Merge remote-tracking branch 'lsk/v3.10/topic/arm64-topology' into linux-linaro-lsk

7 files changed, 483 insertions, 44 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index c2b4a765ff4..37cbbdd7248 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -144,6 +144,14 @@ config SMP
 
 	  If you don't know what to do here, say N.
 
+config ARM_CPU_TOPOLOGY
+	bool "Support CPU topology definition"
+	depends on SMP
+	default y
+	help
+	  Support CPU topology definition, based on configuration
+	  provided by the firmware.
+
 config NR_CPUS
 	int "Maximum number of CPUs (2-32)"
 	range 2 32
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
new file mode 100644
index 00000000000..611edefaeaf
--- /dev/null
+++ b/arch/arm64/include/asm/topology.h
@@ -0,0 +1,42 @@
+#ifndef _ASM_ARM_TOPOLOGY_H
+#define _ASM_ARM_TOPOLOGY_H
+
+#ifdef CONFIG_ARM_CPU_TOPOLOGY
+
+#include <linux/cpumask.h>
+
+struct cputopo_arm {
+	int thread_id;
+	int core_id;
+	int socket_id;
+	cpumask_t thread_sibling;
+	cpumask_t core_sibling;
+};
+
+extern struct cputopo_arm cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
+#define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
+#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+
+#define mc_capable()	(cpu_topology[0].socket_id != -1)
+#define smt_capable()	(cpu_topology[0].thread_id != -1)
+
+void init_cpu_topology(void);
+void store_cpu_topology(unsigned int cpuid);
+const struct cpumask *cpu_coregroup_mask(int cpu);
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask);
+
+#else
+
+static inline void init_cpu_topology(void) { }
+static inline void store_cpu_topology(unsigned int cpuid) { }
+static inline int cluster_to_logical_mask(unsigned int socket_id,
+	cpumask_t *cluster_mask) { return -EINVAL; }
+
+#endif
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 7b4b564961d..4e4c80d1150 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -18,6 +18,7 @@ arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o smp_psci.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o
 arm64-obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
+arm64-obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index a28d2859932..8d8a1f2af29 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -161,6 +161,11 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
 	return ret;
 }
 
+static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
+{
+	store_cpu_topology(cpuid);
+}
+
 /*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
@@ -209,6 +214,8 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	local_irq_enable();
 	local_fiq_enable();
 
+	smp_store_cpu_info(cpu);
+
 	/*
 	 * OK, now it's safe to let the boot CPU continue.  Wait for
 	 * the CPU migration code to notice that the CPU is online
@@ -389,6 +396,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	int cpu, err;
 	unsigned int ncores = num_possible_cpus();
 
