = np;
-
 	cpu_clk = clk_get(cpu_dev, NULL);
 	if (IS_ERR(cpu_clk)) {
 		ret = PTR_ERR(cpu_clk);
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index e37cdaedbb5b..b16632bb5a56 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -221,14 +221,12 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 
 	cpu_dev = &pdev->dev;
 
-	np = of_find_node_by_path("/cpus/cpu@0");
+	np = of_node_get(cpu_dev->of_node);
 	if (!np) {
 		dev_err(cpu_dev, "failed to find cpu0 node\n");
 		return -ENOENT;
 	}
 
-	cpu_dev->of_node = np;
-
 	arm_clk = devm_clk_get(cpu_dev, "arm");
 	pll1_sys_clk = devm_clk_get(cpu_dev, "pll1_sys");
 	pll1_sw_clk = devm_clk_get(cpu_dev, "pll1_sw");
diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c
index 45e4d7fc261d..ba10658a9394 100644
--- a/drivers/cpufreq/kirkwood-cpufreq.c
+++ b/drivers/cpufreq/kirkwood-cpufreq.c
@@ -14,7 +14,7 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/cpufreq.h>
-#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <asm/proc-fns.h>
@@ -174,9 +174,11 @@ static int kirkwood_cpufreq_probe(struct platform_device *pdev)
 	if (IS_ERR(priv.base))
 		return PTR_ERR(priv.base);
 
-	np = of_find_node_by_path("/cpus/cpu@0");
-	if (!np)
+	np = of_cpu_device_node_get(0);
+	if (!np) {
+		dev_err(&pdev->dev, "failed to get cpu device node\n");
 		return -ENODEV;
+	}
 
 	priv.cpu_clk = of_clk_get_by_name(np, "cpu_clk");
 	if (IS_ERR(priv.cpu_clk)) {
diff --git a/drivers/cpufreq/maple-cpufreq.c b/drivers/cpufreq/maple-cpufreq.c
index 41c601f4631e..6168d77b296d 100644
--- a/drivers/cpufreq/maple-cpufreq.c
+++ b/drivers/cpufreq/maple-cpufreq.c
@@ -24,7 +24,7 @@
 #include <linux/completion.h>
 #include <linux/mutex.h>
 #include <linux/time.h>
-#include <linux/of.h>
+#include <linux/of_device.h>
 
 #define DBG(fmt...) pr_debug(fmt)
 
@@ -200,7 +200,6 @@ static struct cpufreq_driver maple_cpufreq_driver = {
 
 static int __init maple_cpufreq_init(void)
 {
-	struct device_node *cpus;
 	struct device_node *cpunode;
 	unsigned int psize;
 	unsigned long max_freq;
@@ -216,24 +215,11 @@ static int __init maple_cpufreq_init(void)
 	    !of_machine_is_compatible("Momentum,Apache"))
 		return 0;
 
-	cpus = of_find_node_by_path("/cpus");
-	if (cpus == NULL) {
-		DBG("No /cpus node !\n");
-		return -ENODEV;
-	}
-
 	/* Get first CPU node */
-	for (cpunode = NULL;
-	     (cpunode = of_get_next_child(cpus, cpunode)) != NULL;) {
-		const u32 *reg = of_get_property(cpunode, "reg", NULL);
-		if (reg == NULL || (*reg) != 0)
-			continue;
-		if (!strcmp(cpunode->type, "cpu"))
-			break;
-	}
+	cpunode = of_cpu_device_node_get(0);
 	if (cpunode == NULL) {
 		printk(KERN_ERR "cpufreq: Can't find any CPU 0 node\n");
-		goto bail_cpus;
+		goto bail_noprops;
 	}
 
