[PATCH 0/4] arm64: Topology

[PATCH 0/4] arm64: Topology

[Mark Brown]

Use the scheduler documented default for unknown CPUs rather than
assigning them to a cluster.

Mark Brown (4):
      arm64: topology: Implement basic CPU topology support
      arm64: topology: Add support for topology DT bindings
      arm64: topology: Tell the scheduler about the relative power of cores
      arm64: topology: Provide relative power numbers for cores

 arch/arm64/Kconfig                |  24 +++
 arch/arm64/include/asm/topology.h |  39 ++++
 arch/arm64/kernel/Makefile        |   1 +
 arch/arm64/kernel/smp.c           |  11 ++
 arch/arm64/kernel/topology.c      | 380 ++++++++++++++++++++++++++++++++++++++
 5 files changed, 455 insertions(+)

[PATCH 1/4] arm64: topology: Implement basic CPU topology support

[Mark Brown]

From: Mark Brown <broonie@linaro.org>

Add basic CPU topology support to arm64, based on the existing pre-v8
code and some work done by Mark Hambleton.  This patch does not
implement any topology discovery support since that should be based on
information from firmware, it merely implements the scaffolding for
integration of topology support in the architecture.

No locking of the topology data is done since it is only modified during
CPU bringup with external serialisation from the SMP code.

The goal is to separate the architecture hookup for providing topology
information from the DT parsing in order to ease review and avoid
blocking the architecture code (which will be built on by other work)
with the DT code review by providing something simple and basic.

A following patch will implement support for parsing the DT topology
bindings for ARM, similar patches will be needed for ACPI.

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 arch/arm64/Kconfig                | 24 ++++++++++
 arch/arm64/include/asm/topology.h | 39 ++++++++++++++++
 arch/arm64/kernel/Makefile        |  1 +
 arch/arm64/kernel/smp.c           | 11 +++++
 arch/arm64/kernel/topology.c      | 95 +++++++++++++++++++++++++++++++++++++++
 5 files changed, 170 insertions(+)
 create mode 100644 arch/arm64/include/asm/topology.h
 create mode 100644 arch/arm64/kernel/topology.c

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 27bbcfc..fea7b47 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -164,6 +164,30 @@ config SMP
 
 	  If you don't know what to do here, say N.
 
+config 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 SCHED_MC
+	bool "Multi-core scheduler support"
+	depends on CPU_TOPOLOGY
+	help
+	  Multi-core scheduler support improves the CPU scheduler's decision
+	  making when dealing with multi-core CPU chips at a cost of slightly
+	  increased overhead in some places. If unsure say N here.
+
+config SCHED_SMT
+	bool "SMT scheduler support"
+	depends on CPU_TOPOLOGY
+	help
+	  Improves the CPU scheduler's decision making when dealing with
+	  MultiThreading at a cost of slightly increased overhead in some
+	  places. If unsure say N here.
+
 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 0000000..c8a47e8
--- /dev/null
+++ b/arch/arm64/include/asm/topology.h
@@ -0,0 +1,39 @@
+#ifndef __ASM_TOPOLOGY_H
+#define __ASM_TOPOLOGY_H
+
+#ifdef CONFIG_CPU_TOPOLOGY
+
+#include <linux/cpumask.h>
+
+struct cpu_topology {
+	int thread_id;
+	int core_id;
+	int cluster_id;
+	cpumask_t thread_sibling;
+	cpumask_t core_sibling;
+};
+
+extern struct cpu_topology cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu)	(cpu_topology[cpu].cluster_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].cluster_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);
+
+#else
+
+static inline void init_cpu_topology(void) { }
+static inline void store_cpu_topology(unsigned int cpuid) { }
+
+#endif
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 2d4554b..252b621 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -20,6 +20,7 @@ arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o
 arm64-obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND)	+= sleep.o suspend.o
 arm64-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
+arm64-obj-$(CONFIG_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 7cfb92a..9660750 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -114,6 +114,11 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	return ret;
 }
 