+	init_cpu_topology();
+
+	smp_store_cpu_info(smp_processor_id());
+
+
 	/*
 	 * are we trying to boot more cores than exist?
 	 */
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
new file mode 100644
index 00000000000..83d6919d4e0
--- /dev/null
+++ b/arch/arm64/kernel/topology.c
@@ -0,0 +1,418 @@
+/*
+ * arch/arm64/kernel/topology.c
+ *
+ * Copyright (C) 2011,2013 Linaro Limited.
+ * Written by: Vincent Guittot
+ *
+ * based on arch/sh/kernel/topology.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/of.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/cputype.h>
+#include <asm/smp_plat.h>
+#include <asm/topology.h>
+
+/*
+ * cpu power scale management
+ */
+
+/*
+ * cpu power table
+ * This per cpu data structure describes the relative capacity of each core.
+ * On a heteregenous system, cores don't have the same computation capacity
+ * and we reflect that difference in the cpu_power field so the scheduler can
+ * take this difference into account during load balance. A per cpu structure
+ * is preferred because each CPU updates its own cpu_power field during the
+ * load balance except for idle cores. One idle core is selected to run the
+ * rebalance_domains for all idle cores and the cpu_power can be updated
+ * during this sequence.
+ */
+static DEFINE_PER_CPU(unsigned long, cpu_scale);
+
+unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	return per_cpu(cpu_scale, cpu);
+}
+
+static void set_power_scale(unsigned int cpu, unsigned long power)
+{
+	per_cpu(cpu_scale, cpu) = power;
+}
+
+#ifdef CONFIG_OF
+struct cpu_efficiency {
+	const char *compatible;
+	unsigned long efficiency;
+};
+
+/*
+ * Table of relative efficiency of each processors
+ * The efficiency value must fit in 20bit and the final
+ * cpu_scale value must be in the range
+ *   0 < cpu_scale < 3*SCHED_POWER_SCALE/2
+ * in order to return at most 1 when DIV_ROUND_CLOSEST
+ * is used to compute the capacity of a CPU.
+ * Processors that are not defined in the table,
+ * use the default SCHED_POWER_SCALE value for cpu_scale.
+ */
+static const struct cpu_efficiency table_efficiency[] = {
+	{ "arm,cortex-a57", 3891 },
+	{ "arm,cortex-a53", 2048 },
+	{ NULL, },
+};
+
+static unsigned long *__cpu_capacity;
+#define cpu_capacity(cpu)	__cpu_capacity[cpu]
+
+static unsigned long middle_capacity = 1;
+static int cluster_id;
+
+static int __init get_cpu_for_node(struct device_node *node)
+{
+	struct device_node *cpu_node;
+	int cpu;
+
+	cpu_node = of_parse_phandle(node, "cpu", 0);
+	if (!cpu_node) {
+		pr_crit("%s: Unable to parse CPU phandle\n", node->full_name);
+		return -1;
+	}
+
+	for_each_possible_cpu(cpu) {
+		if (of_get_cpu_node(cpu, NULL) == cpu_node)
+			return cpu;
+	}
+
+	pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name);
+	return -1;
+}
+
+static void __init parse_core(struct device_node *core, int core_id)
+{
+	char name[10];
+	bool leaf = true;
+	int i, cpu;
+	struct device_node *t;
+
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "thread%d", i);
+		t = of_get_child_by_name(core, name);
+		if (t) {
+			leaf = false;
+			cpu = get_cpu_for_node(t);
+			if (cpu) {
+				pr_info("CPU%d: socket %d core %d thread %d\n",
+					cpu, cluster_id, core_id, i);
+				cpu_topology[cpu].socket_id = cluster_id;
+				cpu_topology[cpu].core_id = core_id;
+				cpu_topology[cpu].thread_id = i;
+			} else {
+				pr_err("%s: Can't get CPU for thread\n",
+				       t->full_name);
+			}
+		}
+		i++;
+	} while (t);
+
+	cpu = get_cpu_for_node(core);
+	if (cpu >= 0) {
+		if (!leaf) {
+			pr_err("%s: Core has both threads and CPU\n",
+			       core->full_name);
+			return;
+		}
+
+		pr_info("CPU%d: socket %d core %d\n",
+			cpu, cluster_id, core_id);
+		cpu_topology[cpu].socket_id = cluster_id;
+		cpu_topology[cpu].core_id = core_id;
+	} else if (leaf) {
+		pr_err("%s: Can't get CPU for leaf core\n", core->full_name);
+	}
+}
+
+static void __init parse_cluster(struct device_node *cluster)
+{
+	char name[10];
+	bool leaf = true;
+	bool has_cores = false;
+	struct device_node *c;
+	int core_id = 0;
+	int i;
+
+	/*
+	 * First check for child clusters; we currently ignore any
+	 * information about the nesting of clusters and present the
+	 * scheduler with a flat list of them.
+	 */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "cluster%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			parse_cluster(c);
+			leaf = false;
+		}
+		i++;
+	} while (c);
+
+	/* Now check for cores */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "core%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			has_cores = true;
+
+			if (leaf)
+				parse_core(c, core_id++);
+			else
+				pr_err("%s: Non-leaf cluster with core %s\n",
+				       cluster->full_name, name);
+		}
+		i++;
+	} while (c);
+
+	if (leaf && !has_cores)
+		pr_warn("%s: empty cluster\n", cluster->full_name);
+
+	if (leaf)
+		cluster_id++;
+}
+
+/*
+ * Iterate all CPUs' descriptor in DT and compute the efficiency
+ * (as per table_efficiency). Also calculate a middle efficiency
+ * as close as possible to  (max{eff_i} - min{eff_i}) / 2
+ * This is later used to scale the cpu_power field such that an
+ * 'average' CPU is of middle power. Also see the comments near
+ * table_efficiency[] and update_cpu_power().
+ */
+static void __init parse_dt_topology(void)
+{
+	const struct cpu_efficiency *cpu_eff;
+	struct device_node *cn = NULL;