 	/* Check 970FX for now */
@@ -289,14 +275,11 @@ static int __init maple_cpufreq_init(void)
 	rc = cpufreq_register_driver(&maple_cpufreq_driver);
 
 	of_node_put(cpunode);
-	of_node_put(cpus);
 
 	return rc;
 
 bail_noprops:
 	of_node_put(cpunode);
-bail_cpus:
-	of_node_put(cpus);
 
 	return rc;
 }
diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c
index 38cdc63c38da..a096cd3fa23d 100644
--- a/drivers/cpufreq/pmac32-cpufreq.c
+++ b/drivers/cpufreq/pmac32-cpufreq.c
@@ -25,6 +25,7 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/hardirq.h>
+#include <linux/of_device.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/irq.h>
@@ -648,8 +649,8 @@ static int __init pmac_cpufreq_setup(void)
 	if (strstr(cmd_line, "nocpufreq"))
 		return 0;
 
-	/* Assume only one CPU */
-	cpunode = of_find_node_by_type(NULL, "cpu");
+	/* Get first CPU node */
+	cpunode = of_cpu_device_node_get(0);
 	if (!cpunode)
 		goto out;
 
diff --git a/drivers/cpufreq/pmac64-cpufreq.c b/drivers/cpufreq/pmac64-cpufreq.c
index b6850d97f0d5..3a51ad7e47c8 100644
--- a/drivers/cpufreq/pmac64-cpufreq.c
+++ b/drivers/cpufreq/pmac64-cpufreq.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/completion.h>
 #include <linux/mutex.h>
+#include <linux/of_device.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/irq.h>
@@ -382,9 +383,8 @@ static struct cpufreq_driver g5_cpufreq_driver = {
 
 #ifdef CONFIG_PMAC_SMU
 
-static int __init g5_neo2_cpufreq_init(struct device_node *cpus)
+static int __init g5_neo2_cpufreq_init(struct device_node *cpunode)
 {
-	struct device_node *cpunode;
 	unsigned int psize, ssize;
 	unsigned long max_freq;
 	char *freq_method, *volt_method;
@@ -404,20 +404,6 @@ static int __init g5_neo2_cpufreq_init(struct device_node *cpus)
 	else
 		return -ENODEV;
 
-	/* Get first CPU node */
-	for (cpunode = NULL;
-	     (cpunode = of_get_next_child(cpus, cpunode)) != NULL;) {
-		const u32 *reg = of_get_property(cpunode, "reg", NULL);
-		if (reg == NULL || (*reg) != 0)
-			continue;
-		if (!strcmp(cpunode->type, "cpu"))
-			break;
-	}
-	if (cpunode == NULL) {
-		printk(KERN_ERR "cpufreq: Can't find any CPU 0 node\n");
-		return -ENODEV;
-	}
-
 	/* Check 970FX for now */
 	valp = of_get_property(cpunode, "cpu-version", NULL);
 	if (!valp) {
@@ -535,9 +521,9 @@ static int __init g5_neo2_cpufreq_init(struct device_node *cpus)
 #endif /* CONFIG_PMAC_SMU */
 
 
-static int __init g5_pm72_cpufreq_init(struct device_node *cpus)
+static int __init g5_pm72_cpufreq_init(struct device_node *cpunode)
 {
-	struct device_node *cpuid = NULL, *hwclock = NULL, *cpunode = NULL;
+	struct device_node *cpuid = NULL, *hwclock = NULL;
 	const u8 *eeprom = NULL;
 	const u32 *valp;
 	u64 max_freq, min_freq, ih, il;
@@ -546,17 +532,6 @@ static int __init g5_pm72_cpufreq_init(struct device_node *cpus)
 	DBG("cpufreq: Initializing for PowerMac7,2, PowerMac7,3 and"
 	    " RackMac3,1...\n");
 
-	/* Get first CPU node */
-	for (cpunode = NULL;
-	     (cpunode = of_get_next_child(cpus, cpunode)) != NULL;) {
-		if (!strcmp(cpunode->type, "cpu"))
-			break;
-	}
-	if (cpunode == NULL) {
-		printk(KERN_ERR "cpufreq: Can't find any CPU node\n");
-		return -ENODEV;
-	}
-
 	/* Lookup the cpuid eeprom node */
         cpuid = of_find_node_by_path("/u3@0,f8000000/i2c@f8001000/cpuid@a0");
 	if (cpuid != NULL)
@@ -716,25 +691,25 @@ static int __init g5_pm72_cpufreq_init(struct device_node *cpus)
 
 static int __init g5_cpufreq_init(void)
 {
-	struct device_node *cpus;
+	struct device_node *cpunode;
 	int rc = 0;
 