+static void 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.
@@ -152,6 +157,8 @@ asmlinkage void secondary_start_kernel(void)
 	 */
 	notify_cpu_starting(cpu);
 
+	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
@@ -390,6 +397,10 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	int err;
 	unsigned int cpu, 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 0000000..0d94918
--- /dev/null
+++ b/arch/arm64/kernel/topology.c
@@ -0,0 +1,95 @@
+/*
+ * arch/arm64/kernel/topology.c
+ *
+ * Copyright (C) 2011,2013 Linaro Limited.
+ *
+ * Based on the arm32 version written by Vincent Guittot in turn 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/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/sched.h>
+
+#include <asm/topology.h>
+
+/*
+ * cpu topology table
+ */
+struct cpu_topology 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 cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
+	int cpu;
+
+	if (cpuid_topo->cluster_id == -1) {
+		/*
+		 * DT does not contain topology information for this cpu
+		 * reset it to default behaviour
+		 */
+		pr_warn("CPU%u: No topology information configured\n", cpuid);
+		cpuid_topo->core_id = 0;
+		cpumask_set_cpu(cpuid, &cpuid_topo->core_sibling);
+		cpumask_set_cpu(cpuid, &cpuid_topo->thread_sibling);
+		return;
+	}
+
+	/* update core and thread sibling masks */
+	for_each_possible_cpu(cpu) {
+		cpu_topo = &cpu_topology[cpu];
+
+		if (cpuid_topo->cluster_id != cpu_topo->cluster_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);
+	}
+}
+
+void store_cpu_topology(unsigned int cpuid)
+{
+	update_siblings_masks(cpuid);
+}
+
+/*
+ * 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 cpu_topology *cpu_topo = &cpu_topology[cpu];
+
+		cpu_topo->thread_id = -1;
+		cpu_topo->core_id =  -1;
+		cpu_topo->cluster_id = -1;
+		cpumask_clear(&cpu_topo->core_sibling);
+		cpumask_clear(&cpu_topo->thread_sibling);
+	}
+}
-- 
1.9.0

[PATCH 2/4] arm64: topology: Add support for topology DT bindings

[Mark Brown]

From: Mark Brown <broonie@linaro.org>

Add support for parsing the explicit topology bindings to discover the
topology of the system.

Since it is not currently clear how to map multi-level clusters for the
scheduler all leaf clusters are presented to the scheduler at the same
level. This should be enough to provide good support for current systems.

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 arch/arm64/kernel/topology.c | 142 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 142 insertions(+)

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 0d94918..13ef616 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -17,10 +17,150 @@
 #include <linux/percpu.h>
 #include <linux/node.h>
 #include <linux/nodemask.h>
+#include <linux/of.h>
 #include <linux/sched.h>
 
 #include <asm/topology.h>
 
+#ifdef CONFIG_OF
+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)
+		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 cluster_id,
+			      int core_id)
+{
+	char name[10];
+	bool leaf = true;
+	int i = 0;
+	int cpu;
+	struct device_node *t;
+
+	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 >= 0) {
+				cpu_topology[cpu].cluster_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;
+		}
+
+		cpu_topology[cpu].cluster_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, int depth)
+{
+	char name[10];
+	bool leaf = true;
+	bool has_cores = false;
+	struct device_node *c;
+	static int __initdata cluster_id;
+	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, depth + 1);
+			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 (depth == 0)
+				pr_err("%s: cpu-map children should be clusters\n",
+				       c->full_name);
+
+			if (leaf)
+				parse_core(c, cluster_id, 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++;
+}
+
+static void __init parse_dt_topology(void)
+{
+	struct device_node *cn;
+
+	cn = of_find_node_by_path("/cpus");
+	if (!cn) {
+		pr_err("No CPU information found in DT\n");
+		return;
+	}
+
+	/*
+	 * When topology is provided cpu-map is essentially a root
+	 * cluster with restricted subnodes.
+	 */
+	cn = of_find_node_by_name(cn, "cpu-map");
+	if (!cn)
+		return;
+	parse_cluster(cn, 0);
+}
+
+#else
+static inline void parse_dt_topology(void) {}
+#endif
+
 /*
  * cpu topology table
  */
@@ -92,4 +232,6 @@ void __init init_cpu_topology(void)
 		cpumask_clear(&cpu_topo->core_sibling);
 		cpumask_clear(&cpu_topo->thread_sibling);
 	}
+
+	parse_dt_topology();
 }
-- 
1.9.0