+	unsigned long min_capacity = (unsigned long)(-1);
+	unsigned long max_capacity = 0;
+	unsigned long capacity = 0;
+	int alloc_size, cpu;
+
+	alloc_size = nr_cpu_ids * sizeof(*__cpu_capacity);
+	__cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);
+
+	cn = of_find_node_by_path("/cpus");
+	if (!cn) {
+		pr_err("No CPU information found in DT\n");
+		return;
+	}
+
+	/*
+	 * If topology is provided as a cpu-map it is essentially a
+	 * root cluster.
+	 */
+	cn = of_find_node_by_name(cn, "cpu-map");
+	if (!cn)
+		return;
+	parse_cluster(cn);
+
+	for_each_possible_cpu(cpu) {
+		const u32 *rate;
+		int len;
+
+		/* 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;
+		}
+
+		/* check if the cpu is marked as "disabled", if so ignore */
+		if (!of_device_is_available(cn))
+			continue;
+
+		for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++)
+			if (of_device_is_compatible(cn, cpu_eff->compatible))
+				break;
+
+		if (cpu_eff->compatible == NULL) {
+			pr_warn("%s: Unknown CPU type\n", cn->full_name);
+			continue;
+		}
+
+		rate = of_get_property(cn, "clock-frequency", &len);
+		if (!rate || len != 4) {
+			pr_err("%s: Missing clock-frequency property\n",
+				cn->full_name);
+			continue;
+		}
+
+		capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency;
+
+		/* Save min capacity of the system */
+		if (capacity < min_capacity)
+			min_capacity = capacity;
+
+		/* Save max capacity of the system */
+		if (capacity > max_capacity)
+			max_capacity = capacity;
+
+		cpu_capacity(cpu) = capacity;
+	}
+
+	/* If min and max capacities are equal 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
+	 * of an 'average' CPU of the system will be as close as possible to
+	 * SCHED_POWER_SCALE, which is the default value, but with the
+	 * constraint explained near table_efficiency[].
+	 */
+	if (min_capacity == max_capacity)
+		return;
+	else if (4 * max_capacity < (3 * (max_capacity + min_capacity)))
+		middle_capacity = (min_capacity + max_capacity)
+				>> (SCHED_POWER_SHIFT+1);
+	else
+		middle_capacity = ((max_capacity / 3)
+				>> (SCHED_POWER_SHIFT-1)) + 1;
+
+}
+
+/*
+ * Look for a customed capacity of a CPU in the cpu_topo_data table during the
+ * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
+ * function returns directly for SMP system.
+ */
+static void update_cpu_power(unsigned int cpu)
+{
+	if (!cpu_capacity(cpu))
+		return;
+
+	set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity);
+
+	pr_info("CPU%u: update cpu_power %lu\n",
+		cpu, arch_scale_freq_power(NULL, cpu));
+}
+
+#else
+static inline void parse_dt_topology(void) {}
+static inline void update_cpu_power(unsigned int cpuid) {}
+#endif
+
+/*
+ * cpu topology table
+ */
+struct cputopo_arm cpu_topology[NR_CPUS];
+EXPORT_SYMBOL_GPL(cpu_topology);
+
+const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+	return &cpu_topology[cpu].core_sibling;
+}
+
+static void update_siblings_masks(unsigned int cpuid)
+{
+	struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
+	int cpu;
+
+	/* update core and thread sibling masks */
+	for_each_possible_cpu(cpu) {
+		cpu_topo = &cpu_topology[cpu];
+
+		if (cpuid_topo->socket_id != cpu_topo->socket_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+		if (cpu != cpuid)
+			cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+
+		if (cpuid_topo->core_id != cpu_topo->core_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
+		if (cpu != cpuid)
+			cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
+	}
+	smp_wmb();
+}
+
+void store_cpu_topology(unsigned int cpuid)
+{
+	struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid];
+
+	/* DT should have been parsed by the time we get here */
+	if (cpuid_topo->core_id == -1)
+		pr_info("CPU%u: No topology information configured\n", cpuid);
+	else
+		update_siblings_masks(cpuid);
+
+	update_cpu_power(cpuid);
+}
+
+
+/*
+ * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster
+ * @socket_id:		cluster HW identifier
+ * @cluster_mask:	the cpumask location to be initialized, modified by the
+ *			function only if return value == 0
+ *
+ * Return:
+ *
+ * 0 on success
+ * -EINVAL if cluster_mask is NULL or there is no record matching socket_id
+ */
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask)
+{
+	int cpu;
+
+	if (!cluster_mask)
+		return -EINVAL;
+
+	for_each_online_cpu(cpu) {
+		if (socket_id == topology_physical_package_id(cpu)) {
+			cpumask_copy(cluster_mask, topology_core_cpumask(cpu));
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+/*
+ * init_cpu_topology is called at boot when only one cpu is running
+ * which prevent simultaneous write access to cpu_topology array
+ */
+void __init init_cpu_topology(void)
+{
+	unsigned int cpu;
+
+	/* init core mask and power*/
+	for_each_possible_cpu(cpu) {
+		struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);
+
+		cpu_topo->thread_id = -1;
+		cpu_topo->core_id =  -1;
+		cpu_topo->socket_id = -1;
+		cpumask_clear(&cpu_topo->core_sibling);
+		cpumask_clear(&cpu_topo->thread_sibling);
+
+		set_power_scale(cpu, SCHED_POWER_SCALE);
+	}
+	smp_wmb();
+
+	parse_dt_topology();
+}
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index bc2da154f68..ac204e02292 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 8b6f7a99cce..00610a34fb9 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -827,49 +827,10 @@ 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;