-	cpus = of_find_node_by_path("/cpus");
-	if (cpus == NULL) {
-		DBG("No /cpus node !\n");
+	/* Get first CPU node */
+	cpunode = of_cpu_device_node_get(0);
+	if (cpunode == NULL) {
+		pr_err("cpufreq: Can't find any CPU node\n");
 		return -ENODEV;
 	}
 
 	if (of_machine_is_compatible("PowerMac7,2") ||
 	    of_machine_is_compatible("PowerMac7,3") ||
 	    of_machine_is_compatible("RackMac3,1"))
-		rc = g5_pm72_cpufreq_init(cpus);
+		rc = g5_pm72_cpufreq_init(cpunode);
 #ifdef CONFIG_PMAC_SMU
 	else
-		rc = g5_neo2_cpufreq_init(cpus);
+		rc = g5_neo2_cpufreq_init(cpunode);
 #endif /* CONFIG_PMAC_SMU */
 
-	of_node_put(cpus);
 	return rc;
 }
 
diff --git a/drivers/cpufreq/spear-cpufreq.c b/drivers/cpufreq/spear-cpufreq.c
index c3efa7f2a908..19e364fa5955 100644
--- a/drivers/cpufreq/spear-cpufreq.c
+++ b/drivers/cpufreq/spear-cpufreq.c
@@ -18,7 +18,7 @@
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 
@@ -223,7 +223,7 @@ static int spear_cpufreq_driver_init(void)
 	const __be32 *val;
 	int cnt, i, ret;
 
-	np = of_find_node_by_path("/cpus/cpu@0");
+	np = of_cpu_device_node_get(0);
 	if (!np) {
 		pr_err("No cpu node found");
 		return -ENODEV;
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 5c5427918eb2..605afa9fbe5e 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -18,6 +18,7 @@
  *      2 of the License, or (at your option) any later version.
  */
 #include <linux/ctype.h>
+#include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/spinlock.h>
@@ -230,6 +231,100 @@ const void *of_get_property(const struct device_node *np, const char *name,
 }
 EXPORT_SYMBOL(of_get_property);
 