[PATCH 3/4] arm64: topology: Tell the scheduler about the relative power of cores

[Mark Brown]

From: Mark Brown <broonie@linaro.org>

In heterogeneous systems like big.LITTLE systems the scheduler will be
able to make better use of the available cores if we provide power numbers
to it indicating their relative performance. Do this by parsing the CPU
nodes in the DT.

This code currently has no effect as no information on the relative
performance of the cores is provided.

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 arch/arm64/kernel/topology.c | 141 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 141 insertions(+)

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 13ef616..8a9b325 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -19,9 +19,33 @@
 #include <linux/nodemask.h>
 #include <linux/of.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 
 #include <asm/topology.h>
 
+/*
+ * 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
 static int __init get_cpu_for_node(struct device_node *node)
 {
@@ -137,9 +161,49 @@ static void __init parse_cluster(struct device_node *cluster, int depth)
 		cluster_id++;
 }
 
+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@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[] = {
+	{ NULL, },
+};
+
+static unsigned long *__cpu_capacity;
+#define cpu_capacity(cpu)	__cpu_capacity[cpu]
+
+static unsigned long middle_capacity = 1;
+
+/*
+ * 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;
+	unsigned long min_capacity = ULONG_MAX;
+	unsigned long max_capacity = 0;
+	unsigned long capacity = 0;
+	int cpu;
+
+	__cpu_capacity = kcalloc(nr_cpu_ids, sizeof(*__cpu_capacity),
+				 GFP_NOWAIT);
 
 	cn = of_find_node_by_path("/cpus");
 	if (!cn) {
@@ -155,10 +219,84 @@ static void __init parse_dt_topology(void)
 	if (!cn)
 		return;
 	parse_cluster(cn, 0);
+
+	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;
+		}
+
+		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
 
 /*
@@ -212,6 +350,7 @@ static void update_siblings_masks(unsigned int cpuid)
 void store_cpu_topology(unsigned int cpuid)
 {
 	update_siblings_masks(cpuid);
+	update_cpu_power(cpuid);
 }
 
 /*
@@ -231,6 +370,8 @@ void __init init_cpu_topology(void)
 		cpu_topo->cluster_id = -1;
 		cpumask_clear(&cpu_topo->core_sibling);
 		cpumask_clear(&cpu_topo->thread_sibling);
+
+		set_power_scale(cpu, SCHED_POWER_SCALE);
 	}
 
 	parse_dt_topology();
-- 
1.9.0

[PATCH 4/4] arm64: topology: Provide relative power numbers for cores

[Mark Brown]

From: Mark Brown <broonie@linaro.org>

Provide performance numbers to the scheduler to help it fill the cores in
the system on big.LITTLE systems. With the current scheduler this may
perform poorly for applications that try to do OpenMP style work over all
cores but should help for more common workloads. The current 32 bit ARM
implementation provides a similar estimate so this helps ensure that
work to improve big.LITTLE systems on ARMv7 systems performs similarly
on ARMv8 systems.

The power numbers are the same as for ARMv7 since it seems that the
expected differential between the big and little cores is very similar on
both ARMv7 and ARMv8.  In both ARMv7 and ARMv8 cases the numbers were
based on the published DMIPS numbers.

These numbers are just an initial and basic approximation for use with
the current scheduler, it is likely that both experience with silicon
and ongoing work on improving the scheduler will lead to further tuning
or will tune automatically at runtime and so make the specific choice of
numbers here less critical.

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 arch/arm64/kernel/topology.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 8a9b325..22ce390 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -177,6 +177,8 @@ struct cpu_efficiency {
  * 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, },
 };
 
-- 
1.9.0