+/*
+ * arch_match_cpu_phys_id - Match the given logical CPU and physical id
+ *
+ * @cpu: logical cpu index of a core/thread
+ * @phys_id: physical identifier of a core/thread
+ *
+ * CPU logical to physical index mapping is architecture specific.
+ * However this __weak function provides a default match of physical
+ * id to logical cpu index. phys_id provided here is usually values read
+ * from the device tree which must match the hardware internal registers.
+ *
+ * Returns true if the physical identifier and the logical cpu index
+ * correspond to the same core/thread, false otherwise.
+ */
+bool __weak arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+	return (u32)phys_id == cpu;
+}
+
+/**
+ * Checks if the given "prop_name" property holds the physical id of the
+ * core/thread corresponding to the logical cpu 'cpu'. If 'thread' is not
+ * NULL, local thread number within the core is returned in it.
+ */
+static bool __of_find_n_match_cpu_property(struct device_node *cpun,
+			const char *prop_name, int cpu, unsigned int *thread)
+{
+	const __be32 *cell;
+	int ac, prop_len, tid;
+	u64 hwid;
+
+	ac = of_n_addr_cells(cpun);
+	cell = of_get_property(cpun, prop_name, &prop_len);
+	if (!cell)
+		return false;
+	prop_len /= sizeof(*cell);
+	for (tid = 0; tid < prop_len; tid++) {
+		hwid = of_read_number(cell, ac);
+		if (arch_match_cpu_phys_id(cpu, hwid)) {
+			if (thread)
+				*thread = tid;
+			return true;
+		}
+		cell += ac;
+	}
+	return false;
+}
+
+/**
+ * of_get_cpu_node - Get device node associated with the given logical CPU
+ *
+ * @cpu: CPU number(logical index) for which device node is required
+ * @thread: if not NULL, local thread number within the physical core is
+ *          returned
+ *
+ * The main purpose of this function is to retrieve the device node for the
+ * given logical CPU index. It should be used to initialize the of_node in
+ * cpu device. Once of_node in cpu device is populated, all the further
+ * references can use that instead.
+ *
+ * CPU logical to physical index mapping is architecture specific and is built
+ * before booting secondary cores. This function uses arch_match_cpu_phys_id
+ * which can be overridden by architecture specific implementation.
+ *
+ * Returns a node pointer for the logical cpu if found, else NULL.
+ */
+struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
+{
+	struct device_node *cpun, *cpus;
+
+	cpus = of_find_node_by_path("/cpus");
+	if (!cpus) {
+		pr_warn("Missing cpus node, bailing out\n");
+		return NULL;
+	}
+
+	for_each_child_of_node(cpus, cpun) {
+		if (of_node_cmp(cpun->type, "cpu"))
+			continue;
+		/* Check for non-standard "ibm,ppc-interrupt-server#s" property
+		 * for thread ids on PowerPC. If it doesn't exist fallback to
+		 * standard "reg" property.
+		 */
+		if (IS_ENABLED(CONFIG_PPC) &&
+			__of_find_n_match_cpu_property(cpun,
+				"ibm,ppc-interrupt-server#s", cpu, thread))
+			return cpun;
+		if (__of_find_n_match_cpu_property(cpun, "reg", cpu, thread))
+			return cpun;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(of_get_cpu_node);
+
 /** Checks if the given "compat" string matches one of the strings in
  * the device's "compatible" property
  */
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index ab0eade73039..3dfed2b9ae2e 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -28,6 +28,7 @@ struct cpu {
 extern int register_cpu(struct cpu *cpu, int num);
 extern struct device *get_cpu_device(unsigned cpu);
 extern bool cpu_is_hotpluggable(unsigned cpu);
+extern bool arch_match_cpu_phys_id(int cpu, u64 phys_id);
 
 extern int cpu_add_dev_attr(struct device_attribute *attr);
 extern void cpu_remove_dev_attr(struct device_attribute *attr);
diff --git a/include/linux/of.h b/include/linux/of.h
index 1fd08ca23106..c0bb2f188048 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -266,6 +266,7 @@ extern int of_device_is_available(const struct device_node *device);
 extern const void *of_get_property(const struct device_node *node,
 				const char *name,
 				int *lenp);
+extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
 #define for_each_property_of_node(dn, pp) \
 	for (pp = dn->properties; pp != NULL; pp = pp->next)
 
@@ -459,6 +460,12 @@ static inline const void *of_get_property(const struct device_node *node,
 	return NULL;
 }
 
+static inline struct device_node *of_get_cpu_node(int cpu,
+					unsigned int *thread)
+{
+	return NULL;
+}
+
 static inline int of_property_read_u64(const struct device_node *np,
 				       const char *propname, u64 *out_value)
 {
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 9d27475feec1..82ce324fdce7 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -1,6 +1,7 @@
 #ifndef _LINUX_OF_DEVICE_H
 #define _LINUX_OF_DEVICE_H
 
+#include <linux/cpu.h>
 #include <linux/platform_device.h>
 #include <linux/of_platform.h> /* temporary until merge */
 
@@ -43,6 +44,15 @@ static inline void of_device_node_put(struct device *dev)
 	of_node_put(dev->of_node);
 }
 
+static inline struct device_node *of_cpu_device_node_get(int cpu)
+{
+	struct device *cpu_dev;
+	cpu_dev = get_cpu_device(cpu);
+	if (!cpu_dev)
+		return NULL;
+	return of_node_get(cpu_dev->of_node);
+}
+
 #else /* CONFIG_OF */
 
 static inline int of_driver_match_device(struct device *dev,
@@ -67,6 +77,11 @@ static inline const struct of_device_id *of_match_device(
 {
 	return NULL;
 }
+
+static inline struct device_node *of_cpu_device_node_get(int cpu)
+{
+	return NULL;
+}
 #endif /* CONFIG_OF */
 
 #endif /* _LINUX_OF_DEVICE_H */